twin/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-08-15 04:05:46 -07:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: twin:grep-cli-0.1.8
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:globset-0.4.11
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

49 Commits
grep-cli-0 ... globset-0.

Author SHA1 Message Date
Andrew Gallant
1d35859861 globset-0.4.11 2023-07-12 12:58:43 -04:00
mataha
601e122e9f ignore/types: add Windows Command Prompt files 
This PR adds `*.bat` and `*.cmd` file types.

In doing so, it makes a distinction between batch files (old standard
from the MS-DOS era) and command scripts (new flavor - can operate on
batch files, although `*.cmd` is preferred for various reasons, the
main one being batch files will set `ERRORLEVEL` following inconsistent
MS-DOS style rules[1]).

PR #2556

[1]: https://groups.google.com/g/microsoft.public.win2000.cmdprompt.admin/c/XHeUq8oe2wk/m/LIEViGNmkK0J#i106
 2023-07-10 15:58:17 -04:00
Andrew Gallant
efb2e8ce1e ci/release: use latest OS versions 2023-07-09 10:14:03 -04:00
xEgoist
8d464e5c78 ci/release: add sha256 sums to release artifacts 
Fixes #1924, Closes #2168
 2023-07-09 10:14:03 -04:00
Andrew Gallant
d67809d6c4 github: remove dependabot configuration 
This does not seem to have worked at all. For example, there were
Actions being used that were clearly deprecated/archived[1]. But
Dependabot didn't make a peep. So just get rid of it to avoid the false
sense that someone is checking our dependencies for us.

[1]: https://github.com/BurntSushi/ripgrep/pull/2360
 2023-07-09 10:14:03 -04:00
nguyenvukhang
6abb962f0d cli: fix non-path sorting behavior 
Previously, sorting worked by sorting the parents and then sorting the
children within each parent. This was done during traversal, but it only
works when sorting parents preserves the overall order. This generally
only works for '--sort path' in ascending order.

This commit fixes the rest of the sorting behavior by collecting all of
the paths to search and then sorting them before searching. We only
collect all of the paths when sorting was requested.

Fixes #2243, Closes #2361
 2023-07-09 10:14:03 -04:00
Edoardo Pirovano
6d95c130d5 cli: add --stop-on-nonmatch flag 
This causes ripgrep to stop searching an individual file after it has
found a non-matching line. But this only occurs after it has found a
matching line.

Fixes #1790, Closes #1930
 2023-07-08 18:52:42 -04:00
Garrett Thornburg
4782ebd5e0 core: lock stdout before printing an error message to stderr 
Adds a new eprintln_locked macro which locks STDOUT before logging
to STDERR. This patch also replaces instances of eprintln with
eprintln_locked to avoid interleaving lines.

Fixes #1941, Closes #1968
 2023-07-08 18:52:42 -04:00
piegames
4993d29a16 globset: add 'escape' routine 
Fixes #2060, Closes #2061
 2023-07-08 18:52:42 -04:00
Seth Stadick
23adbd6795 cli: force binary existance check 
Previously, we were only doing a binary existence check on Windows. And
in fact, the main point there wasn't binary existence, but ensuring we
didn't accidentally resolve a binary name relative to the CWD, which
could result in executing a program one didn't mean to run.

However, it is useful to be able to check whether a binary exists on any
platform when associating a glob with a binary. If the binary doesn't
exist, then the association can fail eagerly and let some other glob
apply.

Closes #1946
 2023-07-08 18:52:42 -04:00
Kevin Svetlitski
9df8ab42b1 cargo: reduce the size of the .crate file published to crates.io 
None of this stuff is needed for the main ripgrep crate.

Closes #1940
 2023-07-08 18:52:42 -04:00
Michal Terepeta
cb7501ff11 doc: clarify the comment on Worker.work_done 
We call `work_done` only once the work has been actually performed
(otherwise `num_pending` could go to 0 before the actual work is done).

Closes #2039
 2023-07-08 18:52:42 -04:00
Kyle Todeschini
3b66f37a31 doc: improve -r/--replace flag syntax docs 
Fixes #2108, Closes #2123
 2023-07-08 18:52:42 -04:00
Andrew Gallant
3eccb7c363 readme: add 'yum-utils' to RHEL/Centos instructions 
Closes #2103
 2023-07-08 18:52:42 -04:00
kotborealis
f30a30867e ignore/types: name aliases for file types 
We also make py/python, md/markdown and ts/typescript aliases of one
another.

Note that this only introduces aliases at the point where default types
are defined. This just makes them a bit easier to read/write, and also
makes it easier to expose more names that describe the same thing.

Fixes #1857, Closes #1895
 2023-07-08 18:52:42 -04:00
Klas Mellbourn
7313dca472 ignore/types: add 'typescript' alias for 'ts' 
Closes #2009
 2023-07-08 18:52:42 -04:00
Tama McGlinn
99bf2b01dc ignore/types: add Ada filetypes, including gprbuild and alire 
*.adb and *.ads are the usual extensions for Ada source code,
and *.gpr indicates a GPRbuild project file used for Ada, and
these days often being combined with alire for package dependency
resolution. Alire stores a bunch of files named alire.toml in
different directories in your (gitignored) cache/dependencies/...

Closes #2013
 2023-07-08 18:52:42 -04:00
Juan Francisco Cantero Hurtado
ee1360cc07 ignore/types: add raku extensions to ignore types 
Closes #2117
 2023-07-08 18:52:42 -04:00
Andrew Gallant
db6bb21a62 windows: attempt to enable long path support for MSVC targets 
See the README and comments in the build.rs. Basically, this embeds an
XML file that I guess is a way of setting configuration knobs on
Windows. One of those knobs is enabling long path support. You still
need to enable it in your registry (lol), but this will handle the other
half of it.

Fixes #364, Closes #2049
 2023-07-08 18:52:42 -04:00
Andrew Gallant
da7c81fb96 ignore/types: add MDX format to Markdown types 
Ref https://mdxjs.com/

Closes #2142
 2023-07-08 18:52:42 -04:00
chrispy
a4e3d56de1 ignore/types: add DITA (Darwin Information Typing Architecture) 
Closes #2148
 2023-07-08 18:52:42 -04:00
Ludi Rehak
7c83b90f95 doc: fix typo 
Closes #2153
 2023-07-08 18:52:42 -04:00
cuishuang
97b5b7769c doc: fix some typos 
Closes #2195
 2023-07-08 18:52:42 -04:00
dana
2708f9e81d complete: add extra-verbose support to _rg_types 
When the extra-verbose style is set for the types tag, completed types
are displayed along with the patterns they correspond to. This can be
enabled by e.g. adding the following to .zshrc:

  zstyle ':completion:*:rg:*:types' extra-verbose true

This change also makes _rg_types use the actual rg specified on the
command line to look up types, and it fixes a mangled complete-all
style check

Fixes #2195
 2023-07-08 18:52:42 -04:00
Richard Sternagel
f3241fd657 cli: '--no-ignore-dot' should also '.rgignore' 
Fixes #2198, Closes #2202
 2023-07-08 18:52:42 -04:00
Andrew Gallant
cfe357188d ignore/types: fix formatting 2023-07-08 18:52:42 -04:00
edam
792451e331 ignore/types: added V type 
V (http://vlang.io) uses '.v' files.

Closes #2302
 2023-07-08 18:52:42 -04:00
Andrew Gallant
7dafd58a32 readme: use 'sudo' more consistently 
I definitely wonder whether I should just drop 'sudo' from the install
instructions and just rely on the user to "know" to do it. But some
commands legitimately do not require 'sudo', so there are actual
differences. Overall, this feels clearer to me but reasonable people can
disagree.
 2023-07-08 18:52:42 -04:00
Andrew Savchenko
b92550b67b readme: add install command for ALT Linux 
Closes #2330
 2023-07-08 18:52:42 -04:00
Kevin Ushey
383d3b336b doc: add '--hidden' to example configuration 
This increases visibility of the fact that hidden files are skipped by
default.

