twin/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-08-19 14:13:49 -07:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: twin:ignore-0.2.1
Branches Tags
twin:master twin:ag/rollup twin:ag/fix-ci twin:ag/index twin:ag/fix-multiline-replace-duplicate twin:ag/fix-cve-2021-3013 twin:ag/moarci twin:ag/ghactions twin:ag/snafu twin:ag/disable-bom-sniff twin:ag/partial-bstr-migration twin:ag/bstr-migration twin:ag/prepare-0.10.0 twin:ag/libripgrep-freeze-2 twin:ag/libripgrep-freeze-1 twin:ag/changelog
twin:globset-0.4.16 twin:14.1.1 twin:14.1.0 twin:ignore-0.4.22 twin:14.0.3 twin:14.0.2 twin:grep-0.3.1 twin:grep-printer-0.2.1 twin:grep-searcher-0.1.13 twin:14.0.1 twin:grep-0.3.0 twin:grep-printer-0.2.0 twin:14.0.0 twin:grep-0.2.13 twin:grep-searcher-0.1.12 twin:grep-pcre2-0.1.7 twin:grep-regex-0.1.12 twin:grep-matcher-0.1.7 twin:grep-cli-0.1.10 twin:ignore-0.4.21 twin:globset-0.4.14 twin:globset-0.4.13 twin:globset-0.4.12 twin:grep-cli-0.1.9 twin:globset-0.4.11 twin:grep-cli-0.1.8 twin:grep-0.2.12 twin:ignore-0.4.20 twin:grep-0.2.11 twin:grep-printer-0.1.7 twin:grep-searcher-0.1.11 twin:grep-pcre2-0.1.6 twin:grep-regex-0.1.11 twin:grep-matcher-0.1.6 twin:grep-cli-0.1.7 twin:ignore-0.4.19 twin:globset-0.4.10 twin:grep-0.2.10 twin:grep-searcher-0.1.10 twin:grep-0.2.9 twin:grep-searcher-0.1.9 twin:grep-regex-0.1.10 twin:globset-0.4.9 twin:globset-0.4.8 twin:13.0.0 twin:grep-0.2.8 twin:grep-printer-0.1.6 twin:grep-searcher-0.1.8 twin:grep-pcre2-0.1.5 twin:grep-regex-0.1.9 twin:grep-matcher-0.1.5 twin:grep-cli-0.1.6 twin:ignore-0.4.18 twin:globset-0.4.7 twin:ignore-0.4.17 twin:globset-0.4.6 twin:12.1.1 twin:grep-0.2.7 twin:grep-cli-0.1.5 twin:ignore-0.4.16 twin:12.1.0 twin:grep-0.2.6 twin:grep-printer-0.1.5 twin:grep-regex-0.1.8 twin:ignore-0.4.15 twin:12.0.1 twin:ignore-0.4.14 twin:ignore-0.4.13 twin:grep-regex-0.1.7 twin:12.0.0 twin:grep-searcher-0.1.7 twin:grep-regex-0.1.6 twin:grep-printer-0.1.4 twin:grep-pcre2-0.1.4 twin:grep-matcher-0.1.4 twin:ignore-0.4.12 twin:grep-0.2.5 twin:globset-0.4.5 twin:grep-cli-0.1.4 twin:ignore-0.4.11 twin:grep-regex-0.1.5 twin:grep-searcher-0.1.6 twin:ignore-0.4.10 twin:11.0.2 twin:grep-matcher-0.1.3 twin:grep-regex-0.1.4 twin:ignore-0.4.9 twin:ignore-0.4.8 twin:grep-searcher-0.1.5 twin:grep-printer-0.1.3 twin:grep-cli-0.1.3 twin:globset-0.4.4 twin:11.0.1 twin:11.0.0 twin:grep-0.2.4 twin:grep-cli-0.1.2 twin:grep-printer-0.1.2 twin:grep-searcher-0.1.4 twin:grep-regex-0.1.3 twin:grep-pcre2-0.1.3 twin:grep-matcher-0.1.2 twin:ignore-0.4.7 twin:globset-0.4.3 twin:grep-regex-0.1.2 twin:grep-searcher-0.1.3 twin:grep-searcher-0.1.2 twin:ignore-0.4.6 twin:ignore-0.4.5 twin:grep-0.2.3 twin:grep-pcre2-0.1.2 twin:0.10.0 twin:grep-searcher-0.1.1 twin:globset-0.4.2 twin:grep-pcre2-0.1.1 twin:grep-0.2.2 twin:grep-printer-0.1.1 twin:ignore-0.4.4 twin:grep-regex-0.1.1 twin:grep-matcher-0.1.1 twin:grep-cli-0.1.1 twin:grep-0.2.1 twin:grep-cli-0.1.0 twin:grep-0.2.0 twin:grep-search-0.1.0 twin:grep-matcher-0.1.0 twin:grep-printer-0.1.0 twin:grep-pcre2-0.1.0 twin:grep-regex-0.1.0 twin:0.9.0 twin:grep-0.1.9 twin:ignore-0.4.3 twin:globset-0.4.1 twin:ignore-0.4.2 twin:globset-0.4.0 twin:termcolor-0.3.6 twin:0.8.1 twin:termcolor-0.3.5 twin:ignore-0.4.1 twin:0.8.0 twin:ignore-0.4.0 twin:globset-0.3.0 twin:termcolor-0.3.4 twin:wincolor-0.1.6 twin:grep-0.1.8 twin:wincolor-0.1.5 twin:0.7.1 twin:ignore-0.3.1 twin:ignore-0.3.0 twin:grep-0.1.7 twin:globset-0.2.1 twin:0.7.0 twin:termcolor-0.3.3 twin:0.6.0 twin:ignore-0.2.2 twin:ignore-0.2.1 twin:wincolor-0.1.4 twin:0.5.2 twin:ignore-0.1.9 twin:0.5.1 twin:termcolor-0.3.2 twin:0.5.0 twin:grep-0.1.6 twin:ignore-0.1.8 twin:globset-0.1.4 twin:termcolor-0.3.1 twin:wincolor-0.1.3 twin:termcolor-0.3.0 twin:wincolor-0.1.2 twin:0.4.0 twin:0.3.2 twin:ignore-0.1.6 twin:0.3.1 twin:termcolor-0.1.1 twin:0.3.0 twin:termcolor-0.1.0 twin:wincolor-0.1.0 twin:0.2.9 twin:ignore-0.1.5 twin:0.2.8 twin:0.2.7 twin:ignore-0.1.4 twin:grep-0.1.4 twin:globset-0.1.2 twin:0.2.6 twin:ignore-0.1.3 twin:ignore-0.1.2 twin:0.2.5 twin:0.2.4 twin:ignore-0.1.1 twin:ignore-0.1.0 twin:globset-0.1.1 twin:0.2.3 twin:0.2.2 twin:globset-0.1.0 twin:0.2.1 twin:0.2.0 twin:0.1.18 twin:0.1.17 twin:0.1.16 twin:0.1.15 twin:0.1.14 twin:0.1.13 twin:0.1.12 twin:0.1.11 twin:0.1.10 twin:0.1.9 twin:0.1.8 twin:0.1.7 twin:0.1.6 twin:0.1.5 twin:0.1.4 twin:0.1.3 twin:0.1.2 twin:0.1.1 twin:0.1.0 twin:0.0.19 twin:0.0.18 twin:0.0.17 twin:0.0.16 twin:0.0.15 twin:0.0.14 twin:0.0.13 twin:0.0.12 twin:0.0.11 twin:0.0.10 twin:0.0.9 twin:0.0.8 twin:0.0.7 twin:0.0.6 twin:0.0.5 twin:0.0.4 twin:0.0.3 twin:0.0.2 twin:0.0.1
..
compare: twin:ag/disable-bom-sniff
Branches Tags
twin:ag/rollup twin:master twin:ag/fix-ci twin:ag/index twin:ag/fix-multiline-replace-duplicate twin:ag/fix-cve-2021-3013 twin:ag/moarci twin:ag/ghactions twin:ag/snafu twin:ag/disable-bom-sniff twin:ag/partial-bstr-migration twin:ag/bstr-migration twin:ag/prepare-0.10.0 twin:ag/libripgrep-freeze-2 twin:ag/libripgrep-freeze-1 twin:ag/changelog
twin:globset-0.4.16 twin:14.1.1 twin:14.1.0 twin:ignore-0.4.22 twin:14.0.3 twin:14.0.2 twin:grep-0.3.1 twin:grep-printer-0.2.1 twin:grep-searcher-0.1.13 twin:14.0.1 twin:grep-0.3.0 twin:grep-printer-0.2.0 twin:14.0.0 twin:grep-0.2.13 twin:grep-searcher-0.1.12 twin:grep-pcre2-0.1.7 twin:grep-regex-0.1.12 twin:grep-matcher-0.1.7 twin:grep-cli-0.1.10 twin:ignore-0.4.21 twin:globset-0.4.14 twin:globset-0.4.13 twin:globset-0.4.12 twin:grep-cli-0.1.9 twin:globset-0.4.11 twin:grep-cli-0.1.8 twin:grep-0.2.12 twin:ignore-0.4.20 twin:grep-0.2.11 twin:grep-printer-0.1.7 twin:grep-searcher-0.1.11 twin:grep-pcre2-0.1.6 twin:grep-regex-0.1.11 twin:grep-matcher-0.1.6 twin:grep-cli-0.1.7 twin:ignore-0.4.19 twin:globset-0.4.10 twin:grep-0.2.10 twin:grep-searcher-0.1.10 twin:grep-0.2.9 twin:grep-searcher-0.1.9 twin:grep-regex-0.1.10 twin:globset-0.4.9 twin:globset-0.4.8 twin:13.0.0 twin:grep-0.2.8 twin:grep-printer-0.1.6 twin:grep-searcher-0.1.8 twin:grep-pcre2-0.1.5 twin:grep-regex-0.1.9 twin:grep-matcher-0.1.5 twin:grep-cli-0.1.6 twin:ignore-0.4.18 twin:globset-0.4.7 twin:ignore-0.4.17 twin:globset-0.4.6 twin:12.1.1 twin:grep-0.2.7 twin:grep-cli-0.1.5 twin:ignore-0.4.16 twin:12.1.0 twin:grep-0.2.6 twin:grep-printer-0.1.5 twin:grep-regex-0.1.8 twin:ignore-0.4.15 twin:12.0.1 twin:ignore-0.4.14 twin:ignore-0.4.13 twin:grep-regex-0.1.7 twin:12.0.0 twin:grep-searcher-0.1.7 twin:grep-regex-0.1.6 twin:grep-printer-0.1.4 twin:grep-pcre2-0.1.4 twin:grep-matcher-0.1.4 twin:ignore-0.4.12 twin:grep-0.2.5 twin:globset-0.4.5 twin:grep-cli-0.1.4 twin:ignore-0.4.11 twin:grep-regex-0.1.5 twin:grep-searcher-0.1.6 twin:ignore-0.4.10 twin:11.0.2 twin:grep-matcher-0.1.3 twin:grep-regex-0.1.4 twin:ignore-0.4.9 twin:ignore-0.4.8 twin:grep-searcher-0.1.5 twin:grep-printer-0.1.3 twin:grep-cli-0.1.3 twin:globset-0.4.4 twin:11.0.1 twin:11.0.0 twin:grep-0.2.4 twin:grep-cli-0.1.2 twin:grep-printer-0.1.2 twin:grep-searcher-0.1.4 twin:grep-regex-0.1.3 twin:grep-pcre2-0.1.3 twin:grep-matcher-0.1.2 twin:ignore-0.4.7 twin:globset-0.4.3 twin:grep-regex-0.1.2 twin:grep-searcher-0.1.3 twin:grep-searcher-0.1.2 twin:ignore-0.4.6 twin:ignore-0.4.5 twin:grep-0.2.3 twin:grep-pcre2-0.1.2 twin:0.10.0 twin:grep-searcher-0.1.1 twin:globset-0.4.2 twin:grep-pcre2-0.1.1 twin:grep-0.2.2 twin:grep-printer-0.1.1 twin:ignore-0.4.4 twin:grep-regex-0.1.1 twin:grep-matcher-0.1.1 twin:grep-cli-0.1.1 twin:grep-0.2.1 twin:grep-cli-0.1.0 twin:grep-0.2.0 twin:grep-search-0.1.0 twin:grep-matcher-0.1.0 twin:grep-printer-0.1.0 twin:grep-pcre2-0.1.0 twin:grep-regex-0.1.0 twin:0.9.0 twin:grep-0.1.9 twin:ignore-0.4.3 twin:globset-0.4.1 twin:ignore-0.4.2 twin:globset-0.4.0 twin:termcolor-0.3.6 twin:0.8.1 twin:termcolor-0.3.5 twin:ignore-0.4.1 twin:0.8.0 twin:ignore-0.4.0 twin:globset-0.3.0 twin:termcolor-0.3.4 twin:wincolor-0.1.6 twin:grep-0.1.8 twin:wincolor-0.1.5 twin:0.7.1 twin:ignore-0.3.1 twin:ignore-0.3.0 twin:grep-0.1.7 twin:globset-0.2.1 twin:0.7.0 twin:termcolor-0.3.3 twin:0.6.0 twin:ignore-0.2.2 twin:ignore-0.2.1 twin:wincolor-0.1.4 twin:0.5.2 twin:ignore-0.1.9 twin:0.5.1 twin:termcolor-0.3.2 twin:0.5.0 twin:grep-0.1.6 twin:ignore-0.1.8 twin:globset-0.1.4 twin:termcolor-0.3.1 twin:wincolor-0.1.3 twin:termcolor-0.3.0 twin:wincolor-0.1.2 twin:0.4.0 twin:0.3.2 twin:ignore-0.1.6 twin:0.3.1 twin:termcolor-0.1.1 twin:0.3.0 twin:termcolor-0.1.0 twin:wincolor-0.1.0 twin:0.2.9 twin:ignore-0.1.5 twin:0.2.8 twin:0.2.7 twin:ignore-0.1.4 twin:grep-0.1.4 twin:globset-0.1.2 twin:0.2.6 twin:ignore-0.1.3 twin:ignore-0.1.2 twin:0.2.5 twin:0.2.4 twin:ignore-0.1.1 twin:ignore-0.1.0 twin:globset-0.1.1 twin:0.2.3 twin:0.2.2 twin:globset-0.1.0 twin:0.2.1 twin:0.2.0 twin:0.1.18 twin:0.1.17 twin:0.1.16 twin:0.1.15 twin:0.1.14 twin:0.1.13 twin:0.1.12 twin:0.1.11 twin:0.1.10 twin:0.1.9 twin:0.1.8 twin:0.1.7 twin:0.1.6 twin:0.1.5 twin:0.1.4 twin:0.1.3 twin:0.1.2 twin:0.1.1 twin:0.1.0 twin:0.0.19 twin:0.0.18 twin:0.0.17 twin:0.0.16 twin:0.0.15 twin:0.0.14 twin:0.0.13 twin:0.0.12 twin:0.0.11 twin:0.0.10 twin:0.0.9 twin:0.0.8 twin:0.0.7 twin:0.0.6 twin:0.0.5 twin:0.0.4 twin:0.0.3 twin:0.0.2 twin:0.0.1

534 Commits
ignore-0.2 ... ag/disable

Author SHA1 Message Date
Andrew Gallant
ebc80b01fa deps: update to clap 2.33 2019-04-06 09:37:33 -04:00
lesnyrumcajs
b00cd69a40 searcher: add option to disable BOM sniffing 
This commit adds a new encoding feature where the -E/--encoding flag
will now accept a value of 'none'. When given this value, all encoding
related machinery is disabled and ripgrep will search the raw bytes of
the file, including the BOM if it's present.

Closes #1207, Closes #1208
 2019-04-06 09:36:32 -04:00
Andrew Gallant
77439f99a4 deps: add bstr to Cargo.lock 2019-04-05 23:24:08 -04:00
Andrew Gallant
be7d6dd9ce regex: print out final regex in trace mode 
This is useful for debugging to see what regex is actually being run.
We put this as a trace since the regex can be quite gnarly. (It is not
pretty printed.)
 2019-04-05 23:24:08 -04:00
Andrew Gallant
9f15e3b671 regex: fix a perf bug when using -w flag 
When looking for an inner literal to speed up searches, if only a prefix
is found, then we generally give up doing inner literal optimizations since
the regex engine will generally handle it for us. Unfortunately, this
decision was being made *before* we wrap the regex in (^|\W)...($|\W) when
using the -w/--word-regexp flag, which would then defeat the literal
optimizations inside the regex engine.

We fix this with a bit of a hack that says, "if we're doing a word regexp,
then give me back any literal you find, even if it's a prefix."
 2019-04-05 23:24:08 -04:00
Andrew Gallant
254b8b67bb globset: small perf improvements 
This tweaks the path handling functions slightly to make them a hair
faster. In particular, `file_name` is called on every path that ripgrep
visits, and it was possible to remove a few branches without changing
behavior.
 2019-04-05 23:24:08 -04:00
Andrew Gallant
8a7f43b84d globset: use bstr 
This simplifies the various path related functions and pushed more platform
dependent code down into bstr. This likely also makes things a bit more
efficient on Windows, since we now only do a single UTF-8 check for each
file path.
 2019-04-05 23:24:08 -04:00
Andrew Gallant
d968a27ed5 cli: use bstr 
This uses bstr in the unescaping logic. This lets us remove some platform
specific code, and also lets us remove a hacked UTF-8 decoder on raw
bytes.
 2019-04-05 23:24:08 -04:00
Andrew Gallant
9b8f5cbaba config: switch to using bstrs 
This lets us implement correct Unicode trimming and also simplifies the
parsing logic a bit. This also removes the last platform specific bits of
code in ripgrep core.
 2019-04-05 23:24:08 -04:00
Andrew Gallant
c52da74ac3 printer: use bstr 
This starts the usage of bstr in the printer. We don't use it too much
yet, but it comes in handy for implementing PrinterPath and lets us push
down some platform specific code into bstr.
 2019-04-05 23:24:08 -04:00
Andrew Gallant
7dcbff9a9b searcher: partially migrate to bstr 
This commit causes grep-searcher to use byte strings internally for its
line buffer support. We manage to remove a use of `unsafe` by doing this
(by pushing it down into `bstr`).

We stop short of using byte strings everywhere else because we rely
heavily on the `impl ops::Index<[u8]> for grep_matcher::Match` impl,
which isn't available for byte strings. (It is premature to make bstr a
public dep of a core crate like grep-matcher, but maybe some day.)
 2019-04-05 23:24:08 -04:00
Andrew Gallant
bef1f0e770 ci: switch to xenial (#1234) 
Rust is having problems with trusty, in particular, see this bug I
filed: https://github.com/rust-lang/rust/issues/59411

This was purpotedly fixed in
https://github.com/rust-lang/rust/pull/59468,
but it appears the issue is still occurring.

This commit tries to update to Ubuntu 16.04 in the hope that it will fix
this problem.
 2019-04-03 19:52:34 -04:00
Andrew Gallant
cd9815cb37 deps: update to aho-corasick 0.7 
We do the simplest possible change to migrate to the new version.

Fixes #1228
 2019-04-03 13:51:26 -04:00
Andrew Gallant
3f22c3a658 deps: update everything 
This updates all dependencies to their latest versions.

We tolerate a duplicative aho-corasick for now, which we will fix in the
next commit.
 2019-04-03 13:07:26 -04:00
Andrew Gallant
0913972104 deps: bump encoding_rs_io 
This brings in a new API for disabling BOM sniffing.

This is part of the work toward completing
https://github.com/BurntSushi/ripgrep/issues/1207
 2019-03-03 16:36:34 -05:00
Andrew Gallant
f19b84fb23 regex: bump regex dep to fix match bug 
See

* 661bf53d5b
* edf45e6f5f

for details on the bug fix, which was in the regex engine.

Fixes #1203
 2019-02-27 17:42:14 -05:00
Andrew Gallant
59fc583aeb readme: include details about filtering 
Despite the fact that we mention this in several places, people are
still surprised by ripgrep's "smart" filtering.
 2019-02-27 08:01:23 -05:00
Andrew Gallant
1c7c4e6640 deps: update tempfile 2019-02-21 16:32:17 -05:00
Andrew Gallant
69c5e3938d deps: bump smallvec 
This gets rid of the unmaintained crates `unreachable` and `void`. Yay!
 2019-02-21 16:31:48 -05:00
Andrew Gallant
d9cf05ad50 deps: update to aho-corasick 0.6.10 
This brings in a fix for this bug:
https://github.com/BurntSushi/aho-corasick/issues/37

Fixes #1079
 2019-02-16 11:39:33 -05:00
Andrew Gallant
af8b6caebb deps: update various dependencies 2019-02-16 09:39:42 -05:00
Andrew Gallant
c84cfb6756 grep-regex-0.1.2 2019-02-16 09:30:06 -05:00
Andrew Gallant
895e26a000 ci: don't do releases on all tags 
This attempts to make Appveyor more conservative in what tags it thinks
are releases. I don't know for sure, but it looks like the previous
regex could match anywhere, so we anchor it.

Fixes #1195
 2019-02-10 12:51:56 -05:00
Andrew Gallant
8c95290ff6 deps: miscellaneous updates 2019-02-10 07:45:08 -05:00
Andrew Gallant
d6feeb7ff2 grep-searcher-0.1.3 2019-02-10 07:42:37 -05:00
Andrew Gallant
626ed00c19 searcher: revert big-endian patch 
This undoes the patch to stop using bytecount on big-endian
architectures. In particular, we bump our bytecount dependency to the
latest release, which has a fix.

This reverts commit a4868b8835.

Fixes #1144 (again), Closes #1194
 2019-02-10 07:40:32 -05:00
Andrew Gallant
332ad18401 tests: use const constructor for atomics 
We did this in 05411b2b for core ripgrep, but didn't carry it over to
tests.
 2019-02-09 16:27:25 -05:00
Andrew Gallant
fc3cf41247 grep-searcher-0.1.2 2019-02-09 16:13:07 -05:00
Andrew Gallant
a4868b8835 searcher: use naive line counting on big-endian 
This patches out bytecount's "fast" vectorized algorithm on big-endian
machines, where it has been observed to fail. Going forward, bytecount
should probably fix this on their end, but for now, we take a small
performance hit on big-endian machines.

Fixes #1144
 2019-02-09 16:13:07 -05:00
John Schmidt
f99b991117 ignore/types: add zig 
PR #1191
 2019-02-08 08:12:40 -05:00
Andrew Gallant
de0bc78982 deps: bump encoding_rs to 0.8.16 
This brings in an updated `encoding_rs` crate that uses `packed_simd`,
which compiles on the latest nightly. Compilation times do appear to be
impacted significantly though.

Fixes #1175 (again)
 2019-02-07 17:05:14 -05:00
Steffen Banhardt
147e96914c ignore/types: *.dtx and *.ins added for tex 
PR #1182
 2019-01-31 09:06:19 -05:00
Andrew Gallant
0abc40c23c readme: bump MSRV 
We bumped it a while back in the CI configuration, but didn't update the
README.
 2019-01-29 13:10:43 -05:00
Andrew Gallant
f768796e4f deps: update other deps 2019-01-29 13:08:56 -05:00
Andrew Gallant
da0c0c4705 deps: update to crossbeam-channel 0.3.8 
This drops dependencies on parking_lot and rand from ripgrep.

(rand is still used for tests.)
 2019-01-29 13:07:37 -05:00
Andrew Gallant
05411b2b32 deprecated: remove use of ATOMIC_BOOL_INIT 
Our MSRV is high enough that we can use const functions now.
 2019-01-29 13:05:16 -05:00
Andrew Gallant
cc93db3b18 cargo: include auto-generated message 
This is going to be annoying for a while if one switches between the
latest nightly compiler and older compilers. Sigh.
 2019-01-29 13:04:40 -05:00
Alex Macleod
049354b766 readme: remove EOL Fedora install instructions 
Fedora 27 and below are past their EOL, so it can now be said that it's
supported regularly on Fedora.

PR #1177
 2019-01-28 08:15:36 -05:00
Andrew Gallant
386dd2806d changelog: BUG #916 
This was fixed by bumping the MSRV above Rust 1.28.

Fixes #916
 2019-01-27 13:15:17 -05:00
Andrew Gallant
5fe9a954e6 changelog: BUG #1154 2019-01-27 13:05:50 -05:00
Andrew Gallant
f158a42a71 ignore: correctly detect hidden files on Windows 
This commit fixes a bug where ripgrep only treated files beginning with
a `.` as hidden. On Windows, we continue this tradition, but
additionally check whether a file has the special Windows "hidden"
attribute set. If so, we treat it as a hidden file.

In order to make this work without an additional stat call, we had to
rearrange some of the plumbing from the directory traverser.

Fixes #1154
 2019-01-27 12:11:52 -05:00
Andrew Gallant
5724391d39 doc: small updates to the FAQ and GUIDE 
Notably, ripgrep can do multiline search now. We also update the
supported compression format list and replace deprecated flags like
`--sort-files` with `--sort path`.
 2019-01-26 16:19:09 -05:00
Andrew Gallant
0df71240ff search: fix -F and -f interaction bug 
This fixes what appears to be a pretty egregious regression where the
`-F/--fixed-strings` flag wasn't be applied to patterns supplied via
the `-f/--file` flag. The same bug existed for the `-x/--line-regexp`
flag as well, which we fix here.

Fixes #1176
 2019-01-26 16:01:52 -05:00
Andrew Gallant
f3164f2615 exit: tweak exit status logic 
This changes how ripgrep emit exit status codes. In particular, any error
that occurs while searching will now cause ripgrep to emit a `2` exit
code, where as it previously would emit either a `0` or a `1` code based
on whether it matched or not. That is, ripgrep would only emit a `2` exit
code for a catastrophic error.

This tweak includes additional logic that GNU grep adheres to, which seems
like good sense. Namely, if -q/--quiet is given, and an error occurs and
a match occurs, then ripgrep will emit a `0` exit code.

Closes #1159
 2019-01-26 15:44:49 -05:00
Andrew Gallant
31d3e24130 args: prevent panicking in 'rg -h | rg' 
Previously, we relied on clap to handle printing either an error
message, or --help/--version output, in addition to setting the exit
status code. Unfortunately, for --help/--version output, clap was
panicking if the write failed, which can happen in fairly common
scenarios via a broken pipe error. e.g., `rg -h | head`.

We fix this by using clap's "safe" API and doing the printing ourselves.
We also set the exit code to `2` when an invalid command has been given.

Fixes #1125 and partially addresses #1159
 2019-01-26 14:39:40 -05:00
Andrew Gallant
bf842dbc7f doc: add note about inverted flags 
Fixes #1091
 2019-01-26 14:13:06 -05:00
Andrew Gallant
6d5dba85bd doc: clarify automatic encoding detection 
Fixes #1103
 2019-01-26 13:55:47 -05:00
Andrew Gallant
afb89bcdad fmt: shorten --ignore-file-case-insensitive description 2019-01-26 13:45:02 -05:00
Andrew Gallant
332dc56372 changelog: BUG #1095 2019-01-26 13:40:59 -05:00
Andrew Gallant
12a6ca45f9 config: add --no-ignore-dot flag 
This flag causes ripgrep to ignore `.ignore` files.

Closes #1138
 2019-01-26 13:40:12 -05:00
Andrew Gallant
9d703110cf regex: make CRLF hack more robust 
This commit improves the CRLF hack to be more robust. In particular, in
addition to rewriting `$` as `(?:\r??$)`, we now strip `\r` from the end
of a match if and only if the regex has an ending line anchor required for
a match. This doesn't quite make the hack 100% correct, but should fix most
use cases in practice. An example of a regex that will still be incorrect
is `foo|bar$`, since the analysis isn't quite sophisticated enough to
determine that a `\r` can be safely stripped from any match. Even if we
fix that, regexes like `foo\r|bar$` still won't be handled correctly. Alas,
more work on this front should really be focused on enabling this in the
regex engine itself.

The specific cause of this bug was that grep-searcher was sneakily
stripping CRLF from matching lines when it really shouldn't have. We remove
that code now, and instead rely on better match semantics provided at a
lower level.

Fixes #1095
 2019-01-26 12:34:28 -05:00
Andrew Gallant
e99b6bda0e deps: bump regex-syntax to 0.6.5 
This is necessary for the use of the new is_line_anchored_{start,end}
APIs.
 2019-01-26 12:20:02 -05:00
Andrew Gallant
276e2c9b9a searcher: always strip BOM 
This fixes a bug where a BOM prefix was included. While this was somewhat
intentional in order to have a faithful "UTF8 passthru" option, in
practice, this causes problems such as breaking patterns like `^` in a
really non-obvious way.

The actual fix was to add a new API to encoding_rs_io, which this commit
brings in.

Fixes #1163
 2019-01-25 17:18:57 -05:00
Andrew Gallant
9a9f54d44c readme: encoding_rs's SIMD support is broken 
Add a note about it to the README.

Also, remove mention of the avx-accel feature since it no longer exists.
(bytecount now uses runtime detection to enable SIMD support.)

Fixes #1175
 2019-01-24 07:00:53 -05:00
Andrew Gallant
47833b9ce7 deps: update removal of grep devdeps 2019-01-23 20:14:37 -05:00
Awad Mackie
44a9e37737 ignore/types: add method for retrieving file type definition 
Fixes #1116, Closes #1120
 2019-01-23 20:08:48 -05:00
Andrew Gallant
8fd05cacee changelog: BUG #1121 2019-01-23 20:06:01 -05:00
Rob Lourens
4691d11034 ripgrep: don't skip stdout in --files mode 
Specifically, this avoids triggering Windows antimalware when in --files mode.

See also #600.

Fixes #1121
 2019-01-23 20:04:44 -05:00
Andrew Gallant
519a6b68af grep: remove unused dependencies 
We remove these for now, but we'll eventually add them back once the
examples get more fleshed out.

Closes #1043
 2019-01-23 20:01:32 -05:00
Andrew Gallant
9c940b45f4 globset: permit ** to appear anywhere 
Previously, `man gitignore` specified that `**` was invalid unless it
was used in one of a few specific circumstances, i.e., `**`, `a/**`,
`**/b` or `a/**/b`. That is, `**` always had to be surrounded by either
a path separator or the beginning/end of the pattern.

It turns out that git itself has treated `**` outside the above contexts
as valid for quite a while, so there was an inconsistency between the
spec `man gitignore` and the implementation, and it wasn't clear which
was actually correct.

@okdana filed a bug against git[1] and got this fixed. The spec was wrong,
which has now been fixed [2] and updated[2].

This commit brings ripgrep in line with git and treats `**` outside of
the above contexts as two consecutive `*` patterns. We deprecate the
`InvalidRecursive` error since it is no longer used.

Fixes #373, Fixes #1098

[1] - https://public-inbox.org/git/C16A9F17-0375-42F9-90A9-A92C9F3D8BBA@dana.is
[2] - 627186d020
[3] - https://git-scm.com/docs/gitignore
 2019-01-23 19:59:39 -05:00
Andrew Gallant
0a167021c3 changelog: BUG #1174 2019-01-23 19:19:26 -05:00
Andrew Gallant
aeaa5fc1b1 globset: fix repeated use of ** 
This fixes a bug where repeated use of ** didn't behave as it should. In
particular, each use of `**` added a new requirement directory depth
requirement. For example, something like `**/**/b` would match
`foo/bar/b`, but it wouldn't match `foo/b` even though it should. In
particular, `**` semantics demand "infinite" depth, so repeated uses of
`**` should just coalesce as if only one was given.

We do this coalescing in the parser. It's a little tricky because we
treat `**/a`, `a/**` and `a/**/b` as distinct tokens with their own
regex conversions. We also test the crap out of it.

Fixes #1174
 2019-01-23 19:15:02 -05:00
Andrew Gallant
7048a06c31 changelog: BUG #1173 2019-01-23 18:14:16 -05:00
Andrew Gallant
23be3cf850 ignore: fix handling of ** 
When deciding whether to add the `**/` prefix or not, we should choose
not to add it if the pattern is simply a bare `**`. Previously, we were
only not adding it if it was `**/`, which is correct, but we also need
to do it for `**` since `**` can already match anywhere.

There's likely a more principled solution to this, but this works for
now.

Fixes #1173
 2019-01-23 18:12:35 -05:00
Andrew Gallant
b48bbf527d changelog: PR #1093 2019-01-23 17:56:18 -05:00
dana
8eabe47b57 ignore: always use literal_separator for gitignore patterns (#1093) 
PR #1093
 2019-01-23 17:54:28 -05:00
Michele Bologna
ff712bfd9d readme: add instructions for openSUSE 15.0 
PR #1088
 2019-01-22 21:46:11 -05:00
Mika Dede
a7f2d48234 printer: fix path handling in summarizer 
This commit fixes a bug where both of the following commands always
reported an error:

    rg --files-with-matches foo file
    rg --files-without-match foo file

In particular, the printer was erroneously respecting the `path` option
even the the summary kind was `PathWithMatch` or `PathWithoutMatch`. The
documented behavior is that those summary kinds always require a path,
and thus, the `path` option has no effect. We fix this by correcting the
case analysis.

This also fixes a bug where the exit code for `--files-without-match`
was not set correctly. We update the printer's `has_match` method to
report the correct value.

Fixes #1106, Closes #1130
 2019-01-22 21:37:23 -05:00
Andrew Gallant
57500ad013 changelog: brotli/zstd addition 2019-01-22 20:57:28 -05:00
dana
0b04553aff grep-cli: support Brotli/Zstd decompression 
Fixes #1099
 2019-01-22 20:56:16 -05:00
dana
1ae121122f ignore/types: add/update brotli, bzip2, gzip, xz, zstd 2019-01-22 20:56:16 -05:00
Andrew Gallant
688003e51c ripgrep: ban rustfmt 2019-01-22 20:07:26 -05:00
David Torosyan
718a00f6f2 ripgrep: add --ignore-file-case-insensitive 
The --ignore-file-case-insensitive flag causes all
.gitignore/.rgignore/.ignore files to have their globs matched without
regard for case. Because this introduces a potentially significant
performance regression, this is always disabled by default. Users that
need case insensitive matching can enable it on a case by case basis.

Closes #1164, Closes #1170
 2019-01-22 20:03:59 -05:00
Andrew Gallant
7cbc535d70 edition: fix build.rs 2019-01-19 10:46:57 -05:00
Andrew Gallant
7a6a40bae1 edition: move core ripgrep to Rust 2018 2019-01-19 10:44:30 -05:00
Andrew Gallant
1e9ee2cc85 deps: update memmap 2019-01-19 10:44:30 -05:00
Andrew Gallant
968491f8e9 deps: update to bytecount 0.5 
bytecount now uses runtime dispatch for enabling SIMD, which means we can
no longer need the avx-accel features. We remove it from ripgrep since the
next release will be a minor version bump, but leave them as no-ops for
the crates that previously used it.
 2019-01-19 10:44:30 -05:00
Andrew Gallant
63b0f31a22 deps: update various dependencies 
We also increase the MSRV to 1.32, the current stable release, which sets
the stage for migrating to Rust 2018.
 2019-01-19 10:44:30 -05:00
P M
7ecee299a5 ignore/types: add QML 
PR #1165
 2019-01-18 06:48:47 -05:00
David Håsäther
dd396ff34e doc: fix typo 
PR #1161
 2019-01-14 06:50:30 -05:00
Andrew Gallant
fb0a82f3c3 grep-printer: add macro docs, redux 2019-01-11 09:18:09 -05:00
Andrew Gallant
dbc8ca9cc1 grep-searcher: add docs for assert_eq_printed 
Looks like the deny(missing_docs) lint got a bit stronger.
 2019-01-11 09:03:00 -05:00
Marco Hinz
c3db8db93d doc: fix typo 2019-01-05 11:18:05 -05:00
Andrew Gallant
17ef4c40f3 ignore-0.4.6 2018-12-30 08:46:09 -05:00
Andrew Gallant
a9e0477ea8 ignore: permit use of deprecated trim_right 2018-12-30 08:44:59 -05:00
Andrew Gallant
b3c5773266 deps: bump ignore 2018-12-30 08:43:18 -05:00
Andrew Gallant
118b950085 ignore-0.4.5 2018-12-15 08:44:10 -05:00
Andrew Gallant
b45b2f58ea deps: update most other dependencies 
This commit is the result of doing:

  $ cargo update
  $ cargo update -p encoding_rs --precise 0.8.10

where the latter line prevents encoding_rs from updating to 0.8.11 (or
newer). In particular, the 0.8.11 release increased the minimum Rust
version to 1.29, where as ripgrep 0.10.x is still on 1.28. We stay on an
older version for now until ripgrep is ready to move to 0.11.x.
 2018-12-15 08:42:14 -05:00
Andrew Gallant
662a9bc73d deps: update to crossbeam-channel 0.3 
This also requires corresponding updates to both rand and rand_core. Doing
an update of rand without doing an update of rand_core results in
compilation errors because two distinct versions of rand_core are included
in the build, and the traits they expose are distinct and incompatible.

We also switch over to using tempfile instead of tempdir, which drops the
last remaining thing keeping rand 0.4 in the build.

Fixes #1141, Fixes #1142
 2018-12-15 08:40:04 -05:00
Andrew Gallant
401add0a99 deps: update regex and regex-syntax 
This brings in some new Unicode properties, such as \p{Emoji}.

It is now also technically possible construct a regex that recognizes
grapheme clusters.
 2018-12-09 16:33:37 -05:00
Simon Morgan
f81b72721b ignore/types: add ASP 
PR #1134
 2018-12-07 16:19:33 -05:00
Antony Lee
1d4fccaadc ignore/types: add postscript 
Although postscript/encapsulated postscript is usually thought of as a
binary format, it's actually mostly ASCII, so ripgrep will not ignore
these files.

The situation is basically the same as for pdf, which is also already
present in the list of known filetypes.

PR #1118
 2018-11-23 09:46:11 -05:00
Matteo Bertini
09e464e674 ignore/types: add more Cython file types 
From the [Cython file types](https://cython.readthedocs.io/en/latest/src/userguide/language_basics.html?highlight=pxi#cython-file-types) paragraph on the official docs:

> There are three file types in Cython:
>    The implementation files, carrying a .py or .pyx suffix.
>    The definition files, carrying a .pxd suffix.
>    The include files, carrying a .pxi suffix.

PR #1113
 2018-11-19 07:37:00 -05:00
Jon Parise
31adff6f3c ignore/types: add Apache Thrift 
PR #1102
 2018-11-07 07:42:13 -05:00
Andrew Gallant
b41e596327 doc: escape braces in AsciiDoc 
This commit fixes a bug where AsciiDoc would drop any line containing a
'{foo}' because it interpreted it as an undefined attribute reference:

> Simple attribute references take the form {<name>}. If the attribute name
> is defined its text value is substituted otherwise the line containing the
> reference is dropped from the output.

See: https://www.methods.co.nz/asciidoc/chunked/ch30.html

We fix this by simply replacing all occurrences of '{' and '}' with
their escaped forms: '&#123;' and '&#125;'.

Fixes #1101
 2018-11-06 06:57:16 -05:00
Andrew Gallant
fb62266620 deps: update encoding_rs 
This commit bumps the version of encoding_rs to use the latest release.
This appears to fix a panic in UTF-16 decoding.

Fixes #1089
 2018-10-22 06:50:35 -04:00
Dave Lee
acf226c39d ignore/types: add BUILD.bazel to bazel file type 
PR #1074
 2018-10-02 18:00:04 -04:00
Mathieu Bridon
8299625e48 ignore/types: add buildstream 
BuildStream is a Free Software tool for building/integrating software stacks.: https://buildstream.gitlab.io/buildstream/

It uses recipes written in YAML, in files with the `.bst` extension.

PR #1071
 2018-09-28 08:32:24 -04:00
Andrew Gallant
db256c87eb ripgrep: suggest -U/--multiline 
When a "\n literal is not allowed" error is reported, ripgrep will now
suggest the use of the -U/--multiline flag, which enables matching
newlines.

Fixes #1055
 2018-09-25 16:56:04 -04:00
Andrew Gallant
ba533f390e grep-searcher: update to encoding_rs_io 0.1.3 
This update includes a work-around for a presumed bug in encoding_rs
that causes a panic:
https://github.com/hsivonen/encoding_rs/issues/34

Specifically, to reproduce this in ripgrep, one can run the following:

    $ curl -LO https://cache.ruby-lang.org/pub/ruby/2.5/ruby-2.5.1.tar.gz
    $ tar xf ruby-2.5.1.tar.gz
    $ rg ZZZZZ ruby-2.5.1/test/rexml/data/t63-2.svg
    thread 'main' panicked at 'index out of bounds: the len is 1 but the index is 1'

Fixes #1052
 2018-09-25 16:56:04 -04:00
Andrew Gallant
ba503eb677 grep-regex: fix inner literal detection 
It seems the inner literal detector fails spectacularly in cases of
concatenations that involve groups. The issue here is that if the prefix
of a group inside a concatenation can match the empty string, then any
literals generated to that point in the concatenation need to be cut
such that they are never extended. The detector isn't really built to
handle this case, so we just act conservative cut literals whenever we
see a sub-group. This may make some regexes slower, but the inner
literal detector already misses plenty of cases.

Literal detection (including in the regex engine) is a key component
that needs to be completely rethought at some point.

Fixes #1064
 2018-09-25 16:56:04 -04:00
Andrew Gallant
f72c2dfd90 readme: touch up README 
Make the wording consistent.
 2018-09-14 11:33:56 -04:00
Sylvestre Ledru
c0aa58b4f7 Ripgrep is also available in Ubuntu (from Cosmic) 2018-09-14 08:41:05 +02:00
ykgmfq
184ee4c328 deb: add section info 
Put it in the same section as
https://packages.debian.org/stretch/grep

PR #1051
 2018-09-13 08:17:24 -04:00
Gabe Berke-Williams
e82fbf2c46 doc: fix typo 
"cretion" -> "creation"

PR #1045
 2018-09-10 06:49:48 -04:00
Andrew Gallant
eb18da0450 pcre2: use jit_if_available 
This will allow PCRE2 to fall back to non-JIT matching when running on
platforms without JIT support.

ref https://github.com/BurntSushi/rust-pcre2/issues/3
 2018-09-08 17:12:14 -04:00
Andrew Gallant
0f7494216f readme: update dpkg version 2018-09-08 10:46:40 -04:00
Andrew Chin
442a278635 readme: fancy regexes are not supported by default 
PR #1042
 2018-09-07 17:43:24 -04:00
Andrew Gallant
7ebed3ace6 pkg: update brew tap to 0.10.0 2018-09-07 14:43:59 -04:00
Andrew Gallant
8a7db1a918 ci: tweak deployment conditions 2018-09-07 14:07:52 -04:00
Andrew Gallant
ce80d794c0 changelog: add release date 2018-09-07 14:00:23 -04:00
Andrew Gallant
c5d467a2ab ci: always force PCRE2 static builds for releases 2018-09-07 14:00:23 -04:00
Andrew Gallant
a62cd553c2 ci: clean up appveyor 
Remove some outdated comments and unused config. Also, make the regex for
matching tags a bit more specific.
 2018-09-07 14:00:22 -04:00
Andrew Gallant
ce5188335b ci: remove 'branch' condition for deployment 
Travis docs[1] say this is ignore when 'tags' is used.

[1] - https://docs.travis-ci.com/user/deployment/#conditional-releases-with-on
 2018-09-07 14:00:22 -04:00
Andrew Gallant
b7a456ae83 deb: add completions 
This commit adds Bash, zsh and fish completions to the Debian binary
package.

Fixes #1032
 2018-09-07 14:00:22 -04:00
Andrew Gallant
d14f0b37d6 deps: update versions for all crates 
I don't think every change here is needed, but this ensures we're using
the latest version of every direct dependency.
 2018-09-07 14:00:22 -04:00
Andrew Gallant
3ddc3c040f deps: minor updates 2018-09-07 13:03:01 -04:00
Andrew Gallant
eeaa42ecaf scripts: add copy-examples 
This is a preliminary script to copy example code from a Markdown file
into a crate's example directory.

This is intended to be used for the upcoming libripgrep guide, but we
don't commit any examples yet.
 2018-09-07 12:27:48 -04:00
Andrew Gallant
3797a2a5cb simplegrep: touch up 2018-09-07 12:24:50 -04:00
Andrew Gallant
0e2f8f7b47 grep: add clap and regex dev dependencies to grep 
These are (or will be) used in grep's examples.
 2018-09-07 12:06:05 -04:00
Andrew Gallant
3dd4b77dfb grep-searcher: add Box<...> impl for Sink 
We initially did not have this impl because the first revision of the Sink
trait was much more complicated. In particular, each method was
parameterized over a Matcher. But not every Sink impl actually needs a
Matcher, and it is just as easy to borrow a Matcher explicitly, so the
added parameterization wasn't holding its own.

This does permit Sink implementations to be used as trait objects. One
key use case here is to reduce compile times, since there is quite a bit
of code inside grep-searcher that is parameterized on Sink. Unfortunately,
that code is *also* parameterized on Matcher, and the various printers in
grep-printer are also parameterized on Matcher, which means Sink trait
objects are necessary but no sufficient for a major reduction in compile
times. Unfortunately, the path to making Matcher object safe isn't quite
clear. Extension traits maybe? There's also stuff in the Serde ecosystem
that might help, but the type shenanigans can get pretty gnarly.
 2018-09-07 12:06:05 -04:00
Andrew Gallant
3b5cdea862 doc: minor touchups to API docs 2018-09-07 12:06:05 -04:00
Andrew Gallant
54b3e9eb10 grep-printer: delete unused code 2018-09-07 12:06:05 -04:00
Andrew Gallant
56e8864426 grep-matcher: add LineTerminator::is_suffix 
This centralizes the logic for checking whether a line has a line
terminator or not.
 2018-09-07 12:06:04 -04:00
Andrew Gallant
b8f619d16e readme: a few clarifications 2018-09-07 12:06:04 -04:00
Andrew Gallant
83dff33326 deps: update various deps 2018-09-04 23:29:22 -04:00
Andrew Gallant
003c3695f4 deps: update grep version 2018-09-04 23:29:05 -04:00
Andrew Gallant
10777c150d grep-0.2.1 2018-09-04 23:25:39 -04:00
Andrew Gallant
827179250b changelog: assign feature id 2018-09-04 23:24:22 -04:00
Andrew Gallant
fd22cd520b windows: fix unused warnings on Windows 2018-09-04 23:18:55 -04:00
Andrew Gallant
241bc8f8fc ripgrep: add --pre-glob flag 
The --pre-glob flag is like the --glob flag, except it applies to filtering
files through the preprocessor instead of for search. This makes it
possible to apply the preprocessor to only a small subset of files, which
can greatly reduce the process overhead of using a preprocessor when
searching large directories.
 2018-09-04 23:18:55 -04:00
Andrew Gallant
b6e30124e0 ripgrep: add --line-buffered and --block-buffered 
These flags provide granular control over ripgrep's buffering strategy.
The --line-buffered flag can be genuinely useful in certain types of shell
pipelines. The --block-buffered flag has a murkier use case, but we add it
for completeness.
 2018-09-04 23:18:55 -04:00
Andrew Gallant
4846d63539 grep-cli: introduce new grep-cli crate 
This commit moves a lot of "utility" code from ripgrep core into
grep-cli. Any one of these things might not be worth creating a new
crate, but combining everything together results in a fair number of a
convenience routines that make up a decent sized crate.

There is potentially more we could move into the crate, but much of what
remains in ripgrep core is almost entirely dealing with the number of
flags we support.

In the course of doing moving things to the grep-cli crate, we clean up
a lot of gunk and improve failure modes in a number of cases. In
particular, we've fixed a bug where other processes could deadlock if
they write too much to stderr.

Fixes #990
 2018-09-04 23:18:55 -04:00
helloer
13c47530a6 ignore/types: add pascal type 
PR #1036
 2018-09-03 07:25:07 -04:00
Jakub Wilk
328f4369e6 doc: fix typos 2018-08-31 11:59:28 -04:00
Andrew Gallant
04518e32e7 deps: update other crates 2018-08-30 23:03:07 -04:00
Andrew Gallant
f2eaf5b977 deps: update termcolor for perf tweaks 2018-08-30 22:57:01 -04:00
Andrew Gallant
3edeeca6e9 changelog: fix typo 2018-08-29 18:46:34 -04:00
Andrew Gallant
c41b353009 changelog: update 
This brings the changelog up to date with HEAD and rewords a few things.
 2018-08-29 18:25:08 -04:00
Aaron Power
d18839f3dc ignore: add into_path for DirEntry (#1031) 
This commit adds ignore::DirEntry::into_path to match
the corresponding method on walkdir::DirEntry.
 2018-08-28 18:27:34 -04:00
Andrew Gallant
8f978a3cf7 doc: clarify and fix typo 
Clarify that --byte-offset may be wrong if the source isn't being read
directly.

Also tweak the README a bit. And remove a damned Oxford comma.
 2018-08-27 21:21:37 -04:00
Andrew Gallant
87b745454d ripgrep: use 'ignore' for skipping stdout 
This removes ripgrep-specific code for filtering files that correspond to
stdout and instead uses the 'ignore' crate's functionality for doing the
same.
 2018-08-27 21:18:53 -04:00
Andrew Gallant
e5bb750995 ignore: add 'stdout' skipping to the walker 
This commit adds a new 'skip_stdout' option to the directory walker. When
enabled, it will skip yielding any directory entries that are believed to
correspond to stdout for the current process. This is useful for filtering
out 'results' in a command like 'grep -r foo > results' in order to avoid
an unbounded feedback mechanism.
 2018-08-27 21:18:53 -04:00
dana
d599f0b3c7 complete: don't complete bare pattern after -f 2018-08-27 07:56:40 -04:00
Andrew Gallant
40e310a9f9 ripgrep: add --sort and --sortr flags 
These flags each accept one of five choices: none, path, modified,
accessed or created. The value indicates how the results are sorted.
For --sort, results are sorted in ascending order where as for --sortr,
results are sorted in descending order.

Closes #404
 2018-08-26 18:42:25 -04:00
Andrew Gallant
510f15f4da ignore: add sort_by_file_path builder method 
This permits callers to sort entries by their full file path, which makes
it easy to query for various file statistics.

It would have been better to provide a comparator on DirEntry itself,
similar to how walkdir does it, but this seems to require quite a bit of
work to make the types work out, assuming we want to continue to use
walkdir's sorting support (we do).
 2018-08-26 18:42:25 -04:00
Andrew Gallant
f9ce7a84a8 ignore: add 'same_file_system' option 
This commit adds a 'same_file_system' option to the walk builder. For
single threaded walking, it defers to the walkdir crate, which has the
same option. The bulk of this commit implements this flag for the parallel
walker. We add one very feeble test for this.

The parallel walker is now officially a complete mess.

Closes #321
 2018-08-26 18:42:25 -04:00
Andrew Gallant
1b6089674e deps: more updates 2018-08-26 18:42:25 -04:00
Andrew Gallant
05a0389555 ripgrep: use winapi-util for stdin_is_readable 2018-08-25 00:30:15 -04:00
Andrew Gallant
16353bad6e deps: update various deps 
This includes a new crate, winapi-util, that is now used in wincolor,
walkdir and same-file.
 2018-08-25 00:19:40 -04:00
Tim Kilbourn
fe442de091 changelog: fix typo 
Fuchsia is a pain to spell.

PR #1026
 2018-08-23 13:17:27 -04:00
Andrew Gallant
1bb8b7170f doc: clarify use of SIMD features 
You need a nightly compiler.

Ref #188
 2018-08-23 09:56:37 -04:00
Andrew Gallant
55ed698a98 deps: update walkdir minimum version 
We'll want to be using the new `same_file_system` option soon.
 2018-08-23 09:54:45 -04:00
Andrew Gallant
f1e025873f deps: update dependencies 
This includes an update to walkdir 2.2.2, which includes a
`same_file_system` option.
 2018-08-22 20:50:24 -04:00
Andrew Gallant
033ad2b8e4 deps: update clap 
Update clap to the latest version.

Also, drop the ansi_term dependency by disabling color output in clap's
error messages.
 2018-08-21 23:10:34 -04:00
Andrew Gallant
098a8ee843 deps: various patch upgrades 2018-08-21 23:05:52 -04:00
Andrew Gallant
2f3dbf5fee ignore: fix false positive in path_is_symlink 
This commit fixes a bug where the first path always reported itself as
as symlink via `path_is_symlink`.

Part of this fix includes updating walkdir to 2.2.1, which also includes
a corresponding bug fix.

Fixes #984
 2018-08-21 23:05:52 -04:00
Andrew Gallant
5c80e4adb6 release: better support for binary Debian package 
This commit beefs up the package metadata used by the 'cargo deb' tool to
produce a binary dpkg. In particular, we now include ripgrep's man page.

This commit includes a new script, 'ci/build_deb.sh', which will handle
the build process for a dpkg, which has become a bit more nuanced than
just running 'cargo deb'. We don't (yet) run this script in CI.

Fixes #842
 2018-08-21 23:05:52 -04:00
Andrew Gallant
fcd1853031 doc: update ripgrep's description 
This now mentions PCRE2 support.
 2018-08-21 23:05:52 -04:00
Andrew Gallant
74a89be641 grep-printer: fix bug in printing truncated lines 
When emitting color, the printer wasn't checking whether the line
exceeded the maximum allowed length.
 2018-08-21 23:05:52 -04:00
Andrew Gallant
5b1ce8bdc2 tests: touch up tests on Windows 
This fixes warnings and adds an additional invalid UTF-8 test that will
run on Windows.
 2018-08-21 23:05:52 -04:00
Andrew Gallant
1529ce3341 ripgrep: remove workaround for std bug 
This commit undoes a work-around for a bug in Rust's standard library
that prevented correct file type detection on Windows in OneDrive
directories. We remove the work-around because we are moving to a
latest-stable Rust version policy, which has included this fix for a while
now.

ref #705, https://github.com/rust-lang/rust/issues/46484
 2018-08-21 23:05:52 -04:00
Andrew Gallant
95a4f15916 ignore: clarify docs for DirEntry::error 
Fixes #953
 2018-08-21 23:05:52 -04:00
Andrew Gallant
0eef05142a ripgrep: move minimum version to Rust stable 
This also updates some code to make use of our more liberal versioning
requirement, including the use of crossbeam-channel instead of the MsQueue
from the older an unmaintained crossbeam 0.3. This does regrettably add
a sizable number of dependencies, however, compile times seem mostly
unaffected.

Closes #1019
 2018-08-21 23:05:52 -04:00
Andrew Gallant
edd6eb4e06 ripgrep: make --no-pcre2-unicode the canonical flag 
Previously, we used --pcre2-unicode as the canonical flag despite the
fact that it is enabled by default, which is inconsistent with how we
handle other similar flags.

The reason why --pcre2-unicode was made the canonical flag was to make
it easier to discover since it would be sorted near the --pcre2 flag. To
solve that problem, we simply start a convention that lists related
flags in the docs.

Fixes #1022
 2018-08-21 23:05:52 -04:00
Andrew Gallant
7ac9782970 doc: fix typo 2018-08-20 18:00:14 -04:00
Andrew Gallant
180054d7dc doc: caveats 2018-08-20 17:58:29 -04:00
Andrew Gallant
7eaaa04c69 ripgrep: small cleanups 2018-08-20 17:34:45 -04:00
Andrew Gallant
87a627631c doc: add section on PCRE2 performance 2018-08-20 17:34:45 -04:00
Andrew Gallant
9df60e164e deps: update other dependencies to latest 2018-08-20 17:34:45 -04:00
Andrew Gallant
afa06c518a deps: update libripgrep crate versions 
This prepares them for an initial 0.1.0 release.
 2018-08-20 17:34:45 -04:00
Andy Freeland
e46aeb34f8 ignore/types: add .mako and .mao for Mako templates 
I've personally never seen `.mao`, but GitHub includes it in Linguist: 
4f11062304/lib/linguist/languages.yml (L2702-L2709)
 2018-08-20 15:26:49 -04:00
dana
d8f187e990 complete: add completion reference guide 2018-08-20 11:53:19 -04:00
dana
7d93d2ab05 ripgrep: add --no-multiline-dotall 2018-08-20 07:50:00 -04:00
dana
9ca2d68e94 ripgrep: fix typos in option descriptions 2018-08-20 07:50:00 -04:00
dana
60b0e3ff80 complete: update wording, exclusion, &c. 2018-08-20 07:50:00 -04:00
dana
3a1c081c13 test_complete: match certain long options in description bodies 2018-08-20 07:50:00 -04:00
Andrew Gallant
d5c0b03030 changelog: massive update for libripgrep 
This commit updates the CHANGELOG to reflect all the work done to make
libripgrep a reality.

* Closes #162 (libripgrep)
* Closes #176 (multiline search)
* Closes #188 (opt-in PCRE2 support)
* Closes #244 (JSON output)
* Closes #416 (Windows CRLF support)
* Closes #917 (trim prefix whitespace)
* Closes #993 (add --null-data flag)
* Closes #997 (--passthru works with --replace)

* Fixes #2 (memory maps and context handling work)
* Fixes #200 (ripgrep stops when pipe is closed)
* Fixes #389 (more intuitive `-w/--word-regexp`)
* Fixes #643 (detection of stdin on Windows is better)
* Fixes #441, Fixes #690, Fixes #980 (empty matching lines are weird)
* Fixes #764 (coalesce color escapes)
* Fixes #922 (memory maps failing is no big deal)
* Fixes #937 (color escapes no longer used for empty matches)
* Fixes #940 (--passthru does not impact exit status)
* Fixes #1013 (show runtime CPU features in --version output)
 2018-08-20 07:10:19 -04:00
Andrew Gallant
eb184d7711 tests: re-tool integration tests 
This basically rewrites every integration test. We reduce the amount of
magic involved here in terms of which arguments are being passed to
ripgrep processes. To make up for the boiler plate saved by the magic,
we make the Dir (formerly WorkDir) type a bit nicer to use, along with a
new TestCommand that wraps a std::process::Command. In exchange, we get
tests that are easier to read and write.

We also run every test with the `--pcre2` flag to make sure that works,
when PCRE2 is available.
 2018-08-20 07:10:19 -04:00
Andrew Gallant
bb110c1ebe ripgrep: migrate to libripgrep 
This commit does the work to delete the old `grep` crate and effectively
rewrite most of ripgrep core to use the new libripgrep crates. The new
`grep` crate is now a facade that collects the various crates that make
up libripgrep.

The most complex part of ripgrep core is now arguably the translation
between command line parameters and the library options, which is
ultimately where we want to be.
 2018-08-20 07:10:19 -04:00
Andrew Gallant
d9ca529356 libripgrep: initial commit introducing libripgrep 
libripgrep is not any one library, but rather, a collection of libraries
that roughly separate the following key distinct phases in a grep
implementation:

  1. Pattern matching (e.g., by a regex engine).
  2. Searching a file using a pattern matcher.
  3. Printing results.

Ultimately, both (1) and (3) are defined by de-coupled interfaces, of
which there may be multiple implementations. Namely, (1) is satisfied by
the `Matcher` trait in the `grep-matcher` crate and (3) is satisfied by
the `Sink` trait in the `grep2` crate. The searcher (2) ties everything
together and finds results using a matcher and reports those results
using a `Sink` implementation.

Closes #162
 2018-08-20 07:10:19 -04:00
Sylvestre Ledru
0958837ee1 readme: ripgrep is available in Debian Buster 
PR #1016
 2018-08-17 06:35:43 -04:00
Andrew Gallant
94be3bd4bb grep: remove senseless test 
It was pulling in a sizable data file and doesn't appear to be testing
anything meaningful that isn't covered by a variety of other tests.
 2018-08-15 19:52:50 -04:00
woky
deb1de6e1e ignore/types: add *.sbt to scala type 
Sbt is currently most used Scala build tool which uses
*.sbt files, which are basically Scala.

PR #1010
 2018-08-14 06:29:27 -07:00
Vanessa McHale
6afdf15d85 ignore/types: add Idris, Dhall and ATS 
And also improve Haskell detection.

PR #1007
 2018-08-07 13:10:19 -04:00
Jonatan Hamberg
6cda7b24e9 readme: update debian link to 0.9.0 
PR #1006
 2018-08-07 07:50:08 -04:00
llogiq
ad9befbc1d deps: update bytecount to 0.3.2 
PR #1003
 2018-08-06 06:44:16 -04:00
Andrew Gallant
e86d3d95c2 pkg: update brew tap to 0.9.0 2018-08-03 17:04:36 -04:00
Andrew Gallant
6799dcfc0e release: 0.9.0 2018-08-03 16:13:31 -04:00
Andrew Gallant
0fdab0ec5e grep-0.1.9 2018-08-03 16:12:08 -04:00
Andrew Gallant
74ec5b8932 deps: update termcolor and encoding_rs_io 2018-08-03 16:08:57 -04:00
Andrew Gallant
2913fc4cd0 tests: reduce reliance on state in tests 
This commit improves the integration test setup by running tests inside
the system's temporary directory instead of within ripgrep's `target`
directory. The motivation here is to attempt to reduce the effect of
unanticipated state on ripgrep's integration tests, such as the presence
of `.gitignore` files in ripgrep's checkout directory hierarchy
(including parent directories).

This doesn't remove all possible state. For example, there's no
guarantee that the system's temporary directory isn't itself within a
git repository. Moreover, there may still be other ignore rules in the
directory tree that might impact test behavior. Fixing this seems
somewhat difficult. Conceptually, it seems like ripgrep should run each
test in its own `chroot`-like environment, but doing this in a
non-annoying and portable way (including Windows) doesn't appear to be
possible.

Another approach to take here might be to teach ripgrep itself that a
particular directory should be treated as root, and therefore, never
look at anything outside that directory. This also seems complex to
implement, but tractable. Let's see how this approach works for now.

Fixes #448, #996
 2018-07-29 10:41:03 -04:00
Andrew Gallant
7c412bb2fa tests/style: 80 columns, dammit 2018-07-29 10:41:03 -04:00
Andrew Gallant
651a0f1ddf ignore: fix typo 2018-07-29 08:37:24 -04:00
Andrew Gallant
45473ba48f ignore/style: 80 columns, dammit 2018-07-29 08:31:04 -04:00
Andrew Gallant
0863c75a5a ignore: fix bug in matched_path_or_any_parents 
This method was supposed to panic whenever the given path wasn't under
the root of the gitignore patcher. Instead of using assert!, it was using
debug_assert!. This actually caused tests to fail when running under
release mode, because the debug_assert! wouldn't trip.

Fixes #671
 2018-07-29 08:30:53 -04:00
Andrew Gallant
d94d99f657 ignore-0.4.3 2018-07-28 11:05:27 -04:00
Andrew Gallant
84585908ac globset-0.4.1 2018-07-28 10:59:54 -04:00
Andrew Gallant
1611c04e6f ignore: respect XDG_CONFIG_DIR/git/config 
This commit updates the logic for finding the value of git's
`core.excludesFile` configuration parameter. Namely, we now check
`$XDG_CONFIG_DIR/git/config` in addition to `$HOME/.gitconfig` (where
the latter overrules the former on a knob-by-knob basis).

Fixes #995
 2018-07-28 10:04:16 -04:00
dana
d857ad6ed3 complete: add --no-pre, improve --pre/--search-zip exclusivity 2018-07-24 07:21:18 -04:00
Andrew Gallant
4dd2f8e40e deps: update atty and winapi 
This updates atty and winapi to their latest versions, including the bug
fix in atty that allows it to work with winapi 0.3.5.
 2018-07-22 13:07:48 -04:00
Andrew Gallant
dca8110da2 ripgrep: when given no patterns, don't match 
Generally speaking, ripgrep prevents the case of not having any patterns
via its arg parsing. However, it is possible for users to provide a file
of patterns via the `-f` flag. If that file is empty, then ripgrep has
nothing to search for and therefore should not ever produce any match.

One way of fixing this might be to replace the absence of patterns with
a pattern that can never match, but this still requires opening and
searching through every file, which is quite a waste. Instead, we detect
this case explicitly and quit early.

Fixes #900
 2018-07-22 12:07:18 -04:00
Andrew Gallant
0d11497d21 tests: be looser with gzip failure 
Don't expect the exact error message. Instead, just ask that the error
message exist and be non-empty.

Fixes #903
 2018-07-22 11:08:16 -04:00
Andrew Gallant
22ac2e056e ripgrep: stop early when --files --quiet is used 
This commit tweaks the implementation of the --files flag to stop early
when --quiet is provided.

Fixes #907
 2018-07-22 11:05:24 -04:00
Andrew Gallant
03af61fc7b ripgrep: don't skip tar archives 
This removes logic from the decompressor for skipping tar archives. This
logic was originally added under the assumption that we probably want to
avoid the cost of reading them. However, this is generally inconsistent
with how ripgrep treats files like tar archives: it should search them
and do binary detection like normal.

Fixes #918
 2018-07-22 10:59:09 -04:00
Andrew Gallant
560dffd247 ripgrep: add --no-ignore-global flag 
This commit adds a new --no-ignore-global flag that permits disabling
the use of global gitignore filtering. Global gitignores are generally
found in `$HOME/.config/git/ignore`, but its location can be configured
via git's `core.excludesFile` option.

Closes #934
 2018-07-22 10:42:32 -04:00
Andrew Gallant
e65ca21a6c ignore: only respect .gitignore in git repos 
This commit fixes an interesting bug in the `ignore` crate where it
would basically respect any `.gitignore` file anywhere (including global
gitignores in `~/.config/git/ignore`), regardless of whether we were
searching in a git repository or not. This commit rectifies that
behavior to only respect gitignore rules when in a git repo.

The key change here is to move the logic of whether to traverse parents
into the directory matcher rather than putting the onus on the directory
traverser. In particular, we now need to traverse parent directories in
more cases than we previously did, since we need to determine whether
we're in a git repository or not.

Fixes #934
 2018-07-22 10:33:23 -04:00
Andrew Gallant
6771626553 ripgrep: improve usage documentation 
This shows an example for reading stdin.

Fixes #951
 2018-07-22 09:38:49 -04:00
Andrew Gallant
b9c922be53 ripgrep: better --path-separator error message 
This commit improves the error message when --path-separator fails. Namely,
it prints the separator it got and also prints a notice for Windows users
for common failure modes.

Fixes #957
 2018-07-22 09:33:03 -04:00
Andrew Gallant
7a44cad599 deps: pin winapi to 0.3.4 
winapi 0.3.5 changed how it represents some of its structs, which caused
a bug to surface in atty that prevents tty detection on Windows. atty
has an open PR to fix this: https://github.com/softprops/atty/pull/28

Until a new release of atty, we pin winapi to a version that works.
 2018-07-22 09:31:22 -04:00
Andrew Gallant
6dc09c5b1b ripgrep: add --no-pre switch 
This switch explicitly disables the --pre behavior. An empty string will
also disable --pre behavior, but actually utterring an empty flag value
is quite awkward, so we provide an explicit switch to do the same thing.

Thanks to @c-blake for pointing this out.
 2018-07-21 20:57:27 -04:00
Andrew Gallant
209a125ea2 ripgrep: replace decoder with encoding_rs_io 
This commit mostly moves the transcoder implementation to its own
crate: https://github.com/BurntSushi/encoding_rs_io

The new crate adds clear documentation and cleans up the implementation
to fully implement the contract of io::Read.
 2018-07-21 20:36:32 -04:00
Andrew Gallant
090216cf00 ripgrep: reformat --pre warning 2018-07-21 17:53:55 -04:00
Andrew Gallant
c96a358593 ripgrep: add warning to --pre flag 
The --pre flag can result in a pretty large performance penalty, so put
a warning in the flag documentation. This warning is important because a
flag like this could easily wind up in a user's configuration file.
 2018-07-21 17:50:54 -04:00
Charles Blake
231456c409 ripgrep: add --pre flag 
The preprocessor flag accepts a command program and executes this
program for every input file that is searched. Instead of searching the
file directly, ripgrep will instead search the stdout contents of the
program.

Closes #978, Closes #981
 2018-07-21 17:25:12 -04:00
Kalle Samuels
1d09d4d31b ripgrep: add support for lz4 decompression 
This uses the lz4 binary for decompression.

Closes #898
 2018-07-21 16:26:39 -04:00
Andrew Gallant
02f08f3800 changelog: updates 
We continue our quest to update the CHANGELOG incrementally.
 2018-07-21 14:23:38 -04:00
Mateusz Mikuła
470afa1bd7 snap: build without wrappers 
Wrappers usually define things required for snaps to work like library path.
Ripgrep being static binary doesn't need it at all.

This will give minor speed up in scenarios when ripgrep is ran multiple
times and can be considered as good practice for static binaries.

PR #979
 2018-07-21 13:28:27 -04:00
phiresky
aa2ce39d14 ignore: fix has_any_ignore_rules for explicit ignores 
When building a ignore::WalkBuilder by disabling all standard filters
and adding a custom global ignore file, the ignore file is not used. Example:

    let mut walker = ignore::WalkBuilder::new(dir);
    walker.standard_filters(false);
    walker.add_ignore(myfile);

This makes it impossible to use the ignore crate to walk a directory
with only custom ignore files. Very similar to issue #800 (fixed in
b71a110).

PR #988
 2018-07-21 13:26:54 -04:00
Andrew Gallant
d11a3b3377 crates.io: use 'OR' instead of '/' 
Fixes #987
 2018-07-21 13:25:39 -04:00
Andrew Gallant
d09e2f6af1 globset: clarify documentation on regex method 
This makes it clear that the `bytes` API of the regex crate should be
used instead of the Unicode API.

Fixes #985
 2018-07-21 13:23:46 -04:00
Andrew Gallant
7b6af5a177 deps: update regex to 1.0.2 
And also update to regex-syntax 0.6.2.
 2018-07-18 09:29:04 -04:00
Andrew Gallant
9bd1aa1c04 readme: update rogue 1.20 reference 2018-07-17 20:41:34 -04:00
Andrew Gallant
1393ce4b6b deps: update all transitive dependencies 
This updates all remaining transitive dependencies. Most changes appear
minor and there appear to be no minimum Rust version conflicts. Yay!
 2018-07-17 20:34:03 -04:00
Andrew Gallant
8e358ee056 deps: bump various dependencies 
Nothing major here. All patch releases. This should bring us completely
up to date with all direct dependencies.
 2018-07-17 20:33:13 -04:00
Andrew Gallant
5b5f4e74d9 deps: bump encoding_rs to 0.8 
This brings in performance improvements.
 2018-07-17 20:29:41 -04:00
Andrew Gallant
7829850bf0 deps: bump minimum Rust to 1.23.0 from 1.20.0 
1.23.0 is the first Rust release of 2018 and is around half a year old,
which seems old enough to move to. This also lets us bring in encoding_rs
0.8, which includes performance optimizations.
 2018-07-17 20:29:20 -04:00
Andrew Gallant
06b66efd59 deps: get rid of unstable feature 
This was introduced as a temporary measure for dealing with the regex
crate's unstable feature, but it was never included in a release of
ripgrep. Thus, we remove it. The regex crate will now automatically enable
SIMD optimizations when available.
 2018-07-17 20:27:04 -04:00
Andrew Gallant
7e5a590276 grep: small literal detection fix 
This commit tweaks the inner literal detection heuristic such that if it
comes up with any literal that is all whitespace, then it's likely a bad
literal to look for since it's so common. Therefore, we simply reject the
inner literal optimization in this case and let the regex engine do its
thang.
 2018-07-17 20:27:04 -04:00
Andrew Gallant
d17ca45063 deps: update termcolor to 1.0.0 2018-07-17 18:37:02 -04:00
Andrew Gallant
df469fe1b4 termcolor: moved to its own repository 
We also move wincolor with it.

Fixes #924
 2018-07-17 18:03:38 -04:00
Andrew Gallant
b64475aeac ignore: permit use of env::home_dir 
Upstream deprecated env::home_dir because of minor bugs in some corner
cases. We should probably eventually migrate to a correct implementation
in the `dirs` crate, but using the buggy version is just fine for now.
 2018-07-16 17:40:02 -04:00
dana
fca9709d94 complete: improve zsh completion 
- Use groups with _arguments
- Conditionally complete 'negation' options (--messages, --no-column, &c.)
- Improve option exclusivity
- Improve option descriptions
- Improve completion of colour 'whens'
- Improve completion of colour specs
- Remove some unnecessary work-arounds
- Use more idiomatic conventions
 2018-07-06 10:23:20 -04:00
dana
62b4813b8a ci: minor improvements to test_complete.sh 2018-07-06 10:23:20 -04:00
dana
b38b101c77 ripgrep: rename --maxdepth to --max-depth 
We keep the old `--maxdepth` spelling to preserve backward
compatibility.

PR #967
 2018-06-25 20:22:09 -04:00
dana
ac90316e35 ripgrep: add --fixed-strings flag 
Fixes #964

PR #965
 2018-06-25 17:02:02 -04:00
Andrew Gallant
a6467f880a ripgrep: disable autotests 
This keeps us working in Rust 2018.

Fixes #923
 2018-06-23 20:49:05 -04:00
Andrew Gallant
004bb35694 ripgrep/printer: fix small performance regression 
This commit removes an unconditional extra regex search that is in fact
not always necessary. This can result in a 2x performance improvement in
cases where ripgrep reports many matches.

The fix itself isn't ideal, but we continue to punt on cleaning up the
printer until it is rewritten for libripgrep, which is happening Real
Soon Now.

Fixes #955
 2018-06-23 20:49:05 -04:00
Andrew Gallant
cd6c190967 ripgrep: use new BufferedStandardStream from termcolor 
Specifically, this will use a buffered writer when not printing to a tty.
This fixes a long standing performance regression where ripgrep would
slow down dramatically if it needed to report a lot of matches.

Fixes #955
 2018-06-23 20:49:05 -04:00
Andrew Gallant
d5139228e5 termcolor: add BufferedStandardStream 
This commit adds a new type, BufferedStandardStream, which emulates the
StandardStream API (sans `lock`), but will internally use a buffered
writer.

To achieve this, we add a new default method to the WriteColor trait that
indicates whether the underlying writer must synchronously communicate
with an API to control coloring (e.g., the Windows console API). The new
BufferedStandardStream then uses this default method to determine how
eager it should be to flush its buffer before employing color settings.
This should have basically zero overhead when using ANSI color escape
sequences.
 2018-06-23 20:49:05 -04:00
Stepan Koltsov
bb16ba6311 ignore/types: add Bazel 
`BUILD`, `WORKSPACE` are mentioned here:
https://docs.bazel.build/versions/master/build-ref.html

`*.bzl` is mentioned here:
https://docs.bazel.build/versions/master/skylark/concepts.html

PR #960
 2018-06-23 15:25:43 -04:00
Andrew Gallant
5e85f2577b deps: update to regex 1.0.1 
This causes SIMD to kick in automatically when compiling with stable
Rust 1.27+.

We also update the README to describe the current state of things.

Thanks to @hartley for pointing this out:
https://twitter.com/hartley/status/1009950392862453760
 2018-06-21 20:14:23 -04:00
Jon Surrell
ca23a170f7 ripgrep: use exit code 2 to indicate error 
Exit code 1 was shared to indicate both "no results" and "error." Use
status code 2 to indicate errors, similar to grep's behavior.

Fixes #948 

PR #954
 2018-06-19 07:41:44 -04:00
Mårten Kongstad
223d7d9846 ignore/types: add Android makefile types 
The Android platform is gradually moving from Makefiles (*.mk) to
Blueprint files (*.bp). Add support for both. See [1] for more
information.

1. https://android.googlesource.com/platform/build/blueprint/+/master-soong
 2018-06-15 08:29:53 -04:00
Mårten Kongstad
e4bce86111 ignore/types: add AIDL file type 
Add support for Android Interface Definition Language files (*.aidl).
See [1] for more information.

1. https://developer.android.com/guide/components/aidl
 2018-06-15 08:29:53 -04:00
Tim Kilbourn
15fa77cdb3 ignore/types: add FIDL type 
FIDL is the Fuchsia Interface Definition Language
https://fuchsia.googlesource.com/zircon/+/HEAD/docs/fidl/index.md
 2018-06-06 07:42:08 -04:00
Ahmed El Gabri
c3f97513d6 doc: sync config file examples 
This brings the examples for configuration files in sync between
the man page and the guide.
 2018-05-25 06:42:05 -04:00
George Plymale II
c21b9b20cf doc: add MacPorts installation instructions 2018-05-24 13:01:28 -04:00
Khalid Jebbari
ce145c6a2a doc: update crates.io badge 
This is the official markdown snippet from shields.io
 2018-05-24 06:46:08 -04:00
Wesley Moore
a383d5c4e9 doc: add BSD packages to README 2018-05-14 06:45:39 -04:00
Michael Hay
64317bda9f doc: fix broken link to RegexSet docs 2018-05-08 12:03:47 -04:00
Stephen E. Baker
7f3a0f0828 ignore/types: add jsp extension to java type 2018-05-08 12:03:19 -04:00
Bastien Orivel
49f36c7dcd deps: update regex to 1.0 
We retain the `simd-accel` feature on globset for backwards
compatibility, but will remove it in the next semver release.
 2018-05-07 13:07:30 -04:00
Garrett Squire
83b4fdb8d6 ignore/doc: improve docs for case_insensitive 
This commit updates the OverrideBuilder and GitignoreBuilder docs
for the case_insensitive method, denoting that it must be called before
adding any patterns.
 2018-05-06 19:03:11 -04:00
Elliott Slaughter
8b57d78b96 doc: update suggested version for ignore 2018-05-06 19:02:08 -04:00
Bram Geron
a2d8c49d6f ignore/types: add shorthand 'hs' for Haskell 2018-05-03 09:05:00 -04:00
Andrew Gallant
6ffb4b7466 doc: go away snap 
Snap has caused a number of nonsensical bug reports, and not even the
`--classic` flag seems capable of fixing them. Therefore, remove snap
from the README and put in a special line in the ISSUE_TEMPLATE about
snap.

FIxes #902
 2018-04-30 15:25:51 -04:00
Andrew Gallant
198d1fede9 ignore/types: fix typo in puppet glob 
Thanks @CYBAI for noticing this!

See #899
 2018-04-29 09:30:44 -04:00
Zach Crownover
667b9a7d62 ignore/types: add puppet 
Puppet is primarily written in it's own format of .pp files, but
custom facts and functions are often written in Ruby. The templating
language is ERB and so this will allow scanning of any of the three
most commonly used formats for Puppet specific things.
 2018-04-29 09:21:48 -04:00
Andrew Gallant
1f528f1641 doc: update crates.io description 
This brings it in line with the README.
 2018-04-26 17:04:35 -04:00
Andrew Gallant
ab64da73ab ignore: speed up Gitignore::empty 
This commit makes Gitignore::empty a bit faster by avoiding allocation
and manually specializing the implementation instead of routing it through
the GitignoreBuilder.

This helps improve uses of ripgrep that traverse *many* directories, and
in particular, when the use of ignores is disabled via command line
switches.

Fixes #835, Closes #836
 2018-04-24 11:19:03 -04:00
Jonathan Klimt
1266de3d4c ignore/types: add verilog 2018-04-24 09:00:03 -04:00
Andrew Gallant
bf51058eb2 tests: fix tests on Windows 
A bug in the atty crate was previously masking a problem with the
integration tests on Windows. Namely, the bug in atty resulted in
atty::is(Stdin) returning true if we couldn't get the file name for the
stdin stream. This in turn caused tests like `rg foo` to search the CWD,
which was the intended behavior. However, once the atty bug was fixed,
atty::is(Stdin) no longer returned true, causing `rg foo` searches to
fail.

On Unix-like systems, the atty behavior has always been correct.
However, on Unix-like systems we have a decent way of detecting whether
stdin is readable or not. If it isn't---which is the case in the
integration tests---then we fall back to searching the CWD. On Windows
however, we haven't yet implemented anything to detect whether stdin is
readable or not, so we must always assume that it is. Therefore, we
never get the "go ahead" to search the CWD and the tests fail.

Most of the tests are written to search the CWD explicitly, but there
were a few stragglers that don't.

This isn't great, and we should try to figure out how to do better stdin
detection on Windows.
 2018-04-23 20:37:59 -04:00
Andrew Gallant
3dc6fe6f05 output: remove unnecessary mut binding 2018-04-23 20:06:03 -04:00
Andrew Gallant
06438d5360 changelog: update 2018-04-23 20:01:57 -04:00
Andrew Gallant
ae6f871491 output: remove --line-number-width flag 
This commit does what no software project has ever done before: we've
outright removed a flag with no possible way to recapture its
functionality.

This flag presents numerous problems in that it never really worked well
in the first place, and completely falls over when ripgrep uses the
--no-heading output format. Well meaning users want ripgrep to fix this
by getting into the alignment business by buffering all output, but that
is a line that I refuse to cross.

Fixes #795
 2018-04-23 19:57:22 -04:00
Andrew Gallant
ed059559cd deps: update to atty 0.2.9 
https://github.com/softprops/atty/pull/25 was merged, so we can upgrade.
 2018-04-23 19:32:39 -04:00
Andrew Gallant
b75526bd7f output: add --no-column flag 
This disables columns in the output if they were otherwise enabled.

Fixes #880
 2018-04-23 19:26:58 -04:00
Andrew Gallant
507801c1f2 ignore: support .git directory OR file 
This improves support for submodules, which seem to use a '.git' file
instead of a '.git' directory to indicate a worktree.

Fixes #893
 2018-04-23 18:33:25 -04:00
Andrew Gallant
2a9d007261 complete: add --no-ignore-messages 2018-04-23 18:29:02 -04:00
Andrew Gallant
0ee0b160b5 logging: add new --no-ignore-messages flag 
The new --no-ignore-messages flag permits suppressing errors related to
parsing .gitignore or .ignore files. These error messages can be somewhat
annoying since they can surface from repositories that one has no control
over.

Fixes #646
 2018-04-23 18:18:44 -04:00
Andrew Gallant
b4781e2f91 doc: more specific docs for --no-messages 
This makes it clear that the --no-messages flag doesn't actually
suppress all error messages, and is therefore not equivalent to
redirecting stderr to /dev/null.

See also: #860
 2018-04-23 18:07:57 -04:00
Jeremy Day
8cb03941e6 doc: add search and replace faq 
Closes #870
 2018-04-23 17:45:26 -04:00
Andrew Gallant
6b15ce2342 deps: update remove_dir_all 2018-04-21 12:13:16 -04:00
Andrew Gallant
4c0b0c6c9d ignore: release 0.4.2 2018-04-21 12:10:16 -04:00
Andrew Gallant
6c8b1e93d5 globset: release 0.4.0 2018-04-21 12:09:15 -04:00
Andrew Gallant
ebdb7c1d4c ignore: impl Clone for DirEntry 
There is a small hiccup here in that a `DirEntry` can embed errors
associated with reading an ignore file, which can be accessed and logged
by consumers if desired. That error type can contain an io::Error, which
isn't cloneable. We therefore implement Clone on our library's error
type in a way that re-creates the I/O error as best as possible.

Fixes #891
 2018-04-21 12:01:11 -04:00
Andrew Gallant
58bd0c67da deps: pin to atty 0.2.6 
atty 0.2.7 (and 0.2.8) contain a regression in cygwin terminals that
prevents basic use of ripgrep, and is also the cause of the Windows CI
test failures. For now, we pin to 0.2.6, but a patch has been submitted
upstream: https://github.com/softprops/atty/pull/25
 2018-04-21 12:01:11 -04:00
Andrew Gallant
1503b3175f readme: add --classic flag to snap install 
It would be nicer to switch to the `ripgrep` snap package, but
apparently it is configured to install with a binary name `ripgrep.rg`
instead of just `rg`. *sigh*
 2018-04-17 06:43:43 -04:00
Andrew Gallant
0345e089aa deps: update regex-syntax 2018-04-15 08:45:05 -04:00
Avindra Goolcharan
0911ab1546 readme: add openSUSE Tumbleweed package 
Link to software.opensuse.org package and add `zypper` instructions.
 2018-04-09 07:22:04 -04:00
FlorentBecker
c4dd927a13 ignore: add Clone/Debug for builders 2018-04-05 08:06:26 -04:00
Andrew Gallant
34abed597f deps: update all dependencies 
In particular, we can now drop rand 0.3.
 2018-04-01 10:59:44 -04:00
Andrew Gallant
835600794f termcolor: release 0.3.6 2018-03-26 17:28:21 -04:00
ehuss
07713fb5c5 termcolor: fix bold + intense colors in Win 10 
There is an issue with the Windows 10 console where if you issue the bold
escape sequence after one of the extended foreground colors, it overrides the
color.  This happens in termcolor if you have bold, intense, and color set.
The workaround is to issue the bold sequence before the color.

Fixes rust-lang/rust#49322
 2018-03-26 16:42:48 -04:00
Dezhi “Andy” Fang
d7c9323a68 deps: update regex 
This fixes build failures on latest nightly with SIMD features.
 2018-03-17 19:33:34 -04:00
Andrew Gallant
b7d29d126f deps: update clap, atty, libc 
Nothing to see here.

Note that we continue to refrain to update tempdir, which means we are
still bringing in rand 0.4 and rand 0.3. Updating tempdir brings in an
old version of remove_dir_all, which in turn brings in winapi 0.2. No
thanks.
 2018-03-13 22:55:39 -04:00
Andrew Gallant
42b8132d0a grep: add "perfect" smart case detection 
This commit removes the previous smart case detection logic and replaces
it with detection based on the regex AST. This particular AST is a faithful
representation of the concrete syntax, which lets us be very precise in
how we handle it.

Closes #851
 2018-03-13 22:55:39 -04:00
Andrew Gallant
cd08707c7c grep: upgrade to regex-syntax 0.5 
This update brings with it many bug fixes:

  * Better error messages are printed overall. We also include
    explicit call out for unsupported features like backreferences
    and look-around.
  * Regexes like `\s*{` no longer emit incomprehensible errors.
  * Unicode escape sequences, such as `\u{..}` are now supported.

For the most part, this upgrade was done in a straight-forward way. We
resist the urge to refactor the `grep` crate, in anticipation of it
being rewritten anyway.

Note that we removed the `--fixed-strings` suggestion whenever a regex
syntax error occurs. In practice, I've found that it results in a lot of
false positives, and I believe that its use is not as paramount now that
regex parse errors are much more readable.

Closes #268, Closes #395, Closes #702, Closes #853
 2018-03-13 22:55:39 -04:00
Andrew Gallant
c2e97cd858 changelog: update for 0.9.0 2018-03-12 23:21:42 -04:00
Andrew Gallant
1f70e9187c deps: update regex crate 
This update brings with it a new feature of the regex crate which will
now use SIMD optimizations automatically at runtime with no necessary
compile time flags. All that's needed is to enable the `unstable` feature.

Other crates, such as bytecount and encoding_rs, are still using the
old-style SIMD support, so we leave the simd-accel and avx-accel features.
However, the binaries we distribute on Github no longer have those
features enabled, which makes them truly portable.

Fixes #135
 2018-03-12 23:21:42 -04:00
Markus Staab
7120f32258 globset/doc: update README for 0.3 release 2018-03-12 07:19:55 -04:00
Balaji Sivaraman
00520b30f5 output: add --stats flag 
This commit provides basic support for a --stats flag, which will print
various aggregate statistics about a search after all of the results
have been printed. This is mostly intended to support a similar feature
found in the Silver Searcher. Note though that we don't emit the total
bytes searched; this is a first pass at an implementation and we can
improve upon it later.

Closes #411, Closes #799
 2018-03-10 10:59:00 -05:00
Andrew Gallant
11a8f0eaf0 args: treat --count --only-matching as --count-matches 
Namely, when ripgrep is asked to count things and is also asked to print
every match on its own line, then we should just automatically count the
matches and not the lines. This is a departure from how GNU grep behaves,
but there is a compelling argument to be made that GNU grep's behavior
doesn't make a lot of sense.

Note that since this changes the behavior of combining two existing
flags, this is a breaking change.
 2018-03-10 10:38:34 -05:00
Balaji Sivaraman
27fc9f2fd3 search: add a --count-matches flag 
This commit introduces a new flag, --count-matches, which will cause
ripgrep to report a total count of all matches instead of a count of
total lines matched.

Closes #566, Closes #814
 2018-03-10 10:38:25 -05:00
Balaji Sivaraman
96f73293c0 cleanup: rename match_count to match_line_count 2018-03-10 10:23:38 -05:00
Balaji Sivaraman
b006943c01 search: add -b/--byte-offset flag 
This commit adds support for printing 0-based byte offset before each
line. We handle corner cases such as `-o/--only-matching` and
`-C/--context` as well.

Closes #812
 2018-03-10 10:15:19 -05:00
Brian Malehorn
91d0756f62 ignore: support backslash escaping 
Use the new `Globset::backslash_escape` knob to conform to git behavior:
`\` will escape the following character. For example, the pattern `\*`
will match a file literally named `*`.

Also tweak a test in ripgrep that was relying on this incorrect
behavior.

Closes #526, Closes #811
 2018-03-10 09:30:55 -05:00
Andrew Gallant
54256515b4 globset: make ErrorKind enum extensible 
This commit makes the ErrorKind enum extensible by adding a
__Nonexhaustive variant. Callers should use this as a hint that
exhaustive case analysis isn't possible in a stable way since new
variants may be added in the future without a semver bump.
 2018-03-10 09:30:55 -05:00
Brian Malehorn
e2516ed095 globset: support backslash escaping 
From `man 7 glob`:

    One can remove the special meaning of '?', '*' and '[' by preceding
    them by a backslash, or, in case this is part of a shell command
    line, enclosing them in quotes.

Conform to glob / fnmatch / git implementations by making `\` escape the
following character - for example `\?` will match a literal `?`.

However, only enable this by default on Unix platforms. Windows builds
will continue to use `\` as a path separator, but can still get the new
behavior by calling `globset.backslash_escape(true)`.

Adding tests for the `Globset::backslash_escape` option was a bit
involved, since the default value of this option is platform-dependent.

Extend the options framework to hold an `Option<T>` for each
knob, where `None` means "default" and `Some(v)` means "override with
`v`". This way we only have to specify the default values once in
`GlobOptions::default()` rather than replicated in both code and tests.

Finally write a few behavioral tests, and some tests to confirm it
varies by platform.
 2018-03-10 09:30:55 -05:00
Alejandro Barreto
c0c80e0209 doc: add Windows Scoop install instructions 2018-03-10 08:15:22 -05:00
Andrew Gallant
dbf6f15625 mmap: handle ENOMEM error 
This commit causes a memory map strategy to fall back to a file backed
strategy if the mmap call fails with an `ENOMEM` error.

Fixes #852
 2018-03-10 08:13:27 -05:00
Ryan Hayle
9163aaac27 doc: add additional instructions for snap 
In the snap store, ripgrep 0.8.1 is only available as a candidate
release, while the default (stable) release is 0.7.1.
 2018-03-09 07:09:02 -05:00
Patrick Artounian
9d7448bfc0 doc: shorten Rust nightly brew install command 
The burntsushi/ripgrep/ prefix is not needed.
 2018-03-07 12:44:06 -05:00
Richard Dodd (dodj)
b98585b429 termcolor/doc: fix typo 2018-03-03 09:20:28 -05:00
Andrew Gallant
f5411b992c doc: use PATTERNFILE for -f/--file flag 
Fixes #832
 2018-02-23 12:18:15 -05:00
Anthony Wong
492effc7be pkg: update snapcraft.yaml 
Update version number and don't declare alias as it has been deprecated.
 2018-02-23 06:51:39 -05:00
Andrew Gallant
4889d2d37c doc: clarify licensing story 2018-02-22 19:01:43 -05:00
Andrew Gallant
354996a16f doc: clarify snap installation instructions 
Fixes #782
 2018-02-22 16:56:22 -05:00
Andrew Gallant
cbebb010a7 doc: fix typos 2018-02-21 15:59:12 -05:00
Andrew Gallant
7098daf6a8 doc: "to rip" means "fast" 
Answer the origin story of ripgrep's name.
 2018-02-21 15:53:50 -05:00
Andrew Gallant
17d09c0882 pkg: update brew tap to 0.8.1 2018-02-20 21:51:41 -05:00
Andrew Gallant
c8e9f25b85 ci: fix macOS asciidoc installation 2018-02-20 21:05:40 -05:00
Andrew Gallant
9305f89f39 ci: fix man page generation on macOS 2018-02-20 20:55:12 -05:00
Andrew Gallant
9c216ad9a4 release: 0.8.1 2018-02-20 20:19:03 -05:00
Andrew Gallant
6862e07870 changelog: 0.8.1 2018-02-20 20:18:01 -05:00
Andrew Gallant
a6d09b2d42 deps: update to clap 2.30.0 2018-02-20 20:16:57 -05:00
Andrew Gallant
ab1b877c20 termcolor: release 0.3.5 2018-02-20 20:15:08 -05:00
Andrew Gallant
2b5c488814 ignore: release 0.4.1 2018-02-20 20:13:56 -05:00
Andrew Gallant
cb47be938e ci: build man page on ARM cross-compile 
This fixes a bug where ripgrep's man page wasn't generated in the ARM
cross-compile build. Mostly, this should just require installing
asciidoc and making sure we test that it actually works.

Fixes #791
 2018-02-20 20:05:55 -05:00
Andrew Gallant
fe9be658f4 doc: omit revision when it isn't available 
If the revision is empty, then we shouldn't show the `(rev )` text in
the output of `rg --version`.

Fixes #789
 2018-02-20 20:05:55 -05:00
Andrew Gallant
8c800adab7 doc: clarify failure mode 
This adds a hint for end users that run into a common failure mode where
ripgrep won't search any files because they have a `*` rule in their
`$HOME/.gitignore`.

Fixes #815
 2018-02-20 20:05:55 -05:00
Andrew Gallant
d65966efbc ignore: fix performance regression on Windows 
This commit fixes a performance regression in Windows that resulted from
fallout from fixing #705. In particular, we introduced an additional
stat call for every single directory entry, which can be quite
disastrous for performance.

There is a corresponding companion PR that fixes the same bug in
walkdir: https://github.com/BurntSushi/walkdir/pull/96

Fixes #820
 2018-02-20 19:50:52 -05:00
Markus Westerlind
597bf04a56 termcolor: add ?Sized bound for &mut T impl 2018-02-20 07:13:37 -05:00
Balaji Sivaraman
c78ab9e669 termcolor: improve "intense" docs 
Fixes #797
 2018-02-20 07:11:25 -05:00
Balaji Sivaraman
d57fc58081 termcolor: add underline support 
This commit adds underline support to the termcolor crate, and
exposes it through ripgrep.

Fixes #798
 2018-02-20 07:10:03 -05:00
Andrew Gallant
d09538c974 doc: clarify Debian/Ubuntu install instructions 
Thanks @x4121 for the tip!
 2018-02-20 07:02:08 -05:00
David Peter
94768881e1 doc: fix typo in Debian install instructions 2018-02-20 06:59:21 -05:00
Andrey Kolomoets
f3a9ced82c types: add csv 2018-02-19 20:59:15 -05:00
Andrew Gallant
18f549d289 ignore: fix symlink following on Windows 
This commit fixes a bug where symlinks were always being followed on
Windows, even if the user did not request it. This only impacts the
parallel iterator.

This is a regression from the fallout of fixing #705.

Fixes #824
 2018-02-19 20:52:37 -05:00
Cosmin Lehene
c749b604dc doc: clarify --ignore-file flag 
Fixes #684
 2018-02-18 17:53:10 -05:00
Andrew Gallant
d6748a3445 doc: add .deb installation instructions 
Generating a Debian binary package was pretty easy using `cargo deb`, so
it is now part of the release. This commit updates the README's
installation methods to reference it.

I did look into setting up a PPA for Ubuntu, but my eyes glazed over while
reading the documentation. Providing a binary Debian package is likely a
faux pas, but it is extraordinarily convenient.
 2018-02-18 10:32:53 -05:00
Uwe Dauernheim
9b7f420faa doc: fix files-with-matches typo 2018-02-17 08:24:31 -05:00
Andrew Gallant
361698b90a ignore: fix improper hidden filtering 
This commit fixes a bug where `rg --hidden .` would behave differently
with respect to ignore filtering than `rg --hidden ./`. In particular,
this was due to a bug where the directory name `.` caused the leading
`.` in a hidden directory to get stripped, which in turn caused the
ignore rules to fail.

Fixes #807
 2018-02-14 18:16:38 -05:00
David Peter
b71a110ccf ignore: fix custom ignore name bug 
This commit fixes a bug in the handling of custom gitignore file names.
Previously, the directory walker would check for whether there were any
ignore rules present, but this check didn't incorporate the custom gitignore
rules. At a high level, this permits custom gitignore names to be used
even if no other source of gitignore rules is used.

Fixes #800
 2018-02-14 06:53:26 -05:00
unsignedint
5c1af3c25d types: add VHDL 2018-02-13 07:32:16 -05:00
Keith Devens
ad3f55b0e5 doc: the year is 2018 2018-02-12 18:30:02 -05:00
Andrew Gallant
b8e6d50bbe doc: add "grep replacement" question to FAQ 
I am tired of being throwing "but ripgrep is marketed as a grep
replacement" in my face. Let's answer it once and for all.
 2018-02-12 17:57:14 -05:00
KARASZI István
81afe8c5a0 doc: fix typo 2018-02-12 07:16:10 -05:00
Andrew Gallant
c4e0d4bd7b pkg: update brew tap to 0.8.0, take 2 2018-02-11 20:39:12 -05:00
Andrew Gallant
23d1b91ead release: 0.8.0 2018-02-11 20:22:22 -05:00
Andrew Gallant
ac83ed4992 pkg: update brew tap to 0.8.0 2018-02-11 20:19:25 -05:00
Andrew Gallant
555fbd1201 pkg: delete Archlinux PKGBUILD 
Other people are maintaining it and it has bitrotted anyway.
 2018-02-11 20:18:56 -05:00
Andrew Gallant
f3146f8316 changelog: 0.8.0 2018-02-11 13:57:29 -05:00
Andrew Gallant
56341973ee ignore: release 0.4.0 2018-02-11 13:42:59 -05:00
Andrew Gallant
a431160d4c globset: release 0.3.0 2018-02-11 13:41:36 -05:00
Andrew Gallant
5d15f49f0c termcolor: release 0.3.4 2018-02-11 13:39:12 -05:00
Andrew Gallant
7718ee362e wincolor: release 0.1.6 2018-02-11 13:38:00 -05:00
Andrew Gallant
739f8f596b grep: release 0.1.8 2018-02-11 13:35:54 -05:00
Andrew Gallant
e818d7529b deps: update several dependencies 
We specifically avoid updating tempdir since it seems to have grown a
dependency on `remove_dir_all`, which in turn still uses winapi 0.2.
 2018-02-11 13:31:41 -05:00
Andrew Gallant
a2a7f58aa6 doc: fix asciidoc->man formatting 2018-02-10 22:48:46 -05:00
Andrew Gallant
c4a5bc06c5 ci: remove cargo clean 
We aren't using Travis' Cargo cache any more (because it actually seems
to slow down builds), so there's no reason to clean out old build
outputs.

Also, even if we were using the Cargo cache, our approach to finding the
correct Cargo OUT_DIR has become more robust, so we still wouldn't need
to remove the old build outputs.
 2018-02-10 22:28:12 -05:00
Andrew Gallant
96ee4482cd globset: remove use of unsafe 
This commit removes, in retrospect, a silly use of `unsafe`. In particular,
to extract a file name extension (distinct from how `std` implements it),
we were transmuting an OsStr to its underlying WTF-8 byte representation
and then searching that. This required `unsafe` and relied on an
undocumented std API, so it was a bad choice to make, but everything gets
sacrificed at the Alter of Performance.

The thing I didn't seem to realize at the time was that:

  1. On Unix, you can already get the raw byte representation in a manner
     that has zero cost.
  2. On Windows, paths are already being encoded and copied every which
     way. So doing a UTF-8 check and, in rare cases (for invalid UTF-8),
     an extra copy, doesn't seem like that much more of an added expense.

Thus, rewrite the extension extraction using safe APIs. On Unix, this
should have identical performance characteristics as the previous
implementation. On Windows, we do pay a higher cost in the UTF-8
check, but Windows is already paying a similar cost a few times over
anyway.
 2018-02-10 22:28:12 -05:00
Andrew Gallant
3effea0b7c doc: add color FAQ entries 
This commit adds FAQ entries about how to configure ripgrep's coloring,
and how to get true color support in Windows consoles.
 2018-02-10 22:28:12 -05:00
Andrew Gallant
2d68054b1d termcolor: support ANSI in Windows terminals 
This commit uses the new virtual terminal processing feature in Windows 10
to enable the use of ANSI escape codes to color ripgrep's output. This
technique is preferred over the console APIs because it seems like where
the future is heading, but also because it avoids needing to use an
intermediate buffer to deal with the Windows console in a multithreaded
environment.
 2018-02-10 22:28:12 -05:00
Andrew Gallant
65a63788bc wincolor: add support for enabling VT100 
This commit adds a new method to the Console type which permits toggling
the VIRTUAL_TERMINAL_PROCESSING mode on a console. Specifically, this
enables the use of ANSI escape sequences for color in Windows terminals.
 2018-02-10 22:28:12 -05:00
Andrew Gallant
7e5589f07d termcolor: permit hex colors 
This commit adds support for specifying Ansi256 or RGB colors using
hexadecimal notation.
 2018-02-10 22:28:12 -05:00
Andrew Gallant
09c5b2c4ea ci: update deployment for doc rearrangement 
This fixes CI to handle the new documentation files. We also continue to
do more cleanup. In particular, we devise a nicer way of detecting the
most recent Cargo OUT_DIR by writing a dummy file, and looking for the
most recently modified version of that file.
 2018-02-10 12:12:47 -05:00
Andrew Gallant
904c75bd30 doc: overhaul documentation 
This commit cleans up the README and splits portions of it out into
a user guide (GUIDE.md) and a FAQ (FAQ.md). The README now provides a
small list of documentation "quick" links to various parts of the docs.

This commit also does a few other minor touchups.
 2018-02-10 12:12:47 -05:00
Andrew Gallant
ca3e0e8a49 doc: clarify --files-without-match 
This adds a couple common keywords to the documentation.

Fixes #779
 2018-02-10 12:12:47 -05:00
Andrew Gallant
ae2d036dd4 build: remove compile script 
This script has only ever intended to be a convenience to me to compile
ripgrep. It is otherwise a distraction, so remove it.
 2018-02-10 12:12:47 -05:00
Andrew Gallant
8e93fa0e7f deps: update regex to 0.2.6 
This regex update disabled the Tuned Boyer-Moore literal searcher which
has a bug in it that isn't straight-forward to fix. We bring that update
into ripgrep with this commit.

Fixes #780, Fixes #781
 2018-02-08 18:25:55 -05:00
Andrew Gallant
7f5c07434b argv: add several hidden flags 
This adds hidden counter-flags for the following:

  -L/--follow [--no-follow]
  --hidden [--no-hidden]
  --no-ignore [--ignore]
  --no-ignore-parent [--ignore-parent]
  --no-ignore-vcs [--ignore-vcs]
  --no-messages [--messages]
  --search-zip [--no-search-zip]
  --sort-files [--no-sort-files]
  --text [--no-text]

In the above list, the counter-flags are in brackets.

While these flags are hidden, we document the counter-flags in the
documentation for the flags they are countering.
 2018-02-06 18:28:39 -05:00
Andrew Gallant
874f0b96a6 argv: support hidden flags 
This commit adds support for hidden flags. The purpose of hidden flags
is for things that end users likely won't need unless they have a
configuration file that disables ripgrep's defaults. These flags will
provide a way to re-enable ripgrep's defaults.
 2018-02-06 18:26:23 -05:00
Behnam Esfahbod
706323ad8f globset: add more tests for single-asterisk pattern 
This adds a few tests that check for bugs reported here:
https://github.com/rust-lang/cargo/issues/4268

The bugs reported in the aforementioned issue are probably caused by not
enabling the `literal_separator` option in `GlobBuilder`. Enabling that
in the tests under question fixes the issue.

Closes #773
 2018-02-06 17:42:22 -05:00
Andrew Gallant
8460d7fe3d ci: fix deploy condition 
The previous setting was for debugging that accidentally got merged.
 2018-02-06 17:27:57 -05:00
Andrew Gallant
e1f1ede17d ci: test build outputs 
This modifies CI to check that we generate completion files and a man
page.

We also enable tests on arm.
 2018-02-06 17:24:31 -05:00
Andrew Gallant
6553940328 doc: generate man page 
This commit uses the recent refactoring for defining flags to
automatically generate a man page. This finally allows us to define the
documentation for each flag in a single place.

The man page is generated on every build, if and only if `asciidoc` is
installed. When generated, it is placed in Cargo's `OUT_DIR` directory,
which is the same place that shell completions live.
 2018-02-06 12:07:59 -05:00
Andrew Gallant
b50ae9a99c ci: cleanup 
This cleans up our CI scripts but doesn't significantly change anything.
Mostly this is removing dead code and wrong comments, and making the style
a bit more consistent.
 2018-02-06 12:07:59 -05:00
Andrew Gallant
224c112e05 argv: tweak the meaning of zero 
This commit makes a small tweak to the --max-columns flag. Namely, if
the value of the flag is 0, then ripgrep behaves as-if the flag were
absent.

This is useful in the context of ripgrep reading configuration from the
environment. For example, an end user might set --max-columns=150, but we
should permit the user to disable this setting when needed. Using -M0 is
a nice way to do that.

We do this because a zero value for --max-columns isn't particularly
meaningful. We do leave the --max-count, --max-filesize and --maxdepth
flags alone though, since a zero value for those flags is potentially
meaningful. (--max-count even has tests for ripgrep's behavior when
given a value of 0.)
 2018-02-06 12:07:59 -05:00
Andrew Gallant
8cb5833ef9 argv: update clap to 2.29.4 
We use the new AppSettings::AllArgsOverrideSelf to permit all flags to
be specified multiple times. This removes the need for our previous
work-around where we would enable `multiple` for every flag and then
just extract the last value when consuming clap's matches.

We also add a couple regression tests that ensure repeated switches and
flags work as expected.
 2018-02-06 12:07:59 -05:00
Kevin K
85cd3f0a6e argv: fix PATTERN typo 
When referencing the PATTERN positional argument,
we should use `pattern` and not `PATTERN`. The former
is the clap identifier name while the latter is the argument
value name.
 2018-02-05 11:37:17 -05:00
Andrew Gallant
c57d0fb4e8 config: add persistent configuration 
This commit adds support for reading configuration files that change
ripgrep's default behavior. The format of the configuration file is an
"rc" style and is very simple. It is defined by two rules:

  1. Every line is a shell argument, after trimming ASCII whitespace.
  2. Lines starting with '#' (optionally preceded by any amount of
     ASCII whitespace) are ignored.

ripgrep will look for a single configuration file if and only if the
RIPGREP_CONFIG_PATH environment variable is set and is non-empty.
ripgrep will parse shell arguments from this file on startup and will
behave as if the arguments in this file were prepended to any explicit
arguments given to ripgrep on the command line.

For example, if your ripgreprc file contained a single line:

    --smart-case

then the following command

    RIPGREP_CONFIG_PATH=wherever/.ripgreprc rg foo

would behave identically to the following command

    rg --smart-case foo

This commit also adds a new flag, --no-config, that when present will
suppress any and all support for configuration. This includes any future
support for auto-loading configuration files from pre-determined paths
(which this commit does not add).

Conflicts between configuration files and explicit arguments are handled
exactly like conflicts in the same command line invocation. That is,
this command:

    RIPGREP_CONFIG_PATH=wherever/.ripgreprc rg foo --case-sensitive

is exactly equivalent to

    rg --smart-case foo --case-sensitive

in which case, the --case-sensitive flag would override the --smart-case
flag.

Closes #196
 2018-02-04 10:40:20 -05:00
Andrew Gallant
d83bab4d3f argv: permit repeated flags 
This commit builds on the previous argv refactor by being more principled
about how we declared our flags. In particular, we now require that every
clap argument is one of three things: a positional argument, a switch or
a flag that accepts exactly one value. The latter two are always permitted
to be repeated, and we modify the code that consumes a clap::ArgMatches to
always use the *last* value of an argument. (clap by default always uses
the first value of argument, if it has been repeated and is accessed via
one of the singleton accessors.)

Fixes #553
 2018-02-04 10:40:20 -05:00
Andrew Gallant
ce84e1ef04 argv: refactor clap initialization 
This commit refactors how we define flags. In theory, this commit
should not result in any behavioral changes (other than perhaps more
consistent rules for flag overrides).

There are two important changes:

Firstly, each flag (or tightly coupled group of flags) is defined in its
own function. This function includes the documentation for that flag. This
improves the locality for each flag; everything you need to know about it
is self-contained in one small region of code.

Secondly, each flag is defined in terms of a very small ripgrep-specific
layer above clap. This permits us to have a set of structured arguments
independent of clap. The intention here is that we can use this indirection
to generate other documentation such as man pages.

This commit lays the ground work for modifying our use of clap in
principled way such that flags can be specified multiple times without
conflict. This in turn will help us implement support for persistent
configuration.
 2018-02-04 10:40:20 -05:00
Andrew Gallant
c8e755f11f deps: remove vec-map feature from clap 
This removes the vec-map feature from clap. clap's README claims that
vec-map provides a small performance benefit, but I could observe any in
ripgrep workloads.

The benefit here is that it drops a dependency.

Amazingly, this drops whole release build times for ripgrep from 68s to
33s, and debug build time also decreases from 22s to 15.5s. This was
entirely unintentional but a welcome surprise.
 2018-02-04 10:40:20 -05:00
Andrew Gallant
68dac7c4b0 build: add git hash 
This commit makes the git hash ripgrep was built with available for use
in the version string.

We also do a few minor touchups in build.rs and src/app.rs.
 2018-02-04 10:40:20 -05:00
Andrew Gallant
3535047094 logger: drop env_logger 
This commit updates the `log` crate to 0.4 and drops the dependency on
env_logger. In particular, the latest version of env_logger brings in
additional non-optional dependencies such as chrono that I don't think is
worth including into ripgrep.

It turns out ripgrep doesn't need any fancy logging. We just need a concept
of log levels and the ability to print to stderr. Therefore, we just roll
our own super simple logger.

This update is motivated by the persistent configuration task. In
particular, we need the ability to toggle the global log level more than
once, and this doesn't appear to be possible with older versions of the
log crate.
 2018-02-04 10:40:20 -05:00
Andrew Gallant
fe00255494 deps: bump wincolor 2018-02-03 20:38:03 -05:00
Andrew Gallant
07c837e740 wincolor-0.1.5 2018-02-03 20:34:08 -05:00
Andrew Gallant
cb0e693e31 docs: touch up issue template 2018-02-03 09:21:21 -05:00
Andrew Gallant
e9d448e93b docs: add an issue template 2018-02-03 09:18:31 -05:00
Andrew Gallant
c7fc916e6b deps: bump walkdir (again) 
walkdir 2.1.2 introduced a subtle bug on Windows when dealing with
symlinks. We update to the latest to get the fix.
 2018-02-01 22:51:34 -05:00
Andrew Gallant
e36b65a11a windows: fix OneDrive traversals 
This commit fixes a bug on Windows where directory traversals were
completely broken when attempting to scan OneDrive directories that use
the "file on demand" strategy.

The specific problem was that Rust's standard library treats OneDrive
directories as reparse points instead of directories, which causes
methods like `FileType::is_file` and `FileType::is_dir` to always return
false, even when retrieved via methods like `metadata` that purport to
follow symbolic links.

We fix this by peppering our code with checks on the underlying file
attributes exposed by Windows. We consider an entry a directory if and
only if the directory bit is set on the attributes. We are careful to
make sure that the code remains the same on non-Windows platforms.

Note that we also bump the dependency on `walkdir`, which contains a
similar fix for its traversals.

This bug is recorded upstream:
https://github.com/rust-lang/rust/issues/46484

Upstream also has a pending PR:
https://github.com/rust-lang/rust/pull/47956

Fixes #705
 2018-02-01 21:11:02 -05:00
Andrew Gallant
11ad7ab204 ignore/deps: update walkdir 
This commit updates to the latest walkdir release, which fixes a bug on
Windows where ripgrep would panic if it was told to traverse a directory
while following symlinks *and* if opening one of those symlinks failed.

Fixes #633
 2018-02-01 17:09:06 -05:00
Andrew Gallant
93943793c3 worker: better error handling for memory maps 
Previously, we would bail out of using memory maps if we could detect
ahead of time that opening a memory map would fail. The only case we
checked was whether the file size was 0 or not.

This is actually insufficient. The mmap call can return ENODEV errors
when a file doesn't support memory maps. This is the case for new files
exposed by Linux, for example,
/sys/devices/system/cpu/vulnerabilities/meltdown.

We fix this by checking the actual error codes returned by the mmap call.
If ENODEV (or EOVERFLOW) is returned, then we fall back to regular `read`
calls. If any other error occurs, we report it to the user.

Fixes #760
 2018-01-31 19:20:36 -05:00
Andrew Gallant
0fedaa7d28 style: remove eprintln macro 
The eprintln! macro was added to Rust's standard library in Rust 1.19.0,
which is below ripgrep's minimum Rust version. Therefore, we can rely on
the standard library variant now.
 2018-01-31 19:17:51 -05:00
llogiq
e05023b406 deps: update bytecount 
This improves performance with current nightly rustc.
 2018-01-30 16:34:30 -05:00
Balaji Sivaraman
f007f940c5 search: add support for searching compressed files 
This commit adds opt-in support for searching compressed files during
recursive search. This behavior is only enabled when the
`-z/--search-zip` flag is passed to ripgrep. When enabled, a limited set
of common compression formats are recognized via file extension, and a
new process is spawned to perform the decompression. ripgrep then
searches the stdout of that spawned process.

Closes #539
 2018-01-30 09:13:53 -05:00
Marc Tiehuis
a8543f798d termcolor: add extended color support 
This commit adds 256-color and 24-bit truecolor support to ripgrep.
This only provides output support on ANSI terminals. If the Windows
console is used for coloring, then 256-color and 24-bit color settings
are ignored.
 2018-01-29 18:49:50 -05:00
Andrew Gallant
ef9e17d28a deps: bump memmap to 0.6.2 
This removes the last dependency that required winapi 0.2. ripgrep now
only depends on winapi 0.3.
 2018-01-29 17:09:01 -05:00
ptzz
3cb4d1337e ignore: support custom file names 
This commit adds support for ignore files with custom names. This
allows for application specific ignorefile names, e.g. using
`.fdignore` for `fd`.

See also: https://github.com/BurntSushi/ripgrep/issues/673

See also: https://github.com/sharkdp/fd/issues/156
 2018-01-29 16:06:05 -05:00
kennytm
8514d4fbb4 termcolor: tweak reset escape 
Write `Ansi::reset()` using `\x1b[0m` instead of `\x1b[m`.

This works around an AppVeyor bug: https://github.com/appveyor/ci/issues/1824
 2018-01-29 14:14:55 -05:00
Michael Salihi
ed9150c9b4 types: add Smarty tpl 
It is used by Prestashop CMS and more.
 2018-01-29 14:12:02 -05:00
dana
51864c13fc ignore: fix handling of / in patterns 
This commit makes handling of patterns containing a `/`
match actual git behaviour and the specification written
in `man gitignore`.

Fixes #761
 2018-01-29 14:10:59 -05:00
Arvid Gerstmann
35f802166d types: add gn type 
This is for Google's new build system.
 2018-01-17 08:49:01 -05:00
Arvid Gerstmann
bba2d56292 types: add hxx to the cpp type 2018-01-17 08:47:23 -05:00
Hendrik Sollich
012880914b types: add webidl (*.webidl) 2018-01-14 11:20:21 -05:00
Hendrik Sollich
832f5baf1a types: add webidl 2018-01-12 19:48:50 -05:00
dana
a6d3a959eb types: yarn.lock is not YAML 
Fixes #747
 2018-01-12 19:35:46 -05:00
Sebastian Torres
f00625c3f4 readme: add Ubuntu install instructions 2018-01-12 18:44:28 -05:00
Igor Gnatenko
82d03b99cd readme: ripgrep is in Fedora 27 
References: https://bodhi.fedoraproject.org/updates/FEDORA-2018-ca3c304458
 2018-01-12 13:40:00 -05:00
Mridul Singhai
ab2e8190e7 types: add Apache avro 2018-01-11 18:47:19 -05:00
dana
58bdc366ec printer: add --passthru flag 
The --passthru flag causes ripgrep to print every line,
even if the line does not contain a match. This is a
response to the common pattern of `^|foo` to match every
line, while still highlighting things like `foo`.

Fixes #740
 2018-01-11 18:45:51 -05:00
dana
34c0b1bc70 doc: various updates 
* Don't use 'smart typography' when generating man page
* Document PATTERN and PATH
* Capitalise place-holder names consistently
* Add note about PATH overriding glob/ignore rules
* Update args.rs for new PATH capitalisation

Fixes #725
 2018-01-11 08:05:52 -05:00
Eitan Adler
74e96b498c Update types.rs 2018-01-09 07:29:44 -05:00
Eitan Adler
7e0fa1c6be Add a type for man pages 2018-01-09 07:29:44 -05:00
Igor Gnatenko
50616935a9 deps: update bytecount to 0.3 
Signed-off-by: Igor Gnatenko <i.gnatenko.brain@gmail.com>
 2018-01-09 07:09:29 -05:00
Andrew Gallant
01b7859399 benchsuite: fix formatting 2018-01-08 19:23:43 -05:00
Andrew Gallant
5aed0522e8 readme: update summary benchmarks 2018-01-08 19:21:23 -05:00
Andrew Gallant
d1fa295bb2 benchsuite: add updated benchmarks 2018-01-08 19:10:49 -05:00
Andrew Gallant
85d463c0cc readme: link to Andy Lester's feature comparison 2018-01-08 18:31:34 -05:00
Igor Gnatenko
75a4b7b361 remove reference to copr for F28+ 
Signed-off-by: Igor Gnatenko <i.gnatenko.brain@gmail.com>
 2018-01-07 16:57:51 -05:00
Igor Gnatenko
c687d3a7c0 trivial: update instructions for Fedora 
Signed-off-by: Igor Gnatenko <i.gnatenko.brain@gmail.com>
 2018-01-07 16:48:48 -05:00
Stjepan Glavina
fbc1e7fa18 Update crossbeam to 0.3.2 2018-01-06 09:05:51 -05:00
Balaji Sivaraman
14779ed0ea ux: suggest --fixed-strings flag 
If a regex syntax error occurs, then ripgrep will suggest
using the --fixed-strings flag.

Fixes #727
 2018-01-01 11:24:46 -05:00
Balaji Sivaraman
b6177f0459 cleanup: replace try! with ? 2018-01-01 09:22:35 -05:00
Balaji Sivaraman
ba1023e1e4 printer: add support for line number alignment 
Closes #544
 2018-01-01 09:00:31 -05:00
Igor Gnatenko
5e73075ef5 deps: bump lazy_static to 1 2017-12-30 16:50:18 -05:00
Andrew Gallant
1b42c02489 deps: update same-file dep 
The same-file update includes a migration to winapi 0.3.
 2017-12-30 16:50:18 -05:00
Steffen Butzer
0d03145293 wincolor: migrate to winapi 0.3 2017-12-30 16:50:18 -05:00
Andrew Gallant
f8162d2707 deps: update all deps 2017-12-30 16:50:18 -05:00
Andrew Gallant
e044cfb33f deps: update to latest clap release 
This also bumps the minimum Rust version required to 1.20.
 2017-12-30 16:50:18 -05:00
Andrew Gallant
7dd1194a97 deps: update to latest regex crate 
The regex update fixes the Rust nightly build failure by in turn updating
its simd dependency to 2.x.

The regex update also includes a literal optimization that uses Tuned
Boyer Moore.

Fixes #617
 2017-12-30 16:50:18 -05:00
Igor Gnatenko
a5855a5d73 couple of trivial fixes to make clippy a bit more happy (#704) 
clippy: fix a few lints

The fixes are:

  * Use single quotes for single-character
  * Use ticks in documentation when necessary.
  * Just bow to clippy's wisdom.
 2017-12-30 16:06:16 -05:00
flip111
03b0d832ed Update app.rs (#707) 
docs: clarify --ignore-file

Fixes #684
 2017-12-30 16:04:21 -05:00
Lilian A. Moraru
636bbc7c8f Speeding CI builds 2017-12-19 08:16:31 -05:00
dana
162e085b98 Add note about --smart-case smartness 2017-12-18 17:58:26 -05:00
dana
86c890bcec Improve detection of upper-case characters by smart-case feature 
Fixes #717 (partially)

The previous implementation of the smart-case feature was actually *too* smart,
in that it inspected the final character ranges in the AST to determine if the
pattern contained upper-case characters. This meant that patterns like `foo\w`
would not be handled case-insensitively, since `\w` includes the range of
upper-case characters A–Z.

As a medium-term solution to this problem, we now inspect the input pattern
itself for upper-case characters, ignoring any that immediately follow a `\`.
This neatly handles all of the most basic cases like `\w`, `\S`, and `É`, though
it still has problems with more complex features like `\p{Ll}`. Handling those
correctly will require improvements to the AST.
 2017-12-18 17:58:26 -05:00
Lilian A. Moraru
d775259ed9 Add armhf build to Travis CI 
Fixes #676
 2017-12-18 16:26:27 -05:00
dana
d73a75d6cd Omit context separators when using a contextless option like -c or -l 
Fixes #693
 2017-11-29 12:55:42 -05:00
Matthias Krüger
7ae1f373c2 clippy: fix warnings about useless format call and remove references that would be immediately dereferenced by the compiler. 2017-11-22 10:50:28 -05:00
Matthias Krüger
4d34132365 clippy: main.rs: call Clone() on trait instead of ref-counted pointers and pass Arc<Args> by ref more often. 2017-11-22 10:50:28 -05:00
Matthias Krüger
5173bfb11b clippy: docs: put more relevant things into backticks. 2017-11-22 10:50:28 -05:00
Matthias Krüger
8141da9d39 clippy: string constants have static lifetime by default. 2017-11-22 10:50:28 -05:00
Igor Gnatenko
373e0595e6 bump bytecount to 0.2 
Signed-off-by: Igor Gnatenko <i.gnatenko.brain@gmail.com>
 2017-11-22 09:52:47 -05:00
Jonas Stein
1374f15bdf full package name for Gentoo sys-apps/ripgrep 2017-11-22 06:58:43 -05:00
Dan Burkert
263e8f92b9 Update to memmap 0.6 
`memmap` 0.6.0 introduces major API changes in anticipation of a 1.0
release. See https://github.com/danburkert/memmap-rs/releases/tag/0.6.0
for more information. CC danburkert/memmap-rs#33.
 2017-11-22 06:57:15 -05:00
M Pacer
231698f802 switch nb to jupyter 2017-11-22 06:56:30 -05:00
M Pacer
3e8b44619d add notebook file extensions to types 2017-11-22 06:56:30 -05:00
dana
679198e71a Support both [^...] and [!...] for globset class negation 
Adds support for [^...] class negation in globs for parity with git, &al.

Fixes #663
 2017-11-22 06:56:03 -05:00
David Barsky
2c84825ccb Bump Cargo.toml version in ReadMe from 0.2 to 0.3 2017-11-17 17:57:57 -05:00
Zoltan Kalmar
948821753c Add Google Closure Templates type (.soy) 2017-11-16 07:07:56 -05:00
Igor Gnatenko
d2a3b61220 bump crossbeam to 0.3 2017-11-10 13:08:34 -05:00
Jesse Claven
acb57eb4ad Add Protocol Buffer file type. 2017-11-08 08:17:42 -05:00
Reuben D'Netto
256aeb5546 Added example for --colors to README 2017-11-03 06:46:29 -04:00
Francois Ferrand
a9377da624 Support ripgrep-bin installation with linuxbrew 2017-11-01 07:11:52 -04:00
Martin Lindhe
c794ef2f04 fix some typos 2017-11-01 07:10:54 -04:00
Brian Campbell
8b9eba2147 Properly match the rules "**/" and "!**/" 
When processing a rule that ends in a slash, we strip it off and set the
`is_only_dir` flag.  We then apply the rule that paths that aren't
absolute should be given an implicit `**/` prefix, while avoiding
adding that prefix if it already exists.

However, this means that we miss the case in which we had already
stripped off the trailing slash and set `is_only_dir`.  Correct this
by also explicitly checking for that case.

Fixes #649
 2017-11-01 07:10:33 -04:00
Christoph Michelbach
c4732ca012 Correct spelling mistakes in readme file. 2017-11-01 07:09:34 -04:00
Andrew Gallant
1aec4b1123 update brew tap 2017-10-22 11:15:11 -04:00
Andrew Gallant
c4e1945384 cargo: bump to 0.7.1 2017-10-22 10:33:09 -04:00
Andrew Gallant
04d17040e7 changelog 0.7.1 2017-10-22 10:31:42 -04:00
Andrew Gallant
8c8c83a1f8 deps: bump ignore to 0.3.1 2017-10-22 10:31:42 -04:00
Andrew Gallant
5714dbde09 ignore: partially revert symlink loop check optimization 
This optimization wasn't tested too carefully, and it seems to result
in a massive amount of file handles open simultaneously. This is likely
a result of the parallel iterator, where many directories are being
traversed simultaneously.

Fixes #648
 2017-10-22 10:31:34 -04:00
Andrew Gallant
311ccb1f6b update brew tap 2017-10-22 08:08:49 -04:00
Andrew Gallant
efa4de8126 cargo: bump to 0.7.0 2017-10-21 22:40:10 -04:00
Andrew Gallant
ad5fa56490 changelog 0.7.0 2017-10-21 22:40:10 -04:00
Andrew Gallant
1bf9d29259 ignore: be fastidious with file handles 
This commit fixes the symlink loop checker in the parallel directory
traverser to open fewer handles at the expense of keeping handles held
open longer.

This roughly matches the corresponding change in walkdir:
5bcc5b87ee

Fixes #633
 2017-10-21 22:40:10 -04:00
Andrew Gallant
2a14bf2249 printer: fix colors on empty matches 
This fixes a bug where a "match" color escape was erroneously emitted
after the new line character. This is because `^` is actually allowed to
match after the end of a trailing new line, which means `^$` matches both
before and after the trailing new line when multiline mode is enabled.
The trailing match was causing the phantom escape sequence to appear,
which we don't want.

Incidentally, this is the root cause of #441 as well, although this commit
doesn't fix that issue, since the line itself is printed before we detect
the phantom match.

Fixes #599
 2017-10-21 22:40:10 -04:00
Andrew Gallant
f0028a66ec style 2017-10-21 22:40:10 -04:00
Andrew Gallant
08060a2105 deps: update everything 2017-10-21 22:40:09 -04:00
Andrew Gallant
cd575d99f8 ignore: upgrade to walkdir 2 
The uninteresting bits of this commit involve mechanical changes for
updates to walkdir 2. The more interesting bits of this commit are the
breaking changes, although none of them should require any significant
change on users of this library. The breaking changes are as follows:

* `DirEntry::path_is_symbolic_link` has been renamed to
  `DirEntry::path_is_symlink`. This matches the conventions in the
  standard library, and also the corresponding name change in walkdir.
* Removed the `From<walkdir::Error> for ignore::Error` impl. This was
  intended to only be used internally, but was the only thing that
  made `walkdir` a public dependency of `ignore`. Therefore, we remove
  it since it seems unnecessary.
* Renamed `WalkBuilder::sort_by` to `WalkBuilder::sort_by_file_name`,
  and changed the type of the comparator from

    Fn(&OsString, &OsString) -> cmp::Ordering + 'static

  to

    Fn(&OsStr, &OsStr) -> cmp::Ordering + Send + Sync + 'static

  The corresponding change in `walkdir` retains the `sort_by` name, but
  gives the comparator a pair of `&DirEntry` values instead of a pair
  of `&OsStr` values. Ideally, `ignore` would hand off its own pair of
  `&ignore::DirEntry` values, but this requires more design work. So for
  now, we retain previous functionality, but leave room to make a proper
  `sort_by` method.

[breaking-change]
 2017-10-21 22:40:09 -04:00
Andrew Gallant
1267f01c24 deps: upgrade to memchr 2 2017-10-21 22:40:09 -04:00
Andrew Gallant
322d5515e5 style: 80 cols 2017-10-21 22:40:09 -04:00
Shubham Lagwankar
f4770c2094 Fix typos 2017-10-21 22:38:01 -04:00
Evgeny Kulikov
f887bc1f86 printer: --only-matching works with --replace 
When -o/--only-matching is used with -r/--replace, the replacement works
as expected. This is not a breaking change because the flags were
previously set to conflict.
 2017-10-20 20:58:27 -04:00
Sebastian Nowicki
363a4fa9b7 Fix path passed to try_create_bytes() 2017-10-20 20:51:12 -04:00
Sebastian Nowicki
712311fdc6 Don't create command until we know we can test it 
For regression 210 we may not actually need to test anything if the file
system doesn't support creating files with invalid UTF-8 bytes. Don't
create the command until we know there will be an assertion.
 2017-10-20 20:51:12 -04:00
Sebastian Nowicki
0d2354aca6 Wrap comments to 79 columns 2017-10-20 20:51:12 -04:00
Sebastian Nowicki
8dc513b5d2 Skip regression 210 test on APFS 
APFS does not support creating filenames with invalid UTF-8 byte codes,
thus this test doesn't make sense. Skip it on file systems where this
shouldn't be possible.

Fixes #559
 2017-10-20 20:51:12 -04:00
TJ Rana
a98156e71c Fix minor typos 
Update name Mac OS X to macOS
 2017-10-14 07:02:03 -04:00
Trent Davis
cf94072429 State the default case sensitivity 2017-10-12 20:02:33 -04:00
James Smith
db14046de4 Add purescript to built-in types 
Purescript is a functional language that compiles to javascript (https://github.com/purescript/purescript)
 2017-10-12 20:02:25 -04:00
dana
36091591f0 Add troubleshooting notes re: conflicting tools/aliases 2017-10-12 06:40:38 -04:00
Andrew Gallant
12ffcb4296 readme: clarify intro 2017-10-10 18:33:23 -04:00
Antti Keränen
e7c06b92fb Fix printing context after an early return from a search 
Print the context if there's a context left to be printed after
returning early from a search (because of --max-count).

Fixes #402.
 2017-10-08 08:10:35 -04:00
dana
353806b87a Type improvements (config, license, sh, systemd, &c.) 
- Add `license` type for various copyright/licence files
- Add `systemd` type for systemd config/unit files
- Update existing `config`, `jinja`, `json`, `sh`, `sql`, `xml`, `yaml` types
- Minor formatting improvements
 2017-10-08 08:05:28 -04:00
Omer Katz
aebb132a86 Addressed code reivew. 2017-10-08 08:03:00 -04:00
Omer Katz
ab4b6ab9c3 Ripgrep installs from Linuxbrew just fine and works as expected. 
Mentioned it in the README file :)
 2017-10-08 08:03:00 -04:00
Félix Cantournet
413178bc2c Add support for Dockerfiles filtering 2017-10-08 08:02:31 -04:00
dana
58fb4f987e Update README to be more explicit about precompiled binaries (fixes #618) 2017-10-08 08:02:19 -04:00
Benjamin Sago
4f1d6af296 globset README version bump 2017-10-08 08:01:50 -04:00
Daniel Vergeylen
6b79349f83 Rewording README 
Trial to stay consistent with rest of the text.
Rewording by native english.
 2017-10-08 08:01:29 -04:00
Daniel Vergeylen
f858828f61 Update README 
Notify user `cargo install ripgrep` contains debug symbols and informs how to stripe them.
 2017-10-08 08:01:29 -04:00
James McCoy
67b835fe2a Color --replace text using the match type 
Closes #521
 2017-10-08 08:01:11 -04:00
Tri Nguyen
214f2bef66 add support for terraform file type 2017-09-23 11:29:09 -04:00
Christof Marti
1136f8adab Avoid expensive check with --files (fixes #600) 2017-09-18 11:54:48 -04:00
Dan Fabulich
beb010d004 doc: clarify --with-filename behavior with --heading 2017-09-06 08:25:05 -04:00
Andrew Gallant
f9cbf7d3d4 tweak working 2017-09-04 11:15:14 -04:00
Philip Munksgaard
7eb1dd129e Add support for Standard ML file types 2017-09-04 07:26:47 -04:00
Alex Burka
a5f82e8826 ignore: add grouped toggle for standard filters 2017-09-02 12:28:59 -04:00
Jesse Claven
ca6bd648ab Add Elm file type. 2017-08-30 06:46:31 -04:00
Henri Sivonen
af77dd55a2 Update encoding_rs to 0.7.0 2017-08-28 08:14:33 -04:00
Jack O'Connor
3065a8c9c8 restore the default SIGPIPE behavior as a temporary workaround 
See https://github.com/BurntSushi/ripgrep/issues/200.
 2017-08-27 15:01:05 -04:00
Andrew Gallant
208c11af56 deps: bump termcolor in lock file 2017-08-27 11:34:58 -04:00
Andrew Gallant
12a78a992c termcolor-0.3.3 2017-08-27 11:05:55 -04:00
Andrew Gallant
d97c80be63 termcolor: make StandardStream be Send 
This commit fixes a bug where the `StandardStream` type isn't `Send` on
Windows. This can cause some surprising compile breakage, and the only
motivation for it being non-Send was dubious. Namely, it was a result of
trying to eliminate code duplication.

This refactoring also eliminates at least one "unreachable" panic case
that was a result of trying to eliminate code reuse, so that's a nice
benefit as well.

Fixes #503
 2017-08-27 11:05:02 -04:00
Andrew Gallant
5213bd30ea termcolor: 80 cols 2017-08-27 11:05:02 -04:00
Alex Burka
82d101907a ignore: document git_global enabled by default 2017-08-26 14:49:40 -04:00
Andrew Gallant
30608f2444 readme: update minimum version 2017-08-23 23:08:21 -04:00
Andrew Gallant
3d323928a0 update brew tap 2017-08-23 22:04:16 -04:00
Andrew Gallant
8b6a3bc858 ci: unpin nightly, redux 2017-08-23 20:05:27 -04:00
Andrew Gallant
e10544f819 0.6.0 2017-08-23 19:54:50 -04:00
Andrew Gallant
dc7e39a6ba cargo: add crates.io badges 2017-08-23 19:54:33 -04:00
Andrew Gallant
36c16eb00c bump deps 2017-08-23 19:52:13 -04:00
Andrew Gallant
fffee61f80 changelog 0.6.0 2017-08-23 19:49:35 -04:00
Andrew Gallant
4cfb2b515b ci: bump rustc from 1.16 to 1.17 
... and unpin the nightlies.
 2017-08-23 19:49:02 -04:00
Andrew Gallant
398326bfe2 doc: note that ripgrep may terminate unexpectedly 
Fixes #581
 2017-08-23 19:14:27 -04:00
Andrew Gallant
01358a155c man: synchronize man page with --help 2017-08-23 19:13:52 -04:00
Andrew Gallant
30ca3ecca6 ci: strip ripgrep binary on Unix 
This commit strips the ripgrep binary release artifact produced by CI
for Unix.

Fixes #413
 2017-08-23 18:07:41 -04:00
Lilian A. Moraru
dbc91644fd Types extension and Yocto renaming to BitBake 2017-08-23 17:52:24 -04:00
Andrew Gallant
73c9ac4da5 integration tests: ignore regression_428 on Windows 
The test is severely constrained to the specific ANSI formatting of
ripgrep in accordance with its default color scheme. The default color
scheme on Windows changed, which caused the test to fail.

For now, just disable the test on Windows.
 2017-08-23 17:49:40 -04:00
Henri Sivonen
fe7fe74b0a Pass the simd-accel feature to encoding_rs 2017-08-20 08:42:31 -04:00
Gergő Pintér
3d9acdab18 Add short key for julia type 
Fixes #574
 2017-08-16 10:46:13 -04:00
dana
40bacbcd7c Add -x/--line-regexp (#520) 
add -x/--line-regexp flag
 2017-08-09 06:53:35 -04:00
Vurich
b3a9c34515 Remove unused libc dependency 2017-08-08 07:03:58 -04:00
Andrew Gallant
972ec1adc6 bump clap to 2.26 
Fixes #482
 2017-07-30 18:04:49 -04:00
Igor Gnatenko
a2d4c03c71 bump encoding_rs to 0.6 2017-07-30 18:00:50 -04:00
dana
b7c3cf314d Add test for option-arguments with leading hyphens 2017-07-30 17:55:24 -04:00
dana
6dce04963d Allow options with non-numeric arguments to accept leading hyphens in arguments (fixes #568) 2017-07-30 17:55:24 -04:00
dana
d4b790fd8d Install zsh APT package 2017-07-26 09:30:14 -04:00
dana
9283dd122e Update test_complete to source completion function for more reliable options parsing 2017-07-26 09:30:14 -04:00
dana
4c41e9225b Make completion support short-option values in same word; handle debug variable 2017-07-26 09:30:14 -04:00
Leonardo Santagada
9f2b054550 fix profile showing command for powershell 
change the profile showing command to one that matches the microsoft article linked, as its simpler and the old one didn't work at least on windows 10 creators edition.
 2017-07-22 08:53:46 -04:00
dana
5613df3034 Refactor zsh completion function 
- Improve documentation
- Reorganise into functions
- Order options lexicographically
- Correct minor wording inconsistencies
- Fix --count error
- Fix --maxdepth error
- Fix --path-separator error
- Fix --version error
- Adjust exclusivity for --files, -h, -j, -o, -r, -t, -T, -v, -V, &c.
- Improve pattern-operand guard behaviour
- Partially fix issue with colorspec state
- Fix issue with typespec state
- Add completion for <type>:include: sequence
- Move licence info out of the way
 2017-07-18 07:03:36 -04:00
dana
79ad81626f Update test_complete.sh to avoid false positives related to shell syntax 2017-07-18 07:03:36 -04:00
Lincoln Atkinson
354a5cad97 Fix invisible file path text in PowerShell (#557) 
change default path color on Windows

This avoids a conflict with a PowerShell configuration that causes text to be invisible.

Fixes #342
 2017-07-17 18:01:13 -04:00
Andrew Gallant
92e5fad27d ignore-0.2.2 2017-07-17 17:56:33 -04:00
Andrew Gallant
f86f987d71 benchsuite: fix another bug 2017-07-17 09:28:49 -04:00
Andrew Gallant
bfbd53eb92 benchsuite: fix bugs 
This fixes a few bugs in the benchsuite script that have apparently
cropped up over time due to insufficient testing.

Fixes #558
 2017-07-17 08:21:42 -04:00
Behnam Esfahbod
0668c74ed4 [ignore] Fix matched_path_or_any_parents() for patterns ending in slash 
In `matched_path_or_any_parents()` implementation, we missed the point
that when we start walking up the tree, we have to set `is_dir` to
`true`, so path `ROOT/a/b/c` matches pattern `/a/`, although the
original path is not a dir.
 2017-07-13 08:44:09 -04:00
Andrew Gallant
1c03298903 bump ignore version, take 2 2017-07-12 22:26:59 -04:00
Andrew Gallant
e0e8f26c56 bump ignore version 2017-07-12 22:26:23 -04:00
172 changed files with 36053 additions and 25489 deletions
Expand all files Collapse all files

3
.gitignore vendored
View File

@@ -6,6 +6,7 @@ target
/ignore/Cargo.lock
/termcolor/Cargo.lock
/wincolor/Cargo.lock
/deployment
# Snapcraft files
stage
@@ -13,4 +14,4 @@ prime
parts
*.snap
*.pyc
ripgrep*_source.tar.bz2
ripgrep*_source.tar.bz2

116
.travis.yml
View File

@@ -1,74 +1,110 @@
language: rust
dist: xenial
env:
global:
- PROJECT_NAME=ripgrep
- PROJECT_NAME: ripgrep
- RUST_BACKTRACE: full
addons:
apt:
packages:
# For generating man page.
- libxslt1-dev
- asciidoc
- docbook-xsl
- xsltproc
- libxml2-utils
# Needed for completion-function test.
- zsh
# Needed for testing decompression search.
- xz-utils
- liblz4-tool
# For building MUSL static builds on Linux.
- musl-tools
matrix:
fast_finish: true
include:
# Nightly channel.
# (All *nix releases are done on the nightly channel to take advantage
# of the regex library's multiple pattern SIMD search.)
# All *nix releases are done on the nightly channel to take advantage
# of the regex library's multiple pattern SIMD search.
- os: linux
rust: nightly-2017-03-13
rust: nightly
env: TARGET=i686-unknown-linux-musl
- os: linux
rust: nightly-2017-03-13
rust: nightly
env: TARGET=x86_64-unknown-linux-musl
- os: osx
rust: nightly-2017-03-13
env: TARGET=x86_64-apple-darwin
# Beta channel.
rust: nightly
# XML_CATALOG_FILES is apparently necessary for asciidoc on macOS.
env: TARGET=x86_64-apple-darwin XML_CATALOG_FILES=/usr/local/etc/xml/catalog
- os: linux
rust: nightly
env: TARGET=arm-unknown-linux-gnueabihf GCC_VERSION=4.8
addons:
apt:
packages:
- gcc-4.8-arm-linux-gnueabihf
- binutils-arm-linux-gnueabihf
- libc6-armhf-cross
- libc6-dev-armhf-cross
# For generating man page.
- libxslt1-dev
- asciidoc
- docbook-xsl
- xsltproc
- libxml2-utils
# Beta channel. We enable these to make sure there are no regressions in
# Rust beta releases.
- os: linux
rust: beta
env: TARGET=x86_64-unknown-linux-musl
- os: linux
rust: beta
env: TARGET=x86_64-unknown-linux-gnu
# Minimum Rust supported channel.
# Minimum Rust supported channel. We enable these to make sure ripgrep
# continues to work on the advertised minimum Rust version.
- os: linux
rust: 1.12.0
rust: 1.32.0
env: TARGET=x86_64-unknown-linux-gnu
- os: linux
rust: 1.12.0
rust: 1.32.0
env: TARGET=x86_64-unknown-linux-musl
before_install:
- export PATH="$PATH:$HOME/.cargo/bin"
install:
- bash ci/install.sh
script:
- bash ci/script.sh
before_deploy:
- bash ci/before_deploy.sh
- os: linux
rust: 1.32.0
env: TARGET=arm-unknown-linux-gnueabihf GCC_VERSION=4.8
addons:
apt:
packages:
- gcc-4.8-arm-linux-gnueabihf
- binutils-arm-linux-gnueabihf
- libc6-armhf-cross
- libc6-dev-armhf-cross
# For generating man page.
- libxslt1-dev
- asciidoc
- docbook-xsl
- xsltproc
- libxml2-utils
install: ci/install.sh
script: ci/script.sh
before_deploy: ci/before_deploy.sh
deploy:
provider: releases
file_glob: true
file: deployment/${PROJECT_NAME}-${TRAVIS_TAG}-${TARGET}.tar.gz
skip_cleanup: true
on:
condition: $TRAVIS_RUST_VERSION = nightly
branch: master # i guess we do need this after all?
tags: true
api_key:
secure: "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"
file_glob: true
file: ${PROJECT_NAME}-${TRAVIS_TAG}-${TARGET}.*
# don't delete the artifacts from previous phases
skip_cleanup: true
# deploy when a new tag is pushed
on:
# channel to use to produce the release artifacts
# NOTE make sure you only release *once* per target
# TODO you may want to pick a different channel
condition: $TRAVIS_RUST_VERSION = nightly-2017-03-13
tags: true
branches:
only:
# Pushes and PR to the master branch
- master
# IMPORTANT Ruby regex to match tags. Required, or travis won't trigger deploys when a new tag
# is pushed. This regex matches semantic versions like v1.2.3-rc4+2016.02.22
# Ruby regex to match tags. Required, or travis won't trigger deploys when
# a new tag is pushed.
- /^\d+\.\d+\.\d+.*$/
notifications:
email:
on_success: never

549
CHANGELOG.md
View File

@@ -1,3 +1,552 @@
0.11.0 (TBD)
============
TODO.
**BREAKING CHANGES**:
* ripgrep has tweaked its exit status codes to be more like GNU grep's. Namely,
if a non-fatal error occurs during a search, then ripgrep will now always
emit a `2` exit status code, regardless of whether a match is found or not.
Previously, ripgrep would only emit a `2` exit status code for a catastrophic
error (e.g., regex syntax error). One exception to this is if ripgrep is run
with `-q/--quiet`. In that case, if an error occurs and a match is found,
then ripgrep will exit with a `0` exit status code.
* The `avx-accel` feature of ripgrep has been removed since it is no longer
necessary. All uses of AVX in ripgrep are now enabled automatically via
runtime CPU feature detection. The `simd-accel` feature does remain
available, however, it does increase compilation times substantially at the
moment.
Feature enhancements:
* [FEATURE #1099](https://github.com/BurntSushi/ripgrep/pull/1099):
Add support for Brotli and Zstd to the `-z/--search-zip` flag.
* [FEATURE #1138](https://github.com/BurntSushi/ripgrep/pull/1138):
Add `--no-ignore-dot` flag for ignoring `.ignore` files.
* [FEATURE #1159](https://github.com/BurntSushi/ripgrep/pull/1159):
ripgrep's exit status logic should now match GNU grep. See updated man page.
* [FEATURE #1170](https://github.com/BurntSushi/ripgrep/pull/1170):
Add `--ignore-file-case-insensitive` for case insensitive .ignore globs.
Bug fixes:
* [BUG #373](https://github.com/BurntSushi/ripgrep/issues/373),
[BUG #1098](https://github.com/BurntSushi/ripgrep/issues/1098):
`**` is now accepted as valid syntax anywhere in a glob.
* [BUG #916](https://github.com/BurntSushi/ripgrep/issues/916):
ripgrep no longer hangs when searching `/proc` with a zombie process present.
* [BUG #1091](https://github.com/BurntSushi/ripgrep/issues/1091):
Add note about inverted flags to the man page.
* [BUG #1095](https://github.com/BurntSushi/ripgrep/issues/1095):
Fix corner cases involving the `--crlf` flag.
* [BUG #1103](https://github.com/BurntSushi/ripgrep/issues/1103):
Clarify what `--encoding auto` does.
* [BUG #1106](https://github.com/BurntSushi/ripgrep/issues/1106):
`--files-with-matches` and `--files-without-match` work with one file.
* [BUG #1093](https://github.com/BurntSushi/ripgrep/pull/1093):
Fix handling of literal slashes in gitignore patterns.
* [BUG #1121](https://github.com/BurntSushi/ripgrep/issues/1121):
Fix bug that was triggering Windows antimalware when using the --files flag.
* [BUG #1125](https://github.com/BurntSushi/ripgrep/issues/1125),
[BUG #1159](https://github.com/BurntSushi/ripgrep/issues/1159):
ripgrep shouldn't panic for `rg -h | rg` and should emit correct exit status.
* [BUG #1154](https://github.com/BurntSushi/ripgrep/issues/1154):
Windows files with "hidden" attribute are now treated as hidden.
* [BUG #1173](https://github.com/BurntSushi/ripgrep/issues/1173):
Fix handling of `**` patterns in gitignore files.
* [BUG #1174](https://github.com/BurntSushi/ripgrep/issues/1174):
Fix handling of repeated `**` patterns in gitignore files.
* [BUG #1176](https://github.com/BurntSushi/ripgrep/issues/1176):
Fix bug where `-F`/`-x` weren't applied to patterns given via `-f`.
0.10.0 (2018-09-07)
===================
This is a new minor version release of ripgrep that contains some major new
features, a huge number of bug fixes, and is the first release based on
libripgrep. The entirety of ripgrep's core search and printing code has been
rewritten and generalized so that anyone can make use of it.
Major new features include PCRE2 support, multi-line search and a JSON output
format.
**BREAKING CHANGES**:
* The minimum version required to compile Rust has now changed to track the
latest stable version of Rust. Patch releases will continue to compile with
the same version of Rust as the previous patch release, but new minor
versions will use the current stable version of the Rust compile as its
minimum supported version.
* The match semantics of `-w/--word-regexp` have changed slightly. They used
to be `\b(?:<your pattern>)\b`, but now it's
`(?:^|\W)(?:<your pattern>)(?:$|\W)`. This matches the behavior of GNU grep
and is believed to be closer to the intended semantics of the flag. See
[#389](https://github.com/BurntSushi/ripgrep/issues/389) for more details.
Feature enhancements:
* [FEATURE #162](https://github.com/BurntSushi/ripgrep/issues/162):
libripgrep is now a thing. The primary crate is
[`grep`](https://docs.rs/grep).
* [FEATURE #176](https://github.com/BurntSushi/ripgrep/issues/176):
Add `-U/--multiline` flag that permits matching over multiple lines.
* [FEATURE #188](https://github.com/BurntSushi/ripgrep/issues/188):
Add `-P/--pcre2` flag that gives support for look-around and backreferences.
* [FEATURE #244](https://github.com/BurntSushi/ripgrep/issues/244):
Add `--json` flag that prints results in a JSON Lines format.
* [FEATURE #321](https://github.com/BurntSushi/ripgrep/issues/321):
Add `--one-file-system` flag to skip directories on different file systems.
* [FEATURE #404](https://github.com/BurntSushi/ripgrep/issues/404):
Add `--sort` and `--sortr` flag for more sorting. Deprecate `--sort-files`.
* [FEATURE #416](https://github.com/BurntSushi/ripgrep/issues/416):
Add `--crlf` flag to permit `$` to work with carriage returns on Windows.
* [FEATURE #917](https://github.com/BurntSushi/ripgrep/issues/917):
The `--trim` flag strips prefix whitespace from all lines printed.
* [FEATURE #993](https://github.com/BurntSushi/ripgrep/issues/993):
Add `--null-data` flag, which makes ripgrep use NUL as a line terminator.
* [FEATURE #997](https://github.com/BurntSushi/ripgrep/issues/997):
The `--passthru` flag now works with the `--replace` flag.
* [FEATURE #1038-1](https://github.com/BurntSushi/ripgrep/issues/1038):
Add `--line-buffered` and `--block-buffered` for forcing a buffer strategy.
* [FEATURE #1038-2](https://github.com/BurntSushi/ripgrep/issues/1038):
Add `--pre-glob` for filtering files through the `--pre` flag.
Bug fixes:
* [BUG #2](https://github.com/BurntSushi/ripgrep/issues/2):
Searching with non-zero context can now use memory maps if appropriate.
* [BUG #200](https://github.com/BurntSushi/ripgrep/issues/200):
ripgrep will now stop correctly when its output pipe is closed.
* [BUG #389](https://github.com/BurntSushi/ripgrep/issues/389):
The `-w/--word-regexp` flag now works more intuitively.
* [BUG #643](https://github.com/BurntSushi/ripgrep/issues/643):
Detection of readable stdin has improved on Windows.
* [BUG #441](https://github.com/BurntSushi/ripgrep/issues/441),
[BUG #690](https://github.com/BurntSushi/ripgrep/issues/690),
[BUG #980](https://github.com/BurntSushi/ripgrep/issues/980):
Matching empty lines now works correctly in several corner cases.
* [BUG #764](https://github.com/BurntSushi/ripgrep/issues/764):
Color escape sequences now coalesce, which reduces output size.
* [BUG #842](https://github.com/BurntSushi/ripgrep/issues/842):
Add man page to binary Debian package.
* [BUG #922](https://github.com/BurntSushi/ripgrep/issues/922):
ripgrep is now more robust with respect to memory maps failing.
* [BUG #937](https://github.com/BurntSushi/ripgrep/issues/937):
Color escape sequences are no longer emitted for empty matches.
* [BUG #940](https://github.com/BurntSushi/ripgrep/issues/940):
Context from the `--passthru` flag should not impact process exit status.
* [BUG #984](https://github.com/BurntSushi/ripgrep/issues/984):
Fixes bug in `ignore` crate where first path was always treated as a symlink.
* [BUG #990](https://github.com/BurntSushi/ripgrep/issues/990):
Read stderr asynchronously when running a process.
* [BUG #1013](https://github.com/BurntSushi/ripgrep/issues/1013):
Add compile time and runtime CPU features to `--version` output.
* [BUG #1028](https://github.com/BurntSushi/ripgrep/pull/1028):
Don't complete bare pattern after `-f` in zsh.
0.9.0 (2018-08-03)
==================
This is a new minor version release of ripgrep that contains some minor new
features and a panoply of bug fixes.
Releases provided on Github for `x86_64` will now work on all target CPUs, and
will also automatically take advantage of features found on modern CPUs (such
as AVX2) for additional optimizations.
This release increases the **minimum supported Rust version** from 1.20.0 to
1.23.0.
It is anticipated that the next release of ripgrep (0.10.0) will provide
multi-line search support and a JSON output format.
**BREAKING CHANGES**:
* When `--count` and `--only-matching` are provided simultaneously, the
behavior of ripgrep is as if the `--count-matches` flag was given. That is,
the total number of matches is reported, where there may be multiple matches
per line. Previously, the behavior of ripgrep was to report the total number
of matching lines. (Note that this behavior diverges from the behavior of
GNU grep.)
* Octal syntax is no longer supported. ripgrep previously accepted expressions
like `\1` as syntax for matching `U+0001`, but ripgrep will now report an
error instead.
* The `--line-number-width` flag has been removed. Its functionality was not
carefully considered with all ripgrep output formats.
See [#795](https://github.com/BurntSushi/ripgrep/issues/795) for more
details.
Feature enhancements:
* Added or improved file type filtering for Android, Bazel, Fuchsia, Haskell,
Java and Puppet.
* [FEATURE #411](https://github.com/BurntSushi/ripgrep/issues/411):
Add a `--stats` flag, which emits aggregate statistics after search results.
* [FEATURE #646](https://github.com/BurntSushi/ripgrep/issues/646):
Add a `--no-ignore-messages` flag, which suppresses parse errors from reading
`.ignore` and `.gitignore` files.
* [FEATURE #702](https://github.com/BurntSushi/ripgrep/issues/702):
Support `\u{..}` Unicode escape sequences.
* [FEATURE #812](https://github.com/BurntSushi/ripgrep/issues/812):
Add `-b/--byte-offset` flag that shows the byte offset of each matching line.
* [FEATURE #814](https://github.com/BurntSushi/ripgrep/issues/814):
Add `--count-matches` flag, which is like `--count`, but for each match.
* [FEATURE #880](https://github.com/BurntSushi/ripgrep/issues/880):
Add a `--no-column` flag, which disables column numbers in the output.
* [FEATURE #898](https://github.com/BurntSushi/ripgrep/issues/898):
Add support for `lz4` when using the `-z/--search-zip` flag.
* [FEATURE #924](https://github.com/BurntSushi/ripgrep/issues/924):
`termcolor` has moved to its own repository:
https://github.com/BurntSushi/termcolor
* [FEATURE #934](https://github.com/BurntSushi/ripgrep/issues/934):
Add a new flag, `--no-ignore-global`, that permits disabling global
gitignores.
* [FEATURE #967](https://github.com/BurntSushi/ripgrep/issues/967):
Rename `--maxdepth` to `--max-depth` for consistency. Keep `--maxdepth` for
backwards compatibility.
* [FEATURE #978](https://github.com/BurntSushi/ripgrep/issues/978):
Add a `--pre` option to filter inputs with an arbitrary program.
* [FEATURE fca9709d](https://github.com/BurntSushi/ripgrep/commit/fca9709d):
Improve zsh completion.
Bug fixes:
* [BUG #135](https://github.com/BurntSushi/ripgrep/issues/135):
Release portable binaries that conditionally use SSSE3, AVX2, etc., at
runtime.
* [BUG #268](https://github.com/BurntSushi/ripgrep/issues/268):
Print descriptive error message when trying to use look-around or
backreferences.
* [BUG #395](https://github.com/BurntSushi/ripgrep/issues/395):
Show comprehensible error messages for regexes like `\s*{`.
* [BUG #526](https://github.com/BurntSushi/ripgrep/issues/526):
Support backslash escapes in globs.
* [BUG #795](https://github.com/BurntSushi/ripgrep/issues/795):
Fix problems with `--line-number-width` by removing it.
* [BUG #832](https://github.com/BurntSushi/ripgrep/issues/832):
Clarify usage instructions for `-f/--file` flag.
* [BUG #835](https://github.com/BurntSushi/ripgrep/issues/835):
Fix small performance regression while crawling very large directory trees.
* [BUG #851](https://github.com/BurntSushi/ripgrep/issues/851):
Fix `-S/--smart-case` detection once and for all.
* [BUG #852](https://github.com/BurntSushi/ripgrep/issues/852):
Be robust with respect to `ENOMEM` errors returned by `mmap`.
* [BUG #853](https://github.com/BurntSushi/ripgrep/issues/853):
Upgrade `grep` crate to `regex-syntax 0.6.0`.
* [BUG #893](https://github.com/BurntSushi/ripgrep/issues/893):
Improve support for git submodules.
* [BUG #900](https://github.com/BurntSushi/ripgrep/issues/900):
When no patterns are given, ripgrep should never match anything.
* [BUG #907](https://github.com/BurntSushi/ripgrep/issues/907):
ripgrep will now stop traversing after the first file when `--quiet --files`
is used.
* [BUG #918](https://github.com/BurntSushi/ripgrep/issues/918):
Don't skip tar archives when `-z/--search-zip` is used.
* [BUG #934](https://github.com/BurntSushi/ripgrep/issues/934):
Don't respect gitignore files when searching outside git repositories.
* [BUG #948](https://github.com/BurntSushi/ripgrep/issues/948):
Use exit code 2 to indicate error, and use exit code 1 to indicate no
matches.
* [BUG #951](https://github.com/BurntSushi/ripgrep/issues/951):
Add stdin example to ripgrep usage documentation.
* [BUG #955](https://github.com/BurntSushi/ripgrep/issues/955):
Use buffered writing when not printing to a tty, which fixes a performance
regression.
* [BUG #957](https://github.com/BurntSushi/ripgrep/issues/957):
Improve the error message shown for `--path separator /` in some Windows
shells.
* [BUG #964](https://github.com/BurntSushi/ripgrep/issues/964):
Add a `--no-fixed-strings` flag to disable `-F/--fixed-strings`.
* [BUG #988](https://github.com/BurntSushi/ripgrep/issues/988):
Fix a bug in the `ignore` crate that prevented the use of explicit ignore
files after disabling all other ignore rules.
* [BUG #995](https://github.com/BurntSushi/ripgrep/issues/995):
Respect `$XDG_CONFIG_DIR/git/config` for detecting `core.excludesFile`.
0.8.1 (2018-02-20)
==================
This is a patch release of ripgrep that primarily fixes regressions introduced
in 0.8.0 (#820 and #824) in directory traversal on Windows. These regressions
do not impact non-Windows users.
Feature enhancements:
* Added or improved file type filtering for csv and VHDL.
* [FEATURE #798](https://github.com/BurntSushi/ripgrep/issues/798):
Add `underline` support to `termcolor` and ripgrep. See documentation on the
`--colors` flag for details.
Bug fixes:
* [BUG #684](https://github.com/BurntSushi/ripgrep/issues/684):
Improve documentation for the `--ignore-file` flag.
* [BUG #789](https://github.com/BurntSushi/ripgrep/issues/789):
Don't show `(rev )` if the revision wasn't available during the build.
* [BUG #791](https://github.com/BurntSushi/ripgrep/issues/791):
Add man page to ARM release.
* [BUG #797](https://github.com/BurntSushi/ripgrep/issues/797):
Improve documentation for "intense" setting in `termcolor`.
* [BUG #800](https://github.com/BurntSushi/ripgrep/issues/800):
Fix a bug in the `ignore` crate for custom ignore files. This had no impact
on ripgrep.
* [BUG #807](https://github.com/BurntSushi/ripgrep/issues/807):
Fix a bug where `rg --hidden .` behaved differently from `rg --hidden ./`.
* [BUG #815](https://github.com/BurntSushi/ripgrep/issues/815):
Clarify a common failure mode in user guide.
* [BUG #820](https://github.com/BurntSushi/ripgrep/issues/820):
Fixes a bug on Windows where symlinks were followed even if not requested.
* [BUG #824](https://github.com/BurntSushi/ripgrep/issues/824):
Fix a performance regression in directory traversal on Windows.
0.8.0 (2018-02-11)
==================
This is a new minor version releae of ripgrep that satisfies several popular
feature requests (config files, search compressed files, true colors), fixes
many bugs and improves the quality of life for ripgrep maintainers. This
release also includes greatly improved documentation in the form of a
[User Guide](GUIDE.md) and a [FAQ](FAQ.md).
This release increases the **minimum supported Rust version** from 1.17 to
1.20.
**BREAKING CHANGES**:
Note that these are all very minor and unlikely to impact most users.
* In order to support configuration files, flag overrides needed to be
rethought. In some cases, this changed ripgrep's behavior. For example,
in ripgrep 0.7.1, `rg foo -s -i` will perform a case sensitive search
since the `-s/--case-sensitive` flag was defined to always take precedence
over the `-i/--ignore-case` flag, regardless of position. In ripgrep 0.8.0
however, the override rule for all flags has changed to "the most recent
flag wins among competing flags." That is, `rg foo -s -i` now performs a
case insensitive search.
* The `-M/--max-columns` flag was tweaked so that specifying a value of `0`
now makes ripgrep behave as if the flag was absent. This makes it possible
to set a default value in a configuration file and then override it. The
previous ripgrep behavior was to suppress all matching non-empty lines.
* In all globs, `[^...]` is now equivalent to `[!...]` (indicating class
negation). Previously, `^` had no special significance in a character class.
* For **downstream packagers**, the directory hierarchy in ripgrep's archive
releases has changed. The root directory now only contains the executable,
README and license. There is now a new directory called `doc` which contains
the man page (previously in the root), a user guide (new), a FAQ (new) and
the CHANGELOG (previously not included in release). The `complete`
directory remains the same.
Feature enhancements:
* Added or improved file type filtering for
Apache Avro, C++, GN, Google Closure Templates, Jupyter notebooks, man pages,
Protocol Buffers, Smarty and Web IDL.
* [FEATURE #196](https://github.com/BurntSushi/ripgrep/issues/196):
Support a configuration file. See
[the new user guide](GUIDE.md#configuration-file)
for details.
* [FEATURE #261](https://github.com/BurntSushi/ripgrep/issues/261):
Add extended or "true" color support. Works in Windows 10!
[See the FAQ for details.](FAQ.md#colors)
* [FEATURE #539](https://github.com/BurntSushi/ripgrep/issues/539):
Search gzip, bzip2, lzma or xz files when given `-z/--search-zip` flag.
* [FEATURE #544](https://github.com/BurntSushi/ripgrep/issues/544):
Add support for line number alignment via a new `--line-number-width` flag.
* [FEATURE #654](https://github.com/BurntSushi/ripgrep/pull/654):
Support linuxbrew in ripgrep's Brew tap.
* [FEATURE #673](https://github.com/BurntSushi/ripgrep/issues/673):
Bring back `.rgignore` files. (A higher precedent, application specific
version of `.ignore`.)
* [FEATURE #676](https://github.com/BurntSushi/ripgrep/issues/676):
Provide ARM binaries. **WARNING:** This will be provided on a best effort
basis.
* [FEATURE #709](https://github.com/BurntSushi/ripgrep/issues/709):
Suggest `-F/--fixed-strings` flag on a regex syntax error.
* [FEATURE #740](https://github.com/BurntSushi/ripgrep/issues/740):
Add a `--passthru` flag that causes ripgrep to print every line it reads.
* [FEATURE #785](https://github.com/BurntSushi/ripgrep/pull/785):
Overhaul documentation. Cleaned up README, added user guide and FAQ.
* [FEATURE 7f5c07](https://github.com/BurntSushi/ripgrep/commit/7f5c07434be92103b5bf7e216b9c7494aed2d8cb):
Add hidden flags for convenient overrides (e.g., `--no-text`).
Bug fixes:
* [BUG #553](https://github.com/BurntSushi/ripgrep/issues/553):
Permit flags to be repeated.
* [BUG #633](https://github.com/BurntSushi/ripgrep/issues/633):
Fix a bug where ripgrep would panic on Windows while following symlinks.
* [BUG #649](https://github.com/BurntSushi/ripgrep/issues/649):
Fix handling of `!**/` in `.gitignore`.
* [BUG #663](https://github.com/BurntSushi/ripgrep/issues/663):
**BREAKING CHANGE:** Support `[^...]` glob syntax (as identical to `[!...]`).
* [BUG #693](https://github.com/BurntSushi/ripgrep/issues/693):
Don't display context separators when not printing matches.
* [BUG #705](https://github.com/BurntSushi/ripgrep/issues/705):
Fix a bug that prevented ripgrep from searching OneDrive directories.
* [BUG #717](https://github.com/BurntSushi/ripgrep/issues/717):
Improve `--smart-case` uppercase character detection.
* [BUG #725](https://github.com/BurntSushi/ripgrep/issues/725):
Clarify that globs do not override explicitly given paths to search.
* [BUG #742](https://github.com/BurntSushi/ripgrep/pull/742):
Write ANSI reset code as `\x1B[0m` instead of `\x1B[m`.
* [BUG #747](https://github.com/BurntSushi/ripgrep/issues/747):
Remove `yarn.lock` from YAML file type.
* [BUG #760](https://github.com/BurntSushi/ripgrep/issues/760):
ripgrep can now search `/sys/devices/system/cpu/vulnerabilities/*` files.
* [BUG #761](https://github.com/BurntSushi/ripgrep/issues/761):
Fix handling of gitignore patterns that contain a `/`.
* [BUG #776](https://github.com/BurntSushi/ripgrep/pull/776):
**BREAKING CHANGE:** `--max-columns=0` now disables the limit.
* [BUG #779](https://github.com/BurntSushi/ripgrep/issues/779):
Clarify documentation for `--files-without-match`.
* [BUG #780](https://github.com/BurntSushi/ripgrep/issues/780),
[BUG #781](https://github.com/BurntSushi/ripgrep/issues/781):
Fix bug where ripgrep missed some matching lines.
Maintenance fixes:
* [MAINT #772](https://github.com/BurntSushi/ripgrep/pull/772):
Drop `env_logger` in favor of simpler logger to avoid many new dependencies.
* [MAINT #772](https://github.com/BurntSushi/ripgrep/pull/772):
Add git revision hash to ripgrep's version string.
* [MAINT #772](https://github.com/BurntSushi/ripgrep/pull/772):
(Seemingly) improve compile times.
* [MAINT #776](https://github.com/BurntSushi/ripgrep/pull/776):
Automatically generate man page during build.
* [MAINT #786](https://github.com/BurntSushi/ripgrep/pull/786):
Remove use of `unsafe` in `globset`. :tada:
* [MAINT e9d448](https://github.com/BurntSushi/ripgrep/commit/e9d448e93bb4e1fb3b0c1afc29adb5af6ed5283d):
Add an issue template (has already drastically improved bug reports).
* [MAINT ae2d03](https://github.com/BurntSushi/ripgrep/commit/ae2d036dd4ba2a46acac9c2d77c32e7c667eb850):
Remove the `compile` script.
Friends of ripgrep:
I'd like to extend my gratitude to
[@balajisivaraman](https://github.com/balajisivaraman)
for their recent hard work in a number of areas, and in particular, for
implementing the "search compressed files" feature. Their work in sketching out
a specification for that and other work has been exemplary.
Thanks
[@balajisivaraman](https://github.com/balajisivaraman)!
0.7.1 (2017-10-22)
==================
This is a patch release of ripgrep that includes a fix to very bad regression
introduced in ripgrep 0.7.0.
Bug fixes:
* [BUG #648](https://github.com/BurntSushi/ripgrep/issues/648):
Fix a bug where it was very easy to exceed standard file descriptor limits.
0.7.0 (2017-10-20)
==================
This is a new minor version release of ripgrep that includes mostly bug fixes.
ripgrep continues to require Rust 1.17, and there are no known breaking changes
introduced in this release.
Feature enhancements:
* Added or improved file type filtering for config & license files, Elm,
Purescript, Standard ML, sh, systemd, Terraform
* [FEATURE #593](https://github.com/BurntSushi/ripgrep/pull/593):
Using both `-o/--only-matching` and `-r/--replace` does the right thing.
Bug fixes:
* [BUG #200](https://github.com/BurntSushi/ripgrep/issues/200):
ripgrep will stop when its pipe is closed.
* [BUG #402](https://github.com/BurntSushi/ripgrep/issues/402):
Fix context printing bug when the `-m/--max-count` flag is used.
* [BUG #521](https://github.com/BurntSushi/ripgrep/issues/521):
Fix interaction between `-r/--replace` and terminal colors.
* [BUG #559](https://github.com/BurntSushi/ripgrep/issues/559):
Ignore test that tried reading a non-UTF-8 file path on macOS.
* [BUG #599](https://github.com/BurntSushi/ripgrep/issues/599):
Fix color escapes on empty matches.
* [BUG #600](https://github.com/BurntSushi/ripgrep/issues/600):
Avoid expensive (on Windows) file handle check when using --files.
* [BUG #618](https://github.com/BurntSushi/ripgrep/issues/618):
Clarify installation instructions for Ubuntu users.
* [BUG #633](https://github.com/BurntSushi/ripgrep/issues/633):
Faster symlink loop checking on Windows.
0.6.0 (2017-08-23)
==================
This is a new minor version release of ripgrep that includes many bug fixes
and a few new features such as `--iglob` and `-x/--line-regexp`.
Note that this release increases the minimum supported Rust version from 1.12
to 1.17.
Feature enhancements:
* Added or improved file type filtering for BitBake, C++, Cabal, cshtml, Julia,
Make, msbuild, QMake, Yocto
* [FEATURE #163](https://github.com/BurntSushi/ripgrep/issues/163):
Add an `--iglob` flag that is like `-g/--glob`, but matches globs
case insensitively.
* [FEATURE #520](https://github.com/BurntSushi/ripgrep/pull/518):
Add `-x/--line-regexp` flag, which requires a match to span an entire line.
* [FEATURE #551](https://github.com/BurntSushi/ripgrep/pull/551),
[FEATURE #554](https://github.com/BurntSushi/ripgrep/pull/554):
`ignore`: add new `matched_path_or_any_parents` method.
Bug fixes:
* [BUG #342](https://github.com/BurntSushi/ripgrep/issues/342):
Fix invisible text in some PowerShell environments by changing the
default color scheme on Windows.
* [BUG #413](https://github.com/BurntSushi/ripgrep/issues/413):
Release binaries on Unix are now `strip`'d by default. This decreases
binary size by an order of magnitude.
* [BUG #483](https://github.com/BurntSushi/ripgrep/issues/483):
When `--quiet` is passed, `--files` should be quiet.
* [BUG #488](https://github.com/BurntSushi/ripgrep/pull/488):
When `--vimgrep` is passed, `--with-filename` should be enabled
automatically.
* [BUG #493](https://github.com/BurntSushi/ripgrep/issues/493):
Fix another bug in the implementation of the `-o/--only-matching`
flag.
* [BUG #499](https://github.com/BurntSushi/ripgrep/pull/499):
Permit certain flags to override others.
* [BUG #523](https://github.com/BurntSushi/ripgrep/pull/523):
`wincolor`: Re-fetch Windows console on all calls.
* [BUG #523](https://github.com/BurntSushi/ripgrep/issues/524):
`--version` now shows enabled compile-time features.
* [BUG #532](https://github.com/BurntSushi/ripgrep/issues/532),
[BUG #536](https://github.com/BurntSushi/ripgrep/pull/536),
[BUG #538](https://github.com/BurntSushi/ripgrep/pull/538),
[BUG #540](https://github.com/BurntSushi/ripgrep/pull/540),
[BUG #560](https://github.com/BurntSushi/ripgrep/pull/560),
[BUG #565](https://github.com/BurntSushi/ripgrep/pull/565):
Improve zsh completion.
* [BUG #578](https://github.com/BurntSushi/ripgrep/pull/578):
Enable SIMD for `encoding_rs` when appropriate.
* [BUG #580](https://github.com/BurntSushi/ripgrep/issues/580):
Fix `-w/--word-regexp` in the presence of capturing groups.
* [BUG #581](https://github.com/BurntSushi/ripgrep/issues/581):
Document that ripgrep may terminate unexpectedly when searching via
memory maps (which can happen using default settings).
Friends of ripgrep:
I'd like to give a big Thank You to @okdana for their recent hard work on
ripgrep. This includes new features like `--line-regexp`, heroic effort on
zsh auto-completion and thinking through some thorny argv issues with me.
I'd also like to thank @ericbn for their work on improving ripgrep's argv
parsing by allowing some flags to override others.
Thanks @okdana and @ericbn!
0.5.2 (2017-05-11)
==================
Feature enhancements:

785
Cargo.lock generated
View File

@@ -1,370 +1,763 @@
[root]
name = "ripgrep"
version = "0.5.2"
dependencies = [
"atty 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"bytecount 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"clap 2.24.1 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
"env_logger 0.4.2 (registry+https://github.com/rust-lang/crates.io-index)",
"grep 0.1.6",
"ignore 0.2.0",
"lazy_static 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"memmap 0.5.2 (registry+https://github.com/rust-lang/crates.io-index)",
"num_cpus 1.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 0.3.2",
]
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
[[package]]
name = "aho-corasick"
version = "0.6.3"
version = "0.7.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ansi_term"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "atty"
version = "0.2.2"
version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"termion 1.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "autocfg"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "base64"
version = "0.10.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"byteorder 1.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "bitflags"
version = "0.8.2"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "bytecount"
version = "0.1.6"
name = "bstr"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"simd 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-automata 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "bytecount"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "byteorder"
version = "1.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "cc"
version = "1.0.34"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "cfg-if"
version = "0.1.0"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "clap"
version = "2.24.1"
version = "2.33.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"ansi_term 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)",
"atty 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"bitflags 0.8.2 (registry+https://github.com/rust-lang/crates.io-index)",
"strsim 0.6.0 (registry+https://github.com/rust-lang/crates.io-index)",
"term_size 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-segmentation 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-width 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)",
"vec_map 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)",
"bitflags 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"strsim 0.8.0 (registry+https://github.com/rust-lang/crates.io-index)",
"textwrap 0.11.0 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-width 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "crossbeam"
version = "0.2.10"
name = "cloudabi"
version = "0.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"bitflags 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "crossbeam-channel"
version = "0.3.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"crossbeam-utils 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)",
"smallvec 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "crossbeam-utils"
version = "0.6.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding_rs"
version = "0.5.1"
version = "0.8.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"packed_simd 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "env_logger"
version = "0.4.2"
name = "encoding_rs_io"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs 0.8.17 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "fnv"
version = "1.0.5"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "fs2"
version = "0.4.1"
name = "fuchsia-cprng"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "glob"
version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "globset"
version = "0.2.0"
version = "0.4.2"
dependencies = [
"aho-corasick 0.6.3 (registry+https://github.com/rust-lang/crates.io-index)",
"fnv 1.0.5 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"aho-corasick 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"fnv 1.0.6 (registry+https://github.com/rust-lang/crates.io-index)",
"glob 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep"
version = "0.1.6"
version = "0.2.3"
dependencies = [
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)",
"grep-cli 0.1.1",
"grep-matcher 0.1.1",
"grep-pcre2 0.1.2",
"grep-printer 0.1.1",
"grep-regex 0.1.2",
"grep-searcher 0.1.3",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"walkdir 2.2.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-cli"
version = "0.1.1"
dependencies = [
"atty 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"globset 0.4.2",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-matcher"
version = "0.1.1"
dependencies = [
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-pcre2"
version = "0.1.2"
dependencies = [
"grep-matcher 0.1.1",
"pcre2 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-printer"
version = "0.1.1"
dependencies = [
"base64 0.10.1 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"grep-matcher 0.1.1",
"grep-regex 0.1.2",
"grep-searcher 0.1.3",
"serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_derive 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_json 1.0.39 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-regex"
version = "0.1.2"
dependencies = [
"grep-matcher 0.1.1",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.6.6 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"utf8-ranges 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-searcher"
version = "0.1.3"
dependencies = [
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"bytecount 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs 0.8.17 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs_io 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"grep-matcher 0.1.1",
"grep-regex 0.1.2",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"memmap 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ignore"
version = "0.2.0"
version = "0.4.6"
dependencies = [
"crossbeam 0.2.10 (registry+https://github.com/rust-lang/crates.io-index)",
"globset 0.2.0",
"lazy_static 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
"walkdir 1.0.7 (registry+https://github.com/rust-lang/crates.io-index)",
"crossbeam-channel 0.3.8 (registry+https://github.com/rust-lang/crates.io-index)",
"globset 0.4.2",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"tempfile 3.0.7 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"walkdir 2.2.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "kernel32-sys"
version = "0.2.2"
name = "itoa"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-build 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "lazy_static"
version = "0.2.8"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "libc"
version = "0.2.23"
version = "0.2.51"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "log"
version = "0.3.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "memchr"
version = "1.0.1"
version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "memchr"
version = "2.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "memmap"
version = "0.5.2"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"fs2 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)",
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "num_cpus"
version = "1.4.0"
version = "1.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "packed_simd"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "pcre2"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"pcre2-sys 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "pcre2-sys"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cc 1.0.34 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"pkg-config 0.3.14 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "pkg-config"
version = "0.3.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "proc-macro2"
version = "0.4.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "quote"
version = "0.6.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand"
version = "0.6.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_chacha 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_hc 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_isaac 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_jitter 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_os 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_pcg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_xorshift 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_chacha"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_core"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_core"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "rand_hc"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_isaac"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_jitter"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_os"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cloudabi 0.0.3 (registry+https://github.com/rust-lang/crates.io-index)",
"fuchsia-cprng 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rdrand 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_pcg"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_xorshift"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rdrand"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "redox_syscall"
version = "0.1.52"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "redox_termios"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex"
version = "0.2.2"
version = "1.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"aho-corasick 0.6.3 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)",
"simd 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
"utf8-ranges 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
"aho-corasick 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.6.6 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"utf8-ranges 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex-automata"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"byteorder 1.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex-syntax"
version = "0.4.1"
version = "0.6.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"ucd-util 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "remove_dir_all"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ripgrep"
version = "0.10.0"
dependencies = [
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"clap 2.33.0 (registry+https://github.com/rust-lang/crates.io-index)",
"grep 0.2.3",
"ignore 0.4.6",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"num_cpus 1.10.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_derive 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_json 1.0.39 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ryu"
version = "0.2.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "same-file"
version = "0.1.3"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "simd"
version = "0.1.1"
name = "serde"
version = "1.0.90"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "serde_derive"
version = "1.0.90"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 0.6.11 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 0.15.30 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "serde_json"
version = "1.0.39"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"itoa 0.4.3 (registry+https://github.com/rust-lang/crates.io-index)",
"ryu 0.2.7 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "smallvec"
version = "0.6.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "strsim"
version = "0.6.0"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "term_size"
version = "0.3.0"
name = "syn"
version = "0.15.30"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 0.6.11 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "tempfile"
version = "3.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"rand 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)",
"remove_dir_all 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "termcolor"
version = "0.3.2"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"wincolor 0.1.4",
"wincolor 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "thread-id"
version = "3.1.0"
name = "termion"
version = "1.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_termios 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "textwrap"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"unicode-width 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "thread_local"
version = "0.3.3"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"thread-id 3.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"unreachable 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "unicode-segmentation"
version = "1.1.0"
name = "ucd-util"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "unicode-width"
version = "0.1.4"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "unreachable"
version = "0.1.1"
name = "unicode-xid"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "utf8-ranges"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "vec_map"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "void"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "walkdir"
version = "1.0.7"
version = "2.2.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "winapi"
version = "0.2.8"
version = "0.3.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi-i686-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-x86_64-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "winapi-build"
version = "0.1.1"
name = "winapi-util"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "wincolor"
version = "0.1.4"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[metadata]
"checksum aho-corasick 0.6.3 (registry+https://github.com/rust-lang/crates.io-index)" = "500909c4f87a9e52355b26626d890833e9e1d53ac566db76c36faa984b889699"
"checksum ansi_term 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "23ac7c30002a5accbf7e8987d0632fa6de155b7c3d39d0067317a391e00a2ef6"
"checksum atty 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)" = "d912da0db7fa85514874458ca3651fe2cddace8d0b0505571dbdcd41ab490159"
"checksum bitflags 0.8.2 (registry+https://github.com/rust-lang/crates.io-index)" = "1370e9fc2a6ae53aea8b7a5110edbd08836ed87c88736dfabccade1c2b44bff4"
"checksum bytecount 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)" = "1e8f09fbc8c6726a4b616dcfbd4f54491068d6bb1b93ac03c78ac18ff9a5924a"
"checksum cfg-if 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "de1e760d7b6535af4241fca8bd8adf68e2e7edacc6b29f5d399050c5e48cf88c"
"checksum clap 2.24.1 (registry+https://github.com/rust-lang/crates.io-index)" = "b7541069be0b8aec41030802abe8b5cdef0490070afaa55418adea93b1e431e0"
"checksum crossbeam 0.2.10 (registry+https://github.com/rust-lang/crates.io-index)" = "0c5ea215664ca264da8a9d9c3be80d2eaf30923c259d03e870388eb927508f97"
"checksum encoding_rs 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)" = "e4bc519d572af08cf72c4d61e0de9b05e9fa66d1fdb5e739fb5c405860b42d43"
"checksum env_logger 0.4.2 (registry+https://github.com/rust-lang/crates.io-index)" = "e3856f1697098606fc6cb97a93de88ca3f3bc35bb878c725920e6e82ecf05e83"
"checksum fnv 1.0.5 (registry+https://github.com/rust-lang/crates.io-index)" = "6cc484842f1e2884faf56f529f960cc12ad8c71ce96cc7abba0a067c98fee344"
"checksum fs2 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)" = "34edaee07555859dc13ca387e6ae05686bb4d0364c95d649b6dab959511f4baf"
"checksum kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)" = "7507624b29483431c0ba2d82aece8ca6cdba9382bff4ddd0f7490560c056098d"
"checksum lazy_static 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)" = "3b37545ab726dd833ec6420aaba8231c5b320814b9029ad585555d2a03e94fbf"
"checksum libc 0.2.23 (registry+https://github.com/rust-lang/crates.io-index)" = "e7eb6b826bfc1fdea7935d46556250d1799b7fe2d9f7951071f4291710665e3e"
"checksum log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)" = "5141eca02775a762cc6cd564d8d2c50f67c0ea3a372cbf1c51592b3e029e10ad"
"checksum memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)" = "1dbccc0e46f1ea47b9f17e6d67c5a96bd27030519c519c9c91327e31275a47b4"
"checksum memmap 0.5.2 (registry+https://github.com/rust-lang/crates.io-index)" = "46f3c7359028b31999287dae4e5047ddfe90a23b7dca2282ce759b491080c99b"
"checksum num_cpus 1.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "ca313f1862c7ec3e0dfe8ace9fa91b1d9cb5c84ace3d00f5ec4216238e93c167"
"checksum regex 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)" = "1731164734096285ec2a5ec7fea5248ae2f5485b3feeb0115af4fda2183b2d1b"
"checksum regex-syntax 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)" = "ad890a5eef7953f55427c50575c680c42841653abd2b028b68cd223d157f62db"
"checksum same-file 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "d931a44fdaa43b8637009e7632a02adc4f2b2e0733c08caa4cf00e8da4a117a7"
"checksum simd 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "63b5847c2d766ca7ce7227672850955802fabd779ba616aeabead4c2c3877023"
"checksum strsim 0.6.0 (registry+https://github.com/rust-lang/crates.io-index)" = "b4d15c810519a91cf877e7e36e63fe068815c678181439f2f29e2562147c3694"
"checksum term_size 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "e2b6b55df3198cc93372e85dd2ed817f0e38ce8cc0f22eb32391bfad9c4bf209"
"checksum thread-id 3.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "8df7875b676fddfadffd96deea3b1124e5ede707d4884248931077518cf1f773"
"checksum thread_local 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "c85048c6260d17cf486ceae3282d9fb6b90be220bf5b28c400f5485ffc29f0c7"
"checksum unicode-segmentation 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "18127285758f0e2c6cf325bb3f3d138a12fee27de4f23e146cd6a179f26c2cf3"
"checksum unicode-width 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)" = "bf3a113775714a22dcb774d8ea3655c53a32debae63a063acc00a91cc586245f"
"checksum unreachable 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "1f2ae5ddb18e1c92664717616dd9549dde73f539f01bd7b77c2edb2446bdff91"
"checksum utf8-ranges 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "662fab6525a98beff2921d7f61a39e7d59e0b425ebc7d0d9e66d316e55124122"
"checksum vec_map 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)" = "f8cdc8b93bd0198ed872357fb2e667f7125646b1762f16d60b2c96350d361897"
"checksum void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "6a02e4885ed3bc0f2de90ea6dd45ebcbb66dacffe03547fadbb0eeae2770887d"
"checksum walkdir 1.0.7 (registry+https://github.com/rust-lang/crates.io-index)" = "bb08f9e670fab86099470b97cd2b252d6527f0b3cc1401acdb595ffc9dd288ff"
"checksum winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)" = "167dc9d6949a9b857f3451275e911c3f44255842c1f7a76f33c55103a909087a"
"checksum winapi-build 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "2d315eee3b34aca4797b2da6b13ed88266e6d612562a0c46390af8299fc699bc"
"checksum aho-corasick 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)" = "e6f484ae0c99fec2e858eb6134949117399f222608d84cadb3f58c1f97c2364c"
"checksum atty 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)" = "9a7d5b8723950951411ee34d271d99dddcc2035a16ab25310ea2c8cfd4369652"
"checksum autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "a6d640bee2da49f60a4068a7fae53acde8982514ab7bae8b8cea9e88cbcfd799"
"checksum base64 0.10.1 (registry+https://github.com/rust-lang/crates.io-index)" = "0b25d992356d2eb0ed82172f5248873db5560c4721f564b13cb5193bda5e668e"
"checksum bitflags 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)" = "228047a76f468627ca71776ecdebd732a3423081fcf5125585bcd7c49886ce12"
"checksum bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "6c8203ca06c502958719dae5f653a79e0cc6ba808ed02beffbf27d09610f2143"
"checksum bytecount 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)" = "be0fdd54b507df8f22012890aadd099979befdba27713c767993f8380112ca7c"
"checksum byteorder 1.3.1 (registry+https://github.com/rust-lang/crates.io-index)" = "a019b10a2a7cdeb292db131fc8113e57ea2a908f6e7894b0c3c671893b65dbeb"
"checksum cc 1.0.34 (registry+https://github.com/rust-lang/crates.io-index)" = "30f813bf45048a18eda9190fd3c6b78644146056740c43172a5a3699118588fd"
"checksum cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)" = "11d43355396e872eefb45ce6342e4374ed7bc2b3a502d1b28e36d6e23c05d1f4"
"checksum clap 2.33.0 (registry+https://github.com/rust-lang/crates.io-index)" = "5067f5bb2d80ef5d68b4c87db81601f0b75bca627bc2ef76b141d7b846a3c6d9"
"checksum cloudabi 0.0.3 (registry+https://github.com/rust-lang/crates.io-index)" = "ddfc5b9aa5d4507acaf872de71051dfd0e309860e88966e1051e462a077aac4f"
"checksum crossbeam-channel 0.3.8 (registry+https://github.com/rust-lang/crates.io-index)" = "0f0ed1a4de2235cabda8558ff5840bffb97fcb64c97827f354a451307df5f72b"
"checksum crossbeam-utils 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)" = "f8306fcef4a7b563b76b7dd949ca48f52bc1141aa067d2ea09565f3e2652aa5c"
"checksum encoding_rs 0.8.17 (registry+https://github.com/rust-lang/crates.io-index)" = "4155785c79f2f6701f185eb2e6b4caf0555ec03477cb4c70db67b465311620ed"
"checksum encoding_rs_io 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)" = "9619ee7a2bf4e777e020b95c1439abaf008f8ea8041b78a0552c4f1bcf4df32c"
"checksum fnv 1.0.6 (registry+https://github.com/rust-lang/crates.io-index)" = "2fad85553e09a6f881f739c29f0b00b0f01357c743266d478b68951ce23285f3"
"checksum fuchsia-cprng 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "a06f77d526c1a601b7c4cdd98f54b5eaabffc14d5f2f0296febdc7f357c6d3ba"
"checksum glob 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)" = "8be18de09a56b60ed0edf84bc9df007e30040691af7acd1c41874faac5895bfb"
"checksum itoa 0.4.3 (registry+https://github.com/rust-lang/crates.io-index)" = "1306f3464951f30e30d12373d31c79fbd52d236e5e896fd92f96ec7babbbe60b"
"checksum lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "bc5729f27f159ddd61f4df6228e827e86643d4d3e7c32183cb30a1c08f604a14"
"checksum libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)" = "bedcc7a809076656486ffe045abeeac163da1b558e963a31e29fbfbeba916917"
"checksum log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)" = "c84ec4b527950aa83a329754b01dbe3f58361d1c5efacd1f6d68c494d08a17c6"
"checksum memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)" = "2efc7bc57c883d4a4d6e3246905283d8dae951bb3bd32f49d6ef297f546e1c39"
"checksum memmap 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)" = "6585fd95e7bb50d6cc31e20d4cf9afb4e2ba16c5846fc76793f11218da9c475b"
"checksum num_cpus 1.10.0 (registry+https://github.com/rust-lang/crates.io-index)" = "1a23f0ed30a54abaa0c7e83b1d2d87ada7c3c23078d1d87815af3e3b6385fbba"
"checksum packed_simd 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "a85ea9fc0d4ac0deb6fe7911d38786b32fc11119afd9e9d38b84ff691ce64220"
"checksum pcre2 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "3ae0a2682105ec5ca0ee5910bbc7e926386d348a05166348f74007942983c319"
"checksum pcre2-sys 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "a9027f9474e4e13d3b965538aafcaebe48c803488ad76b3c97ef061a8324695f"
"checksum pkg-config 0.3.14 (registry+https://github.com/rust-lang/crates.io-index)" = "676e8eb2b1b4c9043511a9b7bea0915320d7e502b0a079fb03f9635a5252b18c"
"checksum proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)" = "4d317f9caece796be1980837fd5cb3dfec5613ebdb04ad0956deea83ce168915"
"checksum quote 0.6.11 (registry+https://github.com/rust-lang/crates.io-index)" = "cdd8e04bd9c52e0342b406469d494fcb033be4bdbe5c606016defbb1681411e1"
"checksum rand 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)" = "6d71dacdc3c88c1fde3885a3be3fbab9f35724e6ce99467f7d9c5026132184ca"
"checksum rand_chacha 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "556d3a1ca6600bfcbab7c7c91ccb085ac7fbbcd70e008a98742e7847f4f7bcef"
"checksum rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)" = "7a6fdeb83b075e8266dcc8762c22776f6877a63111121f5f8c7411e5be7eed4b"
"checksum rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "d0e7a549d590831370895ab7ba4ea0c1b6b011d106b5ff2da6eee112615e6dc0"
"checksum rand_hc 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "7b40677c7be09ae76218dc623efbf7b18e34bced3f38883af07bb75630a21bc4"
"checksum rand_isaac 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "ded997c9d5f13925be2a6fd7e66bf1872597f759fd9dd93513dd7e92e5a5ee08"
"checksum rand_jitter 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "7b9ea758282efe12823e0d952ddb269d2e1897227e464919a554f2a03ef1b832"
"checksum rand_os 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "7b75f676a1e053fc562eafbb47838d67c84801e38fc1ba459e8f180deabd5071"
"checksum rand_pcg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "abf9b09b01790cfe0364f52bf32995ea3c39f4d2dd011eac241d2914146d0b44"
"checksum rand_xorshift 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "cbf7e9e623549b0e21f6e97cf8ecf247c1a8fd2e8a992ae265314300b2455d5c"
"checksum rdrand 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "678054eb77286b51581ba43620cc911abf02758c91f93f479767aed0f90458b2"
"checksum redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)" = "d32b3053e5ced86e4bc0411fec997389532bf56b000e66cb4884eeeb41413d69"
"checksum redox_termios 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "7e891cfe48e9100a70a3b6eb652fef28920c117d366339687bd5576160db0f76"
"checksum regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)" = "559008764a17de49a3146b234641644ed37d118d1ef641a0bb573d146edc6ce0"
"checksum regex-automata 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)" = "a25a7daa2eea48550e9946133d6cc9621020d29cc7069089617234bf8b6a8693"
"checksum regex-syntax 0.6.6 (registry+https://github.com/rust-lang/crates.io-index)" = "dcfd8681eebe297b81d98498869d4aae052137651ad7b96822f09ceb690d0a96"
"checksum remove_dir_all 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)" = "3488ba1b9a2084d38645c4c08276a1752dcbf2c7130d74f1569681ad5d2799c5"
"checksum ryu 0.2.7 (registry+https://github.com/rust-lang/crates.io-index)" = "eb9e9b8cde282a9fe6a42dd4681319bfb63f121b8a8ee9439c6f4107e58a46f7"
"checksum same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)" = "8f20c4be53a8a1ff4c1f1b2bd14570d2f634628709752f0702ecdd2b3f9a5267"
"checksum serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)" = "aa5f7c20820475babd2c077c3ab5f8c77a31c15e16ea38687b4c02d3e48680f4"
"checksum serde_derive 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)" = "58fc82bec244f168b23d1963b45c8bf5726e9a15a9d146a067f9081aeed2de79"
"checksum serde_json 1.0.39 (registry+https://github.com/rust-lang/crates.io-index)" = "5a23aa71d4a4d43fdbfaac00eff68ba8a06a51759a89ac3304323e800c4dd40d"
"checksum smallvec 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)" = "c4488ae950c49d403731982257768f48fada354a5203fe81f9bb6f43ca9002be"
"checksum strsim 0.8.0 (registry+https://github.com/rust-lang/crates.io-index)" = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
"checksum syn 0.15.30 (registry+https://github.com/rust-lang/crates.io-index)" = "66c8865bf5a7cbb662d8b011950060b3c8743dca141b054bf7195b20d314d8e2"
"checksum tempfile 3.0.7 (registry+https://github.com/rust-lang/crates.io-index)" = "b86c784c88d98c801132806dadd3819ed29d8600836c4088e855cdf3e178ed8a"
"checksum termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)" = "4096add70612622289f2fdcdbd5086dc81c1e2675e6ae58d6c4f62a16c6d7f2f"
"checksum termion 1.5.1 (registry+https://github.com/rust-lang/crates.io-index)" = "689a3bdfaab439fd92bc87df5c4c78417d3cbe537487274e9b0b2dce76e92096"
"checksum textwrap 0.11.0 (registry+https://github.com/rust-lang/crates.io-index)" = "d326610f408c7a4eb6f51c37c330e496b08506c9457c9d34287ecc38809fb060"
"checksum thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)" = "c6b53e329000edc2b34dbe8545fd20e55a333362d0a321909685a19bd28c3f1b"
"checksum ucd-util 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "535c204ee4d8434478593480b8f86ab45ec9aae0e83c568ca81abf0fd0e88f86"
"checksum unicode-width 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)" = "882386231c45df4700b275c7ff55b6f3698780a650026380e72dabe76fa46526"
"checksum unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "fc72304796d0818e357ead4e000d19c9c174ab23dc11093ac919054d20a6a7fc"
"checksum utf8-ranges 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "796f7e48bef87609f7ade7e06495a87d5cd06c7866e6a5cbfceffc558a243737"
"checksum walkdir 2.2.7 (registry+https://github.com/rust-lang/crates.io-index)" = "9d9d7ed3431229a144296213105a390676cc49c9b6a72bd19f3176c98e129fa1"
"checksum winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)" = "f10e386af2b13e47c89e7236a7a14a086791a2b88ebad6df9bf42040195cf770"
"checksum winapi-i686-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
"checksum winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "7168bab6e1daee33b4557efd0e95d5ca70a03706d39fa5f3fe7a236f584b03c9"
"checksum winapi-x86_64-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
"checksum wincolor 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)" = "561ed901ae465d6185fa7864d63fbd5720d0ef718366c9a4dc83cf6170d7e9ba"

103
Cargo.toml
View File

@@ -1,10 +1,11 @@
[package]
name = "ripgrep"
version = "0.5.2" #:version
version = "0.10.0" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Line oriented search tool using Rust's regex library. Combines the raw
performance of grep with the usability of the silver searcher.
ripgrep is a line-oriented search tool that recursively searches your current
directory for a regex pattern while respecting your gitignore rules. ripgrep
has first class support on Windows, macOS and Linux
"""
documentation = "https://github.com/BurntSushi/ripgrep"
homepage = "https://github.com/BurntSushi/ripgrep"
@@ -12,9 +13,15 @@ repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["regex", "grep", "egrep", "search", "pattern"]
categories = ["command-line-utilities", "text-processing"]
license = "Unlicense/MIT"
license = "Unlicense OR MIT"
exclude = ["HomebrewFormula"]
build = "build.rs"
autotests = false
edition = "2018"
[badges]
travis-ci = { repository = "BurntSushi/ripgrep" }
appveyor = { repository = "BurntSushi/ripgrep" }
[[bin]]
bench = false
@@ -25,31 +32,77 @@ name = "rg"
name = "integration"
path = "tests/tests.rs"
[workspace]
members = [
"globset",
"grep",
"grep-cli",
"grep-matcher",
"grep-pcre2",
"grep-printer",
"grep-regex",
"grep-searcher",
"ignore",
]
[dependencies]
atty = "0.2.2"
bytecount = "0.1.4"
clap = "2.24.1"
encoding_rs = "0.5.0"
env_logger = { version = "0.4", default-features = false }
grep = { version = "0.1.5", path = "grep" }
ignore = { version = "0.2.0", path = "ignore" }
lazy_static = "0.2"
libc = "0.2"
log = "0.3"
memchr = "1"
memmap = "0.5"
num_cpus = "1"
regex = "0.2.1"
same-file = "0.1.1"
termcolor = { version = "0.3.0", path = "termcolor" }
bstr = "0.1.2"
grep = { version = "0.2.3", path = "grep" }
ignore = { version = "0.4.4", path = "ignore" }
lazy_static = "1.1.0"
log = "0.4.5"
num_cpus = "1.8.0"
regex = "1.0.5"
serde_json = "1.0.23"
termcolor = "1.0.3"
[dependencies.clap]
version = "2.32.0"
default-features = false
features = ["suggestions"]
[build-dependencies]
clap = "2.24.1"
lazy_static = "0.2"
lazy_static = "1.1.0"
[build-dependencies.clap]
version = "2.32.0"
default-features = false
features = ["suggestions"]
[dev-dependencies]
serde = "1.0.77"
serde_derive = "1.0.77"
[features]
avx-accel = ["bytecount/avx-accel"]
simd-accel = ["bytecount/simd-accel", "regex/simd-accel"]
simd-accel = ["grep/simd-accel"]
pcre2 = ["grep/pcre2"]
[profile.release]
debug = true
debug = 1
[package.metadata.deb]
features = ["pcre2"]
section = "utils"
assets = [
["target/release/rg", "usr/bin/", "755"],
["COPYING", "usr/share/doc/ripgrep/", "644"],
["LICENSE-MIT", "usr/share/doc/ripgrep/", "644"],
["UNLICENSE", "usr/share/doc/ripgrep/", "644"],
["CHANGELOG.md", "usr/share/doc/ripgrep/CHANGELOG", "644"],
["README.md", "usr/share/doc/ripgrep/README", "644"],
["FAQ.md", "usr/share/doc/ripgrep/FAQ", "644"],
# The man page is automatically generated by ripgrep's build process, so
# this file isn't actually commited. Instead, to create a dpkg, either
# create a deployment/deb directory and copy the man page to it, or use the
# 'ci/build_deb.sh' script.
["deployment/deb/rg.1", "usr/share/man/man1/rg.1", "644"],
# Similarly for shell completions.
["deployment/deb/rg.bash", "usr/share/bash-completion/completions/rg", "644"],
["deployment/deb/rg.fish", "usr/share/fish/completions/rg.fish", "644"],
["deployment/deb/_rg", "usr/share/zsh/vendor-completions/", "644"],
]
extended-description = """\
ripgrep (rg) recursively searches your current directory for a regex pattern.
By default, ripgrep will respect your .gitignore and automatically skip hidden
files/directories and binary files.
"""

983
FAQ.md Normal file
View File

@@ -0,0 +1,983 @@
## FAQ
* [Does ripgrep support configuration files?](#config)
* [What's changed in ripgrep recently?](#changelog)
* [When is the next release?](#release)
* [Does ripgrep have a man page?](#manpage)
* [Does ripgrep have support for shell auto-completion?](#complete)
* [How do I use lookaround and/or backreferences?](#fancy)
* [How do I configure ripgrep's colors?](#colors)
* [How do I enable true colors on Windows?](#truecolors-windows)
* [How do I stop ripgrep from messing up colors when I kill it?](#stop-ripgrep)
* [How can I get results in a consistent order?](#order)
* [How do I search files that aren't UTF-8?](#encoding)
* [How do I search compressed files?](#compressed)
* [How do I search over multiple lines?](#multiline)
* [How do I get around the regex size limit?](#size-limit)
* [How do I make the `-f/--file` flag faster?](#dfa-size)
* [How do I make the output look like The Silver Searcher's output?](#silver-searcher-output)
* [Why does ripgrep get slower when I enabled PCRE2 regexes?](#pcre2-slow)
* [When I run `rg`, why does it execute some other command?](#rg-other-cmd)
* [How do I create an alias for ripgrep on Windows?](#rg-alias-windows)
* [How do I create a PowerShell profile?](#powershell-profile)
* [How do I pipe non-ASCII content to ripgrep on Windows?](#pipe-non-ascii-windows)
* [How can I search and replace with ripgrep?](#search-and-replace)
* [How is ripgrep licensed?](#license)
* [Can ripgrep replace grep?](#posix4ever)
* [What does the "rip" in ripgrep mean?](#intentcountsforsomething)
<h3 name="config">
Does ripgrep support configuration files?
</h3>
Yes. See the
[guide's section on configuration files](GUIDE.md#configuration-file).
<h3 name="changelog">
What's changed in ripgrep recently?
</h3>
Please consult ripgrep's [CHANGELOG](CHANGELOG.md).
<h3 name="release">
When is the next release?
</h3>
ripgrep is a project whose contributors are volunteers. A release schedule
adds undue stress to said volunteers. Therefore, releases are made on a best
effort basis and no dates **will ever be given**.
One exception to this is high impact bugs. If a ripgrep release contains a
significant regression, then there will generally be a strong push to get a
patch release out with a fix.
<h3 name="manpage">
Does ripgrep have a man page?
</h3>
Yes! Whenever ripgrep is compiled on a system with `asciidoc` present, then a
man page is generated from ripgrep's argv parser. After compiling ripgrep, you
can find the man page like so from the root of the repository:
```
$ find ./target -name rg.1 -print0 | xargs -0 ls -t | head -n1
./target/debug/build/ripgrep-79899d0edd4129ca/out/rg.1
```
Running `man -l ./target/debug/build/ripgrep-79899d0edd4129ca/out/rg.1` will
show the man page in your normal pager.
Note that the man page's documentation for options is equivalent to the output
shown in `rg --help`. To see more condensed documentation (one line per flag),
run `rg -h`.
The man page is also included in all
[ripgrep binary releases](https://github.com/BurntSushi/ripgrep/releases).
<h3 name="complete">
Does ripgrep have support for shell auto-completion?
</h3>
Yes! Shell completions can be found in the
[same directory as the man page](#manpage)
after building ripgrep. Zsh completions are maintained separately and committed
to the repository in `complete/_rg`.
Shell completions are also included in all
[ripgrep binary releases](https://github.com/BurntSushi/ripgrep/releases).
For **bash**, move `rg.bash` to
`$XDG_CONFIG_HOME/bash_completion` or `/etc/bash_completion.d/`.
For **fish**, move `rg.fish` to `$HOME/.config/fish/completions/`.
For **zsh**, move `_rg` to one of your `$fpath` directories.
For **PowerShell**, add `. _rg.ps1` to your PowerShell
[profile](https://technet.microsoft.com/en-us/library/bb613488(v=vs.85).aspx)
(note the leading period). If the `_rg.ps1` file is not on your `PATH`, do
`. /path/to/_rg.ps1` instead.
<h3 name="order">
How can I get results in a consistent order?
</h3>
By default, ripgrep uses parallelism to execute its search because this makes
the search much faster on most modern systems. This in turn means that ripgrep
has a non-deterministic aspect to it, since the interleaving of threads during
the execution of the program is itself non-deterministic. This has the effect
of printing results in a somewhat arbitrary order, and this order can change
from run to run of ripgrep.
The only way to make the order of results consistent is to ask ripgrep to
sort the output. Currently, this will disable all parallelism. (On smaller
repositories, you might not notice much of a performance difference!) You
can achieve this with the `--sort path` flag.
There is more discussion on this topic here:
https://github.com/BurntSushi/ripgrep/issues/152
<h3 name="encoding">
How do I search files that aren't UTF-8?
</h3>
See the [guide's section on file encoding](GUIDE.md#file-encoding).
<h3 name="compressed">
How do I search compressed files?
</h3>
ripgrep's `-z/--search-zip` flag will cause it to search compressed files
automatically. Currently, this supports gzip, bzip2, xz, lzma, lz4, Brotli and
Zstd. Each of these requires requires the corresponding `gzip`, `bzip2`, `xz`,
`lz4`, `brotli` and `zstd` binaries to be installed on your system. (That is,
ripgrep does decompression by shelling out to another process.)
ripgrep currently does not search archive formats, so `*.tar.gz` files, for
example, are skipped.
<h3 name="multiline">
How do I search over multiple lines?
</h3>
The `-U/--multiline` flag enables ripgrep to report results that span over
multiple lines.
<h3 name="fancy">
How do I use lookaround and/or backreferences?
</h3>
ripgrep's default regex engine does not support lookaround or backreferences.
This is primarily because the default regex engine is implemented using finite
state machines in order to guarantee a linear worst case time complexity on all
inputs. Backreferences are not possible to implement in this paradigm, and
lookaround appears difficult to do efficiently.
However, ripgrep optionally supports using PCRE2 as the regex engine instead of
the default one based on finite state machines. You can enable PCRE2 with the
`-P/--pcre2` flag. For example, in the root of the ripgrep repo, you can easily
find all palindromes:
```
$ rg -P '(\w{10})\1'
tests/misc.rs
483: cmd.arg("--max-filesize").arg("44444444444444444444");
globset/src/glob.rs
1206: matches!(match7, "a*a*a*a*a*a*a*a*a", "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa");
```
If your version of ripgrep doesn't support PCRE2, then you'll get an error
message when you try to use the `-P/--pcre2` flag:
```
$ rg -P '(\w{10})\1'
PCRE2 is not available in this build of ripgrep
```
Most of the releases distributed by the ripgrep project here on GitHub will
come bundled with PCRE2 enabled. If you installed ripgrep through a different
means (like your system's package manager), then please reach out to the
maintainer of that package to see whether it's possible to enable the PCRE2
feature.
<h3 name="colors">
How do I configure ripgrep's colors?
</h3>
ripgrep has two flags related to colors:
* `--color` controls *when* to use colors.
* `--colors` controls *which* colors to use.
The `--color` flag accepts one of the following possible values: `never`,
`auto`, `always` or `ansi`. The `auto` value is the default and will cause
ripgrep to only enable colors when it is printing to a terminal. But if you
pipe ripgrep to a file or some other process, then it will suppress colors.
The --colors` flag is a bit more complicated. The general format is:
```
--colors '{type}:{attribute}:{value}'
```
* `{type}` should be one of `path`, `line`, `column` or `match`. Each of these
correspond to the four different types of things that ripgrep will add color
to in its output. Select the type whose color you want to change.
* `{attribute}` should be one of `fg`, `bg` or `style`, corresponding to
foreground color, background color, or miscellaneous styling (such as whether
to bold the output or not).
* `{value}` is determined by the value of `{attribute}`. If
`{attribute}` is `style`, then `{value}` should be one of `nobold`,
`bold`, `nointense`, `intense`, `nounderline` or `underline`. If
`{attribute}` is `fg` or `bg`, then `{value}` should be a color.
A color is specified by either one of eight of English names, a single 256-bit
number or an RGB triple (with over 16 million possible values, or "true
color").
The color names are `red`, `blue`, `green`, `cyan`, `magenta`, `yellow`,
`white` or `black`.
A single 256-bit number is a value in the range 0-255 (inclusive). It can
either be in decimal format (e.g., `62`) or hexadecimal format (e.g., `0x3E`).
An RGB triple corresponds to three numbers (decimal or hexadecimal) separated
by commas.
As a special case, `--colors '{type}:none'` will clear all colors and styles
associated with `{type}`, which lets you start with a clean slate (instead of
building on top of ripgrep's default color settings).
Here's an example that makes highlights the matches with a nice blue background
with bolded white text:
```
$ rg somepattern \
--colors 'match:none' \
--colors 'match:bg:0x33,0x66,0xFF' \
--colors 'match:fg:white' \
--colors 'match:style:bold'
```
Colors are an ideal candidate to set in your
[configuration file](GUIDE.md#configuration-file). See the
[question on emulating The Silver Searcher's output style](#silver-searcher-output)
for an example specific to colors.
<h3 name="truecolors-windows">
How do I enable true colors on Windows?
</h3>
First, see the previous question's
[answer on configuring colors](#colors).
Secondly, coloring on Windows is a bit complicated. If you're using a terminal
like Cygwin, then it's likely true color support already works out of the box.
However, if you are using a normal Windows console (`cmd` or `PowerShell`) and
a version of Windows prior to 10, then there is no known way to get true
color support. If you are on Windows 10 and using a Windows console, then
true colors should work out of the box with one caveat: you might need to
clear ripgrep's default color settings first. That is, instead of this:
```
$ rg somepattern --colors 'match:fg:0x33,0x66,0xFF'
```
you should do this
```
$ rg somepattern --colors 'match:none' --colors 'match:fg:0x33,0x66,0xFF'
```
This is because ripgrep might set the default style for `match` to `bold`, and
it seems like Windows 10's VT100 support doesn't permit bold and true color
ANSI escapes to be used simultaneously. The work-around above will clear
ripgrep's default styling, allowing you to craft it exactly as desired.
<h3 name="stop-ripgrep">
How do I stop ripgrep from messing up colors when I kill it?
</h3>
Type in `color` in cmd.exe (Command Prompt) and `echo -ne "\033[0m"` on
Unix-like systems to restore your original foreground color.
In PowerShell, you can add the following code to your profile which will
restore the original foreground color when `Reset-ForegroundColor` is called.
Including the `Set-Alias` line will allow you to call it with simply `color`.
```powershell
$OrigFgColor = $Host.UI.RawUI.ForegroundColor
function Reset-ForegroundColor {
$Host.UI.RawUI.ForegroundColor = $OrigFgColor
}
Set-Alias -Name color -Value Reset-ForegroundColor
```
PR [#187](https://github.com/BurntSushi/ripgrep/pull/187) fixed this, and it
was later deprecated in
[#281](https://github.com/BurntSushi/ripgrep/issues/281). A full explanation is
available
[here](https://github.com/BurntSushi/ripgrep/issues/281#issuecomment-269093893).
<h3 name="size-limit">
How do I get around the regex size limit?
</h3>
If you've given ripgrep a particularly large pattern (or a large number of
smaller patterns), then it is possible that it will fail to compile because it
hit a pre-set limit. For example:
```
$ rg '\pL{1000}'
Compiled regex exceeds size limit of 10485760 bytes.
```
(Note: `\pL{1000}` may look small, but `\pL` is the character class containing
all Unicode letters, which is quite large. *And* it's repeated 1000 times.)
In this case, you can work around by simply increasing the limit:
```
$ rg '\pL{1000}' --regex-size-limit 1G
```
Increasing the limit to 1GB does not necessarily mean that ripgrep will use
that much memory. The limit just says that it's allowed to (approximately) use
that much memory for constructing the regular expression.
<h3 name="dfa-size">
How do I make the <code>-f/--file</code> flag faster?
</h3>
The `-f/--file` permits one to give a file to ripgrep which contains a pattern
on each line. ripgrep will then report any line that matches any of the
patterns.
If this pattern file gets too big, then it is possible ripgrep will slow down
dramatically. *Typically* this is because an internal cache is too small, and
will cause ripgrep to spill over to a slower but more robust regular expression
engine. If this is indeed the problem, then it is possible to increase this
cache and regain speed. The cache can be controlled via the `--dfa-size-limit`
flag. For example, using `--dfa-size-limit 1G` will set the cache size to 1GB.
(Note that this doesn't mean ripgrep will use 1GB of memory automatically, but
it will allow the regex engine to if it needs to.)
<h3 name="silver-searcher-output">
How do I make the output look like The Silver Searcher's output?
</h3>
Use the `--colors` flag, like so:
```
rg --colors line:fg:yellow \
--colors line:style:bold \
--colors path:fg:green \
--colors path:style:bold \
--colors match:fg:black \
--colors match:bg:yellow \
--colors match:style:nobold \
foo
```
Alternatively, add your color configuration to your ripgrep config file (which
is activated by setting the `RIPGREP_CONFIG_PATH` environment variable to point
to your config file). For example:
```
$ cat $HOME/.config/ripgrep/rc
--colors=line:fg:yellow
--colors=line:style:bold
--colors=path:fg:green
--colors=path:style:bold
--colors=match:fg:black
--colors=match:bg:yellow
--colors=match:style:nobold
$ RIPGREP_CONFIG_PATH=$HOME/.config/ripgrep/rc rg foo
```
<h3 name="pcre2-slow">
Why does ripgrep get slower when I enable PCRE2 regexes?
</h3>
When you use the `--pcre2` (`-P` for short) flag, ripgrep will use the PCRE2
regex engine instead of the default. Both regex engines are quite fast,
but PCRE2 provides a number of additional features such as look-around and
backreferences that many enjoy using. This is largely because PCRE2 uses
a backtracking implementation where as the default regex engine uses a finite
automaton based implementation. The former provides the ability to add lots of
bells and whistles over the latter, but the latter executes with worst case
linear time complexity.
With that out of the way, if you've used `-P` with ripgrep, you may have
noticed that it can be slower. The reasons for why this is are quite complex,
and they are complex because the optimizations that ripgrep uses to implement
fast search are complex.
The task ripgrep has before it is somewhat simple; all it needs to do is search
a file for occurrences of some pattern and then print the lines containing
those occurrences. The problem lies in what is considered a valid match and how
exactly we read the bytes from a file.
In terms of what is considered a valid match, remember that ripgrep will only
report matches spanning a single line by default. The problem here is that
some patterns can match across multiple lines, and ripgrep needs to prevent
that from happening. For example, `foo\sbar` will match `foo\nbar`. The most
obvious way to achieve this is to read the data from a file, and then apply
the pattern search to that data for each line. The problem with this approach
is that it can be quite slow; it would be much faster to let the pattern
search across as much data as possible. It's faster because it gets rid of the
overhead of finding the boundaries of every line, and also because it gets rid
of the overhead of starting and stopping the pattern search for every single
line. (This is operating under the general assumption that matching lines are
much rarer than non-matching lines.)
It turns out that we can use the faster approach by applying a very simple
restriction to the pattern: *statically prevent* the pattern from matching
through a `\n` character. Namely, when given a pattern like `foo\sbar`,
ripgrep will remove `\n` from the `\s` character class automatically. In some
cases, a simple removal is not so easy. For example, ripgrep will return an
error when your pattern includes a `\n` literal:
```
$ rg '\n'
the literal '"\n"' is not allowed in a regex
```
So what does this have to do with PCRE2? Well, ripgrep's default regex engine
exposes APIs for doing syntactic analysis on the pattern in a way that makes
it quite easy to strip `\n` from the pattern (or otherwise detect it and report
an error if stripping isn't possible). PCRE2 seemingly does not provide a
similar API, so ripgrep does not do any stripping when PCRE2 is enabled. This
forces ripgrep to use the "slow" search strategy of searching each line
individually.
OK, so if enabling PCRE2 slows down the default method of searching because it
forces matches to be limited to a single line, then why is PCRE2 also sometimes
slower when performing multiline searches? Well, that's because there are
*multiple* reasons why using PCRE2 in ripgrep can be slower than the default
regex engine. This time, blame PCRE2's Unicode support, which ripgrep enables
by default. In particular, PCRE2 cannot simultaneously enable Unicode support
and search arbitrary data. That is, when PCRE2's Unicode support is enabled,
the data **must** be valid UTF-8 (to do otherwise is to invoke undefined
behavior). This is in contrast to ripgrep's default regex engine, which can
enable Unicode support and still search arbitrary data. ripgrep's default
regex engine simply won't match invalid UTF-8 for a pattern that can otherwise
only match valid UTF-8. Why doesn't PCRE2 do the same? This author isn't
familiar with its internals, so we can't comment on it here.
The bottom line here is that we can't enable PCRE2's Unicode support without
simultaneously incurring a performance penalty for ensuring that we are
searching valid UTF-8. In particular, ripgrep will transcode the contents
of each file to UTF-8 while replacing invalid UTF-8 data with the Unicode
replacement codepoint. ripgrep then disables PCRE2's own internal UTF-8
checking, since we've guaranteed the data we hand it will be valid UTF-8. The
reason why ripgrep takes this approach is because if we do hand PCRE2 invalid
UTF-8, then it will report a match error if it comes across an invalid UTF-8
sequence. This is not good news for ripgrep, since it will stop it from
searching the rest of the file, and will also print potentially undesirable
error messages to users.
All right, the above is a lot of information to swallow if you aren't already
familiar with ripgrep internals. Let's make this concrete with some examples.
First, let's get some data big enough to magnify the performance differences:
```
$ curl -O 'https://burntsushi.net/stuff/subtitles2016-sample.gz'
$ gzip -d subtitles2016-sample
$ md5sum subtitles2016-sample
e3cb796a20bbc602fbfd6bb43bda45f5 subtitles2016-sample
```
To search this data, we will use the pattern `^\w{42}$`, which contains exactly
one hit in the file and has no literals. Having no literals is important,
because it ensures that the regex engine won't use literal optimizations to
speed up the search. In other words, it lets us reason coherently about the
actual task that the regex engine is performing.
Let's now walk through a few examples in light of the information above. First,
let's consider the default search using ripgrep's default regex engine and
then the same search with PCRE2:
```
$ time rg '^\w{42}$' subtitles2016-sample
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m1.783s
user 0m1.731s
sys 0m0.051s
$ time rg -P '^\w{42}$' subtitles2016-sample
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m2.458s
user 0m2.419s
sys 0m0.038s
```
In this particular example, both pattern searches are using a Unicode aware
`\w` character class and both are counting lines in order to report line
numbers. The key difference here is that the first search will not search
line by line, but the second one will. We can observe which strategy ripgrep
uses by passing the `--trace` flag:
```
$ rg '^\w{42}$' subtitles2016-sample --trace
[... snip ...]
TRACE|grep_searcher::searcher|grep-searcher/src/searcher/mod.rs:622: Some("subtitles2016-sample"): searching via memory map
TRACE|grep_searcher::searcher|grep-searcher/src/searcher/mod.rs:712: slice reader: searching via slice-by-line strategy
TRACE|grep_searcher::searcher::core|grep-searcher/src/searcher/core.rs:61: searcher core: will use fast line searcher
[... snip ...]
$ rg -P '^\w{42}$' subtitles2016-sample --trace
[... snip ...]
TRACE|grep_searcher::searcher|grep-searcher/src/searcher/mod.rs:622: Some("subtitles2016-sample"): searching via memory map
TRACE|grep_searcher::searcher|grep-searcher/src/searcher/mod.rs:705: slice reader: needs transcoding, using generic reader
TRACE|grep_searcher::searcher|grep-searcher/src/searcher/mod.rs:685: generic reader: searching via roll buffer strategy
TRACE|grep_searcher::searcher::core|grep-searcher/src/searcher/core.rs:63: searcher core: will use slow line searcher
[... snip ...]
```
The first says it is using the "fast line searcher" where as the latter says
it is using the "slow line searcher." The latter also shows that we are
decoding the contents of the file, which also impacts performance.
Interestingly, in this case, the pattern does not match a `\n` and the file
we're searching is valid UTF-8, so neither the slow line-by-line search
strategy nor the decoding are necessary. We could fix the former issue with
better PCRE2 introspection APIs. We can actually fix the latter issue with
ripgrep's `--no-encoding` flag, which prevents the automatic UTF-8 decoding,
but will enable PCRE2's own UTF-8 validity checking. Unfortunately, it's slower
in my build of ripgrep:
```
$ time rg -P '^\w{42}$' subtitles2016-sample --no-encoding
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m3.074s
user 0m3.021s
sys 0m0.051s
```
(Tip: use the `--trace` flag to verify that no decoding in ripgrep is
happening.)
A possible reason why PCRE2's UTF-8 checking is slower is because it might
not be better than the highly optimized UTF-8 checking routines found in the
[`encoding_rs`](https://github.com/hsivonen/encoding_rs) library, which is what
ripgrep uses for UTF-8 decoding. Moreover, my build of ripgrep enables
`encoding_rs`'s SIMD optimizations, which may be in play here.
Also, note that using the `--no-encoding` flag can cause PCRE2 to report
invalid UTF-8 errors, which causes ripgrep to stop searching the file:
```
$ cat invalid-utf8
foobar
$ xxd invalid-utf8
00000000: 666f 6fff 6261 720a foo.bar.
$ rg foo invalid-utf8
1:foobar
$ rg -P foo invalid-utf8
1:foo<6F>bar
$ rg -P foo invalid-utf8 --no-encoding
invalid-utf8: PCRE2: error matching: UTF-8 error: illegal byte (0xfe or 0xff)
```
All right, so at this point, you might think that we could remove the penalty
for line-by-line searching by enabling multiline search. After all, our
particular pattern can't match across multiple lines anyway, so we'll still get
the results we want. Let's try it:
```
$ time rg -U '^\w{42}$' subtitles2016-sample
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m1.803s
user 0m1.748s
sys 0m0.054s
$ time rg -P -U '^\w{42}$' subtitles2016-sample
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m2.962s
user 0m2.246s
sys 0m0.713s
```
Search times remain the same with the default regex engine, but the PCRE2
search gets _slower_. What happened? The secrets can be revealed with the
`--trace` flag once again. In the former case, ripgrep actually detects that
the pattern can't match across multiple lines, and so will fall back to the
"fast line search" strategy as with our search without `-U`.
However, for PCRE2, things are much worse. Namely, since Unicode mode is still
enabled, ripgrep is still going to decode UTF-8 to ensure that it hands only
valid UTF-8 to PCRE2. Unfortunately, one key downside of multiline search is
that ripgrep cannot do it incrementally. Since matches can be arbitrarily long,
ripgrep actually needs the entire file in memory at once. Normally, we can use
a memory map for this, but because we need to UTF-8 decode the file before
searching it, ripgrep winds up reading the entire contents of the file on to
the heap before executing a search. Owch.
OK, so Unicode is killing us here. The file we're searching is _mostly_ ASCII,
so maybe we're OK with missing some data. (Try `rg '[\w--\p{ascii}]'` to see
non-ASCII word characters that an ASCII-only `\w` character class would miss.)
We can disable Unicode in both searches, but this is done differently depending
on the regex engine we use:
```
$ time rg '(?-u)^\w{42}$' subtitles2016-sample
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m1.714s
user 0m1.669s
sys 0m0.044s
$ time rg -P '^\w{42}$' subtitles2016-sample --no-pcre2-unicode
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m1.997s
user 0m1.958s
sys 0m0.037s
```
For the most part, ripgrep's default regex engine performs about the same.
PCRE2 does improve a little bit, and is now almost as fast as the default
regex engine. If you look at the output of `--trace`, you'll see that ripgrep
will no longer perform UTF-8 decoding, but it does still use the slow
line-by-line searcher.
At this point, we can combine all of our insights above: let's try to get off
of the slow line-by-line searcher by enabling multiline mode, and let's stop
UTF-8 decoding by disabling Unicode support:
```
$ time rg -U '(?-u)^\w{42}$' subtitles2016-sample
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m1.714s
user 0m1.655s
sys 0m0.058s
$ time rg -P -U '^\w{42}$' subtitles2016-sample --no-pcre2-unicode
21225780:EverymajordevelopmentinthehistoryofAmerica
real 0m1.121s
user 0m1.071s
sys 0m0.048s
```
Ah, there's PCRE2's JIT shining! ripgrep's default regex engine once again
remains about the same, but PCRE2 no longer needs to search line-by-line and it
no longer needs to do any kind of UTF-8 checks. This allows the file to get
memory mapped and passed right through PCRE2's JIT at impressive speeds. (As
a brief and interesting historical note, the configuration of "memory map +
multiline + no-Unicode" is exactly the configuration used by The Silver
Searcher. This analysis perhaps sheds some reasoning as to why that
configuration is useful!)
In summary, if you want PCRE2 to go as fast as possible and you don't care
about Unicode and you don't care about matches possibly spanning across
multiple lines, then enable multiline mode with `-U` and disable PCRE2's
Unicode support with the `--no-pcre2-unicode` flag.
Caveat emptor: This author is not a PCRE2 expert, so there may be APIs that can
improve performance that the author missed. Similarly, there may be alternative
designs for a searching tool that are more amenable to how PCRE2 works.
<h3 name="rg-other-cmd">
When I run <code>rg</code>, why does it execute some other command?
</h3>
It's likely that you have a shell alias or even another tool called `rg` which
is interfering with ripgrep. Run `which rg` to see what it is.
(Notably, the Rails plug-in for
[Oh My Zsh](https://github.com/robbyrussell/oh-my-zsh/wiki/Plugins#rails) sets
up an `rg` alias for `rails generate`.)
Problems like this can be resolved in one of several ways:
* If you're using the OMZ Rails plug-in, disable it by editing the `plugins`
array in your zsh configuration.
* Temporarily bypass an existing `rg` alias by calling ripgrep as
`command rg`, `\rg`, or `'rg'`.
* Temporarily bypass an existing alias or another tool named `rg` by calling
ripgrep by its full path (e.g., `/usr/bin/rg` or `/usr/local/bin/rg`).
* Permanently disable an existing `rg` alias by adding `unalias rg` to the
bottom of your shell configuration file (e.g., `.bash_profile` or `.zshrc`).
* Give ripgrep its own alias that doesn't conflict with other tools/aliases by
adding a line like the following to the bottom of your shell configuration
file: `alias ripgrep='command rg'`.
<h3 name="rg-alias-windows">
How do I create an alias for ripgrep on Windows?
</h3>
Often you can find a need to make alias for commands you use a lot that set
certain flags. But PowerShell function aliases do not behave like your typical
linux shell alias. You always need to propagate arguments and `stdin` input.
But it cannot be done simply as
`function grep() { $input | rg.exe --hidden $args }`
Use below example as reference to how setup alias in PowerShell.
```powershell
function grep {
$count = @($input).Count
$input.Reset()
if ($count) {
$input | rg.exe --hidden $args
}
else {
rg.exe --hidden $args
}
}
```
PowerShell special variables:
* input - is powershell `stdin` object that allows you to access its content.
* args - is array of arguments passed to this function.
This alias checks whether there is `stdin` input and propagates only if there
is some lines. Otherwise empty `$input` will make powershell to trigger `rg` to
search empty `stdin`.
<h3 name="powershell-profile">
How do I create a PowerShell profile?
</h3>
To customize powershell on start-up, there is a special PowerShell script that
has to be created. In order to find its location, type `$profile`.
See
[Microsoft's documentation](https://technet.microsoft.com/en-us/library/bb613488(v=vs.85).aspx)
for more details.
Any PowerShell code in this file gets evaluated at the start of console. This
way you can have own aliases to be created at start.
<h3 name="pipe-non-ascii-windows">
How do I pipe non-ASCII content to ripgrep on Windows?
</h3>
When piping input into native executables in PowerShell, the encoding of the
input is controlled by the `$OutputEncoding` variable. By default, this is set
to US-ASCII, and any characters in the pipeline that don't have encodings in
US-ASCII are converted to `?` (question mark) characters.
To change this setting, set `$OutputEncoding` to a different encoding, as
represented by a .NET encoding object. Some common examples are below. The
value of this variable is reset when PowerShell restarts, so to make this
change take effect every time PowerShell is started add a line setting the
variable into your PowerShell profile.
Example `$OutputEncoding` settings:
* UTF-8 without BOM: `$OutputEncoding = [System.Text.UTF8Encoding]::new()`
* The console's output encoding:
`$OutputEncoding = [System.Console]::OutputEncoding`
If you continue to have encoding problems, you can also force the encoding
that the console will use for printing to UTF-8 with
`[System.Console]::OutputEncoding = [System.Text.Encoding]::UTF8`. This
will also reset when PowerShell is restarted, so you can add that line
to your profile as well if you want to make the setting permanent.
<h3 name="search-and-replace">
How can I search and replace with ripgrep?
</h3>
Using ripgrep alone, you can't. ripgrep is a search tool that will never
touch your files. However, the output of ripgrep can be piped to other tools
that do modify files on disk. See
[this issue](https://github.com/BurntSushi/ripgrep/issues/74) for more
information.
sed is one such tool that can modify files on disk. sed can take a filename
and a substitution command to search and replace in the specified file.
Files containing matching patterns can be provided to sed using
```
rg foo --files-with-matches
```
The output of this command is a list of filenames that contain a match for
the `foo` pattern.
This list can be piped into `xargs`, which will split the filenames from
standard input into arguments for the command following xargs. You can use this
combination to pipe a list of filenames into sed for replacement. For example:
```
rg foo --files-with-matches | xargs sed -i 's/foo/bar/g'
```
will replace all instances of 'foo' with 'bar' in the files in which
ripgrep finds the foo pattern. The `-i` flag to sed indicates that you are
editing files in place, and `s/foo/bar/g` says that you are performing a
**s**ubstitution of the pattren `foo` for `bar`, and that you are doing this
substitution **g**lobally (all occurrences of the pattern in each file).
Note: the above command assumes that you are using GNU sed. If you are using
BSD sed (the default on macOS and FreeBSD) then you must modify the above
command to be the following:
```
rg foo --files-with-matches | xargs sed -i '' 's/foo/bar/g'
```
The `-i` flag in BSD sed requires a file extension to be given to make backups
for all modified files. Specifying the empty string prevents file backups from
being made.
Finally, if any of your file paths contain whitespace in them, then you might
need to delimit your file paths with a NUL terminator. This requires telling
ripgrep to output NUL bytes between each path, and telling xargs to read paths
delimited by NUL bytes:
```
rg foo --files-with-matches -0 | xargs -0 sed -i 's/foo/bar/g'
```
To learn more about sed, see the sed manual
[here](https://www.gnu.org/software/sed/manual/sed.html).
Additionally, Facebook has a tool called
[fastmod](https://github.com/facebookincubator/fastmod)
that uses some of the same libraries as ripgrep and might provide a more
ergonomic search-and-replace experience.
<h3 name="license">
How is ripgrep licensed?
</h3>
ripgrep is dual licensed under the
[Unlicense](https://unlicense.org/)
and MIT licenses. Specifically, you may use ripgrep under the terms of either
license.
The reason why ripgrep is dual licensed this way is two-fold:
1. I, as ripgrep's author, would like to participate in a small bit of
ideological activism by promoting the Unlicense's goal: to disclaim
copyright monopoly interest.
2. I, as ripgrep's author, would like as many people to use rigprep as
possible. Since the Unlicense is not a proven or well known license, ripgrep
is also offered under the MIT license, which is ubiquitous and accepted by
almost everyone.
More specifically, ripgrep and all its dependencies are compatible with this
licensing choice. In particular, ripgrep's dependencies (direct and transitive)
will always be limited to permissive licenses. That is, ripgrep will never
depend on code that is not permissively licensed. This means rejecting any
dependency that uses a copyleft license such as the GPL, LGPL, MPL or any of
the Creative Commons ShareAlike licenses. Whether the license is "weak"
copyleft or not does not matter; ripgrep will **not** depend on it.
<h3 name="posix4ever">
Can ripgrep replace grep?
</h3>
Yes and no.
If, upon hearing that "ripgrep can replace grep," you *actually* hear, "ripgrep
can be used in every instance grep can be used, in exactly the same way, for
the same use cases, with exactly the same bug-for-bug behavior," then no,
ripgrep trivially *cannot* replace grep. Moreover, ripgrep will *never* replace
grep.
If, upon hearing that "ripgrep can replace grep," you *actually* hear, "ripgrep
can replace grep in some cases and not in other use cases," then yes, that is
indeed true!
Let's go over some of those use cases in favor of ripgrep. Some of these may
not apply to you. That's OK. There may be other use cases not listed here that
do apply to you. That's OK too.
(For all claims related to performance in the following words, see my
[blog post](https://blog.burntsushi.net/ripgrep/)
introducing ripgrep.)
* Are you frequently searching a repository of code? If so, ripgrep might be a
good choice since there's likely a good chunk of your repository that you
don't want to search. grep, can, of course, be made to filter files using
recursive search, and if you don't mind writing out the requisite `--exclude`
rules or writing wrapper scripts, then grep might be sufficient. (I'm not
kidding, I myself did this with grep for almost a decade before writing
ripgrep.) But if you instead enjoy having a search tool respect your
`.gitignore`, then ripgrep might be perfect for you!
* Are you frequently searching non-ASCII text that is UTF-8 encoded? One of
ripgrep's key features is that it can handle Unicode features in your
patterns in a way that tends to be faster than GNU grep. Unicode features
in ripgrep are enabled by default; there is no need to configure your locale
settings to use ripgrep properly because ripgrep doesn't respect your locale
settings.
* Do you need to search UTF-16 files and you don't want to bother explicitly
transcoding them? Great. ripgrep does this for you automatically. No need
to enable it.
* Do you need to search a large directory of large files? ripgrep uses
parallelism by default, which tends to make it faster than a standard
`grep -r` search. However, if you're OK writing the occasional
`find ./ -print0 | xargs -P8 -0 grep` command, then maybe grep is good
enough.
Here are some cases where you might *not* want to use ripgrep. The same caveats
for the previous section apply.
* Are you writing portable shell scripts intended to work in a variety of
environments? Great, probably not a good idea to use ripgrep! ripgrep is has
nowhere near the ubquity of grep, so if you do use ripgrep, you might need
to futz with the installation process more than you would with grep.
* Do you care about POSIX compatibility? If so, then you can't use ripgrep
because it never was, isn't and never will be POSIX compatible.
* Do you hate tools that try to do something smart? If so, ripgrep is all about
being smart, so you might prefer to just stick with grep.
* Is there a particular feature of grep you rely on that ripgrep either doesn't
have or never will have? If the former, file a bug report, maybe ripgrep can
do it! If the latter, well, then, just use grep.
<h3 name="intentcountsforsomething">
What does the "rip" in ripgrep mean?
</h3>
When I first started writing ripgrep, I called it `rep`, intending it to be a
shorter variant of `grep`. Soon after, I renamed it to `xrep` since `rep`
wasn't obvious enough of a name for my taste. And also because adding `x` to
anything always makes it better, right?
Before ripgrep's first public release, I decided that I didn't like `xrep`. I
thought it was slightly awkward to type, and despite my previous praise of the
letter `x`, I kind of thought it was pretty lame. Being someone who really
likes Rust, I wanted to call it "rustgrep" or maybe "rgrep" for short. But I
thought that was just as lame, and maybe a little too in-your-face. But I
wanted to continue using `r` so I could at least pretend Rust had something to
do with it.
I spent a couple of days trying to think of very short words that began with
the letter `r` that were even somewhat related to the task of searching. I
don't remember how it popped into my head, but "rip" came up as something that
meant "fast," as in, "to rip through your text." The fact that RIP is also
an initialism for "Rest in Peace" (as in, "ripgrep kills grep") never really
dawned on me. Perhaps the coincidence is too striking to believe that, but
I didn't realize it until someone explicitly pointed it out to me after the
initial public release. I admit that I found it mildly amusing, but if I had
realized it myself before the public release, I probably would have pressed on
and chose a different name. Alas, renaming things after a release is hard, so I
decided to mush on.
Given the fact that
[ripgrep never was, is or will be a 100% drop-in replacement for
grep](#posix4ever),
ripgrep is neither actually a "grep killer" nor was it ever intended to be. It
certainly does eat into some of its use cases, but that's nothing that other
tools like ack or The Silver Searcher weren't already doing.