Closes #2356
 2023-07-08 18:52:42 -04:00
James McKinney
fc7e634395 ci/release: Use GITHUB_REF_NAME instead of GITHUB_REF 
This is a nice quality of life improvement.

Closes #2358
 2023-07-08 18:52:42 -04:00
James McKinney
c9584b035b ci/release: use GitHub CLI 
The old actions I was using are apparently archived because they make
use of deprecated features (like `set-output`). Sigh.

Closes #2360
 2023-07-08 18:52:42 -04:00
Alex Rawson
f34fd5c4b6 globset: introduce option to keep empty alternates 
Add a method GlobBuilder::empty_alternates and supporting mechanisms.

Ref #1368
Closes #2369
 2023-07-08 18:52:42 -04:00
Jérome Eertmans
d51c6c005a globset: permit deserializing Glob from String 
Closes #2386, Closes #2388
 2023-07-08 18:52:42 -04:00
Jakub Wilk
ea05881319 readme: fix awkward grammar 
Closes #2402
 2023-07-08 18:52:42 -04:00
sitiom
1d4e3df19c readme: add winget installation section 
Closes #2409
 2023-07-08 18:52:42 -04:00
Mark Sisson
0f6181d309 ignore/types: add USD to the default file types 
Closes #2432
 2023-07-08 18:52:42 -04:00
Sam James
e902e2fef4 ignore/types: add Gentoo eclass type 
Eclasses are "ebuild libraries" and generally if you're filtering
for/filtering out an ebuild/eclass, you don't want the other either.

Followup to 4dfea016b9

Closes #2437
 2023-07-08 18:52:42 -04:00
angrycandy
07cbfee225 ignore/types: improve Elixir globs 
Closes #2450
 2023-07-08 18:52:42 -04:00
Andrew Gallant
d675844510 core: don't let context flags override eachother 
This matches the behavior of GNU grep which does not ignore
before-context and after-context completely if the context flag is also
provided.

Note that this change wasn't done just to match GNU grep. In this case,
GNU grep has the more sensible behavior.

Fixes #2288, Closes #2451
 2023-07-08 18:52:42 -04:00
Andrew Gallant
54e609d657 doc: add another example for the config file 
Closes #2453
 2023-07-08 18:52:42 -04:00
Misaki
43bbcca06f doc: note '-n' and '-N' override each other 
Closes #2460
 2023-07-08 18:52:42 -04:00
Eric Arellano
ad9bfdd981 ignore/gitignore: expose gitconfig_excludes_path 
I have reservations about this, but it looks useful and doesn't seem
terribly onerous to support. The `ignore` crate will really always need
to have some kind of logic supporting this in some form I think.

Closes #2482
 2023-07-08 18:52:42 -04:00
Gal Ofri
36194c2742 test: test that regex inline flags work as intended 
This was originally fixed by using non-capturing groups when joining
patterns in crates/core/args.rs, but before that landed, it ended up
getting fixed via a refactor in the course of migrating to regex 1.9.
Namely, it's now fixed by pushing pattern joining down into the regex
layer, so that patterns can be joined in the most effective way
possible.

Still, #2488 contains a useful test, so we bring that in here. The
test actually failed for `rg -e ')('`, since it expected the command to
fail with a syntax error. But my refactor actually causes this command
to succeed. And indeed, #2488 worked around this by special casing a
single pattern. That work-around fixes it for the single pattern case,
but doesn't fix it for the -w or -X or multi-pattern case. So for now,
we're content to leave well enough alone. The only real way to fix this
for real is to parse each regexp individual and verify that each is
valid on its own. It's not clear that doing so is worth it.

Fixes #2480, Closes #2488
 2023-07-08 18:52:42 -04:00
Jakub Jirutka
0c1cbd99f3 ignore: tweak regex crate features 
This removes most of the Unicode features as they aren't currently
used. We can always add them back later if necessary.

We can avoid the unicode-perl feature by changing `\s` to `[[:space:]]`,
which uses the ASCII-only definition of `\s`. Since we don't expect
non-ASCII whitespace in git config files, this seems okay.

Closes #2502
 2023-07-08 18:52:42 -04:00
Jon Parise
96cfc0ed13 ignore/types: add 'graphql' type 
GraphQL file extensions: .graphql and .graphqls (schema)

We could also add `.gql`, but perhaps it's less correct to do so. We'll
start conservatively here, and we can always add `.gql` later.

Closes #2439, Closes #2508
 2023-07-08 18:52:42 -04:00
mataha
da8ecddce9 cli: make resolve_binary take COM executables into account 
When `resolve_binary()` attempts to resolve a path to a program on
Windows while searching for a program in `PATH` without an extension,
`ripgrep` will assume the extension of the file to be `.exe` as it's
the *de facto* standard, which will work most (99.99%) of the time...

...unless the binary is a COM executable (we're on Windows, duh).

Closes #2523
 2023-07-08 18:52:42 -04:00
Yifei Teng
545a7dc759 ignore/types: add cml to the default types list 
It's used in Fuchsia to mean "component manifest language."[1]

[1]: https://fuchsia.dev/reference/cml?hl=en

Closes #2529
 2023-07-08 18:52:42 -04:00
Jonathan Schwender
16f783832e doc: update rust-version in Cargo.toml 
The MSRV got bumped a little bit ago, so this is just catchup.

Closes #2539
 2023-07-08 18:52:42 -04:00
34 changed files with 1032 additions and 427 deletions
Expand all files Collapse all files

6
.github/dependabot.yml vendored
View File

@@ -1,6 +0,0 @@
version: 2
updates:
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "weekly"

52
.github/workflows/release.yml vendored
View File

@@ -24,31 +24,24 @@ on:
jobs:
create-release:
name: create-release
runs-on: ubuntu-22.04
runs-on: ubuntu-latest
# env:
# Set to force version number, e.g., when no tag exists.
# RG_VERSION: TEST-0.0.0
outputs:
upload_url: ${{ steps.release.outputs.upload_url }}
rg_version: ${{ env.RG_VERSION }}
steps:
- uses: actions/checkout@v3
- name: Get the release version from the tag
shell: bash
if: env.RG_VERSION == ''
run: |
# Apparently, this is the right way to get a tag name. Really?
#
# See: https://github.community/t5/GitHub-Actions/How-to-get-just-the-tag-name/m-p/32167/highlight/true#M1027
echo "RG_VERSION=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
echo "RG_VERSION=$GITHUB_REF_NAME" >> $GITHUB_ENV
echo "version is: ${{ env.RG_VERSION }}"
- name: Create GitHub release
id: release
uses: actions/create-release@v1
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
tag_name: ${{ env.RG_VERSION }}
release_name: ${{ env.RG_VERSION }}
GH_TOKEN: ${{ github.token }}
run: gh release create ${{ env.RG_VERSION }}
build-release:
name: build-release
@@ -71,27 +64,27 @@ jobs:
build: [linux, linux-arm, macos, win-msvc, win-gnu, win32-msvc]
include:
- build: linux
os: ubuntu-22.04
os: ubuntu-latest
rust: nightly
target: x86_64-unknown-linux-musl
- build: linux-arm
os: ubuntu-22.04
os: ubuntu-latest
rust: nightly
target: arm-unknown-linux-gnueabihf
- build: macos
os: macos-12
os: macos-latest
rust: nightly
target: x86_64-apple-darwin
- build: win-msvc
os: windows-2022
os: windows-latest
rust: nightly
target: x86_64-pc-windows-msvc
- build: win-gnu
os: windows-2022
os: windows-latest
rust: nightly-x86_64-gnu
target: x86_64-pc-windows-gnu
- build: win32-msvc
os: windows-2022
os: windows-latest
rust: nightly
target: i686-pc-windows-msvc
@@ -100,12 +93,12 @@ jobs:
uses: actions/checkout@v3
- name: Install packages (Ubuntu)
if: matrix.os == 'ubuntu-22.04'
if: matrix.os == 'ubuntu-latest'
run: |
ci/ubuntu-install-packages
- name: Install packages (macOS)
if: matrix.os == 'macos-12'
if: matrix.os == 'macos-latest'
run: |
ci/macos-install-packages
@@ -132,8 +125,8 @@ jobs:
- name: Build release binary
run: ${{ env.CARGO }} build --verbose --release --features pcre2 ${{ env.TARGET_FLAGS }}
- name: Strip release binary (linux and macos)
if: matrix.build == 'linux' || matrix.build == 'macos'
- name: Strip release binary (linux, macos and macos-arm)
if: matrix.build == 'linux' || matrix.os == 'macos'
run: strip "target/${{ matrix.target }}/release/rg"
- name: Strip release binary (arm)
@@ -157,24 +150,23 @@ jobs:
cp "$outdir"/{rg.bash,rg.fish,_rg.ps1} "$staging/complete/"
cp complete/_rg "$staging/complete/"
if [ "${{ matrix.os }}" = "windows-2022" ]; then
if [ "${{ matrix.os }}" = "windows-latest" ]; then
cp "target/${{ matrix.target }}/release/rg.exe" "$staging/"
7z a "$staging.zip" "$staging"
certutil -hashfile "$staging.zip" SHA256 > "$staging.zip.sha256"
echo "ASSET=$staging.zip" >> $GITHUB_ENV
echo "ASSET_SUM=$staging.zip.sha256" >> $GITHUB_ENV
else
# The man page is only generated on Unix systems. ¯\_(ツ)_/¯
cp "$outdir"/rg.1 "$staging/doc/"
cp "target/${{ matrix.target }}/release/rg" "$staging/"
tar czf "$staging.tar.gz" "$staging"
shasum -a 256 "$staging.tar.gz" > "$staging.tar.gz.sha256"
echo "ASSET=$staging.tar.gz" >> $GITHUB_ENV
echo "ASSET_SUM=$staging.tar.gz.sha256" >> $GITHUB_ENV
fi
- name: Upload release archive
uses: actions/upload-release-asset@v1.0.2
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
upload_url: ${{ needs.create-release.outputs.upload_url }}
asset_path: ${{ env.ASSET }}
asset_name: ${{ env.ASSET }}
asset_content_type: application/octet-stream
GH_TOKEN: ${{ github.token }}
run: gh release upload ${{ needs.create-release.outputs.rg_version }} ${{ env.ASSET }} ${{ env.ASSET_SUM }}

28
CHANGELOG.md
View File

@@ -2,14 +2,42 @@ TBD
===
Unreleased changes. Release notes have not yet been written.
**BREAKING CHANGES**
* `rg -C1 -A2` used to be equivalent to `rg -A2`, but now it is equivalent to
`rg -B1 -A2`. That is, `-A` and `-B` no longer completely override `-C`.
Instead, they only partially override `-C`.
Feature enhancements:
* Added or improved file type filtering for Ada, DITA, Elixir, Fuchsia, Gentoo, GraphQL, Markdown, Raku, TypeScript, USD, V
* [FEATURE #1790](https://github.com/BurntSushi/ripgrep/issues/1790):
Add new `--stop-on-nonmatch` flag.
* [FEATURE #2195](https://github.com/BurntSushi/ripgrep/issues/2195):
When `extra-verbose` mode is enabled in zsh, show extra file type info.
* [FEATURE #2409](https://github.com/BurntSushi/ripgrep/pull/2409):
Added installation instructions for `winget`.
Bug fixes:
* [BUG #1891](https://github.com/BurntSushi/ripgrep/issues/1891):
Fix bug when using `-w` with a regex that can match the empty string.
* [BUG #1911](https://github.com/BurntSushi/ripgrep/issues/1911):
Disable mmap searching in all non-64-bit environments.
* [BUG #2108](https://github.com/BurntSushi/ripgrep/issues/2108):
Improve docs for `-r/--replace` syntax.
* [BUG #2198](https://github.com/BurntSushi/ripgrep/issues/2198):
Fix bug where `--no-ignore-dot` would not ignore `.rgignore`.
* [BUG #2288](https://github.com/BurntSushi/ripgrep/issues/2288):
`-A` and `-B` now only each partially override `-C`.
* [BUG #2236](https://github.com/BurntSushi/ripgrep/issues/2236):
Fix gitignore parsing bug where a trailing `\/` resulted in an error.
* [BUG #2243](https://github.com/BurntSushi/ripgrep/issues/2243):
Fix `--sort` flag for values other than `path`.
* [BUG #2480](https://github.com/BurntSushi/ripgrep/issues/2480):
Fix bug when using inline regex flags with `-e/--regexp`.
* [BUG #2523](https://github.com/BurntSushi/ripgrep/issues/2523):
Make executable searching take `.com` into account on Windows.
13.0.0 (2021-06-12)

2
Cargo.lock generated
View File

@@ -119,7 +119,7 @@ checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
[[package]]
name = "globset"
version = "0.4.10"
version = "0.4.11"
dependencies = [
"aho-corasick",
"bstr",

11
Cargo.toml
View File

@@ -13,11 +13,18 @@ repository = "https://github.com/BurntSushi/ripgrep"
keywords = ["regex", "grep", "egrep", "search", "pattern"]
categories = ["command-line-utilities", "text-processing"]
license = "Unlicense OR MIT"
exclude = ["HomebrewFormula"]
exclude = [
"HomebrewFormula",
"/.github/",
"/ci/",
"/pkg/",
"/benchsuite/",
"/scripts/",
]
build = "build.rs"
autotests = false
edition = "2018"
rust-version = "1.65"
rust-version = "1.70"
[[bin]]
bench = false

7
GUIDE.md
View File

@@ -567,12 +567,15 @@ $ cat $HOME/.ripgreprc
--type-add
web:*.{html,css,js}*
# Search hidden files / directories (e.g. dotfiles) by default
--hidden
# Using glob patterns to include/exclude files or folders
--glob=!git/*
--glob=!.git/*
# or
--glob
!git/*
!.git/*
# Set the colors.
--colors=line:none