713
GUIDE.md Normal file
View File

@@ -0,0 +1,713 @@
## User Guide
This guide is intended to give an elementary description of ripgrep and an
overview of its capabilities. This guide assumes that ripgrep is
[installed](README.md#installation)
and that readers have passing familiarity with using command line tools. This
also assumes a Unix-like system, although most commands are probably easily
translatable to any command line shell environment.
### Table of Contents
* [Basics](#basics)
* [Recursive search](#recursive-search)
* [Automatic filtering](#automatic-filtering)
* [Manual filtering: globs](#manual-filtering-globs)
* [Manual filtering: file types](#manual-filtering-file-types)
* [Replacements](#replacements)
* [Configuration file](#configuration-file)
* [File encoding](#file-encoding)
* [Common options](#common-options)
### Basics
ripgrep is a command line tool that searches your files for patterns that
you give it. ripgrep behaves as if reading each file line by line. If a line
matches the pattern provided to ripgrep, then that line will be printed. If a
line does not match the pattern, then the line is not printed.
The best way to see how this works is with an example. To show an example, we
need something to search. Let's try searching ripgrep's source code. First
grab a ripgrep source archive from
https://github.com/BurntSushi/ripgrep/archive/0.7.1.zip
and extract it:
```
$ curl -LO https://github.com/BurntSushi/ripgrep/archive/0.7.1.zip
$ unzip 0.7.1.zip
$ cd ripgrep-0.7.1
$ ls
benchsuite grep tests Cargo.toml LICENSE-MIT
ci ignore wincolor CHANGELOG.md README.md
complete pkg appveyor.yml compile snapcraft.yaml
doc src build.rs COPYING UNLICENSE
globset termcolor Cargo.lock HomebrewFormula
```
Let's try our first search by looking for all occurrences of the word `fast`
in `README.md`:
```
$ rg fast README.md
75: faster than both. (N.B. It is not, strictly speaking, a "drop-in" replacement
88: color and full Unicode support. Unlike GNU grep, `ripgrep` stays fast while
119:### Is it really faster than everything else?
124:Summarizing, `ripgrep` is fast because:
129: optimizations to make searching very fast.
```
(**Note:** If you see an error message from ripgrep saying that it didn't
search any files, then re-run ripgrep with the `--debug` flag. One likely cause
of this is that you have a `*` rule in a `$HOME/.gitignore` file.)
So what happened here? ripgrep read the contents of `README.md`, and for each
line that contained `fast`, ripgrep printed it to your terminal. ripgrep also
included the line number for each line by default. If your terminal supports
colors, then your output might actually look something like this screenshot:
[![A screenshot of a sample search ripgrep](https://burntsushi.net/stuff/ripgrep-guide-sample.png)](https://burntsushi.net/stuff/ripgrep-guide-sample.png)
In this example, we searched for something called a "literal" string. This
means that our pattern was just some normal text that we asked ripgrep to
find. But ripgrep supports the ability to specify patterns via [regular
expressions](https://en.wikipedia.org/wiki/Regular_expression). As an example,
what if we wanted to find all lines have a word that contains `fast` followed
by some number of other letters?
```
$ rg 'fast\w+' README.md
75: faster than both. (N.B. It is not, strictly speaking, a "drop-in" replacement
119:### Is it really faster than everything else?
```
In this example, we used the pattern `fast\w+`. This pattern tells ripgrep to
look for any lines containing the letters `fast` followed by *one or more*
word-like characters. Namely, `\w` matches characters that compose words (like
`a` and `L` but unlike `.` and ` `). The `+` after the `\w` means, "match the
previous pattern one or more times." This means that the word `fast` won't
match because there are no word characters following the final `t`. But a word
like `faster` will. `faste` would also match!
Here's a different variation on this same theme:
```
$ rg 'fast\w*' README.md
75: faster than both. (N.B. It is not, strictly speaking, a "drop-in" replacement
88: color and full Unicode support. Unlike GNU grep, `ripgrep` stays fast while
119:### Is it really faster than everything else?
124:Summarizing, `ripgrep` is fast because:
129: optimizations to make searching very fast.
```
In this case, we used `fast\w*` for our pattern instead of `fast\w+`. The `*`
means that it should match *zero* or more times. In this case, ripgrep will
print the same lines as the pattern `fast`, but if your terminal supports
colors, you'll notice that `faster` will be highlighted instead of just the
`fast` prefix.
It is beyond the scope of this guide to provide a full tutorial on regular
expressions, but ripgrep's specific syntax is documented here:
https://docs.rs/regex/0.2.5/regex/#syntax
### Recursive search
In the previous section, we showed how to use ripgrep to search a single file.
In this section, we'll show how to use ripgrep to search an entire directory
of files. In fact, *recursively* searching your current working directory is
the default mode of operation for ripgrep, which means doing this is very
simple.
Using our unzipped archive of ripgrep source code, here's how to find all
function definitions whose name is `write`:
```
$ rg 'fn write\('
src/printer.rs
469: fn write(&mut self, buf: &[u8]) {
termcolor/src/lib.rs
227: fn write(&mut self, b: &[u8]) -> io::Result<usize> {
250: fn write(&mut self, b: &[u8]) -> io::Result<usize> {
428: fn write(&mut self, b: &[u8]) -> io::Result<usize> { self.wtr.write(b) }
441: fn write(&mut self, b: &[u8]) -> io::Result<usize> { self.wtr.write(b) }
454: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
511: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
848: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
915: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
949: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
1114: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
1348: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
1353: fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
```
(**Note:** We escape the `(` here because `(` has special significance inside
regular expressions. You could also use `rg -F 'fn write('` to achieve the
same thing, where `-F` interprets your pattern as a literal string instead of
a regular expression.)
In this example, we didn't specify a file at all. Instead, ripgrep defaulted
to searching your current directory in the absence of a path. In general,
`rg foo` is equivalent to `rg foo ./`.
This particular search showed us results in both the `src` and `termcolor`
directories. The `src` directory is the core ripgrep code where as `termcolor`
is a dependency of ripgrep (and is used by other tools). What if we only wanted
to search core ripgrep code? Well, that's easy, just specify the directory you
want:
```
$ rg 'fn write\(' src
src/printer.rs
469: fn write(&mut self, buf: &[u8]) {
```
Here, ripgrep limited its search to the `src` directory. Another way of doing
this search would be to `cd` into the `src` directory and simply use `rg 'fn
write\('` again.
### Automatic filtering
After recursive search, ripgrep's most important feature is what it *doesn't*
search. By default, when you search a directory, ripgrep will ignore all of
the following:
1. Files and directories that match the rules in your `.gitignore` glob
pattern.
2. Hidden files and directories.
3. Binary files. (ripgrep considers any file with a `NUL` byte to be binary.)
4. Symbolic links aren't followed.
All of these things can be toggled using various flags provided by ripgrep:
1. You can disable `.gitignore` handling with the `--no-ignore` flag.
2. Hidden files and directories can be searched with the `--hidden` flag.
3. Binary files can be searched via the `--text` (`-a` for short) flag.
Be careful with this flag! Binary files may emit control characters to your
terminal, which might cause strange behavior.
4. ripgrep can follow symlinks with the `--follow` (`-L` for short) flag.
As a special convenience, ripgrep also provides a flag called `--unrestricted`
(`-u` for short). Repeated uses of this flag will cause ripgrep to disable
more and more of its filtering. That is, `-u` will disable `.gitignore`
handling, `-uu` will search hidden files and directories and `-uuu` will search
binary files. This is useful when you're using ripgrep and you aren't sure
whether its filtering is hiding results from you. Tacking on a couple `-u`
flags is a quick way to find out. (Use the `--debug` flag if you're still
perplexed, and if that doesn't help,
[file an issue](https://github.com/BurntSushi/ripgrep/issues/new).)
ripgrep's `.gitignore` handling actually goes a bit beyond just `.gitignore`
files. ripgrep will also respect repository specific rules found in
`$GIT_DIR/info/exclude`, as well as any global ignore rules in your
`core.excludesFile` (which is usually `$XDG_CONFIG_HOME/git/ignore` on
Unix-like systems).
Sometimes you want to search files that are in your `.gitignore`, so it is
possible to specify additional ignore rules or overrides in a `.ignore`
(application agnostic) or `.rgignore` (ripgrep specific) file.
For example, let's say you have a `.gitignore` file that looks like this:
```
log/
```
This generally means that any `log` directory won't be tracked by `git`.
However, perhaps it contains useful output that you'd like to include in your
searches, but you still don't want to track it in `git`. You can achieve this
by creating a `.ignore` file in the same directory as the `.gitignore` file
with the following contents:
```
!log/
```
ripgrep treats `.ignore` files with higher precedence than `.gitignore` files
(and treats `.rgignore` files with higher precedence than `.ignore` files).
This means ripgrep will see the `!log/` whitelist rule first and search that
directory.
Like `.gitignore`, a `.ignore` file can be placed in any directory. Its rules
will be processed with respect to the directory it resides in, just like
`.gitignore`.
To process `.gitignore` and `.ignore` files case insensitively, use the flag
`--ignore-file-case-insensitive`. This is especially useful on case insensitive
file systems like those on Windows and macOS. Note though that this can come
with a significant performance penalty, and is therefore disabled by default.
For a more in depth description of how glob patterns in a `.gitignore` file
are interpreted, please see `man gitignore`.
### Manual filtering: globs
In the previous section, we talked about ripgrep's filtering that it does by
default. It is "automatic" because it reacts to your environment. That is, it
uses already existing `.gitignore` files to produce more relevant search
results.
In addition to automatic filtering, ripgrep also provides more manual or ad hoc
filtering. This comes in two varieties: additional glob patterns specified in
your ripgrep commands and file type filtering. This section covers glob
patterns while the next section covers file type filtering.
In our ripgrep source code (see [Basics](#basics) for instructions on how to
get a source archive to search), let's say we wanted to see which things depend
on `clap`, our argument parser.
We could do this:
```
$ rg clap
[lots of results]
```
But this shows us many things, and we're only interested in where we wrote
`clap` as a dependency. Instead, we could limit ourselves to TOML files, which
is how dependencies are communicated to Rust's build tool, Cargo:
```
$ rg clap -g '*.toml'
Cargo.toml
35:clap = "2.26"
51:clap = "2.26"
```
The `-g '*.toml'` syntax says, "make sure every file searched matches this
glob pattern." Note that we put `'*.toml'` in single quotes to prevent our
shell from expanding the `*`.
If we wanted, we could tell ripgrep to search anything *but* `*.toml` files:
```
$ rg clap -g '!*.toml'
[lots of results]
```
This will give you a lot of results again as above, but they won't include
files ending with `.toml`. Note that the use of a `!` here to mean "negation"
is a bit non-standard, but it was chosen to be consistent with how globs in
`.gitignore` files are written. (Although, the meaning is reversed. In
`.gitignore` files, a `!` prefix means whitelist, and on the command line, a
`!` means blacklist.)
Globs are interpreted in exactly the same way as `.gitignore` patterns. That
is, later globs will override earlier globs. For example, the following command
will search only `*.toml` files:
```
$ rg clap -g '!*.toml' -g '*.toml'
```
Interestingly, reversing the order of the globs in this case will match
nothing, since the presence of at least one non-blacklist glob will institute a
requirement that every file searched must match at least one glob. In this
case, the blacklist glob takes precedence over the previous glob and prevents
any file from being searched at all!
### Manual filtering: file types
Over time, you might notice that you use the same glob patterns over and over.
For example, you might find yourself doing a lot of searches where you only
want to see results for Rust files:
```
$ rg 'fn run' -g '*.rs'
```
Instead of writing out the glob every time, you can use ripgrep's support for
file types:
```
$ rg 'fn run' --type rust
```
or, more succinctly,
```
$ rg 'fn run' -trust
```
The way the `--type` flag functions is simple. It acts as a name that is
assigned to one or more globs that match the relevant files. This lets you
write a single type that might encompass a broad range of file extensions. For
example, if you wanted to search C files, you'd have to check both C source
files and C header files:
```
$ rg 'int main' -g '*.{c,h}'
```
or you could just use the C file type:
```
$ rg 'int main' -tc
```
Just as you can write blacklist globs, you can blacklist file types too:
```
$ rg clap --type-not rust
```
or, more succinctly,
```
$ rg clap -Trust
```
That is, `-t` means "include files of this type" where as `-T` means "exclude
files of this type."
To see the globs that make up a type, run `rg --type-list`:
```
$ rg --type-list | rg '^make:'
make: *.mak, *.mk, GNUmakefile, Gnumakefile, Makefile, gnumakefile, makefile
```
By default, ripgrep comes with a bunch of pre-defined types. Generally, these
types correspond to well known public formats. But you can define your own
types as well. For example, perhaps you frequently search "web" files, which
consist of Javascript, HTML and CSS:
```
$ rg --type-add 'web:*.html' --type-add 'web:*.css' --type-add 'web:*.js' -tweb title
```
or, more succinctly,
```
$ rg --type-add 'web:*.{html,css,js}' -tweb title
```
The above command defines a new type, `web`, corresponding to the glob
`*.{html,css,js}`. It then applies the new filter with `-tweb` and searches for
the pattern `title`. If you ran
```
$ rg --type-add 'web:*.{html,css,js}' --type-list
```
Then you would see your `web` type show up in the list, even though it is not
part of ripgrep's built-in types.
It is important to stress here that the `--type-add` flag only applies to the
current command. It does not add a new file type and save it somewhere in a
persistent form. If you want a type to be available in every ripgrep command,
then you should either create a shell alias:
```
alias rg="rg --type-add 'web:*.{html,css,js}'"
```
or add `--type-add=web:*.{html,css,js}` to your ripgrep configuration file.
([Configuration files](#configuration-file) are covered in more detail later.)
### Replacements
ripgrep provides a limited ability to modify its output by replacing matched
text with some other text. This is easiest to explain with an example. Remember
when we searched for the word `fast` in ripgrep's README?
```
$ rg fast README.md
75: faster than both. (N.B. It is not, strictly speaking, a "drop-in" replacement
88: color and full Unicode support. Unlike GNU grep, `ripgrep` stays fast while
119:### Is it really faster than everything else?
124:Summarizing, `ripgrep` is fast because:
129: optimizations to make searching very fast.
```
What if we wanted to *replace* all occurrences of `fast` with `FAST`? That's
easy with ripgrep's `--replace` flag:
```
$ rg fast README.md --replace FAST
75: FASTer than both. (N.B. It is not, strictly speaking, a "drop-in" replacement
88: color and full Unicode support. Unlike GNU grep, `ripgrep` stays FAST while
119:### Is it really FASTer than everything else?
124:Summarizing, `ripgrep` is FAST because:
129: optimizations to make searching very FAST.
```
or, more succinctly,
```
$ rg fast README.md -r FAST
[snip]
```
In essence, the `--replace` flag applies *only* to the matching portion of text
in the output. If you instead wanted to replace an entire line of text, then
you need to include the entire line in your match. For example:
```
$ rg '^.*fast.*$' README.md -r FAST
75:FAST
88:FAST
119:FAST
124:FAST
129:FAST
```
Alternatively, you can combine the `--only-matching` (or `-o` for short) with
the `--replace` flag to achieve the same result:
```
$ rg fast README.md --only-matching --replace FAST
75:FAST
88:FAST
119:FAST
124:FAST
129:FAST
```
or, more succinctly,
```
$ rg fast README.md -or FAST
[snip]
```
Finally, replacements can include capturing groups. For example, let's say
we wanted to find all occurrences of `fast` followed by another word and
join them together with a dash. The pattern we might use for that is
`fast\s+(\w+)`, which matches `fast`, followed by any amount of whitespace,
followed by any number of "word" characters. We put the `\w+` in a "capturing
group" (indicated by parentheses) so that we can reference it later in our
replacement string. For example:
```
$ rg 'fast\s+(\w+)' README.md -r 'fast-$1'
88: color and full Unicode support. Unlike GNU grep, `ripgrep` stays fast-while
124:Summarizing, `ripgrep` is fast-because:
```
Our replacement string here, `fast-$1`, consists of `fast-` followed by the
contents of the capturing group at index `1`. (Capturing groups actually start
at index 0, but the `0`th capturing group always corresponds to the entire
match. The capturing group at index `1` always corresponds to the first
explicit capturing group found in the regex pattern.)
Capturing groups can also be named, which is sometimes more convenient than
using the indices. For example, the following command is equivalent to the
above command:
```
$ rg 'fast\s+(?P<word>\w+)' README.md -r 'fast-$word'
88: color and full Unicode support. Unlike GNU grep, `ripgrep` stays fast-while
124:Summarizing, `ripgrep` is fast-because:
```
It is important to note that ripgrep **will never modify your files**. The
`--replace` flag only controls ripgrep's output. (And there is no flag to let
you do a replacement in a file.)
### Configuration file
It is possible that ripgrep's default options aren't suitable in every case.
For that reason, and because shell aliases aren't always convenient, ripgrep
supports configuration files.
Setting up a configuration file is simple. ripgrep will not look in any
predetermined directory for a config file automatically. Instead, you need to
set the `RIPGREP_CONFIG_PATH` environment variable to the file path of your
config file. Once the environment variable is set, open the file and just type
in the flags you want set automatically. There are only two rules for
describing the format of the config file:
1. Every line is a shell argument, after trimming whitespace.
2. Lines starting with `#` (optionally preceded by any amount of whitespace)
are ignored.
In particular, there is no escaping. Each line is given to ripgrep as a single
command line argument verbatim.
Here's an example of a configuration file, which demonstrates some of the
formatting peculiarities:
```
$ cat $HOME/.ripgreprc
# Don't let ripgrep vomit really long lines to my terminal.
--max-columns=150
# Add my 'web' type.
--type-add
web:*.{html,css,js}*
# Using glob patterns to include/exclude files or folders
--glob=!git/*
# or
--glob
!git/*
# Set the colors.
--colors=line:none
--colors=line:style:bold
# Because who cares about case!?
--smart-case
```
When we use a flag that has a value, we either put the flag and the value on
the same line but delimited by an `=` sign (e.g., `--max-columns=150`), or we
put the flag and the value on two different lines. This is because ripgrep's
argument parser knows to treat the single argument `--max-columns=150` as a
flag with a value, but if we had written `--max-columns 150` in our
configuration file, then ripgrep's argument parser wouldn't know what to do
with it.
Putting the flag and value on different lines is exactly equivalent and is a
matter of style.
Comments are encouraged so that you remember what the config is doing. Empty
lines are OK too.
So let's say you're using the above configuration file, but while you're at a
terminal, you really want to be able to see lines longer than 150 columns. What
do you do? Thankfully, all you need to do is pass `--max-columns 0` (or `-M0`
for short) on the command line, which will override your configuration file's
setting. This works because ripgrep's configuration file is *prepended* to the
explicit arguments you give it on the command line. Since flags given later
override flags given earlier, everything works as expected. This works for most
other flags as well, and each flag's documentation states which other flags
override it.
If you're confused about what configuration file ripgrep is reading arguments
from, then running ripgrep with the `--debug` flag should help clarify things.
The debug output should note what config file is being loaded and the arguments
that have been read from the configuration.
Finally, if you want to make absolutely sure that ripgrep *isn't* reading a
configuration file, then you can pass the `--no-config` flag, which will always
prevent ripgrep from reading extraneous configuration from the environment,
regardless of what other methods of configuration are added to ripgrep in the
future.
### File encoding
[Text encoding](https://en.wikipedia.org/wiki/Character_encoding) is a complex
topic, but we can try to summarize its relevancy to ripgrep:
* Files are generally just a bundle of bytes. There is no reliable way to know
their encoding.
* Either the encoding of the pattern must match the encoding of the files being
searched, or a form of transcoding must be performed that converts either the
pattern or the file to the same encoding as the other.
* ripgrep tends to work best on plain text files, and among plain text files,
the most popular encodings likely consist of ASCII, latin1 or UTF-8. As
a special exception, UTF-16 is prevalent in Windows environments
In light of the above, here is how ripgrep behaves when `--encoding auto` is
given, which is the default:
* All input is assumed to be ASCII compatible (which means every byte that
corresponds to an ASCII codepoint actually is an ASCII codepoint). This
includes ASCII itself, latin1 and UTF-8.
* ripgrep works best with UTF-8. For example, ripgrep's regular expression
engine supports Unicode features. Namely, character classes like `\w` will
match all word characters by Unicode's definition and `.` will match any
Unicode codepoint instead of any byte. These constructions assume UTF-8,
so they simply won't match when they come across bytes in a file that aren't
UTF-8.
* To handle the UTF-16 case, ripgrep will do something called "BOM sniffing"
by default. That is, the first three bytes of a file will be read, and if
they correspond to a UTF-16 BOM, then ripgrep will transcode the contents of
the file from UTF-16 to UTF-8, and then execute the search on the transcoded
version of the file. (This incurs a performance penalty since transcoding
is slower than regex searching.) If the file contains invalid UTF-16, then
the Unicode replacement codepoint is substituted in place of invalid code
units.
* To handle other cases, ripgrep provides a `-E/--encoding` flag, which permits
you to specify an encoding from the
[Encoding Standard](https://encoding.spec.whatwg.org/#concept-encoding-get).
ripgrep will assume *all* files searched are the encoding specified (unless
the file has a BOM) and will perform a transcoding step just like in the
UTF-16 case described above.
By default, ripgrep will not require its input be valid UTF-8. That is, ripgrep
can and will search arbitrary bytes. The key here is that if you're searching
content that isn't UTF-8, then the usefulness of your pattern will degrade. If
you're searching bytes that aren't ASCII compatible, then it's likely the
pattern won't find anything. With all that said, this mode of operation is
important, because it lets you find ASCII or UTF-8 *within* files that are
otherwise arbitrary bytes.
As a special case, the `-E/--encoding` flag supports the value `none`, which
will completely disable all encoding related logic, including BOM sniffing.
When `-E/--encoding` is set to `none`, ripgrep will search the raw bytes of
the underlying file with no transcoding step. For example, here's how you might
search the raw UTF-16 encoding of the string `Шерлок`:
```
$ rg '(?-u)\(\x045\x04@\x04;\x04>\x04:\x04' -E none -a some-utf16-file
```
Of course, that's just an example meant to show how one can drop down into
raw bytes. Namely, the simpler command works as you might expect automatically:
```
$ rg 'Шерлок' some-utf16-file
```
Finally, it is possible to disable ripgrep's Unicode support from within the
regular expression. For example, let's say you wanted `.` to match any byte
rather than any Unicode codepoint. (You might want this while searching a
binary file, since `.` by default will not match invalid UTF-8.) You could do
this by disabling Unicode via a regular expression flag:
```
$ rg '(?-u:.)'
```
This works for any part of the pattern. For example, the following will find
any Unicode word character followed by any ASCII word character followed by
another Unicode word character:
```
$ rg '\w(?-u:\w)\w'
```
### Common options
ripgrep has a lot of flags. Too many to keep in your head at once. This section
is intended to give you a sampling of some of the most important and frequently
used options that will likely impact how you use ripgrep on a regular basis.
* `-h`: Show ripgrep's condensed help output.
* `--help`: Show ripgrep's longer form help output. (Nearly what you'd find in
ripgrep's man page, so pipe it into a pager!)
* `-i/--ignore-case`: When searching for a pattern, ignore case differences.
That is `rg -i fast` matches `fast`, `fASt`, `FAST`, etc.
* `-S/--smart-case`: This is similar to `--ignore-case`, but disables itself
if the pattern contains any uppercase letters. Usually this flag is put into
alias or a config file.
* `-w/--word-regexp`: Require that all matches of the pattern be surrounded
by word boundaries. That is, given `pattern`, the `--word-regexp` flag will
cause ripgrep to behave as if `pattern` were actually `\b(?:pattern)\b`.
* `-c/--count`: Report a count of total matched lines.
* `--files`: Print the files that ripgrep *would* search, but don't actually
search them.
* `-a/--text`: Search binary files as if they were plain text.
* `-z/--search-zip`: Search compressed files (gzip, bzip2, lzma, xz, lz4,
brotli, zstd). This is disabled by default.
* `-C/--context`: Show the lines surrounding a match.
* `--sort path`: Force ripgrep to sort its output by file name. (This disables
parallelism, so it might be slower.)
* `-L/--follow`: Follow symbolic links while recursively searching.
* `-M/--max-columns`: Limit the length of lines printed by ripgrep.
* `--debug`: Shows ripgrep's debug output. This is useful for understanding
why a particular file might be ignored from search, or what kinds of
configuration ripgrep is loading from the environment.

53
ISSUE_TEMPLATE.md Normal file
View File

@@ -0,0 +1,53 @@
#### What version of ripgrep are you using?
Replace this text with the output of `rg --version`.
#### How did you install ripgrep?
If you installed ripgrep with snap and are getting strange file permission or
file not found errors, then please do not file a bug. Instead, use one of the
Github binary releases.
#### What operating system are you using ripgrep on?
Replace this text with your operating system and version.
#### Describe your question, feature request, or bug.
If a question, please describe the problem you're trying to solve and give
as much context as possible.
If a feature request, please describe the behavior you want and the motivation.
Please also provide an example of how ripgrep would be used if your feature
request were added.
If a bug, please see below.
#### If this is a bug, what are the steps to reproduce the behavior?
If possible, please include both your search patterns and the corpus on which
you are searching. Unless the bug is very obvious, then it is unlikely that it
will be fixed if the ripgrep maintainers cannot reproduce it.
If the corpus is too big and you cannot decrease its size, file the bug anyway
and the ripgrep maintainers will help figure out next steps.
#### If this is a bug, what is the actual behavior?
Show the command you ran and the actual output. Include the `--debug` flag in
your invocation of ripgrep.
If the output is large, put it in a gist: https://gist.github.com/
If the output is small, put it in code fences:
```
your
output
goes
here
```
#### If this is a bug, what is the expected behavior?
What do you think ripgrep should have done?

591
README.md
View File

@@ -1,160 +1,206 @@
ripgrep (rg)
------------
`ripgrep` is a line oriented search tool that combines the usability of The
Silver Searcher (similar to `ack`) with the raw speed of GNU grep. `ripgrep`
works by recursively searching your current directory for a regex pattern.
`ripgrep` has first class support on Windows, Mac and Linux, with binary
downloads available for
[every release](https://github.com/BurntSushi/ripgrep/releases).
ripgrep is a line-oriented search tool that recursively searches your current
directory for a regex pattern. By default, ripgrep will respect your .gitignore
and automatically skip hidden files/directories and binary files. ripgrep
has first class support on Windows, macOS and Linux, with binary downloads
available for [every release](https://github.com/BurntSushi/ripgrep/releases).
ripgrep is similar to other popular search tools like The Silver Searcher, ack
and grep.
[![Linux build status](https://travis-ci.org/BurntSushi/ripgrep.svg?branch=master)](https://travis-ci.org/BurntSushi/ripgrep)
[![Linux build status](https://travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/ripgrep.svg)](https://crates.io/crates/ripgrep)
[![Crates.io](https://img.shields.io/crates/v/ripgrep.svg)](https://crates.io/crates/ripgrep)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
### CHANGELOG
Please see the [CHANGELOG](CHANGELOG.md) for a release history.
### Documentation quick links
* [Installation](#installation)
* [User Guide](GUIDE.md)
* [Frequently Asked Questions](FAQ.md)
* [Regex syntax](https://docs.rs/regex/1/regex/#syntax)
* [Configuration files](GUIDE.md#configuration-file)
* [Shell completions](FAQ.md#complete)
* [Building](#building)
### Screenshot of search results
[![A screenshot of a sample search with ripgrep](http://burntsushi.net/stuff/ripgrep1.png)](http://burntsushi.net/stuff/ripgrep1.png)
### Quick examples comparing tools
This example searches the entire Linux kernel source tree (after running
`make defconfig && make -j8`) for `[A-Z]+_SUSPEND`, where all matches must be
words. Timings were collected on a system with an Intel i7-6900K 3.2 GHz, and
ripgrep was compiled using the `compile` script in this repo.
ripgrep was compiled with SIMD enabled.
Please remember that a single benchmark is never enough! See my
[blog post on `ripgrep`](http://blog.burntsushi.net/ripgrep/)
[blog post on ripgrep](http://blog.burntsushi.net/ripgrep/)
for a very detailed comparison with more benchmarks and analysis.
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep (Unicode) | `rg -n -w '[A-Z]+_SUSPEND'` | 450 | **0.134s** |
| [The Silver Searcher](https://github.com/ggreer/the_silver_searcher) | `ag -w '[A-Z]+_SUSPEND'` | 450 | 0.753s |
| [git grep](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=C git grep -E -n -w '[A-Z]+_SUSPEND'` | 450 | 0.823s |
| [git grep (Unicode)](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=en_US.UTF-8 git grep -E -n -w '[A-Z]+_SUSPEND'` | 450 | 2.880s |
| [sift](https://github.com/svent/sift) | `sift --git -n -w '[A-Z]+_SUSPEND'` | 450 | 3.656s |
| [The Platinum Searcher](https://github.com/monochromegane/the_platinum_searcher) | `pt -w -e '[A-Z]+_SUSPEND'` | 450 | 12.369s |
| [ack](https://github.com/petdance/ack2) | `ack -w '[A-Z]+_SUSPEND'` | 1878 | 16.952s |
| ripgrep (Unicode) | `rg -n -w '[A-Z]+_SUSPEND'` | 450 | **0.106s** |
| [git grep](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=C git grep -E -n -w '[A-Z]+_SUSPEND'` | 450 | 0.553s |
| [The Silver Searcher](https://github.com/ggreer/the_silver_searcher) | `ag -w '[A-Z]+_SUSPEND'` | 450 | 0.589s |
| [git grep (Unicode)](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=en_US.UTF-8 git grep -E -n -w '[A-Z]+_SUSPEND'` | 450 | 2.266s |
| [sift](https://github.com/svent/sift) | `sift --git -n -w '[A-Z]+_SUSPEND'` | 450 | 3.505s |
| [ack](https://github.com/petdance/ack2) | `ack -w '[A-Z]+_SUSPEND'` | 1878 | 6.823s |
| [The Platinum Searcher](https://github.com/monochromegane/the_platinum_searcher) | `pt -w -e '[A-Z]+_SUSPEND'` | 450 | 14.208s |
(Yes, `ack` [has](https://github.com/petdance/ack2/issues/445) a
[bug](https://github.com/petdance/ack2/issues/14).)
Here's another benchmark that disregards gitignore files and searches with a
whitelist instead. The corpus is the same as in the previous benchmark, and the
flags passed to each command ensures that they are doing equivalent work:
flags passed to each command ensure that they are doing equivalent work:
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep | `rg -L -u -tc -n -w '[A-Z]+_SUSPEND'` | 404 | **0.108s** |
| [ucg](https://github.com/gvansickle/ucg) | `ucg --type=cc -w '[A-Z]+_SUSPEND'` | 392 | 0.219s |
| [GNU grep](https://www.gnu.org/software/grep/) | `egrep -R -n --include='*.c' --include='*.h' -w '[A-Z]+_SUSPEND'` | 404 | 0.733s |
| ripgrep | `rg -L -u -tc -n -w '[A-Z]+_SUSPEND'` | 404 | **0.079s** |
| [ucg](https://github.com/gvansickle/ucg) | `ucg --type=cc -w '[A-Z]+_SUSPEND'` | 390 | 0.163s |
| [GNU grep](https://www.gnu.org/software/grep/) | `egrep -R -n --include='*.c' --include='*.h' -w '[A-Z]+_SUSPEND'` | 404 | 0.611s |
(`ucg` [has slightly different behavior in the presence of symbolic links](https://github.com/gvansickle/ucg/issues/106).)
And finally, a straight up comparison between ripgrep and GNU grep on a single
And finally, a straight-up comparison between ripgrep and GNU grep on a single
large file (~9.3GB,
[`OpenSubtitles2016.raw.en.gz`](http://opus.lingfil.uu.se/OpenSubtitles2016/mono/OpenSubtitles2016.raw.en.gz)):
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep | `rg -w 'Sherlock [A-Z]\w+'` | 5268 | **2.520s** |
| [GNU grep](https://www.gnu.org/software/grep/) | `LC_ALL=C egrep -w 'Sherlock [A-Z]\w+'` | 5268 | 7.143s |
| ripgrep | `rg -w 'Sherlock [A-Z]\w+'` | 5268 | **2.108s** |
| [GNU grep](https://www.gnu.org/software/grep/) | `LC_ALL=C egrep -w 'Sherlock [A-Z]\w+'` | 5268 | 7.014s |
In the above benchmark, passing the `-n` flag (for showing line numbers)
increases the times to `3.081s` for ripgrep and `11.403s` for GNU grep.
increases the times to `2.640s` for ripgrep and `10.277s` for GNU grep.
### Why should I use `ripgrep`?
* It can replace both The Silver Searcher and GNU grep because it is faster
than both. (N.B. It is not, strictly speaking, a "drop-in" replacement for
both, but the feature sets are far more similar than different.)
* Like The Silver Searcher, `ripgrep` defaults to recursive directory search
and won't search files ignored by your `.gitignore` files. It also ignores
hidden and binary files by default. `ripgrep` also implements full support
for `.gitignore`, where as there are many bugs related to that functionality
in The Silver Searcher.
* `ripgrep` can search specific types of files. For example, `rg -tpy foo`
### Why should I use ripgrep?
* It can replace many use cases served by other search tools
because it contains most of their features and is generally faster. (See
[the FAQ](FAQ.md#posix4ever) for more details on whether ripgrep can truly
replace grep.)
* Like other tools specialized to code search, ripgrep defaults to recursive
directory search and won't search files ignored by your `.gitignore` files.
It also ignores hidden and binary files by default. ripgrep also implements
full support for `.gitignore`, whereas there are many bugs related to that
functionality in other code search tools claiming to provide the same
functionality.
* ripgrep can search specific types of files. For example, `rg -tpy foo`
limits your search to Python files and `rg -Tjs foo` excludes Javascript
files from your search. `ripgrep` can be taught about new file types with
files from your search. ripgrep can be taught about new file types with
custom matching rules.
* `ripgrep` supports many features found in `grep`, such as showing the context
* ripgrep supports many features found in `grep`, such as showing the context
of search results, searching multiple patterns, highlighting matches with
color and full Unicode support. Unlike GNU grep, `ripgrep` stays fast while
color and full Unicode support. Unlike GNU grep, ripgrep stays fast while
supporting Unicode (which is always on).
* `ripgrep` supports searching files in text encodings other than UTF-8, such
* ripgrep has optional support for switching its regex engine to use PCRE2.
Among other things, this makes it possible to use look-around and
backreferences in your patterns, which are not supported in ripgrep's default
regex engine. PCRE2 support is enabled with `-P`.
* ripgrep supports searching files in text encodings other than UTF-8, such
as UTF-16, latin-1, GBK, EUC-JP, Shift_JIS and more. (Some support for
automatically detecting UTF-16 is provided. Other text encodings must be
specifically specified with the `-E/--encoding` flag.)
* ripgrep supports searching files compressed in a common format (gzip, xz,
lzma, bzip2 or lz4) with the `-z/--search-zip` flag.
* ripgrep supports arbitrary input preprocessing filters which could be PDF
text extraction, less supported decompression, decrypting, automatic encoding
detection and so on.
In other words, use `ripgrep` if you like speed, filtering by default, fewer
In other words, use ripgrep if you like speed, filtering by default, fewer
bugs and Unicode support.
### Why shouldn't I use `ripgrep`?
I'd like to try to convince you why you *shouldn't* use `ripgrep`. This should
give you a glimpse at some important downsides or missing features of
`ripgrep`.
### Why shouldn't I use ripgrep?
* `ripgrep` uses a regex engine based on finite automata, so if you want fancy
regex features such as backreferences or look around, `ripgrep` won't give
them to you. `ripgrep` does support lots of things though, including, but not
limited to: lazy quantification (e.g., `a+?`), repetitions (e.g., `a{2,5}`),
begin/end assertions (e.g., `^\w+$`), word boundaries (e.g., `\bfoo\b`), and
support for Unicode categories (e.g., `\p{Sc}` to match currency symbols or
`\p{Lu}` to match any uppercase letter). (Fancier regexes will never be
supported.)
* `ripgrep` doesn't yet support searching compressed files. (Likely to be
supported in the future.)
* `ripgrep` doesn't have multiline search. (Unlikely to ever be supported.)
Despite initially not wanting to add every feature under the sun to ripgrep,
over time, ripgrep has grown support for most features found in other file
searching tools. This includes searching for results spanning across multiple
lines, and opt-in support for PCRE2, which provides look-around and
backreference support.
At this point, the primary reasons not to use ripgrep probably consist of one
or more of the following:
* You need a portable and ubiquitous tool. While ripgrep works on Windows,
macOS and Linux, it is not ubiquitous and it does not conform to any
standard such as POSIX. The best tool for this job is good old grep.
* There still exists some other feature (or bug) not listed in this README that
you rely on that's in another tool that isn't in ripgrep.
* There is a performance edge case where ripgrep doesn't do well where another
tool does do well. (Please file a bug report!)
* ripgrep isn't possible to install on your machine or isn't available for your
platform. (Please file a bug report!)
In other words, if you like fancy regexes, searching compressed files or
multiline search, then `ripgrep` may not quite meet your needs (yet).
### Is it really faster than everything else?
Yes. A large number of benchmarks with detailed analysis for each is
Generally, yes. A large number of benchmarks with detailed analysis for each is
[available on my blog](http://blog.burntsushi.net/ripgrep/).
Summarizing, `ripgrep` is fast because:
Summarizing, ripgrep is fast because:
* It is built on top of
[Rust's regex engine](https://github.com/rust-lang-nursery/regex).
Rust's regex engine uses finite automata, SIMD and aggressive literal
optimizations to make searching very fast.
optimizations to make searching very fast. (PCRE2 support can be opted into
with the `-P/--pcre2` flag.)
* Rust's regex library maintains performance with full Unicode support by
building UTF-8 decoding directly into its deterministic finite automaton
engine.
* It supports searching with either memory maps or by searching incrementally
with an intermediate buffer. The former is better for single files and the
latter is better for large directories. `ripgrep` chooses the best searching
latter is better for large directories. ripgrep chooses the best searching
strategy for you automatically.
* Applies your ignore patterns in `.gitignore` files using a
[`RegexSet`](https://doc.rust-lang.org/regex/regex/struct.RegexSet.html).
[`RegexSet`](https://docs.rs/regex/1/regex/struct.RegexSet.html).
That means a single file path can be matched against multiple glob patterns
simultaneously.
* It uses a lock-free parallel recursive directory iterator, courtesy of
[`crossbeam`](https://docs.rs/crossbeam) and
[`ignore`](https://docs.rs/ignore).
### Feature comparison
Andy Lester, author of [ack](https://beyondgrep.com/), has published an
excellent table comparing the features of ack, ag, git-grep, GNU grep and
ripgrep: https://beyondgrep.com/feature-comparison/
Note that ripgrep has grown a few significant new features recently that
are not yet present in Andy's table. This includes, but is not limited to,
configuration files, passthru, support for searching compressed files,
multiline search and opt-in fancy regex support via PCRE2.
### Installation
The binary name for `ripgrep` is `rg`.
The binary name for ripgrep is `rg`.
[Binaries for `ripgrep` are available for Windows, Mac and
Linux.](https://github.com/BurntSushi/ripgrep/releases) Linux binaries are
static executables. Windows binaries are available either as built with MinGW
(GNU) or with Microsoft Visual C++ (MSVC). When possible, prefer MSVC over GNU,
but you'll need to have the
[Microsoft VC++ 2015 redistributable](https://www.microsoft.com/en-us/download/details.aspx?id=48145)
**[Archives of precompiled binaries for ripgrep are available for Windows,
macOS and Linux.](https://github.com/BurntSushi/ripgrep/releases)** Users of
platforms not explicitly mentioned below are advised to download one of these
archives.
Linux binaries are static executables. Windows binaries are available either as
built with MinGW (GNU) or with Microsoft Visual C++ (MSVC). When possible,
prefer MSVC over GNU, but you'll need to have the [Microsoft VC++ 2015
redistributable](https://www.microsoft.com/en-us/download/details.aspx?id=48145)
installed.
If you're a **Mac OS X Homebrew** user, then you can install ripgrep either
If you're a **macOS Homebrew** or a **Linuxbrew** user,
then you can install ripgrep either
from homebrew-core, (compiled with rust stable, no SIMD):
```
@@ -166,195 +212,158 @@ optimizations) by utilizing a custom tap:
```
$ brew tap burntsushi/ripgrep https://github.com/BurntSushi/ripgrep.git
$ brew install burntsushi/ripgrep/ripgrep-bin
$ brew install ripgrep-bin
```
If you're a **Windows Chocolatey** user, then you can install `ripgrep` from the [official repo](https://chocolatey.org/packages/ripgrep):
If you're a **MacPorts** user, then you can install ripgrep from the
[official ports](https://www.macports.org/ports.php?by=name&substr=ripgrep):
```
$ sudo port install ripgrep
```
If you're a **Windows Chocolatey** user, then you can install ripgrep from the
[official repo](https://chocolatey.org/packages/ripgrep):
```
$ choco install ripgrep
```
If you're an **Arch Linux** user, then you can install `ripgrep` from the official repos:
If you're a **Windows Scoop** user, then you can install ripgrep from the
[official bucket](https://github.com/lukesampson/scoop/blob/master/bucket/ripgrep.json):
```
$ scoop install ripgrep
```
If you're an **Arch Linux** user, then you can install ripgrep from the official repos:
```
$ pacman -S ripgrep
```
If you're a **Gentoo** user, you can install `ripgrep` from the [official repo](https://packages.gentoo.org/packages/sys-apps/ripgrep):
If you're a **Gentoo** user, you can install ripgrep from the
[official repo](https://packages.gentoo.org/packages/sys-apps/ripgrep):
```
$ emerge ripgrep
$ emerge sys-apps/ripgrep
```
If you're a **Fedora 24+** user, you can install `ripgrep` from [copr](https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/):
If you're a **Fedora** user, you can install ripgrep from official
repositories.
```
$ dnf copr enable carlwgeorge/ripgrep
$ dnf install ripgrep
$ sudo dnf install ripgrep
```
If you're a **RHEL/CentOS 7** user, you can install `ripgrep` from [copr](https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/):
If you're an **openSUSE Leap 15.0** user, you can install ripgrep from the
[utilities repo](https://build.opensuse.org/package/show/utilities/ripgrep):
```
$ yum-config-manager --add-repo=https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/repo/epel-7/carlwgeorge-ripgrep-epel-7.repo
$ yum install ripgrep
$ sudo zypper ar https://download.opensuse.org/repositories/utilities/openSUSE_Leap_15.0/utilities.repo
$ sudo zypper install ripgrep
```
If you're a **Nix** user, you can install `ripgrep` from
If you're an **openSUSE Tumbleweed** user, you can install ripgrep from the
[official repo](http://software.opensuse.org/package/ripgrep):
```
$ sudo zypper install ripgrep
```
If you're a **RHEL/CentOS 7** user, you can install ripgrep from
[copr](https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/):
```
$ sudo yum-config-manager --add-repo=https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/repo/epel-7/carlwgeorge-ripgrep-epel-7.repo
$ sudo yum install ripgrep
```
If you're a **Nix** user, you can install ripgrep from
[nixpkgs](https://github.com/NixOS/nixpkgs/blob/master/pkgs/tools/text/ripgrep/default.nix):
```
$ nix-env --install ripgrep
$ # (Or using the attribute name, which is also `ripgrep`.)
$ # (Or using the attribute name, which is also ripgrep.)
```
If you're a **Rust programmer**, `ripgrep` can be installed with `cargo`. Note
that this requires you to have **Rust 1.12 or newer** installed.
If you're a **Debian** user (or a user of a Debian derivative like **Ubuntu**),
then ripgrep can be installed using a binary `.deb` file provided in each
[ripgrep release](https://github.com/BurntSushi/ripgrep/releases).
```
$ curl -LO https://github.com/BurntSushi/ripgrep/releases/download/0.10.0/ripgrep_0.10.0_amd64.deb
$ sudo dpkg -i ripgrep_0.10.0_amd64.deb
```
If you run Debian Buster (currently Debian testing) or Debian sid, ripgrep is
[officially maintained by Debian](https://tracker.debian.org/pkg/rust-ripgrep).
```
$ sudo apt-get install ripgrep
```
If you're an **Ubuntu Cosmic (18.10)** (or newer) user, ripgrep is
[available](https://launchpad.net/ubuntu/+source/rust-ripgrep) using the same
packaging as Debian:
```
$ sudo apt-get install ripgrep
```
(N.B. Various snaps for ripgrep on Ubuntu are also available, but none of them
seem to work right and generate a number of very strange bug reports that I
don't know how to fix and don't have the time to fix. Therefore, it is no
longer a recommended installation option.)
If you're a **FreeBSD** user, then you can install ripgrep from the
[official ports](https://www.freshports.org/textproc/ripgrep/):
```
# pkg install ripgrep
```
If you're an **OpenBSD** user, then you can install ripgrep from the
[official ports](http://openports.se/textproc/ripgrep):
```
$ doas pkg_add ripgrep
```
If you're a **NetBSD** user, then you can install ripgrep from
[pkgsrc](http://pkgsrc.se/textproc/ripgrep):
```
# pkgin install ripgrep
```
If you're a **Rust programmer**, ripgrep can be installed with `cargo`.
* Note that the minimum supported version of Rust for ripgrep is **1.32.0**,
although ripgrep may work with older versions.
* Note that the binary may be bigger than expected because it contains debug
symbols. This is intentional. To remove debug symbols and therefore reduce
the file size, run `strip` on the binary.
```
$ cargo install ripgrep
```
`ripgrep` isn't currently in any other package repositories.
When compiling with Rust 1.27 or newer, this will automatically enable SIMD
optimizations for search.
ripgrep isn't currently in any other package repositories.
[I'd like to change that](https://github.com/BurntSushi/ripgrep/issues/10).
### Whirlwind tour
The command line usage of `ripgrep` doesn't differ much from other tools that
perform a similar function, so you probably already know how to use `ripgrep`.
The full details can be found in `rg --help`, but let's go on a whirlwind tour.
`ripgrep` detects when its printing to a terminal, and will automatically
colorize your output and show line numbers, just like The Silver Searcher.
Coloring works on Windows too! Colors can be controlled more granularly with
the `--color` flag.
One last thing before we get started: generally speaking, `ripgrep` assumes the
input is reading is UTF-8. However, if ripgrep notices a file is encoded as
UTF-16, then it will know how to search it. For other encodings, you'll need to
explicitly specify them with the `-E/--encoding` flag.
To recursively search the current directory, while respecting all `.gitignore`
files, ignore hidden files and directories and skip binary files:
```
$ rg foobar
```
The above command also respects all `.ignore` files, including in parent
directories. `.ignore` files can be used when `.gitignore` files are
insufficient. In all cases, `.ignore` patterns take precedence over
`.gitignore`.
To ignore all ignore files, use `-u`. To additionally search hidden files
and directories, use `-uu`. To additionally search binary files, use `-uuu`.
(In other words, "search everything, dammit!") In particular, `rg -uuu` is
similar to `grep -a -r`.
```
$ rg -uu foobar # similar to `grep -r`
$ rg -uuu foobar # similar to `grep -a -r`
```
(Tip: If your ignore files aren't being adhered to like you expect, run your
search with the `--debug` flag.)
Make the search case insensitive with `-i`, invert the search with `-v` or
show the 2 lines before and after every search result with `-C2`.
Force all matches to be surrounded by word boundaries with `-w`.
Search and replace (find first and last names and swap them):
```
$ rg '([A-Z][a-z]+)\s+([A-Z][a-z]+)' --replace '$2, $1'
```
Named groups are supported:
```
$ rg '(?P<first>[A-Z][a-z]+)\s+(?P<last>[A-Z][a-z]+)' --replace '$last, $first'
```
Up the ante with full Unicode support, by matching any uppercase Unicode letter
followed by any sequence of lowercase Unicode letters (good luck doing this
with other search tools!):
```
$ rg '(\p{Lu}\p{Ll}+)\s+(\p{Lu}\p{Ll}+)' --replace '$2, $1'
```
Search only files matching a particular glob:
```
$ rg foo -g 'README.*'
```
<!--*-->
Or exclude files matching a particular glob:
```
$ rg foo -g '!*.min.js'
```
Search and return paths matching a particular glob (i.e., `-g` flag in ag/ack):
```
$ rg -g 'doc*' --files
```
Search only HTML and CSS files:
```
$ rg -thtml -tcss foobar
```
Search everything except for Javascript files:
```
$ rg -Tjs foobar
```
To see a list of types supported, run `rg --type-list`. To add a new type, use
`--type-add`, which must be accompanied by a pattern for searching (`rg` won't
persist your type settings):
```
$ rg --type-add 'foo:*.{foo,foobar}' -tfoo bar
```
The type `foo` will now match any file ending with the `.foo` or `.foobar`
extensions.
### Regex syntax
The syntax supported is
[documented as part of Rust's regex library](https://doc.rust-lang.org/regex/regex/index.html#syntax).
### Shell completions
Shell completion files are included in the release tarball for Bash, Fish, Zsh
and PowerShell.
For **bash**, move `complete/rg.bash-completion` to `$XDG_CONFIG_HOME/bash_completion`
or `/etc/bash_completion.d/`.
For **fish**, move `complete/rg.fish` to `$HOME/.config/fish/completions/`.
For **PowerShell**, add `. _rg.ps1` to your PowerShell
[profile](https://technet.microsoft.com/en-us/library/bb613488(v=vs.85).aspx)
(note the leading period). If the `_rg.ps1` file is not on your `PATH`, do
`. /path/to/_rg.ps1` instead.
For **zsh**, move `complete/_rg` to one of your `$fpath` directories.
### Building
`ripgrep` is written in Rust, so you'll need to grab a
ripgrep is written in Rust, so you'll need to grab a
[Rust installation](https://www.rust-lang.org/) in order to compile it.
`ripgrep` compiles with Rust 1.12 (stable) or newer. Building is easy:
ripgrep compiles with Rust 1.32.0 (stable) or newer. In general, ripgrep tracks
the latest stable release of the Rust compiler.
To build ripgrep:
```
$ git clone https://github.com/BurntSushi/ripgrep
@@ -364,118 +373,60 @@ $ ./target/release/rg --version
0.1.3
```
If you have a Rust nightly compiler, then you can enable optional SIMD
acceleration like so:
If you have a Rust nightly compiler and a recent Intel CPU, then you can enable
additional optional SIMD acceleration like so:
```
RUSTFLAGS="-C target-cpu=native" cargo build --release --features 'simd-accel avx-accel'
RUSTFLAGS="-C target-cpu=native" cargo build --release --features 'simd-accel'
```
If your machine doesn't support AVX instructions, then simply remove
`avx-accel` from the features list. Similarly for SIMD.
The `simd-accel` feature enables SIMD support in certain ripgrep dependencies
(responsible for transcoding). They are not necessary to get SIMD optimizations
for search; those are enabled automatically. Hopefully, some day, the
`simd-accel` feature will similarly become unnecessary. **WARNING:** Currently,
enabling this option can increase compilation times dramatically.
Finally, optional PCRE2 support can be built with ripgrep by enabling the
`pcre2` feature:
```
$ cargo build --release --features 'pcre2'
```
(Tip: use `--features 'pcre2 simd-accel'` to also include compile time SIMD
optimizations, which will only work with a nightly compiler.)
Enabling the PCRE2 feature works with a stable Rust compiler and will
attempt to automatically find and link with your system's PCRE2 library via
`pkg-config`. If one doesn't exist, then ripgrep will build PCRE2 from source
using your system's C compiler and then statically link it into the final
executable. Static linking can be forced even when there is an available PCRE2
system library by either building ripgrep with the MUSL target or by setting
`PCRE2_SYS_STATIC=1`.
ripgrep can be built with the MUSL target on Linux by first installing the MUSL
library on your system (consult your friendly neighborhood package manager).
Then you just need to add MUSL support to your Rust toolchain and rebuild
ripgrep, which yields a fully static executable:
```
$ rustup target add x86_64-unknown-linux-musl
$ cargo build --release --target x86_64-unknown-linux-musl
```
Applying the `--features` flag from above works as expected. If you want to
build a static executable with MUSL and with PCRE2, then you will need to have
`musl-gcc` installed, which might be in a separate package from the actual
MUSL library, depending on your Linux distribution.
### Running tests
`ripgrep` is relatively well tested, including both unit tests and integration
ripgrep is relatively well-tested, including both unit tests and integration
tests. To run the full test suite, use:
```
$ cargo test
$ cargo test --all
```
from the repository root.
### Tips
#### Windows Powershell
##### Powershell Profile
To customize powershell on start-up there is a special powershell script that has to be created.
In order to find its location run command `Get-Command $profile | Select-Object -ExpandProperty Definition`
See [more](https://technet.microsoft.com/en-us/library/bb613488(v=vs.85).aspx) for profile details.
Any powershell code in this file gets evaluated at the start of console.
This way you can have own aliases to be created at start.
##### Setup function alias
Often you can find a need to make alias for the favourite utility.
But powershell function aliases do not behave like your typical linux shell alias.
You always need to propagate arguments and **Stdin** input.
But it cannot be done simply as `function grep() { $input | rg.exe --hidden $args }`
Use below example as reference to how setup alias in powershell.
```powershell
function grep {
$count = @($input).Count
$input.Reset()
if ($count) {
$input | rg.exe --hidden $args
}
else {
rg.exe --hidden $args
}
}
```
Powershell special variables:
* input - is powershell **Stdin** object that allows you to access its content.
* args - is array of arguments passed to this function.
This alias checks whether there is **Stdin** input and propagates only if there is some lines.
Otherwise empty `$input` will make powershell to trigger `rg` to search empty **Stdin**
##### Piping non-ASCII content to ripgrep
When piping input into native executables in PowerShell, the encoding of the
input is controlled by the `$OutputEncoding` variable. By default, this is set
to US-ASCII, and any characters in the pipeline that don't have encodings in
US-ASCII are converted to `?` (question mark) characters.
To change this setting, set `$OutputEncoding` to a different encoding, as
represented by a .NET encoding object. Some common examples are below. The
value of this variable is reset when PowerShell restarts, so to make this
change take effect every time PowerShell is started add a line setting the
variable into your PowerShell profile.
Example `$OutputEncoding` settings:
* UTF-8 without BOM: `$OutputEncoding = [System.Text.UTF8Encoding]::new()`
* The console's output encoding:
`$OutputEncoding = [System.Console]::OutputEncoding`
If you continue to have encoding problems, you can also force the encoding
that the console will use for printing to UTF-8 with
`[System.Console]::OutputEncoding = [System.Text.Encoding]::UTF8`. This
will also reset when PowerShell is restarted, so you can add that line
to your profile as well if you want to make the setting permanent.
### Known issues
#### I just hit Ctrl+C in the middle of ripgrep's output and now my terminal's foreground color is wrong!
Type in `color` in cmd.exe (Command Prompt) and `echo -ne "\033[0m"` on Unix
to restore your original foreground color.
In PowerShell, you can add the following code to your profile which will
restore the original foreground color when `Reset-ForegroundColor` is called.
Including the `Set-Alias` line will allow you to call it with simply `color`.
```powershell
$OrigFgColor = $Host.UI.RawUI.ForegroundColor
function Reset-ForegroundColor {
$Host.UI.RawUI.ForegroundColor = $OrigFgColor
}
Set-Alias -Name color -Value Reset-ForegroundColor
```
PR [#187](https://github.com/BurntSushi/ripgrep/pull/187) fixed this, and it
was later deprecated in
[#281](https://github.com/BurntSushi/ripgrep/issues/281). A full explanation is
available [here][msys issue explanation].
[msys issue explanation]: https://github.com/BurntSushi/ripgrep/issues/281#issuecomment-269093893

57
appveyor.yml
View File

@@ -1,16 +1,39 @@
cache:
- c:\cargo\registry
- c:\cargo\git
init:
- mkdir c:\cargo
- mkdir c:\rustup
- SET PATH=c:\cargo\bin;%PATH%
clone_folder: c:\projects\ripgrep
environment:
CARGO_HOME: "c:\\cargo"
RUSTUP_HOME: "c:\\rustup"
CARGO_TARGET_DIR: "c:\\projects\\ripgrep\\target"
global:
PROJECT_NAME: ripgrep
RUST_BACKTRACE: full
matrix:
- TARGET: i686-pc-windows-gnu
CHANNEL: stable
- TARGET: i686-pc-windows-msvc
CHANNEL: stable
- TARGET: x86_64-pc-windows-gnu
CHANNEL: stable
BITS: 64
MSYS2: 1
- TARGET: x86_64-pc-windows-msvc
CHANNEL: stable
BITS: 64
- TARGET: i686-pc-windows-gnu
CHANNEL: stable
BITS: 32
MSYS2: 1
- TARGET: i686-pc-windows-msvc
CHANNEL: stable
BITS: 32
matrix:
fast_finish: true
# Install Rust and Cargo
# (Based on from https://github.com/rust-lang/libc/blob/master/appveyor.yml)
@@ -18,32 +41,25 @@ install:
- curl -sSf -o rustup-init.exe https://win.rustup.rs/
- rustup-init.exe -y --default-host %TARGET%
- set PATH=%PATH%;C:\Users\appveyor\.cargo\bin
- if defined MSYS2_BITS set PATH=%PATH%;C:\msys64\mingw%MSYS2_BITS%\bin
- if defined MSYS2 set PATH=C:\msys64\mingw%BITS%\bin;%PATH%
- rustc -V
- cargo -V
# ???
# Hack to work around a harmless warning in Appveyor builds?
build: false
# Equivalent to Travis' `script` phase
# TODO modify this phase as you see fit
test_script:
- cargo test --verbose
- cargo test --verbose --manifest-path grep/Cargo.toml
- cargo test --verbose --manifest-path globset/Cargo.toml
- cargo test --verbose --manifest-path ignore/Cargo.toml
- cargo test --verbose --manifest-path wincolor/Cargo.toml
- cargo test --verbose --manifest-path termcolor/Cargo.toml
- cargo test --verbose --all --features pcre2
before_deploy:
# Generate artifacts for release
# TODO(burntsushi): How can we enable SSSE3 on Windows?
- cargo build --release
- cargo build --release --features pcre2
- mkdir staging
- copy target\release\rg.exe staging
- ps: copy target\release\build\ripgrep-*\out\_rg.ps1 staging
- cd staging
# release zipfile will look like 'rust-everywhere-v1.2.3-x86_64-pc-windows-msvc'
# release zipfile will look like 'ripgrep-1.2.3-x86_64-pc-windows-msvc'
- 7z a ../%PROJECT_NAME%-%APPVEYOR_REPO_TAG_NAME%-%TARGET%.zip *
- appveyor PushArtifact ../%PROJECT_NAME%-%APPVEYOR_REPO_TAG_NAME%-%TARGET%.zip
@@ -56,17 +72,10 @@ deploy:
provider: GitHub
# deploy when a new tag is pushed and only on the stable channel
on:
# channel to use to produce the release artifacts
# NOTE make sure you only release *once* per target
# TODO you may want to pick a different channel
CHANNEL: stable
appveyor_repo_tag: true
branches:
only:
- /\d+\.\d+\.\d+/
- /^\d+\.\d+\.\d+$/
- master
# - appveyor
# - /\d+\.\d+\.\d+/
# except:
# - master

9
benchsuite/benchsuite
View File

@@ -1082,7 +1082,7 @@ def download_subtitles_en(suite_dir):
if not os.path.exists(en_path):
if not os.path.exists(en_path_gz):
run_cmd(['curl', '-LO', SUBTITLES_EN_URL], cwd=subtitle_dir)
run_cmd(['gunzip', en_path_gz], cwd=subtitle_dir)
run_cmd(['gunzip', en_path_gz])
if not os.path.exists(en_path_sample):
# Get a sample roughly the same size as the Russian corpus so that
# benchmarks finish in a reasonable time.
@@ -1109,7 +1109,7 @@ def download_subtitles_ru(suite_dir):
if not os.path.exists(ru_path):
if not os.path.exists(ru_path_gz):
run_cmd(['curl', '-LO', SUBTITLES_RU_URL], cwd=subtitle_dir)
run_cmd(['gunzip', ru_path_gz], cwd=subtitle_dir)
run_cmd(['gunzip', ru_path_gz])
def has_subtitles_ru(suite_dir):
@@ -1184,6 +1184,7 @@ def collect_benchmarks(suite_dir, filter_pat=None,
name,
' '.join(['--download %s' % n for n in e.missing_names]),
))
continue
except MissingCommands as e:
fmt = 'missing commands: %s, skipping benchmark %s ' \
'(run with --allow-missing to run incomplete benchmarks)'
@@ -1239,7 +1240,7 @@ def main():
benchmarks = collect_benchmarks(
args.dir, filter_pat=args.bench,
allow_missing_commands=args.allow_missing,
disabled_cmds=args.disabled.split(','),
disabled_cmds=(args.disabled or '').split(','),
warmup_iter=args.warmup_iter, bench_iter=args.bench_iter)
for b in benchmarks:
print(b.name)
@@ -1266,7 +1267,7 @@ def main():
benchmarks = collect_benchmarks(
args.dir, filter_pat=args.bench,
allow_missing_commands=args.allow_missing,
disabled_cmds=args.disabled.split(','),
disabled_cmds=(args.disabled or '').split(','),
warmup_iter=args.warmup_iter, bench_iter=args.bench_iter)
for i, b in enumerate(benchmarks):
result = b.run()

59
benchsuite/runs/2018-01-08-archlinux-cheetah/README Normal file
View File

@@ -0,0 +1,59 @@
This directory contains updated benchmarks as of 2018-01-08. They were captured
via the benchsuite script at `benchsuite/benchsuite` from the root of this
repository. The command that was run:
$ ./benchsuite \
--dir /tmp/benchsuite \
--raw runs/2018-01-08-archlinux-cheetah/raw.csv \
--warmup-iter 1 \
--bench-iter 5
These results are most directly comparable to the
`2016-09-22-archlinux-cheetah` run in the parent directory.
The versions of each tool are as follows:
$ grep -V
grep (GNU grep) 3.1
$ ag -V
ag version 2.1.0
Features:
+jit +lzma +zlib
$ sift -V
sift 0.8.0 (linux/amd64)
built from commit 2ca94717 (which seems to be 0.9.0)
$ pt --version
pt version 2.1.4
$ ucg -V
UniversalCodeGrep 0.3.3
[...]
Build info
Repo version: 0.3.3-251-g9b5a3e3
Compiler info:
Name ($(CXX)): "g++ -std=gnu++1z"
Version string: "g++ (GCC) 7.2.1 20171224"
ISA extensions in use:
sse4.2: yes
popcnt: yes
libpcre info:
Not linked against libpcre.
libpcre2-8 info:
Version: 10.30 2017-08-14
JIT support built in?: yes
JIT target architecture: x86 64bit (little endian + unaligned)
Newline style: LF
The version of ripgrep was compiled from source on commit 85d463c0, with the
simd-accel and avx-accel features enabled:
$ export RUSTFLAGS="-C target-cpu=native"
$ cargo build --release --features 'simd-accel avx-accel'

806
benchsuite/runs/2018-01-08-archlinux-cheetah/raw.csv Normal file
View File

@@ -0,0 +1,806 @@
benchmark,warmup_iter,iter,name,command,duration,lines,env
linux_alternates,1,5,rg (ignore),rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.10186767578125,68,
linux_alternates,1,5,rg (ignore),rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.10199356079101562,68,
linux_alternates,1,5,rg (ignore),rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09750819206237793,68,
linux_alternates,1,5,rg (ignore),rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09634733200073242,68,
linux_alternates,1,5,rg (ignore),rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.10117292404174805,68,
linux_alternates,1,5,ag (ignore),ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.49642109870910645,68,
linux_alternates,1,5,ag (ignore),ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.48993706703186035,68,
linux_alternates,1,5,ag (ignore),ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.4837028980255127,68,
linux_alternates,1,5,ag (ignore),ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.4773833751678467,68,
linux_alternates,1,5,ag (ignore),ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.558436393737793,68,
linux_alternates,1,5,git grep (ignore),git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.2605454921722412,68,LC_ALL=C
linux_alternates,1,5,git grep (ignore),git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.26748204231262207,68,LC_ALL=C
linux_alternates,1,5,git grep (ignore),git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.26719212532043457,68,LC_ALL=C
linux_alternates,1,5,git grep (ignore),git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.2719383239746094,68,LC_ALL=C
linux_alternates,1,5,git grep (ignore),git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.26963257789611816,68,LC_ALL=C
linux_alternates,1,5,rg (whitelist),rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.08797001838684082,68,
linux_alternates,1,5,rg (whitelist),rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09073781967163086,68,
linux_alternates,1,5,rg (whitelist),rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.0914468765258789,68,
linux_alternates,1,5,rg (whitelist),rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09071612358093262,68,
linux_alternates,1,5,rg (whitelist),rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.0914316177368164,68,
linux_alternates,1,5,ucg (whitelist),ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.1372535228729248,68,
linux_alternates,1,5,ucg (whitelist),ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.13880419731140137,68,
linux_alternates,1,5,ucg (whitelist),ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.13315439224243164,68,
linux_alternates,1,5,ucg (whitelist),ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.1367807388305664,68,
linux_alternates,1,5,ucg (whitelist),ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.13135552406311035,68,
linux_alternates_casei,1,5,rg (ignore),rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.12781810760498047,160,
linux_alternates_casei,1,5,rg (ignore),rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.11988544464111328,160,
linux_alternates_casei,1,5,rg (ignore),rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.1205439567565918,160,
linux_alternates_casei,1,5,rg (ignore),rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.12867259979248047,160,
linux_alternates_casei,1,5,rg (ignore),rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.1215970516204834,160,
linux_alternates_casei,1,5,ag (ignore),ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.5444357395172119,160,
linux_alternates_casei,1,5,ag (ignore),ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.5511739253997803,160,
linux_alternates_casei,1,5,ag (ignore),ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.5382294654846191,160,
linux_alternates_casei,1,5,ag (ignore),ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.5499558448791504,160,
linux_alternates_casei,1,5,ag (ignore),ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.6376545429229736,160,
linux_alternates_casei,1,5,git grep (ignore),git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.9767155647277832,160,LC_ALL=C
linux_alternates_casei,1,5,git grep (ignore),git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.920574426651001,160,LC_ALL=C
linux_alternates_casei,1,5,git grep (ignore),git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.9352290630340576,160,LC_ALL=C
linux_alternates_casei,1,5,git grep (ignore),git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.8866012096405029,160,LC_ALL=C
linux_alternates_casei,1,5,git grep (ignore),git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.9189445972442627,160,LC_ALL=C
linux_alternates_casei,1,5,rg (whitelist),rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09351730346679688,160,
linux_alternates_casei,1,5,rg (whitelist),rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09393739700317383,160,
linux_alternates_casei,1,5,rg (whitelist),rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09986448287963867,160,
linux_alternates_casei,1,5,rg (whitelist),rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09596824645996094,160,
linux_alternates_casei,1,5,rg (whitelist),rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.09604883193969727,160,
linux_alternates_casei,1,5,ucg (whitelist),ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.23943114280700684,160,
linux_alternates_casei,1,5,ucg (whitelist),ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.2587015628814697,160,
linux_alternates_casei,1,5,ucg (whitelist),ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.2543606758117676,160,
linux_alternates_casei,1,5,ucg (whitelist),ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.2490406036376953,160,
linux_alternates_casei,1,5,ucg (whitelist),ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.24046540260314941,160,
linux_literal,1,5,rg (ignore),rg -n PM_RESUME,0.08253765106201172,16,
linux_literal,1,5,rg (ignore),rg -n PM_RESUME,0.08176755905151367,16,
linux_literal,1,5,rg (ignore),rg -n PM_RESUME,0.08141684532165527,16,
linux_literal,1,5,rg (ignore),rg -n PM_RESUME,0.08108830451965332,16,
linux_literal,1,5,rg (ignore),rg -n PM_RESUME,0.08082938194274902,16,
linux_literal,1,5,rg (ignore) (mmap),rg -n --mmap PM_RESUME,0.6870582103729248,16,
linux_literal,1,5,rg (ignore) (mmap),rg -n --mmap PM_RESUME,0.807842493057251,16,
linux_literal,1,5,rg (ignore) (mmap),rg -n --mmap PM_RESUME,0.8129942417144775,16,
linux_literal,1,5,rg (ignore) (mmap),rg -n --mmap PM_RESUME,0.7582321166992188,16,
linux_literal,1,5,rg (ignore) (mmap),rg -n --mmap PM_RESUME,0.6869800090789795,16,
linux_literal,1,5,ag (ignore) (mmap),ag -s PM_RESUME,0.6534101963043213,16,
linux_literal,1,5,ag (ignore) (mmap),ag -s PM_RESUME,0.6020612716674805,16,
linux_literal,1,5,ag (ignore) (mmap),ag -s PM_RESUME,0.6712157726287842,16,
linux_literal,1,5,ag (ignore) (mmap),ag -s PM_RESUME,0.6267571449279785,16,
linux_literal,1,5,ag (ignore) (mmap),ag -s PM_RESUME,0.505136251449585,16,
linux_literal,1,5,pt (ignore),pt PM_RESUME,0.21415948867797852,16,
linux_literal,1,5,pt (ignore),pt PM_RESUME,0.19318318367004395,16,
linux_literal,1,5,pt (ignore),pt PM_RESUME,0.21352124214172363,16,
linux_literal,1,5,pt (ignore),pt PM_RESUME,0.18979454040527344,16,
linux_literal,1,5,pt (ignore),pt PM_RESUME,0.16629600524902344,16,
linux_literal,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME,0.46967077255249023,16,
linux_literal,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME,0.46343088150024414,16,
linux_literal,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME,0.4723978042602539,16,
linux_literal,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME,0.4741063117980957,16,
linux_literal,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME,0.4613051414489746,16,
linux_literal,1,5,git grep (ignore),git grep -I -n PM_RESUME,0.20196986198425293,16,LC_ALL=C
linux_literal,1,5,git grep (ignore),git grep -I -n PM_RESUME,0.18932533264160156,16,LC_ALL=C
linux_literal,1,5,git grep (ignore),git grep -I -n PM_RESUME,0.19396305084228516,16,LC_ALL=C
linux_literal,1,5,git grep (ignore),git grep -I -n PM_RESUME,0.1952073574066162,16,LC_ALL=C
linux_literal,1,5,git grep (ignore),git grep -I -n PM_RESUME,0.20149731636047363,16,LC_ALL=C
linux_literal,1,5,rg (whitelist),rg -n --no-ignore -tall PM_RESUME,0.08270478248596191,16,
linux_literal,1,5,rg (whitelist),rg -n --no-ignore -tall PM_RESUME,0.08414745330810547,16,
linux_literal,1,5,rg (whitelist),rg -n --no-ignore -tall PM_RESUME,0.08627724647521973,16,
linux_literal,1,5,rg (whitelist),rg -n --no-ignore -tall PM_RESUME,0.08978700637817383,16,
linux_literal,1,5,rg (whitelist),rg -n --no-ignore -tall PM_RESUME,0.0836489200592041,16,
linux_literal,1,5,ucg (whitelist),ucg --nosmart-case PM_RESUME,0.15774202346801758,16,
linux_literal,1,5,ucg (whitelist),ucg --nosmart-case PM_RESUME,0.16005396842956543,16,
linux_literal,1,5,ucg (whitelist),ucg --nosmart-case PM_RESUME,0.15743708610534668,16,
linux_literal,1,5,ucg (whitelist),ucg --nosmart-case PM_RESUME,0.16156601905822754,16,
linux_literal,1,5,ucg (whitelist),ucg --nosmart-case PM_RESUME,0.1557624340057373,16,
linux_literal_casei,1,5,rg (ignore),rg -n -i PM_RESUME,0.1028127670288086,374,
linux_literal_casei,1,5,rg (ignore),rg -n -i PM_RESUME,0.10258054733276367,374,
linux_literal_casei,1,5,rg (ignore),rg -n -i PM_RESUME,0.10902261734008789,374,
linux_literal_casei,1,5,rg (ignore),rg -n -i PM_RESUME,0.10802555084228516,374,
linux_literal_casei,1,5,rg (ignore),rg -n -i PM_RESUME,0.10153412818908691,374,
linux_literal_casei,1,5,rg (ignore) (mmap),rg -n -i --mmap PM_RESUME,0.7902817726135254,374,
linux_literal_casei,1,5,rg (ignore) (mmap),rg -n -i --mmap PM_RESUME,0.7985179424285889,374,
linux_literal_casei,1,5,rg (ignore) (mmap),rg -n -i --mmap PM_RESUME,0.8208649158477783,374,
linux_literal_casei,1,5,rg (ignore) (mmap),rg -n -i --mmap PM_RESUME,0.7937076091766357,374,
linux_literal_casei,1,5,rg (ignore) (mmap),rg -n -i --mmap PM_RESUME,0.7936429977416992,374,
linux_literal_casei,1,5,ag (ignore) (mmap),ag -i PM_RESUME,0.5215470790863037,374,
linux_literal_casei,1,5,ag (ignore) (mmap),ag -i PM_RESUME,0.46518707275390625,374,
linux_literal_casei,1,5,ag (ignore) (mmap),ag -i PM_RESUME,0.4467353820800781,374,
linux_literal_casei,1,5,ag (ignore) (mmap),ag -i PM_RESUME,0.4595184326171875,374,
linux_literal_casei,1,5,ag (ignore) (mmap),ag -i PM_RESUME,0.4531285762786865,374,
linux_literal_casei,1,5,pt (ignore),pt -i PM_RESUME,14.187762022018433,374,
linux_literal_casei,1,5,pt (ignore),pt -i PM_RESUME,14.178058385848999,374,
linux_literal_casei,1,5,pt (ignore),pt -i PM_RESUME,14.096448421478271,374,
linux_literal_casei,1,5,pt (ignore),pt -i PM_RESUME,14.190524339675903,374,
linux_literal_casei,1,5,pt (ignore),pt -i PM_RESUME,14.231573343276978,374,
linux_literal_casei,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME,0.4668574333190918,374,
linux_literal_casei,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME,0.46050214767456055,374,
linux_literal_casei,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME,0.46228861808776855,374,
linux_literal_casei,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME,0.44957947731018066,374,
linux_literal_casei,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME,0.4612581729888916,374,
linux_literal_casei,1,5,git grep (ignore),git grep -I -n -i PM_RESUME,0.1932981014251709,370,LC_ALL=C
linux_literal_casei,1,5,git grep (ignore),git grep -I -n -i PM_RESUME,0.20561552047729492,370,LC_ALL=C
linux_literal_casei,1,5,git grep (ignore),git grep -I -n -i PM_RESUME,0.19516706466674805,370,LC_ALL=C
linux_literal_casei,1,5,git grep (ignore),git grep -I -n -i PM_RESUME,0.20196247100830078,370,LC_ALL=C
linux_literal_casei,1,5,git grep (ignore),git grep -I -n -i PM_RESUME,0.19236421585083008,370,LC_ALL=C
linux_literal_casei,1,5,rg (whitelist),rg -n -i --no-ignore -tall PM_RESUME,0.09555959701538086,370,
linux_literal_casei,1,5,rg (whitelist),rg -n -i --no-ignore -tall PM_RESUME,0.09589338302612305,370,
linux_literal_casei,1,5,rg (whitelist),rg -n -i --no-ignore -tall PM_RESUME,0.09479856491088867,370,
linux_literal_casei,1,5,rg (whitelist),rg -n -i --no-ignore -tall PM_RESUME,0.09741568565368652,370,
linux_literal_casei,1,5,rg (whitelist),rg -n -i --no-ignore -tall PM_RESUME,0.10127615928649902,370,
linux_literal_casei,1,5,ucg (whitelist),ucg -i PM_RESUME,0.15514039993286133,370,
linux_literal_casei,1,5,ucg (whitelist),ucg -i PM_RESUME,0.15668940544128418,370,
linux_literal_casei,1,5,ucg (whitelist),ucg -i PM_RESUME,0.15429425239562988,370,
linux_literal_casei,1,5,ucg (whitelist),ucg -i PM_RESUME,0.15332818031311035,370,
linux_literal_casei,1,5,ucg (whitelist),ucg -i PM_RESUME,0.14861536026000977,370,
linux_literal_default,1,5,rg,rg PM_RESUME,0.08931398391723633,16,
linux_literal_default,1,5,rg,rg PM_RESUME,0.08717465400695801,16,
linux_literal_default,1,5,rg,rg PM_RESUME,0.0879361629486084,16,
linux_literal_default,1,5,rg,rg PM_RESUME,0.08688950538635254,16,
linux_literal_default,1,5,rg,rg PM_RESUME,0.09138607978820801,16,
linux_literal_default,1,5,ag,ag PM_RESUME,0.5342838764190674,16,
linux_literal_default,1,5,ag,ag PM_RESUME,0.47187042236328125,16,
linux_literal_default,1,5,ag,ag PM_RESUME,0.4456596374511719,16,
linux_literal_default,1,5,ag,ag PM_RESUME,0.4507424831390381,16,
linux_literal_default,1,5,ag,ag PM_RESUME,0.44472575187683105,16,
linux_literal_default,1,5,ucg,ucg PM_RESUME,0.15556907653808594,16,
linux_literal_default,1,5,ucg,ucg PM_RESUME,0.1533644199371338,16,
linux_literal_default,1,5,ucg,ucg PM_RESUME,0.15392351150512695,16,
linux_literal_default,1,5,ucg,ucg PM_RESUME,0.1535196304321289,16,
linux_literal_default,1,5,ucg,ucg PM_RESUME,0.15589547157287598,16,
linux_literal_default,1,5,pt,pt PM_RESUME,0.2261514663696289,16,
linux_literal_default,1,5,pt,pt PM_RESUME,0.2731902599334717,16,
linux_literal_default,1,5,pt,pt PM_RESUME,0.2563004493713379,16,
linux_literal_default,1,5,pt,pt PM_RESUME,0.2575085163116455,16,
linux_literal_default,1,5,pt,pt PM_RESUME,0.1724245548248291,16,
linux_literal_default,1,5,sift,sift PM_RESUME,0.13233542442321777,16,
linux_literal_default,1,5,sift,sift PM_RESUME,0.1256580352783203,16,
linux_literal_default,1,5,sift,sift PM_RESUME,0.12435102462768555,16,
linux_literal_default,1,5,sift,sift PM_RESUME,0.1259307861328125,16,
linux_literal_default,1,5,sift,sift PM_RESUME,0.12412142753601074,16,
linux_literal_default,1,5,git grep,git grep PM_RESUME,0.1742086410522461,16,LC_ALL=en_US.UTF-8
linux_literal_default,1,5,git grep,git grep PM_RESUME,0.16890597343444824,16,LC_ALL=en_US.UTF-8
linux_literal_default,1,5,git grep,git grep PM_RESUME,0.16680669784545898,16,LC_ALL=en_US.UTF-8
linux_literal_default,1,5,git grep,git grep PM_RESUME,0.16899871826171875,16,LC_ALL=en_US.UTF-8
linux_literal_default,1,5,git grep,git grep PM_RESUME,0.19794917106628418,16,LC_ALL=en_US.UTF-8
linux_no_literal,1,5,rg (ignore),rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.33940672874450684,490,
linux_no_literal,1,5,rg (ignore),rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.3274960517883301,490,
linux_no_literal,1,5,rg (ignore),rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.32681775093078613,490,
linux_no_literal,1,5,rg (ignore),rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.32865071296691895,490,
linux_no_literal,1,5,rg (ignore),rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.3240926265716553,490,
linux_no_literal,1,5,rg (ignore) (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.17426586151123047,490,
linux_no_literal,1,5,rg (ignore) (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.17265701293945312,490,
linux_no_literal,1,5,rg (ignore) (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.1703634262084961,490,
linux_no_literal,1,5,rg (ignore) (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.17192435264587402,490,
linux_no_literal,1,5,rg (ignore) (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.1704559326171875,490,
linux_no_literal,1,5,ag (ignore) (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.8443403244018555,766,
linux_no_literal,1,5,ag (ignore) (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.6956703662872314,766,
linux_no_literal,1,5,ag (ignore) (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.6938261985778809,766,
linux_no_literal,1,5,ag (ignore) (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.695967435836792,766,
linux_no_literal,1,5,ag (ignore) (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.6945271492004395,766,
linux_no_literal,1,5,pt (ignore) (ASCII),pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},12.645716428756714,490,
linux_no_literal,1,5,pt (ignore) (ASCII),pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},12.441533088684082,490,
linux_no_literal,1,5,pt (ignore) (ASCII),pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},12.472522735595703,490,
linux_no_literal,1,5,pt (ignore) (ASCII),pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},12.42497444152832,490,
linux_no_literal,1,5,pt (ignore) (ASCII),pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},12.407486200332642,490,
linux_no_literal,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},9.091489553451538,490,
linux_no_literal,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},9.049214124679565,490,
linux_no_literal,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},8.879419803619385,490,
linux_no_literal,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},9.07261848449707,490,
linux_no_literal,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},8.918747901916504,490,
linux_no_literal,1,5,git grep (ignore),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},8.334321975708008,490,LC_ALL=en_US.UTF-8
linux_no_literal,1,5,git grep (ignore),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},8.993232727050781,490,LC_ALL=en_US.UTF-8
linux_no_literal,1,5,git grep (ignore),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},8.622304916381836,490,LC_ALL=en_US.UTF-8
linux_no_literal,1,5,git grep (ignore),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},8.35973048210144,490,LC_ALL=en_US.UTF-8
linux_no_literal,1,5,git grep (ignore),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},8.39980435371399,490,LC_ALL=en_US.UTF-8
linux_no_literal,1,5,git grep (ignore) (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},2.0318400859832764,490,LC_ALL=C
linux_no_literal,1,5,git grep (ignore) (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},1.8587837219238281,490,LC_ALL=C
linux_no_literal,1,5,git grep (ignore) (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},1.873384714126587,490,LC_ALL=C
linux_no_literal,1,5,git grep (ignore) (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},1.8111364841461182,490,LC_ALL=C
linux_no_literal,1,5,git grep (ignore) (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},1.8385357856750488,490,LC_ALL=C
linux_no_literal,1,5,rg (whitelist),rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.28792643547058105,458,
linux_no_literal,1,5,rg (whitelist),rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.28545212745666504,458,
linux_no_literal,1,5,rg (whitelist),rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.28576135635375977,458,
linux_no_literal,1,5,rg (whitelist),rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.29883813858032227,458,
linux_no_literal,1,5,rg (whitelist),rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.28493285179138184,458,
linux_no_literal,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.15974783897399902,458,
linux_no_literal,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.15943312644958496,458,
linux_no_literal,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.160233736038208,458,
linux_no_literal,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.16201996803283691,458,
linux_no_literal,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.16033530235290527,458,
linux_no_literal,1,5,ucg (whitelist) (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.4639148712158203,416,
linux_no_literal,1,5,ucg (whitelist) (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.46042823791503906,416,
linux_no_literal,1,5,ucg (whitelist) (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.45925426483154297,416,
linux_no_literal,1,5,ucg (whitelist) (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.477064847946167,416,
linux_no_literal,1,5,ucg (whitelist) (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.507554292678833,416,
linux_re_literal_suffix,1,5,rg (ignore),rg -n [A-Z]+_RESUME,0.08520364761352539,1652,
linux_re_literal_suffix,1,5,rg (ignore),rg -n [A-Z]+_RESUME,0.08203816413879395,1652,
linux_re_literal_suffix,1,5,rg (ignore),rg -n [A-Z]+_RESUME,0.08355021476745605,1652,
linux_re_literal_suffix,1,5,rg (ignore),rg -n [A-Z]+_RESUME,0.0865166187286377,1652,
linux_re_literal_suffix,1,5,rg (ignore),rg -n [A-Z]+_RESUME,0.08125448226928711,1652,
linux_re_literal_suffix,1,5,ag (ignore),ag -s [A-Z]+_RESUME,0.4846627712249756,1652,
linux_re_literal_suffix,1,5,ag (ignore),ag -s [A-Z]+_RESUME,0.48070311546325684,1652,
linux_re_literal_suffix,1,5,ag (ignore),ag -s [A-Z]+_RESUME,0.4813041687011719,1652,
linux_re_literal_suffix,1,5,ag (ignore),ag -s [A-Z]+_RESUME,0.4755582809448242,1652,
linux_re_literal_suffix,1,5,ag (ignore),ag -s [A-Z]+_RESUME,0.4926290512084961,1652,
linux_re_literal_suffix,1,5,pt (ignore),pt -e [A-Z]+_RESUME,14.124520540237427,1652,
linux_re_literal_suffix,1,5,pt (ignore),pt -e [A-Z]+_RESUME,14.151537656784058,1652,
linux_re_literal_suffix,1,5,pt (ignore),pt -e [A-Z]+_RESUME,14.157994270324707,1652,
linux_re_literal_suffix,1,5,pt (ignore),pt -e [A-Z]+_RESUME,14.102291822433472,1652,
linux_re_literal_suffix,1,5,pt (ignore),pt -e [A-Z]+_RESUME,14.103861093521118,1652,
linux_re_literal_suffix,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME,4.182392835617065,1652,
linux_re_literal_suffix,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME,4.190829277038574,1652,
linux_re_literal_suffix,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME,3.9770240783691406,1652,
linux_re_literal_suffix,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME,3.9978606700897217,1652,
linux_re_literal_suffix,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME,4.146454572677612,1652,
linux_re_literal_suffix,1,5,git grep (ignore),git grep -E -I -n [A-Z]+_RESUME,0.5080702304840088,1652,LC_ALL=C
linux_re_literal_suffix,1,5,git grep (ignore),git grep -E -I -n [A-Z]+_RESUME,0.5281260013580322,1652,LC_ALL=C
linux_re_literal_suffix,1,5,git grep (ignore),git grep -E -I -n [A-Z]+_RESUME,0.5350546836853027,1652,LC_ALL=C
linux_re_literal_suffix,1,5,git grep (ignore),git grep -E -I -n [A-Z]+_RESUME,0.5474245548248291,1652,LC_ALL=C
linux_re_literal_suffix,1,5,git grep (ignore),git grep -E -I -n [A-Z]+_RESUME,0.5256762504577637,1652,LC_ALL=C
linux_re_literal_suffix,1,5,rg (whitelist),rg -n --no-ignore -tall [A-Z]+_RESUME,0.07924222946166992,1630,
linux_re_literal_suffix,1,5,rg (whitelist),rg -n --no-ignore -tall [A-Z]+_RESUME,0.0767812728881836,1630,
linux_re_literal_suffix,1,5,rg (whitelist),rg -n --no-ignore -tall [A-Z]+_RESUME,0.07874488830566406,1630,
linux_re_literal_suffix,1,5,rg (whitelist),rg -n --no-ignore -tall [A-Z]+_RESUME,0.0804905891418457,1630,
linux_re_literal_suffix,1,5,rg (whitelist),rg -n --no-ignore -tall [A-Z]+_RESUME,0.07479119300842285,1630,
linux_re_literal_suffix,1,5,ucg (whitelist),ucg --nosmart-case [A-Z]+_RESUME,0.13643193244934082,1630,
linux_re_literal_suffix,1,5,ucg (whitelist),ucg --nosmart-case [A-Z]+_RESUME,0.13543128967285156,1630,
linux_re_literal_suffix,1,5,ucg (whitelist),ucg --nosmart-case [A-Z]+_RESUME,0.13312768936157227,1630,
linux_re_literal_suffix,1,5,ucg (whitelist),ucg --nosmart-case [A-Z]+_RESUME,0.13562273979187012,1630,
linux_re_literal_suffix,1,5,ucg (whitelist),ucg --nosmart-case [A-Z]+_RESUME,0.13236212730407715,1630,
linux_unicode_greek,1,5,rg,rg -n \p{Greek},0.17355775833129883,23,
linux_unicode_greek,1,5,rg,rg -n \p{Greek},0.1676032543182373,23,
linux_unicode_greek,1,5,rg,rg -n \p{Greek},0.1727275848388672,23,
linux_unicode_greek,1,5,rg,rg -n \p{Greek},0.17095375061035156,23,
linux_unicode_greek,1,5,rg,rg -n \p{Greek},0.17271947860717773,23,
linux_unicode_greek,1,5,pt,pt -e \p{Greek},14.14364218711853,23,
linux_unicode_greek,1,5,pt,pt -e \p{Greek},14.137334108352661,23,
linux_unicode_greek,1,5,pt,pt -e \p{Greek},14.083475351333618,23,
linux_unicode_greek,1,5,pt,pt -e \p{Greek},14.095231056213379,23,
linux_unicode_greek,1,5,pt,pt -e \p{Greek},14.151906490325928,23,
linux_unicode_greek,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek},2.8376963138580322,23,
linux_unicode_greek,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek},2.8271427154541016,23,
linux_unicode_greek,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek},2.8310961723327637,23,
linux_unicode_greek,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek},2.826141595840454,23,
linux_unicode_greek,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek},2.805818796157837,23,
linux_unicode_greek_casei,1,5,rg,rg -n -i \p{Greek},0.16843819618225098,103,
linux_unicode_greek_casei,1,5,rg,rg -n -i \p{Greek},0.1704998016357422,103,
linux_unicode_greek_casei,1,5,rg,rg -n -i \p{Greek},0.17055058479309082,103,
linux_unicode_greek_casei,1,5,rg,rg -n -i \p{Greek},0.17064881324768066,103,
linux_unicode_greek_casei,1,5,rg,rg -n -i \p{Greek},0.1699228286743164,103,
linux_unicode_greek_casei,1,5,pt,pt -i -e \p{Greek},14.164355993270874,23,
linux_unicode_greek_casei,1,5,pt,pt -i -e \p{Greek},14.099931478500366,23,
linux_unicode_greek_casei,1,5,pt,pt -i -e \p{Greek},14.155095338821411,23,
linux_unicode_greek_casei,1,5,pt,pt -i -e \p{Greek},14.109308004379272,23,
linux_unicode_greek_casei,1,5,pt,pt -i -e \p{Greek},14.072362422943115,23,
linux_unicode_greek_casei,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek},0.003945589065551758,,
linux_unicode_greek_casei,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek},0.004189729690551758,,
linux_unicode_greek_casei,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek},0.0034589767456054688,,
linux_unicode_greek_casei,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek},0.003614187240600586,,
linux_unicode_greek_casei,1,5,sift,sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek},0.003975629806518555,,
linux_unicode_word,1,5,rg (ignore),rg -n \wAh,0.09798526763916016,186,
linux_unicode_word,1,5,rg (ignore),rg -n \wAh,0.09575009346008301,186,
linux_unicode_word,1,5,rg (ignore),rg -n \wAh,0.10181760787963867,186,
linux_unicode_word,1,5,rg (ignore),rg -n \wAh,0.09650158882141113,186,
linux_unicode_word,1,5,rg (ignore),rg -n \wAh,0.09717488288879395,186,
linux_unicode_word,1,5,rg (ignore) (ASCII),rg -n (?-u)\wAh,0.09417867660522461,174,
linux_unicode_word,1,5,rg (ignore) (ASCII),rg -n (?-u)\wAh,0.09903812408447266,174,
linux_unicode_word,1,5,rg (ignore) (ASCII),rg -n (?-u)\wAh,0.09407877922058105,174,
linux_unicode_word,1,5,rg (ignore) (ASCII),rg -n (?-u)\wAh,0.09681963920593262,174,
linux_unicode_word,1,5,rg (ignore) (ASCII),rg -n (?-u)\wAh,0.09762454032897949,174,
linux_unicode_word,1,5,ag (ignore) (ASCII),ag -s \wAh,0.5779609680175781,174,
linux_unicode_word,1,5,ag (ignore) (ASCII),ag -s \wAh,0.635645866394043,174,
linux_unicode_word,1,5,ag (ignore) (ASCII),ag -s \wAh,0.6109263896942139,174,
linux_unicode_word,1,5,ag (ignore) (ASCII),ag -s \wAh,0.6260912418365479,174,
linux_unicode_word,1,5,ag (ignore) (ASCII),ag -s \wAh,0.6823546886444092,174,
linux_unicode_word,1,5,pt (ignore) (ASCII),pt -e \wAh,14.178487062454224,174,
linux_unicode_word,1,5,pt (ignore) (ASCII),pt -e \wAh,14.190000057220459,174,
linux_unicode_word,1,5,pt (ignore) (ASCII),pt -e \wAh,14.16363000869751,174,
linux_unicode_word,1,5,pt (ignore) (ASCII),pt -e \wAh,14.160430431365967,174,
linux_unicode_word,1,5,pt (ignore) (ASCII),pt -e \wAh,14.2189621925354,174,
linux_unicode_word,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh,4.17629337310791,174,
linux_unicode_word,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh,4.051238059997559,174,
linux_unicode_word,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh,4.323853015899658,174,
linux_unicode_word,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh,4.085661172866821,174,
linux_unicode_word,1,5,sift (ignore) (ASCII),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh,4.036486625671387,174,
linux_unicode_word,1,5,git grep (ignore),git grep -E -I -n \wAh,4.620476961135864,186,LC_ALL=en_US.UTF-8
linux_unicode_word,1,5,git grep (ignore),git grep -E -I -n \wAh,4.536192417144775,186,LC_ALL=en_US.UTF-8
linux_unicode_word,1,5,git grep (ignore),git grep -E -I -n \wAh,4.510494232177734,186,LC_ALL=en_US.UTF-8
linux_unicode_word,1,5,git grep (ignore),git grep -E -I -n \wAh,6.001620769500732,186,LC_ALL=en_US.UTF-8
linux_unicode_word,1,5,git grep (ignore),git grep -E -I -n \wAh,4.602652311325073,186,LC_ALL=en_US.UTF-8
linux_unicode_word,1,5,git grep (ignore) (ASCII),git grep -E -I -n \wAh,1.3785994052886963,174,LC_ALL=C
linux_unicode_word,1,5,git grep (ignore) (ASCII),git grep -E -I -n \wAh,1.4163663387298584,174,LC_ALL=C
linux_unicode_word,1,5,git grep (ignore) (ASCII),git grep -E -I -n \wAh,1.402677297592163,174,LC_ALL=C
linux_unicode_word,1,5,git grep (ignore) (ASCII),git grep -E -I -n \wAh,1.3327512741088867,174,LC_ALL=C
linux_unicode_word,1,5,git grep (ignore) (ASCII),git grep -E -I -n \wAh,1.3501760959625244,174,LC_ALL=C
linux_unicode_word,1,5,rg (whitelist),rg -n --no-ignore -tall \wAh,0.07958698272705078,180,
linux_unicode_word,1,5,rg (whitelist),rg -n --no-ignore -tall \wAh,0.0798649787902832,180,
linux_unicode_word,1,5,rg (whitelist),rg -n --no-ignore -tall \wAh,0.08086204528808594,180,
linux_unicode_word,1,5,rg (whitelist),rg -n --no-ignore -tall \wAh,0.0814356803894043,180,
linux_unicode_word,1,5,rg (whitelist),rg -n --no-ignore -tall \wAh,0.08273720741271973,180,
linux_unicode_word,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\wAh,0.08280825614929199,168,
linux_unicode_word,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\wAh,0.08074021339416504,168,
linux_unicode_word,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\wAh,0.0821676254272461,168,
linux_unicode_word,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\wAh,0.07926368713378906,168,
linux_unicode_word,1,5,rg (whitelist) (ASCII),rg -n --no-ignore -tall (?-u)\wAh,0.08405280113220215,168,
linux_unicode_word,1,5,ucg (ASCII),ucg --nosmart-case \wAh,0.1545090675354004,168,
linux_unicode_word,1,5,ucg (ASCII),ucg --nosmart-case \wAh,0.1517190933227539,168,
linux_unicode_word,1,5,ucg (ASCII),ucg --nosmart-case \wAh,0.15704965591430664,168,
linux_unicode_word,1,5,ucg (ASCII),ucg --nosmart-case \wAh,0.15523767471313477,168,
linux_unicode_word,1,5,ucg (ASCII),ucg --nosmart-case \wAh,0.1582942008972168,168,
linux_word,1,5,rg (ignore),rg -n -w PM_RESUME,0.09102368354797363,6,
linux_word,1,5,rg (ignore),rg -n -w PM_RESUME,0.08986210823059082,6,
linux_word,1,5,rg (ignore),rg -n -w PM_RESUME,0.08989477157592773,6,
linux_word,1,5,rg (ignore),rg -n -w PM_RESUME,0.0895695686340332,6,
linux_word,1,5,rg (ignore),rg -n -w PM_RESUME,0.09547114372253418,6,
linux_word,1,5,ag (ignore),ag -s -w PM_RESUME,0.4948008060455322,6,
linux_word,1,5,ag (ignore),ag -s -w PM_RESUME,0.45710110664367676,6,
linux_word,1,5,ag (ignore),ag -s -w PM_RESUME,0.44803452491760254,6,
linux_word,1,5,ag (ignore),ag -s -w PM_RESUME,0.44779396057128906,6,
linux_word,1,5,ag (ignore),ag -s -w PM_RESUME,0.4563112258911133,6,
linux_word,1,5,pt (ignore),pt -w PM_RESUME,14.233235597610474,6,
linux_word,1,5,pt (ignore),pt -w PM_RESUME,14.277648687362671,6,
linux_word,1,5,pt (ignore),pt -w PM_RESUME,14.218127727508545,6,
linux_word,1,5,pt (ignore),pt -w PM_RESUME,14.171622037887573,6,
linux_word,1,5,pt (ignore),pt -w PM_RESUME,14.214240312576294,6,
linux_word,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME,3.1536731719970703,6,
linux_word,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME,3.2415099143981934,6,
linux_word,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME,3.2526626586914062,6,
linux_word,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME,3.2590816020965576,6,
linux_word,1,5,sift (ignore),sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME,3.222473621368408,6,
linux_word,1,5,git grep (ignore),git grep -E -I -n -w PM_RESUME,0.16982412338256836,6,LC_ALL=C
linux_word,1,5,git grep (ignore),git grep -E -I -n -w PM_RESUME,0.16739583015441895,6,LC_ALL=C
linux_word,1,5,git grep (ignore),git grep -E -I -n -w PM_RESUME,0.16866540908813477,6,LC_ALL=C
linux_word,1,5,git grep (ignore),git grep -E -I -n -w PM_RESUME,0.18207120895385742,6,LC_ALL=C
linux_word,1,5,git grep (ignore),git grep -E -I -n -w PM_RESUME,0.17716264724731445,6,LC_ALL=C
linux_word,1,5,rg (whitelist),rg -n -w --no-ignore -tall PM_RESUME,0.07490420341491699,6,
linux_word,1,5,rg (whitelist),rg -n -w --no-ignore -tall PM_RESUME,0.07714152336120605,6,
linux_word,1,5,rg (whitelist),rg -n -w --no-ignore -tall PM_RESUME,0.07552146911621094,6,
linux_word,1,5,rg (whitelist),rg -n -w --no-ignore -tall PM_RESUME,0.07651710510253906,6,
linux_word,1,5,rg (whitelist),rg -n -w --no-ignore -tall PM_RESUME,0.0757131576538086,6,
linux_word,1,5,ucg (whitelist),ucg --nosmart-case -w PM_RESUME,0.1530015468597412,6,
linux_word,1,5,ucg (whitelist),ucg --nosmart-case -w PM_RESUME,0.15152239799499512,6,
linux_word,1,5,ucg (whitelist),ucg --nosmart-case -w PM_RESUME,0.1571195125579834,6,
linux_word,1,5,ucg (whitelist),ucg --nosmart-case -w PM_RESUME,0.15993595123291016,6,
linux_word,1,5,ucg (whitelist),ucg --nosmart-case -w PM_RESUME,0.15633797645568848,6,
subtitles_en_alternate,1,5,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.33371877670288086,848,
subtitles_en_alternate,1,5,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3207988739013672,848,
subtitles_en_alternate,1,5,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3301675319671631,848,
subtitles_en_alternate,1,5,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.29731154441833496,848,
subtitles_en_alternate,1,5,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2711911201477051,848,
subtitles_en_alternate,1,5,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.186570405960083,848,
subtitles_en_alternate,1,5,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.1659939289093018,848,
subtitles_en_alternate,1,5,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.187847137451172,848,
subtitles_en_alternate,1,5,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.3522064685821533,848,
subtitles_en_alternate,1,5,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.316105842590332,848,
subtitles_en_alternate,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.1400718688964844,848,
subtitles_en_alternate,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.1492774486541748,848,
subtitles_en_alternate,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.1337254047393799,848,
subtitles_en_alternate,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.1037378311157227,848,
subtitles_en_alternate,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.1312851905822754,848,
subtitles_en_alternate,1,5,grep (lines),grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.8294000625610352,848,LC_ALL=C
subtitles_en_alternate,1,5,grep (lines),grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.808884620666504,848,LC_ALL=C
subtitles_en_alternate,1,5,grep (lines),grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.8134734630584717,848,LC_ALL=C
subtitles_en_alternate,1,5,grep (lines),grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.8405649662017822,848,LC_ALL=C
subtitles_en_alternate,1,5,grep (lines),grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.8500289916992188,848,LC_ALL=C
subtitles_en_alternate,1,5,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.21175312995910645,848,
subtitles_en_alternate,1,5,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2118232250213623,848,
subtitles_en_alternate,1,5,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.21287035942077637,848,
subtitles_en_alternate,1,5,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.21167230606079102,848,
subtitles_en_alternate,1,5,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.28102636337280273,848,
subtitles_en_alternate,1,5,grep,grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5029187202453613,848,LC_ALL=C
subtitles_en_alternate,1,5,grep,grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.49977445602417,848,LC_ALL=C
subtitles_en_alternate,1,5,grep,grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.508340835571289,848,LC_ALL=C
subtitles_en_alternate,1,5,grep,grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5002548694610596,848,LC_ALL=C
subtitles_en_alternate,1,5,grep,grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.629526138305664,848,LC_ALL=C
subtitles_en_alternate_casei,1,5,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.730497360229492,862,
subtitles_en_alternate_casei,1,5,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.781018018722534,862,
subtitles_en_alternate_casei,1,5,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.7858059406280518,862,
subtitles_en_alternate_casei,1,5,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.7127914428710938,862,
subtitles_en_alternate_casei,1,5,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.717308759689331,862,
subtitles_en_alternate_casei,1,5,ucg (ASCII),ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.428208351135254,862,
subtitles_en_alternate_casei,1,5,ucg (ASCII),ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.389420509338379,862,
subtitles_en_alternate_casei,1,5,ucg (ASCII),ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.403301954269409,862,
subtitles_en_alternate_casei,1,5,ucg (ASCII),ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.4691550731658936,862,
subtitles_en_alternate_casei,1,5,ucg (ASCII),ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.4245004653930664,862,
subtitles_en_alternate_casei,1,5,grep (ASCII),grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.978189706802368,862,LC_ALL=C
subtitles_en_alternate_casei,1,5,grep (ASCII),grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.974303722381592,862,LC_ALL=C
subtitles_en_alternate_casei,1,5,grep (ASCII),grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.982886552810669,862,LC_ALL=C
subtitles_en_alternate_casei,1,5,grep (ASCII),grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.90018630027771,862,LC_ALL=C
subtitles_en_alternate_casei,1,5,grep (ASCII),grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.0078439712524414,862,LC_ALL=C
subtitles_en_alternate_casei,1,5,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.9129142761230469,862,
subtitles_en_alternate_casei,1,5,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.9066660404205322,862,
subtitles_en_alternate_casei,1,5,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.946380615234375,862,
subtitles_en_alternate_casei,1,5,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.9672930240631104,862,
subtitles_en_alternate_casei,1,5,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.028451919555664,862,
subtitles_en_alternate_casei,1,5,grep,grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.9427030086517334,862,LC_ALL=en_US.UTF-8
subtitles_en_alternate_casei,1,5,grep,grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.938739061355591,862,LC_ALL=en_US.UTF-8
subtitles_en_alternate_casei,1,5,grep,grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.921248435974121,862,LC_ALL=en_US.UTF-8
subtitles_en_alternate_casei,1,5,grep,grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.9194068908691406,862,LC_ALL=en_US.UTF-8
subtitles_en_alternate_casei,1,5,grep,grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,2.917184829711914,862,LC_ALL=en_US.UTF-8
subtitles_en_literal,1,5,rg,rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.12293672561645508,629,
subtitles_en_literal,1,5,rg,rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.1259000301361084,629,
subtitles_en_literal,1,5,rg,rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.12285709381103516,629,
subtitles_en_literal,1,5,rg,rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.12280964851379395,629,
subtitles_en_literal,1,5,rg,rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.1547396183013916,629,
subtitles_en_literal,1,5,rg (no mmap),rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.22011375427246094,629,
subtitles_en_literal,1,5,rg (no mmap),rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.23095202445983887,629,
subtitles_en_literal,1,5,rg (no mmap),rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2577846050262451,629,
subtitles_en_literal,1,5,rg (no mmap),rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2563819885253906,629,
subtitles_en_literal,1,5,rg (no mmap),rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.24869346618652344,629,
subtitles_en_literal,1,5,pt,pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.415337324142456,629,
subtitles_en_literal,1,5,pt,pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.4208543300628662,629,
subtitles_en_literal,1,5,pt,pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.416351079940796,629,
subtitles_en_literal,1,5,pt,pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.4270708560943604,629,
subtitles_en_literal,1,5,pt,pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.4243996143341064,629,
subtitles_en_literal,1,5,sift,sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2245020866394043,629,
subtitles_en_literal,1,5,sift,sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2382345199584961,629,
subtitles_en_literal,1,5,sift,sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.23533034324645996,629,
subtitles_en_literal,1,5,sift,sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2577829360961914,629,
subtitles_en_literal,1,5,sift,sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2599349021911621,629,
subtitles_en_literal,1,5,grep,grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.4733700752258301,629,LC_ALL=C
subtitles_en_literal,1,5,grep,grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.4598572254180908,629,LC_ALL=C
subtitles_en_literal,1,5,grep,grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.5303301811218262,629,LC_ALL=C
subtitles_en_literal,1,5,grep,grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.4775106906890869,629,LC_ALL=C
subtitles_en_literal,1,5,grep,grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.4881136417388916,629,LC_ALL=C
subtitles_en_literal,1,5,rg (lines),rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.20051789283752441,629,
subtitles_en_literal,1,5,rg (lines),rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.17326998710632324,629,
subtitles_en_literal,1,5,rg (lines),rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.20733428001403809,629,
subtitles_en_literal,1,5,rg (lines),rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.189713716506958,629,
subtitles_en_literal,1,5,rg (lines),rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.17817258834838867,629,
subtitles_en_literal,1,5,ag (lines),ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5327835083007812,629,
subtitles_en_literal,1,5,ag (lines),ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5411181449890137,629,
subtitles_en_literal,1,5,ag (lines),ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.600783109664917,629,
subtitles_en_literal,1,5,ag (lines),ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5838911533355713,629,
subtitles_en_literal,1,5,ag (lines),ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.6051928997039795,629,
subtitles_en_literal,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.4090385437011719,629,
subtitles_en_literal,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3816399574279785,629,
subtitles_en_literal,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.38033008575439453,629,
subtitles_en_literal,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3731727600097656,629,
subtitles_en_literal,1,5,ucg (lines),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.38796329498291016,629,
subtitles_en_literal,1,5,pt (lines),pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.4102630615234375,629,
subtitles_en_literal,1,5,pt (lines),pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.4137451648712158,629,
subtitles_en_literal,1,5,pt (lines),pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.4649333953857422,629,
subtitles_en_literal,1,5,pt (lines),pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.430387258529663,629,
subtitles_en_literal,1,5,pt (lines),pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.541991949081421,629,
subtitles_en_literal,1,5,sift (lines),sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.6231405735015869,629,
subtitles_en_literal,1,5,sift (lines),sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.5986526012420654,629,
subtitles_en_literal,1,5,sift (lines),sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.5821917057037354,629,
subtitles_en_literal,1,5,sift (lines),sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.6045489311218262,629,
subtitles_en_literal,1,5,sift (lines),sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.5986905097961426,629,
subtitles_en_literal,1,5,grep (lines),grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.8278565406799316,629,LC_ALL=C
subtitles_en_literal,1,5,grep (lines),grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.777052640914917,629,LC_ALL=C
subtitles_en_literal,1,5,grep (lines),grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.7619414329528809,629,LC_ALL=C
subtitles_en_literal,1,5,grep (lines),grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.8248744010925293,629,LC_ALL=C
subtitles_en_literal,1,5,grep (lines),grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.824932336807251,629,LC_ALL=C
subtitles_en_literal_casei,1,5,rg,rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.2718961238861084,642,
subtitles_en_literal_casei,1,5,rg,rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.27082157135009766,642,
subtitles_en_literal_casei,1,5,rg,rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.27086758613586426,642,
subtitles_en_literal_casei,1,5,rg,rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.274705171585083,642,
subtitles_en_literal_casei,1,5,rg,rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3337059020996094,642,
subtitles_en_literal_casei,1,5,grep,grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.9112112522125244,642,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,5,grep,grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.907888650894165,642,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,5,grep,grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.912668228149414,642,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,5,grep,grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.9082865715026855,642,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,5,grep,grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.9177796840667725,642,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,5,grep (ASCII),grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.6020669937133789,642,LC_ALL=C
subtitles_en_literal_casei,1,5,grep (ASCII),grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.568228006362915,642,LC_ALL=C
subtitles_en_literal_casei,1,5,grep (ASCII),grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.5648214817047119,642,LC_ALL=C
subtitles_en_literal_casei,1,5,grep (ASCII),grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.5568234920501709,642,LC_ALL=C
subtitles_en_literal_casei,1,5,grep (ASCII),grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.5588953495025635,642,LC_ALL=C
subtitles_en_literal_casei,1,5,rg (lines),rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3486766815185547,642,
subtitles_en_literal_casei,1,5,rg (lines),rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.34010815620422363,642,
subtitles_en_literal_casei,1,5,rg (lines),rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.33849263191223145,642,
subtitles_en_literal_casei,1,5,rg (lines),rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3917088508605957,642,
subtitles_en_literal_casei,1,5,rg (lines),rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.39266490936279297,642,
subtitles_en_literal_casei,1,5,ag (lines) (ASCII),ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5564041137695312,642,
subtitles_en_literal_casei,1,5,ag (lines) (ASCII),ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5533506870269775,642,
subtitles_en_literal_casei,1,5,ag (lines) (ASCII),ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.6205368041992188,642,
subtitles_en_literal_casei,1,5,ag (lines) (ASCII),ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5530028343200684,642,
subtitles_en_literal_casei,1,5,ag (lines) (ASCII),ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.6189889907836914,642,
subtitles_en_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3834850788116455,642,
subtitles_en_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.41916346549987793,642,
subtitles_en_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3895289897918701,642,
subtitles_en_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.4278140068054199,642,
subtitles_en_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.4013493061065674,642,
subtitles_en_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.17953085899353027,629,
subtitles_en_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.17679834365844727,629,
subtitles_en_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.17448186874389648,629,
subtitles_en_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.21117281913757324,629,
subtitles_en_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.1848156452178955,629,
subtitles_en_literal_word,1,5,ag (ASCII),ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5236153602600098,629,
subtitles_en_literal_word,1,5,ag (ASCII),ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.52512526512146,629,
subtitles_en_literal_word,1,5,ag (ASCII),ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5218794345855713,629,
subtitles_en_literal_word,1,5,ag (ASCII),ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5384306907653809,629,
subtitles_en_literal_word,1,5,ag (ASCII),ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5150353908538818,629,
subtitles_en_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3757903575897217,629,
subtitles_en_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3744041919708252,629,
subtitles_en_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.37261366844177246,629,
subtitles_en_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.40795230865478516,629,
subtitles_en_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.3868849277496338,629,
subtitles_en_literal_word,1,5,grep (ASCII),grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.8265349864959717,629,LC_ALL=C
subtitles_en_literal_word,1,5,grep (ASCII),grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.8123743534088135,629,LC_ALL=C
subtitles_en_literal_word,1,5,grep (ASCII),grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.7669925689697266,629,LC_ALL=C
subtitles_en_literal_word,1,5,grep (ASCII),grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.766636848449707,629,LC_ALL=C
subtitles_en_literal_word,1,5,grep (ASCII),grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.7665839195251465,629,LC_ALL=C
subtitles_en_literal_word,1,5,rg,rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.1879115104675293,629,
subtitles_en_literal_word,1,5,rg,rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18082356452941895,629,
subtitles_en_literal_word,1,5,rg,rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18497347831726074,629,
subtitles_en_literal_word,1,5,rg,rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.1769394874572754,629,
subtitles_en_literal_word,1,5,rg,rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.1917715072631836,629,
subtitles_en_literal_word,1,5,grep,grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.8192996978759766,629,LC_ALL=en_US.UTF-8
subtitles_en_literal_word,1,5,grep,grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.8193323612213135,629,LC_ALL=en_US.UTF-8
subtitles_en_literal_word,1,5,grep,grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.7837738990783691,629,LC_ALL=en_US.UTF-8
subtitles_en_literal_word,1,5,grep,grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.7639024257659912,629,LC_ALL=en_US.UTF-8
subtitles_en_literal_word,1,5,grep,grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.7634689807891846,629,LC_ALL=en_US.UTF-8
subtitles_en_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.7922985553741455,13,
subtitles_en_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.7885758876800537,13,
subtitles_en_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.802325963973999,13,
subtitles_en_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.792595386505127,13,
subtitles_en_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.7909605503082275,13,
subtitles_en_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5903098583221436,13,
subtitles_en_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5982813835144043,13,
subtitles_en_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5926671028137207,13,
subtitles_en_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.5976767539978027,13,
subtitles_en_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.593153953552246,13,
subtitles_en_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,6.614634275436401,48,
subtitles_en_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,6.574857473373413,48,
subtitles_en_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,6.54079270362854,48,
subtitles_en_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,6.600660800933838,48,
subtitles_en_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,6.531627178192139,48,
subtitles_en_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,5.361133337020874,13,
subtitles_en_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,5.456786870956421,13,
subtitles_en_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,5.403071403503418,13,
subtitles_en_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,5.398236274719238,13,
subtitles_en_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,5.348573923110962,13,
subtitles_en_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.5057969093322754,13,LC_ALL=C
subtitles_en_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.4157862663269043,13,LC_ALL=C
subtitles_en_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.471182346343994,13,LC_ALL=C
subtitles_en_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.4590909481048584,13,LC_ALL=C
subtitles_en_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.3759689331054688,13,LC_ALL=C
subtitles_en_surrounding_words,1,5,rg,rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18518710136413574,317,
subtitles_en_surrounding_words,1,5,rg,rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18791556358337402,317,
subtitles_en_surrounding_words,1,5,rg,rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18598675727844238,317,
subtitles_en_surrounding_words,1,5,rg,rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18552684783935547,317,
subtitles_en_surrounding_words,1,5,rg,rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.19262075424194336,317,
subtitles_en_surrounding_words,1,5,grep,grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.1321008205413818,317,LC_ALL=en_US.UTF-8
subtitles_en_surrounding_words,1,5,grep,grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.0709969997406006,317,LC_ALL=en_US.UTF-8
subtitles_en_surrounding_words,1,5,grep,grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.1117346286773682,317,LC_ALL=en_US.UTF-8
subtitles_en_surrounding_words,1,5,grep,grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.0880234241485596,317,LC_ALL=en_US.UTF-8
subtitles_en_surrounding_words,1,5,grep,grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.0745558738708496,317,LC_ALL=en_US.UTF-8
subtitles_en_surrounding_words,1,5,rg (ASCII),rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.1827528476715088,317,
subtitles_en_surrounding_words,1,5,rg (ASCII),rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18874144554138184,317,
subtitles_en_surrounding_words,1,5,rg (ASCII),rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.17983436584472656,317,
subtitles_en_surrounding_words,1,5,rg (ASCII),rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.18831133842468262,317,
subtitles_en_surrounding_words,1,5,rg (ASCII),rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,0.17810606956481934,317,
subtitles_en_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,4.5957207679748535,323,
subtitles_en_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,4.627211570739746,323,
subtitles_en_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,4.554431200027466,323,
subtitles_en_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,4.492656469345093,323,
subtitles_en_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,4.443558216094971,323,
subtitles_en_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.522758722305298,317,
subtitles_en_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.502918004989624,317,
subtitles_en_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.6503307819366455,317,
subtitles_en_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.58940052986145,317,
subtitles_en_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,3.569624423980713,317,
subtitles_en_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.0672054290771484,317,LC_ALL=C
subtitles_en_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.0729331970214844,317,LC_ALL=C
subtitles_en_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.052501916885376,317,LC_ALL=C
subtitles_en_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.0711696147918701,317,LC_ALL=C
subtitles_en_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en,1.0863316059112549,317,LC_ALL=C
subtitles_ru_alternate,1,5,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0312588214874268,691,
subtitles_ru_alternate,1,5,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.063939094543457,691,
subtitles_ru_alternate,1,5,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0000121593475342,691,
subtitles_ru_alternate,1,5,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9842438697814941,691,
subtitles_ru_alternate,1,5,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.95733642578125,691,
subtitles_ru_alternate,1,5,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.7781903743743896,691,
subtitles_ru_alternate,1,5,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.861164093017578,691,
subtitles_ru_alternate,1,5,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.8268885612487793,691,
subtitles_ru_alternate,1,5,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.8621268272399902,691,
subtitles_ru_alternate,1,5,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.8216166496276855,691,
subtitles_ru_alternate,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0069098472595215,691,
subtitles_ru_alternate,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.025178909301758,691,
subtitles_ru_alternate,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0631070137023926,691,
subtitles_ru_alternate,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0902633666992188,691,
subtitles_ru_alternate,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0272655487060547,691,
subtitles_ru_alternate,1,5,grep (lines),grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.510146617889404,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep (lines),grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.541701793670654,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep (lines),grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.506088733673096,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep (lines),grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.51838755607605,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep (lines),grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.486810684204102,691,LC_ALL=C
subtitles_ru_alternate,1,5,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9679937362670898,691,
subtitles_ru_alternate,1,5,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9942011833190918,691,
subtitles_ru_alternate,1,5,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9233448505401611,691,
subtitles_ru_alternate,1,5,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9294781684875488,691,
subtitles_ru_alternate,1,5,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.8729774951934814,691,
subtitles_ru_alternate,1,5,grep,grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.100147485733032,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep,grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.075790166854858,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep,grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.069685220718384,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep,grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.0526063442230225,691,LC_ALL=C
subtitles_ru_alternate,1,5,grep,grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.129194498062134,691,LC_ALL=C
subtitles_ru_alternate_casei,1,5,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.7894201278686523,691,
subtitles_ru_alternate_casei,1,5,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.7878782749176025,691,
subtitles_ru_alternate_casei,1,5,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.796328544616699,691,
subtitles_ru_alternate_casei,1,5,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.8249149322509766,691,
subtitles_ru_alternate_casei,1,5,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.7949724197387695,691,
subtitles_ru_alternate_casei,1,5,ucg (ASCII),ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.075739622116089,691,
subtitles_ru_alternate_casei,1,5,ucg (ASCII),ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.013590097427368,691,
subtitles_ru_alternate_casei,1,5,ucg (ASCII),ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.012375593185425,691,
subtitles_ru_alternate_casei,1,5,ucg (ASCII),ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.023118495941162,691,
subtitles_ru_alternate_casei,1,5,ucg (ASCII),ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0641982555389404,691,
subtitles_ru_alternate_casei,1,5,grep (ASCII),grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.467320442199707,691,LC_ALL=C
subtitles_ru_alternate_casei,1,5,grep (ASCII),grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.486851692199707,691,LC_ALL=C
subtitles_ru_alternate_casei,1,5,grep (ASCII),grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.479818344116211,691,LC_ALL=C
subtitles_ru_alternate_casei,1,5,grep (ASCII),grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.516186475753784,691,LC_ALL=C
subtitles_ru_alternate_casei,1,5,grep (ASCII),grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,7.471773862838745,691,LC_ALL=C
subtitles_ru_alternate_casei,1,5,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,11.026185274124146,735,
subtitles_ru_alternate_casei,1,5,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,11.168465614318848,735,
subtitles_ru_alternate_casei,1,5,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,11.039950370788574,735,
subtitles_ru_alternate_casei,1,5,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,11.089850425720215,735,
subtitles_ru_alternate_casei,1,5,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,11.112446546554565,735,
subtitles_ru_alternate_casei,1,5,grep,grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.822641849517822,735,LC_ALL=en_US.UTF-8
subtitles_ru_alternate_casei,1,5,grep,grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.808355331420898,735,LC_ALL=en_US.UTF-8
subtitles_ru_alternate_casei,1,5,grep,grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.80171275138855,735,LC_ALL=en_US.UTF-8
subtitles_ru_alternate_casei,1,5,grep,grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.794351577758789,735,LC_ALL=en_US.UTF-8
subtitles_ru_alternate_casei,1,5,grep,grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.844403266906738,735,LC_ALL=en_US.UTF-8
subtitles_ru_literal,1,5,rg,rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.20681476593017578,583,
subtitles_ru_literal,1,5,rg,rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.190568208694458,583,
subtitles_ru_literal,1,5,rg,rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.18462657928466797,583,
subtitles_ru_literal,1,5,rg,rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.1873643398284912,583,
subtitles_ru_literal,1,5,rg,rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.20382428169250488,583,
subtitles_ru_literal,1,5,rg (no mmap),rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.3085510730743408,583,
subtitles_ru_literal,1,5,rg (no mmap),rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.318758487701416,583,
subtitles_ru_literal,1,5,rg (no mmap),rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.3177149295806885,583,
subtitles_ru_literal,1,5,rg (no mmap),rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.31236958503723145,583,
subtitles_ru_literal,1,5,rg (no mmap),rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.31880998611450195,583,
subtitles_ru_literal,1,5,pt,pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.152938365936279,583,
subtitles_ru_literal,1,5,pt,pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.124867677688599,583,
subtitles_ru_literal,1,5,pt,pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.132290363311768,583,
subtitles_ru_literal,1,5,pt,pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.158328056335449,583,
subtitles_ru_literal,1,5,pt,pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.1022467613220215,583,
subtitles_ru_literal,1,5,sift,sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.807113409042358,583,
subtitles_ru_literal,1,5,sift,sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.8178558349609375,583,
subtitles_ru_literal,1,5,sift,sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.925220012664795,583,
subtitles_ru_literal,1,5,sift,sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.861236333847046,583,
subtitles_ru_literal,1,5,sift,sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.763278484344482,583,
subtitles_ru_literal,1,5,grep,grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.704503059387207,583,LC_ALL=C
subtitles_ru_literal,1,5,grep,grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6887199878692627,583,LC_ALL=C
subtitles_ru_literal,1,5,grep,grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7092702388763428,583,LC_ALL=C
subtitles_ru_literal,1,5,grep,grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6964359283447266,583,LC_ALL=C
subtitles_ru_literal,1,5,grep,grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6928379535675049,583,LC_ALL=C
subtitles_ru_literal,1,5,rg (lines),rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2646975517272949,583,
subtitles_ru_literal,1,5,rg (lines),rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.26806163787841797,583,
subtitles_ru_literal,1,5,rg (lines),rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2700214385986328,583,
subtitles_ru_literal,1,5,rg (lines),rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2669072151184082,583,
subtitles_ru_literal,1,5,rg (lines),rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2656106948852539,583,
subtitles_ru_literal,1,5,ag (lines),ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.9972407817840576,583,
subtitles_ru_literal,1,5,ag (lines),ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.906053066253662,583,
subtitles_ru_literal,1,5,ag (lines),ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.864766836166382,583,
subtitles_ru_literal,1,5,ag (lines),ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.7820546627044678,583,
subtitles_ru_literal,1,5,ag (lines),ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.7599871158599854,583,
subtitles_ru_literal,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.411653995513916,583,
subtitles_ru_literal,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.394604206085205,583,
subtitles_ru_literal,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.362853765487671,583,
subtitles_ru_literal,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.4795477390289307,583,
subtitles_ru_literal,1,5,ucg (lines),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.4428844451904297,583,
subtitles_ru_literal,1,5,pt (lines),pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.122563123703003,583,
subtitles_ru_literal,1,5,pt (lines),pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.17008900642395,583,
subtitles_ru_literal,1,5,pt (lines),pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.1965367794036865,583,
subtitles_ru_literal,1,5,pt (lines),pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.152370929718018,583,
subtitles_ru_literal,1,5,pt (lines),pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,5.106513738632202,583,
subtitles_ru_literal,1,5,sift (lines),sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.408761978149414,583,
subtitles_ru_literal,1,5,sift (lines),sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.423579454421997,583,
subtitles_ru_literal,1,5,sift (lines),sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.2807464599609375,583,
subtitles_ru_literal,1,5,sift (lines),sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.3771467208862305,583,
subtitles_ru_literal,1,5,sift (lines),sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.378506422042847,583,
subtitles_ru_literal,1,5,grep (lines),grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.121800422668457,583,LC_ALL=C
subtitles_ru_literal,1,5,grep (lines),grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.1189923286437988,583,LC_ALL=C
subtitles_ru_literal,1,5,grep (lines),grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0678138732910156,583,LC_ALL=C
subtitles_ru_literal,1,5,grep (lines),grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0668041706085205,583,LC_ALL=C
subtitles_ru_literal,1,5,grep (lines),grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0713574886322021,583,LC_ALL=C
subtitles_ru_literal_casei,1,5,rg,rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9427816867828369,604,
subtitles_ru_literal_casei,1,5,rg,rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0397350788116455,604,
subtitles_ru_literal_casei,1,5,rg,rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9732518196105957,604,
subtitles_ru_literal_casei,1,5,rg,rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9387776851654053,604,
subtitles_ru_literal_casei,1,5,rg,rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.9536802768707275,604,
subtitles_ru_literal_casei,1,5,grep,grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.338641405105591,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,5,grep,grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.280565023422241,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,5,grep,grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.241750240325928,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,5,grep,grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.316105604171753,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,5,grep,grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,6.307560205459595,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,5,grep (ASCII),grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7379302978515625,583,LC_ALL=C
subtitles_ru_literal_casei,1,5,grep (ASCII),grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7226619720458984,583,LC_ALL=C
subtitles_ru_literal_casei,1,5,grep (ASCII),grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.683293342590332,583,LC_ALL=C
subtitles_ru_literal_casei,1,5,grep (ASCII),grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.714146614074707,583,LC_ALL=C
subtitles_ru_literal_casei,1,5,grep (ASCII),grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7654330730438232,583,LC_ALL=C
subtitles_ru_literal_casei,1,5,rg (lines),rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0237820148468018,604,
subtitles_ru_literal_casei,1,5,rg (lines),rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0194151401519775,604,
subtitles_ru_literal_casei,1,5,rg (lines),rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0364336967468262,604,
subtitles_ru_literal_casei,1,5,rg (lines),rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.035005807876587,604,
subtitles_ru_literal_casei,1,5,rg (lines),rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0438766479492188,604,
subtitles_ru_literal_casei,1,5,ag (lines) (ASCII),ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.619025468826294,,
subtitles_ru_literal_casei,1,5,ag (lines) (ASCII),ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.647244930267334,,
subtitles_ru_literal_casei,1,5,ag (lines) (ASCII),ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6785612106323242,,
subtitles_ru_literal_casei,1,5,ag (lines) (ASCII),ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6503715515136719,,
subtitles_ru_literal_casei,1,5,ag (lines) (ASCII),ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6314499378204346,,
subtitles_ru_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.8302316665649414,583,
subtitles_ru_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7719593048095703,583,
subtitles_ru_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7697594165802002,583,
subtitles_ru_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7312629222869873,583,
subtitles_ru_literal_casei,1,5,ucg (lines) (ASCII),ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.767866849899292,583,
subtitles_ru_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.19411826133728027,,
subtitles_ru_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.18651676177978516,,
subtitles_ru_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.19614577293395996,,
subtitles_ru_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.18459081649780273,,
subtitles_ru_literal_word,1,5,rg (ASCII),rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.1797487735748291,,
subtitles_ru_literal_word,1,5,ag (ASCII),ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6507105827331543,,
subtitles_ru_literal_word,1,5,ag (ASCII),ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6480035781860352,,
subtitles_ru_literal_word,1,5,ag (ASCII),ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.7138750553131104,,
subtitles_ru_literal_word,1,5,ag (ASCII),ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6521759033203125,,
subtitles_ru_literal_word,1,5,ag (ASCII),ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.6728894710540771,,
subtitles_ru_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.3646819591522217,583,
subtitles_ru_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.3836848735809326,583,
subtitles_ru_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.419490337371826,583,
subtitles_ru_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.363335609436035,583,
subtitles_ru_literal_word,1,5,ucg (ASCII),ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.488351345062256,583,
subtitles_ru_literal_word,1,5,grep (ASCII),grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.171506643295288,583,LC_ALL=C
subtitles_ru_literal_word,1,5,grep (ASCII),grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.1602776050567627,583,LC_ALL=C
subtitles_ru_literal_word,1,5,grep (ASCII),grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.084787368774414,583,LC_ALL=C
subtitles_ru_literal_word,1,5,grep (ASCII),grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0714166164398193,583,LC_ALL=C
subtitles_ru_literal_word,1,5,grep (ASCII),grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.083632469177246,583,LC_ALL=C
subtitles_ru_literal_word,1,5,rg,rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2769143581390381,579,
subtitles_ru_literal_word,1,5,rg,rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2694058418273926,579,
subtitles_ru_literal_word,1,5,rg,rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.26763367652893066,579,
subtitles_ru_literal_word,1,5,rg,rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2671318054199219,579,
subtitles_ru_literal_word,1,5,rg,rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2922348976135254,579,
subtitles_ru_literal_word,1,5,grep,grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.083528757095337,579,LC_ALL=en_US.UTF-8
subtitles_ru_literal_word,1,5,grep,grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0857081413269043,579,LC_ALL=en_US.UTF-8
subtitles_ru_literal_word,1,5,grep,grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.07025146484375,579,LC_ALL=en_US.UTF-8
subtitles_ru_literal_word,1,5,grep,grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.071930170059204,579,LC_ALL=en_US.UTF-8
subtitles_ru_literal_word,1,5,grep,grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.0709245204925537,579,LC_ALL=en_US.UTF-8
subtitles_ru_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.1552906036376953,41,
subtitles_ru_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.164951801300049,41,
subtitles_ru_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.175389289855957,41,
subtitles_ru_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.1861774921417236,41,
subtitles_ru_no_literal,1,5,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,3.153625011444092,41,
subtitles_ru_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.7353317737579346,,
subtitles_ru_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.7592883110046387,,
subtitles_ru_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.7242491245269775,,
subtitles_ru_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.747089385986328,,
subtitles_ru_no_literal,1,5,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.732586145401001,,
subtitles_ru_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0796375274658203,,
subtitles_ru_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.9670393466949463,,
subtitles_ru_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.9413447380065918,,
subtitles_ru_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.916764497756958,,
subtitles_ru_no_literal,1,5,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.9110031127929688,,
subtitles_ru_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0622072219848633,,
subtitles_ru_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0975682735443115,,
subtitles_ru_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0741493701934814,,
subtitles_ru_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0423810482025146,,
subtitles_ru_no_literal,1,5,ucg (ASCII),ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.000764846801758,,
subtitles_ru_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.6251120567321777,,LC_ALL=C
subtitles_ru_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.644089698791504,,LC_ALL=C
subtitles_ru_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.6416165828704834,,LC_ALL=C
subtitles_ru_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.6321892738342285,,LC_ALL=C
subtitles_ru_no_literal,1,5,grep (ASCII),grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.6264762878417969,,LC_ALL=C
subtitles_ru_surrounding_words,1,5,rg,rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.29879307746887207,278,
subtitles_ru_surrounding_words,1,5,rg,rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.3226010799407959,278,
subtitles_ru_surrounding_words,1,5,rg,rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.32187771797180176,278,
subtitles_ru_surrounding_words,1,5,rg,rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.2825047969818115,278,
subtitles_ru_surrounding_words,1,5,rg,rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,0.283217191696167,278,
subtitles_ru_surrounding_words,1,5,grep,grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.3977878093719482,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,5,grep,grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.4288139343261719,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,5,grep,grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.4054889678955078,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,5,grep,grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.4003441333770752,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,5,grep,grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.5269148349761963,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.8912529945373535,,
subtitles_ru_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.9221522808074951,,
subtitles_ru_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.9416618347167969,,
subtitles_ru_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.893650770187378,,
subtitles_ru_surrounding_words,1,5,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.8895554542541504,,
subtitles_ru_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0110745429992676,,
subtitles_ru_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.9790067672729492,,
subtitles_ru_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.0426392555236816,,
subtitles_ru_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.121723175048828,,
subtitles_ru_surrounding_words,1,5,ucg (ASCII),ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,2.1247596740722656,,
subtitles_ru_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.3579976558685303,,LC_ALL=C
subtitles_ru_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.382859468460083,,LC_ALL=C
subtitles_ru_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.393401861190796,,LC_ALL=C
subtitles_ru_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.474374532699585,,LC_ALL=C
subtitles_ru_surrounding_words,1,5,grep (ASCII),grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru,1.3835601806640625,,LC_ALL=C
1 benchmark warmup_iter iter name command duration lines env
2 linux_alternates 1 5 rg (ignore) rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.10186767578125 68
3 linux_alternates 1 5 rg (ignore) rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.10199356079101562 68
4 linux_alternates 1 5 rg (ignore) rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09750819206237793 68
5 linux_alternates 1 5 rg (ignore) rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09634733200073242 68
6 linux_alternates 1 5 rg (ignore) rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.10117292404174805 68
7 linux_alternates 1 5 ag (ignore) ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.49642109870910645 68
8 linux_alternates 1 5 ag (ignore) ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.48993706703186035 68
9 linux_alternates 1 5 ag (ignore) ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.4837028980255127 68
10 linux_alternates 1 5 ag (ignore) ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.4773833751678467 68
11 linux_alternates 1 5 ag (ignore) ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.558436393737793 68
12 linux_alternates 1 5 git grep (ignore) git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.2605454921722412 68 LC_ALL=C
13 linux_alternates 1 5 git grep (ignore) git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.26748204231262207 68 LC_ALL=C
14 linux_alternates 1 5 git grep (ignore) git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.26719212532043457 68 LC_ALL=C
15 linux_alternates 1 5 git grep (ignore) git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.2719383239746094 68 LC_ALL=C
16 linux_alternates 1 5 git grep (ignore) git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.26963257789611816 68 LC_ALL=C
17 linux_alternates 1 5 rg (whitelist) rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.08797001838684082 68
18 linux_alternates 1 5 rg (whitelist) rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09073781967163086 68
19 linux_alternates 1 5 rg (whitelist) rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.0914468765258789 68
20 linux_alternates 1 5 rg (whitelist) rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09071612358093262 68
21 linux_alternates 1 5 rg (whitelist) rg --no-ignore -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.0914316177368164 68
22 linux_alternates 1 5 ucg (whitelist) ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.1372535228729248 68
23 linux_alternates 1 5 ucg (whitelist) ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.13880419731140137 68
24 linux_alternates 1 5 ucg (whitelist) ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.13315439224243164 68
25 linux_alternates 1 5 ucg (whitelist) ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.1367807388305664 68
26 linux_alternates 1 5 ucg (whitelist) ucg --nosmart-case ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.13135552406311035 68
27 linux_alternates_casei 1 5 rg (ignore) rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.12781810760498047 160
28 linux_alternates_casei 1 5 rg (ignore) rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.11988544464111328 160
29 linux_alternates_casei 1 5 rg (ignore) rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.1205439567565918 160
30 linux_alternates_casei 1 5 rg (ignore) rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.12867259979248047 160
31 linux_alternates_casei 1 5 rg (ignore) rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.1215970516204834 160
32 linux_alternates_casei 1 5 ag (ignore) ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.5444357395172119 160
33 linux_alternates_casei 1 5 ag (ignore) ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.5511739253997803 160
34 linux_alternates_casei 1 5 ag (ignore) ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.5382294654846191 160
35 linux_alternates_casei 1 5 ag (ignore) ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.5499558448791504 160
36 linux_alternates_casei 1 5 ag (ignore) ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.6376545429229736 160
37 linux_alternates_casei 1 5 git grep (ignore) git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.9767155647277832 160 LC_ALL=C
38 linux_alternates_casei 1 5 git grep (ignore) git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.920574426651001 160 LC_ALL=C
39 linux_alternates_casei 1 5 git grep (ignore) git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.9352290630340576 160 LC_ALL=C
40 linux_alternates_casei 1 5 git grep (ignore) git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.8866012096405029 160 LC_ALL=C
41 linux_alternates_casei 1 5 git grep (ignore) git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.9189445972442627 160 LC_ALL=C
42 linux_alternates_casei 1 5 rg (whitelist) rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09351730346679688 160
43 linux_alternates_casei 1 5 rg (whitelist) rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09393739700317383 160
44 linux_alternates_casei 1 5 rg (whitelist) rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09986448287963867 160
45 linux_alternates_casei 1 5 rg (whitelist) rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09596824645996094 160
46 linux_alternates_casei 1 5 rg (whitelist) rg --no-ignore -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.09604883193969727 160
47 linux_alternates_casei 1 5 ucg (whitelist) ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.23943114280700684 160
48 linux_alternates_casei 1 5 ucg (whitelist) ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.2587015628814697 160
49 linux_alternates_casei 1 5 ucg (whitelist) ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.2543606758117676 160
50 linux_alternates_casei 1 5 ucg (whitelist) ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.2490406036376953 160
51 linux_alternates_casei 1 5 ucg (whitelist) ucg -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.24046540260314941 160
52 linux_literal 1 5 rg (ignore) rg -n PM_RESUME 0.08253765106201172 16
53 linux_literal 1 5 rg (ignore) rg -n PM_RESUME 0.08176755905151367 16
54 linux_literal 1 5 rg (ignore) rg -n PM_RESUME 0.08141684532165527 16
55 linux_literal 1 5 rg (ignore) rg -n PM_RESUME 0.08108830451965332 16
56 linux_literal 1 5 rg (ignore) rg -n PM_RESUME 0.08082938194274902 16
57 linux_literal 1 5 rg (ignore) (mmap) rg -n --mmap PM_RESUME 0.6870582103729248 16
58 linux_literal 1 5 rg (ignore) (mmap) rg -n --mmap PM_RESUME 0.807842493057251 16
59 linux_literal 1 5 rg (ignore) (mmap) rg -n --mmap PM_RESUME 0.8129942417144775 16
60 linux_literal 1 5 rg (ignore) (mmap) rg -n --mmap PM_RESUME 0.7582321166992188 16
61 linux_literal 1 5 rg (ignore) (mmap) rg -n --mmap PM_RESUME 0.6869800090789795 16
62 linux_literal 1 5 ag (ignore) (mmap) ag -s PM_RESUME 0.6534101963043213 16
63 linux_literal 1 5 ag (ignore) (mmap) ag -s PM_RESUME 0.6020612716674805 16
64 linux_literal 1 5 ag (ignore) (mmap) ag -s PM_RESUME 0.6712157726287842 16
65 linux_literal 1 5 ag (ignore) (mmap) ag -s PM_RESUME 0.6267571449279785 16
66 linux_literal 1 5 ag (ignore) (mmap) ag -s PM_RESUME 0.505136251449585 16
67 linux_literal 1 5 pt (ignore) pt PM_RESUME 0.21415948867797852 16
68 linux_literal 1 5 pt (ignore) pt PM_RESUME 0.19318318367004395 16
69 linux_literal 1 5 pt (ignore) pt PM_RESUME 0.21352124214172363 16
70 linux_literal 1 5 pt (ignore) pt PM_RESUME 0.18979454040527344 16
71 linux_literal 1 5 pt (ignore) pt PM_RESUME 0.16629600524902344 16
72 linux_literal 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME 0.46967077255249023 16
73 linux_literal 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME 0.46343088150024414 16
74 linux_literal 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME 0.4723978042602539 16
75 linux_literal 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME 0.4741063117980957 16
76 linux_literal 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git PM_RESUME 0.4613051414489746 16
77 linux_literal 1 5 git grep (ignore) git grep -I -n PM_RESUME 0.20196986198425293 16 LC_ALL=C
78 linux_literal 1 5 git grep (ignore) git grep -I -n PM_RESUME 0.18932533264160156 16 LC_ALL=C
79 linux_literal 1 5 git grep (ignore) git grep -I -n PM_RESUME 0.19396305084228516 16 LC_ALL=C
80 linux_literal 1 5 git grep (ignore) git grep -I -n PM_RESUME 0.1952073574066162 16 LC_ALL=C
81 linux_literal 1 5 git grep (ignore) git grep -I -n PM_RESUME 0.20149731636047363 16 LC_ALL=C
82 linux_literal 1 5 rg (whitelist) rg -n --no-ignore -tall PM_RESUME 0.08270478248596191 16
83 linux_literal 1 5 rg (whitelist) rg -n --no-ignore -tall PM_RESUME 0.08414745330810547 16
84 linux_literal 1 5 rg (whitelist) rg -n --no-ignore -tall PM_RESUME 0.08627724647521973 16
85 linux_literal 1 5 rg (whitelist) rg -n --no-ignore -tall PM_RESUME 0.08978700637817383 16
86 linux_literal 1 5 rg (whitelist) rg -n --no-ignore -tall PM_RESUME 0.0836489200592041 16
87 linux_literal 1 5 ucg (whitelist) ucg --nosmart-case PM_RESUME 0.15774202346801758 16
88 linux_literal 1 5 ucg (whitelist) ucg --nosmart-case PM_RESUME 0.16005396842956543 16
89 linux_literal 1 5 ucg (whitelist) ucg --nosmart-case PM_RESUME 0.15743708610534668 16
90 linux_literal 1 5 ucg (whitelist) ucg --nosmart-case PM_RESUME 0.16156601905822754 16
91 linux_literal 1 5 ucg (whitelist) ucg --nosmart-case PM_RESUME 0.1557624340057373 16
92 linux_literal_casei 1 5 rg (ignore) rg -n -i PM_RESUME 0.1028127670288086 374
93 linux_literal_casei 1 5 rg (ignore) rg -n -i PM_RESUME 0.10258054733276367 374
94 linux_literal_casei 1 5 rg (ignore) rg -n -i PM_RESUME 0.10902261734008789 374
95 linux_literal_casei 1 5 rg (ignore) rg -n -i PM_RESUME 0.10802555084228516 374
96 linux_literal_casei 1 5 rg (ignore) rg -n -i PM_RESUME 0.10153412818908691 374
97 linux_literal_casei 1 5 rg (ignore) (mmap) rg -n -i --mmap PM_RESUME 0.7902817726135254 374
98 linux_literal_casei 1 5 rg (ignore) (mmap) rg -n -i --mmap PM_RESUME 0.7985179424285889 374
99 linux_literal_casei 1 5 rg (ignore) (mmap) rg -n -i --mmap PM_RESUME 0.8208649158477783 374
100 linux_literal_casei 1 5 rg (ignore) (mmap) rg -n -i --mmap PM_RESUME 0.7937076091766357 374
101 linux_literal_casei 1 5 rg (ignore) (mmap) rg -n -i --mmap PM_RESUME 0.7936429977416992 374
102 linux_literal_casei 1 5 ag (ignore) (mmap) ag -i PM_RESUME 0.5215470790863037 374
103 linux_literal_casei 1 5 ag (ignore) (mmap) ag -i PM_RESUME 0.46518707275390625 374
104 linux_literal_casei 1 5 ag (ignore) (mmap) ag -i PM_RESUME 0.4467353820800781 374
105 linux_literal_casei 1 5 ag (ignore) (mmap) ag -i PM_RESUME 0.4595184326171875 374
106 linux_literal_casei 1 5 ag (ignore) (mmap) ag -i PM_RESUME 0.4531285762786865 374
107 linux_literal_casei 1 5 pt (ignore) pt -i PM_RESUME 14.187762022018433 374
108 linux_literal_casei 1 5 pt (ignore) pt -i PM_RESUME 14.178058385848999 374
109 linux_literal_casei 1 5 pt (ignore) pt -i PM_RESUME 14.096448421478271 374
110 linux_literal_casei 1 5 pt (ignore) pt -i PM_RESUME 14.190524339675903 374
111 linux_literal_casei 1 5 pt (ignore) pt -i PM_RESUME 14.231573343276978 374
112 linux_literal_casei 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME 0.4668574333190918 374
113 linux_literal_casei 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME 0.46050214767456055 374
114 linux_literal_casei 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME 0.46228861808776855 374
115 linux_literal_casei 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME 0.44957947731018066 374
116 linux_literal_casei 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git PM_RESUME 0.4612581729888916 374
117 linux_literal_casei 1 5 git grep (ignore) git grep -I -n -i PM_RESUME 0.1932981014251709 370 LC_ALL=C
118 linux_literal_casei 1 5 git grep (ignore) git grep -I -n -i PM_RESUME 0.20561552047729492 370 LC_ALL=C
119 linux_literal_casei 1 5 git grep (ignore) git grep -I -n -i PM_RESUME 0.19516706466674805 370 LC_ALL=C
120 linux_literal_casei 1 5 git grep (ignore) git grep -I -n -i PM_RESUME 0.20196247100830078 370 LC_ALL=C
121 linux_literal_casei 1 5 git grep (ignore) git grep -I -n -i PM_RESUME 0.19236421585083008 370 LC_ALL=C
122 linux_literal_casei 1 5 rg (whitelist) rg -n -i --no-ignore -tall PM_RESUME 0.09555959701538086 370
123 linux_literal_casei 1 5 rg (whitelist) rg -n -i --no-ignore -tall PM_RESUME 0.09589338302612305 370
124 linux_literal_casei 1 5 rg (whitelist) rg -n -i --no-ignore -tall PM_RESUME 0.09479856491088867 370
125 linux_literal_casei 1 5 rg (whitelist) rg -n -i --no-ignore -tall PM_RESUME 0.09741568565368652 370
126 linux_literal_casei 1 5 rg (whitelist) rg -n -i --no-ignore -tall PM_RESUME 0.10127615928649902 370
127 linux_literal_casei 1 5 ucg (whitelist) ucg -i PM_RESUME 0.15514039993286133 370
128 linux_literal_casei 1 5 ucg (whitelist) ucg -i PM_RESUME 0.15668940544128418 370
129 linux_literal_casei 1 5 ucg (whitelist) ucg -i PM_RESUME 0.15429425239562988 370
130 linux_literal_casei 1 5 ucg (whitelist) ucg -i PM_RESUME 0.15332818031311035 370
131 linux_literal_casei 1 5 ucg (whitelist) ucg -i PM_RESUME 0.14861536026000977 370
132 linux_literal_default 1 5 rg rg PM_RESUME 0.08931398391723633 16
133 linux_literal_default 1 5 rg rg PM_RESUME 0.08717465400695801 16
134 linux_literal_default 1 5 rg rg PM_RESUME 0.0879361629486084 16
135 linux_literal_default 1 5 rg rg PM_RESUME 0.08688950538635254 16
136 linux_literal_default 1 5 rg rg PM_RESUME 0.09138607978820801 16
137 linux_literal_default 1 5 ag ag PM_RESUME 0.5342838764190674 16
138 linux_literal_default 1 5 ag ag PM_RESUME 0.47187042236328125 16
139 linux_literal_default 1 5 ag ag PM_RESUME 0.4456596374511719 16
140 linux_literal_default 1 5 ag ag PM_RESUME 0.4507424831390381 16
141 linux_literal_default 1 5 ag ag PM_RESUME 0.44472575187683105 16
142 linux_literal_default 1 5 ucg ucg PM_RESUME 0.15556907653808594 16
143 linux_literal_default 1 5 ucg ucg PM_RESUME 0.1533644199371338 16
144 linux_literal_default 1 5 ucg ucg PM_RESUME 0.15392351150512695 16
145 linux_literal_default 1 5 ucg ucg PM_RESUME 0.1535196304321289 16
146 linux_literal_default 1 5 ucg ucg PM_RESUME 0.15589547157287598 16
147 linux_literal_default 1 5 pt pt PM_RESUME 0.2261514663696289 16
148 linux_literal_default 1 5 pt pt PM_RESUME 0.2731902599334717 16
149 linux_literal_default 1 5 pt pt PM_RESUME 0.2563004493713379 16
150 linux_literal_default 1 5 pt pt PM_RESUME 0.2575085163116455 16
151 linux_literal_default 1 5 pt pt PM_RESUME 0.1724245548248291 16
152 linux_literal_default 1 5 sift sift PM_RESUME 0.13233542442321777 16
153 linux_literal_default 1 5 sift sift PM_RESUME 0.1256580352783203 16
154 linux_literal_default 1 5 sift sift PM_RESUME 0.12435102462768555 16
155 linux_literal_default 1 5 sift sift PM_RESUME 0.1259307861328125 16
156 linux_literal_default 1 5 sift sift PM_RESUME 0.12412142753601074 16
157 linux_literal_default 1 5 git grep git grep PM_RESUME 0.1742086410522461 16 LC_ALL=en_US.UTF-8
158 linux_literal_default 1 5 git grep git grep PM_RESUME 0.16890597343444824 16 LC_ALL=en_US.UTF-8
159 linux_literal_default 1 5 git grep git grep PM_RESUME 0.16680669784545898 16 LC_ALL=en_US.UTF-8
160 linux_literal_default 1 5 git grep git grep PM_RESUME 0.16899871826171875 16 LC_ALL=en_US.UTF-8
161 linux_literal_default 1 5 git grep git grep PM_RESUME 0.19794917106628418 16 LC_ALL=en_US.UTF-8
162 linux_no_literal 1 5 rg (ignore) rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.33940672874450684 490
163 linux_no_literal 1 5 rg (ignore) rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.3274960517883301 490
164 linux_no_literal 1 5 rg (ignore) rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.32681775093078613 490
165 linux_no_literal 1 5 rg (ignore) rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.32865071296691895 490
166 linux_no_literal 1 5 rg (ignore) rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.3240926265716553 490
167 linux_no_literal 1 5 rg (ignore) (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.17426586151123047 490
168 linux_no_literal 1 5 rg (ignore) (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.17265701293945312 490
169 linux_no_literal 1 5 rg (ignore) (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.1703634262084961 490
170 linux_no_literal 1 5 rg (ignore) (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.17192435264587402 490
171 linux_no_literal 1 5 rg (ignore) (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.1704559326171875 490
172 linux_no_literal 1 5 ag (ignore) (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.8443403244018555 766
173 linux_no_literal 1 5 ag (ignore) (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.6956703662872314 766
174 linux_no_literal 1 5 ag (ignore) (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.6938261985778809 766
175 linux_no_literal 1 5 ag (ignore) (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.695967435836792 766
176 linux_no_literal 1 5 ag (ignore) (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.6945271492004395 766
177 linux_no_literal 1 5 pt (ignore) (ASCII) pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 12.645716428756714 490
178 linux_no_literal 1 5 pt (ignore) (ASCII) pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 12.441533088684082 490
179 linux_no_literal 1 5 pt (ignore) (ASCII) pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 12.472522735595703 490
180 linux_no_literal 1 5 pt (ignore) (ASCII) pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 12.42497444152832 490
181 linux_no_literal 1 5 pt (ignore) (ASCII) pt -e \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 12.407486200332642 490
182 linux_no_literal 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 9.091489553451538 490
183 linux_no_literal 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 9.049214124679565 490
184 linux_no_literal 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 8.879419803619385 490
185 linux_no_literal 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 9.07261848449707 490
186 linux_no_literal 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 8.918747901916504 490
187 linux_no_literal 1 5 git grep (ignore) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 8.334321975708008 490 LC_ALL=en_US.UTF-8
188 linux_no_literal 1 5 git grep (ignore) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 8.993232727050781 490 LC_ALL=en_US.UTF-8
189 linux_no_literal 1 5 git grep (ignore) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 8.622304916381836 490 LC_ALL=en_US.UTF-8
190 linux_no_literal 1 5 git grep (ignore) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 8.35973048210144 490 LC_ALL=en_US.UTF-8
191 linux_no_literal 1 5 git grep (ignore) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 8.39980435371399 490 LC_ALL=en_US.UTF-8
192 linux_no_literal 1 5 git grep (ignore) (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 2.0318400859832764 490 LC_ALL=C
193 linux_no_literal 1 5 git grep (ignore) (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 1.8587837219238281 490 LC_ALL=C
194 linux_no_literal 1 5 git grep (ignore) (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 1.873384714126587 490 LC_ALL=C
195 linux_no_literal 1 5 git grep (ignore) (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 1.8111364841461182 490 LC_ALL=C
196 linux_no_literal 1 5 git grep (ignore) (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 1.8385357856750488 490 LC_ALL=C
197 linux_no_literal 1 5 rg (whitelist) rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.28792643547058105 458
198 linux_no_literal 1 5 rg (whitelist) rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.28545212745666504 458
199 linux_no_literal 1 5 rg (whitelist) rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.28576135635375977 458
200 linux_no_literal 1 5 rg (whitelist) rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.29883813858032227 458
201 linux_no_literal 1 5 rg (whitelist) rg -n --no-ignore -tall \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.28493285179138184 458
202 linux_no_literal 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.15974783897399902 458
203 linux_no_literal 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.15943312644958496 458
204 linux_no_literal 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.160233736038208 458
205 linux_no_literal 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.16201996803283691 458
206 linux_no_literal 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.16033530235290527 458
207 linux_no_literal 1 5 ucg (whitelist) (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.4639148712158203 416
208 linux_no_literal 1 5 ucg (whitelist) (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.46042823791503906 416
209 linux_no_literal 1 5 ucg (whitelist) (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.45925426483154297 416
210 linux_no_literal 1 5 ucg (whitelist) (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.477064847946167 416
211 linux_no_literal 1 5 ucg (whitelist) (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.507554292678833 416
212 linux_re_literal_suffix 1 5 rg (ignore) rg -n [A-Z]+_RESUME 0.08520364761352539 1652
213 linux_re_literal_suffix 1 5 rg (ignore) rg -n [A-Z]+_RESUME 0.08203816413879395 1652
214 linux_re_literal_suffix 1 5 rg (ignore) rg -n [A-Z]+_RESUME 0.08355021476745605 1652
215 linux_re_literal_suffix 1 5 rg (ignore) rg -n [A-Z]+_RESUME 0.0865166187286377 1652
216 linux_re_literal_suffix 1 5 rg (ignore) rg -n [A-Z]+_RESUME 0.08125448226928711 1652
217 linux_re_literal_suffix 1 5 ag (ignore) ag -s [A-Z]+_RESUME 0.4846627712249756 1652
218 linux_re_literal_suffix 1 5 ag (ignore) ag -s [A-Z]+_RESUME 0.48070311546325684 1652
219 linux_re_literal_suffix 1 5 ag (ignore) ag -s [A-Z]+_RESUME 0.4813041687011719 1652
220 linux_re_literal_suffix 1 5 ag (ignore) ag -s [A-Z]+_RESUME 0.4755582809448242 1652
221 linux_re_literal_suffix 1 5 ag (ignore) ag -s [A-Z]+_RESUME 0.4926290512084961 1652
222 linux_re_literal_suffix 1 5 pt (ignore) pt -e [A-Z]+_RESUME 14.124520540237427 1652
223 linux_re_literal_suffix 1 5 pt (ignore) pt -e [A-Z]+_RESUME 14.151537656784058 1652
224 linux_re_literal_suffix 1 5 pt (ignore) pt -e [A-Z]+_RESUME 14.157994270324707 1652
225 linux_re_literal_suffix 1 5 pt (ignore) pt -e [A-Z]+_RESUME 14.102291822433472 1652
226 linux_re_literal_suffix 1 5 pt (ignore) pt -e [A-Z]+_RESUME 14.103861093521118 1652
227 linux_re_literal_suffix 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME 4.182392835617065 1652
228 linux_re_literal_suffix 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME 4.190829277038574 1652
229 linux_re_literal_suffix 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME 3.9770240783691406 1652
230 linux_re_literal_suffix 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME 3.9978606700897217 1652
231 linux_re_literal_suffix 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git [A-Z]+_RESUME 4.146454572677612 1652
232 linux_re_literal_suffix 1 5 git grep (ignore) git grep -E -I -n [A-Z]+_RESUME 0.5080702304840088 1652 LC_ALL=C
233 linux_re_literal_suffix 1 5 git grep (ignore) git grep -E -I -n [A-Z]+_RESUME 0.5281260013580322 1652 LC_ALL=C
234 linux_re_literal_suffix 1 5 git grep (ignore) git grep -E -I -n [A-Z]+_RESUME 0.5350546836853027 1652 LC_ALL=C
235 linux_re_literal_suffix 1 5 git grep (ignore) git grep -E -I -n [A-Z]+_RESUME 0.5474245548248291 1652 LC_ALL=C
236 linux_re_literal_suffix 1 5 git grep (ignore) git grep -E -I -n [A-Z]+_RESUME 0.5256762504577637 1652 LC_ALL=C
237 linux_re_literal_suffix 1 5 rg (whitelist) rg -n --no-ignore -tall [A-Z]+_RESUME 0.07924222946166992 1630
238 linux_re_literal_suffix 1 5 rg (whitelist) rg -n --no-ignore -tall [A-Z]+_RESUME 0.0767812728881836 1630
239 linux_re_literal_suffix 1 5 rg (whitelist) rg -n --no-ignore -tall [A-Z]+_RESUME 0.07874488830566406 1630
240 linux_re_literal_suffix 1 5 rg (whitelist) rg -n --no-ignore -tall [A-Z]+_RESUME 0.0804905891418457 1630
241 linux_re_literal_suffix 1 5 rg (whitelist) rg -n --no-ignore -tall [A-Z]+_RESUME 0.07479119300842285 1630
242 linux_re_literal_suffix 1 5 ucg (whitelist) ucg --nosmart-case [A-Z]+_RESUME 0.13643193244934082 1630
243 linux_re_literal_suffix 1 5 ucg (whitelist) ucg --nosmart-case [A-Z]+_RESUME 0.13543128967285156 1630
244 linux_re_literal_suffix 1 5 ucg (whitelist) ucg --nosmart-case [A-Z]+_RESUME 0.13312768936157227 1630
245 linux_re_literal_suffix 1 5 ucg (whitelist) ucg --nosmart-case [A-Z]+_RESUME 0.13562273979187012 1630
246 linux_re_literal_suffix 1 5 ucg (whitelist) ucg --nosmart-case [A-Z]+_RESUME 0.13236212730407715 1630
247 linux_unicode_greek 1 5 rg rg -n \p{Greek} 0.17355775833129883 23
248 linux_unicode_greek 1 5 rg rg -n \p{Greek} 0.1676032543182373 23
249 linux_unicode_greek 1 5 rg rg -n \p{Greek} 0.1727275848388672 23
250 linux_unicode_greek 1 5 rg rg -n \p{Greek} 0.17095375061035156 23
251 linux_unicode_greek 1 5 rg rg -n \p{Greek} 0.17271947860717773 23
252 linux_unicode_greek 1 5 pt pt -e \p{Greek} 14.14364218711853 23
253 linux_unicode_greek 1 5 pt pt -e \p{Greek} 14.137334108352661 23
254 linux_unicode_greek 1 5 pt pt -e \p{Greek} 14.083475351333618 23
255 linux_unicode_greek 1 5 pt pt -e \p{Greek} 14.095231056213379 23
256 linux_unicode_greek 1 5 pt pt -e \p{Greek} 14.151906490325928 23
257 linux_unicode_greek 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek} 2.8376963138580322 23
258 linux_unicode_greek 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek} 2.8271427154541016 23
259 linux_unicode_greek 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek} 2.8310961723327637 23
260 linux_unicode_greek 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek} 2.826141595840454 23
261 linux_unicode_greek 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \p{Greek} 2.805818796157837 23
262 linux_unicode_greek_casei 1 5 rg rg -n -i \p{Greek} 0.16843819618225098 103
263 linux_unicode_greek_casei 1 5 rg rg -n -i \p{Greek} 0.1704998016357422 103
264 linux_unicode_greek_casei 1 5 rg rg -n -i \p{Greek} 0.17055058479309082 103
265 linux_unicode_greek_casei 1 5 rg rg -n -i \p{Greek} 0.17064881324768066 103
266 linux_unicode_greek_casei 1 5 rg rg -n -i \p{Greek} 0.1699228286743164 103
267 linux_unicode_greek_casei 1 5 pt pt -i -e \p{Greek} 14.164355993270874 23
268 linux_unicode_greek_casei 1 5 pt pt -i -e \p{Greek} 14.099931478500366 23
269 linux_unicode_greek_casei 1 5 pt pt -i -e \p{Greek} 14.155095338821411 23
270 linux_unicode_greek_casei 1 5 pt pt -i -e \p{Greek} 14.109308004379272 23
271 linux_unicode_greek_casei 1 5 pt pt -i -e \p{Greek} 14.072362422943115 23
272 linux_unicode_greek_casei 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek} 0.003945589065551758
273 linux_unicode_greek_casei 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek} 0.004189729690551758
274 linux_unicode_greek_casei 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek} 0.0034589767456054688
275 linux_unicode_greek_casei 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek} 0.003614187240600586
276 linux_unicode_greek_casei 1 5 sift sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -i --git \p{Greek} 0.003975629806518555
277 linux_unicode_word 1 5 rg (ignore) rg -n \wAh 0.09798526763916016 186
278 linux_unicode_word 1 5 rg (ignore) rg -n \wAh 0.09575009346008301 186
279 linux_unicode_word 1 5 rg (ignore) rg -n \wAh 0.10181760787963867 186
280 linux_unicode_word 1 5 rg (ignore) rg -n \wAh 0.09650158882141113 186
281 linux_unicode_word 1 5 rg (ignore) rg -n \wAh 0.09717488288879395 186
282 linux_unicode_word 1 5 rg (ignore) (ASCII) rg -n (?-u)\wAh 0.09417867660522461 174
283 linux_unicode_word 1 5 rg (ignore) (ASCII) rg -n (?-u)\wAh 0.09903812408447266 174
284 linux_unicode_word 1 5 rg (ignore) (ASCII) rg -n (?-u)\wAh 0.09407877922058105 174
285 linux_unicode_word 1 5 rg (ignore) (ASCII) rg -n (?-u)\wAh 0.09681963920593262 174
286 linux_unicode_word 1 5 rg (ignore) (ASCII) rg -n (?-u)\wAh 0.09762454032897949 174
287 linux_unicode_word 1 5 ag (ignore) (ASCII) ag -s \wAh 0.5779609680175781 174
288 linux_unicode_word 1 5 ag (ignore) (ASCII) ag -s \wAh 0.635645866394043 174
289 linux_unicode_word 1 5 ag (ignore) (ASCII) ag -s \wAh 0.6109263896942139 174
290 linux_unicode_word 1 5 ag (ignore) (ASCII) ag -s \wAh 0.6260912418365479 174
291 linux_unicode_word 1 5 ag (ignore) (ASCII) ag -s \wAh 0.6823546886444092 174
292 linux_unicode_word 1 5 pt (ignore) (ASCII) pt -e \wAh 14.178487062454224 174
293 linux_unicode_word 1 5 pt (ignore) (ASCII) pt -e \wAh 14.190000057220459 174
294 linux_unicode_word 1 5 pt (ignore) (ASCII) pt -e \wAh 14.16363000869751 174
295 linux_unicode_word 1 5 pt (ignore) (ASCII) pt -e \wAh 14.160430431365967 174
296 linux_unicode_word 1 5 pt (ignore) (ASCII) pt -e \wAh 14.2189621925354 174
297 linux_unicode_word 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh 4.17629337310791 174
298 linux_unicode_word 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh 4.051238059997559 174
299 linux_unicode_word 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh 4.323853015899658 174
300 linux_unicode_word 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh 4.085661172866821 174
301 linux_unicode_word 1 5 sift (ignore) (ASCII) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n --git \wAh 4.036486625671387 174
302 linux_unicode_word 1 5 git grep (ignore) git grep -E -I -n \wAh 4.620476961135864 186 LC_ALL=en_US.UTF-8
303 linux_unicode_word 1 5 git grep (ignore) git grep -E -I -n \wAh 4.536192417144775 186 LC_ALL=en_US.UTF-8
304 linux_unicode_word 1 5 git grep (ignore) git grep -E -I -n \wAh 4.510494232177734 186 LC_ALL=en_US.UTF-8
305 linux_unicode_word 1 5 git grep (ignore) git grep -E -I -n \wAh 6.001620769500732 186 LC_ALL=en_US.UTF-8
306 linux_unicode_word 1 5 git grep (ignore) git grep -E -I -n \wAh 4.602652311325073 186 LC_ALL=en_US.UTF-8
307 linux_unicode_word 1 5 git grep (ignore) (ASCII) git grep -E -I -n \wAh 1.3785994052886963 174 LC_ALL=C
308 linux_unicode_word 1 5 git grep (ignore) (ASCII) git grep -E -I -n \wAh 1.4163663387298584 174 LC_ALL=C
309 linux_unicode_word 1 5 git grep (ignore) (ASCII) git grep -E -I -n \wAh 1.402677297592163 174 LC_ALL=C
310 linux_unicode_word 1 5 git grep (ignore) (ASCII) git grep -E -I -n \wAh 1.3327512741088867 174 LC_ALL=C
311 linux_unicode_word 1 5 git grep (ignore) (ASCII) git grep -E -I -n \wAh 1.3501760959625244 174 LC_ALL=C
312 linux_unicode_word 1 5 rg (whitelist) rg -n --no-ignore -tall \wAh 0.07958698272705078 180
313 linux_unicode_word 1 5 rg (whitelist) rg -n --no-ignore -tall \wAh 0.0798649787902832 180
314 linux_unicode_word 1 5 rg (whitelist) rg -n --no-ignore -tall \wAh 0.08086204528808594 180
315 linux_unicode_word 1 5 rg (whitelist) rg -n --no-ignore -tall \wAh 0.0814356803894043 180
316 linux_unicode_word 1 5 rg (whitelist) rg -n --no-ignore -tall \wAh 0.08273720741271973 180
317 linux_unicode_word 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\wAh 0.08280825614929199 168
318 linux_unicode_word 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\wAh 0.08074021339416504 168
319 linux_unicode_word 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\wAh 0.0821676254272461 168
320 linux_unicode_word 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\wAh 0.07926368713378906 168
321 linux_unicode_word 1 5 rg (whitelist) (ASCII) rg -n --no-ignore -tall (?-u)\wAh 0.08405280113220215 168
322 linux_unicode_word 1 5 ucg (ASCII) ucg --nosmart-case \wAh 0.1545090675354004 168
323 linux_unicode_word 1 5 ucg (ASCII) ucg --nosmart-case \wAh 0.1517190933227539 168
324 linux_unicode_word 1 5 ucg (ASCII) ucg --nosmart-case \wAh 0.15704965591430664 168
325 linux_unicode_word 1 5 ucg (ASCII) ucg --nosmart-case \wAh 0.15523767471313477 168
326 linux_unicode_word 1 5 ucg (ASCII) ucg --nosmart-case \wAh 0.1582942008972168 168
327 linux_word 1 5 rg (ignore) rg -n -w PM_RESUME 0.09102368354797363 6
328 linux_word 1 5 rg (ignore) rg -n -w PM_RESUME 0.08986210823059082 6
329 linux_word 1 5 rg (ignore) rg -n -w PM_RESUME 0.08989477157592773 6
330 linux_word 1 5 rg (ignore) rg -n -w PM_RESUME 0.0895695686340332 6
331 linux_word 1 5 rg (ignore) rg -n -w PM_RESUME 0.09547114372253418 6
332 linux_word 1 5 ag (ignore) ag -s -w PM_RESUME 0.4948008060455322 6
333 linux_word 1 5 ag (ignore) ag -s -w PM_RESUME 0.45710110664367676 6
334 linux_word 1 5 ag (ignore) ag -s -w PM_RESUME 0.44803452491760254 6
335 linux_word 1 5 ag (ignore) ag -s -w PM_RESUME 0.44779396057128906 6
336 linux_word 1 5 ag (ignore) ag -s -w PM_RESUME 0.4563112258911133 6
337 linux_word 1 5 pt (ignore) pt -w PM_RESUME 14.233235597610474 6
338 linux_word 1 5 pt (ignore) pt -w PM_RESUME 14.277648687362671 6
339 linux_word 1 5 pt (ignore) pt -w PM_RESUME 14.218127727508545 6
340 linux_word 1 5 pt (ignore) pt -w PM_RESUME 14.171622037887573 6
341 linux_word 1 5 pt (ignore) pt -w PM_RESUME 14.214240312576294 6
342 linux_word 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME 3.1536731719970703 6
343 linux_word 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME 3.2415099143981934 6
344 linux_word 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME 3.2526626586914062 6
345 linux_word 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME 3.2590816020965576 6
346 linux_word 1 5 sift (ignore) sift --binary-skip --exclude-files .* --exclude-files *.pdf -n -w --git PM_RESUME 3.222473621368408 6
347 linux_word 1 5 git grep (ignore) git grep -E -I -n -w PM_RESUME 0.16982412338256836 6 LC_ALL=C
348 linux_word 1 5 git grep (ignore) git grep -E -I -n -w PM_RESUME 0.16739583015441895 6 LC_ALL=C
349 linux_word 1 5 git grep (ignore) git grep -E -I -n -w PM_RESUME 0.16866540908813477 6 LC_ALL=C
350 linux_word 1 5 git grep (ignore) git grep -E -I -n -w PM_RESUME 0.18207120895385742 6 LC_ALL=C
351 linux_word 1 5 git grep (ignore) git grep -E -I -n -w PM_RESUME 0.17716264724731445 6 LC_ALL=C
352 linux_word 1 5 rg (whitelist) rg -n -w --no-ignore -tall PM_RESUME 0.07490420341491699 6
353 linux_word 1 5 rg (whitelist) rg -n -w --no-ignore -tall PM_RESUME 0.07714152336120605 6
354 linux_word 1 5 rg (whitelist) rg -n -w --no-ignore -tall PM_RESUME 0.07552146911621094 6
355 linux_word 1 5 rg (whitelist) rg -n -w --no-ignore -tall PM_RESUME 0.07651710510253906 6
356 linux_word 1 5 rg (whitelist) rg -n -w --no-ignore -tall PM_RESUME 0.0757131576538086 6
357 linux_word 1 5 ucg (whitelist) ucg --nosmart-case -w PM_RESUME 0.1530015468597412 6
358 linux_word 1 5 ucg (whitelist) ucg --nosmart-case -w PM_RESUME 0.15152239799499512 6
359 linux_word 1 5 ucg (whitelist) ucg --nosmart-case -w PM_RESUME 0.1571195125579834 6
360 linux_word 1 5 ucg (whitelist) ucg --nosmart-case -w PM_RESUME 0.15993595123291016 6
361 linux_word 1 5 ucg (whitelist) ucg --nosmart-case -w PM_RESUME 0.15633797645568848 6
362 subtitles_en_alternate 1 5 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.33371877670288086 848
363 subtitles_en_alternate 1 5 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3207988739013672 848
364 subtitles_en_alternate 1 5 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3301675319671631 848
365 subtitles_en_alternate 1 5 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.29731154441833496 848
366 subtitles_en_alternate 1 5 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2711911201477051 848
367 subtitles_en_alternate 1 5 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.186570405960083 848
368 subtitles_en_alternate 1 5 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.1659939289093018 848
369 subtitles_en_alternate 1 5 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.187847137451172 848
370 subtitles_en_alternate 1 5 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.3522064685821533 848
371 subtitles_en_alternate 1 5 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.316105842590332 848
372 subtitles_en_alternate 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.1400718688964844 848
373 subtitles_en_alternate 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.1492774486541748 848
374 subtitles_en_alternate 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.1337254047393799 848
375 subtitles_en_alternate 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.1037378311157227 848
376 subtitles_en_alternate 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.1312851905822754 848
377 subtitles_en_alternate 1 5 grep (lines) grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.8294000625610352 848 LC_ALL=C
378 subtitles_en_alternate 1 5 grep (lines) grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.808884620666504 848 LC_ALL=C
379 subtitles_en_alternate 1 5 grep (lines) grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.8134734630584717 848 LC_ALL=C
380 subtitles_en_alternate 1 5 grep (lines) grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.8405649662017822 848 LC_ALL=C
381 subtitles_en_alternate 1 5 grep (lines) grep -E -an Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.8500289916992188 848 LC_ALL=C
382 subtitles_en_alternate 1 5 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.21175312995910645 848
383 subtitles_en_alternate 1 5 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2118232250213623 848
384 subtitles_en_alternate 1 5 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.21287035942077637 848
385 subtitles_en_alternate 1 5 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.21167230606079102 848
386 subtitles_en_alternate 1 5 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.28102636337280273 848
387 subtitles_en_alternate 1 5 grep grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5029187202453613 848 LC_ALL=C
388 subtitles_en_alternate 1 5 grep grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.49977445602417 848 LC_ALL=C
389 subtitles_en_alternate 1 5 grep grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.508340835571289 848 LC_ALL=C
390 subtitles_en_alternate 1 5 grep grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5002548694610596 848 LC_ALL=C
391 subtitles_en_alternate 1 5 grep grep -E -a Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.629526138305664 848 LC_ALL=C
392 subtitles_en_alternate_casei 1 5 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.730497360229492 862
393 subtitles_en_alternate_casei 1 5 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.781018018722534 862
394 subtitles_en_alternate_casei 1 5 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.7858059406280518 862
395 subtitles_en_alternate_casei 1 5 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.7127914428710938 862
396 subtitles_en_alternate_casei 1 5 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.717308759689331 862
397 subtitles_en_alternate_casei 1 5 ucg (ASCII) ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.428208351135254 862
398 subtitles_en_alternate_casei 1 5 ucg (ASCII) ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.389420509338379 862
399 subtitles_en_alternate_casei 1 5 ucg (ASCII) ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.403301954269409 862
400 subtitles_en_alternate_casei 1 5 ucg (ASCII) ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.4691550731658936 862
401 subtitles_en_alternate_casei 1 5 ucg (ASCII) ucg -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.4245004653930664 862
402 subtitles_en_alternate_casei 1 5 grep (ASCII) grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.978189706802368 862 LC_ALL=C
403 subtitles_en_alternate_casei 1 5 grep (ASCII) grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.974303722381592 862 LC_ALL=C
404 subtitles_en_alternate_casei 1 5 grep (ASCII) grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.982886552810669 862 LC_ALL=C
405 subtitles_en_alternate_casei 1 5 grep (ASCII) grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.90018630027771 862 LC_ALL=C
406 subtitles_en_alternate_casei 1 5 grep (ASCII) grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.0078439712524414 862 LC_ALL=C
407 subtitles_en_alternate_casei 1 5 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.9129142761230469 862
408 subtitles_en_alternate_casei 1 5 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.9066660404205322 862
409 subtitles_en_alternate_casei 1 5 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.946380615234375 862
410 subtitles_en_alternate_casei 1 5 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.9672930240631104 862
411 subtitles_en_alternate_casei 1 5 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.028451919555664 862
412 subtitles_en_alternate_casei 1 5 grep grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.9427030086517334 862 LC_ALL=en_US.UTF-8
413 subtitles_en_alternate_casei 1 5 grep grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.938739061355591 862 LC_ALL=en_US.UTF-8
414 subtitles_en_alternate_casei 1 5 grep grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.921248435974121 862 LC_ALL=en_US.UTF-8
415 subtitles_en_alternate_casei 1 5 grep grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.9194068908691406 862 LC_ALL=en_US.UTF-8
416 subtitles_en_alternate_casei 1 5 grep grep -E -ani Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 2.917184829711914 862 LC_ALL=en_US.UTF-8
417 subtitles_en_literal 1 5 rg rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.12293672561645508 629
418 subtitles_en_literal 1 5 rg rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.1259000301361084 629
419 subtitles_en_literal 1 5 rg rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.12285709381103516 629
420 subtitles_en_literal 1 5 rg rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.12280964851379395 629
421 subtitles_en_literal 1 5 rg rg Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.1547396183013916 629
422 subtitles_en_literal 1 5 rg (no mmap) rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.22011375427246094 629
423 subtitles_en_literal 1 5 rg (no mmap) rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.23095202445983887 629
424 subtitles_en_literal 1 5 rg (no mmap) rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2577846050262451 629
425 subtitles_en_literal 1 5 rg (no mmap) rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2563819885253906 629
426 subtitles_en_literal 1 5 rg (no mmap) rg --no-mmap Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.24869346618652344 629
427 subtitles_en_literal 1 5 pt pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.415337324142456 629
428 subtitles_en_literal 1 5 pt pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.4208543300628662 629
429 subtitles_en_literal 1 5 pt pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.416351079940796 629
430 subtitles_en_literal 1 5 pt pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.4270708560943604 629
431 subtitles_en_literal 1 5 pt pt -N Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.4243996143341064 629
432 subtitles_en_literal 1 5 sift sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2245020866394043 629
433 subtitles_en_literal 1 5 sift sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2382345199584961 629
434 subtitles_en_literal 1 5 sift sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.23533034324645996 629
435 subtitles_en_literal 1 5 sift sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2577829360961914 629
436 subtitles_en_literal 1 5 sift sift Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2599349021911621 629
437 subtitles_en_literal 1 5 grep grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.4733700752258301 629 LC_ALL=C
438 subtitles_en_literal 1 5 grep grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.4598572254180908 629 LC_ALL=C
439 subtitles_en_literal 1 5 grep grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.5303301811218262 629 LC_ALL=C
440 subtitles_en_literal 1 5 grep grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.4775106906890869 629 LC_ALL=C
441 subtitles_en_literal 1 5 grep grep -a Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.4881136417388916 629 LC_ALL=C
442 subtitles_en_literal 1 5 rg (lines) rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.20051789283752441 629
443 subtitles_en_literal 1 5 rg (lines) rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.17326998710632324 629
444 subtitles_en_literal 1 5 rg (lines) rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.20733428001403809 629
445 subtitles_en_literal 1 5 rg (lines) rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.189713716506958 629
446 subtitles_en_literal 1 5 rg (lines) rg -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.17817258834838867 629
447 subtitles_en_literal 1 5 ag (lines) ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5327835083007812 629
448 subtitles_en_literal 1 5 ag (lines) ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5411181449890137 629
449 subtitles_en_literal 1 5 ag (lines) ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.600783109664917 629
450 subtitles_en_literal 1 5 ag (lines) ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5838911533355713 629
451 subtitles_en_literal 1 5 ag (lines) ag -s Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.6051928997039795 629
452 subtitles_en_literal 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.4090385437011719 629
453 subtitles_en_literal 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3816399574279785 629
454 subtitles_en_literal 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.38033008575439453 629
455 subtitles_en_literal 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3731727600097656 629
456 subtitles_en_literal 1 5 ucg (lines) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.38796329498291016 629
457 subtitles_en_literal 1 5 pt (lines) pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.4102630615234375 629
458 subtitles_en_literal 1 5 pt (lines) pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.4137451648712158 629
459 subtitles_en_literal 1 5 pt (lines) pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.4649333953857422 629
460 subtitles_en_literal 1 5 pt (lines) pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.430387258529663 629
461 subtitles_en_literal 1 5 pt (lines) pt Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.541991949081421 629
462 subtitles_en_literal 1 5 sift (lines) sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.6231405735015869 629
463 subtitles_en_literal 1 5 sift (lines) sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.5986526012420654 629
464 subtitles_en_literal 1 5 sift (lines) sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.5821917057037354 629
465 subtitles_en_literal 1 5 sift (lines) sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.6045489311218262 629
466 subtitles_en_literal 1 5 sift (lines) sift -n Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.5986905097961426 629
467 subtitles_en_literal 1 5 grep (lines) grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.8278565406799316 629 LC_ALL=C
468 subtitles_en_literal 1 5 grep (lines) grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.777052640914917 629 LC_ALL=C
469 subtitles_en_literal 1 5 grep (lines) grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.7619414329528809 629 LC_ALL=C
470 subtitles_en_literal 1 5 grep (lines) grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.8248744010925293 629 LC_ALL=C
471 subtitles_en_literal 1 5 grep (lines) grep -an Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.824932336807251 629 LC_ALL=C
472 subtitles_en_literal_casei 1 5 rg rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.2718961238861084 642
473 subtitles_en_literal_casei 1 5 rg rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.27082157135009766 642
474 subtitles_en_literal_casei 1 5 rg rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.27086758613586426 642
475 subtitles_en_literal_casei 1 5 rg rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.274705171585083 642
476 subtitles_en_literal_casei 1 5 rg rg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3337059020996094 642
477 subtitles_en_literal_casei 1 5 grep grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.9112112522125244 642 LC_ALL=en_US.UTF-8
478 subtitles_en_literal_casei 1 5 grep grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.907888650894165 642 LC_ALL=en_US.UTF-8
479 subtitles_en_literal_casei 1 5 grep grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.912668228149414 642 LC_ALL=en_US.UTF-8
480 subtitles_en_literal_casei 1 5 grep grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.9082865715026855 642 LC_ALL=en_US.UTF-8
481 subtitles_en_literal_casei 1 5 grep grep -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.9177796840667725 642 LC_ALL=en_US.UTF-8
482 subtitles_en_literal_casei 1 5 grep (ASCII) grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.6020669937133789 642 LC_ALL=C
483 subtitles_en_literal_casei 1 5 grep (ASCII) grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.568228006362915 642 LC_ALL=C
484 subtitles_en_literal_casei 1 5 grep (ASCII) grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.5648214817047119 642 LC_ALL=C
485 subtitles_en_literal_casei 1 5 grep (ASCII) grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.5568234920501709 642 LC_ALL=C
486 subtitles_en_literal_casei 1 5 grep (ASCII) grep -E -ai Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.5588953495025635 642 LC_ALL=C
487 subtitles_en_literal_casei 1 5 rg (lines) rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3486766815185547 642
488 subtitles_en_literal_casei 1 5 rg (lines) rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.34010815620422363 642
489 subtitles_en_literal_casei 1 5 rg (lines) rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.33849263191223145 642
490 subtitles_en_literal_casei 1 5 rg (lines) rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3917088508605957 642
491 subtitles_en_literal_casei 1 5 rg (lines) rg -n -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.39266490936279297 642
492 subtitles_en_literal_casei 1 5 ag (lines) (ASCII) ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5564041137695312 642
493 subtitles_en_literal_casei 1 5 ag (lines) (ASCII) ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5533506870269775 642
494 subtitles_en_literal_casei 1 5 ag (lines) (ASCII) ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.6205368041992188 642
495 subtitles_en_literal_casei 1 5 ag (lines) (ASCII) ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5530028343200684 642
496 subtitles_en_literal_casei 1 5 ag (lines) (ASCII) ag -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.6189889907836914 642
497 subtitles_en_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3834850788116455 642
498 subtitles_en_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.41916346549987793 642
499 subtitles_en_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3895289897918701 642
500 subtitles_en_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.4278140068054199 642
501 subtitles_en_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.4013493061065674 642
502 subtitles_en_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.17953085899353027 629
503 subtitles_en_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.17679834365844727 629
504 subtitles_en_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.17448186874389648 629
505 subtitles_en_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.21117281913757324 629
506 subtitles_en_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.1848156452178955 629
507 subtitles_en_literal_word 1 5 ag (ASCII) ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5236153602600098 629
508 subtitles_en_literal_word 1 5 ag (ASCII) ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.52512526512146 629
509 subtitles_en_literal_word 1 5 ag (ASCII) ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5218794345855713 629
510 subtitles_en_literal_word 1 5 ag (ASCII) ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5384306907653809 629
511 subtitles_en_literal_word 1 5 ag (ASCII) ag -sw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5150353908538818 629
512 subtitles_en_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3757903575897217 629
513 subtitles_en_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3744041919708252 629
514 subtitles_en_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.37261366844177246 629
515 subtitles_en_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.40795230865478516 629
516 subtitles_en_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.3868849277496338 629
517 subtitles_en_literal_word 1 5 grep (ASCII) grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.8265349864959717 629 LC_ALL=C
518 subtitles_en_literal_word 1 5 grep (ASCII) grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.8123743534088135 629 LC_ALL=C
519 subtitles_en_literal_word 1 5 grep (ASCII) grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.7669925689697266 629 LC_ALL=C
520 subtitles_en_literal_word 1 5 grep (ASCII) grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.766636848449707 629 LC_ALL=C
521 subtitles_en_literal_word 1 5 grep (ASCII) grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.7665839195251465 629 LC_ALL=C
522 subtitles_en_literal_word 1 5 rg rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.1879115104675293 629
523 subtitles_en_literal_word 1 5 rg rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18082356452941895 629
524 subtitles_en_literal_word 1 5 rg rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18497347831726074 629
525 subtitles_en_literal_word 1 5 rg rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.1769394874572754 629
526 subtitles_en_literal_word 1 5 rg rg -nw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.1917715072631836 629
527 subtitles_en_literal_word 1 5 grep grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.8192996978759766 629 LC_ALL=en_US.UTF-8
528 subtitles_en_literal_word 1 5 grep grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.8193323612213135 629 LC_ALL=en_US.UTF-8
529 subtitles_en_literal_word 1 5 grep grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.7837738990783691 629 LC_ALL=en_US.UTF-8
530 subtitles_en_literal_word 1 5 grep grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.7639024257659912 629 LC_ALL=en_US.UTF-8
531 subtitles_en_literal_word 1 5 grep grep -anw Sherlock Holmes /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.7634689807891846 629 LC_ALL=en_US.UTF-8
532 subtitles_en_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.7922985553741455 13
533 subtitles_en_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.7885758876800537 13
534 subtitles_en_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.802325963973999 13
535 subtitles_en_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.792595386505127 13
536 subtitles_en_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.7909605503082275 13
537 subtitles_en_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5903098583221436 13
538 subtitles_en_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5982813835144043 13
539 subtitles_en_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5926671028137207 13
540 subtitles_en_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.5976767539978027 13
541 subtitles_en_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.593153953552246 13
542 subtitles_en_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 6.614634275436401 48
543 subtitles_en_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 6.574857473373413 48
544 subtitles_en_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 6.54079270362854 48
545 subtitles_en_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 6.600660800933838 48
546 subtitles_en_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 6.531627178192139 48
547 subtitles_en_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 5.361133337020874 13
548 subtitles_en_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 5.456786870956421 13
549 subtitles_en_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 5.403071403503418 13
550 subtitles_en_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 5.398236274719238 13
551 subtitles_en_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 5.348573923110962 13
552 subtitles_en_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.5057969093322754 13 LC_ALL=C
553 subtitles_en_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.4157862663269043 13 LC_ALL=C
554 subtitles_en_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.471182346343994 13 LC_ALL=C
555 subtitles_en_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.4590909481048584 13 LC_ALL=C
556 subtitles_en_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.3759689331054688 13 LC_ALL=C
557 subtitles_en_surrounding_words 1 5 rg rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18518710136413574 317
558 subtitles_en_surrounding_words 1 5 rg rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18791556358337402 317
559 subtitles_en_surrounding_words 1 5 rg rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18598675727844238 317
560 subtitles_en_surrounding_words 1 5 rg rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18552684783935547 317
561 subtitles_en_surrounding_words 1 5 rg rg -n \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.19262075424194336 317
562 subtitles_en_surrounding_words 1 5 grep grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.1321008205413818 317 LC_ALL=en_US.UTF-8
563 subtitles_en_surrounding_words 1 5 grep grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.0709969997406006 317 LC_ALL=en_US.UTF-8
564 subtitles_en_surrounding_words 1 5 grep grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.1117346286773682 317 LC_ALL=en_US.UTF-8
565 subtitles_en_surrounding_words 1 5 grep grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.0880234241485596 317 LC_ALL=en_US.UTF-8
566 subtitles_en_surrounding_words 1 5 grep grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.0745558738708496 317 LC_ALL=en_US.UTF-8
567 subtitles_en_surrounding_words 1 5 rg (ASCII) rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.1827528476715088 317
568 subtitles_en_surrounding_words 1 5 rg (ASCII) rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18874144554138184 317
569 subtitles_en_surrounding_words 1 5 rg (ASCII) rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.17983436584472656 317
570 subtitles_en_surrounding_words 1 5 rg (ASCII) rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.18831133842468262 317
571 subtitles_en_surrounding_words 1 5 rg (ASCII) rg -n (?-u)\w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 0.17810606956481934 317
572 subtitles_en_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 4.5957207679748535 323
573 subtitles_en_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 4.627211570739746 323
574 subtitles_en_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 4.554431200027466 323
575 subtitles_en_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 4.492656469345093 323
576 subtitles_en_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 4.443558216094971 323
577 subtitles_en_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.522758722305298 317
578 subtitles_en_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.502918004989624 317
579 subtitles_en_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.6503307819366455 317
580 subtitles_en_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.58940052986145 317
581 subtitles_en_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 3.569624423980713 317
582 subtitles_en_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.0672054290771484 317 LC_ALL=C
583 subtitles_en_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.0729331970214844 317 LC_ALL=C
584 subtitles_en_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.052501916885376 317 LC_ALL=C
585 subtitles_en_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.0711696147918701 317 LC_ALL=C
586 subtitles_en_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Holmes\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.sample.en 1.0863316059112549 317 LC_ALL=C
587 subtitles_ru_alternate 1 5 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0312588214874268 691
588 subtitles_ru_alternate 1 5 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.063939094543457 691
589 subtitles_ru_alternate 1 5 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0000121593475342 691
590 subtitles_ru_alternate 1 5 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9842438697814941 691
591 subtitles_ru_alternate 1 5 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.95733642578125 691
592 subtitles_ru_alternate 1 5 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.7781903743743896 691
593 subtitles_ru_alternate 1 5 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.861164093017578 691
594 subtitles_ru_alternate 1 5 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.8268885612487793 691
595 subtitles_ru_alternate 1 5 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.8621268272399902 691
596 subtitles_ru_alternate 1 5 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.8216166496276855 691
597 subtitles_ru_alternate 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0069098472595215 691
598 subtitles_ru_alternate 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.025178909301758 691
599 subtitles_ru_alternate 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0631070137023926 691
600 subtitles_ru_alternate 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0902633666992188 691
601 subtitles_ru_alternate 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0272655487060547 691
602 subtitles_ru_alternate 1 5 grep (lines) grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.510146617889404 691 LC_ALL=C
603 subtitles_ru_alternate 1 5 grep (lines) grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.541701793670654 691 LC_ALL=C
604 subtitles_ru_alternate 1 5 grep (lines) grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.506088733673096 691 LC_ALL=C
605 subtitles_ru_alternate 1 5 grep (lines) grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.51838755607605 691 LC_ALL=C
606 subtitles_ru_alternate 1 5 grep (lines) grep -E -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.486810684204102 691 LC_ALL=C
607 subtitles_ru_alternate 1 5 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9679937362670898 691
608 subtitles_ru_alternate 1 5 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9942011833190918 691
609 subtitles_ru_alternate 1 5 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9233448505401611 691
610 subtitles_ru_alternate 1 5 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9294781684875488 691
611 subtitles_ru_alternate 1 5 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.8729774951934814 691
612 subtitles_ru_alternate 1 5 grep grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.100147485733032 691 LC_ALL=C
613 subtitles_ru_alternate 1 5 grep grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.075790166854858 691 LC_ALL=C
614 subtitles_ru_alternate 1 5 grep grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.069685220718384 691 LC_ALL=C
615 subtitles_ru_alternate 1 5 grep grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.0526063442230225 691 LC_ALL=C
616 subtitles_ru_alternate 1 5 grep grep -E -a Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.129194498062134 691 LC_ALL=C
617 subtitles_ru_alternate_casei 1 5 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.7894201278686523 691
618 subtitles_ru_alternate_casei 1 5 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.7878782749176025 691
619 subtitles_ru_alternate_casei 1 5 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.796328544616699 691
620 subtitles_ru_alternate_casei 1 5 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.8249149322509766 691
621 subtitles_ru_alternate_casei 1 5 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.7949724197387695 691
622 subtitles_ru_alternate_casei 1 5 ucg (ASCII) ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.075739622116089 691
623 subtitles_ru_alternate_casei 1 5 ucg (ASCII) ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.013590097427368 691
624 subtitles_ru_alternate_casei 1 5 ucg (ASCII) ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.012375593185425 691
625 subtitles_ru_alternate_casei 1 5 ucg (ASCII) ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.023118495941162 691
626 subtitles_ru_alternate_casei 1 5 ucg (ASCII) ucg -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0641982555389404 691
627 subtitles_ru_alternate_casei 1 5 grep (ASCII) grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.467320442199707 691 LC_ALL=C
628 subtitles_ru_alternate_casei 1 5 grep (ASCII) grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.486851692199707 691 LC_ALL=C
629 subtitles_ru_alternate_casei 1 5 grep (ASCII) grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.479818344116211 691 LC_ALL=C
630 subtitles_ru_alternate_casei 1 5 grep (ASCII) grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.516186475753784 691 LC_ALL=C
631 subtitles_ru_alternate_casei 1 5 grep (ASCII) grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 7.471773862838745 691 LC_ALL=C
632 subtitles_ru_alternate_casei 1 5 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 11.026185274124146 735
633 subtitles_ru_alternate_casei 1 5 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 11.168465614318848 735
634 subtitles_ru_alternate_casei 1 5 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 11.039950370788574 735
635 subtitles_ru_alternate_casei 1 5 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 11.089850425720215 735
636 subtitles_ru_alternate_casei 1 5 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 11.112446546554565 735
637 subtitles_ru_alternate_casei 1 5 grep grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.822641849517822 735 LC_ALL=en_US.UTF-8
638 subtitles_ru_alternate_casei 1 5 grep grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.808355331420898 735 LC_ALL=en_US.UTF-8
639 subtitles_ru_alternate_casei 1 5 grep grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.80171275138855 735 LC_ALL=en_US.UTF-8
640 subtitles_ru_alternate_casei 1 5 grep grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.794351577758789 735 LC_ALL=en_US.UTF-8
641 subtitles_ru_alternate_casei 1 5 grep grep -E -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.844403266906738 735 LC_ALL=en_US.UTF-8
642 subtitles_ru_literal 1 5 rg rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.20681476593017578 583
643 subtitles_ru_literal 1 5 rg rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.190568208694458 583
644 subtitles_ru_literal 1 5 rg rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.18462657928466797 583
645 subtitles_ru_literal 1 5 rg rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.1873643398284912 583
646 subtitles_ru_literal 1 5 rg rg Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.20382428169250488 583
647 subtitles_ru_literal 1 5 rg (no mmap) rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.3085510730743408 583
648 subtitles_ru_literal 1 5 rg (no mmap) rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.318758487701416 583
649 subtitles_ru_literal 1 5 rg (no mmap) rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.3177149295806885 583
650 subtitles_ru_literal 1 5 rg (no mmap) rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.31236958503723145 583
651 subtitles_ru_literal 1 5 rg (no mmap) rg --no-mmap Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.31880998611450195 583
652 subtitles_ru_literal 1 5 pt pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.152938365936279 583
653 subtitles_ru_literal 1 5 pt pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.124867677688599 583
654 subtitles_ru_literal 1 5 pt pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.132290363311768 583
655 subtitles_ru_literal 1 5 pt pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.158328056335449 583
656 subtitles_ru_literal 1 5 pt pt -N Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.1022467613220215 583
657 subtitles_ru_literal 1 5 sift sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.807113409042358 583
658 subtitles_ru_literal 1 5 sift sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.8178558349609375 583
659 subtitles_ru_literal 1 5 sift sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.925220012664795 583
660 subtitles_ru_literal 1 5 sift sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.861236333847046 583
661 subtitles_ru_literal 1 5 sift sift Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.763278484344482 583
662 subtitles_ru_literal 1 5 grep grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.704503059387207 583 LC_ALL=C
663 subtitles_ru_literal 1 5 grep grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6887199878692627 583 LC_ALL=C
664 subtitles_ru_literal 1 5 grep grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7092702388763428 583 LC_ALL=C
665 subtitles_ru_literal 1 5 grep grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6964359283447266 583 LC_ALL=C
666 subtitles_ru_literal 1 5 grep grep -a Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6928379535675049 583 LC_ALL=C
667 subtitles_ru_literal 1 5 rg (lines) rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2646975517272949 583
668 subtitles_ru_literal 1 5 rg (lines) rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.26806163787841797 583
669 subtitles_ru_literal 1 5 rg (lines) rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2700214385986328 583
670 subtitles_ru_literal 1 5 rg (lines) rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2669072151184082 583
671 subtitles_ru_literal 1 5 rg (lines) rg -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2656106948852539 583
672 subtitles_ru_literal 1 5 ag (lines) ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.9972407817840576 583
673 subtitles_ru_literal 1 5 ag (lines) ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.906053066253662 583
674 subtitles_ru_literal 1 5 ag (lines) ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.864766836166382 583
675 subtitles_ru_literal 1 5 ag (lines) ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.7820546627044678 583
676 subtitles_ru_literal 1 5 ag (lines) ag -s Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.7599871158599854 583
677 subtitles_ru_literal 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.411653995513916 583
678 subtitles_ru_literal 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.394604206085205 583
679 subtitles_ru_literal 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.362853765487671 583
680 subtitles_ru_literal 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.4795477390289307 583
681 subtitles_ru_literal 1 5 ucg (lines) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.4428844451904297 583
682 subtitles_ru_literal 1 5 pt (lines) pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.122563123703003 583
683 subtitles_ru_literal 1 5 pt (lines) pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.17008900642395 583
684 subtitles_ru_literal 1 5 pt (lines) pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.1965367794036865 583
685 subtitles_ru_literal 1 5 pt (lines) pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.152370929718018 583
686 subtitles_ru_literal 1 5 pt (lines) pt Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 5.106513738632202 583
687 subtitles_ru_literal 1 5 sift (lines) sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.408761978149414 583
688 subtitles_ru_literal 1 5 sift (lines) sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.423579454421997 583
689 subtitles_ru_literal 1 5 sift (lines) sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.2807464599609375 583
690 subtitles_ru_literal 1 5 sift (lines) sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.3771467208862305 583
691 subtitles_ru_literal 1 5 sift (lines) sift -n Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.378506422042847 583
692 subtitles_ru_literal 1 5 grep (lines) grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.121800422668457 583 LC_ALL=C
693 subtitles_ru_literal 1 5 grep (lines) grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.1189923286437988 583 LC_ALL=C
694 subtitles_ru_literal 1 5 grep (lines) grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0678138732910156 583 LC_ALL=C
695 subtitles_ru_literal 1 5 grep (lines) grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0668041706085205 583 LC_ALL=C
696 subtitles_ru_literal 1 5 grep (lines) grep -an Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0713574886322021 583 LC_ALL=C
697 subtitles_ru_literal_casei 1 5 rg rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9427816867828369 604
698 subtitles_ru_literal_casei 1 5 rg rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0397350788116455 604
699 subtitles_ru_literal_casei 1 5 rg rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9732518196105957 604
700 subtitles_ru_literal_casei 1 5 rg rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9387776851654053 604
701 subtitles_ru_literal_casei 1 5 rg rg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.9536802768707275 604
702 subtitles_ru_literal_casei 1 5 grep grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.338641405105591 604 LC_ALL=en_US.UTF-8
703 subtitles_ru_literal_casei 1 5 grep grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.280565023422241 604 LC_ALL=en_US.UTF-8
704 subtitles_ru_literal_casei 1 5 grep grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.241750240325928 604 LC_ALL=en_US.UTF-8
705 subtitles_ru_literal_casei 1 5 grep grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.316105604171753 604 LC_ALL=en_US.UTF-8
706 subtitles_ru_literal_casei 1 5 grep grep -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 6.307560205459595 604 LC_ALL=en_US.UTF-8
707 subtitles_ru_literal_casei 1 5 grep (ASCII) grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7379302978515625 583 LC_ALL=C
708 subtitles_ru_literal_casei 1 5 grep (ASCII) grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7226619720458984 583 LC_ALL=C
709 subtitles_ru_literal_casei 1 5 grep (ASCII) grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.683293342590332 583 LC_ALL=C
710 subtitles_ru_literal_casei 1 5 grep (ASCII) grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.714146614074707 583 LC_ALL=C
711 subtitles_ru_literal_casei 1 5 grep (ASCII) grep -E -ai Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7654330730438232 583 LC_ALL=C
712 subtitles_ru_literal_casei 1 5 rg (lines) rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0237820148468018 604
713 subtitles_ru_literal_casei 1 5 rg (lines) rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0194151401519775 604
714 subtitles_ru_literal_casei 1 5 rg (lines) rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0364336967468262 604
715 subtitles_ru_literal_casei 1 5 rg (lines) rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.035005807876587 604
716 subtitles_ru_literal_casei 1 5 rg (lines) rg -n -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0438766479492188 604
717 subtitles_ru_literal_casei 1 5 ag (lines) (ASCII) ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.619025468826294
718 subtitles_ru_literal_casei 1 5 ag (lines) (ASCII) ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.647244930267334
719 subtitles_ru_literal_casei 1 5 ag (lines) (ASCII) ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6785612106323242
720 subtitles_ru_literal_casei 1 5 ag (lines) (ASCII) ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6503715515136719
721 subtitles_ru_literal_casei 1 5 ag (lines) (ASCII) ag -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6314499378204346
722 subtitles_ru_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.8302316665649414 583
723 subtitles_ru_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7719593048095703 583
724 subtitles_ru_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7697594165802002 583
725 subtitles_ru_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7312629222869873 583
726 subtitles_ru_literal_casei 1 5 ucg (lines) (ASCII) ucg -i Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.767866849899292 583
727 subtitles_ru_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.19411826133728027
728 subtitles_ru_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.18651676177978516
729 subtitles_ru_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.19614577293395996
730 subtitles_ru_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.18459081649780273
731 subtitles_ru_literal_word 1 5 rg (ASCII) rg -n (?-u:\b)Шерлок Холмс(?-u:\b) /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.1797487735748291
732 subtitles_ru_literal_word 1 5 ag (ASCII) ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6507105827331543
733 subtitles_ru_literal_word 1 5 ag (ASCII) ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6480035781860352
734 subtitles_ru_literal_word 1 5 ag (ASCII) ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.7138750553131104
735 subtitles_ru_literal_word 1 5 ag (ASCII) ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6521759033203125
736 subtitles_ru_literal_word 1 5 ag (ASCII) ag -sw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.6728894710540771
737 subtitles_ru_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.3646819591522217 583
738 subtitles_ru_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.3836848735809326 583
739 subtitles_ru_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.419490337371826 583
740 subtitles_ru_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.363335609436035 583
741 subtitles_ru_literal_word 1 5 ucg (ASCII) ucg --nosmart-case Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.488351345062256 583
742 subtitles_ru_literal_word 1 5 grep (ASCII) grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.171506643295288 583 LC_ALL=C
743 subtitles_ru_literal_word 1 5 grep (ASCII) grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.1602776050567627 583 LC_ALL=C
744 subtitles_ru_literal_word 1 5 grep (ASCII) grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.084787368774414 583 LC_ALL=C
745 subtitles_ru_literal_word 1 5 grep (ASCII) grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0714166164398193 583 LC_ALL=C
746 subtitles_ru_literal_word 1 5 grep (ASCII) grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.083632469177246 583 LC_ALL=C
747 subtitles_ru_literal_word 1 5 rg rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2769143581390381 579
748 subtitles_ru_literal_word 1 5 rg rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2694058418273926 579
749 subtitles_ru_literal_word 1 5 rg rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.26763367652893066 579
750 subtitles_ru_literal_word 1 5 rg rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2671318054199219 579
751 subtitles_ru_literal_word 1 5 rg rg -nw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2922348976135254 579
752 subtitles_ru_literal_word 1 5 grep grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.083528757095337 579 LC_ALL=en_US.UTF-8
753 subtitles_ru_literal_word 1 5 grep grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0857081413269043 579 LC_ALL=en_US.UTF-8
754 subtitles_ru_literal_word 1 5 grep grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.07025146484375 579 LC_ALL=en_US.UTF-8
755 subtitles_ru_literal_word 1 5 grep grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.071930170059204 579 LC_ALL=en_US.UTF-8
756 subtitles_ru_literal_word 1 5 grep grep -anw Шерлок Холмс /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.0709245204925537 579 LC_ALL=en_US.UTF-8
757 subtitles_ru_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.1552906036376953 41
758 subtitles_ru_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.164951801300049 41
759 subtitles_ru_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.175389289855957 41
760 subtitles_ru_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.1861774921417236 41
761 subtitles_ru_no_literal 1 5 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 3.153625011444092 41
762 subtitles_ru_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.7353317737579346
763 subtitles_ru_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.7592883110046387
764 subtitles_ru_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.7242491245269775
765 subtitles_ru_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.747089385986328
766 subtitles_ru_no_literal 1 5 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.732586145401001
767 subtitles_ru_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0796375274658203
768 subtitles_ru_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.9670393466949463
769 subtitles_ru_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.9413447380065918
770 subtitles_ru_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.916764497756958
771 subtitles_ru_no_literal 1 5 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.9110031127929688
772 subtitles_ru_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0622072219848633
773 subtitles_ru_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0975682735443115
774 subtitles_ru_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0741493701934814
775 subtitles_ru_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0423810482025146
776 subtitles_ru_no_literal 1 5 ucg (ASCII) ucg --nosmart-case \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.000764846801758
777 subtitles_ru_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.6251120567321777 LC_ALL=C
778 subtitles_ru_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.644089698791504 LC_ALL=C
779 subtitles_ru_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.6416165828704834 LC_ALL=C
780 subtitles_ru_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.6321892738342285 LC_ALL=C
781 subtitles_ru_no_literal 1 5 grep (ASCII) grep -E -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.6264762878417969 LC_ALL=C
782 subtitles_ru_surrounding_words 1 5 rg rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.29879307746887207 278
783 subtitles_ru_surrounding_words 1 5 rg rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.3226010799407959 278
784 subtitles_ru_surrounding_words 1 5 rg rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.32187771797180176 278
785 subtitles_ru_surrounding_words 1 5 rg rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.2825047969818115 278
786 subtitles_ru_surrounding_words 1 5 rg rg -n \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 0.283217191696167 278
787 subtitles_ru_surrounding_words 1 5 grep grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.3977878093719482 278 LC_ALL=en_US.UTF-8
788 subtitles_ru_surrounding_words 1 5 grep grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.4288139343261719 278 LC_ALL=en_US.UTF-8
789 subtitles_ru_surrounding_words 1 5 grep grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.4054889678955078 278 LC_ALL=en_US.UTF-8
790 subtitles_ru_surrounding_words 1 5 grep grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.4003441333770752 278 LC_ALL=en_US.UTF-8
791 subtitles_ru_surrounding_words 1 5 grep grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.5269148349761963 278 LC_ALL=en_US.UTF-8
792 subtitles_ru_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.8912529945373535
793 subtitles_ru_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.9221522808074951
794 subtitles_ru_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.9416618347167969
795 subtitles_ru_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.893650770187378
796 subtitles_ru_surrounding_words 1 5 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.8895554542541504
797 subtitles_ru_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0110745429992676
798 subtitles_ru_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.9790067672729492
799 subtitles_ru_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.0426392555236816
800 subtitles_ru_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.121723175048828
801 subtitles_ru_surrounding_words 1 5 ucg (ASCII) ucg --nosmart-case \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 2.1247596740722656
802 subtitles_ru_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.3579976558685303 LC_ALL=C
803 subtitles_ru_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.382859468460083 LC_ALL=C
804 subtitles_ru_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.393401861190796 LC_ALL=C
805 subtitles_ru_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.474374532699585 LC_ALL=C
806 subtitles_ru_surrounding_words 1 5 grep (ASCII) grep -E -an \w+\s+Холмс\s+\w+ /tmp/benchsuite/subtitles/OpenSubtitles2016.raw.ru 1.3835601806640625 LC_ALL=C

235
benchsuite/runs/2018-01-08-archlinux-cheetah/summary Normal file
View File

@@ -0,0 +1,235 @@
linux_alternates (pattern: ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT)
-------------------------------------------------------------------------
rg (ignore) 0.100 +/- 0.003 (lines: 68)
ag (ignore) 0.501 +/- 0.033 (lines: 68)
git grep (ignore) 0.267 +/- 0.004 (lines: 68)
rg (whitelist)* 0.090 +/- 0.001 (lines: 68)*
ucg (whitelist) 0.135 +/- 0.003 (lines: 68)
linux_alternates_casei (pattern: ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT)
-------------------------------------------------------------------------------
rg (ignore) 0.124 +/- 0.004 (lines: 160)
ag (ignore) 0.564 +/- 0.041 (lines: 160)
git grep (ignore) 0.928 +/- 0.033 (lines: 160)
rg (whitelist)* 0.096 +/- 0.003 (lines: 160)*
ucg (whitelist) 0.248 +/- 0.008 (lines: 160)
linux_literal (pattern: PM_RESUME)
----------------------------------
rg (ignore)* 0.082 +/- 0.001 (lines: 16)*
rg (ignore) (mmap) 0.751 +/- 0.062 (lines: 16)
ag (ignore) (mmap) 0.612 +/- 0.065 (lines: 16)
pt (ignore) 0.195 +/- 0.020 (lines: 16)
sift (ignore) 0.468 +/- 0.006 (lines: 16)
git grep (ignore) 0.196 +/- 0.005 (lines: 16)
rg (whitelist) 0.085 +/- 0.003 (lines: 16)
ucg (whitelist) 0.159 +/- 0.002 (lines: 16)
linux_literal_casei (pattern: PM_RESUME)
----------------------------------------
rg (ignore) 0.105 +/- 0.003 (lines: 374)
rg (ignore) (mmap) 0.799 +/- 0.012 (lines: 374)
ag (ignore) (mmap) 0.469 +/- 0.030 (lines: 374)
pt (ignore) 14.177 +/- 0.049 (lines: 374)
sift (ignore) 0.460 +/- 0.006 (lines: 374)
git grep (ignore) 0.198 +/- 0.006 (lines: 370)
rg (whitelist)* 0.097 +/- 0.003 (lines: 370)*
ucg (whitelist) 0.154 +/- 0.003 (lines: 370)
linux_literal_default (pattern: PM_RESUME)
------------------------------------------
rg* 0.089 +/- 0.002 (lines: 16)*
ag 0.469 +/- 0.038 (lines: 16)
ucg 0.154 +/- 0.001 (lines: 16)
pt 0.237 +/- 0.040 (lines: 16)
sift 0.126 +/- 0.003 (lines: 16)
git grep 0.175 +/- 0.013 (lines: 16)
linux_no_literal (pattern: \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5})
-----------------------------------------------------------------
rg (ignore) 0.329 +/- 0.006 (lines: 490)
rg (ignore) (ASCII) 0.172 +/- 0.002 (lines: 490)
ag (ignore) (ASCII) 0.725 +/- 0.067 (lines: 766)
pt (ignore) (ASCII) 12.478 +/- 0.097 (lines: 490)
sift (ignore) (ASCII) 9.002 +/- 0.096 (lines: 490)
git grep (ignore) 8.542 +/- 0.277 (lines: 490)
git grep (ignore) (ASCII) 1.883 +/- 0.087 (lines: 490)
rg (whitelist) 0.289 +/- 0.006 (lines: 458)
rg (whitelist) (ASCII)* 0.160 +/- 0.001 (lines: 458)*
ucg (whitelist) (ASCII) 0.474 +/- 0.020 (lines: 416)
linux_re_literal_suffix (pattern: [A-Z]+_RESUME)
------------------------------------------------
rg (ignore) 0.084 +/- 0.002 (lines: 1652)
ag (ignore) 0.483 +/- 0.006 (lines: 1652)
pt (ignore) 14.128 +/- 0.026 (lines: 1652)
sift (ignore) 4.099 +/- 0.103 (lines: 1652)
git grep (ignore) 0.529 +/- 0.014 (lines: 1652)
rg (whitelist)* 0.078 +/- 0.002 (lines: 1630)*
ucg (whitelist) 0.135 +/- 0.002 (lines: 1630)
linux_unicode_greek (pattern: \p{Greek})
----------------------------------------
rg* 0.172 +/- 0.002 (lines: 23)*
pt 14.122 +/- 0.031 (lines: 23)
sift 2.826 +/- 0.012 (lines: 23)
linux_unicode_greek_casei (pattern: \p{Greek})
----------------------------------------------
rg 0.170 +/- 0.001 (lines: 103)
pt 14.120 +/- 0.039 (lines: 23)
sift* 0.004 +/- 0.000 (lines: 0)*
linux_unicode_word (pattern: \wAh)
----------------------------------
rg (ignore) 0.098 +/- 0.002 (lines: 186)
rg (ignore) (ASCII) 0.096 +/- 0.002 (lines: 174)
ag (ignore) (ASCII) 0.627 +/- 0.038 (lines: 174)
pt (ignore) (ASCII) 14.182 +/- 0.024 (lines: 174)
sift (ignore) (ASCII) 4.135 +/- 0.119 (lines: 174)
git grep (ignore) 4.854 +/- 0.643 (lines: 186)
git grep (ignore) (ASCII) 1.376 +/- 0.035 (lines: 174)
rg (whitelist) 0.081 +/- 0.001 (lines: 180)*
rg (whitelist) (ASCII)* 0.082 +/- 0.002 (lines: 168)
ucg (ASCII) 0.155 +/- 0.003 (lines: 168)
linux_word (pattern: PM_RESUME)
-------------------------------
rg (ignore) 0.091 +/- 0.002 (lines: 6)
ag (ignore) 0.461 +/- 0.020 (lines: 6)
pt (ignore) 14.223 +/- 0.038 (lines: 6)
sift (ignore) 3.226 +/- 0.043 (lines: 6)
git grep (ignore) 0.173 +/- 0.006 (lines: 6)
rg (whitelist)* 0.076 +/- 0.001 (lines: 6)*
ucg (whitelist) 0.156 +/- 0.003 (lines: 6)
subtitles_en_alternate (pattern: Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty)
---------------------------------------------------------------------------------------------------------------
rg (lines) 0.311 +/- 0.026 (lines: 848)
ag (lines) 2.242 +/- 0.086 (lines: 848)
ucg (lines) 1.132 +/- 0.017 (lines: 848)
grep (lines) 1.828 +/- 0.017 (lines: 848)
rg* 0.226 +/- 0.031 (lines: 848)*
grep 1.528 +/- 0.057 (lines: 848)
subtitles_en_alternate_casei (pattern: Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty)
---------------------------------------------------------------------------------------------------------------------
ag (ASCII) 3.745 +/- 0.035 (lines: 862)
ucg (ASCII) 2.423 +/- 0.030 (lines: 862)
grep (ASCII) 2.969 +/- 0.040 (lines: 862)
rg* 1.952 +/- 0.049 (lines: 862)*
grep 2.928 +/- 0.012 (lines: 862)
subtitles_en_literal (pattern: Sherlock Holmes)
-----------------------------------------------
rg* 0.130 +/- 0.014 (lines: 629)*
rg (no mmap) 0.243 +/- 0.017 (lines: 629)
pt 1.421 +/- 0.005 (lines: 629)
sift 0.243 +/- 0.015 (lines: 629)
grep 0.486 +/- 0.027 (lines: 629)
rg (lines) 0.190 +/- 0.014 (lines: 629)
ag (lines) 1.573 +/- 0.034 (lines: 629)
ucg (lines) 0.386 +/- 0.014 (lines: 629)
pt (lines) 1.452 +/- 0.055 (lines: 629)
sift (lines) 0.601 +/- 0.015 (lines: 629)
grep (lines) 0.803 +/- 0.031 (lines: 629)
subtitles_en_literal_casei (pattern: Sherlock Holmes)
-----------------------------------------------------
rg* 0.284 +/- 0.028 (lines: 642)*
grep 1.912 +/- 0.004 (lines: 642)
grep (ASCII) 0.570 +/- 0.018 (lines: 642)
rg (lines) 0.362 +/- 0.028 (lines: 642)
ag (lines) (ASCII) 1.580 +/- 0.036 (lines: 642)
ucg (lines) (ASCII) 0.404 +/- 0.019 (lines: 642)
subtitles_en_literal_word (pattern: Sherlock Holmes)
----------------------------------------------------
rg (ASCII)* 0.185 +/- 0.015 (lines: 629)
ag (ASCII) 1.525 +/- 0.009 (lines: 629)
ucg (ASCII) 0.384 +/- 0.015 (lines: 629)
grep (ASCII) 0.788 +/- 0.029 (lines: 629)
rg 0.184 +/- 0.006 (lines: 629)*
grep 0.790 +/- 0.028 (lines: 629)
subtitles_en_no_literal (pattern: \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5})
----------------------------------------------------------------------------------------
rg 1.793 +/- 0.005 (lines: 13)
rg (ASCII)* 1.594 +/- 0.003 (lines: 13)*
ag (ASCII) 6.573 +/- 0.036 (lines: 48)
ucg (ASCII) 5.394 +/- 0.042 (lines: 13)
grep (ASCII) 3.446 +/- 0.050 (lines: 13)
subtitles_en_surrounding_words (pattern: \w+\s+Holmes\s+\w+)
------------------------------------------------------------
rg 0.187 +/- 0.003 (lines: 317)
grep 1.095 +/- 0.026 (lines: 317)
rg (ASCII)* 0.184 +/- 0.005 (lines: 317)*
ag (ASCII) 4.543 +/- 0.075 (lines: 323)
ucg (ASCII) 3.567 +/- 0.058 (lines: 317)
grep (ASCII) 1.070 +/- 0.012 (lines: 317)
subtitles_ru_alternate (pattern: Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти)
-----------------------------------------------------------------------------------------------------------
rg (lines) 1.007 +/- 0.041 (lines: 691)
ag (lines) 3.830 +/- 0.035 (lines: 691)
ucg (lines) 2.043 +/- 0.034 (lines: 691)
grep (lines) 7.513 +/- 0.020 (lines: 691)
rg* 0.938 +/- 0.046 (lines: 691)*
grep 7.085 +/- 0.030 (lines: 691)
subtitles_ru_alternate_casei (pattern: Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти)
-----------------------------------------------------------------------------------------------------------------
ag (ASCII) 3.799 +/- 0.015 (lines: 691)
ucg (ASCII)* 2.038 +/- 0.030 (lines: 691)*
grep (ASCII) 7.484 +/- 0.019 (lines: 691)
rg 11.087 +/- 0.057 (lines: 735)
grep 6.814 +/- 0.020 (lines: 735)
subtitles_ru_literal (pattern: Шерлок Холмс)
--------------------------------------------
rg* 0.195 +/- 0.010 (lines: 583)*
rg (no mmap) 0.315 +/- 0.005 (lines: 583)
pt 5.134 +/- 0.023 (lines: 583)
sift 5.835 +/- 0.061 (lines: 583)
grep 0.698 +/- 0.008 (lines: 583)
rg (lines) 0.267 +/- 0.002 (lines: 583)
ag (lines) 2.862 +/- 0.096 (lines: 583)
ucg (lines) 2.418 +/- 0.045 (lines: 583)
pt (lines) 5.150 +/- 0.036 (lines: 583)
sift (lines) 6.374 +/- 0.056 (lines: 583)
grep (lines) 1.089 +/- 0.028 (lines: 583)
subtitles_ru_literal_casei (pattern: Шерлок Холмс)
--------------------------------------------------
rg 0.970 +/- 0.041 (lines: 604)
grep 6.297 +/- 0.037 (lines: 604)
grep (ASCII) 0.725 +/- 0.030 (lines: 583)
rg (lines) 1.032 +/- 0.010 (lines: 604)
ag (lines) (ASCII)* 0.645 +/- 0.022 (lines: 0)*
ucg (lines) (ASCII) 0.774 +/- 0.036 (lines: 583)
subtitles_ru_literal_word (pattern: Шерлок Холмс)
-------------------------------------------------
rg (ASCII)* 0.188 +/- 0.007 (lines: 0)*
ag (ASCII) 0.668 +/- 0.028 (lines: 0)
ucg (ASCII) 2.404 +/- 0.052 (lines: 583)
grep (ASCII) 1.114 +/- 0.048 (lines: 583)
rg 0.275 +/- 0.011 (lines: 579)
grep 1.076 +/- 0.008 (lines: 579)
subtitles_ru_no_literal (pattern: \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5})
----------------------------------------------------------------------------------------
rg 3.167 +/- 0.014 (lines: 41)
rg (ASCII) 2.740 +/- 0.014 (lines: 0)
ag (ASCII) 1.963 +/- 0.069 (lines: 0)
ucg (ASCII) 2.055 +/- 0.037 (lines: 0)
grep (ASCII)* 1.634 +/- 0.009 (lines: 0)*
subtitles_ru_surrounding_words (pattern: \w+\s+Холмс\s+\w+)
-----------------------------------------------------------
rg* 0.302 +/- 0.020 (lines: 278)*
grep 1.432 +/- 0.055 (lines: 278)
ag (ASCII) 1.908 +/- 0.023 (lines: 0)
ucg (ASCII) 2.056 +/- 0.066 (lines: 0)
grep (ASCII) 1.398 +/- 0.044 (lines: 0)

172
build.rs
View File

@@ -1,26 +1,184 @@
#[macro_use]
extern crate clap;
#[macro_use]
extern crate lazy_static;
use std::env;
use std::fs;
use std::fs::{self, File};
use std::io::{self, Read, Write};
use std::path::Path;
use std::process;
use clap::Shell;
use app::{RGArg, RGArgKind};
#[allow(dead_code)]
#[path = "src/app.rs"]
mod app;
fn main() {
// OUT_DIR is set by Cargo and it's where any additional build artifacts
// are written.
let outdir = match env::var_os("OUT_DIR") {
None => return,
Some(outdir) => outdir,
None => {
eprintln!(
"OUT_DIR environment variable not defined. \
Please file a bug: \
https://github.com/BurntSushi/ripgrep/issues/new");
process::exit(1);
}
};
fs::create_dir_all(&outdir).unwrap();
let stamp_path = Path::new(&outdir).join("ripgrep-stamp");
if let Err(err) = File::create(&stamp_path) {
panic!("failed to write {}: {}", stamp_path.display(), err);
}
if let Err(err) = generate_man_page(&outdir) {
eprintln!("failed to generate man page: {}", err);
}
// Use clap to build completion files.
let mut app = app::app();
app.gen_completions("rg", Shell::Bash, &outdir);
app.gen_completions("rg", Shell::Fish, &outdir);
app.gen_completions("rg", Shell::PowerShell, &outdir);
// Note that we do not use clap's support for zsh. Instead, zsh completions
// are manually maintained in `complete/_rg`.
// Make the current git hash available to the build.
if let Some(rev) = git_revision_hash() {
println!("cargo:rustc-env=RIPGREP_BUILD_GIT_HASH={}", rev);
}
}
fn git_revision_hash() -> Option<String> {
let result = process::Command::new("git")
.args(&["rev-parse", "--short=10", "HEAD"])
.output();
result.ok().and_then(|output| {
let v = String::from_utf8_lossy(&output.stdout).trim().to_string();
if v.is_empty() {
None
} else {
Some(v)
}
})
}
fn generate_man_page<P: AsRef<Path>>(outdir: P) -> io::Result<()> {
// If asciidoc isn't installed, then don't do anything.
if let Err(err) = process::Command::new("a2x").output() {
eprintln!("Could not run 'a2x' binary, skipping man page generation.");
eprintln!("Error from running 'a2x': {}", err);
return Ok(());
}
// 1. Read asciidoc template.
// 2. Interpolate template with auto-generated docs.
// 3. Save interpolation to disk.
// 4. Use a2x (part of asciidoc) to convert to man page.
let outdir = outdir.as_ref();
let cwd = env::current_dir()?;
let tpl_path = cwd.join("doc").join("rg.1.txt.tpl");
let txt_path = outdir.join("rg.1.txt");
let mut tpl = String::new();
File::open(&tpl_path)?.read_to_string(&mut tpl)?;
tpl = tpl.replace("{OPTIONS}", &formatted_options()?);
let githash = git_revision_hash();
let githash = githash.as_ref().map(|x| &**x);
tpl = tpl.replace("{VERSION}", &app::long_version(githash));
File::create(&txt_path)?.write_all(tpl.as_bytes())?;
let result = process::Command::new("a2x")
.arg("--no-xmllint")
.arg("--doctype").arg("manpage")
.arg("--format").arg("manpage")
.arg(&txt_path)
.spawn()?
.wait()?;
if !result.success() {
let msg = format!("'a2x' failed with exit code {:?}", result.code());
return Err(ioerr(msg));
}
Ok(())
}
fn formatted_options() -> io::Result<String> {
let mut args = app::all_args_and_flags();
args.sort_by(|x1, x2| x1.name.cmp(&x2.name));
let mut formatted = vec![];
for arg in args {
if arg.hidden {
continue;
}
// ripgrep only has two positional arguments, and probably will only
// ever have two positional arguments, so we just hardcode them into
// the template.
if let app::RGArgKind::Positional{..} = arg.kind {
continue;
}
formatted.push(formatted_arg(&arg)?);
}
Ok(formatted.join("\n\n"))
}
fn formatted_arg(arg: &RGArg) -> io::Result<String> {
match arg.kind {
RGArgKind::Positional{..} => panic!("unexpected positional argument"),
RGArgKind::Switch { long, short, multiple } => {
let mut out = vec![];
let mut header = format!("--{}", long);
if let Some(short) = short {
header = format!("-{}, {}", short, header);
}
if multiple {
header = format!("*{}* ...::", header);
} else {
header = format!("*{}*::", header);
}
writeln!(out, "{}", header)?;
writeln!(out, "{}", formatted_doc_txt(arg)?)?;
Ok(String::from_utf8(out).unwrap())
}
RGArgKind::Flag { long, short, value_name, multiple, .. } => {
let mut out = vec![];
let mut header = format!("--{}", long);
if let Some(short) = short {
header = format!("-{}, {}", short, header);
}
if multiple {
header = format!("*{}* _{}_ ...::", header, value_name);
} else {
header = format!("*{}* _{}_::", header, value_name);
}
writeln!(out, "{}", header)?;
writeln!(out, "{}", formatted_doc_txt(arg)?)?;
Ok(String::from_utf8(out).unwrap())
}
}
}
fn formatted_doc_txt(arg: &RGArg) -> io::Result<String> {
let paragraphs: Vec<String> = arg.doc_long
.replace("{", "&#123;")
.replace("}", r"&#125;")
.split("\n\n")
.map(|s| s.to_string())
.collect();
if paragraphs.is_empty() {
return Err(ioerr(format!("missing docs for --{}", arg.name)));
}
let first = format!(" {}", paragraphs[0].replace("\n", "\n "));
if paragraphs.len() == 1 {
return Ok(first);
}
Ok(format!("{}\n+\n{}", first, paragraphs[1..].join("\n+\n")))
}
fn ioerr(msg: String) -> io::Error {
io::Error::new(io::ErrorKind::Other, msg)
}

58
ci/before_deploy.sh Normal file → Executable file
View File

@@ -1,32 +1,56 @@
# `before_deploy` phase: here we package the build artifacts
#!/bin/bash
# package the build artifacts
set -ex
. $(dirname $0)/utils.sh
. "$(dirname $0)/utils.sh"
# Generate artifacts for release
mk_artifacts() {
RUSTFLAGS="-C target-feature=+ssse3" \
cargo build --target $TARGET --release --features simd-accel
if is_arm; then
cargo build --target "$TARGET" --release
else
# Technically, MUSL builds will force PCRE2 to get statically compiled,
# but we also want PCRE2 statically build for macOS binaries.
PCRE2_SYS_STATIC=1 cargo build --target "$TARGET" --release --features 'pcre2'
fi
}
mk_tarball() {
# create a "staging" directory
local td=$(mktempd)
local out_dir=$(pwd)
# When cross-compiling, use the right `strip` tool on the binary.
local gcc_prefix="$(gcc_prefix)"
# Create a temporary dir that contains our staging area.
# $tmpdir/$name is what eventually ends up as the deployed archive.
local tmpdir="$(mktemp -d)"
local name="${PROJECT_NAME}-${TRAVIS_TAG}-${TARGET}"
mkdir "$td/$name"
mkdir "$td/$name/complete"
local staging="$tmpdir/$name"
mkdir -p "$staging"/{complete,doc}
# The deployment directory is where the final archive will reside.
# This path is known by the .travis.yml configuration.
local out_dir="$(pwd)/deployment"
mkdir -p "$out_dir"
# Find the correct (most recent) Cargo "out" directory. The out directory
# contains shell completion files and the man page.
local cargo_out_dir="$(cargo_out_dir "target/$TARGET")"
cp target/$TARGET/release/rg "$td/$name/"
cp {doc/rg.1,README.md,UNLICENSE,COPYING,LICENSE-MIT} "$td/$name/"
cp target/$TARGET/release/build/ripgrep-*/out/{rg.bash-completion,rg.fish,_rg.ps1} "$td/$name/complete/"
cp complete/_rg "$td/$name/complete/"
# Copy the ripgrep binary and strip it.
cp "target/$TARGET/release/rg" "$staging/rg"
"${gcc_prefix}strip" "$staging/rg"
# Copy the licenses and README.
cp {README.md,UNLICENSE,COPYING,LICENSE-MIT} "$staging/"
# Copy documentation and man page.
cp {CHANGELOG.md,FAQ.md,GUIDE.md} "$staging/doc/"
if command -V a2x 2>&1 > /dev/null; then
# The man page should only exist if we have asciidoc installed.
cp "$cargo_out_dir/rg.1" "$staging/doc/"
fi
# Copy shell completion files.
cp "$cargo_out_dir"/{rg.bash,rg.fish,_rg.ps1} "$staging/complete/"
cp complete/_rg "$staging/complete/"
pushd $td
tar czf "$out_dir/$name.tar.gz" *
popd
rm -r $td
(cd "$tmpdir" && tar czf "$out_dir/$name.tar.gz" "$name")
rm -rf "$tmpdir"
}
main() {

43
ci/build_deb.sh Executable file
View File

@@ -0,0 +1,43 @@
#!/bin/bash
set -e
# This script builds a binary dpkg for Debian based distros. It does not
# currently run in CI, and is instead run manually and the resulting dpkg is
# uploaded to GitHub via the web UI.
#
# Note that this requires 'cargo deb', which can be installed with
# 'cargo install cargo-deb'.
#
# This should be run from the root of the ripgrep repo.
if ! command -V cargo-deb > /dev/null 2>&1; then
echo "cargo-deb command missing" >&2
exit 1
fi
# 'cargo deb' does not seem to provide a way to specify an asset that is
# created at build time, such as ripgrep's man page. To work around this,
# we force a debug build, copy out the man page (and shell completions)
# produced from that build, put it into a predictable location and then build
# the deb, which knows where to look.
DEPLOY_DIR=deployment/deb
mkdir -p "$DEPLOY_DIR"
cargo build
# Find and copy man page.
manpage="$(find ./target/debug -name rg.1 -print0 | xargs -0 ls -t | head -n1)"
cp "$manpage" "$DEPLOY_DIR/"
# Do the same for shell completions.
compbash="$(find ./target/debug -name rg.bash -print0 | xargs -0 ls -t | head -n1)"
cp "$compbash" "$DEPLOY_DIR/"
compfish="$(find ./target/debug -name rg.fish -print0 | xargs -0 ls -t | head -n1)"
cp "$compfish" "$DEPLOY_DIR/"
compzsh="complete/_rg"
cp "$compzsh" "$DEPLOY_DIR/"
# Since we're distributing the dpkg, we don't know whether the user will have
# PCRE2 installed, so just do a static build.
PCRE2_SYS_STATIC=1 cargo deb

52
ci/install.sh Normal file → Executable file
View File

@@ -1,57 +1,61 @@
# `install` phase: install stuff needed for the `script` phase
#!/bin/bash
# install stuff needed for the `script` phase
# Where rustup gets installed.
export PATH="$PATH:$HOME/.cargo/bin"
set -ex
. $(dirname $0)/utils.sh
install_c_toolchain() {
case $TARGET in
aarch64-unknown-linux-gnu)
sudo apt-get install -y --no-install-recommends \
gcc-aarch64-linux-gnu libc6-arm64-cross libc6-dev-arm64-cross
;;
*)
# For other targets, this is handled by addons.apt.packages in .travis.yml
;;
esac
}
. "$(dirname $0)/utils.sh"
install_rustup() {
curl https://sh.rustup.rs -sSf | sh -s -- -y --default-toolchain=$TRAVIS_RUST_VERSION
curl https://sh.rustup.rs -sSf \
| sh -s -- -y --default-toolchain="$TRAVIS_RUST_VERSION"
rustc -V
cargo -V
}
install_standard_crates() {
install_targets() {
if [ $(host) != "$TARGET" ]; then
rustup target add $TARGET
fi
}
install_osx_dependencies() {
if ! is_osx; then
return
fi
brew install asciidoc docbook-xsl
}
configure_cargo() {
local prefix=$(gcc_prefix)
if [ -n "${prefix}" ]; then
local gcc_suffix=
if [ -n "$GCC_VERSION" ]; then
gcc_suffix="-$GCC_VERSION"
fi
local gcc="${prefix}gcc${gcc_suffix}"
if [ ! -z $prefix ]; then
# information about the cross compiler
${prefix}gcc -v
"${gcc}" -v
# tell cargo which linker to use for cross compilation
mkdir -p .cargo
cat >>.cargo/config <<EOF
[target.$TARGET]
linker = "${prefix}gcc"
linker = "${gcc}"
EOF
fi
}
main() {
install_c_toolchain
install_osx_dependencies
install_rustup
install_standard_crates
install_targets
configure_cargo
# TODO if you need to install extra stuff add it here
}
main

76
ci/script.sh Normal file → Executable file
View File

@@ -1,42 +1,50 @@
# `script` phase: you usually build, test and generate docs in this phase
#!/bin/bash
# build, test and generate docs in this phase
set -ex
. $(dirname $0)/utils.sh
# NOTE Workaround for rust-lang/rust#31907 - disable doc tests when cross compiling
# This has been fixed in the nightly channel but it would take a while to reach the other channels
disable_cross_doctests() {
if [ $(host) != "$TARGET" ] && [ "$TRAVIS_RUST_VERSION" = "stable" ]; then
if [ "$TRAVIS_OS_NAME" = "osx" ]; then
brew install gnu-sed --default-names
fi
find src -name '*.rs' -type f | xargs sed -i -e 's:\(//.\s*```\):\1 ignore,:g'
fi
}
run_test_suite() {
cargo clean --target $TARGET --verbose
cargo build --target $TARGET --verbose
cargo test --target $TARGET --verbose
cargo build --target $TARGET --verbose --manifest-path grep/Cargo.toml
cargo test --target $TARGET --verbose --manifest-path grep/Cargo.toml
cargo build --target $TARGET --verbose --manifest-path globset/Cargo.toml
cargo test --target $TARGET --verbose --manifest-path globset/Cargo.toml
cargo build --target $TARGET --verbose --manifest-path ignore/Cargo.toml
cargo test --target $TARGET --verbose --manifest-path ignore/Cargo.toml
cargo build --target $TARGET --verbose --manifest-path termcolor/Cargo.toml
cargo test --target $TARGET --verbose --manifest-path termcolor/Cargo.toml
"$( dirname "${0}" )/test_complete.sh"
# sanity check the file type
file target/$TARGET/debug/rg
}
. "$(dirname $0)/utils.sh"
main() {
# disable_cross_doctests
run_test_suite
# Test a normal debug build.
if is_arm; then
cargo build --target "$TARGET" --verbose
else
cargo build --target "$TARGET" --verbose --all --features 'pcre2'
fi
# Show the output of the most recent build.rs stderr.
set +x
stderr="$(find "target/$TARGET/debug" -name stderr -print0 | xargs -0 ls -t | head -n1)"
if [ -s "$stderr" ]; then
echo "===== $stderr ====="
cat "$stderr"
echo "====="
fi
set -x
# sanity check the file type
file target/"$TARGET"/debug/rg
# Check that we've generated man page and other shell completions.
outdir="$(cargo_out_dir "target/$TARGET/debug")"
file "$outdir/rg.bash"
file "$outdir/rg.fish"
file "$outdir/_rg.ps1"
file "$outdir/rg.1"
# Apparently tests don't work on arm, so just bail now. I guess we provide
# ARM releases on a best effort basis?
if is_arm; then
return 0
fi
# Test that zsh completions are in sync with ripgrep's actual args.
"$(dirname "${0}")/test_complete.sh"
# Run tests for ripgrep and all sub-crates.
cargo test --target "$TARGET" --verbose --all --features 'pcre2'
}
main

0
ci/sha256.sh Normal file → Executable file
View File

168
ci/test_complete.sh
View File

@@ -1,83 +1,97 @@
#!/bin/sh
#!/usr/bin/env zsh
emulate zsh -o extended_glob -o no_function_argzero -o no_unset
##
# Compares options in `rg --help` output to options in zsh completion function
set -e
get_comp_args() {
# Technically there are many options that the completion system sets that
# our function may rely on, but we'll trust that we've got it mostly right
setopt local_options unset
main() {
local rg="target/${TARGET}/release/rg"
local _rg='complete/_rg'
local ret='0'
local helpTemp="$( mktemp )"
local compTemp="$( mktemp )"
local diff
[ -e "${rg}" ] || rg="target/${TARGET}/debug/rg"
if [ ! -e "${rg}" ]; then
printf 'File not found: %s\n' "${rg}" >&2
ret='1'
elif [ ! -e "${_rg}" ]; then
printf 'File not found: %s\n' "${_rg}" >&2
ret='1'
else
# 'Parse' options out of the `--help` output. To prevent false positives
# we only look at lines where the first non-white-space character is `-`
"${rg}" --help |
"${rg}" -- '^\s*-' |
"${rg}" -io -- '[\t ,](-[a-z0-9]|--[a-z0-9-]+)\b' |
tr -d '\t ,' |
sort -u > "${helpTemp}"
# 'Parse' options out of the completion-function file. To prevent false
# negatives, we:
#
# * Exclude lines that look like comments
# * Exclude lines that don't appear to have a bracketed description
# suitable for `_arguments`
# * Exclude those bracketed descriptions so we don't match options
# which might be referenced in them
# * Exclude parenthetical lists of exclusive options so we don't match
# those
#
# This does of course make the following assumptions:
#
# * Each option definition is on its own (single) line
# * Each option definition has a description
# * Option names are static — i.e., they aren't constructed from
# variables or command substitutions. Brace expansion is OK as long as
# each component of the expression is a complete option flag — in
# other words, `{--foo,--bar}` is valid, but `--{foo,bar}` is not
"${rg}" -v -- '^\s*#' "${_rg}" |
"${rg}" --replace '$1' -- '^.*?(?:\(.+?\).*?)?(-.+)\[.+\].*' |
tr -d "\t (){}*=+:'\"" |
tr ',' '\n' |
sort -u > "${compTemp}"
diff="$(
if diff --help 2>&1 | grep -qF -- '--label'; then
diff -U2 \
--label '`rg --help`' \
--label "${_rg}" \
"${helpTemp}" "${compTemp}" || true
else
diff -U2 \
-L '`rg --help`' \
-L "${_rg}" \
"${helpTemp}" "${compTemp}" || true
fi
)"
[ -n "${diff}" ] && {
printf '%s\n' 'zsh completion options differ from `--help` options:' >&2
printf '%s\n' "${diff}" >&2
ret='1'
}
fi
rm -f "${helpTemp}" "${compTemp}"
return "${ret}"
# Our completion function recognises a special variable which tells it to
# dump the _arguments specs and then just return. But do this in a sub-shell
# anyway to avoid any weirdness
( _RG_COMPLETE_LIST_ARGS=1 source $1 )
}
main "${@}"
main() {
local diff
local rg="${0:a:h}/../target/${TARGET:-}/release/rg"
local _rg="${0:a:h}/../complete/_rg"
local -a help_args comp_args
[[ -e $rg ]] || rg=${rg/%\/release\/rg/\/debug\/rg}
rg=${rg:a}
_rg=${_rg:a}
[[ -e $rg ]] || {
print -r >&2 "File not found: $rg"
return 1
}
[[ -e $_rg ]] || {
print -r >&2 "File not found: $_rg"
return 1
}
print -rl - 'Comparing options:' "-$rg" "+$_rg"
# 'Parse' options out of the `--help` output. To prevent false positives we
# only look at lines where the first non-white-space character is `-`, or
# where a long option starting with certain letters (see `_rg`) is found.
# Occasionally we may have to handle some manually, however
help_args=( ${(f)"$(
$rg --help |
$rg -i -- '^\s+--?[a-z0-9]|--[imnp]' |
$rg -ior '$1' -- $'[\t /\"\'`.,](-[a-z0-9]|--[a-z0-9-]+)\\b' |
$rg -v -- --print0 | # False positives
sort -u
)"} )
# 'Parse' options out of the completion function
comp_args=( ${(f)"$( get_comp_args $_rg )"} )
# Note that we currently exclude hidden (!...) options; matching these
# properly against the `--help` output could be irritating
comp_args=( ${comp_args#\(*\)} ) # Strip excluded options
comp_args=( ${comp_args#\*} ) # Strip repetition indicator
comp_args=( ${comp_args%%-[:[]*} ) # Strip everything after -optname-
comp_args=( ${comp_args%%[:+=[]*} ) # Strip everything after other optspecs
comp_args=( ${comp_args##[^-]*} ) # Remove non-options
comp_args=( ${(f)"$( print -rl - $comp_args | sort -u )"} )
(( $#help_args )) || {
print -r >&2 'Failed to get help_args'
return 1
}
(( $#comp_args )) || {
print -r >&2 'Failed to get comp_args'
return 1
}
diff="$(
if diff --help 2>&1 | grep -qF -- '--label'; then
diff -U2 \
--label '`rg --help`' \
--label '`_rg`' \
=( print -rl - $help_args ) =( print -rl - $comp_args )
else
diff -U2 \
-L '`rg --help`' \
-L '`_rg`' \
=( print -rl - $help_args ) =( print -rl - $comp_args )
fi
)"
(( $#diff )) && {
printf >&2 '%s\n' 'zsh completion options differ from `--help` options:'
printf >&2 '%s\n' $diff
return 1
}
printf 'OK\n'
return 0
}
main "$@"

88
ci/utils.sh
View File

@@ -1,5 +1,19 @@
mktempd() {
echo $(mktemp -d 2>/dev/null || mktemp -d -t tmp)
#!/bin/bash
# Various utility functions used through CI.
# Finds Cargo's `OUT_DIR` directory from the most recent build.
#
# This requires one parameter corresponding to the target directory
# to search for the build output.
cargo_out_dir() {
# This works by finding the most recent stamp file, which is produced by
# every ripgrep build.
target_dir="$1"
find "$target_dir" -name ripgrep-stamp -print0 \
| xargs -0 ls -t \
| head -n1 \
| xargs dirname
}
host() {
@@ -13,37 +27,12 @@ host() {
esac
}
gcc_prefix() {
case "$TARGET" in
aarch64-unknown-linux-gnu)
echo aarch64-linux-gnu-
;;
arm*-gnueabihf)
echo arm-linux-gnueabihf-
;;
*)
return
;;
esac
}
dobin() {
[ -z $MAKE_DEB ] && die 'dobin: $MAKE_DEB not set'
[ $# -lt 1 ] && die "dobin: at least one argument needed"
local f prefix=$(gcc_prefix)
for f in "$@"; do
install -m0755 $f $dtd/debian/usr/bin/
${prefix}strip -s $dtd/debian/usr/bin/$(basename $f)
done
}
architecture() {
case $1 in
x86_64-unknown-linux-gnu|x86_64-unknown-linux-musl)
case "$TARGET" in
x86_64-*)
echo amd64
;;
i686-unknown-linux-gnu|i686-unknown-linux-musl)
i686-*|i586-*|i386-*)
echo i386
;;
arm*-unknown-linux-gnueabihf)
@@ -54,3 +43,42 @@ architecture() {
;;
esac
}
gcc_prefix() {
case "$(architecture)" in
armhf)
echo arm-linux-gnueabihf-
;;
*)
return
;;
esac
}
is_x86() {
case "$(architecture)" in
amd64|i386) return 0 ;;
*) return 1 ;;
esac
}
is_arm() {
case "$(architecture)" in
armhf) return 0 ;;
*) return 1 ;;
esac
}
is_linux() {
case "$TRAVIS_OS_NAME" in
linux) return 0 ;;
*) return 1 ;;
esac
}
is_osx() {
case "$TRAVIS_OS_NAME" in
osx) return 0 ;;
*) return 1 ;;
esac
}

8
compile
View File

@@ -1,8 +0,0 @@
#!/bin/sh
# export RUSTFLAGS="-C target-feature=+ssse3"
# cargo build --release --features 'simd-accel'
export RUSTFLAGS="-C target-cpu=native"
cargo build --release --features 'simd-accel avx-accel'
# cargo build --release --features 'simd-accel avx-accel' --target x86_64-unknown-linux-musl

708
complete/_rg
View File

@@ -1,4 +1,552 @@
#compdef rg
##
# zsh completion function for ripgrep
#
# Run ci/test_complete.sh after building to ensure that the options supported by
# this function stay in synch with the `rg` binary.
#
# For convenience, a completion reference guide is included at the bottom of
# this file.
#
# Originally based on code from the zsh-users project — see copyright notice
# below.
_rg() {
local curcontext=$curcontext no='!' descr ret=1
local -a context line state state_descr args tmp suf
local -A opt_args
# ripgrep has many options which negate the effect of a more common one — for
# example, `--no-column` to negate `--column`, and `--messages` to negate
# `--no-messages`. There are so many of these, and they're so infrequently
# used, that some users will probably find it irritating if they're completed
# indiscriminately, so let's not do that unless either the current prefix
# matches one of those negation options or the user has the `complete-all`
# style set. Note that this prefix check has to be updated manually to account
# for all of the potential negation options listed below!
if
# We also want to list all of these options during testing
[[ $_RG_COMPLETE_LIST_ARGS == (1|t*|y*) ]] ||
# (--[imnp]* => --ignore*, --messages, --no-*, --pcre2-unicode)
[[ $PREFIX$SUFFIX == --[imnp]* ]] ||
zstyle -t ":complete:$curcontext:*" complete-all
then
no=
fi
# We make heavy use of argument groups here to prevent the option specs from
# growing unwieldy. These aren't supported in zsh <5.4, though, so we'll strip
# them out below if necessary. This makes the exclusions inaccurate on those
# older versions, but oh well — it's not that big a deal
args=(
+ '(exclusive)' # Misc. fully exclusive options
'(: * -)'{-h,--help}'[display help information]'
'(: * -)'{-V,--version}'[display version information]'
+ '(buffered)' # buffering options
'--line-buffered[force line buffering]'
$no"--no-line-buffered[don't force line buffering]"
'--block-buffered[force block buffering]'
$no"--no-block-buffered[don't force block buffering]"
+ '(case)' # Case-sensitivity options
{-i,--ignore-case}'[search case-insensitively]'
{-s,--case-sensitive}'[search case-sensitively]'
{-S,--smart-case}'[search case-insensitively if pattern is all lowercase]'
+ '(context-a)' # Context (after) options
'(context-c)'{-A+,--after-context=}'[specify lines to show after each match]:number of lines'
+ '(context-b)' # Context (before) options
'(context-c)'{-B+,--before-context=}'[specify lines to show before each match]:number of lines'
+ '(context-c)' # Context (combined) options
'(context-a context-b)'{-C+,--context=}'[specify lines to show before and after each match]:number of lines'
+ '(column)' # Column options
'--column[show column numbers for matches]'
$no"--no-column[don't show column numbers for matches]"
+ '(count)' # Counting options
{-c,--count}'[only show count of matching lines for each file]'
'--count-matches[only show count of individual matches for each file]'
+ '(encoding)' # Encoding options
{-E+,--encoding=}'[specify text encoding of files to search]: :_rg_encodings'
$no'--no-encoding[use default text encoding]'
+ file # File-input options
'(1)*'{-f+,--file=}'[specify file containing patterns to search for]: :_files'
+ '(file-match)' # Files with/without match options
'(stats)'{-l,--files-with-matches}'[only show names of files with matches]'
'(stats)--files-without-match[only show names of files without matches]'
+ '(file-name)' # File-name options
{-H,--with-filename}'[show file name for matches]'
"--no-filename[don't show file name for matches]"
+ '(file-system)' # File system options
"--one-file-system[don't descend into directories on other file systems]"
$no'--no-one-file-system[descend into directories on other file systems]'
+ '(fixed)' # Fixed-string options
{-F,--fixed-strings}'[treat pattern as literal string instead of regular expression]'
$no"--no-fixed-strings[don't treat pattern as literal string]"
+ '(follow)' # Symlink-following options
{-L,--follow}'[follow symlinks]'
$no"--no-follow[don't follow symlinks]"
+ glob # File-glob options
'*'{-g+,--glob=}'[include/exclude files matching specified glob]:glob'
'*--iglob=[include/exclude files matching specified case-insensitive glob]:glob'
+ '(heading)' # Heading options
'(pretty-vimgrep)--heading[show matches grouped by file name]'
"(pretty-vimgrep)--no-heading[don't show matches grouped by file name]"
+ '(hidden)' # Hidden-file options
'--hidden[search hidden files and directories]'
$no"--no-hidden[don't search hidden files and directories]"
+ '(ignore)' # Ignore-file options
"(--no-ignore-global --no-ignore-parent --no-ignore-vcs --no-ignore-dot)--no-ignore[don't respect ignore files]"
$no'(--ignore-global --ignore-parent --ignore-vcs --ignore-dot)--ignore[respect ignore files]'
+ '(ignore-file-case-insensitive)' # Ignore-file case sensitivity options
'--ignore-file-case-insensitive[process ignore files case insensitively]'
$no'--no-ignore-file-case-insensitive[process ignore files case sensitively]'
+ '(ignore-global)' # Global ignore-file options
"--no-ignore-global[don't respect global ignore files]"
$no'--ignore-global[respect global ignore files]'
+ '(ignore-parent)' # Parent ignore-file options
"--no-ignore-parent[don't respect ignore files in parent directories]"
$no'--ignore-parent[respect ignore files in parent directories]'
+ '(ignore-vcs)' # VCS ignore-file options
"--no-ignore-vcs[don't respect version control ignore files]"
$no'--ignore-vcs[respect version control ignore files]'
+ '(ignore-dot)' # .ignore-file options
"--no-ignore-dot[don't respect .ignore files]"
$no'--ignore-dot[respect .ignore files]'
+ '(json)' # JSON options
'--json[output results in JSON Lines format]'
$no"--no-json[don't output results in JSON Lines format]"
+ '(line-number)' # Line-number options
{-n,--line-number}'[show line numbers for matches]'
{-N,--no-line-number}"[don't show line numbers for matches]"
+ '(line-terminator)' # Line-terminator options
'--crlf[use CRLF as line terminator]'
$no"--no-crlf[don't use CRLF as line terminator]"
'(text)--null-data[use NUL as line terminator]'
+ '(max-depth)' # Directory-depth options
'--max-depth=[specify max number of directories to descend]:number of directories'
'!--maxdepth=:number of directories'
+ '(messages)' # Error-message options
'(--no-ignore-messages)--no-messages[suppress some error messages]'
$no"--messages[don't suppress error messages affected by --no-messages]"
+ '(messages-ignore)' # Ignore-error message options
"--no-ignore-messages[don't show ignore-file parse error messages]"
$no'--ignore-messages[show ignore-file parse error messages]'
+ '(mmap)' # mmap options
'--mmap[search using memory maps when possible]'
"--no-mmap[don't search using memory maps]"
+ '(multiline)' # Multiline options
{-U,--multiline}'[permit matching across multiple lines]'
$no'(multiline-dotall)--no-multiline[restrict matches to at most one line each]'
+ '(multiline-dotall)' # Multiline DOTALL options
'(--no-multiline)--multiline-dotall[allow "." to match newline (with -U)]'
$no"(--no-multiline)--no-multiline-dotall[don't allow \".\" to match newline (with -U)]"
+ '(only)' # Only-match options
{-o,--only-matching}'[show only matching part of each line]'
+ '(passthru)' # Pass-through options
'(--vimgrep)--passthru[show both matching and non-matching lines]'
'!(--vimgrep)--passthrough'
+ '(pcre2)' # PCRE2 options
{-P,--pcre2}'[enable matching with PCRE2]'
$no'(pcre2-unicode)--no-pcre2[disable matching with PCRE2]'
+ '(pcre2-unicode)' # PCRE2 Unicode options
$no'(--no-pcre2 --no-pcre2-unicode)--pcre2-unicode[enable PCRE2 Unicode mode (with -P)]'
'(--no-pcre2 --pcre2-unicode)--no-pcre2-unicode[disable PCRE2 Unicode mode (with -P)]'
+ '(pre)' # Preprocessing options
'(-z --search-zip)--pre=[specify preprocessor utility]:preprocessor utility:_command_names -e'
$no'--no-pre[disable preprocessor utility]'
+ pre-glob # Preprocessing glob options
'*--pre-glob[include/exclude files for preprocessing with --pre]'
+ '(pretty-vimgrep)' # Pretty/vimgrep display options
'(heading)'{-p,--pretty}'[alias for --color=always --heading -n]'
'(heading passthru)--vimgrep[show results in vim-compatible format]'
+ regexp # Explicit pattern options
'(1 file)*'{-e+,--regexp=}'[specify pattern]:pattern'
+ '(replace)' # Replacement options
{-r+,--replace=}'[specify string used to replace matches]:replace string'
+ '(sort)' # File-sorting options
'(threads)--sort=[sort results in ascending order (disables parallelism)]:sort method:((
none\:"no sorting"
path\:"sort by file path"
modified\:"sort by last modified time"
accessed\:"sort by last accessed time"
created\:"sort by creation time"
))'
'(threads)--sortr=[sort results in descending order (disables parallelism)]:sort method:((
none\:"no sorting"
path\:"sort by file path"
modified\:"sort by last modified time"
accessed\:"sort by last accessed time"
created\:"sort by creation time"
))'
'!(threads)--sort-files[sort results by file path (disables parallelism)]'
+ '(stats)' # Statistics options
'(--files file-match)--stats[show search statistics]'
$no"--no-stats[don't show search statistics]"
+ '(text)' # Binary-search options
{-a,--text}'[search binary files as if they were text]'
$no"(--null-data)--no-text[don't search binary files as if they were text]"
+ '(threads)' # Thread-count options
'(sort)'{-j+,--threads=}'[specify approximate number of threads to use]:number of threads'
+ '(trim)' # Trim options
'--trim[trim any ASCII whitespace prefix from each line]'
$no"--no-trim[don't trim ASCII whitespace prefix from each line]"
+ type # Type options
'*'{-t+,--type=}'[only search files matching specified type]: :_rg_types'
'*--type-add=[add new glob for specified file type]: :->typespec'
'*--type-clear=[clear globs previously defined for specified file type]: :_rg_types'
# This should actually be exclusive with everything but other type options
'(: *)--type-list[show all supported file types and their associated globs]'
'*'{-T+,--type-not=}"[don't search files matching specified file type]: :_rg_types"
+ '(word-line)' # Whole-word/line match options
{-w,--word-regexp}'[only show matches surrounded by word boundaries]'
{-x,--line-regexp}'[only show matches surrounded by line boundaries]'
+ '(zip)' # Compression options
'(--pre)'{-z,--search-zip}'[search in compressed files]'
$no"--no-search-zip[don't search in compressed files]"
+ misc # Other options — no need to separate these at the moment
'(-b --byte-offset)'{-b,--byte-offset}'[show 0-based byte offset for each matching line]'
'--color=[specify when to use colors in output]:when:((
never\:"never use colors"
auto\:"use colors or not based on stdout, TERM, etc."
always\:"always use colors"
ansi\:"always use ANSI colors (even on Windows)"
))'
'*--colors=[specify color and style settings]: :->colorspec'
'--context-separator=[specify string used to separate non-continuous context lines in output]:separator'
'--debug[show debug messages]'
'--dfa-size-limit=[specify upper size limit of generated DFA]:DFA size (bytes)'
"(1 stats)--files[show each file that would be searched (but don't search)]"
'*--ignore-file=[specify additional ignore file]:ignore file:_files'
'(-v --invert-match)'{-v,--invert-match}'[invert matching]'
'(-M --max-columns)'{-M+,--max-columns=}'[specify max length of lines to print]:number of bytes'
'(-m --max-count)'{-m+,--max-count=}'[specify max number of matches per file]:number of matches'
'--max-filesize=[specify size above which files should be ignored]:file size (bytes)'
"--no-config[don't load configuration files]"
'(-0 --null)'{-0,--null}'[print NUL byte after file names]'
'--path-separator=[specify path separator to use when printing file names]:separator'
'(-q --quiet)'{-q,--quiet}'[suppress normal output]'
'--regex-size-limit=[specify upper size limit of compiled regex]:regex size (bytes)'
'*'{-u,--unrestricted}'[reduce level of "smart" searching]'
+ operand # Operands
'(--files --type-list file regexp)1: :_guard "^-*" pattern'
'(--type-list)*: :_files'
)
# This is used with test_complete.sh to verify that there are no options
# listed in the help output that aren't also defined here
[[ $_RG_COMPLETE_LIST_ARGS == (1|t*|y*) ]] && {
print -rl - $args
return 0
}
# Strip out argument groups where unsupported (see above)
[[ $ZSH_VERSION == (4|5.<0-3>)(.*)# ]] &&
args=( ${(@)args:#(#i)(+|[a-z0-9][a-z0-9_-]#|\([a-z0-9][a-z0-9_-]#\))} )
_arguments -C -s -S : $args && ret=0
case $state in
colorspec)
if [[ ${IPREFIX#--*=}$PREFIX == [^:]# ]]; then
suf=( -qS: )
tmp=(
'column:specify coloring for column numbers'
'line:specify coloring for line numbers'
'match:specify coloring for match text'
'path:specify coloring for file names'
)
descr='color/style type'
elif [[ ${IPREFIX#--*=}$PREFIX == (column|line|match|path):[^:]# ]]; then
suf=( -qS: )
tmp=(
'none:clear color/style for type'
'bg:specify background color'
'fg:specify foreground color'
'style:specify text style'
)
descr='color/style attribute'
elif [[ ${IPREFIX#--*=}$PREFIX == [^:]##:(bg|fg):[^:]# ]]; then
tmp=( black blue green red cyan magenta yellow white )
descr='color name or r,g,b'
elif [[ ${IPREFIX#--*=}$PREFIX == [^:]##:style:[^:]# ]]; then
tmp=( {,no}bold {,no}intense {,no}underline )
descr='style name'
else
_message -e colorspec 'no more arguments'
fi
(( $#tmp )) && {
compset -P '*:'
_describe -t colorspec $descr tmp $suf && ret=0
}
;;
typespec)
if compset -P '[^:]##:include:'; then
_sequence -s , _rg_types && ret=0
# @todo This bit in particular could be better, but it's a little
# complex, and attempting to solve it seems to run us up against a crash
# bug — zsh # 40362
elif compset -P '[^:]##:'; then
_message 'glob or include directive' && ret=1
elif [[ ! -prefix *:* ]]; then
_rg_types -qS : && ret=0
fi
;;
esac
return ret
}
# Complete encodings
_rg_encodings() {
local -a expl
local -aU _encodings
# This is impossible to read, but these encodings rarely if ever change, so it
# probably doesn't matter. They are derived from the list given here:
# https://encoding.spec.whatwg.org/#concept-encoding-get
_encodings=(
{{,us-}ascii,arabic,chinese,cyrillic,greek{,8},hebrew,korean}
logical visual mac {,cs}macintosh x-mac-{cyrillic,roman,ukrainian}
866 ibm{819,866} csibm866
big5{,-hkscs} {cn-,cs}big5 x-x-big5
cp{819,866,125{0..8}} x-cp125{0..8}
csiso2022{jp,kr} csiso8859{6,8}{e,i}
csisolatin{{1..6},9} csisolatin{arabic,cyrillic,greek,hebrew}
ecma-{114,118} asmo-708 elot_928 sun_eu_greek
euc-{jp,kr} x-euc-jp cseuckr cseucpkdfmtjapanese
{,x-}gbk csiso58gb231280 gb18030 {,cs}gb2312 gb_2312{,-80} hz-gb-2312
iso-2022-{cn,cn-ext,jp,kr}
iso8859{,-}{{1..11},13,14,15}
iso-8859-{{1..11},{6,8}-{e,i},13,14,15,16} iso_8859-{{1..9},15}
iso_8859-{1,2,6,7}:1987 iso_8859-{3,4,5,8}:1988 iso_8859-9:1989
iso-ir-{58,100,101,109,110,126,127,138,144,148,149,157}
koi{,8,8-r,8-ru,8-u,8_r} cskoi8r
ks_c_5601-{1987,1989} ksc{,_}5691 csksc56011987
latin{1..6} l{{1..6},9}
shift{-,_}jis csshiftjis {,x-}sjis ms_kanji ms932
utf{,-}8 utf-16{,be,le} unicode-1-1-utf-8
windows-{31j,874,949,125{0..8}} dos-874 tis-620 ansi_x3.4-1968
x-user-defined auto none
)
_wanted encodings expl encoding compadd -a "$@" - _encodings
}
# Complete file types
_rg_types() {
local -a expl
local -aU _types
_types=( ${(@)${(f)"$( _call_program types rg --type-list )"}%%:*} )
_wanted types expl 'file type' compadd -a "$@" - _types
}
_rg "$@"
################################################################################
# ZSH COMPLETION REFERENCE
#
# For the convenience of developers who aren't especially familiar with zsh
# completion functions, a brief reference guide follows. This is in no way
# comprehensive; it covers just enough of the basic structure, syntax, and
# conventions to help someone make simple changes like adding new options. For
# more complete documentation regarding zsh completion functions, please see the
# following:
#
# * http://zsh.sourceforge.net/Doc/Release/Completion-System.html
# * https://github.com/zsh-users/zsh/blob/master/Etc/completion-style-guide
#
# OVERVIEW
#
# Most zsh completion functions are defined in terms of `_arguments`, which is a
# shell function that takes a series of argument specifications. The specs for
# `rg` are stored in an array, which is common for more complex functions; the
# elements of the array are passed to `_arguments` on invocation.
#
# ARGUMENT-SPECIFICATION SYNTAX
#
# The following is a contrived example of the argument specs for a simple tool:
#
# '(: * -)'{-h,--help}'[display help information]'
# '(-q -v --quiet --verbose)'{-q,--quiet}'[decrease output verbosity]'
# '!(-q -v --quiet --verbose)--silent'
# '(-q -v --quiet --verbose)'{-v,--verbose}'[increase output verbosity]'
# '--color=[specify when to use colors]:when:(always never auto)'
# '*:example file:_files'
#
# Although there may appear to be six specs here, there are actually nine; we
# use brace expansion to combine specs for options that go by multiple names,
# like `-q` and `--quiet`. This is customary, and ties in with the fact that zsh
# merges completion possibilities together when they have the same description.
#
# The first line defines the option `-h`/`--help`. With most tools, it isn't
# useful to complete anything after `--help` because it effectively overrides
# all others; the `(: * -)` at the beginning of the spec tells zsh not to
# complete any other operands (`:` and `*`) or options (`-`) after this one has
# been used. The `[...]` at the end associates a description with `-h`/`--help`;
# as mentioned, zsh will see the identical descriptions and merge these options
# together when offering completion possibilities.
#
# The next line defines `-q`/`--quiet`. Here we don't want to suppress further
# completions entirely, but we don't want to offer `-q` if `--quiet` has been
# given (since they do the same thing), nor do we want to offer `-v` (since it
# doesn't make sense to be quiet and verbose at the same time). We don't need to
# tell zsh not to offer `--quiet` a second time, since that's the default
# behaviour, but since this line expands to two specs describing `-q` *and*
# `--quiet` we do need to explicitly list all of them here.
#
# The next line defines a hidden option `--silent` — maybe it's a deprecated
# synonym for `--quiet`. The leading `!` indicates that zsh shouldn't offer this
# option during completion. The benefit of providing a spec for an option that
# shouldn't be completed is that, if someone *does* use it, we can correctly
# suppress completion of other options afterwards.
#
# The next line defines `-v`/`--verbose`; this works just like `-q`/`--quiet`.
#
# The next line defines `--color`. In this example, `--color` doesn't have a
# corresponding short option, so we don't need to use brace expansion. Further,
# there are no other options it's exclusive with (just itself), so we don't need
# to define those at the beginning. However, it does take a mandatory argument.
# The `=` at the end of `--color=` indicates that the argument may appear either
# like `--color always` or like `--color=always`; this is how most GNU-style
# command-line tools work. The corresponding short option would normally use `+`
# — for example, `-c+` would allow either `-c always` or `-calways`. For this
# option, the arguments are known ahead of time, so we can simply list them in
# parentheses at the end (`when` is used as the description for the argument).
#
# The last line defines an operand (a non-option argument). In this example, the
# operand can be used any number of times (the leading `*`), and it should be a
# file path, so we tell zsh to call the `_files` function to complete it. The
# `example file` in the middle is the description to use for this operand; we
# could use a space instead to accept the default provided by `_files`.
#
# GROUPING ARGUMENT SPECIFICATIONS
#
# Newer versions of zsh support grouping argument specs together. All specs
# following a `+` and then a group name are considered to be members of the
# named group. Grouping is useful mostly for organisational purposes; it makes
# the relationship between different options more obvious, and makes it easier
# to specify exclusions.
#
# We could rewrite our example above using grouping as follows:
#
# '(: * -)'{-h,--help}'[display help information]'
# '--color=[specify when to use colors]:when:(always never auto)'
# '*:example file:_files'
# + '(verbosity)'
# {-q,--quiet}'[decrease output verbosity]'
# '!--silent'
# {-v,--verbose}'[increase output verbosity]'
#
# Here we take advantage of a useful feature of spec grouping — when the group
# name is surrounded by parentheses, as in `(verbosity)`, it tells zsh that all
# of the options in that group are exclusive with each other. As a result, we
# don't need to manually list out the exclusions at the beginning of each
# option.
#
# Groups can also be referred to by name in other argument specs; for example:
#
# '(xyz)--aaa' '*: :_files'
# + xyz --xxx --yyy --zzz
#
# Here we use the group name `xyz` to tell zsh that `--xxx`, `--yyy`, and
# `--zzz` are not to be completed after `--aaa`. This makes the exclusion list
# much more compact and reusable.
#
# CONVENTIONS
#
# zsh completion functions generally adhere to the following conventions:
#
# * Use two spaces for indentation
# * Combine specs for options with different names using brace expansion
# * In combined specs, list the short option first (as in `{-a,--text}`)
# * Use `+` or `=` as described above for options that take arguments
# * Provide a description for all options, option-arguments, and operands
# * Capitalise/punctuate argument descriptions as phrases, not complete
# sentences — 'display help information', never 'Display help information.'
# (but still capitalise acronyms and proper names)
# * Write argument descriptions as verb phrases — 'display x', 'enable y',
# 'use z'
# * Word descriptions to make it clear when an option expects an argument;
# usually this is done with the word 'specify', as in 'specify x' or
# 'use specified x')
# * Write argument descriptions as tersely as possible — for example, articles
# like 'a' and 'the' should be omitted unless it would be confusing
#
# Other conventions currently used by this function:
#
# * Order argument specs alphabetically by group name, then option name
# * Group options that are directly related, mutually exclusive, or frequently
# referenced by other argument specs
# * Use only characters in the set [a-z0-9_-] in group names
# * Order exclusion lists as follows: short options, long options, groups
# * Use American English in descriptions
# * Use 'don't' in descriptions instead of 'do not'
# * Word descriptions for related options as similarly as possible. For example,
# `--foo[enable foo]` and `--no-foo[disable foo]`, or `--foo[use foo]` and
# `--no-foo[don't use foo]`
# * Word descriptions to make it clear when an option only makes sense with
# another option, usually by adding '(with -x)' to the end
# * Don't quote strings or variables unnecessarily. When quotes are required,
# prefer single-quotes to double-quotes
# * Prefix option specs with `$no` when the option serves only to negate the
# behaviour of another option that must be provided explicitly by the user.
# This prevents rarely used options from cluttering up the completion menu
################################################################################
# ------------------------------------------------------------------------------
# Copyright (c) 2011 Github zsh-users - http://github.com/zsh-users
# All rights reserved.
@@ -39,166 +587,6 @@
#
# ------------------------------------------------------------------------------
local context state state_descr line
local -A opt_args
local -i ret=1
local -a common_options
common_options=(
'(-a --text)'{-a,--text}'[search binary files as if they were text]'
'(-c, --count)'{-c,--count}'[only show count of matches for each file]'
'--color=[specify when to use colors in output]:when:( never auto always ansi )'
'(1)*'{-e,--regexp=}'[specify pattern]:pattern'
'(-E --encoding)'{-E,--encoding=}'[specify text encoding of files to search]: :->encoding'
'(-F --fixed-strings)'{-F,--fixed-strings}'[treat pattern as literal string instead of regular expression]'
'*'{-g,--glob=}'[include or exclude files for searching that match the specified glob]:glob'
'(-h --help)'{-h,--help}'[display help information]'
'(-i -s -S --ignore-case --case-sensitive --smart-case)'{-i,--ignore-case}'[search case-insensitively]'
'(-n -N --line-number --no-line-number)'{-n,--line-number}'[show line numbers]'
'(-n -N --line-number --no-line-number)'{-N,--no-line-number}'[suppress line numbers]'
'(-o --only-matching)'{-o,--only-matching}'[show only matching part of each line]'
'(-q --quiet)'{-q,--quiet}'[suppress normal output]'
'(-T --type-not)*'{-t,--type=}'[only search files matching specified type]: :->type'
'(-t --type)*'{-T,--type-not=}"[don't search files matching specified type]: :->type"
'*'{-u,--unrestricted}'[reduce level of "smart" searching]'
'(-v --invert-match)'{-v,--invert-match}'[invert matching]'
'(-w --word-regexp)'{-w,--word-regexp}'[only show matches surrounded by word boundaries]'
)
local -a less_common_options
less_common_options=(
'(-A -C --after-context --context)'{-A,--after-context=}'[specify lines to show after each match]:number of lines'
'(-B -C --before-context --context)'{-B,--before-context=}'[specify lines to show before each match]:number of lines'
'(-A -B -C --after-context --before-context --context)'{-C,--context=}'[specify lines to show before and after each match]:number of lines'
'*--colors=[specify color settings and styles]: :->colorspec'
'--column[show column numbers]'
'--context-separator=[specify string used to separate non-continuous context lines in output]:separator string'
'--debug[show debug messages]'
'--dfa-size-limit=[specify upper size limit of generated DFA]:DFA size'
'*'{-f,--file=}'[specify file containing patterns to search for]:file:_files'
"--ignore-file=[specify additional ignore file]:file:_files"
"--files[show each file that would be searched (but don't search)]"
'(-l --files-with-matches --files-without-match)'{-l,--files-with-matches}'[only show names of files with matches]'
'(-l --files-with-matches --files-without-match)--files-without-match[only show names of files without matches]'
'(-H --with-filename --no-filename)'{-H,--with-filename}'[prefix each match with name of file that contains it]'
'(-H --with-filename --no-filename)--no-filename[suppress all file names]'
'(-p --no-heading --pretty --vimgrep)--heading[show matches grouped by file name]'
"(-p --heading --pretty --vimgrep)--no-heading[don't group matches by file name]"
'--hidden[search hidden files and directories]'
'*--iglob=[include or exclude files for searching that match the specified case-insensitive glob]:glob'
'(-L --follow)'{-L,--follow}'[follow symlinks]'
'(-M --max-columns)'{-M,--max-columns=}'[specify max length of lines to print]:number of bytes'
'(-m --max-count)'{-m,--max-count=}'[specify max number of matches per file]:number of matches'
'--max-filesize=[specify size above which files should be ignored]:size'
'--maxdepth[specify max number of directories to descend]:number of directories'
'(--no-mmap)--mmap[search using memory maps when possible]'
'--no-messages[suppress all error messages]'
"(--mmap)--no-mmap[don't search using memory maps]"
"(--no-ignore-parent)--no-ignore[don't respect ignore files]"
"--no-ignore-parent[don't respect ignore files in parent directories]"
"--no-ignore-vcs[don't respect version control ignore files]"
'(-0 --null)'{-0,--null}'[print NUL byte after file names]'
'--path-separator=[specify path separator to use when printing file names]'
'(-p --heading --no-heading --pretty --vimgrep)'{-p,--pretty}'[alias for --color=always --heading -n]'
'--regex-size-limit=[specify upper size limit of compiled regex]:regex size'
'(-r --replace)'{-r,--replace=}'[specify string used to replace matches]:replace string'
'(-i -s -S --ignore-case --case-sensitive --smart-case)'{-s,--case-sensitive}'[search case-sensitively]'
'(-i -s -S --ignore-case --case-sensitive --smart-case)'{-S,--smart-case}'[search case-insensitively if the pattern is all lowercase]'
'--sort-files[sort results by file path (disables parallelism)]'
'(-j --threads)'{-j,--threads=}'[specify approximate number of threads to use]:number of threads'
'(-v --version)'{-V,--version}'[display version information]'
'(-p --heading --no-heading --pretty)--vimgrep[show results in vim-compatible format]'
)
local -a file_type_management_options
file_type_management_options=(
'--type-list[show all supported file types and their associated globs]'
'*--type-add=[add new glob for file type]: :->typespec'
'*--type-clear=[clear globs previously defined for specified file type]: :->type'
)
_arguments -S -s : \
$common_options \
$less_common_options \
$file_type_management_options \
'(-e --regexp)1: :_guard "^--*" pattern' \
'*:file:_files' \
&& ret=0
case "$state" in
colorspec)
_values -S ':' 'color/style type' \
'column[specify coloring for column numbers]: :->attribute' \
'line[specify coloring for line numbers]: :->attribute' \
'match[specify coloring for match text]: :->attribute' \
'path[specify color for file names]: :->attribute' && ret=0
[[ "$state" == 'attribute' ]] &&
_values -S ':' 'color/style attribute' \
'none[clear color/style for type]' \
'bg[specify background color]: :->color' \
'fg[specify foreground color]: :->color' \
'style[specify text style]: :->style' && ret=0
[[ "$state" == 'color' ]] &&
_values -S ':' 'color value' \
black blue green red cyan magenta yellow white && ret=0
[[ "$state" == 'style' ]] &&
_values -S ':' 'style value' \
bold nobold intense nointense && ret=0
;;
encoding)
# This is impossible to read, but these encodings rarely if ever change, so
# it probably doesn't matter. They are derived from the list given here:
# https://encoding.spec.whatwg.org/#concept-encoding-get
local -U encodings
encodings=(
{{,us-}ascii,arabic,chinese,cyrillic,greek{,8},hebrew,korean}
logical visual mac {,cs}macintosh x-mac-{cyrillic,roman,ukrainian}
866 ibm{819,866} csibm866
big5{,-hkscs} {cn-,cs}big5 x-x-big5
cp{819,866,125{0..8}} x-cp125{0..8}
csiso2022{jp,kr} csiso8859{6,8}{e,i}
csisolatin{{1..6},9} csisolatin{arabic,cyrillic,greek,hebrew}
ecma-{114,118} asmo-708 elot_928 sun_eu_greek
euc-{jp,kr} x-euc-jp cseuckr cseucpkdfmtjapanese
{,x-}gbk csiso58gb231280 gb18030 {,cs}gb2312 gb_2312{,-80} hz-gb-2312
iso-2022-{cn,cn-ext,jp,kr}
iso8859{,-}{{1..11},13,14,15}
iso-8859-{{1..11},{6,8}-{e,i},13,14,15,16} iso_8859-{{1..9},15}
iso_8859-{1,2,6,7}\\:1987 iso_8859-{3,4,5,8}\\:1988 iso_8859-9\\:1989
iso-ir-{58,100,101,109,110,126,127,138,144,148,149,157}
koi{,8,8-r,8-ru,8-u,8_r} cskoi8r
ks_c_5601-{1987,1989} ksc{,_}5691 csksc56011987
latin{1..6} l{{1..6},9}
shift{-,_}jis csshiftjis {,x-}sjis ms_kanji ms932
utf{,-}8 utf-16{,be,le} unicode-1-1-utf-8
windows-{31j,874,949,125{0..8}} dos-874 tis-620 ansi_x3.4-1968
x-user-defined auto
)
_describe -t encodings 'encoding' encodings && ret=0
;;
type|typespec)
local -U types
types=( ${${(f)"$(_call_program types rg --type-list)"}%%:*} )
if [[ "$case" == 'type' ]]; then
_describe -t types "type" types && ret=0
else
# @todo: Would be nice to complete type names if an include: directive is
# provided here
_values -S ':' 'type spec' \
${^types}':glob or include directive' && ret=0
fi
;;
esac
return ret
# Local Variables:
# mode: shell-script
# coding: utf-8-unix

4
doc/convert-to-man
View File

@@ -1,4 +0,0 @@
#!/bin/sh
pandoc -s -t man rg.1.md -o rg.1
sed -i 's/\.TH.*/.TH "rg" "1"/g' rg.1

542
doc/rg.1
View File

@@ -1,542 +0,0 @@
.\" Automatically generated by Pandoc 1.19.2.1
.\"
.TH "rg" "1"
.hy
.SH NAME
.PP
rg \- recursively search current directory for lines matching a pattern
.SH SYNOPSIS
.PP
rg [\f[I]options\f[]] \f[I]PATTERN\f[] [\f[I]path\f[] ...]
.PP
rg [\f[I]options\f[]] [\-e \f[I]PATTERN\f[] ...] [\-f \f[I]FILE\f[] ...]
[\f[I]path\f[] ...]
.PP
rg [\f[I]options\f[]] \-\-files [\f[I]path\f[] ...]
.PP
rg [\f[I]options\f[]] \-\-type\-list
.PP
rg [\f[I]options\f[]] \-\-help
.PP
rg [\f[I]options\f[]] \-\-version
.SH DESCRIPTION
.PP
ripgrep (rg) combines the usability of The Silver Searcher (an ack
clone) with the raw speed of grep.
.PP
ripgrep\[aq]s regex engine uses finite automata and guarantees linear
time searching.
Because of this, features like backreferences and arbitrary lookaround
are not supported.
.PP
Project home page: https://github.com/BurntSushi/ripgrep
.SH COMMON OPTIONS
.TP
.B \-a, \-\-text
Search binary files as if they were text.
.RS
.RE
.TP
.B \-c, \-\-count
Only show count of line matches for each file.
.RS
.RE
.TP
.B \-\-color \f[I]WHEN\f[]
Whether to use color in the output.
Valid values are never, auto, always or ansi.
[default: auto]
.RS
.RE
.TP
.B \-e, \-\-regexp \f[I]PATTERN\f[] ...
Use PATTERN to search.
This option can be provided multiple times, where all patterns given are
searched.
This is also useful when searching for patterns that start with a dash.
.RS
.RE
.TP
.B \-F, \-\-fixed\-strings
Treat the pattern as a literal string instead of a regular expression.
.RS
.RE
.TP
.B \-g, \-\-glob \f[I]GLOB\f[] ...
Include or exclude files for searching that match the given glob.
This always overrides any other ignore logic if there is a conflict, but
is otherwise applied in addition to ignore files (e.g., .gitignore or
\&.ignore).
Multiple glob flags may be used.
Globbing rules match .gitignore globs.
Precede a glob with a \[aq]!\[aq] to exclude it.
.RS
.PP
The \-\-glob flag subsumes the functionality of both the \-\-include and
\-\-exclude flags commonly found in other tools.
.PP
Values given to \-g must be quoted or your shell will expand them and
result in unexpected behavior.
.PP
Combine with the \-\-files flag to return matched filenames (i.e., to
replicate ack/ag\[aq]s \-g flag).
For example:
.IP
.nf
\f[C]
rg\ \-g\ \[aq]*.foo\[aq]\ \-\-files
\f[]
.fi
.RE
.TP
.B \-h, \-\-help
Show this usage message.
.RS
.RE
.TP
.B \-i, \-\-ignore\-case
Case insensitive search.
Overridden by \-\-case\-sensitive.
.RS
.RE
.TP
.B \-n, \-\-line\-number
Show line numbers (1\-based).
This is enabled by default at a tty.
.RS
.RE
.TP
.B \-N, \-\-no\-line\-number
Suppress line numbers.
.RS
.RE
.TP
.B \-q, \-\-quiet
Do not print anything to stdout.
If a match is found in a file, stop searching that file.
.RS
.RE
.TP
.B \-t, \-\-type \f[I]TYPE\f[] ...
Only search files matching TYPE.
Multiple type flags may be provided.
Use the \-\-type\-list flag to list all available types.
.RS
.RE
.TP
.B \-T, \-\-type\-not \f[I]TYPE\f[] ...
Do not search files matching TYPE.
Multiple not\-type flags may be provided.
.RS
.RE
.TP
.B \-u, \-\-unrestricted ...
Reduce the level of \[aq]smart\[aq] searching.
A single \-u doesn\[aq]t respect .gitignore (etc.) files.
Two \-u flags will search hidden files and directories.
Three \-u flags will search binary files.
\-uu is equivalent to \f[C]grep\ \-r\f[], and \-uuu is equivalent to
\f[C]grep\ \-a\ \-r\f[].
.RS
.PP
Note that the \-u flags are convenient aliases for other combinations of
flags.
\-u aliases \-\-no\-ignore.
\-uu aliases \-\-no\-ignore \-\-hidden.
\-uuu aliases \-\-no\-ignore \-\-hidden \-\-text.
.RE
.TP
.B \-v, \-\-invert\-match
Invert matching.
.RS
.RE
.TP
.B \-w, \-\-word\-regexp
Only show matches surrounded by word boundaries.
This is equivalent to putting \\b before and after the search pattern.
.RS
.RE
.SH LESS COMMON OPTIONS
.TP
.B \-A, \-\-after\-context \f[I]NUM\f[]
Show NUM lines after each match.
.RS
.RE
.TP
.B \-B, \-\-before\-context \f[I]NUM\f[]
Show NUM lines before each match.
.RS
.RE
.TP
.B \-C, \-\-context \f[I]NUM\f[]
Show NUM lines before and after each match.
.RS
.RE
.TP
.B \-\-colors \f[I]SPEC\f[] ...
This flag specifies color settings for use in the output.
This flag may be provided multiple times.
Settings are applied iteratively.
Colors are limited to one of eight choices: red, blue, green, cyan,
magenta, yellow, white and black.
Styles are limited to nobold, bold, nointense or intense.
.RS
.PP
The format of the flag is {type}:{attribute}:{value}.
{type} should be one of path, line, column or match.
{attribute} can be fg, bg or style.
Value is either a color (for fg and bg) or a text style.
A special format, {type}:none, will clear all color settings for {type}.
.PP
For example, the following command will change the match color to
magenta and the background color for line numbers to yellow:
.IP
.nf
\f[C]
rg\ \-\-colors\ \[aq]match:fg:magenta\[aq]\ \-\-colors\ \[aq]line:bg:yellow\[aq]\ foo.
\f[]
.fi
.RE
.TP
.B \-\-column
Show column numbers (1 based) in output.
This only shows the column numbers for the first match on each line.
Note that this doesn\[aq]t try to account for Unicode.
One byte is equal to one column.
This implies \-\-line\-number.
.RS
.RE
.TP
.B \-\-context\-separator \f[I]SEPARATOR\f[]
The string to use when separating non\-continuous context lines.
Escape sequences may be used.
[default: \-\-]
.RS
.RE
.TP
.B \-\-debug
Show debug messages.
.RS
.RE
.TP
.B \-E, \-\-encoding \f[I]ENCODING\f[]
Specify the text encoding that ripgrep will use on all files searched.
The default value is \[aq]auto\[aq], which will cause ripgrep to do a
best effort automatic detection of encoding on a per\-file basis.
Other supported values can be found in the list of labels here:
https://encoding.spec.whatwg.org/#concept\-encoding\-get
.RS
.RE
.TP
.B \-f, \-\-file \f[I]FILE\f[] ...
Search for patterns from the given file, with one pattern per line.
When this flag is used or multiple times or in combination with the
\-e/\-\-regexp flag, then all patterns provided are searched.
Empty pattern lines will match all input lines, and the newline is not
counted as part of the pattern.
.RS
.RE
.TP
.B \-\-files
Print each file that would be searched (but don\[aq]t search).
.RS
.PP
Combine with the \-g flag to return matched paths, for example:
.IP
.nf
\f[C]
rg\ \-g\ \[aq]*.foo\[aq]\ \-\-files
\f[]
.fi
.RE
.TP
.B \-l, \-\-files\-with\-matches
Only show path of each file with matches.
.RS
.RE
.TP
.B \-\-files\-without\-match
Only show path of each file with no matches.
.RS
.RE
.TP
.B \-H, \-\-with\-filename
Prefix each match with the file name that contains it.
This is the default when more than one file is searched.
.RS
.RE
.TP
.B \-\-no\-filename
Never show the filename for a match.
This is the default when one file is searched.
.RS
.RE
.TP
.B \-\-heading
Show the file name above clusters of matches from each file instead of
showing the file name for every match.
This is the default mode at a tty.
.RS
.RE
.TP
.B \-\-no\-heading
Don\[aq]t group matches by each file.
If \-H/\-\-with\-filename is enabled, then file names will be shown for
every line matched.
This is the default mode when not at a tty.
.RS
.RE
.TP
.B \-\-hidden
Search hidden directories and files.
(Hidden directories and files are skipped by default.)
.RS
.RE
.TP
.B \-\-ignore\-file \f[I]FILE\f[] ...
Specify additional ignore files for filtering file paths.
Ignore files should be in the gitignore format and are matched relative
to the current working directory.
These ignore files have lower precedence than all other ignore files.
When specifying multiple ignore files, earlier files have lower
precedence than later files.
.RS
.RE
.TP
.B \-L, \-\-follow
Follow symlinks.
.RS
.RE
.TP
.B \-M, \-\-max\-columns \f[I]NUM\f[]
Don\[aq]t print lines longer than this limit in bytes.
Longer lines are omitted, and only the number of matches in that line is
printed.
.RS
.RE
.TP
.B \-m, \-\-max\-count \f[I]NUM\f[]
Limit the number of matching lines per file searched to NUM.
.RS
.RE
.TP
.B \-\-max\-filesize \f[I]NUM\f[]+\f[I]SUFFIX\f[]?
Ignore files larger than \f[I]NUM\f[] in size.
Directories will never be ignored.
.RS
.PP
\f[I]SUFFIX\f[] is optional and may be one of K, M or G.
These correspond to kilobytes, megabytes and gigabytes respectively.
If omitted the input is treated as bytes.
.RE
.TP
.B \-\-maxdepth \f[I]NUM\f[]
Descend at most NUM directories below the command line arguments.
A value of zero searches only the starting\-points themselves.
.RS
.RE
.TP
.B \-\-mmap
Search using memory maps when possible.
This is enabled by default when ripgrep thinks it will be faster.
(Note that mmap searching doesn\[aq]t currently support the various
context related options.)
.RS
.RE
.TP
.B \-\-no\-messages
Suppress all error messages.
.RS
.RE
.TP
.B \-\-no\-mmap
Never use memory maps, even when they might be faster.
.RS
.RE
.TP
.B \-\-no\-ignore
Don\[aq]t respect ignore files (.gitignore, .ignore, etc.) This implies
\-\-no\-ignore\-parent.
.RS
.RE
.TP
.B \-\-no\-ignore\-parent
Don\[aq]t respect ignore files in parent directories.
.RS
.RE
.TP
.B \-\-no\-ignore\-vcs
Don\[aq]t respect version control ignore files (e.g., .gitignore).
Note that .ignore files will continue to be respected.
.RS
.RE
.TP
.B \-0, \-\-null
Whenever a file name is printed, follow it with a NUL byte.
This includes printing filenames before matches, and when printing a
list of matching files such as with \-\-count, \-\-files\-with\-matches
and \-\-files.
.RS
.RE
.TP
.B \-o, \-\-only\-matching
Print only the matched (non\-empty) parts of a matching line, with each
such part on a separate output line.
.RS
.RE
.TP
.B \-\-path\-separator \f[I]SEPARATOR\f[]
The path separator to use when printing file paths.
This defaults to your platform\[aq]s path separator, which is / on Unix
and \\ on Windows.
This flag is intended for overriding the default when the environment
demands it (e.g., cygwin).
A path separator is limited to a single byte.
.RS
.RE
.TP
.B \-p, \-\-pretty
Alias for \-\-color=always \-\-heading \-\-line\-number.
.RS
.RE
.TP
.B \-r, \-\-replace \f[I]ARG\f[]
Replace every match with the string given when printing search results.
Neither this flag nor any other flag will modify your files.
.RS
.PP
Capture group indices (e.g., $5) and names (e.g., $foo) are supported in
the replacement string.
.PP
Note that the replacement by default replaces each match, and NOT the
entire line.
To replace the entire line, you should match the entire line.
For example, to emit only the first phone numbers in each line:
.IP
.nf
\f[C]
rg\ \[aq]^.*([0\-9]{3}\-[0\-9]{3}\-[0\-9]{4}).*$\[aq]\ \-\-replace\ \[aq]$1\[aq]
\f[]
.fi
.RE
.TP
.B \-s, \-\-case\-sensitive
Search case sensitively.
This overrides \-\-ignore\-case and \-\-smart\-case.
.RS
.RE
.TP
.B \-S, \-\-smart\-case
Search case insensitively if the pattern is all lowercase.
Search case sensitively otherwise.
This is overridden by either \-\-case\-sensitive or \-\-ignore\-case.
.RS
.RE
.TP
.B \-\-sort\-files
Sort results by file path.
Note that this currently disables all parallelism and runs search in a
single thread.
.RS
.RE
.TP
.B \-j, \-\-threads \f[I]ARG\f[]
The number of threads to use.
0 means use the number of logical CPUs (capped at 12).
[default: 0]
.RS
.RE
.TP
.B \-\-version
Show the version number of ripgrep and exit.
.RS
.RE
.TP
.B \-\-vimgrep
Show results with every match on its own line, including line numbers
and column numbers.
With this option, a line with more than one match will be printed more
than once.
.RS
.PP
Recommended .vimrc configuration:
.IP
.nf
\f[C]
\ \ set\ grepprg=rg\\\ \-\-vimgrep
\ \ set\ grepformat^=%f:%l:%c:%m
\f[]
.fi
.PP
Use :grep to grep for something, then :cn and :cp to navigate through
the matches.
.RE
.SH FILE TYPE MANAGEMENT OPTIONS
.TP
.B \-\-type\-list
Show all supported file types and their associated globs.
.RS
.RE
.TP
.B \-\-type\-add \f[I]ARG\f[] ...
Add a new glob for a particular file type.
Only one glob can be added at a time.
Multiple \-\-type\-add flags can be provided.
Unless \-\-type\-clear is used, globs are added to any existing globs
inside of ripgrep.
Note that this must be passed to every invocation of rg.
Type settings are NOT persisted.
Example:
.RS
.IP
.nf
\f[C]
\ \ rg\ \-\-type\-add\ \[aq]foo:*.foo\[aq]\ \-tfoo\ PATTERN
\f[]
.fi
.PP
\-\-type\-add can also be used to include rules from other types with
the special include directive.
The include directive permits specifying one or more other type names
(separated by a comma) that have been defined and its rules will
automatically be imported into the type specified.
For example, to create a type called src that matches C++, Python and
Markdown files, one can use:
.IP
.nf
\f[C]
\ \ \-\-type\-add\ \[aq]src:include:cpp,py,md\[aq]
\f[]
.fi
.PP
Additional glob rules can still be added to the src type by using the
\-\-type\-add flag again:
.IP
.nf
\f[C]
\ \ \-\-type\-add\ \[aq]src:include:cpp,py,md\[aq]\ \-\-type\-add\ \[aq]src:*.foo\[aq]
\f[]
.fi
.PP
Note that type names must consist only of Unicode letters or numbers.
Punctuation characters are not allowed.
.RE
.TP
.B \-\-type\-clear \f[I]TYPE\f[] ...
Clear the file type globs previously defined for TYPE.
This only clears the default type definitions that are found inside of
ripgrep.
Note that this must be passed to every invocation of rg.
.RS
.RE
.SH SHELL COMPLETION
.PP
Shell completion files are included in the release tarball for Bash,
Fish, Zsh and PowerShell.
.PP
For \f[B]bash\f[], move \f[C]rg.bash\-completion\f[] to
\f[C]$XDG_CONFIG_HOME/bash_completion\f[] or
\f[C]/etc/bash_completion.d/\f[].
.PP
For \f[B]fish\f[], move \f[C]rg.fish\f[] to
\f[C]$HOME/.config/fish/completions\f[].

355
doc/rg.1.md
View File

@@ -1,355 +0,0 @@
# NAME
rg - recursively search current directory for lines matching a pattern
# SYNOPSIS
rg [*options*] *PATTERN* [*path* ...]
rg [*options*] [-e *PATTERN* ...] [-f *FILE* ...] [*path* ...]
rg [*options*] --files [*path* ...]
rg [*options*] --type-list
rg [*options*] --help
rg [*options*] --version
# DESCRIPTION
ripgrep (rg) combines the usability of The Silver Searcher (an ack clone) with
the raw speed of grep.
ripgrep's regex engine uses finite automata and guarantees linear time
searching. Because of this, features like backreferences and arbitrary
lookaround are not supported.
Project home page: https://github.com/BurntSushi/ripgrep
# COMMON OPTIONS
-a, --text
: Search binary files as if they were text.
-c, --count
: Only show count of line matches for each file.
--color *WHEN*
: Whether to use color in the output. Valid values are never, auto, always or
ansi. [default: auto]
-e, --regexp *PATTERN* ...
: Use PATTERN to search. This option can be provided multiple times, where all
patterns given are searched. This is also useful when searching for patterns
that start with a dash.
-F, --fixed-strings
: Treat the pattern as a literal string instead of a regular expression.
-g, --glob *GLOB* ...
: Include or exclude files for searching that match the given glob. This always
overrides any other ignore logic if there is a conflict, but is otherwise
applied in addition to ignore files (e.g., .gitignore or .ignore). Multiple
glob flags may be used. Globbing rules match .gitignore globs. Precede a
glob with a '!' to exclude it.
The --glob flag subsumes the functionality of both the --include and
--exclude flags commonly found in other tools.
Values given to -g must be quoted or your shell will expand them and result
in unexpected behavior.
Combine with the --files flag to return matched filenames
(i.e., to replicate ack/ag's -g flag). For example:
rg -g '*.foo' --files
-h, --help
: Show this usage message.
-i, --ignore-case
: Case insensitive search. Overridden by --case-sensitive.
-n, --line-number
: Show line numbers (1-based). This is enabled by default at a tty.
-N, --no-line-number
: Suppress line numbers.
-q, --quiet
: Do not print anything to stdout. If a match is found in a file, stop
searching that file.
-t, --type *TYPE* ...
: Only search files matching TYPE. Multiple type flags may be provided. Use the
--type-list flag to list all available types.
-T, --type-not *TYPE* ...
: Do not search files matching TYPE. Multiple not-type flags may be provided.
-u, --unrestricted ...
: Reduce the level of 'smart' searching. A single -u doesn't respect .gitignore
(etc.) files. Two -u flags will search hidden files and directories. Three
-u flags will search binary files. -uu is equivalent to `grep -r`, and -uuu
is equivalent to `grep -a -r`.
Note that the -u flags are convenient aliases for other combinations of
flags. -u aliases --no-ignore. -uu aliases --no-ignore --hidden.
-uuu aliases --no-ignore --hidden --text.
-v, --invert-match
: Invert matching.
-w, --word-regexp
: Only show matches surrounded by word boundaries. This is equivalent to
putting \\b before and after the search pattern.
# LESS COMMON OPTIONS
-A, --after-context *NUM*
: Show NUM lines after each match.
-B, --before-context *NUM*
: Show NUM lines before each match.
-C, --context *NUM*
: Show NUM lines before and after each match.
--colors *SPEC* ...
: This flag specifies color settings for use in the output. This flag may be
provided multiple times. Settings are applied iteratively. Colors are limited
to one of eight choices: red, blue, green, cyan, magenta, yellow, white and
black. Styles are limited to nobold, bold, nointense or intense.
The format of the flag is {type}:{attribute}:{value}. {type} should be one
of path, line, column or match. {attribute} can be fg, bg or style. Value
is either a color (for fg and bg) or a text style. A special format,
{type}:none, will clear all color settings for {type}.
For example, the following command will change the match color to magenta
and the background color for line numbers to yellow:
rg --colors 'match:fg:magenta' --colors 'line:bg:yellow' foo.
--column
: Show column numbers (1 based) in output. This only shows the column
numbers for the first match on each line. Note that this doesn't try
to account for Unicode. One byte is equal to one column. This implies
--line-number.
--context-separator *SEPARATOR*
: The string to use when separating non-continuous context lines. Escape
sequences may be used. [default: --]
--debug
: Show debug messages.
-E, --encoding *ENCODING*
: Specify the text encoding that ripgrep will use on all files
searched. The default value is 'auto', which will cause ripgrep to do
a best effort automatic detection of encoding on a per-file basis.
Other supported values can be found in the list of labels here:
https://encoding.spec.whatwg.org/#concept-encoding-get
-f, --file *FILE* ...
: Search for patterns from the given file, with one pattern per line. When this
flag is used or multiple times or in combination with the -e/--regexp flag,
then all patterns provided are searched. Empty pattern lines will match all
input lines, and the newline is not counted as part of the pattern.
--files
: Print each file that would be searched (but don't search).
Combine with the -g flag to return matched paths, for example:
rg -g '*.foo' --files
-l, --files-with-matches
: Only show path of each file with matches.
--files-without-match
: Only show path of each file with no matches.
-H, --with-filename
: Prefix each match with the file name that contains it. This is the
default when more than one file is searched.
--no-filename
: Never show the filename for a match. This is the default when
one file is searched.
--heading
: Show the file name above clusters of matches from each file instead of
showing the file name for every match. This is the default mode at a tty.
--no-heading
: Don't group matches by each file. If -H/--with-filename is enabled, then
file names will be shown for every line matched. This is the default mode
when not at a tty.
--hidden
: Search hidden directories and files. (Hidden directories and files are
skipped by default.)
--ignore-file *FILE* ...
: Specify additional ignore files for filtering file paths.
Ignore files should be in the gitignore format and are matched
relative to the current working directory. These ignore files
have lower precedence than all other ignore files. When
specifying multiple ignore files, earlier files have lower
precedence than later files.
-L, --follow
: Follow symlinks.
-M, --max-columns *NUM*
: Don't print lines longer than this limit in bytes. Longer lines are omitted,
and only the number of matches in that line is printed.
-m, --max-count *NUM*
: Limit the number of matching lines per file searched to NUM.
--max-filesize *NUM*+*SUFFIX*?
: Ignore files larger than *NUM* in size. Directories will never be ignored.
*SUFFIX* is optional and may be one of K, M or G. These correspond to
kilobytes, megabytes and gigabytes respectively. If omitted the input is
treated as bytes.
--maxdepth *NUM*
: Descend at most NUM directories below the command line arguments.
A value of zero searches only the starting-points themselves.
--mmap
: Search using memory maps when possible. This is enabled by default
when ripgrep thinks it will be faster. (Note that mmap searching
doesn't currently support the various context related options.)
--no-messages
: Suppress all error messages.
--no-mmap
: Never use memory maps, even when they might be faster.
--no-ignore
: Don't respect ignore files (.gitignore, .ignore, etc.)
This implies --no-ignore-parent.
--no-ignore-parent
: Don't respect ignore files in parent directories.
--no-ignore-vcs
: Don't respect version control ignore files (e.g., .gitignore).
Note that .ignore files will continue to be respected.
-0, --null
: Whenever a file name is printed, follow it with a NUL byte.
This includes printing filenames before matches, and when printing
a list of matching files such as with --count, --files-with-matches
and --files.
-o, --only-matching
: Print only the matched (non-empty) parts of a matching line, with each such
part on a separate output line.
--path-separator *SEPARATOR*
: The path separator to use when printing file paths. This defaults to your
platform's path separator, which is / on Unix and \\ on Windows. This flag is
intended for overriding the default when the environment demands it (e.g.,
cygwin). A path separator is limited to a single byte.
-p, --pretty
: Alias for --color=always --heading --line-number.
-r, --replace *ARG*
: Replace every match with the string given when printing search results.
Neither this flag nor any other flag will modify your files.
Capture group indices (e.g., $5) and names (e.g., $foo) are supported
in the replacement string.
Note that the replacement by default replaces each match, and NOT the
entire line. To replace the entire line, you should match the entire line.
For example, to emit only the first phone numbers in each line:
rg '^.*([0-9]{3}-[0-9]{3}-[0-9]{4}).*$' --replace '$1'
-s, --case-sensitive
: Search case sensitively. This overrides --ignore-case and --smart-case.
-S, --smart-case
: Search case insensitively if the pattern is all lowercase.
Search case sensitively otherwise. This is overridden by either
--case-sensitive or --ignore-case.
--sort-files
: Sort results by file path. Note that this currently
disables all parallelism and runs search in a single thread.
-j, --threads *ARG*
: The number of threads to use. 0 means use the number of logical CPUs
(capped at 12). [default: 0]
--version
: Show the version number of ripgrep and exit.
--vimgrep
: Show results with every match on its own line, including
line numbers and column numbers. With this option, a line with
more than one match will be printed more than once.
Recommended .vimrc configuration:
set grepprg=rg\ --vimgrep
set grepformat^=%f:%l:%c:%m
Use :grep to grep for something, then :cn and :cp to navigate through the
matches.
# FILE TYPE MANAGEMENT OPTIONS
--type-list
: Show all supported file types and their associated globs.
--type-add *ARG* ...
: Add a new glob for a particular file type. Only one glob can be added
at a time. Multiple --type-add flags can be provided. Unless --type-clear
is used, globs are added to any existing globs inside of ripgrep. Note that
this must be passed to every invocation of rg. Type settings are NOT
persisted. Example:
rg --type-add 'foo:*.foo' -tfoo PATTERN
--type-add can also be used to include rules from other types
with the special include directive. The include directive
permits specifying one or more other type names (separated by a
comma) that have been defined and its rules will automatically
be imported into the type specified. For example, to create a
type called src that matches C++, Python and Markdown files, one
can use:
--type-add 'src:include:cpp,py,md'
Additional glob rules can still be added to the src type by
using the --type-add flag again:
--type-add 'src:include:cpp,py,md' --type-add 'src:*.foo'
Note that type names must consist only of Unicode letters or
numbers. Punctuation characters are not allowed.
--type-clear *TYPE* ...
: Clear the file type globs previously defined for TYPE. This only clears
the default type definitions that are found inside of ripgrep. Note
that this must be passed to every invocation of rg.
# SHELL COMPLETION
Shell completion files are included in the release tarball for Bash, Fish, Zsh
and PowerShell.
For **bash**, move `rg.bash-completion` to `$XDG_CONFIG_HOME/bash_completion`
or `/etc/bash_completion.d/`.
For **fish**, move `rg.fish` to `$HOME/.config/fish/completions`.

211
doc/rg.1.txt.tpl Normal file
View File

@@ -0,0 +1,211 @@
rg(1)
=====
Name
----
rg - recursively search current directory for lines matching a pattern
Synopsis
--------
*rg* [_OPTIONS_] _PATTERN_ [_PATH_...]
*rg* [_OPTIONS_] *-e* _PATTERN_... [_PATH_...]
*rg* [_OPTIONS_] *-f* _PATTERNFILE_... [_PATH_...]
*rg* [_OPTIONS_] *--files* [_PATH_...]
*rg* [_OPTIONS_] *--type-list*
*command* | *rg* [_OPTIONS_] _PATTERN_
*rg* [_OPTIONS_] *--help*
*rg* [_OPTIONS_] *--version*
DESCRIPTION
-----------
ripgrep (rg) recursively searches your current directory for a regex pattern.
By default, ripgrep will respect your .gitignore and automatically skip hidden
files/directories and binary files.
ripgrep's default regex engine uses finite automata and guarantees linear
time searching. Because of this, features like backreferences and arbitrary
look-around are not supported. However, if ripgrep is built with PCRE2, then
the *--pcre2* flag can be used to enable backreferences and look-around.
ripgrep supports configuration files. Set *RIPGREP_CONFIG_PATH* to a
configuration file. The file can specify one shell argument per line. Lines
starting with *#* are ignored. For more details, see the man page or the
*README*.
REGEX SYNTAX
------------
ripgrep uses Rust's regex engine by default, which documents its syntax:
https://docs.rs/regex/*/regex/#syntax
ripgrep uses byte-oriented regexes, which has some additional documentation:
https://docs.rs/regex/*/regex/bytes/index.html#syntax
To a first approximation, ripgrep uses Perl-like regexes without look-around or
backreferences. This makes them very similar to the "extended" (ERE) regular
expressions supported by *egrep*, but with a few additional features like
Unicode character classes.
If you're using ripgrep with the *--pcre2* flag, then please consult
https://www.pcre.org or the PCRE2 man pages for documentation on the supported
syntax.
POSITIONAL ARGUMENTS
--------------------
_PATTERN_::
A regular expression used for searching. To match a pattern beginning with a
dash, use the -e/--regexp option.
_PATH_::
A file or directory to search. Directories are searched recursively. Paths
specified explicitly on the command line override glob and ignore rules.
OPTIONS
-------
Note that for many options, there exist flags to disable them. In some cases,
those flags are not listed in a first class way below. For example, the
*--column* flag (listed below) enables column numbers in ripgrep's output, but
the *--no-column* flag (not listed below) disables them. The reverse can also
exist. For example, the *--no-ignore* flag (listed below) disables ripgrep's
*gitignore* logic, but the *--ignore* flag (not listed below) enables it. These
flags are useful for overriding a ripgrep configuration file on the command
line. Each flag's documentation notes whether an inverted flag exists. In all
cases, the flag specified last takes precedence.
{OPTIONS}
EXIT STATUS
-----------
If ripgrep finds a match, then the exit status of the program is 0. If no match
could be found, then the exit status is 1. If an error occurred, then the exit
status is always 2 unless ripgrep was run with the *--quiet* flag and a match
was found. In summary:
* `0` exit status occurs only when at least one match was found, and if
no error occurred, unless *--quiet* was given.
* `1` exit status occurs only when no match was found and no error occurred.
* `2` exit status occurs when an error occurred. This is true for both
catastrophic errors (e.g., a regex syntax error) and for soft errors (e.g.,
unable to read a file).
CONFIGURATION FILES
-------------------
ripgrep supports reading configuration files that change ripgrep's default
behavior. The format of the configuration file is an "rc" style and is very
simple. It is defined by two rules:
1. Every line is a shell argument, after trimming whitespace.
2. Lines starting with *#* (optionally preceded by any amount of
whitespace) are ignored.
ripgrep will look for a single configuration file if and only if the
*RIPGREP_CONFIG_PATH* environment variable is set and is non-empty.
ripgrep will parse shell arguments from this file on startup and will
behave as if the arguments in this file were prepended to any explicit
arguments given to ripgrep on the command line.
For example, if your ripgreprc file contained a single line:
--smart-case
then the following command
RIPGREP_CONFIG_PATH=wherever/.ripgreprc rg foo
would behave identically to the following command
rg --smart-case foo
another example is adding types
--type-add
web:*.{html,css,js}*
would behave identically to the following command
rg --type-add 'web:*.{html,css,js}*' foo
same with using globs
--glob=!git/*
or
--glob
!git/*
would behave identically to the following command
rg --glob '!git/*' foo
ripgrep also provides a flag, *--no-config*, that when present will suppress
any and all support for configuration. This includes any future support
for auto-loading configuration files from pre-determined paths.
Conflicts between configuration files and explicit arguments are handled
exactly like conflicts in the same command line invocation. That is,
this command:
RIPGREP_CONFIG_PATH=wherever/.ripgreprc rg foo --case-sensitive
is exactly equivalent to
rg --smart-case foo --case-sensitive
in which case, the *--case-sensitive* flag would override the *--smart-case*
flag.
SHELL COMPLETION
----------------
Shell completion files are included in the release tarball for Bash, Fish, Zsh
and PowerShell.
For *bash*, move *rg.bash* to *$XDG_CONFIG_HOME/bash_completion*
or */etc/bash_completion.d/*.
For *fish*, move *rg.fish* to *$HOME/.config/fish/completions*.
For *zsh*, move *_rg* to one of your *$fpath* directories.
CAVEATS
-------
ripgrep may abort unexpectedly when using default settings if it searches a
file that is simultaneously truncated. This behavior can be avoided by passing
the *--no-mmap* flag which will forcefully disable the use of memory maps in
all cases.
VERSION
-------
{VERSION}
HOMEPAGE
--------
https://github.com/BurntSushi/ripgrep
Please report bugs and feature requests in the issue tracker. Please do your
best to provide a reproducible test case for bugs. This should include the
corpus being searched, the *rg* command, the actual output and the expected
output. Please also include the output of running the same *rg* command but
with the *--debug* flag.
AUTHORS
-------
Andrew Gallant <jamslam@gmail.com>

16
globset/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "globset"
version = "0.2.0" #:version
version = "0.4.2" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Cross platform single glob and glob set matching. Glob set matching is the
@@ -19,14 +19,14 @@ name = "globset"
bench = false
[dependencies]
aho-corasick = "0.6.0"
fnv = "1.0"
log = "0.3"
memchr = "1"
regex = "0.2.1"
aho-corasick = "0.7.3"
bstr = { version = "0.1.2", default-features = false, features = ["std"] }
fnv = "1.0.6"
log = "0.4.5"
regex = "1.1.5"
[dev-dependencies]
glob = "0.2"
glob = "0.2.11"
[features]
simd-accel = ["regex/simd-accel"]
simd-accel = []

18
globset/README.md
View File

@@ -4,7 +4,7 @@ Cross platform single glob and glob set matching. Glob set matching is the
process of matching one or more glob patterns against a single candidate path
simultaneously, and returning all of the globs that matched.
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.png)](https://travis-ci.org/BurntSushi/ripgrep)
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/globset.svg)](https://crates.io/crates/globset)
@@ -20,7 +20,7 @@ Add this to your `Cargo.toml`:
```toml
[dependencies]
globset = "0.1"
globset = "0.3"
```
and this to your crate root:
@@ -36,7 +36,7 @@ This example shows how to match a single glob against a single file path.
```rust
use globset::Glob;
let glob = try!(Glob::new("*.rs")).compile_matcher();
let glob = Glob::new("*.rs")?.compile_matcher();
assert!(glob.is_match("foo.rs"));
assert!(glob.is_match("foo/bar.rs"));
@@ -51,8 +51,8 @@ semantics. In this example, we prevent wildcards from matching path separators.
```rust
use globset::GlobBuilder;
let glob = try!(GlobBuilder::new("*.rs")
.literal_separator(true).build()).compile_matcher();
let glob = GlobBuilder::new("*.rs")
.literal_separator(true).build()?.compile_matcher();
assert!(glob.is_match("foo.rs"));
assert!(!glob.is_match("foo/bar.rs")); // no longer matches
@@ -69,10 +69,10 @@ use globset::{Glob, GlobSetBuilder};
let mut builder = GlobSetBuilder::new();
// A GlobBuilder can be used to configure each glob's match semantics
// independently.
builder.add(try!(Glob::new("*.rs")));
builder.add(try!(Glob::new("src/lib.rs")));
builder.add(try!(Glob::new("src/**/foo.rs")));
let set = try!(builder.build());
builder.add(Glob::new("*.rs")?);
builder.add(Glob::new("src/lib.rs")?);
builder.add(Glob::new("src/**/foo.rs")?);
let set = builder.build()?;
assert_eq!(set.matches("src/bar/baz/foo.rs"), vec![0, 2]);
```