39
README.md
View File

@@ -228,17 +228,25 @@ If you're a **Windows Scoop** user, then you can install ripgrep from the
$ scoop install ripgrep
```
If you're a **Windows Winget** user, then you can install ripgrep from the
[winget-pkgs](https://github.com/microsoft/winget-pkgs/tree/master/manifests/b/BurntSushi/ripgrep)
repository:
```
$ winget install BurntSushi.ripgrep.MSVC
```
If you're an **Arch Linux** user, then you can install ripgrep from the official repos:
```
$ pacman -S ripgrep
$ sudo 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):
```
$ emerge sys-apps/ripgrep
$ sudo emerge sys-apps/ripgrep
```
If you're a **Fedora** user, you can install ripgrep from official
@@ -259,6 +267,7 @@ If you're a **RHEL/CentOS 7/8** user, you can install ripgrep from
[copr](https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/):
```
$ sudo yum install -y yum-utils
$ 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
```
@@ -268,14 +277,13 @@ If you're a **Nix** user, you can install ripgrep from
```
$ nix-env --install ripgrep
$ # (Or using the attribute name, which is also ripgrep.)
```
If you're a **Guix** user, you can install ripgrep from the official
package collection:
```
$ guix install ripgrep
$ sudo guix install ripgrep
```
If you're a **Debian** user (or a user of a Debian derivative like **Ubuntu**),
@@ -308,11 +316,18 @@ 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 an **ALT** user, you can install ripgrep from the
[official repo](https://packages.altlinux.org/en/search?name=ripgrep):
```
$ sudo apt-get install ripgrep
```
If you're a **FreeBSD** user, then you can install ripgrep from the
[official ports](https://www.freshports.org/textproc/ripgrep/):
```
# pkg install ripgrep
$ sudo pkg install ripgrep
```
If you're an **OpenBSD** user, then you can install ripgrep from the
@@ -326,21 +341,21 @@ If you're a **NetBSD** user, then you can install ripgrep from
[pkgsrc](https://pkgsrc.se/textproc/ripgrep):
```
# pkgin install ripgrep
$ sudo pkgin install ripgrep
```
If you're a **Haiku x86_64** user, then you can install ripgrep from the
[official ports](https://github.com/haikuports/haikuports/tree/master/sys-apps/ripgrep):
```
$ pkgman install ripgrep
$ sudo pkgman install ripgrep
```
If you're a **Haiku x86_gcc2** user, then you can install ripgrep from the
same port as Haiku x86_64 using the x86 secondary architecture build:
```
$ pkgman install ripgrep_x86
$ sudo pkgman install ripgrep_x86
```
If you're a **Rust programmer**, ripgrep can be installed with `cargo`.
@@ -360,7 +375,7 @@ $ cargo install ripgrep
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 1.65.0 (stable) or newer. In general, ripgrep tracks
ripgrep compiles with Rust 1.70.0 (stable) or newer. In general, ripgrep tracks
the latest stable release of the Rust compiler.
To build ripgrep:
@@ -443,9 +458,9 @@ grep](https://dandavison.github.io/delta/grep.html) for more details.
### Vulnerability reporting
For reporting a security vulnerability, please
[contact Andrew Gallant](https://blog.burntsushi.net/about/),
which has my email address and PGP public key if you wish to send an encrypted
message.
[contact Andrew Gallant](https://blog.burntsushi.net/about/).
The contact page has my email address and PGP public key if you wish to send an
encrypted message.
### Translations

28
build.rs
View File

@@ -48,6 +48,34 @@ fn main() {
if let Some(rev) = git_revision_hash() {
println!("cargo:rustc-env=RIPGREP_BUILD_GIT_HASH={}", rev);
}
// Embed a Windows manifest and set some linker options. The main reason
// for this is to enable long path support on Windows. This still, I
// believe, requires enabling long path support in the registry. But if
// that's enabled, then this will let ripgrep use C:\... style paths that
// are longer than 260 characters.
set_windows_exe_options();
}
fn set_windows_exe_options() {
static MANIFEST: &str = "pkg/windows/Manifest.xml";
let Ok(target_os) = env::var("CARGO_CFG_TARGET_OS") else { return };
let Ok(target_env) = env::var("CARGO_CFG_TARGET_ENV") else { return };
if !(target_os == "windows" && target_env == "msvc") {
return;
}
let Ok(mut manifest) = env::current_dir() else { return };
manifest.push(MANIFEST);
let Some(manifest) = manifest.to_str() else { return };
println!("cargo:rerun-if-changed={}", MANIFEST);
// Embed the Windows application manifest file.
println!("cargo:rustc-link-arg-bin=rg=/MANIFEST:EMBED");
println!("cargo:rustc-link-arg-bin=rg=/MANIFESTINPUT:{manifest}");
// Turn linker warnings into errors. Helps debugging, otherwise the
// warnings get squashed (I believe).
println!("cargo:rustc-link-arg-bin=rg=/WX");
}
fn git_revision_hash() -> Option<String> {

11
complete/_rg
View File

@@ -30,7 +30,7 @@ _rg() {
[[ $_RG_COMPLETE_LIST_ARGS == (1|t*|y*) ]] ||
# (--[imnp]* => --ignore*, --messages, --no-*, --pcre2-unicode)
[[ $PREFIX$SUFFIX == --[imnp]* ]] ||
zstyle -t ":complete:$curcontext:*" complete-all
zstyle -t ":completion:${curcontext}:" complete-all
then
no=
fi
@@ -319,6 +319,7 @@ _rg() {
'(-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]'
'--stop-on-nonmatch[stop on first non-matching line after a matching one]'
+ operand # Operands
'(--files --type-list file regexp)1: :_guard "^-*" pattern'
@@ -432,9 +433,13 @@ _rg_types() {
local -a expl
local -aU _types
_types=( ${(@)${(f)"$( _call_program types rg --type-list )"}%%:*} )
_types=( ${(@)${(f)"$( _call_program types $words[1] --type-list )"}//:[[:space:]]##/:} )
_wanted types expl 'file type' compadd -a "$@" - _types
if zstyle -t ":completion:${curcontext}:types" extra-verbose; then
_describe -t types 'file type' _types
else
_wanted types expl 'file type' compadd "$@" - ${(@)_types%%:*}
fi
}
_rg "$@"

42
crates/cli/src/decompress.rs
View File

@@ -18,7 +18,7 @@ pub struct DecompressionMatcherBuilder {
}
/// A representation of a single command for decompressing data
/// out-of-proccess.
/// out-of-process.
#[derive(Clone, Debug)]
struct DecompressionCommand {
/// The glob that matches this command.
@@ -132,7 +132,7 @@ impl DecompressionMatcherBuilder {
A: AsRef<OsStr>,
{
let glob = glob.to_string();
let bin = resolve_binary(Path::new(program.as_ref()))?;
let bin = try_resolve_binary(Path::new(program.as_ref()))?;
let args =
args.into_iter().map(|a| a.as_ref().to_os_string()).collect();
self.commands.push(DecompressionCommand { glob, bin, args });
@@ -421,6 +421,34 @@ impl io::Read for DecompressionReader {
/// On non-Windows, this is a no-op.
pub fn resolve_binary<P: AsRef<Path>>(
prog: P,
) -> Result<PathBuf, CommandError> {
if !cfg!(windows) {
return Ok(prog.as_ref().to_path_buf());
}
try_resolve_binary(prog)
}
/// Resolves a path to a program to a path by searching for the program in
/// `PATH`.
///
/// If the program could not be resolved, then an error is returned.
///
/// The purpose of doing this instead of passing the path to the program
/// directly to Command::new is that Command::new will hand relative paths
/// to CreateProcess on Windows, which will implicitly search the current
/// working directory for the executable. This could be undesirable for
/// security reasons. e.g., running ripgrep with the -z/--search-zip flag on an
/// untrusted directory tree could result in arbitrary programs executing on
/// Windows.
///
/// Note that this could still return a relative path if PATH contains a
/// relative path. We permit this since it is assumed that the user has set
/// this explicitly, and thus, desires this behavior.
///
/// If `check_exists` is false or the path is already an absolute path this
/// will return immediately.
fn try_resolve_binary<P: AsRef<Path>>(
prog: P,
) -> Result<PathBuf, CommandError> {
use std::env;
@@ -433,7 +461,7 @@ pub fn resolve_binary<P: AsRef<Path>>(
}
let prog = prog.as_ref();
if !cfg!(windows) || prog.is_absolute() {
if prog.is_absolute() {
return Ok(prog.to_path_buf());
}
let syspaths = match env::var_os("PATH") {
@@ -455,9 +483,11 @@ pub fn resolve_binary<P: AsRef<Path>>(
return Ok(abs_prog.to_path_buf());
}
if abs_prog.extension().is_none() {
let abs_prog = abs_prog.with_extension("exe");
if is_exe(&abs_prog) {
return Ok(abs_prog.to_path_buf());
for extension in ["com", "exe"] {
let abs_prog = abs_prog.with_extension(extension);
if is_exe(&abs_prog) {
return Ok(abs_prog.to_path_buf());
}
}
}
}