363
globset/src/glob.rs
View File

@@ -1,4 +1,3 @@
use std::ffi::{OsStr, OsString};
use std::fmt;
use std::hash;
use std::iter;
@@ -28,7 +27,7 @@ pub enum MatchStrategy {
BasenameLiteral(String),
/// A pattern matches if and only if the file path's extension matches this
/// literal string.
Extension(OsString),
Extension(String),
/// A pattern matches if and only if this prefix literal is a prefix of the
/// candidate file path.
Prefix(String),
@@ -47,7 +46,7 @@ pub enum MatchStrategy {
/// extension. Note that this is a necessary but NOT sufficient criterion.
/// Namely, if the extension matches, then a full regex search is still
/// required.
RequiredExtension(OsString),
RequiredExtension(String),
/// A regex needs to be used for matching.
Regex,
}
@@ -121,7 +120,7 @@ impl GlobMatcher {
/// Tests whether the given path matches this pattern or not.
pub fn is_match_candidate(&self, path: &Candidate) -> bool {
self.re.is_match(&path.path)
self.re.is_match(path.path.as_bytes())
}
}
@@ -146,7 +145,7 @@ impl GlobStrategic {
/// Tests whether the given path matches this pattern or not.
fn is_match_candidate(&self, candidate: &Candidate) -> bool {
let byte_path = &*candidate.path;
let byte_path = candidate.path.as_bytes();
match self.strategy {
MatchStrategy::Literal(ref lit) => lit.as_bytes() == byte_path,
@@ -154,7 +153,7 @@ impl GlobStrategic {
lit.as_bytes() == &*candidate.basename
}
MatchStrategy::Extension(ref ext) => {
candidate.ext == ext
ext.as_bytes() == &*candidate.ext
}
MatchStrategy::Prefix(ref pre) => {
starts_with(pre.as_bytes(), byte_path)
@@ -166,7 +165,8 @@ impl GlobStrategic {
ends_with(suffix.as_bytes(), byte_path)
}
MatchStrategy::RequiredExtension(ref ext) => {
candidate.ext == ext && self.re.is_match(byte_path)
let ext = ext.as_bytes();
&*candidate.ext == ext && self.re.is_match(byte_path)
}
MatchStrategy::Regex => self.re.is_match(byte_path),
}
@@ -187,13 +187,26 @@ pub struct GlobBuilder<'a> {
opts: GlobOptions,
}
#[derive(Clone, Copy, Debug, Default, Eq, Hash, PartialEq)]
#[derive(Clone, Copy, Debug, Eq, Hash, PartialEq)]
struct GlobOptions {
/// Whether to match case insensitively.
case_insensitive: bool,
/// Whether to require a literal separator to match a separator in a file
/// path. e.g., when enabled, `*` won't match `/`.
literal_separator: bool,
/// Whether or not to use `\` to escape special characters.
/// e.g., when enabled, `\*` will match a literal `*`.
backslash_escape: bool,
}
impl GlobOptions {
fn default() -> GlobOptions {
GlobOptions {
case_insensitive: false,
literal_separator: false,
backslash_escape: !is_separator('\\'),
}
}
}
#[derive(Clone, Debug, Default, Eq, PartialEq)]
@@ -262,6 +275,19 @@ impl Glob {
}
/// Returns the regular expression string for this glob.
///
/// Note that regular expressions for globs are intended to be matched on
/// arbitrary bytes (`&[u8]`) instead of Unicode strings (`&str`). In
/// particular, globs are frequently used on file paths, where there is no
/// general guarantee that file paths are themselves valid UTF-8. As a
/// result, callers will need to ensure that they are using a regex API
/// that can match on arbitrary bytes. For example, the
/// [`regex`](https://crates.io/regex)
/// crate's
/// [`Regex`](https://docs.rs/regex/*/regex/struct.Regex.html)
/// API is not suitable for this since it matches on `&str`, but its
/// [`bytes::Regex`](https://docs.rs/regex/*/regex/bytes/struct.Regex.html)
/// API is suitable for this.
pub fn regex(&self) -> &str {
&self.re
}
@@ -295,7 +321,7 @@ impl Glob {
/// std::path::Path::extension returns. Namely, this extension includes
/// the '.'. Also, paths like `.rs` are considered to have an extension
/// of `.rs`.
fn ext(&self) -> Option<OsString> {
fn ext(&self) -> Option<String> {
if self.opts.case_insensitive {
return None;
}
@@ -319,11 +345,11 @@ impl Glob {
Some(&Token::Literal('.')) => {}
_ => return None,
}
let mut lit = OsStr::new(".").to_os_string();
let mut lit = ".".to_string();
for t in self.tokens[start + 2..].iter() {
match *t {
Token::Literal('.') | Token::Literal('/') => return None,
Token::Literal(c) => lit.push(c.to_string()),
Token::Literal(c) => lit.push(c),
_ => return None,
}
}
@@ -337,7 +363,7 @@ impl Glob {
/// This is like `ext`, but returns an extension even if it isn't sufficent
/// to imply a match. Namely, if an extension is returned, then it is
/// necessary but not sufficient for a match.
fn required_ext(&self) -> Option<OsString> {
fn required_ext(&self) -> Option<String> {
if self.opts.case_insensitive {
return None;
}
@@ -360,7 +386,7 @@ impl Glob {
None
} else {
ext.reverse();
Some(OsString::from(ext.into_iter().collect::<String>()))
Some(ext.into_iter().collect())
}
}
@@ -509,7 +535,7 @@ impl Glob {
Some(&self.tokens[start..])
}
/// Returns the pattern as a literal if and only if the pattern exclusiely
/// Returns the pattern as a literal if and only if the pattern exclusively
/// matches the basename of a file path *and* is a literal.
///
/// The basic format of these patterns is `**/{literal}`, where `{literal}`
@@ -549,8 +575,9 @@ impl<'a> GlobBuilder<'a> {
chars: self.glob.chars().peekable(),
prev: None,
cur: None,
opts: &self.opts,
};
try!(p.parse());
p.parse()?;
if p.stack.is_empty() {
Err(Error {
glob: Some(self.glob.to_string()),
@@ -585,6 +612,19 @@ impl<'a> GlobBuilder<'a> {
self.opts.literal_separator = yes;
self
}
/// When enabled, a back slash (`\`) may be used to escape
/// special characters in a glob pattern. Additionally, this will
/// prevent `\` from being interpreted as a path separator on all
/// platforms.
///
/// This is enabled by default on platforms where `\` is not a
/// path separator and disabled by default on platforms where `\`
/// is a path separator.
pub fn backslash_escape(&mut self, yes: bool) -> &mut GlobBuilder<'a> {
self.opts.backslash_escape = yes;
self
}
}
impl Tokens {
@@ -710,6 +750,7 @@ struct Parser<'a> {
chars: iter::Peekable<str::Chars<'a>>,
prev: Option<char>,
cur: Option<char>,
opts: &'a GlobOptions,
}
impl<'a> Parser<'a> {
@@ -720,20 +761,14 @@ impl<'a> Parser<'a> {
fn parse(&mut self) -> Result<(), Error> {
while let Some(c) = self.bump() {
match c {
'?' => try!(self.push_token(Token::Any)),
'*' => try!(self.parse_star()),
'[' => try!(self.parse_class()),
'{' => try!(self.push_alternate()),
'}' => try!(self.pop_alternate()),
',' => try!(self.parse_comma()),
c => {
if is_separator(c) {
// Normalize all patterns to use / as a separator.
try!(self.push_token(Token::Literal('/')))
} else {
try!(self.push_token(Token::Literal(c)))
}
}
'?' => self.push_token(Token::Any)?,
'*' => self.parse_star()?,
'[' => self.parse_class()?,
'{' => self.push_alternate()?,
'}' => self.pop_alternate()?,
',' => self.parse_comma()?,
'\\' => self.parse_backslash()?,
c => self.push_token(Token::Literal(c))?,
}
}
Ok(())
@@ -786,42 +821,82 @@ impl<'a> Parser<'a> {
}
}
fn parse_backslash(&mut self) -> Result<(), Error> {
if self.opts.backslash_escape {
match self.bump() {
None => Err(self.error(ErrorKind::DanglingEscape)),
Some(c) => self.push_token(Token::Literal(c)),
}
} else if is_separator('\\') {
// Normalize all patterns to use / as a separator.
self.push_token(Token::Literal('/'))
} else {
self.push_token(Token::Literal('\\'))
}
}
fn parse_star(&mut self) -> Result<(), Error> {
let prev = self.prev;
if self.chars.peek() != Some(&'*') {
try!(self.push_token(Token::ZeroOrMore));
if self.peek() != Some('*') {
self.push_token(Token::ZeroOrMore)?;
return Ok(());
}
assert!(self.bump() == Some('*'));
if !try!(self.have_tokens()) {
try!(self.push_token(Token::RecursivePrefix));
let next = self.bump();
if !next.map(is_separator).unwrap_or(true) {
return Err(self.error(ErrorKind::InvalidRecursive));
if !self.have_tokens()? {
if !self.peek().map_or(true, is_separator) {
self.push_token(Token::ZeroOrMore)?;
self.push_token(Token::ZeroOrMore)?;
} else {
self.push_token(Token::RecursivePrefix)?;
assert!(self.bump().map_or(true, is_separator));
}
return Ok(());
}
try!(self.pop_token());
if !prev.map(is_separator).unwrap_or(false) {
if self.stack.len() <= 1
|| (prev != Some(',') && prev != Some('{')) {
return Err(self.error(ErrorKind::InvalidRecursive));
|| (prev != Some(',') && prev != Some('{'))
{
self.push_token(Token::ZeroOrMore)?;
self.push_token(Token::ZeroOrMore)?;
return Ok(());
}
}
match self.chars.peek() {
None => {
assert!(self.bump().is_none());
self.push_token(Token::RecursiveSuffix)
let is_suffix =
match self.peek() {
None => {
assert!(self.bump().is_none());
true
}
Some(',') | Some('}') if self.stack.len() >= 2 => {
true
}
Some(c) if is_separator(c) => {
assert!(self.bump().map(is_separator).unwrap_or(false));
false
}
_ => {
self.push_token(Token::ZeroOrMore)?;
self.push_token(Token::ZeroOrMore)?;
return Ok(());
}
};
match self.pop_token()? {
Token::RecursivePrefix => {
self.push_token(Token::RecursivePrefix)?;
}
Some(&',') | Some(&'}') if self.stack.len() >= 2 => {
self.push_token(Token::RecursiveSuffix)
Token::RecursiveSuffix => {
self.push_token(Token::RecursiveSuffix)?;
}
Some(&c) if is_separator(c) => {
assert!(self.bump().map(is_separator).unwrap_or(false));
self.push_token(Token::RecursiveZeroOrMore)
_ => {
if is_suffix {
self.push_token(Token::RecursiveSuffix)?;
} else {
self.push_token(Token::RecursiveZeroOrMore)?;
}
}
_ => Err(self.error(ErrorKind::InvalidRecursive)),
}
Ok(())
}
fn parse_class(&mut self) -> Result<(), Error> {
@@ -840,12 +915,15 @@ impl<'a> Parser<'a> {
Ok(())
}
}
let mut negated = false;
let mut ranges = vec![];
if self.chars.peek() == Some(&'!') {
assert!(self.bump() == Some('!'));
negated = true;
}
let negated = match self.chars.peek() {
Some(&'!') | Some(&'^') => {
let bump = self.bump();
assert!(bump == Some('!') || bump == Some('^'));
true
}
_ => false,
};
let mut first = true;
let mut in_range = false;
loop {
@@ -870,7 +948,7 @@ impl<'a> Parser<'a> {
// invariant: in_range is only set when there is
// already at least one character seen.
let r = ranges.last_mut().unwrap();
try!(add_to_last_range(&self.glob, r, '-'));
add_to_last_range(&self.glob, r, '-')?;
in_range = false;
} else {
assert!(!ranges.is_empty());
@@ -881,8 +959,8 @@ impl<'a> Parser<'a> {
if in_range {
// invariant: in_range is only set when there is
// already at least one character seen.
try!(add_to_last_range(
&self.glob, ranges.last_mut().unwrap(), c));
add_to_last_range(
&self.glob, ranges.last_mut().unwrap(), c)?;
} else {
ranges.push((c, c));
}
@@ -907,6 +985,10 @@ impl<'a> Parser<'a> {
self.cur = self.chars.next();
self.cur
}
fn peek(&mut self) -> Option<char> {
self.chars.peek().map(|&ch| ch)
}
}
#[cfg(test)]
@@ -924,16 +1006,15 @@ fn ends_with(needle: &[u8], haystack: &[u8]) -> bool {
#[cfg(test)]
mod tests {
use std::ffi::{OsStr, OsString};
use {GlobSetBuilder, ErrorKind};
use super::{Glob, GlobBuilder, Token};
use super::Token::*;
#[derive(Clone, Copy, Debug, Default)]
struct Options {
casei: bool,
litsep: bool,
casei: Option<bool>,
litsep: Option<bool>,
bsesc: Option<bool>,
}
macro_rules! syntax {
@@ -963,11 +1044,17 @@ mod tests {
($name:ident, $pat:expr, $re:expr, $options:expr) => {
#[test]
fn $name() {
let pat = GlobBuilder::new($pat)
.case_insensitive($options.casei)
.literal_separator($options.litsep)
.build()
.unwrap();
let mut builder = GlobBuilder::new($pat);
if let Some(casei) = $options.casei {
builder.case_insensitive(casei);
}
if let Some(litsep) = $options.litsep {
builder.literal_separator(litsep);
}
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
let pat = builder.build().unwrap();
assert_eq!(format!("(?-u){}", $re), pat.regex());
}
};
@@ -980,11 +1067,17 @@ mod tests {
($name:ident, $pat:expr, $path:expr, $options:expr) => {
#[test]
fn $name() {
let pat = GlobBuilder::new($pat)
.case_insensitive($options.casei)
.literal_separator($options.litsep)
.build()
.unwrap();
let mut builder = GlobBuilder::new($pat);
if let Some(casei) = $options.casei {
builder.case_insensitive(casei);
}
if let Some(litsep) = $options.litsep {
builder.literal_separator(litsep);
}
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
let pat = builder.build().unwrap();
let matcher = pat.compile_matcher();
let strategic = pat.compile_strategic_matcher();
let set = GlobSetBuilder::new().add(pat).build().unwrap();
@@ -1002,11 +1095,17 @@ mod tests {
($name:ident, $pat:expr, $path:expr, $options:expr) => {
#[test]
fn $name() {
let pat = GlobBuilder::new($pat)
.case_insensitive($options.casei)
.literal_separator($options.litsep)
.build()
.unwrap();
let mut builder = GlobBuilder::new($pat);
if let Some(casei) = $options.casei {
builder.case_insensitive(casei);
}
if let Some(litsep) = $options.litsep {
builder.literal_separator(litsep);
}
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
let pat = builder.build().unwrap();
let matcher = pat.compile_matcher();
let strategic = pat.compile_strategic_matcher();
let set = GlobSetBuilder::new().add(pat).build().unwrap();
@@ -1018,7 +1117,6 @@ mod tests {
}
fn s(string: &str) -> String { string.to_string() }
fn os(string: &str) -> OsString { OsStr::new(string).to_os_string() }
fn class(s: char, e: char) -> Token {
Class { negated: false, ranges: vec![(s, e)] }
@@ -1073,14 +1171,9 @@ mod tests {
syntax!(cls17, "[a-z0-9]", vec![rclass(&[('a', 'z'), ('0', '9')])]);
syntax!(cls18, "[!0-9a-z]", vec![rclassn(&[('0', '9'), ('a', 'z')])]);
syntax!(cls19, "[!a-z0-9]", vec![rclassn(&[('a', 'z'), ('0', '9')])]);
syntax!(cls20, "[^a]", vec![classn('a', 'a')]);
syntax!(cls21, "[^a-z]", vec![classn('a', 'z')]);
syntaxerr!(err_rseq1, "a**", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq2, "**a", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq3, "a**b", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq4, "***", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq5, "/a**", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq6, "/**a", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq7, "/a**b", ErrorKind::InvalidRecursive);
syntaxerr!(err_unclosed1, "[", ErrorKind::UnclosedClass);
syntaxerr!(err_unclosed2, "[]", ErrorKind::UnclosedClass);
syntaxerr!(err_unclosed3, "[!", ErrorKind::UnclosedClass);
@@ -1089,12 +1182,24 @@ mod tests {
syntaxerr!(err_range2, "[z--]", ErrorKind::InvalidRange('z', '-'));
const CASEI: Options = Options {
casei: true,
litsep: false,
casei: Some(true),
litsep: None,
bsesc: None,
};
const SLASHLIT: Options = Options {
casei: false,
litsep: true,
casei: None,
litsep: Some(true),
bsesc: None,
};
const NOBSESC: Options = Options {
casei: None,
litsep: None,
bsesc: Some(false),
};
const BSESC: Options = Options {
casei: None,
litsep: None,
bsesc: Some(true),
};
toregex!(re_casei, "a", "(?i)^a$", &CASEI);
@@ -1112,8 +1217,30 @@ mod tests {
toregex!(re8, "[*]", r"^[\*]$");
toregex!(re9, "[+]", r"^[\+]$");
toregex!(re10, "+", r"^\+$");
toregex!(re11, "**", r"^.*$");
toregex!(re12, "☃", r"^\xe2\x98\x83$");
toregex!(re11, "☃", r"^\xe2\x98\x83$");
toregex!(re12, "**", r"^.*$");
toregex!(re13, "**/", r"^.*$");
toregex!(re14, "**/*", r"^(?:/?|.*/).*$");
toregex!(re15, "**/**", r"^.*$");
toregex!(re16, "**/**/*", r"^(?:/?|.*/).*$");
toregex!(re17, "**/**/**", r"^.*$");
toregex!(re18, "**/**/**/*", r"^(?:/?|.*/).*$");
toregex!(re19, "a/**", r"^a(?:/?|/.*)$");
toregex!(re20, "a/**/**", r"^a(?:/?|/.*)$");
toregex!(re21, "a/**/**/**", r"^a(?:/?|/.*)$");
toregex!(re22, "a/**/b", r"^a(?:/|/.*/)b$");
toregex!(re23, "a/**/**/b", r"^a(?:/|/.*/)b$");
toregex!(re24, "a/**/**/**/b", r"^a(?:/|/.*/)b$");
toregex!(re25, "**/b", r"^(?:/?|.*/)b$");
toregex!(re26, "**/**/b", r"^(?:/?|.*/)b$");
toregex!(re27, "**/**/**/b", r"^(?:/?|.*/)b$");
toregex!(re28, "a**", r"^a.*.*$");
toregex!(re29, "**a", r"^.*.*a$");
toregex!(re30, "a**b", r"^a.*.*b$");
toregex!(re31, "***", r"^.*.*.*$");
toregex!(re32, "/a**", r"^/a.*.*$");
toregex!(re33, "/**a", r"^/.*.*a$");
toregex!(re34, "/a**b", r"^/a.*.*b$");
matches!(match1, "a", "a");
matches!(match2, "a*b", "a_b");
@@ -1150,6 +1277,7 @@ mod tests {
matches!(matchrec22, ".*/**", ".abc/abc");
matches!(matchrec23, "foo/**", "foo");
matches!(matchrec24, "**/foo/bar", "foo/bar");
matches!(matchrec25, "some/*/needle.txt", "some/one/needle.txt");
matches!(matchrange1, "a[0-9]b", "a0b");
matches!(matchrange2, "a[0-9]b", "a9b");
@@ -1162,6 +1290,7 @@ mod tests {
matches!(matchrange9, "[-a-c]", "b");
matches!(matchrange10, "[a-c-]", "b");
matches!(matchrange11, "[-]", "-");
matches!(matchrange12, "a[^0-9]b", "a_b");
matches!(matchpat1, "*hello.txt", "hello.txt");
matches!(matchpat2, "*hello.txt", "gareth_says_hello.txt");
@@ -1205,6 +1334,17 @@ mod tests {
#[cfg(not(unix))]
matches!(matchslash5, "abc\\def", "abc/def", SLASHLIT);
matches!(matchbackslash1, "\\[", "[", BSESC);
matches!(matchbackslash2, "\\?", "?", BSESC);
matches!(matchbackslash3, "\\*", "*", BSESC);
matches!(matchbackslash4, "\\[a-z]", "\\a", NOBSESC);
matches!(matchbackslash5, "\\?", "\\a", NOBSESC);
matches!(matchbackslash6, "\\*", "\\\\", NOBSESC);
#[cfg(unix)]
matches!(matchbackslash7, "\\a", "a");
#[cfg(not(unix))]
matches!(matchbackslash8, "\\a", "/a");
nmatches!(matchnot1, "a*b*c", "abcd");
nmatches!(matchnot2, "abc*abc*abc", "abcabcabcabcabcabcabca");
nmatches!(matchnot3, "some/**/needle.txt", "some/other/notthis.txt");
@@ -1234,18 +1374,35 @@ mod tests {
nmatches!(matchnot25, "*.c", "mozilla-sha1/sha1.c", SLASHLIT);
nmatches!(matchnot26, "**/m4/ltoptions.m4",
"csharp/src/packages/repositories.config", SLASHLIT);
nmatches!(matchnot27, "a[^0-9]b", "a0b");
nmatches!(matchnot28, "a[^0-9]b", "a9b");
nmatches!(matchnot29, "[^-]", "-");
nmatches!(matchnot30, "some/*/needle.txt", "some/needle.txt");
nmatches!(
matchrec31,
"some/*/needle.txt", "some/one/two/needle.txt", SLASHLIT);
nmatches!(
matchrec32,
"some/*/needle.txt", "some/one/two/three/needle.txt", SLASHLIT);
macro_rules! extract {
($which:ident, $name:ident, $pat:expr, $expect:expr) => {
extract!($which, $name, $pat, $expect, Options::default());
};
($which:ident, $name:ident, $pat:expr, $expect:expr, $opts:expr) => {
($which:ident, $name:ident, $pat:expr, $expect:expr, $options:expr) => {
#[test]
fn $name() {
let pat = GlobBuilder::new($pat)
.case_insensitive($opts.casei)
.literal_separator($opts.litsep)
.build().unwrap();
let mut builder = GlobBuilder::new($pat);
if let Some(casei) = $options.casei {
builder.case_insensitive(casei);
}
if let Some(litsep) = $options.litsep {
builder.literal_separator(litsep);
}
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
let pat = builder.build().unwrap();
assert_eq!($expect, pat.$which());
}
};
@@ -1302,19 +1459,19 @@ mod tests {
Literal('f'), Literal('o'), ZeroOrMore, Literal('o'),
]), SLASHLIT);
ext!(extract_ext1, "**/*.rs", Some(os(".rs")));
ext!(extract_ext1, "**/*.rs", Some(s(".rs")));
ext!(extract_ext2, "**/*.rs.bak", None);
ext!(extract_ext3, "*.rs", Some(os(".rs")));
ext!(extract_ext3, "*.rs", Some(s(".rs")));
ext!(extract_ext4, "a*.rs", None);
ext!(extract_ext5, "/*.c", None);
ext!(extract_ext6, "*.c", None, SLASHLIT);
ext!(extract_ext7, "*.c", Some(os(".c")));
ext!(extract_ext7, "*.c", Some(s(".c")));
required_ext!(extract_req_ext1, "*.rs", Some(os(".rs")));
required_ext!(extract_req_ext2, "/foo/bar/*.rs", Some(os(".rs")));
required_ext!(extract_req_ext3, "/foo/bar/*.rs", Some(os(".rs")));
required_ext!(extract_req_ext4, "/foo/bar/.rs", Some(os(".rs")));
required_ext!(extract_req_ext5, ".rs", Some(os(".rs")));
required_ext!(extract_req_ext1, "*.rs", Some(s(".rs")));
required_ext!(extract_req_ext2, "/foo/bar/*.rs", Some(s(".rs")));
required_ext!(extract_req_ext3, "/foo/bar/*.rs", Some(s(".rs")));
required_ext!(extract_req_ext4, "/foo/bar/.rs", Some(s(".rs")));
required_ext!(extract_req_ext5, ".rs", Some(s(".rs")));
required_ext!(extract_req_ext6, "./rs", None);
required_ext!(extract_req_ext7, "foo", None);
required_ext!(extract_req_ext8, ".foo/", None);

166
globset/src/lib.rs
View File

@@ -22,7 +22,7 @@ This example shows how to match a single glob against a single file path.
# fn example() -> Result<(), globset::Error> {
use globset::Glob;
let glob = try!(Glob::new("*.rs")).compile_matcher();
let glob = Glob::new("*.rs")?.compile_matcher();
assert!(glob.is_match("foo.rs"));
assert!(glob.is_match("foo/bar.rs"));
@@ -39,8 +39,8 @@ semantics. In this example, we prevent wildcards from matching path separators.
# fn example() -> Result<(), globset::Error> {
use globset::GlobBuilder;
let glob = try!(GlobBuilder::new("*.rs")
.literal_separator(true).build()).compile_matcher();
let glob = GlobBuilder::new("*.rs")
.literal_separator(true).build()?.compile_matcher();
assert!(glob.is_match("foo.rs"));
assert!(!glob.is_match("foo/bar.rs")); // no longer matches
@@ -59,10 +59,10 @@ use globset::{Glob, GlobSetBuilder};
let mut builder = GlobSetBuilder::new();
// A GlobBuilder can be used to configure each glob's match semantics
// independently.
builder.add(try!(Glob::new("*.rs")));
builder.add(try!(Glob::new("src/lib.rs")));
builder.add(try!(Glob::new("src/**/foo.rs")));
let set = try!(builder.build());
builder.add(Glob::new("*.rs")?);
builder.add(Glob::new("src/lib.rs")?);
builder.add(Glob::new("src/**/foo.rs")?);
let set = builder.build()?;
assert_eq!(set.matches("src/bar/baz/foo.rs"), vec![0, 2]);
# Ok(()) } example().unwrap();
@@ -91,6 +91,11 @@ Standard Unix-style glob syntax is supported:
`[!ab]` to match any character except for `a` and `b`.
* Metacharacters such as `*` and `?` can be escaped with character class
notation. e.g., `[*]` matches `*`.
* When backslash escapes are enabled, a backslash (`\`) will escape all meta
characters in a glob. If it precedes a non-meta character, then the slash is
ignored. A `\\` will match a literal `\\`. Note that this mode is only
enabled on Unix platforms by default, but can be enabled on any platform
via the `backslash_escape` setting on `Glob`.
A `GlobBuilder` can be used to prevent wildcards from matching path separators,
or to enable case insensitive matching.
@@ -99,27 +104,25 @@ or to enable case insensitive matching.
#![deny(missing_docs)]
extern crate aho_corasick;
extern crate bstr;
extern crate fnv;
#[macro_use]
extern crate log;
extern crate memchr;
extern crate regex;
use std::borrow::Cow;
use std::collections::{BTreeMap, HashMap};
use std::error::Error as StdError;
use std::ffi::{OsStr, OsString};
use std::fmt;
use std::hash;
use std::path::Path;
use std::str;
use aho_corasick::{Automaton, AcAutomaton, FullAcAutomaton};
use aho_corasick::AhoCorasick;
use bstr::{B, BStr, BString};
use regex::bytes::{Regex, RegexBuilder, RegexSet};
use pathutil::{
file_name, file_name_ext, normalize_path, os_str_bytes, path_bytes,
};
use pathutil::{file_name, file_name_ext, normalize_path};
use glob::MatchStrategy;
pub use glob::{Glob, GlobBuilder, GlobMatcher};
@@ -138,8 +141,13 @@ pub struct Error {
/// The kind of error that can occur when parsing a glob pattern.
#[derive(Clone, Debug, Eq, PartialEq)]
pub enum ErrorKind {
/// Occurs when a use of `**` is invalid. Namely, `**` can only appear
/// adjacent to a path separator, or the beginning/end of a glob.
/// **DEPRECATED**.
///
/// This error used to occur for consistency with git's glob specification,
/// but the specification now accepts all uses of `**`. When `**` does not
/// appear adjacent to a path separator or at the beginning/end of a glob,
/// it is now treated as two consecutive `*` patterns. As such, this error
/// is no longer used.
InvalidRecursive,
/// Occurs when a character class (e.g., `[abc]`) is not closed.
UnclosedClass,
@@ -154,8 +162,17 @@ pub enum ErrorKind {
/// Occurs when an alternating group is nested inside another alternating
/// group, e.g., `{{a,b},{c,d}}`.
NestedAlternates,
/// Occurs when an unescaped '\' is found at the end of a glob.
DanglingEscape,
/// An error associated with parsing or compiling a regex.
Regex(String),
/// Hints that destructuring should not be exhaustive.
///
/// This enum may grow additional variants, so this makes sure clients
/// don't count on exhaustive matching. (Otherwise, adding a new variant
/// could break existing code.)
#[doc(hidden)]
__Nonexhaustive,
}
impl StdError for Error {
@@ -199,7 +216,11 @@ impl ErrorKind {
ErrorKind::NestedAlternates => {
"nested alternate groups are not allowed"
}
ErrorKind::DanglingEscape => {
"dangling '\\'"
}
ErrorKind::Regex(ref err) => err,
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}
@@ -223,12 +244,14 @@ impl fmt::Display for ErrorKind {
| ErrorKind::UnopenedAlternates
| ErrorKind::UnclosedAlternates
| ErrorKind::NestedAlternates
| ErrorKind::DanglingEscape
| ErrorKind::Regex(_) => {
write!(f, "{}", self.description())
}
ErrorKind::InvalidRange(s, e) => {
write!(f, "invalid range; '{}' > '{}'", s, e)
}
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}
@@ -268,12 +291,23 @@ pub struct GlobSet {
}
impl GlobSet {
/// Create an empty `GlobSet`. An empty set matches nothing.
#[inline]
pub fn empty() -> GlobSet {
GlobSet {
len: 0,
strats: vec![],
}
}
/// Returns true if this set is empty, and therefore matches nothing.
#[inline]
pub fn is_empty(&self) -> bool {
self.len == 0
}
/// Returns the number of globs in this set.
#[inline]
pub fn len(&self) -> usize {
self.len
}
@@ -412,8 +446,8 @@ impl GlobSet {
GlobSetMatchStrategy::Suffix(suffixes.suffix()),
GlobSetMatchStrategy::Prefix(prefixes.prefix()),
GlobSetMatchStrategy::RequiredExtension(
try!(required_exts.build())),
GlobSetMatchStrategy::Regex(try!(regexes.regex_set())),
required_exts.build()?),
GlobSetMatchStrategy::Regex(regexes.regex_set()?),
],
})
}
@@ -421,6 +455,7 @@ impl GlobSet {
/// GlobSetBuilder builds a group of patterns that can be used to
/// simultaneously match a file path.
#[derive(Clone, Debug)]
pub struct GlobSetBuilder {
pats: Vec<Glob>,
}
@@ -441,7 +476,6 @@ impl GlobSetBuilder {
}
/// Add a new pattern to this set.
#[allow(dead_code)]
pub fn add(&mut self, pat: Glob) -> &mut GlobSetBuilder {
self.pats.push(pat);
self
@@ -456,24 +490,25 @@ impl GlobSetBuilder {
/// path against multiple globs or sets of globs.
#[derive(Clone, Debug)]
pub struct Candidate<'a> {
path: Cow<'a, [u8]>,
basename: Cow<'a, [u8]>,
ext: &'a OsStr,
path: Cow<'a, BStr>,
basename: Cow<'a, BStr>,
ext: Cow<'a, BStr>,
}
impl<'a> Candidate<'a> {
/// Create a new candidate for matching from the given path.
pub fn new<P: AsRef<Path> + ?Sized>(path: &'a P) -> Candidate<'a> {
let path = path.as_ref();
let basename = file_name(path).unwrap_or(OsStr::new(""));
let path = normalize_path(BString::from_path_lossy(path.as_ref()));
let basename = file_name(&path).unwrap_or(Cow::Borrowed(B("")));
let ext = file_name_ext(&basename).unwrap_or(Cow::Borrowed(B("")));
Candidate {
path: normalize_path(path_bytes(path)),
basename: os_str_bytes(basename),
ext: file_name_ext(basename).unwrap_or(OsStr::new("")),
path: path,
basename: basename,
ext: ext,
}
}
fn path_prefix(&self, max: usize) -> &[u8] {
fn path_prefix(&self, max: usize) -> &BStr {
if self.path.len() <= max {
&*self.path
} else {
@@ -481,7 +516,7 @@ impl<'a> Candidate<'a> {
}
}
fn path_suffix(&self, max: usize) -> &[u8] {
fn path_suffix(&self, max: usize) -> &BStr {
if self.path.len() <= max {
&*self.path
} else {
@@ -542,12 +577,12 @@ impl LiteralStrategy {
}
fn is_match(&self, candidate: &Candidate) -> bool {
self.0.contains_key(&*candidate.path)
self.0.contains_key(candidate.path.as_bytes())
}
#[inline(never)]
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
if let Some(hits) = self.0.get(&*candidate.path) {
if let Some(hits) = self.0.get(candidate.path.as_bytes()) {
matches.extend(hits);
}
}
@@ -569,7 +604,7 @@ impl BasenameLiteralStrategy {
if candidate.basename.is_empty() {
return false;
}
self.0.contains_key(&*candidate.basename)
self.0.contains_key(candidate.basename.as_bytes())
}
#[inline(never)]
@@ -577,29 +612,29 @@ impl BasenameLiteralStrategy {
if candidate.basename.is_empty() {
return;
}
if let Some(hits) = self.0.get(&*candidate.basename) {
if let Some(hits) = self.0.get(candidate.basename.as_bytes()) {
matches.extend(hits);
}
}
}
#[derive(Clone, Debug)]
struct ExtensionStrategy(HashMap<OsString, Vec<usize>, Fnv>);
struct ExtensionStrategy(HashMap<Vec<u8>, Vec<usize>, Fnv>);
impl ExtensionStrategy {
fn new() -> ExtensionStrategy {
ExtensionStrategy(HashMap::with_hasher(Fnv::default()))
}
fn add(&mut self, global_index: usize, ext: OsString) {
self.0.entry(ext).or_insert(vec![]).push(global_index);
fn add(&mut self, global_index: usize, ext: String) {
self.0.entry(ext.into_bytes()).or_insert(vec![]).push(global_index);
}
fn is_match(&self, candidate: &Candidate) -> bool {
if candidate.ext.is_empty() {
return false;
}
self.0.contains_key(candidate.ext)
self.0.contains_key(candidate.ext.as_bytes())
}
#[inline(never)]
@@ -607,7 +642,7 @@ impl ExtensionStrategy {
if candidate.ext.is_empty() {
return;
}
if let Some(hits) = self.0.get(candidate.ext) {
if let Some(hits) = self.0.get(candidate.ext.as_bytes()) {
matches.extend(hits);
}
}
@@ -615,7 +650,7 @@ impl ExtensionStrategy {
#[derive(Clone, Debug)]
struct PrefixStrategy {
matcher: FullAcAutomaton<Vec<u8>>,
matcher: AhoCorasick,
map: Vec<usize>,
longest: usize,
}
@@ -623,8 +658,8 @@ struct PrefixStrategy {
impl PrefixStrategy {
fn is_match(&self, candidate: &Candidate) -> bool {
let path = candidate.path_prefix(self.longest);
for m in self.matcher.find_overlapping(path) {
if m.start == 0 {
for m in self.matcher.find_overlapping_iter(path) {
if m.start() == 0 {
return true;
}
}
@@ -633,9 +668,9 @@ impl PrefixStrategy {
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
let path = candidate.path_prefix(self.longest);
for m in self.matcher.find_overlapping(path) {
if m.start == 0 {
matches.push(self.map[m.pati]);
for m in self.matcher.find_overlapping_iter(path) {
if m.start() == 0 {
matches.push(self.map[m.pattern()]);
}
}
}
@@ -643,7 +678,7 @@ impl PrefixStrategy {
#[derive(Clone, Debug)]
struct SuffixStrategy {
matcher: FullAcAutomaton<Vec<u8>>,
matcher: AhoCorasick,
map: Vec<usize>,
longest: usize,
}
@@ -651,8 +686,8 @@ struct SuffixStrategy {
impl SuffixStrategy {
fn is_match(&self, candidate: &Candidate) -> bool {
let path = candidate.path_suffix(self.longest);
for m in self.matcher.find_overlapping(path) {
if m.end == path.len() {
for m in self.matcher.find_overlapping_iter(path) {
if m.end() == path.len() {
return true;
}
}
@@ -661,27 +696,27 @@ impl SuffixStrategy {
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
let path = candidate.path_suffix(self.longest);
for m in self.matcher.find_overlapping(path) {
if m.end == path.len() {
matches.push(self.map[m.pati]);
for m in self.matcher.find_overlapping_iter(path) {
if m.end() == path.len() {
matches.push(self.map[m.pattern()]);
}
}
}
}
#[derive(Clone, Debug)]
struct RequiredExtensionStrategy(HashMap<OsString, Vec<(usize, Regex)>, Fnv>);
struct RequiredExtensionStrategy(HashMap<Vec<u8>, Vec<(usize, Regex)>, Fnv>);
impl RequiredExtensionStrategy {
fn is_match(&self, candidate: &Candidate) -> bool {
if candidate.ext.is_empty() {
return false;
}
match self.0.get(candidate.ext) {
match self.0.get(candidate.ext.as_bytes()) {
None => false,
Some(regexes) => {
for &(_, ref re) in regexes {
if re.is_match(&*candidate.path) {
if re.is_match(candidate.path.as_bytes()) {
return true;
}
}
@@ -695,9 +730,9 @@ impl RequiredExtensionStrategy {
if candidate.ext.is_empty() {
return;
}
if let Some(regexes) = self.0.get(candidate.ext) {
if let Some(regexes) = self.0.get(candidate.ext.as_bytes()) {
for &(global_index, ref re) in regexes {
if re.is_match(&*candidate.path) {
if re.is_match(candidate.path.as_bytes()) {
matches.push(global_index);
}
}
@@ -713,11 +748,11 @@ struct RegexSetStrategy {
impl RegexSetStrategy {
fn is_match(&self, candidate: &Candidate) -> bool {
self.matcher.is_match(&*candidate.path)
self.matcher.is_match(candidate.path.as_bytes())
}
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
for i in self.matcher.matches(&*candidate.path) {
for i in self.matcher.matches(candidate.path.as_bytes()) {
matches.push(self.map[i]);
}
}
@@ -748,18 +783,16 @@ impl MultiStrategyBuilder {
}
fn prefix(self) -> PrefixStrategy {
let it = self.literals.into_iter().map(|s| s.into_bytes());
PrefixStrategy {
matcher: AcAutomaton::new(it).into_full(),
matcher: AhoCorasick::new_auto_configured(&self.literals),
map: self.map,
longest: self.longest,
}
}
fn suffix(self) -> SuffixStrategy {
let it = self.literals.into_iter().map(|s| s.into_bytes());
SuffixStrategy {
matcher: AcAutomaton::new(it).into_full(),
matcher: AhoCorasick::new_auto_configured(&self.literals),
map: self.map,
longest: self.longest,
}
@@ -767,7 +800,7 @@ impl MultiStrategyBuilder {
fn regex_set(self) -> Result<RegexSetStrategy, Error> {
Ok(RegexSetStrategy {
matcher: try!(new_regex_set(self.literals)),
matcher: new_regex_set(self.literals)?,
map: self.map,
})
}
@@ -775,7 +808,7 @@ impl MultiStrategyBuilder {
#[derive(Clone, Debug)]
struct RequiredExtensionStrategyBuilder(
HashMap<OsString, Vec<(usize, String)>>,
HashMap<Vec<u8>, Vec<(usize, String)>>,
);
impl RequiredExtensionStrategyBuilder {
@@ -783,8 +816,11 @@ impl RequiredExtensionStrategyBuilder {
RequiredExtensionStrategyBuilder(HashMap::new())
}
fn add(&mut self, global_index: usize, ext: OsString, regex: String) {
self.0.entry(ext).or_insert(vec![]).push((global_index, regex));
fn add(&mut self, global_index: usize, ext: String, regex: String) {
self.0
.entry(ext.into_bytes())
.or_insert(vec![])
.push((global_index, regex));
}
fn build(self) -> Result<RequiredExtensionStrategy, Error> {
@@ -792,7 +828,7 @@ impl RequiredExtensionStrategyBuilder {
for (ext, regexes) in self.0.into_iter() {
exts.insert(ext.clone(), vec![]);
for (global_index, regex) in regexes {
let compiled = try!(new_regex(&regex));
let compiled = new_regex(&regex)?;
exts.get_mut(&ext).unwrap().push((global_index, compiled));
}
}

117
globset/src/pathutil.rs
View File

@@ -1,41 +1,26 @@
use std::borrow::Cow;
use std::ffi::OsStr;
use std::path::Path;
use bstr::BStr;
/// The final component of the path, if it is a normal file.
///
/// If the path terminates in ., .., or consists solely of a root of prefix,
/// file_name will return None.
#[cfg(unix)]
pub fn file_name<'a, P: AsRef<Path> + ?Sized>(
path: &'a P,
) -> Option<&'a OsStr> {
use std::os::unix::ffi::OsStrExt;
use memchr::memrchr;
let path = path.as_ref().as_os_str().as_bytes();
pub fn file_name<'a>(path: &Cow<'a, BStr>) -> Option<Cow<'a, BStr>> {
if path.is_empty() {
return None;
} else if path.len() == 1 && path[0] == b'.' {
return None;
} else if path.last() == Some(&b'.') {
return None;
} else if path.len() >= 2 && &path[path.len() - 2..] == &b".."[..] {
} else if path.last() == Some(b'.') {
return None;
}
let last_slash = memrchr(b'/', path).map(|i| i + 1).unwrap_or(0);
Some(OsStr::from_bytes(&path[last_slash..]))
}
/// The final component of the path, if it is a normal file.
///
/// If the path terminates in ., .., or consists solely of a root of prefix,
/// file_name will return None.
#[cfg(not(unix))]
pub fn file_name<'a, P: AsRef<Path> + ?Sized>(
path: &'a P,
) -> Option<&'a OsStr> {
path.as_ref().file_name()
let last_slash = path.rfind_byte(b'/').map(|i| i + 1).unwrap_or(0);
Some(match *path {
Cow::Borrowed(path) => Cow::Borrowed(&path[last_slash..]),
Cow::Owned(ref path) => {
let mut path = path.clone();
path.drain_bytes(..last_slash);
Cow::Owned(path)
}
})
}
/// Return a file extension given a path's file name.
@@ -54,65 +39,28 @@ pub fn file_name<'a, P: AsRef<Path> + ?Sized>(
/// a pattern like `*.rs` is obviously trying to match files with a `rs`
/// extension, but it also matches files like `.rs`, which doesn't have an
/// extension according to std::path::Path::extension.
pub fn file_name_ext(name: &OsStr) -> Option<&OsStr> {
// Yes, these functions are awful, and yes, we are completely violating
// the abstraction barrier of std::ffi. The barrier we're violating is
// that an OsStr's encoding is *ASCII compatible*. While this is obviously
// true on Unix systems, it's also true on Windows because an OsStr uses
// WTF-8 internally: https://simonsapin.github.io/wtf-8/
//
// We should consider doing the same for the other path utility functions.
// Right now, we don't break any barriers, but Windows users are paying
// for it.
//
// Got any better ideas that don't cost anything? Hit me up. ---AG
unsafe fn os_str_as_u8_slice(s: &OsStr) -> &[u8] {
::std::mem::transmute(s)
}
unsafe fn u8_slice_as_os_str(s: &[u8]) -> &OsStr {
::std::mem::transmute(s)
}
pub fn file_name_ext<'a>(name: &Cow<'a, BStr>) -> Option<Cow<'a, BStr>> {
if name.is_empty() {
return None;
}
let name = unsafe { os_str_as_u8_slice(name) };
for (i, &b) in name.iter().enumerate().rev() {
if b == b'.' {
return Some(unsafe { u8_slice_as_os_str(&name[i..]) });
let last_dot_at = match name.rfind_byte(b'.') {
None => return None,
Some(i) => i,
};
Some(match *name {
Cow::Borrowed(name) => Cow::Borrowed(&name[last_dot_at..]),
Cow::Owned(ref name) => {
let mut name = name.clone();
name.drain_bytes(..last_dot_at);
Cow::Owned(name)
}
}
None
}
/// Return raw bytes of a path, transcoded to UTF-8 if necessary.
pub fn path_bytes(path: &Path) -> Cow<[u8]> {
os_str_bytes(path.as_os_str())
}
/// Return the raw bytes of the given OS string, possibly transcoded to UTF-8.
#[cfg(unix)]
pub fn os_str_bytes(s: &OsStr) -> Cow<[u8]> {
use std::os::unix::ffi::OsStrExt;
Cow::Borrowed(s.as_bytes())
}
/// Return the raw bytes of the given OS string, possibly transcoded to UTF-8.
#[cfg(not(unix))]
pub fn os_str_bytes(s: &OsStr) -> Cow<[u8]> {
// TODO(burntsushi): On Windows, OS strings are WTF-8, which is a superset
// of UTF-8, so even if we could get at the raw bytes, they wouldn't
// be useful. We *must* convert to UTF-8 before doing path matching.
// Unfortunate, but necessary.
match s.to_string_lossy() {
Cow::Owned(s) => Cow::Owned(s.into_bytes()),
Cow::Borrowed(s) => Cow::Borrowed(s.as_bytes()),
}
})
}
/// Normalizes a path to use `/` as a separator everywhere, even on platforms
/// that recognize other characters as separators.
#[cfg(unix)]
pub fn normalize_path(path: Cow<[u8]>) -> Cow<[u8]> {
pub fn normalize_path(path: Cow<BStr>) -> Cow<BStr> {
// UNIX only uses /, so we're good.
path
}
@@ -120,7 +68,7 @@ pub fn normalize_path(path: Cow<[u8]>) -> Cow<[u8]> {
/// Normalizes a path to use `/` as a separator everywhere, even on platforms
/// that recognize other characters as separators.
#[cfg(not(unix))]
pub fn normalize_path(mut path: Cow<[u8]>) -> Cow<[u8]> {
pub fn normalize_path(mut path: Cow<BStr>) -> Cow<BStr> {
use std::path::is_separator;
for i in 0..path.len() {
@@ -135,7 +83,8 @@ pub fn normalize_path(mut path: Cow<[u8]>) -> Cow<[u8]> {
#[cfg(test)]
mod tests {
use std::borrow::Cow;
use std::ffi::OsStr;
use bstr::{B, BString};
use super::{file_name_ext, normalize_path};
@@ -143,8 +92,9 @@ mod tests {
($name:ident, $file_name:expr, $ext:expr) => {
#[test]
fn $name() {
let got = file_name_ext(OsStr::new($file_name));
assert_eq!($ext.map(OsStr::new), got);
let bs = BString::from($file_name);
let got = file_name_ext(&Cow::Owned(bs));
assert_eq!($ext.map(|s| Cow::Borrowed(B(s))), got);
}
};
}
@@ -159,7 +109,8 @@ mod tests {
($name:ident, $path:expr, $expected:expr) => {
#[test]
fn $name() {
let got = normalize_path(Cow::Owned($path.to_vec()));
let bs = BString::from_slice($path);
let got = normalize_path(Cow::Owned(bs));
assert_eq!($expected.to_vec(), got.into_owned());
}
};

26
grep-cli/Cargo.toml Normal file
View File

@@ -0,0 +1,26 @@
[package]
name = "grep-cli"
version = "0.1.1" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Utilities for search oriented command line applications.
"""
documentation = "https://docs.rs/grep-cli"
homepage = "https://github.com/BurntSushi/ripgrep"
repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["regex", "grep", "cli", "utility", "util"]
license = "Unlicense/MIT"
[dependencies]
atty = "0.2.11"
bstr = "0.1.2"
globset = { version = "0.4.2", path = "../globset" }
lazy_static = "1.1.0"
log = "0.4.5"
regex = "1.1"
same-file = "1.0.4"
termcolor = "1.0.4"
[target.'cfg(windows)'.dependencies.winapi-util]
version = "0.1.1"

0
termcolor/LICENSE-MIT → grep-cli/LICENSE-MIT
View File

38
grep-cli/README.md Normal file
View File

@@ -0,0 +1,38 @@
grep-cli
--------
A utility library that provides common routines desired in search oriented
command line applications. This includes, but is not limited to, parsing hex
escapes, detecting whether stdin is readable and more. To the extent possible,
this crate strives for compatibility across Windows, macOS and Linux.
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/grep-cli.svg)](https://crates.io/crates/grep-cli)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
### Documentation
[https://docs.rs/grep-cli](https://docs.rs/grep-cli)
**NOTE:** You probably don't want to use this crate directly. Instead, you
should prefer the facade defined in the
[`grep`](https://docs.rs/grep)
crate.
### Usage
Add this to your `Cargo.toml`:
```toml
[dependencies]
grep-cli = "0.1"
```
and this to your crate root:
```rust
extern crate grep_cli;
```

0
termcolor/UNLICENSE → grep-cli/UNLICENSE
View File

382
grep-cli/src/decompress.rs Normal file
View File

@@ -0,0 +1,382 @@
use std::ffi::{OsStr, OsString};
use std::fs::File;
use std::io;
use std::path::Path;
use std::process::Command;
use globset::{Glob, GlobSet, GlobSetBuilder};
use process::{CommandError, CommandReader, CommandReaderBuilder};
/// A builder for a matcher that determines which files get decompressed.
#[derive(Clone, Debug)]
pub struct DecompressionMatcherBuilder {
/// The commands for each matching glob.
commands: Vec<DecompressionCommand>,
/// Whether to include the default matching rules.
defaults: bool,
}
/// A representation of a single command for decompressing data
/// out-of-proccess.
#[derive(Clone, Debug)]
struct DecompressionCommand {
/// The glob that matches this command.
glob: String,
/// The command or binary name.
bin: OsString,
/// The arguments to invoke with the command.
args: Vec<OsString>,
}
impl Default for DecompressionMatcherBuilder {
fn default() -> DecompressionMatcherBuilder {
DecompressionMatcherBuilder::new()
}
}
impl DecompressionMatcherBuilder {
/// Create a new builder for configuring a decompression matcher.
pub fn new() -> DecompressionMatcherBuilder {
DecompressionMatcherBuilder {
commands: vec![],
defaults: true,
}
}
/// Build a matcher for determining how to decompress files.
///
/// If there was a problem compiling the matcher, then an error is
/// returned.
pub fn build(&self) -> Result<DecompressionMatcher, CommandError> {
let defaults =
if !self.defaults {
vec![]
} else {
default_decompression_commands()
};
let mut glob_builder = GlobSetBuilder::new();
let mut commands = vec![];
for decomp_cmd in defaults.iter().chain(&self.commands) {
let glob = Glob::new(&decomp_cmd.glob).map_err(|err| {
CommandError::io(io::Error::new(io::ErrorKind::Other, err))
})?;
glob_builder.add(glob);
commands.push(decomp_cmd.clone());
}
let globs = glob_builder.build().map_err(|err| {
CommandError::io(io::Error::new(io::ErrorKind::Other, err))
})?;
Ok(DecompressionMatcher { globs, commands })
}
/// When enabled, the default matching rules will be compiled into this
/// matcher before any other associations. When disabled, only the
/// rules explicitly given to this builder will be used.
///
/// This is enabled by default.
pub fn defaults(&mut self, yes: bool) -> &mut DecompressionMatcherBuilder {
self.defaults = yes;
self
}
/// Associates a glob with a command to decompress files matching the glob.
///
/// If multiple globs match the same file, then the most recently added
/// glob takes precedence.
///
/// The syntax for the glob is documented in the
/// [`globset` crate](https://docs.rs/globset/#syntax).
pub fn associate<P, I, A>(
&mut self,
glob: &str,
program: P,
args: I,
) -> &mut DecompressionMatcherBuilder
where P: AsRef<OsStr>,
I: IntoIterator<Item=A>,
A: AsRef<OsStr>,
{
let glob = glob.to_string();
let bin = program.as_ref().to_os_string();
let args = args
.into_iter()
.map(|a| a.as_ref().to_os_string())
.collect();
self.commands.push(DecompressionCommand { glob, bin, args });
self
}
}
/// A matcher for determining how to decompress files.
#[derive(Clone, Debug)]
pub struct DecompressionMatcher {
/// The set of globs to match. Each glob has a corresponding entry in
/// `commands`. When a glob matches, the corresponding command should be
/// used to perform out-of-process decompression.
globs: GlobSet,
/// The commands for each matching glob.
commands: Vec<DecompressionCommand>,
}
impl Default for DecompressionMatcher {
fn default() -> DecompressionMatcher {
DecompressionMatcher::new()
}
}
impl DecompressionMatcher {
/// Create a new matcher with default rules.
///
/// To add more matching rules, build a matcher with
/// [`DecompressionMatcherBuilder`](struct.DecompressionMatcherBuilder.html).
pub fn new() -> DecompressionMatcher {
DecompressionMatcherBuilder::new()
.build()
.expect("built-in matching rules should always compile")
}
/// Return a pre-built command based on the given file path that can
/// decompress its contents. If no such decompressor is known, then this
/// returns `None`.
///
/// If there are multiple possible commands matching the given path, then
/// the command added last takes precedence.
pub fn command<P: AsRef<Path>>(&self, path: P) -> Option<Command> {
for i in self.globs.matches(path).into_iter().rev() {
let decomp_cmd = &self.commands[i];
let mut cmd = Command::new(&decomp_cmd.bin);
cmd.args(&decomp_cmd.args);
return Some(cmd);
}
None
}
/// Returns true if and only if the given file path has at least one
/// matching command to perform decompression on.
pub fn has_command<P: AsRef<Path>>(&self, path: P) -> bool {
self.globs.is_match(path)
}
}
/// Configures and builds a streaming reader for decompressing data.
#[derive(Clone, Debug, Default)]
pub struct DecompressionReaderBuilder {
matcher: DecompressionMatcher,
command_builder: CommandReaderBuilder,
}
impl DecompressionReaderBuilder {
/// Create a new builder with the default configuration.
pub fn new() -> DecompressionReaderBuilder {
DecompressionReaderBuilder::default()
}
/// Build a new streaming reader for decompressing data.
///
/// If decompression is done out-of-process and if there was a problem
/// spawning the process, then its error is logged at the debug level and a
/// passthru reader is returned that does no decompression. This behavior
/// typically occurs when the given file path matches a decompression
/// command, but is executing in an environment where the decompression
/// command is not available.
///
/// If the given file path could not be matched with a decompression
/// strategy, then a passthru reader is returned that does no
/// decompression.
pub fn build<P: AsRef<Path>>(
&self,
path: P,
) -> Result<DecompressionReader, CommandError> {
let path = path.as_ref();
let mut cmd = match self.matcher.command(path) {
None => return DecompressionReader::new_passthru(path),
Some(cmd) => cmd,
};
cmd.arg(path);
match self.command_builder.build(&mut cmd) {
Ok(cmd_reader) => Ok(DecompressionReader { rdr: Ok(cmd_reader) }),
Err(err) => {
debug!(
"{}: error spawning command '{:?}': {} \
(falling back to uncompressed reader)",
path.display(),
cmd,
err,
);
DecompressionReader::new_passthru(path)
}
}
}
/// Set the matcher to use to look up the decompression command for each
/// file path.
///
/// A set of sensible rules is enabled by default. Setting this will
/// completely replace the current rules.
pub fn matcher(
&mut self,
matcher: DecompressionMatcher,
) -> &mut DecompressionReaderBuilder {
self.matcher = matcher;
self
}
/// Get the underlying matcher currently used by this builder.
pub fn get_matcher(&self) -> &DecompressionMatcher {
&self.matcher
}
/// When enabled, the reader will asynchronously read the contents of the
/// command's stderr output. When disabled, stderr is only read after the
/// stdout stream has been exhausted (or if the process quits with an error
/// code).
///
/// Note that when enabled, this may require launching an additional
/// thread in order to read stderr. This is done so that the process being
/// executed is never blocked from writing to stdout or stderr. If this is
/// disabled, then it is possible for the process to fill up the stderr
/// buffer and deadlock.
///
/// This is enabled by default.
pub fn async_stderr(
&mut self,
yes: bool,
) -> &mut DecompressionReaderBuilder {
self.command_builder.async_stderr(yes);
self
}
}
/// A streaming reader for decompressing the contents of a file.
///
/// The purpose of this reader is to provide a seamless way to decompress the
/// contents of file using existing tools in the current environment. This is
/// meant to be an alternative to using decompression libraries in favor of the
/// simplicity and portability of using external commands such as `gzip` and
/// `xz`. This does impose the overhead of spawning a process, so other means
/// for performing decompression should be sought if this overhead isn't
/// acceptable.
///
/// A decompression reader comes with a default set of matching rules that are
/// meant to associate file paths with the corresponding command to use to
/// decompress them. For example, a glob like `*.gz` matches gzip compressed
/// files with the command `gzip -d -c`. If a file path does not match any
/// existing rules, or if it matches a rule whose command does not exist in the
/// current environment, then the decompression reader passes through the
/// contents of the underlying file without doing any decompression.
///
/// The default matching rules are probably good enough for most cases, and if
/// they require revision, pull requests are welcome. In cases where they must
/// be changed or extended, they can be customized through the use of
/// [`DecompressionMatcherBuilder`](struct.DecompressionMatcherBuilder.html)
/// and
/// [`DecompressionReaderBuilder`](struct.DecompressionReaderBuilder.html).
///
/// By default, this reader will asynchronously read the processes' stderr.
/// This prevents subtle deadlocking bugs for noisy processes that write a lot
/// to stderr. Currently, the entire contents of stderr is read on to the heap.
///
/// # Example
///
/// This example shows how to read the decompressed contents of a file without
/// needing to explicitly choose the decompression command to run.
///
/// Note that if you need to decompress multiple files, it is better to use
/// `DecompressionReaderBuilder`, which will amortize the cost of compiling the
/// matcher.
///
/// ```no_run
/// use std::io::Read;
/// use std::process::Command;
/// use grep_cli::DecompressionReader;
///
/// # fn example() -> Result<(), Box<::std::error::Error>> {
/// let mut rdr = DecompressionReader::new("/usr/share/man/man1/ls.1.gz")?;
/// let mut contents = vec![];
/// rdr.read_to_end(&mut contents)?;
/// # Ok(()) }
/// ```
#[derive(Debug)]
pub struct DecompressionReader {
rdr: Result<CommandReader, File>,
}
impl DecompressionReader {
/// Build a new streaming reader for decompressing data.
///
/// If decompression is done out-of-process and if there was a problem
/// spawning the process, then its error is returned.
///
/// If the given file path could not be matched with a decompression
/// strategy, then a passthru reader is returned that does no
/// decompression.
///
/// This uses the default matching rules for determining how to decompress
/// the given file. To change those matching rules, use
/// [`DecompressionReaderBuilder`](struct.DecompressionReaderBuilder.html)
/// and
/// [`DecompressionMatcherBuilder`](struct.DecompressionMatcherBuilder.html).
///
/// When creating readers for many paths. it is better to use the builder
/// since it will amortize the cost of constructing the matcher.
pub fn new<P: AsRef<Path>>(
path: P,
) -> Result<DecompressionReader, CommandError> {
DecompressionReaderBuilder::new().build(path)
}
/// Creates a new "passthru" decompression reader that reads from the file
/// corresponding to the given path without doing decompression and without
/// executing another process.
fn new_passthru(path: &Path) -> Result<DecompressionReader, CommandError> {
let file = File::open(path)?;
Ok(DecompressionReader { rdr: Err(file) })
}
}
impl io::Read for DecompressionReader {
fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
match self.rdr {
Ok(ref mut rdr) => rdr.read(buf),
Err(ref mut rdr) => rdr.read(buf),
}
}
}
fn default_decompression_commands() -> Vec<DecompressionCommand> {
const ARGS_GZIP: &[&str] = &["gzip", "-d", "-c"];
const ARGS_BZIP: &[&str] = &["bzip2", "-d", "-c"];
const ARGS_XZ: &[&str] = &["xz", "-d", "-c"];
const ARGS_LZ4: &[&str] = &["lz4", "-d", "-c"];
const ARGS_LZMA: &[&str] = &["xz", "--format=lzma", "-d", "-c"];
const ARGS_BROTLI: &[&str] = &["brotli", "-d", "-c"];
const ARGS_ZSTD: &[&str] = &["zstd", "-q", "-d", "-c"];
fn cmd(glob: &str, args: &[&str]) -> DecompressionCommand {
DecompressionCommand {
glob: glob.to_string(),
bin: OsStr::new(&args[0]).to_os_string(),
args: args
.iter()
.skip(1)
.map(|s| OsStr::new(s).to_os_string())
.collect(),
}
}
vec![
cmd("*.gz", ARGS_GZIP),
cmd("*.tgz", ARGS_GZIP),
cmd("*.bz2", ARGS_BZIP),
cmd("*.tbz2", ARGS_BZIP),
cmd("*.xz", ARGS_XZ),
cmd("*.txz", ARGS_XZ),
cmd("*.lz4", ARGS_LZ4),
cmd("*.lzma", ARGS_LZMA),
cmd("*.br", ARGS_BROTLI),
cmd("*.zst", ARGS_ZSTD),
cmd("*.zstd", ARGS_ZSTD),
]
}

263
grep-cli/src/escape.rs Normal file
View File

@@ -0,0 +1,263 @@
use std::ffi::OsStr;
use std::str;
use bstr::{BStr, BString};
/// A single state in the state machine used by `unescape`.
#[derive(Clone, Copy, Eq, PartialEq)]
enum State {
/// The state after seeing a `\`.
Escape,
/// The state after seeing a `\x`.
HexFirst,
/// The state after seeing a `\x[0-9A-Fa-f]`.
HexSecond(char),
/// Default state.
Literal,
}
/// Escapes arbitrary bytes into a human readable string.
///
/// This converts `\t`, `\r` and `\n` into their escaped forms. It also
/// converts the non-printable subset of ASCII in addition to invalid UTF-8
/// bytes to hexadecimal escape sequences. Everything else is left as is.
///
/// The dual of this routine is [`unescape`](fn.unescape.html).
///
/// # Example
///
/// This example shows how to convert a byte string that contains a `\n` and
/// invalid UTF-8 bytes into a `String`.
///
/// Pay special attention to the use of raw strings. That is, `r"\n"` is
/// equivalent to `"\\n"`.
///
/// ```
/// use grep_cli::escape;
///
/// assert_eq!(r"foo\nbar\xFFbaz", escape(b"foo\nbar\xFFbaz"));
/// ```
pub fn escape(bytes: &[u8]) -> String {
let bytes = BStr::new(bytes);
let mut escaped = String::new();
for (s, e, ch) in bytes.char_indices() {
if ch == '\u{FFFD}' {
for b in bytes[s..e].bytes() {
escape_byte(b, &mut escaped);
}
} else {
escape_char(ch, &mut escaped);
}
}
escaped
}
/// Escapes an OS string into a human readable string.
///
/// This is like [`escape`](fn.escape.html), but accepts an OS string.
pub fn escape_os(string: &OsStr) -> String {
escape(BString::from_os_str_lossy(string).as_bytes())
}
/// Unescapes a string.
///
/// It supports a limited set of escape sequences:
///
/// * `\t`, `\r` and `\n` are mapped to their corresponding ASCII bytes.
/// * `\xZZ` hexadecimal escapes are mapped to their byte.
///
/// Everything else is left as is, including non-hexadecimal escapes like
/// `\xGG`.
///
/// This is useful when it is desirable for a command line argument to be
/// capable of specifying arbitrary bytes or otherwise make it easier to
/// specify non-printable characters.
///
/// The dual of this routine is [`escape`](fn.escape.html).
///
/// # Example
///
/// This example shows how to convert an escaped string (which is valid UTF-8)
/// into a corresponding sequence of bytes. Each escape sequence is mapped to
/// its bytes, which may include invalid UTF-8.
///
/// Pay special attention to the use of raw strings. That is, `r"\n"` is
/// equivalent to `"\\n"`.
///
/// ```
/// use grep_cli::unescape;
///
/// assert_eq!(&b"foo\nbar\xFFbaz"[..], &*unescape(r"foo\nbar\xFFbaz"));
/// ```
pub fn unescape(s: &str) -> Vec<u8> {
use self::State::*;
let mut bytes = vec![];
let mut state = Literal;
for c in s.chars() {
match state {
Escape => {
match c {
'\\' => { bytes.push(b'\\'); state = Literal; }
'n' => { bytes.push(b'\n'); state = Literal; }
'r' => { bytes.push(b'\r'); state = Literal; }
't' => { bytes.push(b'\t'); state = Literal; }
'x' => { state = HexFirst; }
c => {
bytes.extend(format!(r"\{}", c).into_bytes());
state = Literal;
}
}
}
HexFirst => {
match c {
'0'...'9' | 'A'...'F' | 'a'...'f' => {
state = HexSecond(c);
}
c => {
bytes.extend(format!(r"\x{}", c).into_bytes());
state = Literal;
}
}
}
HexSecond(first) => {
match c {
'0'...'9' | 'A'...'F' | 'a'...'f' => {
let ordinal = format!("{}{}", first, c);
let byte = u8::from_str_radix(&ordinal, 16).unwrap();
bytes.push(byte);
state = Literal;
}
c => {
let original = format!(r"\x{}{}", first, c);
bytes.extend(original.into_bytes());
state = Literal;
}
}
}
Literal => {
match c {
'\\' => { state = Escape; }
c => { bytes.extend(c.to_string().as_bytes()); }
}
}
}
}
match state {
Escape => bytes.push(b'\\'),
HexFirst => bytes.extend(b"\\x"),
HexSecond(c) => bytes.extend(format!("\\x{}", c).into_bytes()),
Literal => {}
}
bytes
}
/// Unescapes an OS string.
///
/// This is like [`unescape`](fn.unescape.html), but accepts an OS string.
///
/// Note that this first lossily decodes the given OS string as UTF-8. That
/// is, an escaped string (the thing given) should be valid UTF-8.
pub fn unescape_os(string: &OsStr) -> Vec<u8> {
unescape(&string.to_string_lossy())
}
/// Adds the given codepoint to the given string, escaping it if necessary.
fn escape_char(cp: char, into: &mut String) {
if cp.is_ascii() {
escape_byte(cp as u8, into);
} else {
into.push(cp);
}
}
/// Adds the given byte to the given string, escaping it if necessary.
fn escape_byte(byte: u8, into: &mut String) {
match byte {
0x21...0x5B | 0x5D...0x7D => into.push(byte as char),
b'\n' => into.push_str(r"\n"),
b'\r' => into.push_str(r"\r"),
b'\t' => into.push_str(r"\t"),
b'\\' => into.push_str(r"\\"),
_ => into.push_str(&format!(r"\x{:02X}", byte)),
}
}
#[cfg(test)]
mod tests {
use super::{escape, unescape};
fn b(bytes: &'static [u8]) -> Vec<u8> {
bytes.to_vec()
}
#[test]
fn empty() {
assert_eq!(b(b""), unescape(r""));
assert_eq!(r"", escape(b""));
}
#[test]
fn backslash() {
assert_eq!(b(b"\\"), unescape(r"\\"));
assert_eq!(r"\\", escape(b"\\"));
}
#[test]
fn nul() {
assert_eq!(b(b"\x00"), unescape(r"\x00"));
assert_eq!(r"\x00", escape(b"\x00"));
}
#[test]
fn nl() {
assert_eq!(b(b"\n"), unescape(r"\n"));
assert_eq!(r"\n", escape(b"\n"));
}
#[test]
fn tab() {
assert_eq!(b(b"\t"), unescape(r"\t"));
assert_eq!(r"\t", escape(b"\t"));
}
#[test]
fn carriage() {
assert_eq!(b(b"\r"), unescape(r"\r"));
assert_eq!(r"\r", escape(b"\r"));
}
#[test]
fn nothing_simple() {
assert_eq!(b(b"\\a"), unescape(r"\a"));
assert_eq!(b(b"\\a"), unescape(r"\\a"));
assert_eq!(r"\\a", escape(b"\\a"));
}
#[test]
fn nothing_hex0() {
assert_eq!(b(b"\\x"), unescape(r"\x"));
assert_eq!(b(b"\\x"), unescape(r"\\x"));
assert_eq!(r"\\x", escape(b"\\x"));
}
#[test]
fn nothing_hex1() {
assert_eq!(b(b"\\xz"), unescape(r"\xz"));
assert_eq!(b(b"\\xz"), unescape(r"\\xz"));
assert_eq!(r"\\xz", escape(b"\\xz"));
}
#[test]
fn nothing_hex2() {
assert_eq!(b(b"\\xzz"), unescape(r"\xzz"));
assert_eq!(b(b"\\xzz"), unescape(r"\\xzz"));
assert_eq!(r"\\xzz", escape(b"\\xzz"));
}
#[test]
fn invalid_utf8() {
assert_eq!(r"\xFF", escape(b"\xFF"));
assert_eq!(r"a\xFFb", escape(b"a\xFFb"));
}
}

171
grep-cli/src/human.rs Normal file
View File

@@ -0,0 +1,171 @@
use std::error;
use std::fmt;
use std::io;
use std::num::ParseIntError;
use regex::Regex;
/// An error that occurs when parsing a human readable size description.
///
/// This error provides a end user friendly message describing why the
/// description coudln't be parsed and what the expected format is.
#[derive(Clone, Debug, Eq, PartialEq)]
pub struct ParseSizeError {
original: String,
kind: ParseSizeErrorKind,
}
#[derive(Clone, Debug, Eq, PartialEq)]
enum ParseSizeErrorKind {
InvalidFormat,
InvalidInt(ParseIntError),
Overflow,
}
impl ParseSizeError {
fn format(original: &str) -> ParseSizeError {
ParseSizeError {
original: original.to_string(),
kind: ParseSizeErrorKind::InvalidFormat,
}
}
fn int(original: &str, err: ParseIntError) -> ParseSizeError {
ParseSizeError {
original: original.to_string(),
kind: ParseSizeErrorKind::InvalidInt(err),
}
}
fn overflow(original: &str) -> ParseSizeError {
ParseSizeError {
original: original.to_string(),
kind: ParseSizeErrorKind::Overflow,
}
}
}
impl error::Error for ParseSizeError {
fn description(&self) -> &str { "invalid size" }
}
impl fmt::Display for ParseSizeError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
use self::ParseSizeErrorKind::*;
match self.kind {
InvalidFormat => {
write!(
f,
"invalid format for size '{}', which should be a sequence \
of digits followed by an optional 'K', 'M' or 'G' \
suffix",
self.original
)
}
InvalidInt(ref err) => {
write!(
f,
"invalid integer found in size '{}': {}",
self.original,
err
)
}
Overflow => {
write!(f, "size too big in '{}'", self.original)
}
}
}
}
impl From<ParseSizeError> for io::Error {
fn from(size_err: ParseSizeError) -> io::Error {
io::Error::new(io::ErrorKind::Other, size_err)
}
}
/// Parse a human readable size like `2M` into a corresponding number of bytes.
///
/// Supported size suffixes are `K` (for kilobyte), `M` (for megabyte) and `G`
/// (for gigabyte). If a size suffix is missing, then the size is interpreted
/// as bytes. If the size is too big to fit into a `u64`, then this returns an
/// error.
///
/// Additional suffixes may be added over time.
pub fn parse_human_readable_size(size: &str) -> Result<u64, ParseSizeError> {
lazy_static! {
// Normally I'd just parse something this simple by hand to avoid the
// regex dep, but we bring regex in any way for glob matching, so might
// as well use it.
static ref RE: Regex = Regex::new(r"^([0-9]+)([KMG])?$").unwrap();
}
let caps = match RE.captures(size) {
Some(caps) => caps,
None => return Err(ParseSizeError::format(size)),
};
let value: u64 = caps[1].parse().map_err(|err| {
ParseSizeError::int(size, err)
})?;
let suffix = match caps.get(2) {
None => return Ok(value),
Some(cap) => cap.as_str(),
};
let bytes = match suffix {
"K" => value.checked_mul(1<<10),
"M" => value.checked_mul(1<<20),
"G" => value.checked_mul(1<<30),
// Because if the regex matches this group, it must be [KMG].
_ => unreachable!(),
};
bytes.ok_or_else(|| ParseSizeError::overflow(size))
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn suffix_none() {
let x = parse_human_readable_size("123").unwrap();
assert_eq!(123, x);
}
#[test]
fn suffix_k() {
let x = parse_human_readable_size("123K").unwrap();
assert_eq!(123 * (1<<10), x);
}
#[test]
fn suffix_m() {
let x = parse_human_readable_size("123M").unwrap();
assert_eq!(123 * (1<<20), x);
}
#[test]
fn suffix_g() {
let x = parse_human_readable_size("123G").unwrap();
assert_eq!(123 * (1<<30), x);
}
#[test]
fn invalid_empty() {
assert!(parse_human_readable_size("").is_err());
}
#[test]
fn invalid_non_digit() {
assert!(parse_human_readable_size("a").is_err());
}
#[test]
fn invalid_overflow() {
assert!(parse_human_readable_size("9999999999999999G").is_err());
}
#[test]
fn invalid_suffix() {
assert!(parse_human_readable_size("123T").is_err());
}
}

252
grep-cli/src/lib.rs Normal file
View File

@@ -0,0 +1,252 @@
/*!
This crate provides common routines used in command line applications, with a
focus on routines useful for search oriented applications. As a utility
library, there is no central type or function. However, a key focus of this
crate is to improve failure modes and provide user friendly error messages
when things go wrong.
To the best extent possible, everything in this crate works on Windows, macOS
and Linux.
# Standard I/O
The
[`is_readable_stdin`](fn.is_readable_stdin.html),
[`is_tty_stderr`](fn.is_tty_stderr.html),
[`is_tty_stdin`](fn.is_tty_stdin.html)
and
[`is_tty_stdout`](fn.is_tty_stdout.html)
routines query aspects of standard I/O. `is_readable_stdin` determines whether
stdin can be usefully read from, while the `tty` methods determine whether a
tty is attached to stdin/stdout/stderr.
`is_readable_stdin` is useful when writing an application that changes behavior
based on whether the application was invoked with data on stdin. For example,
`rg foo` might recursively search the current working directory for
occurrences of `foo`, but `rg foo < file` might only search the contents of
`file`.
The `tty` methods are useful for similar reasons. Namely, commands like `ls`
will change their output depending on whether they are printing to a terminal
or not. For example, `ls` shows a file on each line when stdout is redirected
to a file or a pipe, but condenses the output to show possibly many files on
each line when stdout is connected to a tty.
# Coloring and buffering
The
[`stdout`](fn.stdout.html),
[`stdout_buffered_block`](fn.stdout_buffered_block.html)
and
[`stdout_buffered_line`](fn.stdout_buffered_line.html)
routines are alternative constructors for
[`StandardStream`](struct.StandardStream.html).
A `StandardStream` implements `termcolor::WriteColor`, which provides a way
to emit colors to terminals. Its key use is the encapsulation of buffering
style. Namely, `stdout` will return a line buffered `StandardStream` if and
only if stdout is connected to a tty, and will otherwise return a block
buffered `StandardStream`. Line buffering is important for use with a tty
because it typically decreases the latency at which the end user sees output.
Block buffering is used otherwise because it is faster, and redirecting stdout
to a file typically doesn't benefit from the decreased latency that line
buffering provides.
The `stdout_buffered_block` and `stdout_buffered_line` can be used to
explicitly set the buffering strategy regardless of whether stdout is connected
to a tty or not.
# Escaping
The
[`escape`](fn.escape.html),
[`escape_os`](fn.escape_os.html),
[`unescape`](fn.unescape.html)
and
[`unescape_os`](fn.unescape_os.html)
routines provide a user friendly way of dealing with UTF-8 encoded strings that
can express arbitrary bytes. For example, you might want to accept a string
containing arbitrary bytes as a command line argument, but most interactive
shells make such strings difficult to type. Instead, we can ask users to use
escape sequences.
For example, `a\xFFz` is itself a valid UTF-8 string corresponding to the
following bytes:
```ignore
[b'a', b'\\', b'x', b'F', b'F', b'z']
```
However, we can
interpret `\xFF` as an escape sequence with the `unescape`/`unescape_os`
routines, which will yield
```ignore
[b'a', b'\xFF', b'z']
```
instead. For example:
```
use grep_cli::unescape;
// Note the use of a raw string!
assert_eq!(vec![b'a', b'\xFF', b'z'], unescape(r"a\xFFz"));
```
The `escape`/`escape_os` routines provide the reverse transformation, which
makes it easy to show user friendly error messages involving arbitrary bytes.
# Building patterns
Typically, regular expression patterns must be valid UTF-8. However, command
line arguments aren't guaranteed to be valid UTF-8. Unfortunately, the
standard library's UTF-8 conversion functions from `OsStr`s do not provide
good error messages. However, the
[`pattern_from_bytes`](fn.pattern_from_bytes.html)
and
[`pattern_from_os`](fn.pattern_from_os.html)
do, including reporting exactly where the first invalid UTF-8 byte is seen.
Additionally, it can be useful to read patterns from a file while reporting
good error messages that include line numbers. The
[`patterns_from_path`](fn.patterns_from_path.html),
[`patterns_from_reader`](fn.patterns_from_reader.html)
and
[`patterns_from_stdin`](fn.patterns_from_stdin.html)
routines do just that. If any pattern is found that is invalid UTF-8, then the
error includes the file path (if available) along with the line number and the
byte offset at which the first invalid UTF-8 byte was observed.
# Read process output
Sometimes a command line application needs to execute other processes and read
its stdout in a streaming fashion. The
[`CommandReader`](struct.CommandReader.html)
provides this functionality with an explicit goal of improving failure modes.
In particular, if the process exits with an error code, then stderr is read
and converted into a normal Rust error to show to end users. This makes the
underlying failure modes explicit and gives more information to end users for
debugging the problem.
As a special case,
[`DecompressionReader`](struct.DecompressionReader.html)
provides a way to decompress arbitrary files by matching their file extensions
up with corresponding decompression programs (such as `gzip` and `xz`). This
is useful as a means of performing simplistic decompression in a portable
manner without binding to specific compression libraries. This does come with
some overhead though, so if you need to decompress lots of small files, this
may not be an appropriate convenience to use.
Each reader has a corresponding builder for additional configuration, such as
whether to read stderr asynchronously in order to avoid deadlock (which is
enabled by default).
# Miscellaneous parsing
The
[`parse_human_readable_size`](fn.parse_human_readable_size.html)
routine parses strings like `2M` and converts them to the corresponding number
of bytes (`2 * 1<<20` in this case). If an invalid size is found, then a good
error message is crafted that typically tells the user how to fix the problem.
*/
#![deny(missing_docs)]
extern crate atty;
extern crate bstr;
extern crate globset;
#[macro_use]
extern crate lazy_static;
#[macro_use]
extern crate log;
extern crate regex;
extern crate same_file;
extern crate termcolor;
#[cfg(windows)]
extern crate winapi_util;
mod decompress;
mod escape;
mod human;
mod pattern;
mod process;
mod wtr;
pub use decompress::{
DecompressionMatcher, DecompressionMatcherBuilder,
DecompressionReader, DecompressionReaderBuilder,
};
pub use escape::{escape, escape_os, unescape, unescape_os};
pub use human::{ParseSizeError, parse_human_readable_size};
pub use pattern::{
InvalidPatternError,
pattern_from_os, pattern_from_bytes,
patterns_from_path, patterns_from_reader, patterns_from_stdin,
};
pub use process::{CommandError, CommandReader, CommandReaderBuilder};
pub use wtr::{
StandardStream,
stdout, stdout_buffered_line, stdout_buffered_block,
};
/// Returns true if and only if stdin is believed to be readable.
///
/// When stdin is readable, command line programs may choose to behave
/// differently than when stdin is not readable. For example, `command foo`
/// might search the current directory for occurrences of `foo` where as
/// `command foo < some-file` or `cat some-file | command foo` might instead
/// only search stdin for occurrences of `foo`.
pub fn is_readable_stdin() -> bool {
#[cfg(unix)]
fn imp() -> bool {
use std::os::unix::fs::FileTypeExt;
use same_file::Handle;
let ft = match Handle::stdin().and_then(|h| h.as_file().metadata()) {
Err(_) => return false,
Ok(md) => md.file_type(),
};
ft.is_file() || ft.is_fifo()
}
#[cfg(windows)]
fn imp() -> bool {
use winapi_util as winutil;
winutil::file::typ(winutil::HandleRef::stdin())
.map(|t| t.is_disk() || t.is_pipe())
.unwrap_or(false)
}
!is_tty_stdin() && imp()
}
/// Returns true if and only if stdin is believed to be connectted to a tty
/// or a console.
pub fn is_tty_stdin() -> bool {
atty::is(atty::Stream::Stdin)
}
/// Returns true if and only if stdout is believed to be connectted to a tty
/// or a console.
///
/// This is useful for when you want your command line program to produce
/// different output depending on whether it's printing directly to a user's
/// terminal or whether it's being redirected somewhere else. For example,
/// implementations of `ls` will often show one item per line when stdout is
/// redirected, but will condensed output when printing to a tty.
pub fn is_tty_stdout() -> bool {
atty::is(atty::Stream::Stdout)
}
/// Returns true if and only if stderr is believed to be connectted to a tty
/// or a console.
pub fn is_tty_stderr() -> bool {
atty::is(atty::Stream::Stderr)
}

205
grep-cli/src/pattern.rs Normal file
View File

@@ -0,0 +1,205 @@
use std::error;
use std::ffi::OsStr;
use std::fmt;
use std::fs::File;
use std::io::{self, BufRead};
use std::path::Path;
use std::str;
use escape::{escape, escape_os};
/// An error that occurs when a pattern could not be converted to valid UTF-8.
///
/// The purpose of this error is to give a more targeted failure mode for
/// patterns written by end users that are not valid UTF-8.
#[derive(Clone, Debug, Eq, PartialEq)]
pub struct InvalidPatternError {
original: String,
valid_up_to: usize,
}
impl InvalidPatternError {
/// Returns the index in the given string up to which valid UTF-8 was
/// verified.
pub fn valid_up_to(&self) -> usize {
self.valid_up_to
}
}
impl error::Error for InvalidPatternError {
fn description(&self) -> &str { "invalid pattern" }
}
impl fmt::Display for InvalidPatternError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"found invalid UTF-8 in pattern at byte offset {} \
(use hex escape sequences to match arbitrary bytes \
in a pattern, e.g., \\xFF): '{}'",
self.valid_up_to,
self.original,
)
}
}
impl From<InvalidPatternError> for io::Error {
fn from(paterr: InvalidPatternError) -> io::Error {
io::Error::new(io::ErrorKind::Other, paterr)
}
}
/// Convert an OS string into a regular expression pattern.
///
/// This conversion fails if the given pattern is not valid UTF-8, in which
/// case, a targeted error with more information about where the invalid UTF-8
/// occurs is given. The error also suggests the use of hex escape sequences,
/// which are supported by many regex engines.
pub fn pattern_from_os(pattern: &OsStr) -> Result<&str, InvalidPatternError> {
pattern.to_str().ok_or_else(|| {
let valid_up_to = pattern
.to_string_lossy()
.find('\u{FFFD}')
.expect("a Unicode replacement codepoint for invalid UTF-8");
InvalidPatternError {
original: escape_os(pattern),
valid_up_to: valid_up_to,
}
})
}
/// Convert arbitrary bytes into a regular expression pattern.
///
/// This conversion fails if the given pattern is not valid UTF-8, in which
/// case, a targeted error with more information about where the invalid UTF-8
/// occurs is given. The error also suggests the use of hex escape sequences,
/// which are supported by many regex engines.
pub fn pattern_from_bytes(
pattern: &[u8],
) -> Result<&str, InvalidPatternError> {
str::from_utf8(pattern).map_err(|err| {
InvalidPatternError {
original: escape(pattern),
valid_up_to: err.valid_up_to(),
}
})
}
/// Read patterns from a file path, one per line.
///
/// If there was a problem reading or if any of the patterns contain invalid
/// UTF-8, then an error is returned. If there was a problem with a specific
/// pattern, then the error message will include the line number and the file
/// path.
pub fn patterns_from_path<P: AsRef<Path>>(path: P) -> io::Result<Vec<String>> {
let path = path.as_ref();
let file = File::open(path).map_err(|err| {
io::Error::new(
io::ErrorKind::Other,
format!("{}: {}", path.display(), err),
)
})?;
patterns_from_reader(file).map_err(|err| {
io::Error::new(
io::ErrorKind::Other,
format!("{}:{}", path.display(), err),
)
})
}
/// Read patterns from stdin, one per line.
///
/// If there was a problem reading or if any of the patterns contain invalid
/// UTF-8, then an error is returned. If there was a problem with a specific
/// pattern, then the error message will include the line number and the fact
/// that it came from stdin.
pub fn patterns_from_stdin() -> io::Result<Vec<String>> {
let stdin = io::stdin();
let locked = stdin.lock();
patterns_from_reader(locked).map_err(|err| {
io::Error::new(
io::ErrorKind::Other,
format!("<stdin>:{}", err),
)
})
}
/// Read patterns from any reader, one per line.
///
/// If there was a problem reading or if any of the patterns contain invalid
/// UTF-8, then an error is returned. If there was a problem with a specific
/// pattern, then the error message will include the line number.
///
/// Note that this routine uses its own internal buffer, so the caller should
/// not provide their own buffered reader if possible.
///
/// # Example
///
/// This shows how to parse patterns, one per line.
///
/// ```
/// use grep_cli::patterns_from_reader;
///
/// # fn example() -> Result<(), Box<::std::error::Error>> {
/// let patterns = "\
/// foo
/// bar\\s+foo
/// [a-z]{3}
/// ";
///
/// assert_eq!(patterns_from_reader(patterns.as_bytes())?, vec![
/// r"foo",
/// r"bar\s+foo",
/// r"[a-z]{3}",
/// ]);
/// # Ok(()) }
/// ```
pub fn patterns_from_reader<R: io::Read>(rdr: R) -> io::Result<Vec<String>> {
let mut patterns = vec![];
let mut bufrdr = io::BufReader::new(rdr);
let mut line = vec![];
let mut line_number = 0;
while {
line.clear();
line_number += 1;
bufrdr.read_until(b'\n', &mut line)? > 0
} {
line.pop().unwrap(); // remove trailing '\n'
if line.last() == Some(&b'\r') {
line.pop().unwrap();
}
match pattern_from_bytes(&line) {
Ok(pattern) => patterns.push(pattern.to_string()),
Err(err) => {
return Err(io::Error::new(
io::ErrorKind::Other,
format!("{}: {}", line_number, err),
));
}
}
}
Ok(patterns)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn bytes() {
let pat = b"abc\xFFxyz";
let err = pattern_from_bytes(pat).unwrap_err();
assert_eq!(3, err.valid_up_to());
}
#[test]
#[cfg(unix)]
fn os() {
use std::os::unix::ffi::OsStrExt;
use std::ffi::OsStr;
let pat = OsStr::from_bytes(b"abc\xFFxyz");
let err = pattern_from_os(pat).unwrap_err();
assert_eq!(3, err.valid_up_to());
}
}

267
grep-cli/src/process.rs Normal file
View File

@@ -0,0 +1,267 @@
use std::error;
use std::fmt;
use std::io::{self, Read};
use std::iter;
use std::process;
use std::thread::{self, JoinHandle};
/// An error that can occur while running a command and reading its output.
///
/// This error can be seamlessly converted to an `io::Error` via a `From`
/// implementation.
#[derive(Debug)]
pub struct CommandError {
kind: CommandErrorKind,
}
#[derive(Debug)]
enum CommandErrorKind {
Io(io::Error),
Stderr(Vec<u8>),
}
impl CommandError {
/// Create an error from an I/O error.
pub(crate) fn io(ioerr: io::Error) -> CommandError {
CommandError { kind: CommandErrorKind::Io(ioerr) }
}
/// Create an error from the contents of stderr (which may be empty).
pub(crate) fn stderr(bytes: Vec<u8>) -> CommandError {
CommandError { kind: CommandErrorKind::Stderr(bytes) }
}
}
impl error::Error for CommandError {
fn description(&self) -> &str { "command error" }
}
impl fmt::Display for CommandError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self.kind {
CommandErrorKind::Io(ref e) => e.fmt(f),
CommandErrorKind::Stderr(ref bytes) => {
let msg = String::from_utf8_lossy(bytes);
if msg.trim().is_empty() {
write!(f, "<stderr is empty>")
} else {
let div = iter::repeat('-').take(79).collect::<String>();
write!(f, "\n{div}\n{msg}\n{div}", div=div, msg=msg.trim())
}
}
}
}
}
impl From<io::Error> for CommandError {
fn from(ioerr: io::Error) -> CommandError {
CommandError { kind: CommandErrorKind::Io(ioerr) }
}
}
impl From<CommandError> for io::Error {
fn from(cmderr: CommandError) -> io::Error {
match cmderr.kind {
CommandErrorKind::Io(ioerr) => ioerr,
CommandErrorKind::Stderr(_) => {
io::Error::new(io::ErrorKind::Other, cmderr)
}
}
}
}
/// Configures and builds a streaming reader for process output.
#[derive(Clone, Debug, Default)]
pub struct CommandReaderBuilder {
async_stderr: bool,
}
impl CommandReaderBuilder {
/// Create a new builder with the default configuration.
pub fn new() -> CommandReaderBuilder {
CommandReaderBuilder::default()
}
/// Build a new streaming reader for the given command's output.
///
/// The caller should set everything that's required on the given command
/// before building a reader, such as its arguments, environment and
/// current working directory. Settings such as the stdout and stderr (but
/// not stdin) pipes will be overridden so that they can be controlled by
/// the reader.
///
/// If there was a problem spawning the given command, then its error is
/// returned.
pub fn build(
&self,
command: &mut process::Command,
) -> Result<CommandReader, CommandError> {
let mut child = command
.stdout(process::Stdio::piped())
.stderr(process::Stdio::piped())
.spawn()?;
let stdout = child.stdout.take().unwrap();
let stderr =
if self.async_stderr {
StderrReader::async(child.stderr.take().unwrap())
} else {
StderrReader::sync(child.stderr.take().unwrap())
};
Ok(CommandReader {
child: child,
stdout: stdout,
stderr: stderr,
done: false,
})
}
/// When enabled, the reader will asynchronously read the contents of the
/// command's stderr output. When disabled, stderr is only read after the
/// stdout stream has been exhausted (or if the process quits with an error
/// code).
///
/// Note that when enabled, this may require launching an additional
/// thread in order to read stderr. This is done so that the process being
/// executed is never blocked from writing to stdout or stderr. If this is
/// disabled, then it is possible for the process to fill up the stderr
/// buffer and deadlock.
///
/// This is enabled by default.
pub fn async_stderr(&mut self, yes: bool) -> &mut CommandReaderBuilder {
self.async_stderr = yes;
self
}
}
/// A streaming reader for a command's output.
///
/// The purpose of this reader is to provide an easy way to execute processes
/// whose stdout is read in a streaming way while also making the processes'
/// stderr available when the process fails with an exit code. This makes it
/// possible to execute processes while surfacing the underlying failure mode
/// in the case of an error.
///
/// Moreover, by default, this reader will asynchronously read the processes'
/// stderr. This prevents subtle deadlocking bugs for noisy processes that
/// write a lot to stderr. Currently, the entire contents of stderr is read
/// on to the heap.
///
/// # Example
///
/// This example shows how to invoke `gzip` to decompress the contents of a
/// file. If the `gzip` command reports a failing exit status, then its stderr
/// is returned as an error.
///
/// ```no_run
/// use std::io::Read;
/// use std::process::Command;
/// use grep_cli::CommandReader;
///
/// # fn example() -> Result<(), Box<::std::error::Error>> {
/// let mut cmd = Command::new("gzip");
/// cmd.arg("-d").arg("-c").arg("/usr/share/man/man1/ls.1.gz");
///
/// let mut rdr = CommandReader::new(&mut cmd)?;
/// let mut contents = vec![];
/// rdr.read_to_end(&mut contents)?;
/// # Ok(()) }
/// ```
#[derive(Debug)]
pub struct CommandReader {
child: process::Child,
stdout: process::ChildStdout,
stderr: StderrReader,
done: bool,
}
impl CommandReader {
/// Create a new streaming reader for the given command using the default
/// configuration.
///
/// The caller should set everything that's required on the given command
/// before building a reader, such as its arguments, environment and
/// current working directory. Settings such as the stdout and stderr (but
/// not stdin) pipes will be overridden so that they can be controlled by
/// the reader.
///
/// If there was a problem spawning the given command, then its error is
/// returned.
///
/// If the caller requires additional configuration for the reader
/// returned, then use
/// [`CommandReaderBuilder`](struct.CommandReaderBuilder.html).
pub fn new(
cmd: &mut process::Command,
) -> Result<CommandReader, CommandError> {
CommandReaderBuilder::new().build(cmd)
}
}
impl io::Read for CommandReader {
fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
if self.done {
return Ok(0);
}
let nread = self.stdout.read(buf)?;
if nread == 0 {
self.done = true;
// Reap the child now that we're done reading. If the command
// failed, report stderr as an error.
if !self.child.wait()?.success() {
return Err(io::Error::from(self.stderr.read_to_end()));
}
}
Ok(nread)
}
}
/// A reader that encapsulates the asynchronous or synchronous reading of
/// stderr.
#[derive(Debug)]
enum StderrReader {
Async(Option<JoinHandle<CommandError>>),
Sync(process::ChildStderr),
}
impl StderrReader {
/// Create a reader for stderr that reads contents asynchronously.
fn async(mut stderr: process::ChildStderr) -> StderrReader {
let handle = thread::spawn(move || {
stderr_to_command_error(&mut stderr)
});
StderrReader::Async(Some(handle))
}
/// Create a reader for stderr that reads contents synchronously.
fn sync(stderr: process::ChildStderr) -> StderrReader {
StderrReader::Sync(stderr)
}
/// Consumes all of stderr on to the heap and returns it as an error.
///
/// If there was a problem reading stderr itself, then this returns an I/O
/// command error.
fn read_to_end(&mut self) -> CommandError {
match *self {
StderrReader::Async(ref mut handle) => {
let handle = handle
.take()
.expect("read_to_end cannot be called more than once");
handle
.join()
.expect("stderr reading thread does not panic")
}
StderrReader::Sync(ref mut stderr) => {
stderr_to_command_error(stderr)
}
}
}
}
fn stderr_to_command_error(stderr: &mut process::ChildStderr) -> CommandError {
let mut bytes = vec![];
match stderr.read_to_end(&mut bytes) {
Ok(_) => CommandError::stderr(bytes),
Err(err) => CommandError::io(err),
}
}

133
grep-cli/src/wtr.rs Normal file
View File

@@ -0,0 +1,133 @@
use std::io;
use termcolor;
use is_tty_stdout;
/// A writer that supports coloring with either line or block buffering.
pub struct StandardStream(StandardStreamKind);
/// Returns a possibly buffered writer to stdout for the given color choice.
///
/// The writer returned is either line buffered or block buffered. The decision
/// between these two is made automatically based on whether a tty is attached
/// to stdout or not. If a tty is attached, then line buffering is used.
/// Otherwise, block buffering is used. In general, block buffering is more
/// efficient, but may increase the time it takes for the end user to see the
/// first bits of output.
///
/// If you need more fine grained control over the buffering mode, then use one
/// of `stdout_buffered_line` or `stdout_buffered_block`.
///
/// The color choice given is passed along to the underlying writer. To
/// completely disable colors in all cases, use `ColorChoice::Never`.
pub fn stdout(color_choice: termcolor::ColorChoice) -> StandardStream {
if is_tty_stdout() {
stdout_buffered_line(color_choice)
} else {
stdout_buffered_block(color_choice)
}
}
/// Returns a line buffered writer to stdout for the given color choice.
///
/// This writer is useful when printing results directly to a tty such that
/// users see output as soon as it's written. The downside of this approach
/// is that it can be slower, especially when there is a lot of output.
///
/// You might consider using
/// [`stdout`](fn.stdout.html)
/// instead, which chooses the buffering strategy automatically based on
/// whether stdout is connected to a tty.
pub fn stdout_buffered_line(
color_choice: termcolor::ColorChoice,
) -> StandardStream {
let out = termcolor::StandardStream::stdout(color_choice);
StandardStream(StandardStreamKind::LineBuffered(out))
}
/// Returns a block buffered writer to stdout for the given color choice.
///
/// This writer is useful when printing results to a file since it amortizes
/// the cost of writing data. The downside of this approach is that it can
/// increase the latency of display output when writing to a tty.
///
/// You might consider using
/// [`stdout`](fn.stdout.html)
/// instead, which chooses the buffering strategy automatically based on
/// whether stdout is connected to a tty.
pub fn stdout_buffered_block(
color_choice: termcolor::ColorChoice,
) -> StandardStream {
let out = termcolor::BufferedStandardStream::stdout(color_choice);
StandardStream(StandardStreamKind::BlockBuffered(out))
}
enum StandardStreamKind {
LineBuffered(termcolor::StandardStream),
BlockBuffered(termcolor::BufferedStandardStream),
}
impl io::Write for StandardStream {
#[inline]
fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
use self::StandardStreamKind::*;
match self.0 {
LineBuffered(ref mut w) => w.write(buf),
BlockBuffered(ref mut w) => w.write(buf),
}
}
#[inline]
fn flush(&mut self) -> io::Result<()> {
use self::StandardStreamKind::*;
match self.0 {
LineBuffered(ref mut w) => w.flush(),
BlockBuffered(ref mut w) => w.flush(),
}
}
}
impl termcolor::WriteColor for StandardStream {
#[inline]
fn supports_color(&self) -> bool {
use self::StandardStreamKind::*;
match self.0 {
LineBuffered(ref w) => w.supports_color(),
BlockBuffered(ref w) => w.supports_color(),
}
}
#[inline]
fn set_color(&mut self, spec: &termcolor::ColorSpec) -> io::Result<()> {
use self::StandardStreamKind::*;
match self.0 {
LineBuffered(ref mut w) => w.set_color(spec),
BlockBuffered(ref mut w) => w.set_color(spec),
}
}
#[inline]
fn reset(&mut self) -> io::Result<()> {
use self::StandardStreamKind::*;
match self.0 {
LineBuffered(ref mut w) => w.reset(),
BlockBuffered(ref mut w) => w.reset(),
}
}
#[inline]
fn is_synchronous(&self) -> bool {
use self::StandardStreamKind::*;
match self.0 {
LineBuffered(ref w) => w.is_synchronous(),
BlockBuffered(ref w) => w.is_synchronous(),
}
}
}

24
grep-matcher/Cargo.toml Normal file
View File

@@ -0,0 +1,24 @@
[package]
name = "grep-matcher"
version = "0.1.1" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
A trait for regular expressions, with a focus on line oriented search.
"""
documentation = "https://docs.rs/grep-matcher"
homepage = "https://github.com/BurntSushi/ripgrep"
repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["regex", "pattern", "trait"]
license = "Unlicense/MIT"
autotests = false
[dependencies]
memchr = "2.1"
[dev-dependencies]
regex = "1.1"
[[test]]
name = "integration"
path = "tests/tests.rs"

0
wincolor/LICENSE-MIT → grep-matcher/LICENSE-MIT
View File

36
grep-matcher/README.md Normal file
View File

@@ -0,0 +1,36 @@
grep-matcher
------------
This crate provides a low level interface for describing regular expression
matchers. The `grep` crate uses this interface in order to make the regex
engine it uses pluggable.
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/grep-matcher.svg)](https://crates.io/crates/grep-matcher)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
### Documentation
[https://docs.rs/grep-matcher](https://docs.rs/grep-matcher)
**NOTE:** You probably don't want to use this crate directly. Instead, you
should prefer the facade defined in the
[`grep`](https://docs.rs/grep)
crate.
### Usage
Add this to your `Cargo.toml`:
```toml
[dependencies]
grep-matcher = "0.1"
```
and this to your crate root:
```rust
extern crate grep_matcher;
```

0
wincolor/UNLICENSE → grep-matcher/UNLICENSE
View File

328
grep-matcher/src/interpolate.rs Normal file
View File

@@ -0,0 +1,328 @@
use std::str;
use memchr::memchr;
/// Interpolate capture references in `replacement` and write the interpolation
/// result to `dst`. References in `replacement` take the form of $N or $name,
/// where `N` is a capture group index and `name` is a capture group name. The
/// function provided, `name_to_index`, maps capture group names to indices.
///
/// The `append` function given is responsible for writing the replacement
/// to the `dst` buffer. That is, it is called with the capture group index
/// of a capture group reference and is expected to resolve the index to its
/// corresponding matched text. If no such match exists, then `append` should
/// not write anything to its given buffer.
pub fn interpolate<A, N>(
mut replacement: &[u8],
mut append: A,
mut name_to_index: N,
dst: &mut Vec<u8>,
) where
A: FnMut(usize, &mut Vec<u8>),
N: FnMut(&str) -> Option<usize>
{
while !replacement.is_empty() {
match memchr(b'$', replacement) {
None => break,
Some(i) => {
dst.extend(&replacement[..i]);
replacement = &replacement[i..];
}
}
if replacement.get(1).map_or(false, |&b| b == b'$') {
dst.push(b'$');
replacement = &replacement[2..];
continue;
}
debug_assert!(!replacement.is_empty());
let cap_ref = match find_cap_ref(replacement) {
Some(cap_ref) => cap_ref,
None => {
dst.push(b'$');
replacement = &replacement[1..];
continue;
}
};
replacement = &replacement[cap_ref.end..];
match cap_ref.cap {
Ref::Number(i) => append(i, dst),
Ref::Named(name) => {
if let Some(i) = name_to_index(name) {
append(i, dst);
}
}
}
}
dst.extend(replacement);
}
/// `CaptureRef` represents a reference to a capture group inside some text.
/// The reference is either a capture group name or a number.
///
/// It is also tagged with the position in the text immediately proceding the
/// capture reference.
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
struct CaptureRef<'a> {
cap: Ref<'a>,
end: usize,
}
/// A reference to a capture group in some text.
///
/// e.g., `$2`, `$foo`, `${foo}`.
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
enum Ref<'a> {
Named(&'a str),
Number(usize),
}
impl<'a> From<&'a str> for Ref<'a> {
fn from(x: &'a str) -> Ref<'a> {
Ref::Named(x)
}
}
impl From<usize> for Ref<'static> {
fn from(x: usize) -> Ref<'static> {
Ref::Number(x)
}
}
/// Parses a possible reference to a capture group name in the given text,
/// starting at the beginning of `replacement`.
///
/// If no such valid reference could be found, None is returned.
fn find_cap_ref(replacement: &[u8]) -> Option<CaptureRef> {
let mut i = 0;
if replacement.len() <= 1 || replacement[0] != b'$' {
return None;
}
let mut brace = false;
i += 1;
if replacement[i] == b'{' {
brace = true;
i += 1;
}
let mut cap_end = i;
while replacement.get(cap_end).map_or(false, is_valid_cap_letter) {
cap_end += 1;
}
if cap_end == i {
return None;
}
// We just verified that the range 0..cap_end is valid ASCII, so it must
// therefore be valid UTF-8. If we really cared, we could avoid this UTF-8
// check with an unchecked conversion or by parsing the number straight
// from &[u8].
let cap = str::from_utf8(&replacement[i..cap_end])
.expect("valid UTF-8 capture name");
if brace {
if !replacement.get(cap_end).map_or(false, |&b| b == b'}') {
return None;
}
cap_end += 1;
}
Some(CaptureRef {
cap: match cap.parse::<u32>() {
Ok(i) => Ref::Number(i as usize),
Err(_) => Ref::Named(cap),
},
end: cap_end,
})
}
/// Returns true if and only if the given byte is allowed in a capture name.
fn is_valid_cap_letter(b: &u8) -> bool {
match *b {
b'0' ... b'9' | b'a' ... b'z' | b'A' ... b'Z' | b'_' => true,
_ => false,
}
}
#[cfg(test)]
mod tests {
use super::{CaptureRef, find_cap_ref, interpolate};
macro_rules! find {
($name:ident, $text:expr) => {
#[test]
fn $name() {
assert_eq!(None, find_cap_ref($text.as_bytes()));
}
};
($name:ident, $text:expr, $capref:expr) => {
#[test]
fn $name() {
assert_eq!(Some($capref), find_cap_ref($text.as_bytes()));
}
};
}
macro_rules! c {
($name_or_number:expr, $pos:expr) => {
CaptureRef { cap: $name_or_number.into(), end: $pos }
};
}
find!(find_cap_ref1, "$foo", c!("foo", 4));
find!(find_cap_ref2, "${foo}", c!("foo", 6));
find!(find_cap_ref3, "$0", c!(0, 2));
find!(find_cap_ref4, "$5", c!(5, 2));
find!(find_cap_ref5, "$10", c!(10, 3));
find!(find_cap_ref6, "$42a", c!("42a", 4));
find!(find_cap_ref7, "${42}a", c!(42, 5));
find!(find_cap_ref8, "${42");
find!(find_cap_ref9, "${42 ");
find!(find_cap_ref10, " $0 ");
find!(find_cap_ref11, "$");
find!(find_cap_ref12, " ");
find!(find_cap_ref13, "");
// A convenience routine for using interpolate's unwieldy but flexible API.
fn interpolate_string(
mut name_to_index: Vec<(&'static str, usize)>,
caps: Vec<&'static str>,
replacement: &str,
) -> String {
name_to_index.sort_by_key(|x| x.0);
let mut dst = vec![];
interpolate(
replacement.as_bytes(),
|i, dst| {
if let Some(&s) = caps.get(i) {
dst.extend(s.as_bytes());
}
},
|name| -> Option<usize> {
name_to_index
.binary_search_by_key(&name, |x| x.0)
.ok()
.map(|i| name_to_index[i].1)
},
&mut dst,
);
String::from_utf8(dst).unwrap()
}
macro_rules! interp {
($name:ident, $map:expr, $caps:expr, $hay:expr, $expected:expr $(,)*) => {
#[test]
fn $name() {
assert_eq!($expected, interpolate_string($map, $caps, $hay));
}
}
}
interp!(
interp1,
vec![("foo", 2)],
vec!["", "", "xxx"],
"test $foo test",
"test xxx test",
);
interp!(
interp2,
vec![("foo", 2)],
vec!["", "", "xxx"],
"test$footest",
"test",
);
interp!(
interp3,
vec![("foo", 2)],
vec!["", "", "xxx"],
"test${foo}test",
"testxxxtest",
);
interp!(
interp4,
vec![("foo", 2)],
vec!["", "", "xxx"],
"test$2test",
"test",
);
interp!(
interp5,
vec![("foo", 2)],
vec!["", "", "xxx"],
"test${2}test",
"testxxxtest",
);
interp!(
interp6,
vec![("foo", 2)],
vec!["", "", "xxx"],
"test $$foo test",
"test $foo test",
);
interp!(
interp7,
vec![("foo", 2)],
vec!["", "", "xxx"],
"test $foo",
"test xxx",
);
interp!(
interp8,
vec![("foo", 2)],
vec!["", "", "xxx"],
"$foo test",
"xxx test",
);
interp!(
interp9,
vec![("bar", 1), ("foo", 2)],
vec!["", "yyy", "xxx"],
"test $bar$foo",
"test yyyxxx",
);
interp!(
interp10,
vec![("bar", 1), ("foo", 2)],
vec!["", "yyy", "xxx"],
"test $ test",
"test $ test",
);
interp!(
interp11,
vec![("bar", 1), ("foo", 2)],
vec!["", "yyy", "xxx"],
"test ${} test",
"test ${} test",
);
interp!(
interp12,
vec![("bar", 1), ("foo", 2)],
vec!["", "yyy", "xxx"],
"test ${ } test",
"test ${ } test",
);
interp!(
interp13,
vec![("bar", 1), ("foo", 2)],
vec!["", "yyy", "xxx"],
"test ${a b} test",
"test ${a b} test",
);
interp!(
interp14,
vec![("bar", 1), ("foo", 2)],
vec!["", "yyy", "xxx"],
"test ${a} test",
"test test",
);
}

1136
grep-matcher/src/lib.rs Normal file
View File

File diff suppressed because it is too large Load Diff

208
grep-matcher/tests/test_matcher.rs Normal file
View File

@@ -0,0 +1,208 @@
use grep_matcher::{Captures, Match, Matcher};
use regex::bytes::Regex;
use util::{RegexMatcher, RegexMatcherNoCaps};
fn matcher(pattern: &str) -> RegexMatcher {
RegexMatcher::new(Regex::new(pattern).unwrap())
}
fn matcher_no_caps(pattern: &str) -> RegexMatcherNoCaps {
RegexMatcherNoCaps(Regex::new(pattern).unwrap())
}
fn m(start: usize, end: usize) -> Match {
Match::new(start, end)
}
#[test]
fn find() {
let matcher = matcher(r"(\w+)\s+(\w+)");
assert_eq!(matcher.find(b" homer simpson ").unwrap(), Some(m(1, 14)));
}
#[test]
fn find_iter() {
let matcher = matcher(r"(\w+)\s+(\w+)");
let mut matches = vec![];
matcher.find_iter(b"aa bb cc dd", |m| {
matches.push(m);
true
}).unwrap();
assert_eq!(matches, vec![m(0, 5), m(6, 11)]);
// Test that find_iter respects short circuiting.
matches.clear();
matcher.find_iter(b"aa bb cc dd", |m| {
matches.push(m);
false
}).unwrap();
assert_eq!(matches, vec![m(0, 5)]);
}
#[test]
fn try_find_iter() {
#[derive(Clone, Debug, Eq, PartialEq)]
struct MyError;
let matcher = matcher(r"(\w+)\s+(\w+)");
let mut matches = vec![];
let err = matcher.try_find_iter(b"aa bb cc dd", |m| {
if matches.is_empty() {
matches.push(m);
Ok(true)
} else {
Err(MyError)
}
}).unwrap().unwrap_err();
assert_eq!(matches, vec![m(0, 5)]);
assert_eq!(err, MyError);
}
#[test]
fn shortest_match() {
let matcher = matcher(r"a+");
// This tests that the default impl isn't doing anything smart, and simply
// defers to `find`.
assert_eq!(matcher.shortest_match(b"aaa").unwrap(), Some(3));
// The actual underlying regex is smarter.
assert_eq!(matcher.re.shortest_match(b"aaa"), Some(1));
}
#[test]
fn captures() {
let matcher = matcher(r"(?P<a>\w+)\s+(?P<b>\w+)");
assert_eq!(matcher.capture_count(), 3);
assert_eq!(matcher.capture_index("a"), Some(1));
assert_eq!(matcher.capture_index("b"), Some(2));
assert_eq!(matcher.capture_index("nada"), None);
let mut caps = matcher.new_captures().unwrap();
assert!(matcher.captures(b" homer simpson ", &mut caps).unwrap());
assert_eq!(caps.get(0), Some(m(1, 14)));
assert_eq!(caps.get(1), Some(m(1, 6)));
assert_eq!(caps.get(2), Some(m(7, 14)));
}
#[test]
fn captures_iter() {
let matcher = matcher(r"(?P<a>\w+)\s+(?P<b>\w+)");
let mut caps = matcher.new_captures().unwrap();
let mut matches = vec![];
matcher.captures_iter(b"aa bb cc dd", &mut caps, |caps| {
matches.push(caps.get(0).unwrap());
matches.push(caps.get(1).unwrap());
matches.push(caps.get(2).unwrap());
true
}).unwrap();
assert_eq!(matches, vec![
m(0, 5), m(0, 2), m(3, 5),
m(6, 11), m(6, 8), m(9, 11),
]);
// Test that captures_iter respects short circuiting.
matches.clear();
matcher.captures_iter(b"aa bb cc dd", &mut caps, |caps| {
matches.push(caps.get(0).unwrap());
matches.push(caps.get(1).unwrap());
matches.push(caps.get(2).unwrap());
false
}).unwrap();
assert_eq!(matches, vec![
m(0, 5), m(0, 2), m(3, 5),
]);
}
#[test]
fn try_captures_iter() {
#[derive(Clone, Debug, Eq, PartialEq)]
struct MyError;
let matcher = matcher(r"(?P<a>\w+)\s+(?P<b>\w+)");
let mut caps = matcher.new_captures().unwrap();
let mut matches = vec![];
let err = matcher.try_captures_iter(b"aa bb cc dd", &mut caps, |caps| {
if matches.is_empty() {
matches.push(caps.get(0).unwrap());
matches.push(caps.get(1).unwrap());
matches.push(caps.get(2).unwrap());
Ok(true)
} else {
Err(MyError)
}
}).unwrap().unwrap_err();
assert_eq!(matches, vec![m(0, 5), m(0, 2), m(3, 5)]);
assert_eq!(err, MyError);
}
// Test that our default impls for capturing are correct. Namely, when
// capturing isn't supported by the underlying matcher, then all of the
// various capturing related APIs fail fast.
#[test]
fn no_captures() {
let matcher = matcher_no_caps(r"(?P<a>\w+)\s+(?P<b>\w+)");
assert_eq!(matcher.capture_count(), 0);
assert_eq!(matcher.capture_index("a"), None);
assert_eq!(matcher.capture_index("b"), None);
assert_eq!(matcher.capture_index("nada"), None);
let mut caps = matcher.new_captures().unwrap();
assert!(!matcher.captures(b"homer simpson", &mut caps).unwrap());
let mut called = false;
matcher.captures_iter(b"homer simpson", &mut caps, |_| {
called = true;
true
}).unwrap();
assert!(!called);
}
#[test]
fn replace() {
let matcher = matcher(r"(\w+)\s+(\w+)");
let mut dst = vec![];
matcher.replace(b"aa bb cc dd", &mut dst, |_, dst| {
dst.push(b'z');
true
}).unwrap();
assert_eq!(dst, b"z z");
// Test that replacements respect short circuiting.
dst.clear();
matcher.replace(b"aa bb cc dd", &mut dst, |_, dst| {
dst.push(b'z');
false
}).unwrap();
assert_eq!(dst, b"z cc dd");
}
#[test]
fn replace_with_captures() {
let matcher = matcher(r"(\w+)\s+(\w+)");
let haystack = b"aa bb cc dd";
let mut caps = matcher.new_captures().unwrap();
let mut dst = vec![];
matcher.replace_with_captures(haystack, &mut caps, &mut dst, |caps, dst| {
caps.interpolate(
|name| matcher.capture_index(name),
haystack,
b"$2 $1",
dst,
);
true
}).unwrap();
assert_eq!(dst, b"bb aa dd cc");
// Test that replacements respect short circuiting.
dst.clear();
matcher.replace_with_captures(haystack, &mut caps, &mut dst, |caps, dst| {
caps.interpolate(
|name| matcher.capture_index(name),
haystack,
b"$2 $1",
dst,
);
false
}).unwrap();
assert_eq!(dst, b"bb aa cc dd");
}

6
grep-matcher/tests/tests.rs Normal file
View File

@@ -0,0 +1,6 @@
extern crate grep_matcher;
extern crate regex;
mod util;
mod test_matcher;

104
grep-matcher/tests/util.rs Normal file
View File

@@ -0,0 +1,104 @@
use std::collections::HashMap;
use std::result;
use grep_matcher::{Captures, Match, Matcher, NoCaptures, NoError};
use regex::bytes::{CaptureLocations, Regex};
#[derive(Debug)]
pub struct RegexMatcher {
pub re: Regex,
pub names: HashMap<String, usize>,
}
impl RegexMatcher {
pub fn new(re: Regex) -> RegexMatcher {
let mut names = HashMap::new();
for (i, optional_name) in re.capture_names().enumerate() {
if let Some(name) = optional_name {
names.insert(name.to_string(), i);
}
}
RegexMatcher {
re: re,
names: names,
}
}
}
type Result<T> = result::Result<T, NoError>;
impl Matcher for RegexMatcher {
type Captures = RegexCaptures;
type Error = NoError;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>> {
Ok(self.re
.find_at(haystack, at)
.map(|m| Match::new(m.start(), m.end())))
}
fn new_captures(&self) -> Result<RegexCaptures> {
Ok(RegexCaptures(self.re.capture_locations()))
}
fn captures_at(
&self,
haystack: &[u8],
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool> {
Ok(self.re.captures_read_at(&mut caps.0, haystack, at).is_some())
}
fn capture_count(&self) -> usize {
self.re.captures_len()
}
fn capture_index(&self, name: &str) -> Option<usize> {
self.names.get(name).map(|i| *i)
}
// We purposely don't implement any other methods, so that we test the
// default impls. The "real" Regex impl for Matcher provides a few more
// impls. e.g., Its `find_iter` impl is faster than what we can do here,
// since the regex crate avoids synchronization overhead.
}
#[derive(Debug)]
pub struct RegexMatcherNoCaps(pub Regex);
impl Matcher for RegexMatcherNoCaps {
type Captures = NoCaptures;
type Error = NoError;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>> {
Ok(self.0
.find_at(haystack, at)
.map(|m| Match::new(m.start(), m.end())))
}
fn new_captures(&self) -> Result<NoCaptures> {
Ok(NoCaptures::new())
}
}
#[derive(Clone, Debug)]
pub struct RegexCaptures(CaptureLocations);
impl Captures for RegexCaptures {
fn len(&self) -> usize {
self.0.len()
}
fn get(&self, i: usize) -> Option<Match> {
self.0.pos(i).map(|(s, e)| Match::new(s, e))
}
}

17
grep-pcre2/Cargo.toml Normal file
View File

@@ -0,0 +1,17 @@
[package]
name = "grep-pcre2"
version = "0.1.2" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Use PCRE2 with the 'grep' crate.
"""
documentation = "https://docs.rs/grep-pcre2"
homepage = "https://github.com/BurntSushi/ripgrep"
repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["regex", "grep", "pcre", "backreference", "look"]
license = "Unlicense/MIT"
[dependencies]
grep-matcher = { version = "0.1.1", path = "../grep-matcher" }
pcre2 = "0.1.1"

21
grep-pcre2/LICENSE-MIT Normal file
View File

@@ -0,0 +1,21 @@
The MIT License (MIT)
Copyright (c) 2015 Andrew Gallant
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.