57
crates/core/app.rs
View File

@@ -632,6 +632,7 @@ pub fn all_args_and_flags() -> Vec<RGArg> {
flag_sort(&mut args);
flag_sortr(&mut args);
flag_stats(&mut args);
flag_stop_on_nonmatch(&mut args);
flag_text(&mut args);
flag_threads(&mut args);
flag_trim(&mut args);
@@ -698,7 +699,7 @@ fn flag_after_context(args: &mut Vec<RGArg>) {
"\
Show NUM lines after each match.
This overrides the --context and --passthru flags.
This overrides the --passthru flag and partially overrides --context.
"
);
let arg = RGArg::flag("after-context", "NUM")
@@ -706,8 +707,7 @@ This overrides the --context and --passthru flags.
.help(SHORT)
.long_help(LONG)
.number()
.overrides("passthru")
.overrides("context");
.overrides("passthru");
args.push(arg);
}
@@ -768,7 +768,7 @@ fn flag_before_context(args: &mut Vec<RGArg>) {
"\
Show NUM lines before each match.
This overrides the --context and --passthru flags.
This overrides the --passthru flag and partially overrides --context.
"
);
let arg = RGArg::flag("before-context", "NUM")
@@ -776,8 +776,7 @@ This overrides the --context and --passthru flags.
.help(SHORT)
.long_help(LONG)
.number()
.overrides("passthru")
.overrides("context");
.overrides("passthru");
args.push(arg);
}
@@ -1009,8 +1008,7 @@ fn flag_context(args: &mut Vec<RGArg>) {
Show NUM lines before and after each match. This is equivalent to providing
both the -B/--before-context and -A/--after-context flags with the same value.
This overrides both the -B/--before-context and -A/--after-context flags,
in addition to the --passthru flag.
This overrides the --passthru flag.
"
);
let arg = RGArg::flag("context", "NUM")
@@ -1018,9 +1016,7 @@ in addition to the --passthru flag.
.help(SHORT)
.long_help(LONG)
.number()
.overrides("passthru")
.overrides("before-context")
.overrides("after-context");
.overrides("passthru");
args.push(arg);
}
@@ -1711,6 +1707,8 @@ fn flag_line_number(args: &mut Vec<RGArg>) {
"\
Show line numbers (1-based). This is enabled by default when searching in a
terminal.
This flag overrides --no-line-number.
"
);
let arg = RGArg::switch("line-number")
@@ -1725,6 +1723,8 @@ terminal.
"\
Suppress line numbers. This is enabled by default when not searching in a
terminal.
This flag overrides --line-number.
"
);
let arg = RGArg::switch("no-line-number")
@@ -1927,13 +1927,16 @@ Nevertheless, if you only care about matches spanning at most one line, then it
is always better to disable multiline mode.
This flag can be disabled with --no-multiline.
This overrides the --stop-on-nonmatch flag.
"
);
let arg = RGArg::switch("multiline")
.short("U")
.help(SHORT)
.long_help(LONG)
.overrides("no-multiline");
.overrides("no-multiline")
.overrides("stop-on-nonmatch");
args.push(arg);
let arg = RGArg::switch("no-multiline").hidden().overrides("multiline");
@@ -2647,6 +2650,17 @@ replacement string. Capture group indices are numbered based on the position of
the opening parenthesis of the group, where the leftmost such group is $1. The
special $0 group corresponds to the entire match.
The name of a group is formed by taking the longest string of letters, numbers
and underscores (i.e. [_0-9A-Za-z]) after the $. For example, $1a will be
replaced with the group named '1a', not the group at index 1. If the group's
name contains characters that aren't letters, numbers or underscores, or you
want to immediately follow the group with another string, the name should be
put inside braces. For example, ${1}a will take the content of the group at
index 1 and append 'a' to the end of it.
If an index or name does not refer to a valid capture group, it will be
replaced with an empty string.
In shells such as Bash and zsh, you should wrap the pattern in single quotes
instead of double quotes. Otherwise, capture group indices will be replaced by
expanded shell variables which will most likely be empty.
@@ -2844,6 +2858,25 @@ This flag can be disabled with --no-stats.
args.push(arg);
}
fn flag_stop_on_nonmatch(args: &mut Vec<RGArg>) {
const SHORT: &str = "Stop searching after a non-match.";
const LONG: &str = long!(
"\
Enabling this option will cause ripgrep to stop reading a file once it
encounters a non-matching line after it has encountered a matching line.
This is useful if it is expected that all matches in a given file will be on
sequential lines, for example due to the lines being sorted.
This overrides the -U/--multiline flag.
"
);
let arg = RGArg::switch("stop-on-nonmatch")
.help(SHORT)
.long_help(LONG)
.overrides("multiline");
args.push(arg);
}
fn flag_text(args: &mut Vec<RGArg>) {
const SHORT: &str = "Search binary files as if they were text.";
const LONG: &str = long!(

156
crates/core/args.rs
View File

@@ -41,7 +41,7 @@ use crate::path_printer::{PathPrinter, PathPrinterBuilder};
use crate::search::{
PatternMatcher, Printer, SearchWorker, SearchWorkerBuilder,
};
use crate::subject::SubjectBuilder;
use crate::subject::{Subject, SubjectBuilder};
use crate::Result;
/// The command that ripgrep should execute based on the command line
@@ -324,6 +324,46 @@ impl Args {
.build())
}
/// Returns true if and only if `stat`-related sorting is required
pub fn needs_stat_sort(&self) -> bool {
return self.matches().sort_by().map_or(
false,
|sort_by| match sort_by.kind {
SortByKind::LastModified
| SortByKind::Created
| SortByKind::LastAccessed => sort_by.check().is_ok(),
_ => false,
},
);
}
/// Sort subjects if a sorter is specified, but only if the sort requires
/// stat calls. Non-stat related sorts are handled during file traversal
///
/// This function assumes that it is known that a stat-related sort is
/// required, and does not check for it again.
///
/// It is important that that precondition is fulfilled, since this function
/// consumes the subjects iterator, and is therefore a blocking function.
pub fn sort_by_stat<I>(&self, subjects: I) -> Vec<Subject>
where
I: Iterator<Item = Subject>,
{
let sorter = match self.matches().sort_by() {
Ok(v) => v,
Err(_) => return subjects.collect(),
};
use SortByKind::*;
let mut keyed = match sorter.kind {
LastModified => load_timestamps(subjects, |m| m.modified()),
LastAccessed => load_timestamps(subjects, |m| m.accessed()),
Created => load_timestamps(subjects, |m| m.created()),
_ => return subjects.collect(),
};
keyed.sort_by(|a, b| sort_by_option(&a.0, &b.0, sorter.reverse));
keyed.into_iter().map(|v| v.1).collect()
}
/// Return a parallel walker that may use additional threads.
pub fn walker_parallel(&self) -> Result<WalkParallel> {
Ok(self
@@ -404,44 +444,23 @@ impl SortBy {
Ok(())
}
fn configure_walk_builder(self, builder: &mut WalkBuilder) {
// This isn't entirely optimal. In particular, we will wind up issuing
// a stat for many files redundantly. Aside from having potentially
// inconsistent results with respect to sorting, this is also slow.
// We could fix this here at the expense of memory by caching stat
// calls. A better fix would be to find a way to push this down into
// directory traversal itself, but that's a somewhat nasty change.
/// Load sorters only if they are applicable at the walk stage.
///
/// In particular, sorts that involve `stat` calls are not loaded because
/// the walk inherently assumes that parent directories are aware of all its
/// decendent properties, but `stat` does not work that way.
fn configure_builder_sort(self, builder: &mut WalkBuilder) {
use SortByKind::*;
match self.kind {
SortByKind::None => {}
SortByKind::Path => {
if self.reverse {
builder.sort_by_file_name(|a, b| a.cmp(b).reverse());
} else {
builder.sort_by_file_name(|a, b| a.cmp(b));
}
Path if self.reverse => {
builder.sort_by_file_name(|a, b| a.cmp(b).reverse());
}
SortByKind::LastModified => {
builder.sort_by_file_path(move |a, b| {
sort_by_metadata_time(a, b, self.reverse, |md| {
md.modified()
})
});
Path => {
builder.sort_by_file_name(|a, b| a.cmp(b));
}
SortByKind::LastAccessed => {
builder.sort_by_file_path(move |a, b| {
sort_by_metadata_time(a, b, self.reverse, |md| {
md.accessed()
})
});
}
SortByKind::Created => {
builder.sort_by_file_path(move |a, b| {
sort_by_metadata_time(a, b, self.reverse, |md| {
md.created()
})
});
}
}
// these use `stat` calls and will be sorted in Args::sort_by_stat()
LastModified | LastAccessed | Created | None => {}
};
}
}
@@ -821,7 +840,8 @@ impl ArgMatches {
.before_context(ctx_before)
.after_context(ctx_after)
.passthru(self.is_present("passthru"))
.memory_map(self.mmap_choice(paths));
.memory_map(self.mmap_choice(paths))
.stop_on_nonmatch(self.is_present("stop-on-nonmatch"));
match self.encoding()? {
EncodingMode::Some(enc) => {
builder.encoding(Some(enc));
@@ -872,12 +892,10 @@ impl ArgMatches {
.git_exclude(!self.no_ignore_vcs() && !self.no_ignore_exclude())
.require_git(!self.is_present("no-require-git"))
.ignore_case_insensitive(self.ignore_file_case_insensitive());
if !self.no_ignore() {
if !self.no_ignore() && !self.no_ignore_dot() {
builder.add_custom_ignore_filename(".rgignore");
}
let sortby = self.sort_by()?;
sortby.check()?;
sortby.configure_walk_builder(&mut builder);
self.sort_by()?.configure_builder_sort(&mut builder);
Ok(builder)
}
}
@@ -992,10 +1010,10 @@ impl ArgMatches {
/// If there was a problem parsing the values from the user as an integer,
/// then an error is returned.
fn contexts(&self) -> Result<(usize, usize)> {
let after = self.usize_of("after-context")?.unwrap_or(0);
let before = self.usize_of("before-context")?.unwrap_or(0);
let both = self.usize_of("context")?.unwrap_or(0);
Ok(if both > 0 { (both, both) } else { (before, after) })
let after = self.usize_of("after-context")?.unwrap_or(both);
let before = self.usize_of("before-context")?.unwrap_or(both);
Ok((before, after))
}
/// Returns the unescaped context separator in UTF-8 bytes.
@@ -1739,32 +1757,18 @@ fn u64_to_usize(arg_name: &str, value: Option<u64>) -> Result<Option<usize>> {
}
}
/// Builds a comparator for sorting two files according to a system time
/// extracted from the file's metadata.
///
/// If there was a problem extracting the metadata or if the time is not
/// available, then both entries compare equal.
fn sort_by_metadata_time<G>(
p1: &Path,
p2: &Path,
/// Sorts by an optional parameter.
//
/// If parameter is found to be `None`, both entries compare equal.
fn sort_by_option<T: Ord>(
p1: &Option<T>,
p2: &Option<T>,
reverse: bool,
get_time: G,
) -> cmp::Ordering
where
G: Fn(&fs::Metadata) -> io::Result<SystemTime>,
{
let t1 = match p1.metadata().and_then(|md| get_time(&md)) {
Ok(t) => t,
Err(_) => return cmp::Ordering::Equal,
};
let t2 = match p2.metadata().and_then(|md| get_time(&md)) {
Ok(t) => t,
Err(_) => return cmp::Ordering::Equal,
};
if reverse {
t1.cmp(&t2).reverse()
} else {
t1.cmp(&t2)
) -> cmp::Ordering {
match (p1, p2, reverse) {
(Some(p1), Some(p2), true) => p1.cmp(&p2).reverse(),
(Some(p1), Some(p2), false) => p1.cmp(&p2),
_ => cmp::Ordering::Equal,
}
}
@@ -1818,3 +1822,17 @@ fn current_dir() -> Result<PathBuf> {
)
.into())
}
/// Tries to assign a timestamp to every `Subject` in the vector to help with
/// sorting Subjects by time.
fn load_timestamps<G>(
subjects: impl Iterator<Item = Subject>,
get_time: G,
) -> Vec<(Option<SystemTime>, Subject)>
where
G: Fn(&fs::Metadata) -> io::Result<SystemTime>,
{
subjects
.map(|s| (s.path().metadata().and_then(|m| get_time(&m)).ok(), s))
.collect()
}

8
crates/core/logger.rs
View File

@@ -33,7 +33,7 @@ impl Log for Logger {
fn log(&self, record: &log::Record<'_>) {
match (record.file(), record.line()) {
(Some(file), Some(line)) => {
eprintln!(
eprintln_locked!(
"{}|{}|{}:{}: {}",
record.level(),
record.target(),
@@ -43,7 +43,7 @@ impl Log for Logger {
);
}
(Some(file), None) => {
eprintln!(
eprintln_locked!(
"{}|{}|{}: {}",
record.level(),
record.target(),
@@ -52,7 +52,7 @@ impl Log for Logger {
);
}
_ => {
eprintln!(
eprintln_locked!(
"{}|{}: {}",
record.level(),
record.target(),
@@ -63,6 +63,6 @@ impl Log for Logger {
}
fn flush(&self) {
// We use eprintln! which is flushed on every call.
// We use eprintln_locked! which is flushed on every call.
}
}