39
grep-pcre2/README.md Normal file
View File

@@ -0,0 +1,39 @@
grep-pcre2
----------
The `grep-pcre2` crate provides an implementation of the `Matcher` trait from
the `grep-matcher` crate. This implementation permits PCRE2 to be used in the
`grep` crate for fast line oriented searching.
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/grep-pcre2.svg)](https://crates.io/crates/grep-pcre2)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
### Documentation
[https://docs.rs/grep-pcre2](https://docs.rs/grep-pcre2)
**NOTE:** You probably don't want to use this crate directly. Instead, you
should prefer the facade defined in the
[`grep`](https://docs.rs/grep)
crate.
If you're looking to just use PCRE2 from Rust, then you probably want the
[`pcre2`](https://docs.rs/pcre2)
crate, which provide high level safe bindings to PCRE2.
### Usage
Add this to your `Cargo.toml`:
```toml
[dependencies]
grep-pcre2 = "0.1"
```
and this to your crate root:
```rust
extern crate grep_pcre2;
```

24
grep-pcre2/UNLICENSE Normal file
View File

@@ -0,0 +1,24 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org/>

59
grep-pcre2/src/error.rs Normal file
View File

@@ -0,0 +1,59 @@
use std::error;
use std::fmt;
/// An error that can occur in this crate.
///
/// Generally, this error corresponds to problems building a regular
/// expression, whether it's in parsing, compilation or a problem with
/// guaranteeing a configured optimization.
#[derive(Clone, Debug)]
pub struct Error {
kind: ErrorKind,
}
impl Error {
pub(crate) fn regex<E: error::Error>(err: E) -> Error {
Error { kind: ErrorKind::Regex(err.to_string()) }
}
/// Return the kind of this error.
pub fn kind(&self) -> &ErrorKind {
&self.kind
}
}
/// The kind of an error that can occur.
#[derive(Clone, Debug)]
pub enum ErrorKind {
/// An error that occurred as a result of parsing a regular expression.
/// This can be a syntax error or an error that results from attempting to
/// compile a regular expression that is too big.
///
/// The string here is the underlying error converted to a string.
Regex(String),
/// Hints that destructuring should not be exhaustive.
///
/// This enum may grow additional variants, so this makes sure clients
/// don't count on exhaustive matching. (Otherwise, adding a new variant
/// could break existing code.)
#[doc(hidden)]
__Nonexhaustive,
}
impl error::Error for Error {
fn description(&self) -> &str {
match self.kind {
ErrorKind::Regex(_) => "regex error",
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}
impl fmt::Display for Error {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self.kind {
ErrorKind::Regex(ref s) => write!(f, "{}", s),
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}

15
grep-pcre2/src/lib.rs Normal file
View File

@@ -0,0 +1,15 @@
/*!
An implementation of `grep-matcher`'s `Matcher` trait for
[PCRE2](https://www.pcre.org/).
*/
#![deny(missing_docs)]
extern crate grep_matcher;
extern crate pcre2;
pub use error::{Error, ErrorKind};
pub use matcher::{RegexCaptures, RegexMatcher, RegexMatcherBuilder};
mod error;
mod matcher;

443
grep-pcre2/src/matcher.rs Normal file
View File

@@ -0,0 +1,443 @@
use std::collections::HashMap;
use grep_matcher::{Captures, Match, Matcher};
use pcre2::bytes::{CaptureLocations, Regex, RegexBuilder};
use error::Error;
/// A builder for configuring the compilation of a PCRE2 regex.
#[derive(Clone, Debug)]
pub struct RegexMatcherBuilder {
builder: RegexBuilder,
case_smart: bool,
word: bool,
}
impl RegexMatcherBuilder {
/// Create a new matcher builder with a default configuration.
pub fn new() -> RegexMatcherBuilder {
RegexMatcherBuilder {
builder: RegexBuilder::new(),
case_smart: false,
word: false,
}
}
/// Compile the given pattern into a PCRE matcher using the current
/// configuration.
///
/// If there was a problem compiling the pattern, then an error is
/// returned.
pub fn build(&self, pattern: &str) -> Result<RegexMatcher, Error> {
let mut builder = self.builder.clone();
if self.case_smart && !has_uppercase_literal(pattern) {
builder.caseless(true);
}
let res =
if self.word {
let pattern = format!(r"(?<!\w)(?:{})(?!\w)", pattern);
builder.build(&pattern)
} else {
builder.build(pattern)
};
res.map_err(Error::regex).map(|regex| {
let mut names = HashMap::new();
for (i, name) in regex.capture_names().iter().enumerate() {
if let Some(ref name) = *name {
names.insert(name.to_string(), i);
}
}
RegexMatcher { regex, names }
})
}
/// Enables case insensitive matching.
///
/// If the `utf` option is also set, then Unicode case folding is used
/// to determine case insensitivity. When the `utf` option is not set,
/// then only standard ASCII case insensitivity is considered.
///
/// This option corresponds to the `i` flag.
pub fn caseless(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.caseless(yes);
self
}
/// Whether to enable "smart case" or not.
///
/// When smart case is enabled, the builder will automatically enable
/// case insensitive matching based on how the pattern is written. Namely,
/// case insensitive mode is enabled when both of the following things
/// are believed to be true:
///
/// 1. The pattern contains at least one literal character. For example,
/// `a\w` contains a literal (`a`) but `\w` does not.
/// 2. Of the literals in the pattern, none of them are considered to be
/// uppercase according to Unicode. For example, `foo\pL` has no
/// uppercase literals but `Foo\pL` does.
///
/// Note that the implementation of this is not perfect. Namely, `\p{Ll}`
/// will prevent case insensitive matching even though it is part of a meta
/// sequence. This bug will probably never be fixed.
pub fn case_smart(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.case_smart = yes;
self
}
/// Enables "dot all" matching.
///
/// When enabled, the `.` metacharacter in the pattern matches any
/// character, include `\n`. When disabled (the default), `.` will match
/// any character except for `\n`.
///
/// This option corresponds to the `s` flag.
pub fn dotall(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.dotall(yes);
self
}
/// Enable "extended" mode in the pattern, where whitespace is ignored.
///
/// This option corresponds to the `x` flag.
pub fn extended(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.extended(yes);
self
}
/// Enable multiline matching mode.
///
/// When enabled, the `^` and `$` anchors will match both at the beginning
/// and end of a subject string, in addition to matching at the start of
/// a line and the end of a line. When disabled, the `^` and `$` anchors
/// will only match at the beginning and end of a subject string.
///
/// This option corresponds to the `m` flag.
pub fn multi_line(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.multi_line(yes);
self
}
/// Enable matching of CRLF as a line terminator.
///
/// When enabled, anchors such as `^` and `$` will match any of the
/// following as a line terminator: `\r`, `\n` or `\r\n`.
///
/// This is disabled by default, in which case, only `\n` is recognized as
/// a line terminator.
pub fn crlf(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.crlf(yes);
self
}
/// Require that all matches occur on word boundaries.
///
/// Enabling this option is subtly different than putting `\b` assertions
/// on both sides of your pattern. In particular, a `\b` assertion requires
/// that one side of it match a word character while the other match a
/// non-word character. This option, in contrast, merely requires that
/// one side match a non-word character.
///
/// For example, `\b-2\b` will not match `foo -2 bar` since `-` is not a
/// word character. However, `-2` with this `word` option enabled will
/// match the `-2` in `foo -2 bar`.
pub fn word(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.word = yes;
self
}
/// Enable Unicode matching mode.
///
/// When enabled, the following patterns become Unicode aware: `\b`, `\B`,
/// `\d`, `\D`, `\s`, `\S`, `\w`, `\W`.
///
/// When set, this implies UTF matching mode. It is not possible to enable
/// Unicode matching mode without enabling UTF matching mode.
///
/// This is disabled by default.
pub fn ucp(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.ucp(yes);
self
}
/// Enable UTF matching mode.
///
/// When enabled, characters are treated as sequences of code units that
/// make up a single codepoint instead of as single bytes. For example,
/// this will cause `.` to match any single UTF-8 encoded codepoint, where
/// as when this is disabled, `.` will any single byte (except for `\n` in
/// both cases, unless "dot all" mode is enabled).
///
/// Note that when UTF matching mode is enabled, every search performed
/// will do a UTF-8 validation check, which can impact performance. The
/// UTF-8 check can be disabled via the `disable_utf_check` option, but it
/// is undefined behavior to enable UTF matching mode and search invalid
/// UTF-8.
///
/// This is disabled by default.
pub fn utf(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.utf(yes);
self
}
/// When UTF matching mode is enabled, this will disable the UTF checking
/// that PCRE2 will normally perform automatically. If UTF matching mode
/// is not enabled, then this has no effect.
///
/// UTF checking is enabled by default when UTF matching mode is enabled.
/// If UTF matching mode is enabled and UTF checking is enabled, then PCRE2
/// will return an error if you attempt to search a subject string that is
/// not valid UTF-8.
///
/// # Safety
///
/// It is undefined behavior to disable the UTF check in UTF matching mode
/// and search a subject string that is not valid UTF-8. When the UTF check
/// is disabled, callers must guarantee that the subject string is valid
/// UTF-8.
pub unsafe fn disable_utf_check(&mut self) -> &mut RegexMatcherBuilder {
self.builder.disable_utf_check();
self
}
/// Enable PCRE2's JIT and return an error if it's not available.
///
/// This generally speeds up matching quite a bit. The downside is that it
/// can increase the time it takes to compile a pattern.
///
/// If the JIT isn't available or if JIT compilation returns an error, then
/// regex compilation will fail with the corresponding error.
///
/// This is disabled by default, and always overrides `jit_if_available`.
pub fn jit(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.jit(yes);
self
}
/// Enable PCRE2's JIT if it's available.
///
/// This generally speeds up matching quite a bit. The downside is that it
/// can increase the time it takes to compile a pattern.
///
/// If the JIT isn't available or if JIT compilation returns an error,
/// then a debug message with the error will be emitted and the regex will
/// otherwise silently fall back to non-JIT matching.
///
/// This is disabled by default, and always overrides `jit`.
pub fn jit_if_available(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.builder.jit_if_available(yes);
self
}
}
/// An implementation of the `Matcher` trait using PCRE2.
#[derive(Clone, Debug)]
pub struct RegexMatcher {
regex: Regex,
names: HashMap<String, usize>,
}
impl RegexMatcher {
/// Create a new matcher from the given pattern using the default
/// configuration.
pub fn new(pattern: &str) -> Result<RegexMatcher, Error> {
RegexMatcherBuilder::new().build(pattern)
}
}
impl Matcher for RegexMatcher {
type Captures = RegexCaptures;
type Error = Error;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, Error> {
Ok(self.regex
.find_at(haystack, at)
.map_err(Error::regex)?
.map(|m| Match::new(m.start(), m.end())))
}
fn new_captures(&self) -> Result<RegexCaptures, Error> {
Ok(RegexCaptures::new(self.regex.capture_locations()))
}
fn capture_count(&self) -> usize {
self.regex.captures_len()
}
fn capture_index(&self, name: &str) -> Option<usize> {
self.names.get(name).map(|i| *i)
}
fn try_find_iter<F, E>(
&self,
haystack: &[u8],
mut matched: F,
) -> Result<Result<(), E>, Error>
where F: FnMut(Match) -> Result<bool, E>
{
for result in self.regex.find_iter(haystack) {
let m = result.map_err(Error::regex)?;
match matched(Match::new(m.start(), m.end())) {
Ok(true) => continue,
Ok(false) => return Ok(Ok(())),
Err(err) => return Ok(Err(err)),
}
}
Ok(Ok(()))
}
fn captures_at(
&self,
haystack: &[u8],
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, Error> {
Ok(self.regex
.captures_read_at(&mut caps.locs, haystack, at)
.map_err(Error::regex)?
.is_some())
}
}
/// Represents the match offsets of each capturing group in a match.
///
/// The first, or `0`th capture group, always corresponds to the entire match
/// and is guaranteed to be present when a match occurs. The next capture
/// group, at index `1`, corresponds to the first capturing group in the regex,
/// ordered by the position at which the left opening parenthesis occurs.
///
/// Note that not all capturing groups are guaranteed to be present in a match.
/// For example, in the regex, `(?P<foo>\w)|(?P<bar>\W)`, only one of `foo`
/// or `bar` will ever be set in any given match.
///
/// In order to access a capture group by name, you'll need to first find the
/// index of the group using the corresponding matcher's `capture_index`
/// method, and then use that index with `RegexCaptures::get`.
#[derive(Clone, Debug)]
pub struct RegexCaptures {
/// Where the locations are stored.
locs: CaptureLocations,
}
impl Captures for RegexCaptures {
fn len(&self) -> usize {
self.locs.len()
}
fn get(&self, i: usize) -> Option<Match> {
self.locs.get(i).map(|(s, e)| Match::new(s, e))
}
}
impl RegexCaptures {
pub(crate) fn new(locs: CaptureLocations) -> RegexCaptures {
RegexCaptures { locs }
}
}
/// Determine whether the pattern contains an uppercase character which should
/// negate the effect of the smart-case option.
///
/// Ideally we would be able to check the AST in order to correctly handle
/// things like '\p{Ll}' and '\p{Lu}' (which should be treated as explicitly
/// cased), but PCRE doesn't expose enough details for that kind of analysis.
/// For now, our 'good enough' solution is to simply perform a semi-naïve
/// scan of the input pattern and ignore all characters following a '\'. The
/// This at least lets us support the most common cases, like 'foo\w' and
/// 'foo\S', in an intuitive manner.
fn has_uppercase_literal(pattern: &str) -> bool {
let mut chars = pattern.chars();
while let Some(c) = chars.next() {
if c == '\\' {
chars.next();
} else if c.is_uppercase() {
return true;
}
}
false
}
#[cfg(test)]
mod tests {
use grep_matcher::{LineMatchKind, Matcher};
use super::*;
// Test that enabling word matches does the right thing and demonstrate
// the difference between it and surrounding the regex in `\b`.
#[test]
fn word() {
let matcher = RegexMatcherBuilder::new()
.word(true)
.build(r"-2")
.unwrap();
assert!(matcher.is_match(b"abc -2 foo").unwrap());
let matcher = RegexMatcherBuilder::new()
.word(false)
.build(r"\b-2\b")
.unwrap();
assert!(!matcher.is_match(b"abc -2 foo").unwrap());
}
// Test that enabling CRLF permits `$` to match at the end of a line.
#[test]
fn line_terminator_crlf() {
// Test normal use of `$` with a `\n` line terminator.
let matcher = RegexMatcherBuilder::new()
.multi_line(true)
.build(r"abc$")
.unwrap();
assert!(matcher.is_match(b"abc\n").unwrap());
// Test that `$` doesn't match at `\r\n` boundary normally.
let matcher = RegexMatcherBuilder::new()
.multi_line(true)
.build(r"abc$")
.unwrap();
assert!(!matcher.is_match(b"abc\r\n").unwrap());
// Now check the CRLF handling.
let matcher = RegexMatcherBuilder::new()
.multi_line(true)
.crlf(true)
.build(r"abc$")
.unwrap();
assert!(matcher.is_match(b"abc\r\n").unwrap());
}
// Test that smart case works.
#[test]
fn case_smart() {
let matcher = RegexMatcherBuilder::new()
.case_smart(true)
.build(r"abc")
.unwrap();
assert!(matcher.is_match(b"ABC").unwrap());
let matcher = RegexMatcherBuilder::new()
.case_smart(true)
.build(r"aBc")
.unwrap();
assert!(!matcher.is_match(b"ABC").unwrap());
}
// Test that finding candidate lines works as expected.
#[test]
fn candidate_lines() {
fn is_confirmed(m: LineMatchKind) -> bool {
match m {
LineMatchKind::Confirmed(_) => true,
_ => false,
}
}
let matcher = RegexMatcherBuilder::new()
.build(r"\wfoo\s")
.unwrap();
let m = matcher.find_candidate_line(b"afoo ").unwrap().unwrap();
assert!(is_confirmed(m));
}
}

31
grep-printer/Cargo.toml Normal file
View File

@@ -0,0 +1,31 @@
[package]
name = "grep-printer"
version = "0.1.1" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
An implementation of the grep crate's Sink trait that provides standard
printing of search results, similar to grep itself.
"""
documentation = "https://docs.rs/grep-printer"
homepage = "https://github.com/BurntSushi/ripgrep"
repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["grep", "pattern", "print", "printer", "sink"]
license = "Unlicense/MIT"
[features]
default = ["serde1"]
serde1 = ["base64", "serde", "serde_derive", "serde_json"]
[dependencies]
base64 = { version = "0.10.0", optional = true }
bstr = "0.1.2"
grep-matcher = { version = "0.1.1", path = "../grep-matcher" }
grep-searcher = { version = "0.1.1", path = "../grep-searcher" }
termcolor = "1.0.4"
serde = { version = "1.0.77", optional = true }
serde_derive = { version = "1.0.77", optional = true }
serde_json = { version = "1.0.27", optional = true }
[dev-dependencies]
grep-regex = { version = "0.1.1", path = "../grep-regex" }

21
grep-printer/LICENSE-MIT Normal file
View File

@@ -0,0 +1,21 @@
The MIT License (MIT)
Copyright (c) 2015 Andrew Gallant
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.

35
grep-printer/README.md Normal file
View File

@@ -0,0 +1,35 @@
grep-printer
------------
Print results from line oriented searching in a human readable, aggregate or
JSON Lines format.
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/grep-printer.svg)](https://crates.io/crates/grep-printer)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
### Documentation
[https://docs.rs/grep-printer](https://docs.rs/grep-printer)
**NOTE:** You probably don't want to use this crate directly. Instead, you
should prefer the facade defined in the
[`grep`](https://docs.rs/grep)
crate.
### Usage
Add this to your `Cargo.toml`:
```toml
[dependencies]
grep-printer = "0.1"
```
and this to your crate root:
```rust
extern crate grep_printer;
```

24
grep-printer/UNLICENSE Normal file
View File

@@ -0,0 +1,24 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org/>

394
grep-printer/src/color.rs Normal file
View File

@@ -0,0 +1,394 @@
use std::error;
use std::fmt;
use std::str::FromStr;
use termcolor::{Color, ColorSpec, ParseColorError};
/// Returns a default set of color specifications.
///
/// This may change over time, but the color choices are meant to be fairly
/// conservative that work across terminal themes.
///
/// Additional color specifications can be added to the list returned. More
/// recently added specifications override previously added specifications.
pub fn default_color_specs() -> Vec<UserColorSpec> {
vec![
#[cfg(unix)]
"path:fg:magenta".parse().unwrap(),
#[cfg(windows)]
"path:fg:cyan".parse().unwrap(),
"line:fg:green".parse().unwrap(),
"match:fg:red".parse().unwrap(),
"match:style:bold".parse().unwrap(),
]
}
/// An error that can occur when parsing color specifications.
#[derive(Clone, Debug, Eq, PartialEq)]
pub enum ColorError {
/// This occurs when an unrecognized output type is used.
UnrecognizedOutType(String),
/// This occurs when an unrecognized spec type is used.
UnrecognizedSpecType(String),
/// This occurs when an unrecognized color name is used.
UnrecognizedColor(String, String),
/// This occurs when an unrecognized style attribute is used.
UnrecognizedStyle(String),
/// This occurs when the format of a color specification is invalid.
InvalidFormat(String),
}
impl error::Error for ColorError {
fn description(&self) -> &str {
match *self {
ColorError::UnrecognizedOutType(_) => "unrecognized output type",
ColorError::UnrecognizedSpecType(_) => "unrecognized spec type",
ColorError::UnrecognizedColor(_, _) => "unrecognized color name",
ColorError::UnrecognizedStyle(_) => "unrecognized style attribute",
ColorError::InvalidFormat(_) => "invalid color spec",
}
}
}
impl ColorError {
fn from_parse_error(err: ParseColorError) -> ColorError {
ColorError::UnrecognizedColor(
err.invalid().to_string(),
err.to_string(),
)
}
}
impl fmt::Display for ColorError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match *self {
ColorError::UnrecognizedOutType(ref name) => {
write!(
f,
"unrecognized output type '{}'. Choose from: \
path, line, column, match.",
name,
)
}
ColorError::UnrecognizedSpecType(ref name) => {
write!(
f,
"unrecognized spec type '{}'. Choose from: \
fg, bg, style, none.",
name,
)
}
ColorError::UnrecognizedColor(_, ref msg) => {
write!(f, "{}", msg)
}
ColorError::UnrecognizedStyle(ref name) => {
write!(
f,
"unrecognized style attribute '{}'. Choose from: \
nobold, bold, nointense, intense, nounderline, \
underline.",
name,
)
}
ColorError::InvalidFormat(ref original) => {
write!(
f,
"invalid color spec format: '{}'. Valid format \
is '(path|line|column|match):(fg|bg|style):(value)'.",
original,
)
}
}
}
}
/// A merged set of color specifications.
///
/// This set of color specifications represents the various color types that
/// are supported by the printers in this crate. A set of color specifications
/// can be created from a sequence of
/// [`UserColorSpec`s](struct.UserColorSpec.html).
#[derive(Clone, Debug, Default, Eq, PartialEq)]
pub struct ColorSpecs {
path: ColorSpec,
line: ColorSpec,
column: ColorSpec,
matched: ColorSpec,
}
/// A single color specification provided by the user.
///
/// ## Format
///
/// The format of a `Spec` is a triple: `{type}:{attribute}:{value}`. Each
/// component is defined as follows:
///
/// * `{type}` can be one of `path`, `line`, `column` or `match`.
/// * `{attribute}` can be one of `fg`, `bg` or `style`. `{attribute}` may also
/// be the special value `none`, in which case, `{value}` can be omitted.
/// * `{value}` is either a color name (for `fg`/`bg`) or a style instruction.
///
/// `{type}` controls which part of the output should be styled.
///
/// When `{attribute}` is `none`, then this should cause any existing style
/// settings to be cleared for the specified `type`.
///
/// `{value}` should be a color when `{attribute}` is `fg` or `bg`, or it
/// should be a style instruction when `{attribute}` is `style`. When
/// `{attribute}` is `none`, `{value}` must be omitted.
///
/// Valid colors are `black`, `blue`, `green`, `red`, `cyan`, `magenta`,
/// `yellow`, `white`. Extended colors can also be specified, and are formatted
/// as `x` (for 256-bit colors) or `x,x,x` (for 24-bit true color), where
/// `x` is a number between 0 and 255 inclusive. `x` may be given as a normal
/// decimal number of a hexadecimal number, where the latter is prefixed by
/// `0x`.
///
/// Valid style instructions are `nobold`, `bold`, `intense`, `nointense`,
/// `underline`, `nounderline`.
///
/// ## Example
///
/// The standard way to build a `UserColorSpec` is to parse it from a string.
/// Once multiple `UserColorSpec`s have been constructed, they can be provided
/// to the standard printer where they will automatically be applied to the
/// output.
///
/// A `UserColorSpec` can also be converted to a `termcolor::ColorSpec`:
///
/// ```rust
/// extern crate grep_printer;
/// extern crate termcolor;
///
/// # fn main() {
/// use termcolor::{Color, ColorSpec};
/// use grep_printer::UserColorSpec;
///
/// let user_spec1: UserColorSpec = "path:fg:blue".parse().unwrap();
/// let user_spec2: UserColorSpec = "match:bg:0xff,0x7f,0x00".parse().unwrap();
///
/// let spec1 = user_spec1.to_color_spec();
/// let spec2 = user_spec2.to_color_spec();
///
/// assert_eq!(spec1.fg(), Some(&Color::Blue));
/// assert_eq!(spec2.bg(), Some(&Color::Rgb(0xFF, 0x7F, 0x00)));
/// # }
/// ```
#[derive(Clone, Debug, Eq, PartialEq)]
pub struct UserColorSpec {
ty: OutType,
value: SpecValue,
}
impl UserColorSpec {
/// Convert this user provided color specification to a specification that
/// can be used with `termcolor`. This drops the type of this specification
/// (where the type indicates where the color is applied in the standard
/// printer, e.g., to the file path or the line numbers, etc.).
pub fn to_color_spec(&self) -> ColorSpec {
let mut spec = ColorSpec::default();
self.value.merge_into(&mut spec);
spec
}
}
/// The actual value given by the specification.
#[derive(Clone, Debug, Eq, PartialEq)]
enum SpecValue {
None,
Fg(Color),
Bg(Color),
Style(Style),
}
/// The set of configurable portions of ripgrep's output.
#[derive(Clone, Debug, Eq, PartialEq)]
enum OutType {
Path,
Line,
Column,
Match,
}
/// The specification type.
#[derive(Clone, Debug, Eq, PartialEq)]
enum SpecType {
Fg,
Bg,
Style,
None,
}
/// The set of available styles for use in the terminal.
#[derive(Clone, Debug, Eq, PartialEq)]
enum Style {
Bold,
NoBold,
Intense,
NoIntense,
Underline,
NoUnderline
}
impl ColorSpecs {
/// Create color specifications from a list of user supplied
/// specifications.
pub fn new(specs: &[UserColorSpec]) -> ColorSpecs {
let mut merged = ColorSpecs::default();
for spec in specs {
match spec.ty {
OutType::Path => spec.merge_into(&mut merged.path),
OutType::Line => spec.merge_into(&mut merged.line),
OutType::Column => spec.merge_into(&mut merged.column),
OutType::Match => spec.merge_into(&mut merged.matched),
}
}
merged
}
/// Create a default set of specifications that have color.
///
/// This is distinct from `ColorSpecs`'s `Default` implementation in that
/// this provides a set of default color choices, where as the `Default`
/// implementation provides no color choices.
pub fn default_with_color() -> ColorSpecs {
ColorSpecs::new(&default_color_specs())
}
/// Return the color specification for coloring file paths.
pub fn path(&self) -> &ColorSpec {
&self.path
}
/// Return the color specification for coloring line numbers.
pub fn line(&self) -> &ColorSpec {
&self.line
}
/// Return the color specification for coloring column numbers.
pub fn column(&self) -> &ColorSpec {
&self.column
}
/// Return the color specification for coloring matched text.
pub fn matched(&self) -> &ColorSpec {
&self.matched
}
}
impl UserColorSpec {
/// Merge this spec into the given color specification.
fn merge_into(&self, cspec: &mut ColorSpec) {
self.value.merge_into(cspec);
}
}
impl SpecValue {
/// Merge this spec value into the given color specification.
fn merge_into(&self, cspec: &mut ColorSpec) {
match *self {
SpecValue::None => cspec.clear(),
SpecValue::Fg(ref color) => { cspec.set_fg(Some(color.clone())); }
SpecValue::Bg(ref color) => { cspec.set_bg(Some(color.clone())); }
SpecValue::Style(ref style) => {
match *style {
Style::Bold => { cspec.set_bold(true); }
Style::NoBold => { cspec.set_bold(false); }
Style::Intense => { cspec.set_intense(true); }
Style::NoIntense => { cspec.set_intense(false); }
Style::Underline => { cspec.set_underline(true); }
Style::NoUnderline => { cspec.set_underline(false); }
}
}
}
}
}
impl FromStr for UserColorSpec {
type Err = ColorError;
fn from_str(s: &str) -> Result<UserColorSpec, ColorError> {
let pieces: Vec<&str> = s.split(':').collect();
if pieces.len() <= 1 || pieces.len() > 3 {
return Err(ColorError::InvalidFormat(s.to_string()));
}
let otype: OutType = pieces[0].parse()?;
match pieces[1].parse()? {
SpecType::None => {
Ok(UserColorSpec {
ty: otype,
value: SpecValue::None,
})
}
SpecType::Style => {
if pieces.len() < 3 {
return Err(ColorError::InvalidFormat(s.to_string()));
}
let style: Style = pieces[2].parse()?;
Ok(UserColorSpec { ty: otype, value: SpecValue::Style(style) })
}
SpecType::Fg => {
if pieces.len() < 3 {
return Err(ColorError::InvalidFormat(s.to_string()));
}
let color: Color = pieces[2]
.parse()
.map_err(ColorError::from_parse_error)?;
Ok(UserColorSpec { ty: otype, value: SpecValue::Fg(color) })
}
SpecType::Bg => {
if pieces.len() < 3 {
return Err(ColorError::InvalidFormat(s.to_string()));
}
let color: Color = pieces[2]
.parse()
.map_err(ColorError::from_parse_error)?;
Ok(UserColorSpec { ty: otype, value: SpecValue::Bg(color) })
}
}
}
}
impl FromStr for OutType {
type Err = ColorError;
fn from_str(s: &str) -> Result<OutType, ColorError> {
match &*s.to_lowercase() {
"path" => Ok(OutType::Path),
"line" => Ok(OutType::Line),
"column" => Ok(OutType::Column),
"match" => Ok(OutType::Match),
_ => Err(ColorError::UnrecognizedOutType(s.to_string())),
}
}
}
impl FromStr for SpecType {
type Err = ColorError;
fn from_str(s: &str) -> Result<SpecType, ColorError> {
match &*s.to_lowercase() {
"fg" => Ok(SpecType::Fg),
"bg" => Ok(SpecType::Bg),
"style" => Ok(SpecType::Style),
"none" => Ok(SpecType::None),
_ => Err(ColorError::UnrecognizedSpecType(s.to_string())),
}
}
}
impl FromStr for Style {
type Err = ColorError;
fn from_str(s: &str) -> Result<Style, ColorError> {
match &*s.to_lowercase() {
"bold" => Ok(Style::Bold),
"nobold" => Ok(Style::NoBold),
"intense" => Ok(Style::Intense),
"nointense" => Ok(Style::NoIntense),
"underline" => Ok(Style::Underline),
"nounderline" => Ok(Style::NoUnderline),
_ => Err(ColorError::UnrecognizedStyle(s.to_string())),
}
}
}

90
grep-printer/src/counter.rs Normal file
View File

@@ -0,0 +1,90 @@
use std::io::{self, Write};
use termcolor::{ColorSpec, WriteColor};
/// A writer that counts the number of bytes that have been successfully
/// written.
#[derive(Clone, Debug)]
pub struct CounterWriter<W> {
wtr: W,
count: u64,
total_count: u64,
}
impl<W: Write> CounterWriter<W> {
pub fn new(wtr: W) -> CounterWriter<W> {
CounterWriter { wtr: wtr, count: 0, total_count: 0 }
}
}
impl<W> CounterWriter<W> {
/// Returns the total number of bytes written since construction or the
/// last time `reset` was called.
pub fn count(&self) -> u64 {
self.count
}
/// Returns the total number of bytes written since construction.
pub fn total_count(&self) -> u64 {
self.total_count + self.count
}
/// Resets the number of bytes written to `0`.
pub fn reset_count(&mut self) {
self.total_count += self.count;
self.count = 0;
}
/// Clear resets all counting related state for this writer.
///
/// After this call, the total count of bytes written to the underlying
/// writer is erased and reset.
#[allow(dead_code)]
pub fn clear(&mut self) {
self.count = 0;
self.total_count = 0;
}
#[allow(dead_code)]
pub fn get_ref(&self) -> &W {
&self.wtr
}
pub fn get_mut(&mut self) -> &mut W {
&mut self.wtr
}
pub fn into_inner(self) -> W {
self.wtr
}
}
impl<W: Write> Write for CounterWriter<W> {
fn write(&mut self, buf: &[u8]) -> Result<usize, io::Error> {
let n = self.wtr.write(buf)?;
self.count += n as u64;
Ok(n)
}
fn flush(&mut self) -> Result<(), io::Error> {
self.wtr.flush()
}
}
impl<W: WriteColor> WriteColor for CounterWriter<W> {
fn supports_color(&self) -> bool {
self.wtr.supports_color()
}
fn set_color(&mut self, spec: &ColorSpec) -> io::Result<()> {
self.wtr.set_color(spec)
}
fn reset(&mut self) -> io::Result<()> {
self.wtr.reset()
}
fn is_synchronous(&self) -> bool {
self.wtr.is_synchronous()
}
}

963
grep-printer/src/json.rs Normal file
View File

@@ -0,0 +1,963 @@
use std::io::{self, Write};
use std::path::Path;
use std::time::Instant;
use grep_matcher::{Match, Matcher};
use grep_searcher::{
Searcher,
Sink, SinkError, SinkContext, SinkContextKind, SinkFinish, SinkMatch,
};
use serde_json as json;
use counter::CounterWriter;
use jsont;
use stats::Stats;
/// The configuration for the JSON printer.
///
/// This is manipulated by the JSONBuilder and then referenced by the actual
/// implementation. Once a printer is build, the configuration is frozen and
/// cannot changed.
#[derive(Debug, Clone)]
struct Config {
pretty: bool,
max_matches: Option<u64>,
always_begin_end: bool,
}
impl Default for Config {
fn default() -> Config {
Config {
pretty: false,
max_matches: None,
always_begin_end: false,
}
}
}
/// A builder for a JSON lines printer.
///
/// The builder permits configuring how the printer behaves. The JSON printer
/// has fewer configuration options than the standard printer because it is
/// a structured format, and the printer always attempts to find the most
/// information possible.
///
/// Some configuration options, such as whether line numbers are included or
/// whether contextual lines are shown, are drawn directly from the
/// `grep_searcher::Searcher`'s configuration.
///
/// Once a `JSON` printer is built, its configuration cannot be changed.
#[derive(Clone, Debug)]
pub struct JSONBuilder {
config: Config,
}
impl JSONBuilder {
/// Return a new builder for configuring the JSON printer.
pub fn new() -> JSONBuilder {
JSONBuilder { config: Config::default() }
}
/// Create a JSON printer that writes results to the given writer.
pub fn build<W: io::Write>(&self, wtr: W) -> JSON<W> {
JSON {
config: self.config.clone(),
wtr: CounterWriter::new(wtr),
matches: vec![],
}
}
/// Print JSON in a pretty printed format.
///
/// Enabling this will no longer produce a "JSON lines" format, in that
/// each JSON object printed may span multiple lines.
///
/// This is disabled by default.
pub fn pretty(&mut self, yes: bool) -> &mut JSONBuilder {
self.config.pretty = yes;
self
}
/// Set the maximum amount of matches that are printed.
///
/// If multi line search is enabled and a match spans multiple lines, then
/// that match is counted exactly once for the purposes of enforcing this
/// limit, regardless of how many lines it spans.
pub fn max_matches(&mut self, limit: Option<u64>) -> &mut JSONBuilder {
self.config.max_matches = limit;
self
}
/// When enabled, the `begin` and `end` messages are always emitted, even
/// when no match is found.
///
/// When disabled, the `begin` and `end` messages are only shown if there
/// is at least one `match` or `context` message.
///
/// This is disabled by default.
pub fn always_begin_end(&mut self, yes: bool) -> &mut JSONBuilder {
self.config.always_begin_end = yes;
self
}
}
/// The JSON printer, which emits results in a JSON lines format.
///
/// This type is generic over `W`, which represents any implementation of
/// the standard library `io::Write` trait.
///
/// # Format
///
/// This section describes the JSON format used by this printer.
///
/// To skip the rigamarole, take a look at the
/// [example](#example)
/// at the end.
///
/// ## Overview
///
/// The format of this printer is the [JSON Lines](http://jsonlines.org/)
/// format. Specifically, this printer emits a sequence of messages, where
/// each message is encoded as a single JSON value on a single line. There are
/// four different types of messages (and this number may expand over time):
///
/// * **begin** - A message that indicates a file is being searched.
/// * **end** - A message the indicates a file is done being searched. This
/// message also include summary statistics about the search.
/// * **match** - A message that indicates a match was found. This includes
/// the text and offsets of the match.
/// * **context** - A message that indicates a contextual line was found.
/// This includes the text of the line, along with any match information if
/// the search was inverted.
///
/// Every message is encoded in the same envelope format, which includes a tag
/// indicating the message type along with an object for the payload:
///
/// ```json
/// {
/// "type": "{begin|end|match|context}",
/// "data": { ... }
/// }
/// ```
///
/// The message itself is encoded in the envelope's `data` key.
///
/// ## Text encoding
///
/// Before describing each message format, we first must briefly discuss text
/// encoding, since it factors into every type of message. In particular, JSON
/// may only be encoded in UTF-8, UTF-16 or UTF-32. For the purposes of this
/// printer, we need only worry about UTF-8. The problem here is that searching
/// is not limited to UTF-8 exclusively, which in turn implies that matches
/// may be reported that contain invalid UTF-8. Moreover, this printer may
/// also print file paths, and the encoding of file paths is itself not
/// guarnateed to be valid UTF-8. Therefore, this printer must deal with the
/// presence of invalid UTF-8 somehow. The printer could silently ignore such
/// things completely, or even lossily transcode invalid UTF-8 to valid UTF-8
/// by replacing all invalid sequences with the Unicode replacement character.
/// However, this would prevent consumers of this format from accessing the
/// original data in a non-lossy way.
///
/// Therefore, this printer will emit valid UTF-8 encoded bytes as normal
/// JSON strings and otherwise base64 encode data that isn't valid UTF-8. To
/// communicate whether this process occurs or not, strings are keyed by the
/// name `text` where as arbitrary bytes are keyed by `bytes`.
///
/// For example, when a path is included in a message, it is formatted like so,
/// if and only if the path is valid UTF-8:
///
/// ```json
/// {
/// "path": {
/// "text": "/home/ubuntu/lib.rs"
/// }
/// }
/// ```
///
/// If instead our path was `/home/ubuntu/lib\xFF.rs`, where the `\xFF` byte
/// makes it invalid UTF-8, the path would instead be encoded like so:
///
/// ```json
/// {
/// "path": {
/// "bytes": "L2hvbWUvdWJ1bnR1L2xpYv8ucnM="
/// }
/// }
/// ```
///
/// This same representation is used for reporting matches as well.
///
/// The printer guarantees that the `text` field is used whenever the
/// underlying bytes are valid UTF-8.
///
/// ## Wire format
///
/// This section documents the wire format emitted by this printer, starting
/// with the four types of messages.
///
/// Each message has its own format, and is contained inside an envelope that
/// indicates the type of message. The envelope has these fields:
///
/// * **type** - A string indicating the type of this message. It may be one
/// of four possible strings: `begin`, `end`, `match` or `context`. This
/// list may expand over time.
/// * **data** - The actual message data. The format of this field depends on
/// the value of `type`. The possible message formats are
/// [`begin`](#message-begin),
/// [`end`](#message-end),
/// [`match`](#message-match),
/// [`context`](#message-context).
///
/// #### Message: **begin**
///
/// This message indicates that a search has begun. It has these fields:
///
/// * **path** - An
/// [arbitrary data object](#object-arbitrary-data)
/// representing the file path corresponding to the search, if one is
/// present. If no file path is available, then this field is `null`.
///
/// #### Message: **end**
///
/// This message indicates that a search has finished. It has these fields:
///
/// * **path** - An
/// [arbitrary data object](#object-arbitrary-data)
/// representing the file path corresponding to the search, if one is
/// present. If no file path is available, then this field is `null`.
/// * **binary_offset** - The absolute offset in the data searched
/// corresponding to the place at which binary data was detected. If no
/// binary data was detected (or if binary detection was disabled), then this
/// field is `null`.
/// * **stats** - A [`stats` object](#object-stats) that contains summary
/// statistics for the previous search.
///
/// #### Message: **match**
///
/// This message indicates that a match has been found. A match generally
/// corresponds to a single line of text, although it may correspond to
/// multiple lines if the search can emit matches over multiple lines. It
/// has these fields:
///
/// * **path** - An
/// [arbitrary data object](#object-arbitrary-data)
/// representing the file path corresponding to the search, if one is
/// present. If no file path is available, then this field is `null`.
/// * **lines** - An
/// [arbitrary data object](#object-arbitrary-data)
/// representing one or more lines contained in this match.
/// * **line_number** - If the searcher has been configured to report line
/// numbers, then this corresponds to the line number of the first line
/// in `lines`. If no line numbers are available, then this is `null`.
/// * **absolute_offset** - The absolute byte offset corresponding to the start
/// of `lines` in the data being searched.
/// * **submatches** - An array of [`submatch` objects](#object-submatch)
/// corresponding to matches in `lines`. The offsets included in each
/// `submatch` correspond to byte offsets into `lines`. (If `lines` is base64
/// encoded, then the byte offsets correspond to the data after base64
/// decoding.) The `submatch` objects are guaranteed to be sorted by their
/// starting offsets. Note that it is possible for this array to be empty,
/// for example, when searching reports inverted matches.
///
/// #### Message: **context**
///
/// This message indicates that a contextual line has been found. A contextual
/// line is a line that doesn't contain a match, but is generally adjacent to
/// a line that does contain a match. The precise way in which contextual lines
/// are reported is determined by the searcher. It has these fields, which are
/// exactly the same fields found in a [`match`](#message-match):
///
/// * **path** - An
/// [arbitrary data object](#object-arbitrary-data)
/// representing the file path corresponding to the search, if one is
/// present. If no file path is available, then this field is `null`.
/// * **lines** - An
/// [arbitrary data object](#object-arbitrary-data)
/// representing one or more lines contained in this context. This includes
/// line terminators, if they're present.
/// * **line_number** - If the searcher has been configured to report line
/// numbers, then this corresponds to the line number of the first line
/// in `lines`. If no line numbers are available, then this is `null`.
/// * **absolute_offset** - The absolute byte offset corresponding to the start
/// of `lines` in the data being searched.
/// * **submatches** - An array of [`submatch` objects](#object-submatch)
/// corresponding to matches in `lines`. The offsets included in each
/// `submatch` correspond to byte offsets into `lines`. (If `lines` is base64
/// encoded, then the byte offsets correspond to the data after base64
/// decoding.) The `submatch` objects are guaranteed to be sorted by
/// their starting offsets. Note that it is possible for this array to be
/// non-empty, for example, when searching reports inverted matches such that
/// the original matcher could match things in the contextual lines.
///
/// #### Object: **submatch**
///
/// This object describes submatches found within `match` or `context`
/// messages. The `start` and `end` fields indicate the half-open interval on
/// which the match occurs (`start` is included, but `end` is not). It is
/// guaranteed that `start <= end`. It has these fields:
///
/// * **match** - An
/// [arbitrary data object](#object-arbitrary-data)
/// corresponding to the text in this submatch.
/// * **start** - A byte offset indicating the start of this match. This offset
/// is generally reported in terms of the parent object's data. For example,
/// the `lines` field in the
/// [`match`](#message-match) or [`context`](#message-context)
/// messages.
/// * **end** - A byte offset indicating the end of this match. This offset
/// is generally reported in terms of the parent object's data. For example,
/// the `lines` field in the
/// [`match`](#message-match) or [`context`](#message-context)
/// messages.
///
/// #### Object: **stats**
///
/// This object is included in messages and contains summary statistics about
/// a search. It has these fields:
///
/// * **elapsed** - A [`duration` object](#object-duration) describing the
/// length of time that elapsed while performing the search.
/// * **searches** - The number of searches that have run. For this printer,
/// this value is always `1`. (Implementations may emit additional message
/// types that use this same `stats` object that represents summary
/// statistics over multiple searches.)
/// * **searches_with_match** - The number of searches that have run that have
/// found at least one match. This is never more than `searches`.
/// * **bytes_searched** - The total number of bytes that have been searched.
/// * **bytes_printed** - The total number of bytes that have been printed.
/// This includes everything emitted by this printer.
/// * **matched_lines** - The total number of lines that participated in a
/// match. When matches may contain multiple lines, then this includes every
/// line that is part of every match.
/// * **matches** - The total number of matches. There may be multiple matches
/// per line. When matches may contain multiple lines, each match is counted
/// only once, regardless of how many lines it spans.
///
/// #### Object: **duration**
///
/// This object includes a few fields for describing a duration. Two of its
/// fields, `secs` and `nanos`, can be combined to give nanosecond precision
/// on systems that support it. It has these fields:
///
/// * **secs** - A whole number of seconds indicating the length of this
/// duration.
/// * **nanos** - A fractional part of this duration represent by nanoseconds.
/// If nanosecond precision isn't supported, then this is typically rounded
/// up to the nearest number of nanoseconds.
/// * **human** - A human readable string describing the length of the
/// duration. The format of the string is itself unspecified.
///
/// #### Object: **arbitrary data**
///
/// This object is used whenever arbitrary data needs to be represented as a
/// JSON value. This object contains two fields, where generally only one of
/// the fields is present:
///
/// * **text** - A normal JSON string that is UTF-8 encoded. This field is
/// populated if and only if the underlying data is valid UTF-8.
/// * **bytes** - A normal JSON string that is a base64 encoding of the
/// underlying bytes.
///
/// More information on the motivation for this representation can be seen in
/// the section [text encoding](#text-encoding) above.
///
/// ## Example
///
/// This section shows a small example that includes all message types.
///
/// Here's the file we want to search, located at `/home/andrew/sherlock`:
///
/// ```text
/// For the Doctor Watsons of this world, as opposed to the Sherlock
/// Holmeses, success in the province of detective work must always
/// be, to a very large extent, the result of luck. Sherlock Holmes
/// can extract a clew from a wisp of straw or a flake of cigar ash;
/// but Doctor Watson has to have it taken out for him and dusted,
/// and exhibited clearly, with a label attached.
/// ```
///
/// Searching for `Watson` with a `before_context` of `1` with line numbers
/// enabled shows something like this using the standard printer:
///
/// ```text
/// sherlock:1:For the Doctor Watsons of this world, as opposed to the Sherlock
/// --
/// sherlock-4-can extract a clew from a wisp of straw or a flake of cigar ash;
/// sherlock:5:but Doctor Watson has to have it taken out for him and dusted,
/// ```
///
/// Here's what the same search looks like using the JSON wire format described
/// above, where in we show semi-prettified JSON (instead of a strict JSON
/// Lines format), for illustrative purposes:
///
/// ```json
/// {
/// "type": "begin",
/// "data": {
/// "path": {"text": "/home/andrew/sherlock"}}
/// }
/// }
/// {
/// "type": "match",
/// "data": {
/// "path": {"text": "/home/andrew/sherlock"},
/// "lines": {"text": "For the Doctor Watsons of this world, as opposed to the Sherlock\n"},
/// "line_number": 1,
/// "absolute_offset": 0,
/// "submatches": [
/// {"match": {"text": "Watson"}, "start": 15, "end": 21}
/// ]
/// }
/// }
/// {
/// "type": "context",
/// "data": {
/// "path": {"text": "/home/andrew/sherlock"},
/// "lines": {"text": "can extract a clew from a wisp of straw or a flake of cigar ash;\n"},
/// "line_number": 4,
/// "absolute_offset": 193,
/// "submatches": []
/// }
/// }
/// {
/// "type": "match",
/// "data": {
/// "path": {"text": "/home/andrew/sherlock"},
/// "lines": {"text": "but Doctor Watson has to have it taken out for him and dusted,\n"},
/// "line_number": 5,
/// "absolute_offset": 258,
/// "submatches": [
/// {"match": {"text": "Watson"}, "start": 11, "end": 17}
/// ]
/// }
/// }
/// {
/// "type": "end",
/// "data": {
/// "path": {"text": "/home/andrew/sherlock"},
/// "binary_offset": null,
/// "stats": {
/// "elapsed": {"secs": 0, "nanos": 36296, "human": "0.0000s"},
/// "searches": 1,
/// "searches_with_match": 1,
/// "bytes_searched": 367,
/// "bytes_printed": 1151,
/// "matched_lines": 2,
/// "matches": 2
/// }
/// }
/// }
/// ```
#[derive(Debug)]
pub struct JSON<W> {
config: Config,
wtr: CounterWriter<W>,
matches: Vec<Match>,
}
impl<W: io::Write> JSON<W> {
/// Return a JSON lines printer with a default configuration that writes
/// matches to the given writer.
pub fn new(wtr: W) -> JSON<W> {
JSONBuilder::new().build(wtr)
}
/// Return an implementation of `Sink` for the JSON printer.
///
/// This does not associate the printer with a file path, which means this
/// implementation will never print a file path along with the matches.
pub fn sink<'s, M: Matcher>(
&'s mut self,
matcher: M,
) -> JSONSink<'static, 's, M, W> {
JSONSink {
matcher: matcher,
json: self,
path: None,
start_time: Instant::now(),
match_count: 0,
after_context_remaining: 0,
binary_byte_offset: None,
begin_printed: false,
stats: Stats::new(),
}
}
/// Return an implementation of `Sink` associated with a file path.
///
/// When the printer is associated with a path, then it may, depending on
/// its configuration, print the path along with the matches found.
pub fn sink_with_path<'p, 's, M, P>(
&'s mut self,
matcher: M,
path: &'p P,
) -> JSONSink<'p, 's, M, W>
where M: Matcher,
P: ?Sized + AsRef<Path>,
{
JSONSink {
matcher: matcher,
json: self,
path: Some(path.as_ref()),
start_time: Instant::now(),
match_count: 0,
after_context_remaining: 0,
binary_byte_offset: None,
begin_printed: false,
stats: Stats::new(),
}
}
/// Write the given message followed by a new line. The new line is
/// determined from the configuration of the given searcher.
fn write_message(&mut self, message: &jsont::Message) -> io::Result<()> {
if self.config.pretty {
json::to_writer_pretty(&mut self.wtr, message)?;
} else {
json::to_writer(&mut self.wtr, message)?;
}
self.wtr.write(&[b'\n'])?;
Ok(())
}
}
impl<W> JSON<W> {
/// Returns true if and only if this printer has written at least one byte
/// to the underlying writer during any of the previous searches.
pub fn has_written(&self) -> bool {
self.wtr.total_count() > 0
}
/// Return a mutable reference to the underlying writer.
pub fn get_mut(&mut self) -> &mut W {
self.wtr.get_mut()
}
/// Consume this printer and return back ownership of the underlying
/// writer.
pub fn into_inner(self) -> W {
self.wtr.into_inner()
}
}
/// An implementation of `Sink` associated with a matcher and an optional file
/// path for the JSON printer.
///
/// This type is generic over a few type parameters:
///
/// * `'p` refers to the lifetime of the file path, if one is provided. When
/// no file path is given, then this is `'static`.
/// * `'s` refers to the lifetime of the
/// [`JSON`](struct.JSON.html)
/// printer that this type borrows.
/// * `M` refers to the type of matcher used by
/// `grep_searcher::Searcher` that is reporting results to this sink.
/// * `W` refers to the underlying writer that this printer is writing its
/// output to.
#[derive(Debug)]
pub struct JSONSink<'p, 's, M: Matcher, W: 's> {
matcher: M,
json: &'s mut JSON<W>,
path: Option<&'p Path>,
start_time: Instant,
match_count: u64,
after_context_remaining: u64,
binary_byte_offset: Option<u64>,
begin_printed: bool,
stats: Stats,
}
impl<'p, 's, M: Matcher, W: io::Write> JSONSink<'p, 's, M, W> {
/// Returns true if and only if this printer received a match in the
/// previous search.
///
/// This is unaffected by the result of searches before the previous
/// search.
pub fn has_match(&self) -> bool {
self.match_count > 0
}
/// Return the total number of matches reported to this sink.
///
/// This corresponds to the number of times `Sink::matched` is called.
pub fn match_count(&self) -> u64 {
self.match_count
}
/// If binary data was found in the previous search, this returns the
/// offset at which the binary data was first detected.
///
/// The offset returned is an absolute offset relative to the entire
/// set of bytes searched.
///
/// This is unaffected by the result of searches before the previous
/// search. e.g., If the search prior to the previous search found binary
/// data but the previous search found no binary data, then this will
/// return `None`.
pub fn binary_byte_offset(&self) -> Option<u64> {
self.binary_byte_offset
}
/// Return a reference to the stats produced by the printer for all
/// searches executed on this sink.
pub fn stats(&self) -> &Stats {
&self.stats
}
/// Execute the matcher over the given bytes and record the match
/// locations if the current configuration demands match granularity.
fn record_matches(&mut self, bytes: &[u8]) -> io::Result<()> {
self.json.matches.clear();
// If printing requires knowing the location of each individual match,
// then compute and stored those right now for use later. While this
// adds an extra copy for storing the matches, we do amortize the
// allocation for it and this greatly simplifies the printing logic to
// the extent that it's easy to ensure that we never do more than
// one search to find the matches.
let matches = &mut self.json.matches;
self.matcher.find_iter(bytes, |m| {
matches.push(m);
true
}).map_err(io::Error::error_message)?;
// Don't report empty matches appearing at the end of the bytes.
if !matches.is_empty()
&& matches.last().unwrap().is_empty()
&& matches.last().unwrap().start() >= bytes.len()
{
matches.pop().unwrap();
}
Ok(())
}
/// Returns true if this printer should quit.
///
/// This implements the logic for handling quitting after seeing a certain
/// amount of matches. In most cases, the logic is simple, but we must
/// permit all "after" contextual lines to print after reaching the limit.
fn should_quit(&self) -> bool {
let limit = match self.json.config.max_matches {
None => return false,
Some(limit) => limit,
};
if self.match_count < limit {
return false;
}
self.after_context_remaining == 0
}
/// Write the "begin" message.
fn write_begin_message(&mut self) -> io::Result<()> {
if self.begin_printed {
return Ok(());
}
let msg = jsont::Message::Begin(jsont::Begin {
path: self.path,
});
self.json.write_message(&msg)?;
self.begin_printed = true;
Ok(())
}
}
impl<'p, 's, M: Matcher, W: io::Write> Sink for JSONSink<'p, 's, M, W> {
type Error = io::Error;
fn matched(
&mut self,
searcher: &Searcher,
mat: &SinkMatch,
) -> Result<bool, io::Error> {
self.write_begin_message()?;
self.match_count += 1;
self.after_context_remaining = searcher.after_context() as u64;
self.record_matches(mat.bytes())?;
self.stats.add_matches(self.json.matches.len() as u64);
self.stats.add_matched_lines(mat.lines().count() as u64);
let submatches = SubMatches::new(mat.bytes(), &self.json.matches);
let msg = jsont::Message::Match(jsont::Match {
path: self.path,
lines: mat.bytes(),
line_number: mat.line_number(),
absolute_offset: mat.absolute_byte_offset(),
submatches: submatches.as_slice(),
});
self.json.write_message(&msg)?;
Ok(!self.should_quit())
}
fn context(
&mut self,
searcher: &Searcher,
ctx: &SinkContext,
) -> Result<bool, io::Error> {
self.write_begin_message()?;
self.json.matches.clear();
if ctx.kind() == &SinkContextKind::After {
self.after_context_remaining =
self.after_context_remaining.saturating_sub(1);
}
let submatches =
if searcher.invert_match() {
self.record_matches(ctx.bytes())?;
SubMatches::new(ctx.bytes(), &self.json.matches)
} else {
SubMatches::empty()
};
let msg = jsont::Message::Context(jsont::Context {
path: self.path,
lines: ctx.bytes(),
line_number: ctx.line_number(),
absolute_offset: ctx.absolute_byte_offset(),
submatches: submatches.as_slice(),
});
self.json.write_message(&msg)?;
Ok(!self.should_quit())
}
fn begin(
&mut self,
_searcher: &Searcher,
) -> Result<bool, io::Error> {
self.json.wtr.reset_count();
self.start_time = Instant::now();
self.match_count = 0;
self.after_context_remaining = 0;
self.binary_byte_offset = None;
if self.json.config.max_matches == Some(0) {
return Ok(false);
}
if !self.json.config.always_begin_end {
return Ok(true);
}
self.write_begin_message()?;
Ok(true)
}
fn finish(
&mut self,
_searcher: &Searcher,
finish: &SinkFinish,
) -> Result<(), io::Error> {
if !self.begin_printed {
return Ok(());
}
self.binary_byte_offset = finish.binary_byte_offset();
self.stats.add_elapsed(self.start_time.elapsed());
self.stats.add_searches(1);
if self.match_count > 0 {
self.stats.add_searches_with_match(1);
}
self.stats.add_bytes_searched(finish.byte_count());
self.stats.add_bytes_printed(self.json.wtr.count());
let msg = jsont::Message::End(jsont::End {
path: self.path,
binary_offset: finish.binary_byte_offset(),
stats: self.stats.clone(),
});
self.json.write_message(&msg)?;
Ok(())
}
}
/// SubMatches represents a set of matches in a contiguous range of bytes.
///
/// A simpler representation for this would just simply be `Vec<SubMatch>`,
/// but the common case is exactly one match per range of bytes, which we
/// specialize here using a fixed size array without any allocation.
enum SubMatches<'a> {
Empty,
Small([jsont::SubMatch<'a>; 1]),
Big(Vec<jsont::SubMatch<'a>>),
}
impl<'a> SubMatches<'a> {
/// Create a new set of match ranges from a set of matches and the
/// corresponding bytes that those matches apply to.
fn new(bytes: &'a[u8], matches: &[Match]) -> SubMatches<'a> {
if matches.len() == 1 {
let mat = matches[0];
SubMatches::Small([jsont::SubMatch {
m: &bytes[mat],
start: mat.start(),
end: mat.end(),
}])
} else {
let mut match_ranges = vec![];
for &mat in matches {
match_ranges.push(jsont::SubMatch {
m: &bytes[mat],
start: mat.start(),
end: mat.end(),
});
}
SubMatches::Big(match_ranges)
}
}
/// Create an empty set of match ranges.
fn empty() -> SubMatches<'static> {
SubMatches::Empty
}
/// Return this set of match ranges as a slice.
fn as_slice(&self) -> &[jsont::SubMatch] {
match *self {
SubMatches::Empty => &[],
SubMatches::Small(ref x) => x,
SubMatches::Big(ref x) => x,
}
}
}
#[cfg(test)]
mod tests {
use grep_regex::{RegexMatcher, RegexMatcherBuilder};
use grep_matcher::LineTerminator;
use grep_searcher::SearcherBuilder;
use super::{JSON, JSONBuilder};
const SHERLOCK: &'static [u8] = b"\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, success in the province of detective work must always
be, to a very large extent, the result of luck. Sherlock Holmes
can extract a clew from a wisp of straw or a flake of cigar ash;
but Doctor Watson has to have it taken out for him and dusted,
and exhibited clearly, with a label attached.
";
fn printer_contents(
printer: &mut JSON<Vec<u8>>,
) -> String {
String::from_utf8(printer.get_mut().to_owned()).unwrap()
}
#[test]
fn binary_detection() {
use grep_searcher::BinaryDetection;
const BINARY: &'static [u8] = b"\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, success in the province of detective work must always
be, to a very large extent, the result of luck. Sherlock Holmes
can extract a clew \x00 from a wisp of straw or a flake of cigar ash;
but Doctor Watson has to have it taken out for him and dusted,
and exhibited clearly, with a label attached.\
";
let matcher = RegexMatcher::new(
r"Watson"
).unwrap();
let mut printer = JSONBuilder::new()
.build(vec![]);
SearcherBuilder::new()
.binary_detection(BinaryDetection::quit(b'\x00'))
.heap_limit(Some(80))
.build()
.search_reader(&matcher, BINARY, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert_eq!(got.lines().count(), 3);
let last = got.lines().last().unwrap();
assert!(last.contains(r#""binary_offset":212,"#));
}
#[test]
fn max_matches() {
let matcher = RegexMatcher::new(
r"Watson"
).unwrap();
let mut printer = JSONBuilder::new()
.max_matches(Some(1))
.build(vec![]);
SearcherBuilder::new()
.build()
.search_reader(&matcher, SHERLOCK, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert_eq!(got.lines().count(), 3);
}
#[test]
fn no_match() {
let matcher = RegexMatcher::new(
r"DOES NOT MATCH"
).unwrap();
let mut printer = JSONBuilder::new()
.build(vec![]);
SearcherBuilder::new()
.build()
.search_reader(&matcher, SHERLOCK, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert!(got.is_empty());
}
#[test]
fn always_begin_end_no_match() {
let matcher = RegexMatcher::new(
r"DOES NOT MATCH"
).unwrap();
let mut printer = JSONBuilder::new()
.always_begin_end(true)
.build(vec![]);
SearcherBuilder::new()
.build()
.search_reader(&matcher, SHERLOCK, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert_eq!(got.lines().count(), 2);
assert!(got.contains("begin") && got.contains("end"));
}
#[test]
fn missing_crlf() {
let haystack = "test\r\n".as_bytes();
let matcher = RegexMatcherBuilder::new()
.build("test")
.unwrap();
let mut printer = JSONBuilder::new()
.build(vec![]);
SearcherBuilder::new()
.build()
.search_reader(&matcher, haystack, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert_eq!(got.lines().count(), 3);
assert!(
got.lines().nth(1).unwrap().contains(r"test\r\n"),
r"missing 'test\r\n' in '{}'",
got.lines().nth(1).unwrap(),
);
let matcher = RegexMatcherBuilder::new()
.crlf(true)
.build("test")
.unwrap();
let mut printer = JSONBuilder::new()
.build(vec![]);
SearcherBuilder::new()
.line_terminator(LineTerminator::crlf())
.build()
.search_reader(&matcher, haystack, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert_eq!(got.lines().count(), 3);
assert!(
got.lines().nth(1).unwrap().contains(r"test\r\n"),
r"missing 'test\r\n' in '{}'",
got.lines().nth(1).unwrap(),
);
}
}

147
grep-printer/src/jsont.rs Normal file
View File

@@ -0,0 +1,147 @@
// This module defines the types we use for JSON serialization. We specifically
// omit deserialization, partially because there isn't a clear use case for
// them at this time, but also because deserialization will complicate things.
// Namely, the types below are designed in a way that permits JSON
// serialization with little or no allocation. Allocation is often quite
// convenient for deserialization however, so these types would become a bit
// more complex.
use std::borrow::Cow;
use std::path::Path;
use std::str;
use base64;
use serde::{Serialize, Serializer};
use stats::Stats;
#[derive(Serialize)]
#[serde(tag = "type", content = "data")]
#[serde(rename_all = "snake_case")]
pub enum Message<'a> {
Begin(Begin<'a>),
End(End<'a>),
Match(Match<'a>),
Context(Context<'a>),
}
#[derive(Serialize)]
pub struct Begin<'a> {
#[serde(serialize_with = "ser_path")]
pub path: Option<&'a Path>,
}
#[derive(Serialize)]
pub struct End<'a> {
#[serde(serialize_with = "ser_path")]
pub path: Option<&'a Path>,
pub binary_offset: Option<u64>,
pub stats: Stats,
}
#[derive(Serialize)]
pub struct Match<'a> {
#[serde(serialize_with = "ser_path")]
pub path: Option<&'a Path>,
#[serde(serialize_with = "ser_bytes")]
pub lines: &'a [u8],
pub line_number: Option<u64>,
pub absolute_offset: u64,
pub submatches: &'a [SubMatch<'a>],
}
#[derive(Serialize)]
pub struct Context<'a> {
#[serde(serialize_with = "ser_path")]
pub path: Option<&'a Path>,
#[serde(serialize_with = "ser_bytes")]
pub lines: &'a [u8],
pub line_number: Option<u64>,
pub absolute_offset: u64,
pub submatches: &'a [SubMatch<'a>],
}
#[derive(Serialize)]
pub struct SubMatch<'a> {
#[serde(rename = "match")]
#[serde(serialize_with = "ser_bytes")]
pub m: &'a [u8],
pub start: usize,
pub end: usize,
}
/// Data represents things that look like strings, but may actually not be
/// valid UTF-8. To handle this, `Data` is serialized as an object with one
/// of two keys: `text` (for valid UTF-8) or `bytes` (for invalid UTF-8).
///
/// The happy path is valid UTF-8, which streams right through as-is, since
/// it is natively supported by JSON. When invalid UTF-8 is found, then it is
/// represented as arbitrary bytes and base64 encoded.
#[derive(Clone, Debug, Hash, PartialEq, Eq, Serialize)]
#[serde(untagged)]
enum Data<'a> {
Text { text: Cow<'a, str> },
Bytes {
#[serde(serialize_with = "to_base64")]
bytes: &'a [u8],
},
}
impl<'a> Data<'a> {
fn from_bytes(bytes: &[u8]) -> Data {
match str::from_utf8(bytes) {
Ok(text) => Data::Text { text: Cow::Borrowed(text) },
Err(_) => Data::Bytes { bytes },
}
}
#[cfg(unix)]
fn from_path(path: &Path) -> Data {
use std::os::unix::ffi::OsStrExt;
match path.to_str() {
Some(text) => Data::Text { text: Cow::Borrowed(text) },
None => Data::Bytes { bytes: path.as_os_str().as_bytes() },
}
}
#[cfg(not(unix))]
fn from_path(path: &Path) -> Data {
// Using lossy conversion means some paths won't round trip precisely,
// but it's not clear what we should actually do. Serde rejects
// non-UTF-8 paths, and OsStr's are serialized as a sequence of UTF-16
// code units on Windows. Neither seem appropriate for this use case,
// so we do the easy thing for now.
Data::Text { text: path.to_string_lossy() }
}
}
fn to_base64<T, S>(
bytes: T,
ser: S,
) -> Result<S::Ok, S::Error>
where T: AsRef<[u8]>,
S: Serializer
{
ser.serialize_str(&base64::encode(&bytes))
}
fn ser_bytes<T, S>(
bytes: T,
ser: S,
) -> Result<S::Ok, S::Error>
where T: AsRef<[u8]>,
S: Serializer
{
Data::from_bytes(bytes.as_ref()).serialize(ser)
}
fn ser_path<P, S>(
path: &Option<P>,
ser: S,
) -> Result<S::Ok, S::Error>
where P: AsRef<Path>,
S: Serializer
{
path.as_ref().map(|p| Data::from_path(p.as_ref())).serialize(ser)
}

107
grep-printer/src/lib.rs Normal file
View File

@@ -0,0 +1,107 @@
/*!
This crate provides featureful and fast printers that interoperate with the
[`grep-searcher`](https://docs.rs/grep-searcher)
crate.
# Brief overview
The [`Standard`](struct.Standard.html) printer shows results in a human
readable format, and is modeled after the formats used by standard grep-like
tools. Features include, but are not limited to, cross platform terminal
coloring, search & replace, multi-line result handling and reporting summary
statistics.
The [`JSON`](struct.JSON.html) printer shows results in a machine readable
format. To facilitate a stream of search results, the format uses
[JSON Lines](http://jsonlines.org/)
by emitting a series of messages as search results are found.
The [`Summary`](struct.Summary.html) printer shows *aggregate* results for a
single search in a human readable format, and is modeled after similar formats
found in standard grep-like tools. This printer is useful for showing the total
number of matches and/or printing file paths that either contain or don't
contain matches.
# Example
This example shows how to create a "standard" printer and execute a search.
```
extern crate grep_regex;
extern crate grep_printer;
extern crate grep_searcher;
use std::error::Error;
use grep_regex::RegexMatcher;
use grep_printer::Standard;
use grep_searcher::Searcher;
const SHERLOCK: &'static [u8] = b"\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, success in the province of detective work must always
be, to a very large extent, the result of luck. Sherlock Holmes
can extract a clew from a wisp of straw or a flake of cigar ash;
but Doctor Watson has to have it taken out for him and dusted,
and exhibited clearly, with a label attached.
";
# fn main() { example().unwrap(); }
fn example() -> Result<(), Box<Error>> {
let matcher = RegexMatcher::new(r"Sherlock")?;
let mut printer = Standard::new_no_color(vec![]);
Searcher::new().search_slice(&matcher, SHERLOCK, printer.sink(&matcher))?;
// into_inner gives us back the underlying writer we provided to
// new_no_color, which is wrapped in a termcolor::NoColor. Thus, a second
// into_inner gives us back the actual buffer.
let output = String::from_utf8(printer.into_inner().into_inner())?;
let expected = "\
1:For the Doctor Watsons of this world, as opposed to the Sherlock
3:be, to a very large extent, the result of luck. Sherlock Holmes
";
assert_eq!(output, expected);
Ok(())
}
```
*/
#![deny(missing_docs)]
#[cfg(feature = "serde1")]
extern crate base64;
extern crate bstr;
extern crate grep_matcher;
#[cfg(test)]
extern crate grep_regex;
extern crate grep_searcher;
#[cfg(feature = "serde1")]
extern crate serde;
#[cfg(feature = "serde1")]
#[macro_use]
extern crate serde_derive;
#[cfg(feature = "serde1")]
extern crate serde_json;
extern crate termcolor;
pub use color::{ColorError, ColorSpecs, UserColorSpec, default_color_specs};
#[cfg(feature = "serde1")]
pub use json::{JSON, JSONBuilder, JSONSink};
pub use standard::{Standard, StandardBuilder, StandardSink};
pub use stats::Stats;
pub use summary::{Summary, SummaryBuilder, SummaryKind, SummarySink};
pub use util::PrinterPath;
#[macro_use]
mod macros;
mod color;
mod counter;
#[cfg(feature = "serde1")]
mod json;
#[cfg(feature = "serde1")]
mod jsont;
mod standard;
mod stats;
mod summary;
mod util;

24
grep-printer/src/macros.rs Normal file
View File

@@ -0,0 +1,24 @@
/// Like assert_eq, but nicer output for long strings.
#[cfg(test)]
#[macro_export]
macro_rules! assert_eq_printed {
($expected:expr, $got:expr) => {
let expected = &*$expected;
let got = &*$got;
if expected != got {
panic!("
printed outputs differ!
expected:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
{}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
got:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
{}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
", expected, got);
}
}
}

3053
grep-printer/src/standard.rs Normal file
View File

File diff suppressed because it is too large Load Diff

147
grep-printer/src/stats.rs Normal file
View File

@@ -0,0 +1,147 @@
use std::ops::{Add, AddAssign};
use std::time::Duration;
use util::NiceDuration;
/// Summary statistics produced at the end of a search.
///
/// When statistics are reported by a printer, they correspond to all searches
/// executed with that printer.
#[derive(Clone, Debug, Default, PartialEq, Eq)]
#[cfg_attr(feature = "serde1", derive(Serialize))]
pub struct Stats {
elapsed: NiceDuration,
searches: u64,
searches_with_match: u64,
bytes_searched: u64,
bytes_printed: u64,
matched_lines: u64,
matches: u64,
}
impl Add for Stats {
type Output = Stats;
fn add(self, rhs: Stats) -> Stats {
self + &rhs
}
}
impl<'a> Add<&'a Stats> for Stats {
type Output = Stats;
fn add(self, rhs: &'a Stats) -> Stats {
Stats {
elapsed: NiceDuration(self.elapsed.0 + rhs.elapsed.0),
searches: self.searches + rhs.searches,
searches_with_match:
self.searches_with_match + rhs.searches_with_match,
bytes_searched: self.bytes_searched + rhs.bytes_searched,
bytes_printed: self.bytes_printed + rhs.bytes_printed,
matched_lines: self.matched_lines + rhs.matched_lines,
matches: self.matches + rhs.matches,
}
}
}
impl AddAssign for Stats {
fn add_assign(&mut self, rhs: Stats) {
*self += &rhs;
}
}
impl<'a> AddAssign<&'a Stats> for Stats {
fn add_assign(&mut self, rhs: &'a Stats) {
self.elapsed.0 += rhs.elapsed.0;
self.searches += rhs.searches;
self.searches_with_match += rhs.searches_with_match;
self.bytes_searched += rhs.bytes_searched;
self.bytes_printed += rhs.bytes_printed;
self.matched_lines += rhs.matched_lines;
self.matches += rhs.matches;
}
}
impl Stats {
/// Return a new value for tracking aggregate statistics across searches.
///
/// All statistics are set to `0`.
pub fn new() -> Stats {
Stats::default()
}
/// Return the total amount of time elapsed.
pub fn elapsed(&self) -> Duration {
self.elapsed.0
}
/// Return the total number of searches executed.
pub fn searches(&self) -> u64 {
self.searches
}
/// Return the total number of searches that found at least one match.
pub fn searches_with_match(&self) -> u64 {
self.searches_with_match
}
/// Return the total number of bytes searched.
pub fn bytes_searched(&self) -> u64 {
self.bytes_searched
}
/// Return the total number of bytes printed.
pub fn bytes_printed(&self) -> u64 {
self.bytes_printed
}
/// Return the total number of lines that participated in a match.
///
/// When matches may contain multiple lines then this includes every line
/// that is part of every match.
pub fn matched_lines(&self) -> u64 {
self.matched_lines
}
/// Return the total number of matches.
///
/// There may be multiple matches per line.
pub fn matches(&self) -> u64 {
self.matches
}
/// Add to the elapsed time.
pub fn add_elapsed(&mut self, duration: Duration) {
self.elapsed.0 += duration;
}
/// Add to the number of searches executed.
pub fn add_searches(&mut self, n: u64) {
self.searches += n;
}
/// Add to the number of searches that found at least one match.
pub fn add_searches_with_match(&mut self, n: u64) {
self.searches_with_match += n;
}
/// Add to the total number of bytes searched.
pub fn add_bytes_searched(&mut self, n: u64) {
self.bytes_searched += n;
}
/// Add to the total number of bytes printed.
pub fn add_bytes_printed(&mut self, n: u64) {
self.bytes_printed += n;
}
/// Add to the total number of lines that participated in a match.
pub fn add_matched_lines(&mut self, n: u64) {
self.matched_lines += n;
}
/// Add to the total number of matches.
pub fn add_matches(&mut self, n: u64) {
self.matches += n;
}
}

1071
grep-printer/src/summary.rs Normal file
View File

File diff suppressed because it is too large Load Diff

379
grep-printer/src/util.rs Normal file
View File

@@ -0,0 +1,379 @@
use std::borrow::Cow;
use std::fmt;
use std::io;
use std::path::Path;
use std::time;
use bstr::{BStr, BString};
use grep_matcher::{Captures, LineTerminator, Match, Matcher};
use grep_searcher::{
LineIter,
SinkError, SinkContext, SinkContextKind, SinkMatch,
};
#[cfg(feature = "serde1")]
use serde::{Serialize, Serializer};
/// A type for handling replacements while amortizing allocation.
pub struct Replacer<M: Matcher> {
space: Option<Space<M>>,
}
struct Space<M: Matcher> {
/// The place to store capture locations.
caps: M::Captures,
/// The place to write a replacement to.
dst: Vec<u8>,
/// The place to store match offsets in terms of `dst`.
matches: Vec<Match>,
}
impl<M: Matcher> fmt::Debug for Replacer<M> {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let (dst, matches) = self.replacement().unwrap_or((&[], &[]));
f.debug_struct("Replacer")
.field("dst", &dst)
.field("matches", &matches)
.finish()
}
}
impl<M: Matcher> Replacer<M> {
/// Create a new replacer for use with a particular matcher.
///
/// This constructor does not allocate. Instead, space for dealing with
/// replacements is allocated lazily only when needed.
pub fn new() -> Replacer<M> {
Replacer { space: None }
}
/// Executes a replacement on the given subject string by replacing all
/// matches with the given replacement. To access the result of the
/// replacement, use the `replacement` method.
///
/// This can fail if the underlying matcher reports an error.
pub fn replace_all<'a>(
&'a mut self,
matcher: &M,
subject: &[u8],
replacement: &[u8],
) -> io::Result<()> {
{
let &mut Space {
ref mut dst,
ref mut caps,
ref mut matches,
} = self.allocate(matcher)?;
dst.clear();
matches.clear();
matcher.replace_with_captures(
subject,
caps,
dst,
|caps, dst| {
let start = dst.len();
caps.interpolate(
|name| matcher.capture_index(name),
subject,
replacement,
dst,
);
let end = dst.len();
matches.push(Match::new(start, end));
true
},
).map_err(io::Error::error_message)?;
}
Ok(())
}
/// Return the result of the prior replacement and the match offsets for
/// all replacement occurrences within the returned replacement buffer.
///
/// If no replacement has occurred then `None` is returned.
pub fn replacement<'a>(&'a self) -> Option<(&'a [u8], &'a [Match])> {
match self.space {
None => None,
Some(ref space) => {
if space.matches.is_empty() {
None
} else {
Some((&space.dst, &space.matches))
}
}
}
}
/// Clear space used for performing a replacement.
///
/// Subsequent calls to `replacement` after calling `clear` (but before
/// executing another replacement) will always return `None`.
pub fn clear(&mut self) {
if let Some(ref mut space) = self.space {
space.dst.clear();
space.matches.clear();
}
}
/// Allocate space for replacements when used with the given matcher and
/// return a mutable reference to that space.
///
/// This can fail if allocating space for capture locations from the given
/// matcher fails.
fn allocate(&mut self, matcher: &M) -> io::Result<&mut Space<M>> {
if self.space.is_none() {
let caps = matcher
.new_captures()
.map_err(io::Error::error_message)?;
self.space = Some(Space {
caps: caps,
dst: vec![],
matches: vec![],
});
}
Ok(self.space.as_mut().unwrap())
}
}
/// A simple layer of abstraction over either a match or a contextual line
/// reported by the searcher.
///
/// In particular, this provides an API that unions the `SinkMatch` and
/// `SinkContext` types while also exposing a list of all individual match
/// locations.
///
/// While this serves as a convenient mechanism to abstract over `SinkMatch`
/// and `SinkContext`, this also provides a way to abstract over replacements.
/// Namely, after a replacement, a `Sunk` value can be constructed using the
/// results of the replacement instead of the bytes reported directly by the
/// searcher.
#[derive(Debug)]
pub struct Sunk<'a> {
bytes: &'a [u8],
absolute_byte_offset: u64,
line_number: Option<u64>,
context_kind: Option<&'a SinkContextKind>,
matches: &'a [Match],
original_matches: &'a [Match],
}
impl<'a> Sunk<'a> {
#[inline]
pub fn empty() -> Sunk<'static> {
Sunk {
bytes: &[],
absolute_byte_offset: 0,
line_number: None,
context_kind: None,
matches: &[],
original_matches: &[],
}
}
#[inline]
pub fn from_sink_match(
sunk: &'a SinkMatch<'a>,
original_matches: &'a [Match],
replacement: Option<(&'a [u8], &'a [Match])>,
) -> Sunk<'a> {
let (bytes, matches) = replacement.unwrap_or_else(|| {
(sunk.bytes(), original_matches)
});
Sunk {
bytes: bytes,
absolute_byte_offset: sunk.absolute_byte_offset(),
line_number: sunk.line_number(),
context_kind: None,
matches: matches,
original_matches: original_matches,
}
}
#[inline]
pub fn from_sink_context(
sunk: &'a SinkContext<'a>,
original_matches: &'a [Match],
replacement: Option<(&'a [u8], &'a [Match])>,
) -> Sunk<'a> {
let (bytes, matches) = replacement.unwrap_or_else(|| {
(sunk.bytes(), original_matches)
});
Sunk {
bytes: bytes,
absolute_byte_offset: sunk.absolute_byte_offset(),
line_number: sunk.line_number(),
context_kind: Some(sunk.kind()),
matches: matches,
original_matches: original_matches,
}
}
#[inline]
pub fn context_kind(&self) -> Option<&'a SinkContextKind> {
self.context_kind
}
#[inline]
pub fn bytes(&self) -> &'a [u8] {
self.bytes
}
#[inline]
pub fn matches(&self) -> &'a [Match] {
self.matches
}
#[inline]
pub fn original_matches(&self) -> &'a [Match] {
self.original_matches
}
#[inline]
pub fn lines(&self, line_term: u8) -> LineIter<'a> {
LineIter::new(line_term, self.bytes())
}
#[inline]
pub fn absolute_byte_offset(&self) -> u64 {
self.absolute_byte_offset
}
#[inline]
pub fn line_number(&self) -> Option<u64> {
self.line_number
}
}
/// A simple encapsulation of a file path used by a printer.
///
/// This represents any transforms that we might want to perform on the path,
/// such as converting it to valid UTF-8 and/or replacing its separator with
/// something else. This allows us to amortize work if we are printing the
/// file path for every match.
///
/// In the common case, no transformation is needed, which lets us avoid the
/// allocation. Typically, only Windows requires a transform, since we can't
/// access the raw bytes of a path directly and first need to lossily convert
/// to UTF-8. Windows is also typically where the path separator replacement
/// is used, e.g., in cygwin environments to use `/` instead of `\`.
///
/// Users of this type are expected to construct it from a normal `Path`
/// found in the standard library. It can then be written to any `io::Write`
/// implementation using the `as_bytes` method. This achieves platform
/// portability with a small cost: on Windows, paths that are not valid UTF-16
/// will not roundtrip correctly.
#[derive(Clone, Debug)]
pub struct PrinterPath<'a>(Cow<'a, BStr>);
impl<'a> PrinterPath<'a> {
/// Create a new path suitable for printing.
pub fn new(path: &'a Path) -> PrinterPath<'a> {
PrinterPath(BString::from_path_lossy(path))
}
/// Create a new printer path from the given path which can be efficiently
/// written to a writer without allocation.
///
/// If the given separator is present, then any separators in `path` are
/// replaced with it.
pub fn with_separator(path: &'a Path, sep: Option<u8>) -> PrinterPath<'a> {
let mut ppath = PrinterPath::new(path);
if let Some(sep) = sep {
ppath.replace_separator(sep);
}
ppath
}
/// Replace the path separator in this path with the given separator
/// and do it in place. On Windows, both `/` and `\` are treated as
/// path separators that are both replaced by `new_sep`. In all other
/// environments, only `/` is treated as a path separator.
fn replace_separator(&mut self, new_sep: u8) {
let transformed_path: BString = self.0.bytes().map(|b| {
if b == b'/' || (cfg!(windows) && b == b'\\') {
new_sep
} else {
b
}
}).collect();
self.0 = Cow::Owned(transformed_path);
}
/// Return the raw bytes for this path.
pub fn as_bytes(&self) -> &[u8] {
self.0.as_bytes()
}
}
/// A type that provides "nicer" Display and Serialize impls for
/// std::time::Duration. The serialization format should actually be compatible
/// with the Deserialize impl for std::time::Duration, since this type only
/// adds new fields.
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
pub struct NiceDuration(pub time::Duration);
impl fmt::Display for NiceDuration {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{:0.6}s", self.fractional_seconds())
}
}
impl NiceDuration {
/// Returns the number of seconds in this duration in fraction form.
/// The number to the left of the decimal point is the number of seconds,
/// and the number to the right is the number of milliseconds.
fn fractional_seconds(&self) -> f64 {
let fractional = (self.0.subsec_nanos() as f64) / 1_000_000_000.0;
self.0.as_secs() as f64 + fractional
}
}
#[cfg(feature = "serde1")]
impl Serialize for NiceDuration {
fn serialize<S: Serializer>(&self, ser: S) -> Result<S::Ok, S::Error> {
use serde::ser::SerializeStruct;
let mut state = ser.serialize_struct("Duration", 2)?;
state.serialize_field("secs", &self.0.as_secs())?;
state.serialize_field("nanos", &self.0.subsec_nanos())?;
state.serialize_field("human", &format!("{}", self))?;
state.end()
}
}
/// Trim prefix ASCII spaces from the given slice and return the corresponding
/// range.
///
/// This stops trimming a prefix as soon as it sees non-whitespace or a line
/// terminator.
pub fn trim_ascii_prefix_range(
line_term: LineTerminator,
slice: &[u8],
range: Match,
) -> Match {
fn is_space(b: u8) -> bool {
match b {
b'\t' | b'\n' | b'\x0B' | b'\x0C' | b'\r' | b' ' => true,
_ => false,
}
}
let count = slice[range]
.iter()
.take_while(|&&b| -> bool {
is_space(b) && !line_term.as_bytes().contains(&b)
})
.count();
range.with_start(range.start() + count)
}
/// Trim prefix ASCII spaces from the given slice and return the corresponding
/// sub-slice.
pub fn trim_ascii_prefix(line_term: LineTerminator, slice: &[u8]) -> &[u8] {
let range = trim_ascii_prefix_range(
line_term,
slice,
Match::new(0, slice.len()),
);
&slice[range]
}

21
grep-regex/Cargo.toml Normal file
View File

@@ -0,0 +1,21 @@
[package]
name = "grep-regex"
version = "0.1.2" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Use Rust's regex library with the 'grep' crate.
"""
documentation = "https://docs.rs/grep-regex"
homepage = "https://github.com/BurntSushi/ripgrep"
repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["regex", "grep", "search", "pattern", "line"]
license = "Unlicense/MIT"
[dependencies]
log = "0.4.5"
grep-matcher = { version = "0.1.1", path = "../grep-matcher" }
regex = "1.1"
regex-syntax = "0.6.5"
thread_local = "0.3.6"
utf8-ranges = "1.0.1"

21
grep-regex/LICENSE-MIT Normal file
View File

@@ -0,0 +1,21 @@
The MIT License (MIT)
Copyright (c) 2015 Andrew Gallant
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.

35
grep-regex/README.md Normal file
View File

@@ -0,0 +1,35 @@
grep-regex
----------
The `grep-regex` crate provides an implementation of the `Matcher` trait from
the `grep-matcher` crate. This implementation permits Rust's regex engine to
be used in the `grep` crate for fast line oriented searching.
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/grep-regex.svg)](https://crates.io/crates/grep-regex)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
### Documentation
[https://docs.rs/grep-regex](https://docs.rs/grep-regex)
**NOTE:** You probably don't want to use this crate directly. Instead, you
should prefer the facade defined in the
[`grep`](https://docs.rs/grep)
crate.
### Usage
Add this to your `Cargo.toml`:
```toml
[dependencies]
grep-regex = "0.1"
```
and this to your crate root:
```rust
extern crate grep_regex;
```

24
grep-regex/UNLICENSE Normal file
View File

@@ -0,0 +1,24 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org/>

263
grep-regex/src/ast.rs Normal file
View File

@@ -0,0 +1,263 @@
use regex_syntax::ast::{self, Ast};
use regex_syntax::ast::parse::Parser;
/// The results of analyzing AST of a regular expression (e.g., for supporting
/// smart case).
#[derive(Clone, Debug)]
pub struct AstAnalysis {
/// True if and only if a literal uppercase character occurs in the regex.
any_uppercase: bool,
/// True if and only if the regex contains any literal at all.
any_literal: bool,
/// True if and only if the regex consists entirely of a literal and no
/// other special regex characters.
all_verbatim_literal: bool,
}
impl AstAnalysis {
/// Returns a `AstAnalysis` value by doing analysis on the AST of `pattern`.
///
/// If `pattern` is not a valid regular expression, then `None` is
/// returned.
#[allow(dead_code)]
pub fn from_pattern(pattern: &str) -> Option<AstAnalysis> {
Parser::new()
.parse(pattern)
.map(|ast| AstAnalysis::from_ast(&ast))
.ok()
}
/// Perform an AST analysis given the AST.
pub fn from_ast(ast: &Ast) -> AstAnalysis {
let mut analysis = AstAnalysis::new();
analysis.from_ast_impl(ast);
analysis
}
/// Returns true if and only if a literal uppercase character occurs in
/// the pattern.
///
/// For example, a pattern like `\pL` contains no uppercase literals,
/// even though `L` is uppercase and the `\pL` class contains uppercase
/// characters.
pub fn any_uppercase(&self) -> bool {
self.any_uppercase
}
/// Returns true if and only if the regex contains any literal at all.
///
/// For example, a pattern like `\pL` reports `false`, but a pattern like
/// `\pLfoo` reports `true`.
pub fn any_literal(&self) -> bool {
self.any_literal
}
/// Returns true if and only if the entire pattern is a verbatim literal
/// with no special meta characters.
///
/// When this is true, then the pattern satisfies the following law:
/// `escape(pattern) == pattern`. Notable examples where this returns
/// `false` include patterns like `a\u0061` even though `\u0061` is just
/// a literal `a`.
///
/// The purpose of this flag is to determine whether the patterns can be
/// given to non-regex substring search algorithms as-is.
#[allow(dead_code)]
pub fn all_verbatim_literal(&self) -> bool {
self.all_verbatim_literal
}
/// Creates a new `AstAnalysis` value with an initial configuration.
fn new() -> AstAnalysis {
AstAnalysis {
any_uppercase: false,
any_literal: false,
all_verbatim_literal: true,
}
}
fn from_ast_impl(&mut self, ast: &Ast) {
if self.done() {
return;
}
match *ast {
Ast::Empty(_) => {}
Ast::Flags(_)
| Ast::Dot(_)
| Ast::Assertion(_)
| Ast::Class(ast::Class::Unicode(_))
| Ast::Class(ast::Class::Perl(_)) => {
self.all_verbatim_literal = false;
}
Ast::Literal(ref x) => {
self.from_ast_literal(x);
}
Ast::Class(ast::Class::Bracketed(ref x)) => {
self.all_verbatim_literal = false;
self.from_ast_class_set(&x.kind);
}
Ast::Repetition(ref x) => {
self.all_verbatim_literal = false;
self.from_ast_impl(&x.ast);
}
Ast::Group(ref x) => {
self.all_verbatim_literal = false;
self.from_ast_impl(&x.ast);
}
Ast::Alternation(ref alt) => {
self.all_verbatim_literal = false;
for x in &alt.asts {
self.from_ast_impl(x);
}
}
Ast::Concat(ref alt) => {
for x in &alt.asts {
self.from_ast_impl(x);
}
}
}
}
fn from_ast_class_set(&mut self, ast: &ast::ClassSet) {
if self.done() {
return;
}
match *ast {
ast::ClassSet::Item(ref item) => {
self.from_ast_class_set_item(item);
}
ast::ClassSet::BinaryOp(ref x) => {
self.from_ast_class_set(&x.lhs);
self.from_ast_class_set(&x.rhs);
}
}
}
fn from_ast_class_set_item(&mut self, ast: &ast::ClassSetItem) {
if self.done() {
return;
}
match *ast {
ast::ClassSetItem::Empty(_)
| ast::ClassSetItem::Ascii(_)
| ast::ClassSetItem::Unicode(_)
| ast::ClassSetItem::Perl(_) => {}
ast::ClassSetItem::Literal(ref x) => {
self.from_ast_literal(x);
}
ast::ClassSetItem::Range(ref x) => {
self.from_ast_literal(&x.start);
self.from_ast_literal(&x.end);
}
ast::ClassSetItem::Bracketed(ref x) => {
self.from_ast_class_set(&x.kind);
}
ast::ClassSetItem::Union(ref union) => {
for x in &union.items {
self.from_ast_class_set_item(x);
}
}
}
}
fn from_ast_literal(&mut self, ast: &ast::Literal) {
if ast.kind != ast::LiteralKind::Verbatim {
self.all_verbatim_literal = false;
}
self.any_literal = true;
self.any_uppercase = self.any_uppercase || ast.c.is_uppercase();
}
/// Returns true if and only if the attributes can never change no matter
/// what other AST it might see.
fn done(&self) -> bool {
self.any_uppercase && self.any_literal && !self.all_verbatim_literal
}
}
#[cfg(test)]
mod tests {
use super::*;
fn analysis(pattern: &str) -> AstAnalysis {
AstAnalysis::from_pattern(pattern).unwrap()
}
#[test]
fn various() {
let x = analysis("");
assert!(!x.any_uppercase);
assert!(!x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis("foo");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis("Foo");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis("foO");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis(r"foo\\");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\w");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\S");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\p{Ll}");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo[a-z]");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo[A-Z]");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo[\S\t]");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\\S");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"\p{Ll}");
assert!(!x.any_uppercase);
assert!(!x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"aBc\w");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"a\u0061");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
}
}

273
grep-regex/src/config.rs Normal file
View File

@@ -0,0 +1,273 @@
use grep_matcher::{ByteSet, LineTerminator};
use regex::bytes::{Regex, RegexBuilder};
use regex_syntax::ast::{self, Ast};
use regex_syntax::hir::Hir;
use ast::AstAnalysis;
use crlf::crlfify;
use error::Error;
use literal::LiteralSets;
use non_matching::non_matching_bytes;
use strip::strip_from_match;
/// Config represents the configuration of a regex matcher in this crate.
/// The configuration is itself a rough combination of the knobs found in
/// the `regex` crate itself, along with additional `grep-matcher` specific
/// options.
///
/// The configuration can be used to build a "configured" HIR expression. A
/// configured HIR expression is an HIR expression that is aware of the
/// configuration which generated it, and provides transformation on that HIR
/// such that the configuration is preserved.
#[derive(Clone, Debug)]
pub struct Config {
pub case_insensitive: bool,
pub case_smart: bool,
pub multi_line: bool,
pub dot_matches_new_line: bool,
pub swap_greed: bool,
pub ignore_whitespace: bool,
pub unicode: bool,
pub octal: bool,
pub size_limit: usize,
pub dfa_size_limit: usize,
pub nest_limit: u32,
pub line_terminator: Option<LineTerminator>,
pub crlf: bool,
pub word: bool,
}
impl Default for Config {
fn default() -> Config {
Config {
case_insensitive: false,
case_smart: false,
multi_line: false,
dot_matches_new_line: false,
swap_greed: false,
ignore_whitespace: false,
unicode: true,
octal: false,
// These size limits are much bigger than what's in the regex
// crate.
size_limit: 100 * (1<<20),
dfa_size_limit: 1000 * (1<<20),
nest_limit: 250,
line_terminator: None,
crlf: false,
word: false,
}
}
}
impl Config {
/// Parse the given pattern and returned its HIR expression along with
/// the current configuration.
///
/// If there was a problem parsing the given expression then an error
/// is returned.
pub fn hir(&self, pattern: &str) -> Result<ConfiguredHIR, Error> {
let analysis = self.analysis(pattern)?;
let expr = ::regex_syntax::ParserBuilder::new()
.nest_limit(self.nest_limit)
.octal(self.octal)
.allow_invalid_utf8(true)
.ignore_whitespace(self.ignore_whitespace)
.case_insensitive(self.is_case_insensitive(&analysis)?)
.multi_line(self.multi_line)
.dot_matches_new_line(self.dot_matches_new_line)
.swap_greed(self.swap_greed)
.unicode(self.unicode)
.build()
.parse(pattern)
.map_err(Error::regex)?;
let expr = match self.line_terminator {
None => expr,
Some(line_term) => strip_from_match(expr, line_term)?,
};
Ok(ConfiguredHIR {
original: pattern.to_string(),
config: self.clone(),
analysis: analysis,
// If CRLF mode is enabled, replace `$` with `(?:\r?$)`.
expr: if self.crlf { crlfify(expr) } else { expr },
})
}
/// Accounting for the `smart_case` config knob, return true if and only if
/// this pattern should be matched case insensitively.
fn is_case_insensitive(
&self,
analysis: &AstAnalysis,
) -> Result<bool, Error> {
if self.case_insensitive {
return Ok(true);
}
if !self.case_smart {
return Ok(false);
}
Ok(analysis.any_literal() && !analysis.any_uppercase())
}
/// Perform analysis on the AST of this pattern.
///
/// This returns an error if the given pattern failed to parse.
fn analysis(&self, pattern: &str) -> Result<AstAnalysis, Error> {
Ok(AstAnalysis::from_ast(&self.ast(pattern)?))
}
/// Parse the given pattern into its abstract syntax.
///
/// This returns an error if the given pattern failed to parse.
fn ast(&self, pattern: &str) -> Result<Ast, Error> {
ast::parse::ParserBuilder::new()
.nest_limit(self.nest_limit)
.octal(self.octal)
.ignore_whitespace(self.ignore_whitespace)
.build()
.parse(pattern)
.map_err(Error::regex)
}
}
/// A "configured" HIR expression, which is aware of the configuration which
/// produced this HIR.
///
/// Since the configuration is tracked, values with this type can be
/// transformed into other HIR expressions (or regular expressions) in a way
/// that preserves the configuration. For example, the `fast_line_regex`
/// method will apply literal extraction to the inner HIR and use that to build
/// a new regex that matches the extracted literals in a way that is
/// consistent with the configuration that produced this HIR. For example, the
/// size limits set on the configured HIR will be propagated out to any
/// subsequently constructed HIR or regular expression.
#[derive(Clone, Debug)]
pub struct ConfiguredHIR {
original: String,
config: Config,
analysis: AstAnalysis,
expr: Hir,
}
impl ConfiguredHIR {
/// Return the configuration for this HIR expression.
pub fn config(&self) -> &Config {
&self.config
}
/// Compute the set of non-matching bytes for this HIR expression.
pub fn non_matching_bytes(&self) -> ByteSet {
non_matching_bytes(&self.expr)
}
/// Returns true if and only if this regex needs to have its match offsets
/// tweaked because of CRLF support. Specifically, this occurs when the
/// CRLF hack is enabled and the regex is line anchored at the end. In
/// this case, matches that end with a `\r` have the `\r` stripped.
pub fn needs_crlf_stripped(&self) -> bool {
self.config.crlf && self.expr.is_line_anchored_end()
}
/// Builds a regular expression from this HIR expression.
pub fn regex(&self) -> Result<Regex, Error> {
self.pattern_to_regex(&self.expr.to_string())
}
/// Applies the given function to the concrete syntax of this HIR and then
/// generates a new HIR based on the result of the function in a way that
/// preserves the configuration.
///
/// For example, this can be used to wrap a user provided regular
/// expression with additional semantics. e.g., See the `WordMatcher`.
pub fn with_pattern<F: FnMut(&str) -> String>(
&self,
mut f: F,
) -> Result<ConfiguredHIR, Error>
{
self.pattern_to_hir(&f(&self.expr.to_string()))
}
/// If the current configuration has a line terminator set and if useful
/// literals could be extracted, then a regular expression matching those
/// literals is returned. If no line terminator is set, then `None` is
/// returned.
///
/// If compiling the resulting regular expression failed, then an error
/// is returned.
///
/// This method only returns something when a line terminator is set
/// because matches from this regex are generally candidates that must be
/// confirmed before reporting a match. When performing a line oriented
/// search, confirmation is easy: just extend the candidate match to its
/// respective line boundaries and then re-search that line for a full
/// match. This only works when the line terminator is set because the line
/// terminator setting guarantees that the regex itself can never match
/// through the line terminator byte.
pub fn fast_line_regex(&self) -> Result<Option<Regex>, Error> {
if self.config.line_terminator.is_none() {
return Ok(None);
}
match LiteralSets::new(&self.expr).one_regex(self.config.word) {
None => Ok(None),
Some(pattern) => self.pattern_to_regex(&pattern).map(Some),
}
}
/// Create a regex from the given pattern using this HIR's configuration.
fn pattern_to_regex(&self, pattern: &str) -> Result<Regex, Error> {
// The settings we explicitly set here are intentionally a subset
// of the settings we have. The key point here is that our HIR
// expression is computed with the settings in mind, such that setting
// them here could actually lead to unintended behavior. For example,
// consider the pattern `(?U)a+`. This will get folded into the HIR
// as a non-greedy repetition operator which will in turn get printed
// to the concrete syntax as `a+?`, which is correct. But if we
// set the `swap_greed` option again, then we'll wind up with `(?U)a+?`
// which is equal to `a+` which is not the same as what we were given.
//
// We also don't need to apply `case_insensitive` since this gets
// folded into the HIR and would just cause us to do redundant work.
//
// Finally, we don't need to set `ignore_whitespace` since the concrete
// syntax emitted by the HIR printer never needs it.
//
// We set the rest of the options. Some of them are important, such as
// the size limit, and some of them are necessary to preserve the
// intention of the original pattern. For example, the Unicode flag
// will impact how the WordMatcher functions, namely, whether its
// word boundaries are Unicode aware or not.
RegexBuilder::new(&pattern)
.nest_limit(self.config.nest_limit)
.octal(self.config.octal)
.multi_line(self.config.multi_line)
.dot_matches_new_line(self.config.dot_matches_new_line)
.unicode(self.config.unicode)
.size_limit(self.config.size_limit)
.dfa_size_limit(self.config.dfa_size_limit)
.build()
.map_err(Error::regex)
}
/// Create an HIR expression from the given pattern using this HIR's
/// configuration.
fn pattern_to_hir(&self, pattern: &str) -> Result<ConfiguredHIR, Error> {
// See `pattern_to_regex` comment for explanation of why we only set
// a subset of knobs here. e.g., `swap_greed` is explicitly left out.
let expr = ::regex_syntax::ParserBuilder::new()
.nest_limit(self.config.nest_limit)
.octal(self.config.octal)
.allow_invalid_utf8(true)
.multi_line(self.config.multi_line)
.dot_matches_new_line(self.config.dot_matches_new_line)
.unicode(self.config.unicode)
.build()
.parse(pattern)
.map_err(Error::regex)?;
Ok(ConfiguredHIR {
original: self.original.clone(),
config: self.config.clone(),
analysis: self.analysis.clone(),
expr: expr,
})
}
}

188
grep-regex/src/crlf.rs Normal file
View File

@@ -0,0 +1,188 @@
use std::collections::HashMap;
use grep_matcher::{Match, Matcher, NoError};
use regex::bytes::Regex;
use regex_syntax::hir::{self, Hir, HirKind};
use config::ConfiguredHIR;
use error::Error;
use matcher::RegexCaptures;
/// A matcher for implementing "word match" semantics.
#[derive(Clone, Debug)]
pub struct CRLFMatcher {
/// The regex.
regex: Regex,
/// A map from capture group name to capture group index.
names: HashMap<String, usize>,
}
impl CRLFMatcher {
/// Create a new matcher from the given pattern that strips `\r` from the
/// end of every match.
///
/// This panics if the given expression doesn't need its CRLF stripped.
pub fn new(expr: &ConfiguredHIR) -> Result<CRLFMatcher, Error> {
assert!(expr.needs_crlf_stripped());
let regex = expr.regex()?;
let mut names = HashMap::new();
for (i, optional_name) in regex.capture_names().enumerate() {
if let Some(name) = optional_name {
names.insert(name.to_string(), i.checked_sub(1).unwrap());
}
}
Ok(CRLFMatcher { regex, names })
}
/// Return the underlying regex used by this matcher.
pub fn regex(&self) -> &Regex {
&self.regex
}
}
impl Matcher for CRLFMatcher {
type Captures = RegexCaptures;
type Error = NoError;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, NoError> {
let m = match self.regex.find_at(haystack, at) {
None => return Ok(None),
Some(m) => Match::new(m.start(), m.end()),
};
Ok(Some(adjust_match(haystack, m)))
}
fn new_captures(&self) -> Result<RegexCaptures, NoError> {
Ok(RegexCaptures::new(self.regex.capture_locations()))
}
fn capture_count(&self) -> usize {
self.regex.captures_len().checked_sub(1).unwrap()
}
fn capture_index(&self, name: &str) -> Option<usize> {
self.names.get(name).map(|i| *i)
}
fn captures_at(
&self,
haystack: &[u8],
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
caps.strip_crlf(false);
let r = self.regex.captures_read_at(caps.locations(), haystack, at);
if !r.is_some() {
return Ok(false);
}
// If the end of our match includes a `\r`, then strip it from all
// capture groups ending at the same location.
let end = caps.locations().get(0).unwrap().1;
if end > 0 && haystack.get(end - 1) == Some(&b'\r') {
caps.strip_crlf(true);
}
Ok(true)
}
// We specifically do not implement other methods like find_iter or
// captures_iter. Namely, the iter methods are guaranteed to be correct
// by virtue of implementing find_at and captures_at above.
}
/// If the given match ends with a `\r`, then return a new match that ends
/// immediately before the `\r`.
pub fn adjust_match(haystack: &[u8], m: Match) -> Match {
if m.end() > 0 && haystack.get(m.end() - 1) == Some(&b'\r') {
m.with_end(m.end() - 1)
} else {
m
}
}
/// Substitutes all occurrences of multi-line enabled `$` with `(?:\r?$)`.
///
/// This does not preserve the exact semantics of the given expression,
/// however, it does have the useful property that anything that matched the
/// given expression will also match the returned expression. The difference is
/// that the returned expression can match possibly other things as well.
///
/// The principle reason why we do this is because the underlying regex engine
/// doesn't support CRLF aware `$` look-around. It's planned to fix it at that
/// level, but we perform this kludge in the mean time.
///
/// Note that while the match preserving semantics are nice and neat, the
/// match position semantics are quite a bit messier. Namely, `$` only ever
/// matches the position between characters where as `\r??` can match a
/// character and change the offset. This is regretable, but works out pretty
/// nicely in most cases, especially when a match is limited to a single line.
pub fn crlfify(expr: Hir) -> Hir {
match expr.into_kind() {
HirKind::Anchor(hir::Anchor::EndLine) => {
let concat = Hir::concat(vec![
Hir::repetition(hir::Repetition {
kind: hir::RepetitionKind::ZeroOrOne,
greedy: false,
hir: Box::new(Hir::literal(hir::Literal::Unicode('\r'))),
}),
Hir::anchor(hir::Anchor::EndLine),
]);
Hir::group(hir::Group {
kind: hir::GroupKind::NonCapturing,
hir: Box::new(concat),
})
}
HirKind::Empty => Hir::empty(),
HirKind::Literal(x) => Hir::literal(x),
HirKind::Class(x) => Hir::class(x),
HirKind::Anchor(x) => Hir::anchor(x),
HirKind::WordBoundary(x) => Hir::word_boundary(x),
HirKind::Repetition(mut x) => {
x.hir = Box::new(crlfify(*x.hir));
Hir::repetition(x)
}
HirKind::Group(mut x) => {
x.hir = Box::new(crlfify(*x.hir));
Hir::group(x)
}
HirKind::Concat(xs) => {
Hir::concat(xs.into_iter().map(crlfify).collect())
}
HirKind::Alternation(xs) => {
Hir::alternation(xs.into_iter().map(crlfify).collect())
}
}
}
#[cfg(test)]
mod tests {
use regex_syntax::Parser;
use super::crlfify;
fn roundtrip(pattern: &str) -> String {
let expr1 = Parser::new().parse(pattern).unwrap();
let expr2 = crlfify(expr1);
expr2.to_string()
}
#[test]
fn various() {
assert_eq!(roundtrip(r"(?m)$"), "(?:\r??(?m:$))");
assert_eq!(roundtrip(r"(?m)$$"), "(?:\r??(?m:$))(?:\r??(?m:$))");
assert_eq!(
roundtrip(r"(?m)(?:foo$|bar$)"),
"(?:foo(?:\r??(?m:$))|bar(?:\r??(?m:$)))"
);
assert_eq!(roundtrip(r"(?m)$a"), "(?:\r??(?m:$))a");
// Not a multiline `$`, so no crlfifying occurs.
assert_eq!(roundtrip(r"$"), "\\z");
// It's a literal, derp.
assert_eq!(roundtrip(r"\$"), "\\$");
}
}

88
grep-regex/src/error.rs Normal file
View File

@@ -0,0 +1,88 @@
use std::error;
use std::fmt;
use util;
/// An error that can occur in this crate.
///
/// Generally, this error corresponds to problems building a regular
/// expression, whether it's in parsing, compilation or a problem with
/// guaranteeing a configured optimization.
#[derive(Clone, Debug)]
pub struct Error {
kind: ErrorKind,
}
impl Error {
pub(crate) fn new(kind: ErrorKind) -> Error {
Error { kind }
}
pub(crate) fn regex<E: error::Error>(err: E) -> Error {
Error { kind: ErrorKind::Regex(err.to_string()) }
}
/// Return the kind of this error.
pub fn kind(&self) -> &ErrorKind {
&self.kind
}
}
/// The kind of an error that can occur.
#[derive(Clone, Debug)]
pub enum ErrorKind {
/// An error that occurred as a result of parsing a regular expression.
/// This can be a syntax error or an error that results from attempting to
/// compile a regular expression that is too big.
///
/// The string here is the underlying error converted to a string.
Regex(String),
/// An error that occurs when a building a regex that isn't permitted to
/// match a line terminator. In general, building the regex will do its
/// best to make matching a line terminator impossible (e.g., by removing
/// `\n` from the `\s` character class), but if the regex contains a
/// `\n` literal, then there is no reasonable choice that can be made and
/// therefore an error is reported.
///
/// The string is the literal sequence found in the regex that is not
/// allowed.
NotAllowed(String),
/// This error occurs when a non-ASCII line terminator was provided.
///
/// The invalid byte is included in this error.
InvalidLineTerminator(u8),
/// Hints that destructuring should not be exhaustive.
///
/// This enum may grow additional variants, so this makes sure clients
/// don't count on exhaustive matching. (Otherwise, adding a new variant
/// could break existing code.)
#[doc(hidden)]
__Nonexhaustive,
}
impl error::Error for Error {
fn description(&self) -> &str {
match self.kind {
ErrorKind::Regex(_) => "regex error",
ErrorKind::NotAllowed(_) => "literal not allowed",
ErrorKind::InvalidLineTerminator(_) => "invalid line terminator",
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}
impl fmt::Display for Error {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self.kind {
ErrorKind::Regex(ref s) => write!(f, "{}", s),
ErrorKind::NotAllowed(ref lit) => {
write!(f, "the literal '{:?}' is not allowed in a regex", lit)
}
ErrorKind::InvalidLineTerminator(byte) => {
let x = util::show_bytes(&[byte]);
write!(f, "line terminators must be ASCII, but '{}' is not", x)
}
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}

27
grep-regex/src/lib.rs Normal file
View File

@@ -0,0 +1,27 @@
/*!
An implementation of `grep-matcher`'s `Matcher` trait for Rust's regex engine.
*/
#![deny(missing_docs)]
extern crate grep_matcher;
#[macro_use]
extern crate log;
extern crate regex;
extern crate regex_syntax;
extern crate thread_local;
extern crate utf8_ranges;
pub use error::{Error, ErrorKind};
pub use matcher::{RegexCaptures, RegexMatcher, RegexMatcherBuilder};
mod ast;
mod config;
mod crlf;
mod error;
mod literal;
mod matcher;
mod non_matching;
mod strip;
mod util;
mod word;