146
crates/core/main.rs
View File

@@ -47,7 +47,7 @@ type Result<T> = ::std::result::Result<T, Box<dyn error::Error>>;
fn main() {
if let Err(err) = Args::parse().and_then(try_main) {
eprintln!("{}", err);
eprintln_locked!("{}", err);
process::exit(2);
}
}
@@ -77,53 +77,70 @@ fn try_main(args: Args) -> Result<()> {
/// steps through the file list (current directory by default) and searches
/// each file sequentially.
fn search(args: &Args) -> Result<bool> {
let started_at = Instant::now();
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
let mut stats = args.stats()?;
let mut searcher = args.search_worker(args.stdout())?;
let mut matched = false;
let mut searched = false;
/// The meat of the routine is here. This lets us call the same iteration
/// code over each file regardless of whether we stream over the files
/// as they're produced by the underlying directory traversal or whether
/// they've been collected and sorted (for example) first.
fn iter(
args: &Args,
subjects: impl Iterator<Item = Subject>,
started_at: std::time::Instant,
) -> Result<bool> {
let quit_after_match = args.quit_after_match()?;
let mut stats = args.stats()?;
let mut searcher = args.search_worker(args.stdout())?;
let mut matched = false;
let mut searched = false;
for result in args.walker()? {
let subject = match subject_builder.build_from_result(result) {
Some(subject) => subject,
None => continue,
};
searched = true;
let search_result = match searcher.search(&subject) {
Ok(search_result) => search_result,
Err(err) => {
for subject in subjects {
searched = true;
let search_result = match searcher.search(&subject) {
Ok(search_result) => search_result,
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
break;
Err(err) if err.kind() == io::ErrorKind::BrokenPipe => break,
Err(err) => {
err_message!("{}: {}", subject.path().display(), err);
continue;
}
err_message!("{}: {}", subject.path().display(), err);
continue;
};
matched |= search_result.has_match();
if let Some(ref mut stats) = stats {
*stats += search_result.stats().unwrap();
}
if matched && quit_after_match {
break;
}
};
matched = matched || search_result.has_match();
if let Some(ref mut stats) = stats {
*stats += search_result.stats().unwrap();
}
if matched && quit_after_match {
break;
if args.using_default_path() && !searched {
eprint_nothing_searched();
}
if let Some(ref stats) = stats {
let elapsed = Instant::now().duration_since(started_at);
// We don't care if we couldn't print this successfully.
let _ = searcher.print_stats(elapsed, stats);
}
Ok(matched)
}
if args.using_default_path() && !searched {
eprint_nothing_searched();
let started_at = Instant::now();
let subject_builder = args.subject_builder();
let subjects = args
.walker()?
.filter_map(|result| subject_builder.build_from_result(result));
if args.needs_stat_sort() {
let subjects = args.sort_by_stat(subjects).into_iter();
iter(args, subjects, started_at)
} else {
iter(args, subjects, started_at)
}
if let Some(ref stats) = stats {
let elapsed = Instant::now().duration_since(started_at);
// We don't care if we couldn't print this successfully.
let _ = searcher.print_stats(elapsed, stats);
}
Ok(matched)
}
/// The top-level entry point for multi-threaded search. The parallelism is
/// itself achieved by the recursive directory traversal. All we need to do is
/// feed it a worker for performing a search on each file.
///
/// Requesting a sorted output from ripgrep (such as with `--sort path`) will
/// automatically disable parallelism and hence sorting is not handled here.
fn search_parallel(args: &Args) -> Result<bool> {
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering::SeqCst;
@@ -214,35 +231,54 @@ fn eprint_nothing_searched() {
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using a single thread.
fn files(args: &Args) -> Result<bool> {
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
let mut matched = false;
let mut path_printer = args.path_printer(args.stdout())?;
for result in args.walker()? {
let subject = match subject_builder.build_from_result(result) {
Some(subject) => subject,
None => continue,
};
matched = true;
if quit_after_match {
break;
}
if let Err(err) = path_printer.write_path(subject.path()) {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
/// The meat of the routine is here. This lets us call the same iteration
/// code over each file regardless of whether we stream over the files
/// as they're produced by the underlying directory traversal or whether
/// they've been collected and sorted (for example) first.
fn iter(
args: &Args,
subjects: impl Iterator<Item = Subject>,
) -> Result<bool> {
let quit_after_match = args.quit_after_match()?;
let mut matched = false;
let mut path_printer = args.path_printer(args.stdout())?;
for subject in subjects {
matched = true;
if quit_after_match {
break;
}
// Otherwise, we have some other error that's preventing us from
// writing to stdout, so we should bubble it up.
return Err(err.into());
if let Err(err) = path_printer.write_path(subject.path()) {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
break;
}
// Otherwise, we have some other error that's preventing us from
// writing to stdout, so we should bubble it up.
return Err(err.into());
}
}
Ok(matched)
}
let subject_builder = args.subject_builder();
let subjects = args
.walker()?
.filter_map(|result| subject_builder.build_from_result(result));
if args.needs_stat_sort() {
let subjects = args.sort_by_stat(subjects).into_iter();
iter(args, subjects)
} else {
iter(args, subjects)
}
Ok(matched)
}
/// The top-level entry point for listing files without searching them. This
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using multiple threads.
///
/// Requesting a sorted output from ripgrep (such as with `--sort path`) will
/// automatically disable parallelism and hence sorting is not handled here.
fn files_parallel(args: &Args) -> Result<bool> {
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering::SeqCst;

20
crates/core/messages.rs
View File

@@ -4,12 +4,28 @@ static MESSAGES: AtomicBool = AtomicBool::new(false);
static IGNORE_MESSAGES: AtomicBool = AtomicBool::new(false);
static ERRORED: AtomicBool = AtomicBool::new(false);
/// Like eprintln, but locks STDOUT to prevent interleaving lines.
#[macro_export]
macro_rules! eprintln_locked {
($($tt:tt)*) => {{
{
// This is a bit of an abstraction violation because we explicitly
// lock STDOUT before printing to STDERR. This avoids interleaving
// lines within ripgrep because `search_parallel` uses `termcolor`,
// which accesses the same STDOUT lock when writing lines.
let stdout = std::io::stdout();
let _handle = stdout.lock();
eprintln!($($tt)*);
}
}}
}
/// Emit a non-fatal error message, unless messages were disabled.
#[macro_export]
macro_rules! message {
($($tt:tt)*) => {
if crate::messages::messages() {
eprintln!($($tt)*);
eprintln_locked!($($tt)*);
}
}
}
@@ -30,7 +46,7 @@ macro_rules! err_message {
macro_rules! ignore_message {
($($tt:tt)*) => {
if crate::messages::messages() && crate::messages::ignore_messages() {
eprintln!($($tt)*);
eprintln_locked!($($tt)*);
}
}
}

2
crates/globset/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "globset"
version = "0.4.10" #:version
version = "0.4.11" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Cross platform single glob and glob set matching. Glob set matching is the

52
crates/globset/src/glob.rs
View File

@@ -208,6 +208,9 @@ struct GlobOptions {
/// Whether or not to use `\` to escape special characters.
/// e.g., when enabled, `\*` will match a literal `*`.
backslash_escape: bool,
/// Whether or not an empty case in an alternate will be removed.
/// e.g., when enabled, `{,a}` will match "" and "a".
empty_alternates: bool,
}
impl GlobOptions {
@@ -216,6 +219,7 @@ impl GlobOptions {
case_insensitive: false,
literal_separator: false,
backslash_escape: !is_separator('\\'),
empty_alternates: false,
}
}
}
@@ -633,6 +637,16 @@ impl<'a> GlobBuilder<'a> {
self.opts.backslash_escape = yes;
self
}
/// Toggle whether an empty pattern in a list of alternates is accepted.
///
/// For example, if this is set then the glob `foo{,.txt}` will match both `foo` and `foo.txt`.
///
/// By default this is false.
pub fn empty_alternates(&mut self, yes: bool) -> &mut GlobBuilder<'a> {
self.opts.empty_alternates = yes;
self
}
}
impl Tokens {
@@ -714,7 +728,7 @@ impl Tokens {
for pat in patterns {
let mut altre = String::new();
self.tokens_to_regex(options, &pat, &mut altre);
if !altre.is_empty() {
if !altre.is_empty() || options.empty_alternates {
parts.push(altre);
}
}
@@ -1020,6 +1034,7 @@ mod tests {
casei: Option<bool>,
litsep: Option<bool>,
bsesc: Option<bool>,
ealtre: Option<bool>,
}
macro_rules! syntax {
@@ -1059,6 +1074,9 @@ mod tests {
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
if let Some(ealtre) = $options.ealtre {
builder.empty_alternates(ealtre);
}
let pat = builder.build().unwrap();
assert_eq!(format!("(?-u){}", $re), pat.regex());
}
@@ -1082,6 +1100,9 @@ mod tests {
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
if let Some(ealtre) = $options.ealtre {
builder.empty_alternates(ealtre);
}
let pat = builder.build().unwrap();
let matcher = pat.compile_matcher();
let strategic = pat.compile_strategic_matcher();
@@ -1110,6 +1131,9 @@ mod tests {
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
if let Some(ealtre) = $options.ealtre {
builder.empty_alternates(ealtre);
}
let pat = builder.build().unwrap();
let matcher = pat.compile_matcher();
let strategic = pat.compile_strategic_matcher();
@@ -1195,13 +1219,23 @@ mod tests {
syntaxerr!(err_range2, "[z--]", ErrorKind::InvalidRange('z', '-'));
const CASEI: Options =
Options { casei: Some(true), litsep: None, bsesc: None };
Options { casei: Some(true), litsep: None, bsesc: None, ealtre: None };
const SLASHLIT: Options =
Options { casei: None, litsep: Some(true), bsesc: None };
const NOBSESC: Options =
Options { casei: None, litsep: None, bsesc: Some(false) };
Options { casei: None, litsep: Some(true), bsesc: None, ealtre: None };
const NOBSESC: Options = Options {
casei: None,
litsep: None,
bsesc: Some(false),
ealtre: None,
};
const BSESC: Options =
Options { casei: None, litsep: None, bsesc: Some(true) };
Options { casei: None, litsep: None, bsesc: Some(true), ealtre: None };
const EALTRE: Options = Options {
casei: None,
litsep: None,
bsesc: Some(true),
ealtre: Some(true),
};
toregex!(re_casei, "a", "(?i)^a$", &CASEI);
@@ -1326,6 +1360,9 @@ mod tests {
matches!(matchalt11, "{*.foo,*.bar,*.wat}", "test.foo");
matches!(matchalt12, "{*.foo,*.bar,*.wat}", "test.bar");
matches!(matchalt13, "{*.foo,*.bar,*.wat}", "test.wat");
matches!(matchalt14, "foo{,.txt}", "foo.txt");
nmatches!(matchalt15, "foo{,.txt}", "foo");
matches!(matchalt16, "foo{,.txt}", "foo", EALTRE);
matches!(matchslash1, "abc/def", "abc/def", SLASHLIT);
#[cfg(unix)]
@@ -1425,6 +1462,9 @@ mod tests {
if let Some(bsesc) = $options.bsesc {
builder.backslash_escape(bsesc);
}
if let Some(ealtre) = $options.ealtre {
builder.empty_alternates(ealtre);
}
let pat = builder.build().unwrap();
assert_eq!($expect, pat.$which());
}