331
grep-regex/src/literal.rs Normal file
View File

@@ -0,0 +1,331 @@
/*
This module is responsible for extracting *inner* literals out of the AST of a
regular expression. Normally this is the job of the regex engine itself, but
the regex engine doesn't look for inner literals. Since we're doing line based
searching, we can use them, so we need to do it ourselves.
*/
use std::cmp;
use regex_syntax::hir::{self, Hir, HirKind};
use regex_syntax::hir::literal::{Literal, Literals};
use util;
/// Represents prefix, suffix and inner "required" literals for a regular
/// expression.
///
/// Prefixes and suffixes are detected using regex-syntax. The inner required
/// literals are detected using something custom (but based on the code in
/// regex-syntax).
#[derive(Clone, Debug)]
pub struct LiteralSets {
/// A set of prefix literals.
prefixes: Literals,
/// A set of suffix literals.
suffixes: Literals,
/// A set of literals such that at least one of them must appear in every
/// match. A literal in this set may be neither a prefix nor a suffix.
required: Literals,
}
impl LiteralSets {
/// Create a set of literals from the given HIR expression.
pub fn new(expr: &Hir) -> LiteralSets {
let mut required = Literals::empty();
union_required(expr, &mut required);
LiteralSets {
prefixes: Literals::prefixes(expr),
suffixes: Literals::suffixes(expr),
required: required,
}
}
/// If it is deemed advantageuous to do so (via various suspicious
/// heuristics), this will return a single regular expression pattern that
/// matches a subset of the language matched by the regular expression that
/// generated these literal sets. The idea here is that the pattern
/// returned by this method is much cheaper to search for. i.e., It is
/// usually a single literal or an alternation of literals.
pub fn one_regex(&self, word: bool) -> Option<String> {
// TODO: The logic in this function is basically inscrutable. It grew
// organically in the old grep 0.1 crate. Ideally, it would be
// re-worked. In fact, the entire inner literal extraction should be
// re-worked. Actually, most of regex-syntax's literal extraction
// should also be re-worked. Alas... only so much time in the day.
if !word {
if self.prefixes.all_complete() && !self.prefixes.is_empty() {
debug!("literal prefixes detected: {:?}", self.prefixes);
// When this is true, the regex engine will do a literal scan,
// so we don't need to return anything. But we only do this
// if we aren't doing a word regex, since a word regex adds
// a `(?:\W|^)` to the beginning of the regex, thereby
// defeating the regex engine's literal detection.
return None;
}
}
// Out of inner required literals, prefixes and suffixes, which one
// is the longest? We pick the longest to do fast literal scan under
// the assumption that a longer literal will have a lower false
// positive rate.
let pre_lcp = self.prefixes.longest_common_prefix();
let pre_lcs = self.prefixes.longest_common_suffix();
let suf_lcp = self.suffixes.longest_common_prefix();
let suf_lcs = self.suffixes.longest_common_suffix();
let req_lits = self.required.literals();
let req = match req_lits.iter().max_by_key(|lit| lit.len()) {
None => &[],
Some(req) => &***req,
};
let mut lit = pre_lcp;
if pre_lcs.len() > lit.len() {
lit = pre_lcs;
}
if suf_lcp.len() > lit.len() {
lit = suf_lcp;
}
if suf_lcs.len() > lit.len() {
lit = suf_lcs;
}
if req_lits.len() == 1 && req.len() > lit.len() {
lit = req;
}
// Special case: if we detected an alternation of inner required
// literals and its longest literal is bigger than the longest
// prefix/suffix, then choose the alternation. In practice, this
// helps with case insensitive matching, which can generate lots of
// inner required literals.
let any_empty = req_lits.iter().any(|lit| lit.is_empty());
if req.len() > lit.len() && req_lits.len() > 1 && !any_empty {
debug!("required literals found: {:?}", req_lits);
let alts: Vec<String> = req_lits
.into_iter()
.map(|x| util::bytes_to_regex(x))
.collect();
// We're matching raw bytes, so disable Unicode mode.
Some(format!("(?-u:{})", alts.join("|")))
} else if lit.is_empty() {
None
} else {
debug!("required literal found: {:?}", util::show_bytes(lit));
Some(format!("(?-u:{})", util::bytes_to_regex(&lit)))
}
}
}
fn union_required(expr: &Hir, lits: &mut Literals) {
match *expr.kind() {
HirKind::Literal(hir::Literal::Unicode(c)) => {
let mut buf = [0u8; 4];
lits.cross_add(c.encode_utf8(&mut buf).as_bytes());
}
HirKind::Literal(hir::Literal::Byte(b)) => {
lits.cross_add(&[b]);
}
HirKind::Class(hir::Class::Unicode(ref cls)) => {
if count_unicode_class(cls) >= 5 || !lits.add_char_class(cls) {
lits.cut();
}
}
HirKind::Class(hir::Class::Bytes(ref cls)) => {
if count_byte_class(cls) >= 5 || !lits.add_byte_class(cls) {
lits.cut();
}
}
HirKind::Group(hir::Group { ref hir, .. }) => {
union_required(&**hir, lits);
}
HirKind::Repetition(ref x) => {
match x.kind {
hir::RepetitionKind::ZeroOrOne => lits.cut(),
hir::RepetitionKind::ZeroOrMore => lits.cut(),
hir::RepetitionKind::OneOrMore => {
union_required(&x.hir, lits);
lits.cut();
}
hir::RepetitionKind::Range(ref rng) => {
let (min, max) = match *rng {
hir::RepetitionRange::Exactly(m) => (m, Some(m)),
hir::RepetitionRange::AtLeast(m) => (m, None),
hir::RepetitionRange::Bounded(m, n) => (m, Some(n)),
};
repeat_range_literals(
&x.hir, min, max, x.greedy, lits, union_required);
}
}
}
HirKind::Concat(ref es) if es.is_empty() => {}
HirKind::Concat(ref es) if es.len() == 1 => {
union_required(&es[0], lits)
}
HirKind::Concat(ref es) => {
for e in es {
let mut lits2 = lits.to_empty();
union_required(e, &mut lits2);
if lits2.is_empty() {
lits.cut();
continue;
}
if lits2.contains_empty() || !is_simple(&e) {
lits.cut();
}
if !lits.cross_product(&lits2) || !lits2.any_complete() {
// If this expression couldn't yield any literal that
// could be extended, then we need to quit. Since we're
// short-circuiting, we also need to freeze every member.
lits.cut();
break;
}
}
}
HirKind::Alternation(ref es) => {
alternate_literals(es, lits, union_required);
}
_ => lits.cut(),
}
}
fn repeat_range_literals<F: FnMut(&Hir, &mut Literals)>(
e: &Hir,
min: u32,
max: Option<u32>,
_greedy: bool,
lits: &mut Literals,
mut f: F,
) {
if min == 0 {
// This is a bit conservative. If `max` is set, then we could
// treat this as a finite set of alternations. For now, we
// just treat it as `e*`.
lits.cut();
} else {
let n = cmp::min(lits.limit_size(), min as usize);
// We only extract literals from a single repetition, even though
// we could do more. e.g., `a{3}` will have `a` extracted instead of
// `aaa`. The reason is that inner literal extraction can't be unioned
// across repetitions. e.g., extracting `foofoofoo` from `(\w+foo){3}`
// is wrong.
f(e, lits);
if n < min as usize {
lits.cut();
}
if max.map_or(true, |max| min < max) {
lits.cut();
}
}
}
fn alternate_literals<F: FnMut(&Hir, &mut Literals)>(
es: &[Hir],
lits: &mut Literals,
mut f: F,
) {
let mut lits2 = lits.to_empty();
for e in es {
let mut lits3 = lits.to_empty();
lits3.set_limit_size(lits.limit_size() / 5);
f(e, &mut lits3);
if lits3.is_empty() || !lits2.union(lits3) {
// If we couldn't find suffixes for *any* of the
// alternates, then the entire alternation has to be thrown
// away and any existing members must be frozen. Similarly,
// if the union couldn't complete, stop and freeze.
lits.cut();
return;
}
}
// All we do at the moment is look for prefixes and suffixes. If both
// are empty, then we report nothing. We should be able to do better than
// this, but we'll need something more expressive than just a "set of
// literals."
let lcp = lits2.longest_common_prefix();
let lcs = lits2.longest_common_suffix();
if !lcp.is_empty() {
lits.cross_add(lcp);
}
lits.cut();
if !lcs.is_empty() {
lits.add(Literal::empty());
lits.add(Literal::new(lcs.to_vec()));
}
}
fn is_simple(expr: &Hir) -> bool {
match *expr.kind() {
HirKind::Empty
| HirKind::Literal(_)
| HirKind::Class(_)
| HirKind::Repetition(_)
| HirKind::Concat(_)
| HirKind::Alternation(_) => true,
HirKind::Anchor(_)
| HirKind::WordBoundary(_)
| HirKind::Group(_) => false,
}
}
/// Return the number of characters in the given class.
fn count_unicode_class(cls: &hir::ClassUnicode) -> u32 {
cls.iter().map(|r| 1 + (r.end() as u32 - r.start() as u32)).sum()
}
/// Return the number of bytes in the given class.
fn count_byte_class(cls: &hir::ClassBytes) -> u32 {
cls.iter().map(|r| 1 + (r.end() as u32 - r.start() as u32)).sum()
}
#[cfg(test)]
mod tests {
use regex_syntax::Parser;
use super::LiteralSets;
fn sets(pattern: &str) -> LiteralSets {
let hir = Parser::new().parse(pattern).unwrap();
LiteralSets::new(&hir)
}
fn one_regex(pattern: &str) -> Option<String> {
sets(pattern).one_regex(false)
}
// Put a pattern into the same format as the one returned by `one_regex`.
fn pat(pattern: &str) -> Option<String> {
Some(format!("(?-u:{})", pattern))
}
#[test]
fn various() {
// Obviously no literals.
assert!(one_regex(r"\w").is_none());
assert!(one_regex(r"\pL").is_none());
// Tantalizingly close.
assert!(one_regex(r"\w|foo").is_none());
// There's a literal, but it's better if the regex engine handles it
// internally.
assert!(one_regex(r"abc").is_none());
// Core use cases.
assert_eq!(one_regex(r"\wabc\w"), pat("abc"));
assert_eq!(one_regex(r"abc\w"), pat("abc"));
// TODO: Make these pass. We're missing some potentially big wins
// without these.
// assert_eq!(one_regex(r"\w(foo|bar|baz)"), pat("foo|bar|baz"));
// assert_eq!(one_regex(r"\w(foo|bar|baz)\w"), pat("foo|bar|baz"));
}
#[test]
fn regression_1064() {
// Regression from:
// https://github.com/BurntSushi/ripgrep/issues/1064
// assert_eq!(one_regex(r"a.*c"), pat("a"));
assert_eq!(one_regex(r"a(.*c)"), pat("a"));
}
}

934
grep-regex/src/matcher.rs Normal file
View File

@@ -0,0 +1,934 @@
use std::collections::HashMap;
use grep_matcher::{
Captures, LineMatchKind, LineTerminator, Match, Matcher, NoError, ByteSet,
};
use regex::bytes::{CaptureLocations, Regex};
use config::{Config, ConfiguredHIR};
use crlf::CRLFMatcher;
use error::Error;
use word::WordMatcher;
/// A builder for constructing a `Matcher` using regular expressions.
///
/// This builder re-exports many of the same options found on the regex crate's
/// builder, in addition to a few other options such as smart case, word
/// matching and the ability to set a line terminator which may enable certain
/// types of optimizations.
///
/// The syntax supported is documented as part of the regex crate:
/// https://docs.rs/regex/*/regex/#syntax
#[derive(Clone, Debug)]
pub struct RegexMatcherBuilder {
config: Config,
}
impl Default for RegexMatcherBuilder {
fn default() -> RegexMatcherBuilder {
RegexMatcherBuilder::new()
}
}
impl RegexMatcherBuilder {
/// Create a new builder for configuring a regex matcher.
pub fn new() -> RegexMatcherBuilder {
RegexMatcherBuilder {
config: Config::default(),
}
}
/// Build a new matcher using the current configuration for the provided
/// pattern.
///
/// The syntax supported is documented as part of the regex crate:
/// https://docs.rs/regex/*/regex/#syntax
pub fn build(&self, pattern: &str) -> Result<RegexMatcher, Error> {
let chir = self.config.hir(pattern)?;
let fast_line_regex = chir.fast_line_regex()?;
let non_matching_bytes = chir.non_matching_bytes();
if let Some(ref re) = fast_line_regex {
trace!("extracted fast line regex: {:?}", re);
}
let matcher = RegexMatcherImpl::new(&chir)?;
trace!("final regex: {:?}", matcher.regex().to_string());
Ok(RegexMatcher {
config: self.config.clone(),
matcher: matcher,
fast_line_regex: fast_line_regex,
non_matching_bytes: non_matching_bytes,
})
}
/// Set the value for the case insensitive (`i`) flag.
///
/// When enabled, letters in the pattern will match both upper case and
/// lower case variants.
pub fn case_insensitive(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.case_insensitive = yes;
self
}
/// Whether to enable "smart case" or not.
///
/// When smart case is enabled, the builder will automatically enable
/// case insensitive matching based on how the pattern is written. Namely,
/// case insensitive mode is enabled when both of the following things
/// are true:
///
/// 1. The pattern contains at least one literal character. For example,
/// `a\w` contains a literal (`a`) but `\w` does not.
/// 2. Of the literals in the pattern, none of them are considered to be
/// uppercase according to Unicode. For example, `foo\pL` has no
/// uppercase literals but `Foo\pL` does.
pub fn case_smart(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.case_smart = yes;
self
}
/// Set the value for the multi-line matching (`m`) flag.
///
/// When enabled, `^` matches the beginning of lines and `$` matches the
/// end of lines.
///
/// By default, they match beginning/end of the input.
pub fn multi_line(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.multi_line = yes;
self
}
/// Set the value for the any character (`s`) flag, where in `.` matches
/// anything when `s` is set and matches anything except for new line when
/// it is not set (the default).
///
/// N.B. "matches anything" means "any byte" when Unicode is disabled and
/// means "any valid UTF-8 encoding of any Unicode scalar value" when
/// Unicode is enabled.
pub fn dot_matches_new_line(
&mut self,
yes: bool,
) -> &mut RegexMatcherBuilder {
self.config.dot_matches_new_line = yes;
self
}
/// Set the value for the greedy swap (`U`) flag.
///
/// When enabled, a pattern like `a*` is lazy (tries to find shortest
/// match) and `a*?` is greedy (tries to find longest match).
///
/// By default, `a*` is greedy and `a*?` is lazy.
pub fn swap_greed(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.swap_greed = yes;
self
}
/// Set the value for the ignore whitespace (`x`) flag.
///
/// When enabled, whitespace such as new lines and spaces will be ignored
/// between expressions of the pattern, and `#` can be used to start a
/// comment until the next new line.
pub fn ignore_whitespace(
&mut self,
yes: bool,
) -> &mut RegexMatcherBuilder {
self.config.ignore_whitespace = yes;
self
}
/// Set the value for the Unicode (`u`) flag.
///
/// Enabled by default. When disabled, character classes such as `\w` only
/// match ASCII word characters instead of all Unicode word characters.
pub fn unicode(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.unicode = yes;
self
}
/// Whether to support octal syntax or not.
///
/// Octal syntax is a little-known way of uttering Unicode codepoints in
/// a regular expression. For example, `a`, `\x61`, `\u0061` and
/// `\141` are all equivalent regular expressions, where the last example
/// shows octal syntax.
///
/// While supporting octal syntax isn't in and of itself a problem, it does
/// make good error messages harder. That is, in PCRE based regex engines,
/// syntax like `\0` invokes a backreference, which is explicitly
/// unsupported in Rust's regex engine. However, many users expect it to
/// be supported. Therefore, when octal support is disabled, the error
/// message will explicitly mention that backreferences aren't supported.
///
/// Octal syntax is disabled by default.
pub fn octal(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.octal = yes;
self
}
/// Set the approximate size limit of the compiled regular expression.
///
/// This roughly corresponds to the number of bytes occupied by a single
/// compiled program. If the program exceeds this number, then a
/// compilation error is returned.
pub fn size_limit(&mut self, bytes: usize) -> &mut RegexMatcherBuilder {
self.config.size_limit = bytes;
self
}
/// Set the approximate size of the cache used by the DFA.
///
/// This roughly corresponds to the number of bytes that the DFA will
/// use while searching.
///
/// Note that this is a *per thread* limit. There is no way to set a global
/// limit. In particular, if a regex is used from multiple threads
/// simultaneously, then each thread may use up to the number of bytes
/// specified here.
pub fn dfa_size_limit(
&mut self,
bytes: usize,
) -> &mut RegexMatcherBuilder {
self.config.dfa_size_limit = bytes;
self
}
/// Set the nesting limit for this parser.
///
/// The nesting limit controls how deep the abstract syntax tree is allowed
/// to be. If the AST exceeds the given limit (e.g., with too many nested
/// groups), then an error is returned by the parser.
///
/// The purpose of this limit is to act as a heuristic to prevent stack
/// overflow for consumers that do structural induction on an `Ast` using
/// explicit recursion. While this crate never does this (instead using
/// constant stack space and moving the call stack to the heap), other
/// crates may.
///
/// This limit is not checked until the entire Ast is parsed. Therefore,
/// if callers want to put a limit on the amount of heap space used, then
/// they should impose a limit on the length, in bytes, of the concrete
/// pattern string. In particular, this is viable since this parser
/// implementation will limit itself to heap space proportional to the
/// lenth of the pattern string.
///
/// Note that a nest limit of `0` will return a nest limit error for most
/// patterns but not all. For example, a nest limit of `0` permits `a` but
/// not `ab`, since `ab` requires a concatenation, which results in a nest
/// depth of `1`. In general, a nest limit is not something that manifests
/// in an obvious way in the concrete syntax, therefore, it should not be
/// used in a granular way.
pub fn nest_limit(&mut self, limit: u32) -> &mut RegexMatcherBuilder {
self.config.nest_limit = limit;
self
}
/// Set an ASCII line terminator for the matcher.
///
/// The purpose of setting a line terminator is to enable a certain class
/// of optimizations that can make line oriented searching faster. Namely,
/// when a line terminator is enabled, then the builder will guarantee that
/// the resulting matcher will never be capable of producing a match that
/// contains the line terminator. Because of this guarantee, users of the
/// resulting matcher do not need to slowly execute a search line by line
/// for line oriented search.
///
/// If the aforementioned guarantee about not matching a line terminator
/// cannot be made because of how the pattern was written, then the builder
/// will return an error when attempting to construct the matcher. For
/// example, the pattern `a\sb` will be transformed such that it can never
/// match `a\nb` (when `\n` is the line terminator), but the pattern `a\nb`
/// will result in an error since the `\n` cannot be easily removed without
/// changing the fundamental intent of the pattern.
///
/// If the given line terminator isn't an ASCII byte (`<=127`), then the
/// builder will return an error when constructing the matcher.
pub fn line_terminator(
&mut self,
line_term: Option<u8>,
) -> &mut RegexMatcherBuilder {
self.config.line_terminator = line_term.map(LineTerminator::byte);
self
}
/// Set the line terminator to `\r\n` and enable CRLF matching for `$` in
/// regex patterns.
///
/// This method sets two distinct settings:
///
/// 1. It causes the line terminator for the matcher to be `\r\n`. Namely,
/// this prevents the matcher from ever producing a match that contains
/// a `\r` or `\n`.
/// 2. It translates all instances of `$` in the pattern to `(?:\r??$)`.
/// This works around the fact that the regex engine does not support
/// matching CRLF as a line terminator when using `$`.
///
/// In particular, because of (2), the matches produced by the matcher may
/// be slightly different than what one would expect given the pattern.
/// This is the trade off made: in many cases, `$` will "just work" in the
/// presence of `\r\n` line terminators, but matches may require some
/// trimming to faithfully represent the intended match.
///
/// Note that if you do not wish to set the line terminator but would still
/// like `$` to match `\r\n` line terminators, then it is valid to call
/// `crlf(true)` followed by `line_terminator(None)`. Ordering is
/// important, since `crlf` and `line_terminator` override each other.
pub fn crlf(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
if yes {
self.config.line_terminator = Some(LineTerminator::crlf());
} else {
self.config.line_terminator = None;
}
self.config.crlf = yes;
self
}
/// Require that all matches occur on word boundaries.
///
/// Enabling this option is subtly different than putting `\b` assertions
/// on both sides of your pattern. In particular, a `\b` assertion requires
/// that one side of it match a word character while the other match a
/// non-word character. This option, in contrast, merely requires that
/// one side match a non-word character.
///
/// For example, `\b-2\b` will not match `foo -2 bar` since `-` is not a
/// word character. However, `-2` with this `word` option enabled will
/// match the `-2` in `foo -2 bar`.
pub fn word(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.word = yes;
self
}
}
/// An implementation of the `Matcher` trait using Rust's standard regex
/// library.
#[derive(Clone, Debug)]
pub struct RegexMatcher {
/// The configuration specified by the caller.
config: Config,
/// The underlying matcher implementation.
matcher: RegexMatcherImpl,
/// A regex that never reports false negatives but may report false
/// positives that is believed to be capable of being matched more quickly
/// than `regex`. Typically, this is a single literal or an alternation
/// of literals.
fast_line_regex: Option<Regex>,
/// A set of bytes that will never appear in a match.
non_matching_bytes: ByteSet,
}
impl RegexMatcher {
/// Create a new matcher from the given pattern using the default
/// configuration.
pub fn new(pattern: &str) -> Result<RegexMatcher, Error> {
RegexMatcherBuilder::new().build(pattern)
}
/// Create a new matcher from the given pattern using the default
/// configuration, but matches lines terminated by `\n`.
///
/// This is meant to be a convenience constructor for using a
/// `RegexMatcherBuilder` and setting its
/// [`line_terminator`](struct.RegexMatcherBuilder.html#method.line_terminator)
/// to `\n`. The purpose of using this constructor is to permit special
/// optimizations that help speed up line oriented search. These types of
/// optimizations are only appropriate when matches span no more than one
/// line. For this reason, this constructor will return an error if the
/// given pattern contains a literal `\n`. Other uses of `\n` (such as in
/// `\s`) are removed transparently.
pub fn new_line_matcher(pattern: &str) -> Result<RegexMatcher, Error> {
RegexMatcherBuilder::new()
.line_terminator(Some(b'\n'))
.build(pattern)
}
}
/// An encapsulation of the type of matcher we use in `RegexMatcher`.
#[derive(Clone, Debug)]
enum RegexMatcherImpl {
/// The standard matcher used for all regular expressions.
Standard(StandardMatcher),
/// A matcher that strips `\r` from the end of matches.
///
/// This is only used when the CRLF hack is enabled and the regex is line
/// anchored at the end.
CRLF(CRLFMatcher),
/// A matcher that only matches at word boundaries. This transforms the
/// regex to `(^|\W)(...)($|\W)` instead of the more intuitive `\b(...)\b`.
/// Because of this, the WordMatcher provides its own implementation of
/// `Matcher` to encapsulate its use of capture groups to make them
/// invisible to the caller.
Word(WordMatcher),
}
impl RegexMatcherImpl {
/// Based on the configuration, create a new implementation of the
/// `Matcher` trait.
fn new(expr: &ConfiguredHIR) -> Result<RegexMatcherImpl, Error> {
if expr.config().word {
Ok(RegexMatcherImpl::Word(WordMatcher::new(expr)?))
} else if expr.needs_crlf_stripped() {
Ok(RegexMatcherImpl::CRLF(CRLFMatcher::new(expr)?))
} else {
Ok(RegexMatcherImpl::Standard(StandardMatcher::new(expr)?))
}
}
/// Return the underlying regex object used.
fn regex(&self) -> &Regex {
match *self {
RegexMatcherImpl::Word(ref x) => x.regex(),
RegexMatcherImpl::CRLF(ref x) => x.regex(),
RegexMatcherImpl::Standard(ref x) => &x.regex,
}
}
}
// This implementation just dispatches on the internal matcher impl except
// for the line terminator optimization, which is possibly executed via
// `fast_line_regex`.
impl Matcher for RegexMatcher {
type Captures = RegexCaptures;
type Error = NoError;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find_at(haystack, at),
CRLF(ref m) => m.find_at(haystack, at),
Word(ref m) => m.find_at(haystack, at),
}
}
fn new_captures(&self) -> Result<RegexCaptures, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.new_captures(),
CRLF(ref m) => m.new_captures(),
Word(ref m) => m.new_captures(),
}
}
fn capture_count(&self) -> usize {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.capture_count(),
CRLF(ref m) => m.capture_count(),
Word(ref m) => m.capture_count(),
}
}
fn capture_index(&self, name: &str) -> Option<usize> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.capture_index(name),
CRLF(ref m) => m.capture_index(name),
Word(ref m) => m.capture_index(name),
}
}
fn find(&self, haystack: &[u8]) -> Result<Option<Match>, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find(haystack),
CRLF(ref m) => m.find(haystack),
Word(ref m) => m.find(haystack),
}
}
fn find_iter<F>(
&self,
haystack: &[u8],
matched: F,
) -> Result<(), NoError>
where F: FnMut(Match) -> bool
{
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find_iter(haystack, matched),
CRLF(ref m) => m.find_iter(haystack, matched),
Word(ref m) => m.find_iter(haystack, matched),
}
}
fn try_find_iter<F, E>(
&self,
haystack: &[u8],
matched: F,
) -> Result<Result<(), E>, NoError>
where F: FnMut(Match) -> Result<bool, E>
{
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.try_find_iter(haystack, matched),
CRLF(ref m) => m.try_find_iter(haystack, matched),
Word(ref m) => m.try_find_iter(haystack, matched),
}
}
fn captures(
&self,
haystack: &[u8],
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures(haystack, caps),
CRLF(ref m) => m.captures(haystack, caps),
Word(ref m) => m.captures(haystack, caps),
}
}
fn captures_iter<F>(
&self,
haystack: &[u8],
caps: &mut RegexCaptures,
matched: F,
) -> Result<(), NoError>
where F: FnMut(&RegexCaptures) -> bool
{
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures_iter(haystack, caps, matched),
CRLF(ref m) => m.captures_iter(haystack, caps, matched),
Word(ref m) => m.captures_iter(haystack, caps, matched),
}
}
fn try_captures_iter<F, E>(
&self,
haystack: &[u8],
caps: &mut RegexCaptures,
matched: F,
) -> Result<Result<(), E>, NoError>
where F: FnMut(&RegexCaptures) -> Result<bool, E>
{
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.try_captures_iter(haystack, caps, matched),
CRLF(ref m) => m.try_captures_iter(haystack, caps, matched),
Word(ref m) => m.try_captures_iter(haystack, caps, matched),
}
}
fn captures_at(
&self,
haystack: &[u8],
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures_at(haystack, at, caps),
CRLF(ref m) => m.captures_at(haystack, at, caps),
Word(ref m) => m.captures_at(haystack, at, caps),
}
}
fn replace<F>(
&self,
haystack: &[u8],
dst: &mut Vec<u8>,
append: F,
) -> Result<(), NoError>
where F: FnMut(Match, &mut Vec<u8>) -> bool
{
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.replace(haystack, dst, append),
CRLF(ref m) => m.replace(haystack, dst, append),
Word(ref m) => m.replace(haystack, dst, append),
}
}
fn replace_with_captures<F>(
&self,
haystack: &[u8],
caps: &mut RegexCaptures,
dst: &mut Vec<u8>,
append: F,
) -> Result<(), NoError>
where F: FnMut(&Self::Captures, &mut Vec<u8>) -> bool
{
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => {
m.replace_with_captures(haystack, caps, dst, append)
}
CRLF(ref m) => {
m.replace_with_captures(haystack, caps, dst, append)
}
Word(ref m) => {
m.replace_with_captures(haystack, caps, dst, append)
}
}
}
fn is_match(&self, haystack: &[u8]) -> Result<bool, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.is_match(haystack),
CRLF(ref m) => m.is_match(haystack),
Word(ref m) => m.is_match(haystack),
}
}
fn is_match_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<bool, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.is_match_at(haystack, at),
CRLF(ref m) => m.is_match_at(haystack, at),
Word(ref m) => m.is_match_at(haystack, at),
}
}
fn shortest_match(
&self,
haystack: &[u8],
) -> Result<Option<usize>, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.shortest_match(haystack),
CRLF(ref m) => m.shortest_match(haystack),
Word(ref m) => m.shortest_match(haystack),
}
}
fn shortest_match_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<usize>, NoError> {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.shortest_match_at(haystack, at),
CRLF(ref m) => m.shortest_match_at(haystack, at),
Word(ref m) => m.shortest_match_at(haystack, at),
}
}
fn non_matching_bytes(&self) -> Option<&ByteSet> {
Some(&self.non_matching_bytes)
}
fn line_terminator(&self) -> Option<LineTerminator> {
self.config.line_terminator
}
fn find_candidate_line(
&self,
haystack: &[u8],
) -> Result<Option<LineMatchKind>, NoError> {
Ok(match self.fast_line_regex {
Some(ref regex) => {
regex.shortest_match(haystack).map(LineMatchKind::Candidate)
}
None => {
self.shortest_match(haystack)?.map(LineMatchKind::Confirmed)
}
})
}
}
/// The implementation of the standard regex matcher.
#[derive(Clone, Debug)]
struct StandardMatcher {
/// The regular expression compiled from the pattern provided by the
/// caller.
regex: Regex,
/// A map from capture group name to its corresponding index.
names: HashMap<String, usize>,
}
impl StandardMatcher {
fn new(expr: &ConfiguredHIR) -> Result<StandardMatcher, Error> {
let regex = expr.regex()?;
let mut names = HashMap::new();
for (i, optional_name) in regex.capture_names().enumerate() {
if let Some(name) = optional_name {
names.insert(name.to_string(), i);
}
}
Ok(StandardMatcher { regex, names })
}
}
impl Matcher for StandardMatcher {
type Captures = RegexCaptures;
type Error = NoError;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, NoError> {
Ok(self.regex
.find_at(haystack, at)
.map(|m| Match::new(m.start(), m.end())))
}
fn new_captures(&self) -> Result<RegexCaptures, NoError> {
Ok(RegexCaptures::new(self.regex.capture_locations()))
}
fn capture_count(&self) -> usize {
self.regex.captures_len()
}
fn capture_index(&self, name: &str) -> Option<usize> {
self.names.get(name).map(|i| *i)
}
fn try_find_iter<F, E>(
&self,
haystack: &[u8],
mut matched: F,
) -> Result<Result<(), E>, NoError>
where F: FnMut(Match) -> Result<bool, E>
{
for m in self.regex.find_iter(haystack) {
match matched(Match::new(m.start(), m.end())) {
Ok(true) => continue,
Ok(false) => return Ok(Ok(())),
Err(err) => return Ok(Err(err)),
}
}
Ok(Ok(()))
}
fn captures_at(
&self,
haystack: &[u8],
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
Ok(self.regex.captures_read_at(&mut caps.locs, haystack, at).is_some())
}
fn shortest_match_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<usize>, NoError> {
Ok(self.regex.shortest_match_at(haystack, at))
}
}
/// Represents the match offsets of each capturing group in a match.
///
/// The first, or `0`th capture group, always corresponds to the entire match
/// and is guaranteed to be present when a match occurs. The next capture
/// group, at index `1`, corresponds to the first capturing group in the regex,
/// ordered by the position at which the left opening parenthesis occurs.
///
/// Note that not all capturing groups are guaranteed to be present in a match.
/// For example, in the regex, `(?P<foo>\w)|(?P<bar>\W)`, only one of `foo`
/// or `bar` will ever be set in any given match.
///
/// In order to access a capture group by name, you'll need to first find the
/// index of the group using the corresponding matcher's `capture_index`
/// method, and then use that index with `RegexCaptures::get`.
#[derive(Clone, Debug)]
pub struct RegexCaptures {
/// Where the locations are stored.
locs: CaptureLocations,
/// These captures behave as if the capturing groups begin at the given
/// offset. When set to `0`, this has no affect and capture groups are
/// indexed like normal.
///
/// This is useful when building matchers that wrap arbitrary regular
/// expressions. For example, `WordMatcher` takes an existing regex `re`
/// and creates `(?:^|\W)(re)(?:$|\W)`, but hides the fact that the regex
/// has been wrapped from the caller. In order to do this, the matcher
/// and the capturing groups must behave as if `(re)` is the `0`th capture
/// group.
offset: usize,
/// When enable, the end of a match has `\r` stripped from it, if one
/// exists.
strip_crlf: bool,
}
impl Captures for RegexCaptures {
fn len(&self) -> usize {
self.locs.len().checked_sub(self.offset).unwrap()
}
fn get(&self, i: usize) -> Option<Match> {
if !self.strip_crlf {
let actual = i.checked_add(self.offset).unwrap();
return self.locs.pos(actual).map(|(s, e)| Match::new(s, e));
}
// currently don't support capture offsetting with CRLF stripping
assert_eq!(self.offset, 0);
let m = match self.locs.pos(i).map(|(s, e)| Match::new(s, e)) {
None => return None,
Some(m) => m,
};
// If the end position of this match corresponds to the end position
// of the overall match, then we apply our CRLF stripping. Otherwise,
// we cannot assume stripping is correct.
if i == 0 || m.end() == self.locs.pos(0).unwrap().1 {
Some(m.with_end(m.end() - 1))
} else {
Some(m)
}
}
}
impl RegexCaptures {
pub(crate) fn new(locs: CaptureLocations) -> RegexCaptures {
RegexCaptures::with_offset(locs, 0)
}
pub(crate) fn with_offset(
locs: CaptureLocations,
offset: usize,
) -> RegexCaptures {
RegexCaptures { locs, offset, strip_crlf: false }
}
pub(crate) fn locations(&mut self) -> &mut CaptureLocations {
&mut self.locs
}
pub(crate) fn strip_crlf(&mut self, yes: bool) {
self.strip_crlf = yes;
}
}
#[cfg(test)]
mod tests {
use grep_matcher::{LineMatchKind, Matcher};
use super::*;
// Test that enabling word matches does the right thing and demonstrate
// the difference between it and surrounding the regex in `\b`.
#[test]
fn word() {
let matcher = RegexMatcherBuilder::new()
.word(true)
.build(r"-2")
.unwrap();
assert!(matcher.is_match(b"abc -2 foo").unwrap());
let matcher = RegexMatcherBuilder::new()
.word(false)
.build(r"\b-2\b")
.unwrap();
assert!(!matcher.is_match(b"abc -2 foo").unwrap());
}
// Test that enabling a line terminator prevents it from matching through
// said line terminator.
#[test]
fn line_terminator() {
// This works, because there's no line terminator specified.
let matcher = RegexMatcherBuilder::new()
.build(r"abc\sxyz")
.unwrap();
assert!(matcher.is_match(b"abc\nxyz").unwrap());
// This doesn't.
let matcher = RegexMatcherBuilder::new()
.line_terminator(Some(b'\n'))
.build(r"abc\sxyz")
.unwrap();
assert!(!matcher.is_match(b"abc\nxyz").unwrap());
}
// Ensure that the builder returns an error if a line terminator is set
// and the regex could not be modified to remove a line terminator.
#[test]
fn line_terminator_error() {
assert!(RegexMatcherBuilder::new()
.line_terminator(Some(b'\n'))
.build(r"a\nz")
.is_err())
}
// Test that enabling CRLF permits `$` to match at the end of a line.
#[test]
fn line_terminator_crlf() {
// Test normal use of `$` with a `\n` line terminator.
let matcher = RegexMatcherBuilder::new()
.multi_line(true)
.build(r"abc$")
.unwrap();
assert!(matcher.is_match(b"abc\n").unwrap());
// Test that `$` doesn't match at `\r\n` boundary normally.
let matcher = RegexMatcherBuilder::new()
.multi_line(true)
.build(r"abc$")
.unwrap();
assert!(!matcher.is_match(b"abc\r\n").unwrap());
// Now check the CRLF handling.
let matcher = RegexMatcherBuilder::new()
.multi_line(true)
.crlf(true)
.build(r"abc$")
.unwrap();
assert!(matcher.is_match(b"abc\r\n").unwrap());
}
// Test that smart case works.
#[test]
fn case_smart() {
let matcher = RegexMatcherBuilder::new()
.case_smart(true)
.build(r"abc")
.unwrap();
assert!(matcher.is_match(b"ABC").unwrap());
let matcher = RegexMatcherBuilder::new()
.case_smart(true)
.build(r"aBc")
.unwrap();
assert!(!matcher.is_match(b"ABC").unwrap());
}
// Test that finding candidate lines works as expected.
#[test]
fn candidate_lines() {
fn is_confirmed(m: LineMatchKind) -> bool {
match m {
LineMatchKind::Confirmed(_) => true,
_ => false,
}
}
fn is_candidate(m: LineMatchKind) -> bool {
match m {
LineMatchKind::Candidate(_) => true,
_ => false,
}
}
// With no line terminator set, we can't employ any optimizations,
// so we get a confirmed match.
let matcher = RegexMatcherBuilder::new()
.build(r"\wfoo\s")
.unwrap();
let m = matcher.find_candidate_line(b"afoo ").unwrap().unwrap();
assert!(is_confirmed(m));
// With a line terminator and a regex specially crafted to have an
// easy-to-detect inner literal, we can apply an optimization that
// quickly finds candidate matches.
let matcher = RegexMatcherBuilder::new()
.line_terminator(Some(b'\n'))
.build(r"\wfoo\s")
.unwrap();
let m = matcher.find_candidate_line(b"afoo ").unwrap().unwrap();
assert!(is_candidate(m));
}
}

128
grep-regex/src/non_matching.rs Normal file
View File

@@ -0,0 +1,128 @@
use grep_matcher::ByteSet;
use regex_syntax::hir::{self, Hir, HirKind};
use utf8_ranges::Utf8Sequences;
/// Return a confirmed set of non-matching bytes from the given expression.
pub fn non_matching_bytes(expr: &Hir) -> ByteSet {
let mut set = ByteSet::full();
remove_matching_bytes(expr, &mut set);
set
}
/// Remove any bytes from the given set that can occur in a matched produced by
/// the given expression.
fn remove_matching_bytes(
expr: &Hir,
set: &mut ByteSet,
) {
match *expr.kind() {
HirKind::Empty
| HirKind::Anchor(_)
| HirKind::WordBoundary(_) => {}
HirKind::Literal(hir::Literal::Unicode(c)) => {
for &b in c.encode_utf8(&mut [0; 4]).as_bytes() {
set.remove(b);
}
}
HirKind::Literal(hir::Literal::Byte(b)) => {
set.remove(b);
}
HirKind::Class(hir::Class::Unicode(ref cls)) => {
for range in cls.iter() {
// This is presumably faster than encoding every codepoint
// to UTF-8 and then removing those bytes from the set.
for seq in Utf8Sequences::new(range.start(), range.end()) {
for byte_range in seq.as_slice() {
set.remove_all(byte_range.start, byte_range.end);
}
}
}
}
HirKind::Class(hir::Class::Bytes(ref cls)) => {
for range in cls.iter() {
set.remove_all(range.start(), range.end());
}
}
HirKind::Repetition(ref x) => {
remove_matching_bytes(&x.hir, set);
}
HirKind::Group(ref x) => {
remove_matching_bytes(&x.hir, set);
}
HirKind::Concat(ref xs) => {
for x in xs {
remove_matching_bytes(x, set);
}
}
HirKind::Alternation(ref xs) => {
for x in xs {
remove_matching_bytes(x, set);
}
}
}
}
#[cfg(test)]
mod tests {
use grep_matcher::ByteSet;
use regex_syntax::ParserBuilder;
use super::non_matching_bytes;
fn extract(pattern: &str) -> ByteSet {
let expr = ParserBuilder::new()
.allow_invalid_utf8(true)
.build()
.parse(pattern)
.unwrap();
non_matching_bytes(&expr)
}
fn sparse(set: &ByteSet) -> Vec<u8> {
let mut sparse_set = vec![];
for b in (0..256).map(|b| b as u8) {
if set.contains(b) {
sparse_set.push(b);
}
}
sparse_set
}
fn sparse_except(except: &[u8]) -> Vec<u8> {
let mut except_set = vec![false; 256];
for &b in except {
except_set[b as usize] = true;
}
let mut set = vec![];
for b in (0..256).map(|b| b as u8) {
if !except_set[b as usize] {
set.push(b);
}
}
set
}
#[test]
fn dot() {
assert_eq!(sparse(&extract(".")), vec![
b'\n',
192, 193, 245, 246, 247, 248, 249,
250, 251, 252, 253, 254, 255,
]);
assert_eq!(sparse(&extract("(?s).")), vec![
192, 193, 245, 246, 247, 248, 249,
250, 251, 252, 253, 254, 255,
]);
assert_eq!(sparse(&extract("(?-u).")), vec![b'\n']);
assert_eq!(sparse(&extract("(?s-u).")), vec![]);
}
#[test]
fn literal() {
assert_eq!(sparse(&extract("a")), sparse_except(&[b'a']));
assert_eq!(sparse(&extract("☃")), sparse_except(&[0xE2, 0x98, 0x83]));
assert_eq!(sparse(&extract(r"\xFF")), sparse_except(&[0xC3, 0xBF]));
assert_eq!(sparse(&extract(r"(?-u)\xFF")), sparse_except(&[0xFF]));
}
}

154
grep-regex/src/strip.rs Normal file
View File

@@ -0,0 +1,154 @@
use grep_matcher::LineTerminator;
use regex_syntax::hir::{self, Hir, HirKind};
use error::{Error, ErrorKind};
/// Return an HIR that is guaranteed to never match the given line terminator,
/// if possible.
///
/// If the transformation isn't possible, then an error is returned.
///
/// In general, if a literal line terminator occurs anywhere in the HIR, then
/// this will return an error. However, if the line terminator occurs within
/// a character class with at least one other character (that isn't also a line
/// terminator), then the line terminator is simply stripped from that class.
///
/// If the given line terminator is not ASCII, then this function returns an
/// error.
pub fn strip_from_match(
expr: Hir,
line_term: LineTerminator,
) -> Result<Hir, Error> {
if line_term.is_crlf() {
let expr1 = strip_from_match_ascii(expr, b'\r')?;
strip_from_match_ascii(expr1, b'\n')
} else {
let b = line_term.as_byte();
if b > 0x7F {
return Err(Error::new(ErrorKind::InvalidLineTerminator(b)));
}
strip_from_match_ascii(expr, b)
}
}
/// The implementation of strip_from_match. The given byte must be ASCII. This
/// function panics otherwise.
fn strip_from_match_ascii(
expr: Hir,
byte: u8,
) -> Result<Hir, Error> {
assert!(byte <= 0x7F);
let chr = byte as char;
assert_eq!(chr.len_utf8(), 1);
let invalid = || Err(Error::new(ErrorKind::NotAllowed(chr.to_string())));
Ok(match expr.into_kind() {
HirKind::Empty => Hir::empty(),
HirKind::Literal(hir::Literal::Unicode(c)) => {
if c == chr {
return invalid();
}
Hir::literal(hir::Literal::Unicode(c))
}
HirKind::Literal(hir::Literal::Byte(b)) => {
if b as char == chr {
return invalid();
}
Hir::literal(hir::Literal::Byte(b))
}
HirKind::Class(hir::Class::Unicode(mut cls)) => {
let remove = hir::ClassUnicode::new(Some(
hir::ClassUnicodeRange::new(chr, chr),
));
cls.difference(&remove);
if cls.ranges().is_empty() {
return invalid();
}
Hir::class(hir::Class::Unicode(cls))
}
HirKind::Class(hir::Class::Bytes(mut cls)) => {
let remove = hir::ClassBytes::new(Some(
hir::ClassBytesRange::new(byte, byte),
));
cls.difference(&remove);
if cls.ranges().is_empty() {
return invalid();
}
Hir::class(hir::Class::Bytes(cls))
}
HirKind::Anchor(x) => Hir::anchor(x),
HirKind::WordBoundary(x) => Hir::word_boundary(x),
HirKind::Repetition(mut x) => {
x.hir = Box::new(strip_from_match_ascii(*x.hir, byte)?);
Hir::repetition(x)
}
HirKind::Group(mut x) => {
x.hir = Box::new(strip_from_match_ascii(*x.hir, byte)?);
Hir::group(x)
}
HirKind::Concat(xs) => {
let xs = xs.into_iter()
.map(|e| strip_from_match_ascii(e, byte))
.collect::<Result<Vec<Hir>, Error>>()?;
Hir::concat(xs)
}
HirKind::Alternation(xs) => {
let xs = xs.into_iter()
.map(|e| strip_from_match_ascii(e, byte))
.collect::<Result<Vec<Hir>, Error>>()?;
Hir::alternation(xs)
}
})
}
#[cfg(test)]
mod tests {
use regex_syntax::Parser;
use error::Error;
use super::{LineTerminator, strip_from_match};
fn roundtrip(pattern: &str, byte: u8) -> String {
roundtrip_line_term(pattern, LineTerminator::byte(byte)).unwrap()
}
fn roundtrip_crlf(pattern: &str) -> String {
roundtrip_line_term(pattern, LineTerminator::crlf()).unwrap()
}
fn roundtrip_err(pattern: &str, byte: u8) -> Result<String, Error> {
roundtrip_line_term(pattern, LineTerminator::byte(byte))
}
fn roundtrip_line_term(
pattern: &str,
line_term: LineTerminator,
) -> Result<String, Error> {
let expr1 = Parser::new().parse(pattern).unwrap();
let expr2 = strip_from_match(expr1, line_term)?;
Ok(expr2.to_string())
}
#[test]
fn various() {
assert_eq!(roundtrip(r"[a\n]", b'\n'), "[a]");
assert_eq!(roundtrip(r"[a\n]", b'a'), "[\n]");
assert_eq!(roundtrip_crlf(r"[a\n]"), "[a]");
assert_eq!(roundtrip_crlf(r"[a\r]"), "[a]");
assert_eq!(roundtrip_crlf(r"[a\r\n]"), "[a]");
assert_eq!(roundtrip(r"(?-u)\s", b'a'), r"(?-u:[\x09-\x0D\x20])");
assert_eq!(roundtrip(r"(?-u)\s", b'\n'), r"(?-u:[\x09\x0B-\x0D\x20])");
assert!(roundtrip_err(r"\n", b'\n').is_err());
assert!(roundtrip_err(r"abc\n", b'\n').is_err());
assert!(roundtrip_err(r"\nabc", b'\n').is_err());
assert!(roundtrip_err(r"abc\nxyz", b'\n').is_err());
assert!(roundtrip_err(r"\x0A", b'\n').is_err());
assert!(roundtrip_err(r"\u000A", b'\n').is_err());
assert!(roundtrip_err(r"\U0000000A", b'\n').is_err());
assert!(roundtrip_err(r"\u{A}", b'\n').is_err());
assert!(roundtrip_err("\n", b'\n').is_err());
}
}

29
grep-regex/src/util.rs Normal file
View File

@@ -0,0 +1,29 @@
/// Converts an arbitrary sequence of bytes to a literal suitable for building
/// a regular expression.
pub fn bytes_to_regex(bs: &[u8]) -> String {
use std::fmt::Write;
use regex_syntax::is_meta_character;
let mut s = String::with_capacity(bs.len());
for &b in bs {
if b <= 0x7F && !is_meta_character(b as char) {
write!(s, r"{}", b as char).unwrap();
} else {
write!(s, r"\x{:02x}", b).unwrap();
}
}
s
}
/// Converts arbitrary bytes to a nice string.
pub fn show_bytes(bs: &[u8]) -> String {
use std::ascii::escape_default;
use std::str;
let mut nice = String::new();
for &b in bs {
let part: Vec<u8> = escape_default(b).collect();
nice.push_str(str::from_utf8(&part).unwrap());
}
nice
}

201
grep-regex/src/word.rs Normal file
View File

@@ -0,0 +1,201 @@
use std::collections::HashMap;
use std::cell::RefCell;
use std::sync::Arc;
use grep_matcher::{Match, Matcher, NoError};
use regex::bytes::{CaptureLocations, Regex};
use thread_local::CachedThreadLocal;
use config::ConfiguredHIR;
use error::Error;
use matcher::RegexCaptures;
/// A matcher for implementing "word match" semantics.
#[derive(Debug)]
pub struct WordMatcher {
/// The regex which is roughly `(?:^|\W)(<original pattern>)(?:$|\W)`.
regex: Regex,
/// A map from capture group name to capture group index.
names: HashMap<String, usize>,
/// A reusable buffer for finding the match location of the inner group.
locs: Arc<CachedThreadLocal<RefCell<CaptureLocations>>>,
}
impl Clone for WordMatcher {
fn clone(&self) -> WordMatcher {
// We implement Clone manually so that we get a fresh CachedThreadLocal
// such that it can set its own thread owner. This permits each thread
// usings `locs` to hit the fast path.
WordMatcher {
regex: self.regex.clone(),
names: self.names.clone(),
locs: Arc::new(CachedThreadLocal::new()),
}
}
}
impl WordMatcher {
/// Create a new matcher from the given pattern that only produces matches
/// that are considered "words."
///
/// The given options are used to construct the regular expression
/// internally.
pub fn new(expr: &ConfiguredHIR) -> Result<WordMatcher, Error> {
let word_expr = expr.with_pattern(|pat| {
format!(r"(?:(?m:^)|\W)({})(?:(?m:$)|\W)", pat)
})?;
let regex = word_expr.regex()?;
let locs = Arc::new(CachedThreadLocal::new());
let mut names = HashMap::new();
for (i, optional_name) in regex.capture_names().enumerate() {
if let Some(name) = optional_name {
names.insert(name.to_string(), i.checked_sub(1).unwrap());
}
}
Ok(WordMatcher { regex, names, locs })
}
/// Return the underlying regex used by this matcher.
pub fn regex(&self) -> &Regex {
&self.regex
}
}
impl Matcher for WordMatcher {
type Captures = RegexCaptures;
type Error = NoError;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, NoError> {
// To make this easy to get right, we extract captures here instead of
// calling `find_at`. The actual match is at capture group `1` instead
// of `0`. We *could* use `find_at` here and then trim the match after
// the fact, but that's a bit harder to get right, and it's not clear
// if it's worth it.
let cell = self.locs.get_or(|| {
Box::new(RefCell::new(self.regex.capture_locations()))
});
let mut caps = cell.borrow_mut();
self.regex.captures_read_at(&mut caps, haystack, at);
Ok(caps.get(1).map(|m| Match::new(m.0, m.1)))
}
fn new_captures(&self) -> Result<RegexCaptures, NoError> {
Ok(RegexCaptures::with_offset(self.regex.capture_locations(), 1))
}
fn capture_count(&self) -> usize {
self.regex.captures_len().checked_sub(1).unwrap()
}
fn capture_index(&self, name: &str) -> Option<usize> {
self.names.get(name).map(|i| *i)
}
fn captures_at(
&self,
haystack: &[u8],
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
let r = self.regex.captures_read_at(caps.locations(), haystack, at);
Ok(r.is_some())
}
// We specifically do not implement other methods like find_iter or
// captures_iter. Namely, the iter methods are guaranteed to be correct
// by virtue of implementing find_at and captures_at above.
}
#[cfg(test)]
mod tests {
use grep_matcher::{Captures, Match, Matcher};
use config::Config;
use super::WordMatcher;
fn matcher(pattern: &str) -> WordMatcher {
let chir = Config::default().hir(pattern).unwrap();
WordMatcher::new(&chir).unwrap()
}
fn find(pattern: &str, haystack: &str) -> Option<(usize, usize)> {
matcher(pattern)
.find(haystack.as_bytes())
.unwrap()
.map(|m| (m.start(), m.end()))
}
fn find_by_caps(pattern: &str, haystack: &str) -> Option<(usize, usize)> {
let m = matcher(pattern);
let mut caps = m.new_captures().unwrap();
if !m.captures(haystack.as_bytes(), &mut caps).unwrap() {
None
} else {
caps.get(0).map(|m| (m.start(), m.end()))
}
}
// Test that the standard `find` API reports offsets correctly.
#[test]
fn various_find() {
assert_eq!(Some((0, 3)), find(r"foo", "foo"));
assert_eq!(Some((0, 3)), find(r"foo", "foo("));
assert_eq!(Some((1, 4)), find(r"foo", "!foo("));
assert_eq!(None, find(r"foo", "!afoo("));
assert_eq!(Some((0, 3)), find(r"foo", "foo☃"));
assert_eq!(None, find(r"foo", "fooб"));
// assert_eq!(Some((0, 3)), find(r"foo", "fooб"));
// See: https://github.com/BurntSushi/ripgrep/issues/389
assert_eq!(Some((0, 2)), find(r"-2", "-2"));
}
// Test that the captures API also reports offsets correctly, just as
// find does. This exercises a different path in the code since captures
// are handled differently.
#[test]
fn various_captures() {
assert_eq!(Some((0, 3)), find_by_caps(r"foo", "foo"));
assert_eq!(Some((0, 3)), find_by_caps(r"foo", "foo("));
assert_eq!(Some((1, 4)), find_by_caps(r"foo", "!foo("));
assert_eq!(None, find_by_caps(r"foo", "!afoo("));
assert_eq!(Some((0, 3)), find_by_caps(r"foo", "foo☃"));
assert_eq!(None, find_by_caps(r"foo", "fooб"));
// assert_eq!(Some((0, 3)), find_by_caps(r"foo", "fooб"));
// See: https://github.com/BurntSushi/ripgrep/issues/389
assert_eq!(Some((0, 2)), find_by_caps(r"-2", "-2"));
}
// Test that the capture reporting methods work as advertised.
#[test]
fn capture_indexing() {
let m = matcher(r"(a)(?P<foo>b)(c)");
assert_eq!(4, m.capture_count());
assert_eq!(Some(2), m.capture_index("foo"));
let mut caps = m.new_captures().unwrap();
assert_eq!(4, caps.len());
assert!(m.captures(b"abc", &mut caps).unwrap());
assert_eq!(caps.get(0), Some(Match::new(0, 3)));
assert_eq!(caps.get(1), Some(Match::new(0, 1)));
assert_eq!(caps.get(2), Some(Match::new(1, 2)));
assert_eq!(caps.get(3), Some(Match::new(2, 3)));
assert_eq!(caps.get(4), None);
assert!(m.captures(b"#abc#", &mut caps).unwrap());
assert_eq!(caps.get(0), Some(Match::new(1, 4)));
assert_eq!(caps.get(1), Some(Match::new(1, 2)));
assert_eq!(caps.get(2), Some(Match::new(2, 3)));
assert_eq!(caps.get(3), Some(Match::new(3, 4)));
assert_eq!(caps.get(4), None);
}
}

33
grep-searcher/Cargo.toml Normal file
View File

@@ -0,0 +1,33 @@
[package]
name = "grep-searcher"
version = "0.1.3" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Fast line oriented regex searching as a library.
"""
documentation = "https://docs.rs/grep-searcher"
homepage = "https://github.com/BurntSushi/ripgrep"
repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["regex", "grep", "egrep", "search", "pattern"]
license = "Unlicense/MIT"
[dependencies]
bstr = { version = "0.1.2", default-features = false, features = ["std"] }
bytecount = "0.5"
encoding_rs = "0.8.14"
encoding_rs_io = "0.1.6"
grep-matcher = { version = "0.1.1", path = "../grep-matcher" }
log = "0.4.5"
memmap = "0.7"
[dev-dependencies]
grep-regex = { version = "0.1.1", path = "../grep-regex" }
regex = "1.1"
[features]
default = ["bytecount/runtime-dispatch-simd"]
simd-accel = ["encoding_rs/simd-accel"]
# This feature is DEPRECATED. Runtime dispatch is used for SIMD now.
avx-accel = []

21
grep-searcher/LICENSE-MIT Normal file
View File

@@ -0,0 +1,21 @@
The MIT License (MIT)
Copyright (c) 2015 Andrew Gallant
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.

37
grep-searcher/README.md Normal file
View File

@@ -0,0 +1,37 @@
grep-searcher
-------------
A high level library for executing fast line oriented searches. This handles
things like reporting contextual lines, counting lines, inverting a search,
detecting binary data, automatic UTF-16 transcoding and deciding whether or not
to use memory maps.
[![Linux build status](https://api.travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
[![](https://img.shields.io/crates/v/grep-searcher.svg)](https://crates.io/crates/grep-searcher)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).
### Documentation
[https://docs.rs/grep-searcher](https://docs.rs/grep-searcher)
**NOTE:** You probably don't want to use this crate directly. Instead, you
should prefer the facade defined in the
[`grep`](https://docs.rs/grep)
crate.
### Usage
Add this to your `Cargo.toml`:
```toml
[dependencies]
grep-searcher = "0.1"
```
and this to your crate root:
```rust
extern crate grep_searcher;
```

24
grep-searcher/UNLICENSE Normal file
View File

@@ -0,0 +1,24 @@
This is free and unencumbered software released into the public domain.
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
For more information, please refer to <http://unlicense.org/>

33
grep-searcher/examples/search-stdin.rs Normal file
View File

@@ -0,0 +1,33 @@
extern crate grep_regex;
extern crate grep_searcher;
use std::env;
use std::error::Error;
use std::io;
use std::process;
use grep_regex::RegexMatcher;
use grep_searcher::Searcher;
use grep_searcher::sinks::UTF8;
fn main() {
if let Err(err) = example() {
eprintln!("{}", err);
process::exit(1);
}
}
fn example() -> Result<(), Box<Error>> {
let pattern = match env::args().nth(1) {
Some(pattern) => pattern,
None => return Err(From::from(format!(
"Usage: search-stdin <pattern>"
))),
};
let matcher = RegexMatcher::new(&pattern)?;
Searcher::new().search_reader(&matcher, io::stdin(), UTF8(|lnum, line| {
print!("{}:{}", lnum, line);
Ok(true)
}))?;
Ok(())
}

132
grep-searcher/src/lib.rs Normal file
View File

@@ -0,0 +1,132 @@
/*!
This crate provides an implementation of line oriented search, with optional
support for multi-line search.
# Brief overview
The principle type in this crate is a
[`Searcher`](struct.Searcher.html),
which can be configured and built by a
[`SearcherBuilder`](struct.SearcherBuilder.html).
A `Searcher` is responsible for reading bytes from a source (e.g., a file),
executing a search of those bytes using a `Matcher` (e.g., a regex) and then
reporting the results of that search to a
[`Sink`](trait.Sink.html)
(e.g., stdout). The `Searcher` itself is principally responsible for managing
the consumption of bytes from a source and applying a `Matcher` over those
bytes in an efficient way. The `Searcher` is also responsible for inverting
a search, counting lines, reporting contextual lines, detecting binary data
and even deciding whether or not to use memory maps.
A `Matcher` (which is defined in the
[`grep-matcher`](https://crates.io/crates/grep-matcher)
crate) is a trait for describing the lowest levels of pattern search in a
generic way. The interface itself is very similar to the interface of a regular
expression. For example, the
[`grep-regex`](https://crates.io/crates/grep-regex)
crate provides an implementation of the `Matcher` trait using Rust's
[`regex`](https://crates.io/crates/regex)
crate.
Finally, a `Sink` describes how callers receive search results producer by a
`Searcher`. This includes routines that are called at the beginning and end of
a search, in addition to routines that are called when matching or contextual
lines are found by the `Searcher`. Implementations of `Sink` can be trivially
simple, or extraordinarily complex, such as the
`Standard` printer found in the
[`grep-printer`](https://crates.io/crates/grep-printer)
crate, which effectively implements grep-like output.
This crate also provides convenience `Sink` implementations in the
[`sinks`](sinks/index.html)
sub-module for easy searching with closures.
# Example
This example shows how to execute the searcher and read the search results
using the
[`UTF8`](sinks/struct.UTF8.html)
implementation of `Sink`.
```
extern crate grep_matcher;
extern crate grep_regex;
extern crate grep_searcher;
use std::error::Error;
use grep_matcher::Matcher;
use grep_regex::RegexMatcher;
use grep_searcher::Searcher;
use grep_searcher::sinks::UTF8;
const SHERLOCK: &'static [u8] = b"\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, success in the province of detective work must always
be, to a very large extent, the result of luck. Sherlock Holmes
can extract a clew from a wisp of straw or a flake of cigar ash;
but Doctor Watson has to have it taken out for him and dusted,
and exhibited clearly, with a label attached.
";
# fn main() { example().unwrap() }
fn example() -> Result<(), Box<Error>> {
let matcher = RegexMatcher::new(r"Doctor \w+")?;
let mut matches: Vec<(u64, String)> = vec![];
Searcher::new().search_slice(&matcher, SHERLOCK, UTF8(|lnum, line| {
// We are guaranteed to find a match, so the unwrap is OK.
let mymatch = matcher.find(line.as_bytes())?.unwrap();
matches.push((lnum, line[mymatch].to_string()));
Ok(true)
}))?;
assert_eq!(matches.len(), 2);
assert_eq!(
matches[0],
(1, "Doctor Watsons".to_string())
);
assert_eq!(
matches[1],
(5, "Doctor Watson".to_string())
);
Ok(())
}
```
See also `examples/search-stdin.rs` from the root of this crate's directory
to see a similar example that accepts a pattern on the command line and
searches stdin.
*/
#![deny(missing_docs)]
extern crate bstr;
extern crate bytecount;
extern crate encoding_rs;
extern crate encoding_rs_io;
extern crate grep_matcher;
#[macro_use]
extern crate log;
extern crate memmap;
#[cfg(test)]
extern crate regex;
pub use lines::{LineIter, LineStep};
pub use searcher::{
BinaryDetection, ConfigError, Encoding, MmapChoice,
Searcher, SearcherBuilder,
};
pub use sink::{
Sink, SinkError,
SinkContext, SinkContextKind, SinkFinish, SinkMatch,
};
pub use sink::sinks;
#[macro_use]
mod macros;
mod line_buffer;
mod lines;
mod searcher;
mod sink;
#[cfg(test)]
mod testutil;

939
grep-searcher/src/line_buffer.rs Normal file
View File

@@ -0,0 +1,939 @@
use std::cmp;
use std::io;
use bstr::{BStr, BString};
/// The default buffer capacity that we use for the line buffer.
pub(crate) const DEFAULT_BUFFER_CAPACITY: usize = 8 * (1<<10); // 8 KB
/// The behavior of a searcher in the face of long lines and big contexts.
///
/// When searching data incrementally using a fixed size buffer, this controls
/// the amount of *additional* memory to allocate beyond the size of the buffer
/// to accommodate lines (which may include the lines in a context window, when
/// enabled) that do not fit in the buffer.
///
/// The default is to eagerly allocate without a limit.
#[derive(Clone, Copy, Debug)]
pub enum BufferAllocation {
/// Attempt to expand the size of the buffer until either at least the next
/// line fits into memory or until all available memory is exhausted.
///
/// This is the default.
Eager,
/// Limit the amount of additional memory allocated to the given size. If
/// a line is found that requires more memory than is allowed here, then
/// stop reading and return an error.
Error(usize),
}
impl Default for BufferAllocation {
fn default() -> BufferAllocation {
BufferAllocation::Eager
}
}
/// Create a new error to be used when a configured allocation limit has been
/// reached.
pub fn alloc_error(limit: usize) -> io::Error {
let msg = format!("configured allocation limit ({}) exceeded", limit);
io::Error::new(io::ErrorKind::Other, msg)
}
/// The behavior of binary detection in the line buffer.
///
/// Binary detection is the process of _heuristically_ identifying whether a
/// given chunk of data is binary or not, and then taking an action based on
/// the result of that heuristic. The motivation behind detecting binary data
/// is that binary data often indicates data that is undesirable to search
/// using textual patterns. Of course, there are many cases in which this isn't
/// true, which is why binary detection is disabled by default.
#[derive(Clone, Copy, Debug)]
pub enum BinaryDetection {
/// No binary detection is performed. Data reported by the line buffer may
/// contain arbitrary bytes.
None,
/// The given byte is searched in all contents read by the line buffer. If
/// it occurs, then the data is considered binary and the line buffer acts
/// as if it reached EOF. The line buffer guarantees that this byte will
/// never be observable by callers.
Quit(u8),
/// The given byte is searched in all contents read by the line buffer. If
/// it occurs, then it is replaced by the line terminator. The line buffer
/// guarantees that this byte will never be observable by callers.
Convert(u8),
}
impl Default for BinaryDetection {
fn default() -> BinaryDetection {
BinaryDetection::None
}
}
impl BinaryDetection {
/// Returns true if and only if the detection heuristic demands that
/// the line buffer stop read data once binary data is observed.
fn is_quit(&self) -> bool {
match *self {
BinaryDetection::Quit(_) => true,
_ => false,
}
}
}
/// The configuration of a buffer. This contains options that are fixed once
/// a buffer has been constructed.
#[derive(Clone, Copy, Debug)]
struct Config {
/// The number of bytes to attempt to read at a time.
capacity: usize,
/// The line terminator.
lineterm: u8,
/// The behavior for handling long lines.
buffer_alloc: BufferAllocation,
/// When set, the presence of the given byte indicates binary content.
binary: BinaryDetection,
}
impl Default for Config {
fn default() -> Config {
Config {
capacity: DEFAULT_BUFFER_CAPACITY,
lineterm: b'\n',
buffer_alloc: BufferAllocation::default(),
binary: BinaryDetection::default(),
}
}
}
/// A builder for constructing line buffers.
#[derive(Clone, Debug, Default)]
pub struct LineBufferBuilder {
config: Config,
}
impl LineBufferBuilder {
/// Create a new builder for a buffer.
pub fn new() -> LineBufferBuilder {
LineBufferBuilder { config: Config::default() }
}
/// Create a new line buffer from this builder's configuration.
pub fn build(&self) -> LineBuffer {
LineBuffer {
config: self.config,
buf: BString::from(vec![0; self.config.capacity]),
pos: 0,
last_lineterm: 0,
end: 0,
absolute_byte_offset: 0,
binary_byte_offset: None,
}
}
/// Set the default capacity to use for a buffer.
///
/// In general, the capacity of a buffer corresponds to the amount of data
/// to hold in memory, and the size of the reads to make to the underlying
/// reader.
///
/// This is set to a reasonable default and probably shouldn't be changed
/// unless there's a specific reason to do so.
pub fn capacity(&mut self, capacity: usize) -> &mut LineBufferBuilder {
self.config.capacity = capacity;
self
}
/// Set the line terminator for the buffer.
///
/// Every buffer has a line terminator, and this line terminator is used
/// to determine how to roll the buffer forward. For example, when a read
/// to the buffer's underlying reader occurs, the end of the data that is
/// read is likely to correspond to an incomplete line. As a line buffer,
/// callers should not access this data since it is incomplete. The line
/// terminator is how the line buffer determines the part of the read that
/// is incomplete.
///
/// By default, this is set to `b'\n'`.
pub fn line_terminator(&mut self, lineterm: u8) -> &mut LineBufferBuilder {
self.config.lineterm = lineterm;
self
}
/// Set the maximum amount of additional memory to allocate for long lines.
///
/// In order to enable line oriented search, a fundamental requirement is
/// that, at a minimum, each line must be able to fit into memory. This
/// setting controls how big that line is allowed to be. By default, this
/// is set to `BufferAllocation::Eager`, which means a line buffer will
/// attempt to allocate as much memory as possible to fit a line, and will
/// only be limited by available memory.
///
/// Note that this setting only applies to the amount of *additional*
/// memory to allocate, beyond the capacity of the buffer. That means that
/// a value of `0` is sensible, and in particular, will guarantee that a
/// line buffer will never allocate additional memory beyond its initial
/// capacity.
pub fn buffer_alloc(
&mut self,
behavior: BufferAllocation,
) -> &mut LineBufferBuilder {
self.config.buffer_alloc = behavior;
self
}
/// Whether to enable binary detection or not. Depending on the setting,
/// this can either cause the line buffer to report EOF early or it can
/// cause the line buffer to clean the data.
///
/// By default, this is disabled. In general, binary detection should be
/// viewed as an imperfect heuristic.
pub fn binary_detection(
&mut self,
detection: BinaryDetection,
) -> &mut LineBufferBuilder {
self.config.binary = detection;
self
}
}
/// A line buffer reader efficiently reads a line oriented buffer from an
/// arbitrary reader.
#[derive(Debug)]
pub struct LineBufferReader<'b, R> {
rdr: R,
line_buffer: &'b mut LineBuffer,
}
impl<'b, R: io::Read> LineBufferReader<'b, R> {
/// Create a new buffered reader that reads from `rdr` and uses the given
/// `line_buffer` as an intermediate buffer.
///
/// This does not change the binary detection behavior of the given line
/// buffer.
pub fn new(
rdr: R,
line_buffer: &'b mut LineBuffer,
) -> LineBufferReader<'b, R> {
line_buffer.clear();
LineBufferReader { rdr, line_buffer }
}
/// The absolute byte offset which corresponds to the starting offsets
/// of the data returned by `buffer` relative to the beginning of the
/// underlying reader's contents. As such, this offset does not generally
/// correspond to an offset in memory. It is typically used for reporting
/// purposes. It can also be used for counting the number of bytes that
/// have been searched.
pub fn absolute_byte_offset(&self) -> u64 {
self.line_buffer.absolute_byte_offset()
}
/// If binary data was detected, then this returns the absolute byte offset
/// at which binary data was initially found.
pub fn binary_byte_offset(&self) -> Option<u64> {
self.line_buffer.binary_byte_offset()
}
/// Fill the contents of this buffer by discarding the part of the buffer
/// that has been consumed. The free space created by discarding the
/// consumed part of the buffer is then filled with new data from the
/// reader.
///
/// If EOF is reached, then `false` is returned. Otherwise, `true` is
/// returned. (Note that if this line buffer's binary detection is set to
/// `Quit`, then the presence of binary data will cause this buffer to
/// behave as if it had seen EOF at the first occurrence of binary data.)
///
/// This forwards any errors returned by the underlying reader, and will
/// also return an error if the buffer must be expanded past its allocation
/// limit, as governed by the buffer allocation strategy.
pub fn fill(&mut self) -> Result<bool, io::Error> {
self.line_buffer.fill(&mut self.rdr)
}
/// Return the contents of this buffer.
pub fn buffer(&self) -> &[u8] {
self.line_buffer.buffer().as_bytes()
}
/// Return the underlying buffer as a byte string. Used for tests only.
#[cfg(test)]
fn bstr(&self) -> &BStr {
self.line_buffer.buffer()
}
/// Consume the number of bytes provided. This must be less than or equal
/// to the number of bytes returned by `buffer`.
pub fn consume(&mut self, amt: usize) {
self.line_buffer.consume(amt);
}
/// Consumes the remainder of the buffer. Subsequent calls to `buffer` are
/// guaranteed to return an empty slice until the buffer is refilled.
///
/// This is a convenience function for `consume(buffer.len())`.
#[cfg(test)]
fn consume_all(&mut self) {
self.line_buffer.consume_all();
}
}
/// A line buffer manages a (typically fixed) buffer for holding lines.
///
/// Callers should create line buffers sparingly and reuse them when possible.
/// Line buffers cannot be used directly, but instead must be used via the
/// LineBufferReader.
#[derive(Clone, Debug)]
pub struct LineBuffer {
/// The configuration of this buffer.
config: Config,
/// The primary buffer with which to hold data.
buf: BString,
/// The current position of this buffer. This is always a valid sliceable
/// index into `buf`, and its maximum value is the length of `buf`.
pos: usize,
/// The end position of searchable content in this buffer. This is either
/// set to just after the final line terminator in the buffer, or to just
/// after the end of the last byte emitted by the reader when the reader
/// has been exhausted.
last_lineterm: usize,
/// The end position of the buffer. This is always greater than or equal to
/// last_lineterm. The bytes between last_lineterm and end, if any, always
/// correspond to a partial line.
end: usize,
/// The absolute byte offset corresponding to `pos`. This is most typically
/// not a valid index into addressable memory, but rather, an offset that
/// is relative to all data that passes through a line buffer (since
/// construction or since the last time `clear` was called).
///
/// When the line buffer reaches EOF, this is set to the position just
/// after the last byte read from the underlying reader. That is, it
/// becomes the total count of bytes that have been read.
absolute_byte_offset: u64,
/// If binary data was found, this records the absolute byte offset at
/// which it was first detected.
binary_byte_offset: Option<u64>,
}
impl LineBuffer {
/// Reset this buffer, such that it can be used with a new reader.
fn clear(&mut self) {
self.pos = 0;
self.last_lineterm = 0;
self.end = 0;
self.absolute_byte_offset = 0;
self.binary_byte_offset = None;
}
/// The absolute byte offset which corresponds to the starting offsets
/// of the data returned by `buffer` relative to the beginning of the
/// reader's contents. As such, this offset does not generally correspond
/// to an offset in memory. It is typically used for reporting purposes,
/// particularly in error messages.
///
/// This is reset to `0` when `clear` is called.
fn absolute_byte_offset(&self) -> u64 {
self.absolute_byte_offset
}
/// If binary data was detected, then this returns the absolute byte offset
/// at which binary data was initially found.
fn binary_byte_offset(&self) -> Option<u64> {
self.binary_byte_offset
}
/// Return the contents of this buffer.
fn buffer(&self) -> &BStr {
&self.buf[self.pos..self.last_lineterm]
}
/// Return the contents of the free space beyond the end of the buffer as
/// a mutable slice.
fn free_buffer(&mut self) -> &mut BStr {
&mut self.buf[self.end..]
}
/// Consume the number of bytes provided. This must be less than or equal
/// to the number of bytes returned by `buffer`.
fn consume(&mut self, amt: usize) {
assert!(amt <= self.buffer().len());
self.pos += amt;
self.absolute_byte_offset += amt as u64;
}
/// Consumes the remainder of the buffer. Subsequent calls to `buffer` are
/// guaranteed to return an empty slice until the buffer is refilled.
///
/// This is a convenience function for `consume(buffer.len())`.
#[cfg(test)]
fn consume_all(&mut self) {
let amt = self.buffer().len();
self.consume(amt);
}
/// Fill the contents of this buffer by discarding the part of the buffer
/// that has been consumed. The free space created by discarding the
/// consumed part of the buffer is then filled with new data from the given
/// reader.
///
/// Callers should provide the same reader to this line buffer in
/// subsequent calls to fill. A different reader can only be used
/// immediately following a call to `clear`.
///
/// If EOF is reached, then `false` is returned. Otherwise, `true` is
/// returned. (Note that if this line buffer's binary detection is set to
/// `Quit`, then the presence of binary data will cause this buffer to
/// behave as if it had seen EOF.)
///
/// This forwards any errors returned by `rdr`, and will also return an
/// error if the buffer must be expanded past its allocation limit, as
/// governed by the buffer allocation strategy.
fn fill<R: io::Read>(&mut self, mut rdr: R) -> Result<bool, io::Error> {
// If the binary detection heuristic tells us to quit once binary data
// has been observed, then we no longer read new data and reach EOF
// once the current buffer has been consumed.
if self.config.binary.is_quit() && self.binary_byte_offset.is_some() {
return Ok(!self.buffer().is_empty());
}
self.roll();
assert_eq!(self.pos, 0);
loop {
self.ensure_capacity()?;
let readlen = rdr.read(self.free_buffer().as_bytes_mut())?;
if readlen == 0 {
// We're only done reading for good once the caller has
// consumed everything.
self.last_lineterm = self.end;
return Ok(!self.buffer().is_empty());
}
// Get a mutable view into the bytes we've just read. These are
// the bytes that we do binary detection on, and also the bytes we
// search to find the last line terminator. We need a mutable slice
// in the case of binary conversion.
let oldend = self.end;
self.end += readlen;
let newbytes = &mut self.buf[oldend..self.end];
// Binary detection.
match self.config.binary {
BinaryDetection::None => {} // nothing to do
BinaryDetection::Quit(byte) => {
if let Some(i) = newbytes.find_byte(byte) {
self.end = oldend + i;
self.last_lineterm = self.end;
self.binary_byte_offset =
Some(self.absolute_byte_offset + self.end as u64);
// If the first byte in our buffer is a binary byte,
// then our buffer is empty and we should report as
// such to the caller.
return Ok(self.pos < self.end);
}
}
BinaryDetection::Convert(byte) => {
if let Some(i) = replace_bytes(
newbytes,
byte,
self.config.lineterm,
) {
// Record only the first binary offset.
if self.binary_byte_offset.is_none() {
self.binary_byte_offset =
Some(self.absolute_byte_offset
+ (oldend + i) as u64);
}
}
}
}
// Update our `last_lineterm` positions if we read one.
if let Some(i) = newbytes.rfind_byte(self.config.lineterm) {
self.last_lineterm = oldend + i + 1;
return Ok(true);
}
// At this point, if we couldn't find a line terminator, then we
// don't have a complete line. Therefore, we try to read more!
}
}
/// Roll the unconsumed parts of the buffer to the front.
///
/// This operation is idempotent.
///
/// After rolling, `last_lineterm` and `end` point to the same location,
/// and `pos` is always set to `0`.
fn roll(&mut self) {
if self.pos == self.end {
self.pos = 0;
self.last_lineterm = 0;
self.end = 0;
return;
}
let roll_len = self.end - self.pos;
self.buf.copy_within(self.pos.., 0);
self.pos = 0;
self.last_lineterm = roll_len;
self.end = roll_len;
}
/// Ensures that the internal buffer has a non-zero amount of free space
/// in which to read more data. If there is no free space, then more is
/// allocated. If the allocation must exceed the configured limit, then
/// this returns an error.
fn ensure_capacity(&mut self) -> Result<(), io::Error> {
if !self.free_buffer().is_empty() {
return Ok(());
}
// `len` is used for computing the next allocation size. The capacity
// is permitted to start at `0`, so we make sure it's at least `1`.
let len = cmp::max(1, self.buf.len());
let additional = match self.config.buffer_alloc {
BufferAllocation::Eager => len * 2,
BufferAllocation::Error(limit) => {
let used = self.buf.len() - self.config.capacity;
let n = cmp::min(len * 2, limit - used);
if n == 0 {
return Err(alloc_error(self.config.capacity + limit));
}
n
}
};
assert!(additional > 0);
let newlen = self.buf.len() + additional;
self.buf.resize(newlen, 0);
assert!(!self.free_buffer().is_empty());
Ok(())
}
}
/// Replaces `src` with `replacement` in bytes, and return the offset of the
/// first replacement, if one exists.
fn replace_bytes(bytes: &mut BStr, src: u8, replacement: u8) -> Option<usize> {
if src == replacement {
return None;
}
let mut first_pos = None;
let mut pos = 0;
while let Some(i) = bytes[pos..].find_byte(src).map(|i| pos + i) {
if first_pos.is_none() {
first_pos = Some(i);
}
bytes[i] = replacement;
pos = i + 1;
while bytes.get(pos) == Some(&src) {
bytes[pos] = replacement;
pos += 1;
}
}
first_pos
}
#[cfg(test)]
mod tests {
use std::str;
use bstr::BString;
use super::*;
const SHERLOCK: &'static str = "\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, success in the province of detective work must always
be, to a very large extent, the result of luck. Sherlock Holmes
can extract a clew from a wisp of straw or a flake of cigar ash;
but Doctor Watson has to have it taken out for him and dusted,
and exhibited clearly, with a label attached.\
";
fn s(slice: &str) -> String {
slice.to_string()
}
fn replace_str(
slice: &str,
src: u8,
replacement: u8,
) -> (String, Option<usize>) {
let mut dst = BString::from(slice);
let result = replace_bytes(&mut dst, src, replacement);
(dst.into_string().unwrap(), result)
}
#[test]
fn replace() {
assert_eq!(replace_str("abc", b'b', b'z'), (s("azc"), Some(1)));
assert_eq!(replace_str("abb", b'b', b'z'), (s("azz"), Some(1)));
assert_eq!(replace_str("aba", b'a', b'z'), (s("zbz"), Some(0)));
assert_eq!(replace_str("bbb", b'b', b'z'), (s("zzz"), Some(0)));
assert_eq!(replace_str("bac", b'b', b'z'), (s("zac"), Some(0)));
}
#[test]
fn buffer_basics1() {
let bytes = "homer\nlisa\nmaggie";
let mut linebuf = LineBufferBuilder::new().build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\n");
assert_eq!(rdr.absolute_byte_offset(), 0);
rdr.consume(5);
assert_eq!(rdr.absolute_byte_offset(), 5);
rdr.consume_all();
assert_eq!(rdr.absolute_byte_offset(), 11);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "maggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_basics2() {
let bytes = "homer\nlisa\nmaggie\n";
let mut linebuf = LineBufferBuilder::new().build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_basics3() {
let bytes = "\n";
let mut linebuf = LineBufferBuilder::new().build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_basics4() {
let bytes = "\n\n";
let mut linebuf = LineBufferBuilder::new().build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\n\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_empty() {
let bytes = "";
let mut linebuf = LineBufferBuilder::new().build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_zero_capacity() {
let bytes = "homer\nlisa\nmaggie";
let mut linebuf = LineBufferBuilder::new().capacity(0).build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
while rdr.fill().unwrap() {
rdr.consume_all();
}
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_small_capacity() {
let bytes = "homer\nlisa\nmaggie";
let mut linebuf = LineBufferBuilder::new().capacity(1).build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
let mut got = BString::new();
while rdr.fill().unwrap() {
got.push(rdr.buffer());
rdr.consume_all();
}
assert_eq!(bytes, got);
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_limited_capacity1() {
let bytes = "homer\nlisa\nmaggie";
let mut linebuf = LineBufferBuilder::new()
.capacity(1)
.buffer_alloc(BufferAllocation::Error(5))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\n");
rdr.consume_all();
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "lisa\n");
rdr.consume_all();
// This returns an error because while we have just enough room to
// store maggie in the buffer, we *don't* have enough room to read one
// more byte, so we don't know whether we're at EOF or not, and
// therefore must give up.
assert!(rdr.fill().is_err());
// We can mush on though!
assert_eq!(rdr.bstr(), "m");
rdr.consume_all();
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "aggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
}
#[test]
fn buffer_limited_capacity2() {
let bytes = "homer\nlisa\nmaggie";
let mut linebuf = LineBufferBuilder::new()
.capacity(1)
.buffer_alloc(BufferAllocation::Error(6))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\n");
rdr.consume_all();
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "lisa\n");
rdr.consume_all();
// We have just enough space.
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "maggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
}
#[test]
fn buffer_limited_capacity3() {
let bytes = "homer\nlisa\nmaggie";
let mut linebuf = LineBufferBuilder::new()
.capacity(1)
.buffer_alloc(BufferAllocation::Error(0))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().is_err());
assert_eq!(rdr.bstr(), "");
}
#[test]
fn buffer_binary_none() {
let bytes = "homer\nli\x00sa\nmaggie\n";
let mut linebuf = LineBufferBuilder::new().build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nli\x00sa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), None);
}
#[test]
fn buffer_binary_quit1() {
let bytes = "homer\nli\x00sa\nmaggie\n";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Quit(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nli");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), 8);
assert_eq!(rdr.binary_byte_offset(), Some(8));
}
#[test]
fn buffer_binary_quit2() {
let bytes = "\x00homer\nlisa\nmaggie\n";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Quit(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "");
assert_eq!(rdr.absolute_byte_offset(), 0);
assert_eq!(rdr.binary_byte_offset(), Some(0));
}
#[test]
fn buffer_binary_quit3() {
let bytes = "homer\nlisa\nmaggie\n\x00";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Quit(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64 - 1);
assert_eq!(rdr.binary_byte_offset(), Some(bytes.len() as u64 - 1));
}
#[test]
fn buffer_binary_quit4() {
let bytes = "homer\nlisa\nmaggie\x00\n";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Quit(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64 - 2);
assert_eq!(rdr.binary_byte_offset(), Some(bytes.len() as u64 - 2));
}
#[test]
fn buffer_binary_quit5() {
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Quit(b'u'))
.build();
let mut rdr = LineBufferReader::new(SHERLOCK.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, s\
");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), 76);
assert_eq!(rdr.binary_byte_offset(), Some(76));
assert_eq!(SHERLOCK.as_bytes()[76], b'u');
}
#[test]
fn buffer_binary_convert1() {
let bytes = "homer\nli\x00sa\nmaggie\n";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Convert(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nli\nsa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), Some(8));
}
#[test]
fn buffer_binary_convert2() {
let bytes = "\x00homer\nlisa\nmaggie\n";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Convert(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\nhomer\nlisa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), Some(0));
}
#[test]
fn buffer_binary_convert3() {
let bytes = "homer\nlisa\nmaggie\n\x00";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Convert(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), Some(bytes.len() as u64 - 1));
}
#[test]
fn buffer_binary_convert4() {
let bytes = "homer\nlisa\nmaggie\x00\n";
let mut linebuf = LineBufferBuilder::new()
.binary_detection(BinaryDetection::Convert(b'\x00'))
.build();
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.absolute_byte_offset(), bytes.len() as u64);
assert_eq!(rdr.binary_byte_offset(), Some(bytes.len() as u64 - 2));
}
}

464
grep-searcher/src/lines.rs Normal file
View File

@@ -0,0 +1,464 @@
/*!
A collection of routines for performing operations on lines.
*/
use bstr::B;
use bytecount;
use grep_matcher::{LineTerminator, Match};
/// An iterator over lines in a particular slice of bytes.
///
/// Line terminators are considered part of the line they terminate. All lines
/// yielded by the iterator are guaranteed to be non-empty.
///
/// `'b` refers to the lifetime of the underlying bytes.
#[derive(Debug)]
pub struct LineIter<'b> {
bytes: &'b [u8],
stepper: LineStep,
}
impl<'b> LineIter<'b> {
/// Create a new line iterator that yields lines in the given bytes that
/// are terminated by `line_term`.
pub fn new(line_term: u8, bytes: &'b [u8]) -> LineIter<'b> {
LineIter {
bytes: bytes,
stepper: LineStep::new(line_term, 0, bytes.len()),
}
}
}
impl<'b> Iterator for LineIter<'b> {
type Item = &'b [u8];
fn next(&mut self) -> Option<&'b [u8]> {
self.stepper.next_match(self.bytes).map(|m| &self.bytes[m])
}
}
/// An explicit iterator over lines in a particular slice of bytes.
///
/// This iterator avoids borrowing the bytes themselves, and instead requires
/// callers to explicitly provide the bytes when moving through the iterator.
/// While not idiomatic, this provides a simple way of iterating over lines
/// that doesn't require borrowing the slice itself, which can be convenient.
///
/// Line terminators are considered part of the line they terminate. All lines
/// yielded by the iterator are guaranteed to be non-empty.
#[derive(Debug)]
pub struct LineStep {
line_term: u8,
pos: usize,
end: usize,
}
impl LineStep {
/// Create a new line iterator over the given range of bytes using the
/// given line terminator.
///
/// Callers should provide the actual bytes for each call to `next`. The
/// same slice must be provided to each call.
///
/// This panics if `start` is not less than or equal to `end`.
pub fn new(line_term: u8, start: usize, end: usize) -> LineStep {
LineStep { line_term, pos: start, end: end }
}
/// Return the start and end position of the next line in the given bytes.
///
/// The caller must past exactly the same slice of bytes for each call to
/// `next`.
///
/// The range returned includes the line terminator. Ranges are always
/// non-empty.
pub fn next(&mut self, bytes: &[u8]) -> Option<(usize, usize)> {
self.next_impl(bytes)
}
/// Like next, but returns a `Match` instead of a tuple.
#[inline(always)]
pub(crate) fn next_match(&mut self, bytes: &[u8]) -> Option<Match> {
self.next_impl(bytes).map(|(s, e)| Match::new(s, e))
}
#[inline(always)]
fn next_impl(&mut self, mut bytes: &[u8]) -> Option<(usize, usize)> {
bytes = &bytes[..self.end];
match B(&bytes[self.pos..]).find_byte(self.line_term) {
None => {
if self.pos < bytes.len() {
let m = (self.pos, bytes.len());
assert!(m.0 <= m.1);
self.pos = m.1;
Some(m)
} else {
None
}
}
Some(line_end) => {
let m = (self.pos, self.pos + line_end + 1);
assert!(m.0 <= m.1);
self.pos = m.1;
Some(m)
}
}
}
}
/// Count the number of occurrences of `line_term` in `bytes`.
pub fn count(bytes: &[u8], line_term: u8) -> u64 {
bytecount::count(bytes, line_term) as u64
}
/// Given a line that possibly ends with a terminator, return that line without
/// the terminator.
#[inline(always)]
pub fn without_terminator(bytes: &[u8], line_term: LineTerminator) -> &[u8] {
let line_term = line_term.as_bytes();
let start = bytes.len().saturating_sub(line_term.len());
if bytes.get(start..) == Some(line_term) {
return &bytes[..bytes.len() - line_term.len()];
}
bytes
}
/// Return the start and end offsets of the lines containing the given range
/// of bytes.
///
/// Line terminators are considered part of the line they terminate.
#[inline(always)]
pub fn locate(
bytes: &[u8],
line_term: u8,
range: Match,
) -> Match {
let line_start = B(&bytes[..range.start()])
.rfind_byte(line_term)
.map_or(0, |i| i + 1);
let line_end =
if range.end() > line_start && bytes[range.end() - 1] == line_term {
range.end()
} else {
B(&bytes[range.end()..])
.find_byte(line_term)
.map_or(bytes.len(), |i| range.end() + i + 1)
};
Match::new(line_start, line_end)
}
/// Returns the minimal starting offset of the line that occurs `count` lines
/// before the last line in `bytes`.
///
/// Lines are terminated by `line_term`. If `count` is zero, then this returns
/// the starting offset of the last line in `bytes`.
///
/// If `bytes` ends with a line terminator, then the terminator itself is
/// considered part of the last line.
pub fn preceding(bytes: &[u8], line_term: u8, count: usize) -> usize {
preceding_by_pos(bytes, bytes.len(), line_term, count)
}
/// Returns the minimal starting offset of the line that occurs `count` lines
/// before the line containing `pos`. Lines are terminated by `line_term`.
/// If `count` is zero, then this returns the starting offset of the line
/// containing `pos`.
///
/// If `pos` points just past a line terminator, then it is considered part of
/// the line that it terminates. For example, given `bytes = b"abc\nxyz\n"`
/// and `pos = 7`, `preceding(bytes, pos, b'\n', 0)` returns `4` (as does `pos
/// = 8`) and `preceding(bytes, pos, `b'\n', 1)` returns `0`.
fn preceding_by_pos(
bytes: &[u8],
mut pos: usize,
line_term: u8,
mut count: usize,
) -> usize {
if pos == 0 {
return 0;
} else if bytes[pos - 1] == line_term {
pos -= 1;
}
loop {
match B(&bytes[..pos]).rfind_byte(line_term) {
None => {
return 0;
}
Some(i) => {
if count == 0 {
return i + 1;
} else if i == 0 {
return 0;
}
count -= 1;
pos = i;
}
}
}
}
#[cfg(test)]
mod tests {
use std::ops::Range;
use std::str;
use grep_matcher::Match;
use super::*;
const SHERLOCK: &'static str = "\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, success in the province of detective work must always
be, to a very large extent, the result of luck. Sherlock Holmes
can extract a clew from a wisp of straw or a flake of cigar ash;
but Doctor Watson has to have it taken out for him and dusted,
and exhibited clearly, with a label attached.\
";
fn m(start: usize, end: usize) -> Match {
Match::new(start, end)
}
fn lines(text: &str) -> Vec<&str> {
let mut results = vec![];
let mut it = LineStep::new(b'\n', 0, text.len());
while let Some(m) = it.next_match(text.as_bytes()) {
results.push(&text[m]);
}
results
}
fn line_ranges(text: &str) -> Vec<Range<usize>> {
let mut results = vec![];
let mut it = LineStep::new(b'\n', 0, text.len());
while let Some(m) = it.next_match(text.as_bytes()) {
results.push(m.start()..m.end());
}
results
}
fn prev(text: &str, pos: usize, count: usize) -> usize {
preceding_by_pos(text.as_bytes(), pos, b'\n', count)
}
fn loc(text: &str, start: usize, end: usize) -> Match {
locate(text.as_bytes(), b'\n', Match::new(start, end))
}
#[test]
fn line_count() {
assert_eq!(0, count(b"", b'\n'));
assert_eq!(1, count(b"\n", b'\n'));
assert_eq!(2, count(b"\n\n", b'\n'));
assert_eq!(2, count(b"a\nb\nc", b'\n'));
}
#[test]
fn line_locate() {
let t = SHERLOCK;
let lines = line_ranges(t);
assert_eq!(
loc(t, lines[0].start, lines[0].end),
m(lines[0].start, lines[0].end));
assert_eq!(
loc(t, lines[0].start + 1, lines[0].end),
m(lines[0].start, lines[0].end));
assert_eq!(
loc(t, lines[0].end - 1, lines[0].end),
m(lines[0].start, lines[0].end));
assert_eq!(
loc(t, lines[0].end, lines[0].end),
m(lines[1].start, lines[1].end));
assert_eq!(
loc(t, lines[5].start, lines[5].end),
m(lines[5].start, lines[5].end));
assert_eq!(
loc(t, lines[5].start + 1, lines[5].end),
m(lines[5].start, lines[5].end));
assert_eq!(
loc(t, lines[5].end - 1, lines[5].end),
m(lines[5].start, lines[5].end));
assert_eq!(
loc(t, lines[5].end, lines[5].end),
m(lines[5].start, lines[5].end));
}
#[test]
fn line_locate_weird() {
assert_eq!(loc("", 0, 0), m(0, 0));
assert_eq!(loc("\n", 0, 1), m(0, 1));
assert_eq!(loc("\n", 1, 1), m(1, 1));
assert_eq!(loc("\n\n", 0, 0), m(0, 1));
assert_eq!(loc("\n\n", 0, 1), m(0, 1));
assert_eq!(loc("\n\n", 1, 1), m(1, 2));
assert_eq!(loc("\n\n", 1, 2), m(1, 2));
assert_eq!(loc("\n\n", 2, 2), m(2, 2));
assert_eq!(loc("a\nb\nc", 0, 1), m(0, 2));
assert_eq!(loc("a\nb\nc", 1, 2), m(0, 2));
assert_eq!(loc("a\nb\nc", 2, 3), m(2, 4));
assert_eq!(loc("a\nb\nc", 3, 4), m(2, 4));
assert_eq!(loc("a\nb\nc", 4, 5), m(4, 5));
assert_eq!(loc("a\nb\nc", 5, 5), m(4, 5));
}
#[test]
fn line_iter() {
assert_eq!(lines("abc"), vec!["abc"]);
assert_eq!(lines("abc\n"), vec!["abc\n"]);
assert_eq!(lines("abc\nxyz"), vec!["abc\n", "xyz"]);
assert_eq!(lines("abc\nxyz\n"), vec!["abc\n", "xyz\n"]);
assert_eq!(lines("abc\n\n"), vec!["abc\n", "\n"]);
assert_eq!(lines("abc\n\n\n"), vec!["abc\n", "\n", "\n"]);
assert_eq!(lines("abc\n\nxyz"), vec!["abc\n", "\n", "xyz"]);
assert_eq!(lines("abc\n\nxyz\n"), vec!["abc\n", "\n", "xyz\n"]);
assert_eq!(lines("abc\nxyz\n\n"), vec!["abc\n", "xyz\n", "\n"]);
assert_eq!(lines("\n"), vec!["\n"]);
assert_eq!(lines(""), Vec::<&str>::new());
}
#[test]
fn line_iter_empty() {
let mut it = LineStep::new(b'\n', 0, 0);
assert_eq!(it.next(b"abc"), None);
}
#[test]
fn preceding_lines_doc() {
// These are the examples mentions in the documentation of `preceding`.
let bytes = b"abc\nxyz\n";
assert_eq!(4, preceding_by_pos(bytes, 7, b'\n', 0));
assert_eq!(4, preceding_by_pos(bytes, 8, b'\n', 0));
assert_eq!(0, preceding_by_pos(bytes, 7, b'\n', 1));
assert_eq!(0, preceding_by_pos(bytes, 8, b'\n', 1));
}
#[test]
fn preceding_lines_sherlock() {
let t = SHERLOCK;
let lines = line_ranges(t);
// The following tests check the count == 0 case, i.e., finding the
// beginning of the line containing the given position.
assert_eq!(0, prev(t, 0, 0));
assert_eq!(0, prev(t, 1, 0));
// The line terminator is addressed by `end-1` and terminates the line
// it is part of.
assert_eq!(0, prev(t, lines[0].end - 1, 0));
assert_eq!(lines[0].start, prev(t, lines[0].end, 0));
// The end position of line addresses the byte immediately following a
// line terminator, which puts it on the following line.
assert_eq!(lines[1].start, prev(t, lines[0].end + 1, 0));
// Now tests for count > 0.
assert_eq!(0, prev(t, 0, 1));
assert_eq!(0, prev(t, 0, 2));
assert_eq!(0, prev(t, 1, 1));
assert_eq!(0, prev(t, 1, 2));
assert_eq!(0, prev(t, lines[0].end - 1, 1));
assert_eq!(0, prev(t, lines[0].end - 1, 2));
assert_eq!(0, prev(t, lines[0].end, 1));
assert_eq!(0, prev(t, lines[0].end, 2));
assert_eq!(lines[3].start, prev(t, lines[4].end - 1, 1));
assert_eq!(lines[3].start, prev(t, lines[4].end, 1));
assert_eq!(lines[4].start, prev(t, lines[4].end + 1, 1));
// The last line has no line terminator.
assert_eq!(lines[5].start, prev(t, lines[5].end, 0));
assert_eq!(lines[5].start, prev(t, lines[5].end - 1, 0));
assert_eq!(lines[4].start, prev(t, lines[5].end, 1));
assert_eq!(lines[0].start, prev(t, lines[5].end, 5));
}
#[test]
fn preceding_lines_short() {
let t = "a\nb\nc\nd\ne\nf\n";
let lines = line_ranges(t);
assert_eq!(12, t.len());
assert_eq!(lines[5].start, prev(t, lines[5].end, 0));
assert_eq!(lines[4].start, prev(t, lines[5].end, 1));
assert_eq!(lines[3].start, prev(t, lines[5].end, 2));
assert_eq!(lines[2].start, prev(t, lines[5].end, 3));
assert_eq!(lines[1].start, prev(t, lines[5].end, 4));
assert_eq!(lines[0].start, prev(t, lines[5].end, 5));
assert_eq!(lines[0].start, prev(t, lines[5].end, 6));
assert_eq!(lines[5].start, prev(t, lines[5].end - 1, 0));
assert_eq!(lines[4].start, prev(t, lines[5].end - 1, 1));
assert_eq!(lines[3].start, prev(t, lines[5].end - 1, 2));
assert_eq!(lines[2].start, prev(t, lines[5].end - 1, 3));
assert_eq!(lines[1].start, prev(t, lines[5].end - 1, 4));
assert_eq!(lines[0].start, prev(t, lines[5].end - 1, 5));
assert_eq!(lines[0].start, prev(t, lines[5].end - 1, 6));
assert_eq!(lines[4].start, prev(t, lines[5].start, 0));
assert_eq!(lines[3].start, prev(t, lines[5].start, 1));
assert_eq!(lines[2].start, prev(t, lines[5].start, 2));
assert_eq!(lines[1].start, prev(t, lines[5].start, 3));
assert_eq!(lines[0].start, prev(t, lines[5].start, 4));
assert_eq!(lines[0].start, prev(t, lines[5].start, 5));
assert_eq!(lines[3].start, prev(t, lines[4].end - 1, 1));
assert_eq!(lines[2].start, prev(t, lines[4].start, 1));
assert_eq!(lines[2].start, prev(t, lines[3].end - 1, 1));
assert_eq!(lines[1].start, prev(t, lines[3].start, 1));
assert_eq!(lines[1].start, prev(t, lines[2].end - 1, 1));
assert_eq!(lines[0].start, prev(t, lines[2].start, 1));
assert_eq!(lines[0].start, prev(t, lines[1].end - 1, 1));
assert_eq!(lines[0].start, prev(t, lines[1].start, 1));
assert_eq!(lines[0].start, prev(t, lines[0].end - 1, 1));
assert_eq!(lines[0].start, prev(t, lines[0].start, 1));
}
#[test]
fn preceding_lines_empty1() {
let t = "\n\n\nd\ne\nf\n";
let lines = line_ranges(t);
assert_eq!(9, t.len());
assert_eq!(lines[0].start, prev(t, lines[0].end, 0));
assert_eq!(lines[0].start, prev(t, lines[0].end, 1));
assert_eq!(lines[1].start, prev(t, lines[1].end, 0));
assert_eq!(lines[0].start, prev(t, lines[1].end, 1));
assert_eq!(lines[5].start, prev(t, lines[5].end, 0));
assert_eq!(lines[4].start, prev(t, lines[5].end, 1));
assert_eq!(lines[3].start, prev(t, lines[5].end, 2));
assert_eq!(lines[2].start, prev(t, lines[5].end, 3));
assert_eq!(lines[1].start, prev(t, lines[5].end, 4));
assert_eq!(lines[0].start, prev(t, lines[5].end, 5));
assert_eq!(lines[0].start, prev(t, lines[5].end, 6));
}
#[test]
fn preceding_lines_empty2() {
let t = "a\n\n\nd\ne\nf\n";
let lines = line_ranges(t);
assert_eq!(10, t.len());
assert_eq!(lines[0].start, prev(t, lines[0].end, 0));
assert_eq!(lines[0].start, prev(t, lines[0].end, 1));
assert_eq!(lines[1].start, prev(t, lines[1].end, 0));
assert_eq!(lines[0].start, prev(t, lines[1].end, 1));
assert_eq!(lines[5].start, prev(t, lines[5].end, 0));
assert_eq!(lines[4].start, prev(t, lines[5].end, 1));
assert_eq!(lines[3].start, prev(t, lines[5].end, 2));
assert_eq!(lines[2].start, prev(t, lines[5].end, 3));
assert_eq!(lines[1].start, prev(t, lines[5].end, 4));
assert_eq!(lines[0].start, prev(t, lines[5].end, 5));
assert_eq!(lines[0].start, prev(t, lines[5].end, 6));
}
}

25
grep-searcher/src/macros.rs Normal file
View File

@@ -0,0 +1,25 @@
/// Like assert_eq, but nicer output for long strings.
#[cfg(test)]
#[macro_export]
macro_rules! assert_eq_printed {
($expected:expr, $got:expr, $($tt:tt)*) => {
let expected = &*$expected;
let got = &*$got;
let label = format!($($tt)*);
if expected != got {
panic!("
printed outputs differ! (label: {})
expected:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
{}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
got:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
{}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
", label, expected, got);
}
}
}

583
grep-searcher/src/searcher/core.rs Normal file
View File

@@ -0,0 +1,583 @@
use std::cmp;
use bstr::B;
use grep_matcher::{LineMatchKind, Matcher};
use lines::{self, LineStep};
use line_buffer::BinaryDetection;
use searcher::{Config, Range, Searcher};
use sink::{
Sink, SinkError,
SinkFinish, SinkContext, SinkContextKind, SinkMatch,
};
#[derive(Debug)]
pub struct Core<'s, M: 's, S> {
config: &'s Config,
matcher: M,
searcher: &'s Searcher,
sink: S,
binary: bool,
pos: usize,
absolute_byte_offset: u64,
binary_byte_offset: Option<usize>,
line_number: Option<u64>,
last_line_counted: usize,
last_line_visited: usize,
after_context_left: usize,
has_sunk: bool,
}
impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
pub fn new(
searcher: &'s Searcher,
matcher: M,
sink: S,
binary: bool,
) -> Core<'s, M, S> {
let line_number =
if searcher.config.line_number {
Some(1)
} else {
None
};
let core = Core {
config: &searcher.config,
matcher: matcher,
searcher: searcher,
sink: sink,
binary: binary,
pos: 0,
absolute_byte_offset: 0,
binary_byte_offset: None,
line_number: line_number,
last_line_counted: 0,
last_line_visited: 0,
after_context_left: 0,
has_sunk: false,
};
if !core.searcher.multi_line_with_matcher(&core.matcher) {
if core.is_line_by_line_fast() {
trace!("searcher core: will use fast line searcher");
} else {
trace!("searcher core: will use slow line searcher");
}
}
core
}
pub fn pos(&self) -> usize {
self.pos
}
pub fn set_pos(&mut self, pos: usize) {
self.pos = pos;
}
pub fn binary_byte_offset(&self) -> Option<u64> {
self.binary_byte_offset.map(|offset| offset as u64)
}
pub fn matcher(&self) -> &M {
&self.matcher
}
pub fn matched(
&mut self,
buf: &[u8],
range: &Range,
) -> Result<bool, S::Error> {
self.sink_matched(buf, range)
}
pub fn begin(&mut self) -> Result<bool, S::Error> {
self.sink.begin(&self.searcher)
}
pub fn finish(
&mut self,
byte_count: u64,
binary_byte_offset: Option<u64>,
) -> Result<(), S::Error> {
self.sink.finish(
&self.searcher,
&SinkFinish {
byte_count,
binary_byte_offset,
})
}
pub fn match_by_line(&mut self, buf: &[u8]) -> Result<bool, S::Error> {
if self.is_line_by_line_fast() {
self.match_by_line_fast(buf)
} else {
self.match_by_line_slow(buf)
}
}
pub fn roll(&mut self, buf: &[u8]) -> usize {
let consumed =
if self.config.max_context() == 0 {
buf.len()
} else {
// It might seem like all we need to care about here is just
// the "before context," but in order to sink the context
// separator (when before_context==0 and after_context>0), we
// need to know something about the position of the previous
// line visited, even if we're at the beginning of the buffer.
let context_start = lines::preceding(
buf,
self.config.line_term.as_byte(),
self.config.max_context(),
);
let consumed = cmp::max(context_start, self.last_line_visited);
consumed
};
self.count_lines(buf, consumed);
self.absolute_byte_offset += consumed as u64;
self.last_line_counted = 0;
self.last_line_visited = 0;
self.set_pos(buf.len() - consumed);
consumed
}
pub fn detect_binary(&mut self, buf: &[u8], range: &Range) -> bool {
if self.binary_byte_offset.is_some() {
return true;
}
let binary_byte = match self.config.binary.0 {
BinaryDetection::Quit(b) => b,
_ => return false,
};
if let Some(i) = B(&buf[*range]).find_byte(binary_byte) {
self.binary_byte_offset = Some(range.start() + i);
true
} else {
false
}
}
pub fn before_context_by_line(
&mut self,
buf: &[u8],
upto: usize,
) -> Result<bool, S::Error> {
if self.config.before_context == 0 {
return Ok(true);
}
let range = Range::new(self.last_line_visited, upto);
if range.is_empty() {
return Ok(true);
}
let before_context_start = range.start() + lines::preceding(
&buf[range],
self.config.line_term.as_byte(),
self.config.before_context - 1,
);
let range = Range::new(before_context_start, range.end());
let mut stepper = LineStep::new(
self.config.line_term.as_byte(),
range.start(),
range.end(),
);
while let Some(line) = stepper.next_match(buf) {
if !self.sink_break_context(line.start())? {
return Ok(false);
}
if !self.sink_before_context(buf, &line)? {
return Ok(false);
}
}
Ok(true)
}
pub fn after_context_by_line(
&mut self,
buf: &[u8],
upto: usize,
) -> Result<bool, S::Error> {
if self.after_context_left == 0 {
return Ok(true);
}
let range = Range::new(self.last_line_visited, upto);
let mut stepper = LineStep::new(
self.config.line_term.as_byte(),
range.start(),
range.end(),
);
while let Some(line) = stepper.next_match(buf) {
if !self.sink_after_context(buf, &line)? {
return Ok(false);
}
if self.after_context_left == 0 {
break;
}
}
Ok(true)
}
pub fn other_context_by_line(
&mut self,
buf: &[u8],
upto: usize,
) -> Result<bool, S::Error> {
let range = Range::new(self.last_line_visited, upto);
let mut stepper = LineStep::new(
self.config.line_term.as_byte(),
range.start(),
range.end(),
);
while let Some(line) = stepper.next_match(buf) {
if !self.sink_other_context(buf, &line)? {
return Ok(false);
}
}
Ok(true)
}
fn match_by_line_slow(&mut self, buf: &[u8]) -> Result<bool, S::Error> {
debug_assert!(!self.searcher.multi_line_with_matcher(&self.matcher));
let range = Range::new(self.pos(), buf.len());
let mut stepper = LineStep::new(
self.config.line_term.as_byte(),
range.start(),
range.end(),
);
while let Some(line) = stepper.next_match(buf) {
let matched = {
// Stripping the line terminator is necessary to prevent some
// classes of regexes from matching the empty position *after*
// the end of the line. For example, `(?m)^$` will match at
// position (2, 2) in the string `a\n`.
let slice = lines::without_terminator(
&buf[line],
self.config.line_term,
);
match self.matcher.shortest_match(slice) {
Err(err) => return Err(S::Error::error_message(err)),
Ok(result) => result.is_some(),
}
};
self.set_pos(line.end());
if matched != self.config.invert_match {
if !self.before_context_by_line(buf, line.start())? {
return Ok(false);
}
if !self.sink_matched(buf, &line)? {
return Ok(false);
}
} else if self.after_context_left >= 1 {
if !self.sink_after_context(buf, &line)? {
return Ok(false);
}
} else if self.config.passthru {
if !self.sink_other_context(buf, &line)? {
return Ok(false);
}
}
}
Ok(true)
}
fn match_by_line_fast(&mut self, buf: &[u8]) -> Result<bool, S::Error> {
debug_assert!(!self.config.passthru);
while !buf[self.pos()..].is_empty() {
if self.config.invert_match {
if !self.match_by_line_fast_invert(buf)? {
return Ok(false);
}
} else if let Some(line) = self.find_by_line_fast(buf)? {
if self.config.max_context() > 0 {
if !self.after_context_by_line(buf, line.start())? {
return Ok(false);
}
if !self.before_context_by_line(buf, line.start())? {
return Ok(false);
}
}
self.set_pos(line.end());
if !self.sink_matched(buf, &line)? {
return Ok(false);
}
} else {
break;
}
}
if !self.after_context_by_line(buf, buf.len())? {
return Ok(false);
}
self.set_pos(buf.len());
Ok(true)
}
#[inline(always)]
fn match_by_line_fast_invert(
&mut self,
buf: &[u8],
) -> Result<bool, S::Error> {
assert!(self.config.invert_match);
let invert_match = match self.find_by_line_fast(buf)? {
None => {
let range = Range::new(self.pos(), buf.len());
self.set_pos(range.end());
range
}
Some(line) => {
let range = Range::new(self.pos(), line.start());
self.set_pos(line.end());
range
}
};
if invert_match.is_empty() {
return Ok(true);
}
if !self.after_context_by_line(buf, invert_match.start())? {
return Ok(false);
}
if !self.before_context_by_line(buf, invert_match.start())? {
return Ok(false);
}
let mut stepper = LineStep::new(
self.config.line_term.as_byte(),
invert_match.start(),
invert_match.end(),
);
while let Some(line) = stepper.next_match(buf) {
if !self.sink_matched(buf, &line)? {
return Ok(false);
}
}
Ok(true)
}
#[inline(always)]
fn find_by_line_fast(
&self,
buf: &[u8],
) -> Result<Option<Range>, S::Error> {
debug_assert!(!self.searcher.multi_line_with_matcher(&self.matcher));
debug_assert!(self.is_line_by_line_fast());
let mut pos = self.pos();
while !buf[pos..].is_empty() {
match self.matcher.find_candidate_line(&buf[pos..]) {
Err(err) => return Err(S::Error::error_message(err)),
Ok(None) => return Ok(None),
Ok(Some(LineMatchKind::Confirmed(i))) => {
let line = lines::locate(
buf,
self.config.line_term.as_byte(),
Range::zero(i).offset(pos),
);
// If we matched beyond the end of the buffer, then we
// don't report this as a match.
if line.start() == buf.len() {
pos = buf.len();
continue;
}
return Ok(Some(line));
}
Ok(Some(LineMatchKind::Candidate(i))) => {
let line = lines::locate(
buf,
self.config.line_term.as_byte(),
Range::zero(i).offset(pos),
);
// We need to strip the line terminator here to match the
// semantics of line-by-line searching. Namely, regexes
// like `(?m)^$` can match at the final position beyond a
// line terminator, which is non-sensical in line oriented
// matching.
let slice = lines::without_terminator(
&buf[line],
self.config.line_term,
);
match self.matcher.is_match(slice) {
Err(err) => return Err(S::Error::error_message(err)),
Ok(true) => return Ok(Some(line)),
Ok(false) => {
pos = line.end();
continue;
}
}
}
}
}
Ok(None)
}
#[inline(always)]
fn sink_matched(
&mut self,
buf: &[u8],
range: &Range,
) -> Result<bool, S::Error> {
if self.binary && self.detect_binary(buf, range) {
return Ok(false);
}
if !self.sink_break_context(range.start())? {
return Ok(false);
}
self.count_lines(buf, range.start());
let offset = self.absolute_byte_offset + range.start() as u64;
let linebuf = &buf[*range];
let keepgoing = self.sink.matched(
&self.searcher,
&SinkMatch {
line_term: self.config.line_term,
bytes: linebuf,
absolute_byte_offset: offset,
line_number: self.line_number,
},
)?;
if !keepgoing {
return Ok(false);
}
self.last_line_visited = range.end();
self.after_context_left = self.config.after_context;
self.has_sunk = true;
Ok(true)
}
fn sink_before_context(
&mut self,
buf: &[u8],
range: &Range,
) -> Result<bool, S::Error> {
if self.binary && self.detect_binary(buf, range) {
return Ok(false);
}
self.count_lines(buf, range.start());
let offset = self.absolute_byte_offset + range.start() as u64;
let keepgoing = self.sink.context(
&self.searcher,
&SinkContext {
line_term: self.config.line_term,
bytes: &buf[*range],
kind: SinkContextKind::Before,
absolute_byte_offset: offset,
line_number: self.line_number,
},
)?;
if !keepgoing {
return Ok(false);
}
self.last_line_visited = range.end();
self.has_sunk = true;
Ok(true)
}
fn sink_after_context(
&mut self,
buf: &[u8],
range: &Range,
) -> Result<bool, S::Error> {
assert!(self.after_context_left >= 1);
if self.binary && self.detect_binary(buf, range) {
return Ok(false);
}
self.count_lines(buf, range.start());
let offset = self.absolute_byte_offset + range.start() as u64;
let keepgoing = self.sink.context(
&self.searcher,
&SinkContext {
line_term: self.config.line_term,
bytes: &buf[*range],
kind: SinkContextKind::After,
absolute_byte_offset: offset,
line_number: self.line_number,
},
)?;
if !keepgoing {
return Ok(false);
}
self.last_line_visited = range.end();
self.after_context_left -= 1;
self.has_sunk = true;
Ok(true)
}
fn sink_other_context(
&mut self,
buf: &[u8],
range: &Range,
) -> Result<bool, S::Error> {
if self.binary && self.detect_binary(buf, range) {
return Ok(false);
}
self.count_lines(buf, range.start());
let offset = self.absolute_byte_offset + range.start() as u64;
let keepgoing = self.sink.context(
&self.searcher,
&SinkContext {
line_term: self.config.line_term,
bytes: &buf[*range],
kind: SinkContextKind::Other,
absolute_byte_offset: offset,
line_number: self.line_number,
},
)?;
if !keepgoing {
return Ok(false);
}
self.last_line_visited = range.end();
self.has_sunk = true;
Ok(true)
}
fn sink_break_context(
&mut self,
start_of_line: usize,
) -> Result<bool, S::Error> {
let is_gap = self.last_line_visited < start_of_line;
let any_context =
self.config.before_context > 0
|| self.config.after_context > 0;
if !any_context || !self.has_sunk || !is_gap {
Ok(true)
} else {
self.sink.context_break(&self.searcher)
}
}
fn count_lines(&mut self, buf: &[u8], upto: usize) {
if let Some(ref mut line_number) = self.line_number {
if self.last_line_counted >= upto {
return;
}
let slice = &buf[self.last_line_counted..upto];
let count = lines::count(slice, self.config.line_term.as_byte());
*line_number += count;
self.last_line_counted = upto;
}
}
fn is_line_by_line_fast(&self) -> bool {
debug_assert!(!self.searcher.multi_line_with_matcher(&self.matcher));
if self.config.passthru {
return false;
}
if let Some(line_term) = self.matcher.line_terminator() {
if line_term == self.config.line_term {
return true;
}
}
if let Some(non_matching) = self.matcher.non_matching_bytes() {
// If the line terminator is CRLF, we don't actually need to care
// whether the regex can match `\r` or not. Namely, a `\r` is
// neither necessary nor sufficient to terminate a line. A `\n` is
// always required.
if non_matching.contains(self.config.line_term.as_byte()) {
return true;
}
}
false
}
}

1506
grep-searcher/src/searcher/glue.rs Normal file
View File

File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More