35
crates/globset/src/lib.rs
View File

@@ -880,6 +880,29 @@ impl RequiredExtensionStrategyBuilder {
}
}
/// Escape meta-characters within the given glob pattern.
///
/// The escaping works by surrounding meta-characters with brackets. For
/// example, `*` becomes `[*]`.
pub fn escape(s: &str) -> String {
let mut escaped = String::with_capacity(s.len());
for c in s.chars() {
match c {
// note that ! does not need escaping because it is only special
// inside brackets
'?' | '*' | '[' | ']' => {
escaped.push('[');
escaped.push(c);
escaped.push(']');
}
c => {
escaped.push(c);
}
}
}
escaped
}
#[cfg(test)]
mod tests {
use super::{GlobSet, GlobSetBuilder};
@@ -919,4 +942,16 @@ mod tests {
assert!(!set.is_match(""));
assert!(!set.is_match("a"));
}
#[test]
fn escape() {
use super::escape;
assert_eq!("foo", escape("foo"));
assert_eq!("foo[*]", escape("foo*"));
assert_eq!("[[][]]", escape("[]"));
assert_eq!("[*][?]", escape("*?"));
assert_eq!("src/[*][*]/[*].rs", escape("src/**/*.rs"));
assert_eq!("bar[[]ab[]]baz", escape("bar[ab]baz"));
assert_eq!("bar[[]!![]]!baz", escape("bar[!!]!baz"));
}
}

2
crates/globset/src/pathutil.rs
View File

@@ -27,7 +27,7 @@ pub fn file_name<'a>(path: &Cow<'a, [u8]>) -> Option<Cow<'a, [u8]>> {
///
/// Note that this does NOT match the semantics of std::path::Path::extension.
/// Namely, the extension includes the `.` and matching is otherwise more
/// liberal. Specifically, the extenion is:
/// liberal. Specifically, the extension is:
///
/// * None, if the file name given is empty;
/// * None, if there is no embedded `.`;

58
crates/globset/src/serde_impl.rs
View File

@@ -1,5 +1,7 @@
use serde::de::Error;
use serde::{Deserialize, Deserializer, Serialize, Serializer};
use serde::{
de::{Error, Visitor},
{Deserialize, Deserializer, Serialize, Serializer},
};
use crate::Glob;
@@ -12,19 +14,67 @@ impl Serialize for Glob {
}
}
struct GlobVisitor;
impl<'a> Visitor<'a> for GlobVisitor {
type Value = Glob;
fn expecting(
&self,
formatter: &mut std::fmt::Formatter,
) -> std::fmt::Result {
formatter.write_str("a glob pattern")
}
fn visit_str<E>(self, v: &str) -> Result<Self::Value, E>
where
E: Error,
{
Glob::new(v).map_err(serde::de::Error::custom)
}
}
impl<'de> Deserialize<'de> for Glob {
fn deserialize<D: Deserializer<'de>>(
deserializer: D,
) -> Result<Self, D::Error> {
let glob = <&str as Deserialize>::deserialize(deserializer)?;
Glob::new(glob).map_err(D::Error::custom)
deserializer.deserialize_str(GlobVisitor)
}
}
#[cfg(test)]
mod tests {
use std::collections::HashMap;
use crate::Glob;
#[test]
fn glob_deserialize_borrowed() {
let string = r#"{"markdown": "*.md"}"#;
let map: HashMap<String, Glob> =
serde_json::from_str(&string).unwrap();
assert_eq!(map["markdown"], Glob::new("*.md").unwrap());
}
#[test]
fn glob_deserialize_owned() {
let string = r#"{"markdown": "*.md"}"#;
let v: serde_json::Value = serde_json::from_str(&string).unwrap();
let map: HashMap<String, Glob> = serde_json::from_value(v).unwrap();
assert_eq!(map["markdown"], Glob::new("*.md").unwrap());
}
#[test]
fn glob_deserialize_error() {
let string = r#"{"error": "["}"#;
let map = serde_json::from_str::<HashMap<String, Glob>>(&string);
assert!(map.is_err());
}
#[test]
fn glob_json_works() {
let test_glob = Glob::new("src/**/*.rs").unwrap();

2
crates/ignore/Cargo.toml
View File

@@ -23,7 +23,7 @@ globset = { version = "0.4.10", path = "../globset" }
lazy_static = "1.1"
log = "0.4.5"
memchr = "2.5"
regex = "1.8.3"
regex = { version = "1.9.0", default-features = false, features = ["perf", "std", "unicode-gencat"] }
same-file = "1.0.4"
thread_local = "1"
walkdir = "2.2.7"

400
crates/ignore/src/default_types.rs
View File

@@ -9,105 +9,113 @@
/// Please try to keep this list sorted lexicographically and wrapped to 79
/// columns (inclusive).
#[rustfmt::skip]
pub const DEFAULT_TYPES: &[(&str, &[&str])] = &[
("agda", &["*.agda", "*.lagda"]),
("aidl", &["*.aidl"]),
("amake", &["*.mk", "*.bp"]),
("asciidoc", &["*.adoc", "*.asc", "*.asciidoc"]),
("asm", &["*.asm", "*.s", "*.S"]),
("asp", &[
pub const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["ada"], &["*.adb", "*.ads"]),
(&["agda"], &["*.agda", "*.lagda"]),
(&["aidl"], &["*.aidl"]),
(&["alire"], &["alire.toml"]),
(&["amake"], &["*.mk", "*.bp"]),
(&["asciidoc"], &["*.adoc", "*.asc", "*.asciidoc"]),
(&["asm"], &["*.asm", "*.s", "*.S"]),
(&["asp"], &[
"*.aspx", "*.aspx.cs", "*.aspx.vb", "*.ascx", "*.ascx.cs",
"*.ascx.vb", "*.asp"
]),
("ats", &["*.ats", "*.dats", "*.sats", "*.hats"]),
("avro", &["*.avdl", "*.avpr", "*.avsc"]),
("awk", &["*.awk"]),
("bazel", &[
(&["ats"], &["*.ats", "*.dats", "*.sats", "*.hats"]),
(&["avro"], &["*.avdl", "*.avpr", "*.avsc"]),
(&["awk"], &["*.awk"]),
(&["bat", "batch"], &["*.bat"]),
(&["bazel"], &[
"*.bazel", "*.bzl", "*.BUILD", "*.bazelrc", "BUILD", "MODULE.bazel",
"WORKSPACE", "WORKSPACE.bazel",
]),
("bitbake", &["*.bb", "*.bbappend", "*.bbclass", "*.conf", "*.inc"]),
("brotli", &["*.br"]),
("buildstream", &["*.bst"]),
("bzip2", &["*.bz2", "*.tbz2"]),
("c", &["*.[chH]", "*.[chH].in", "*.cats"]),
("cabal", &["*.cabal"]),
("candid", &["*.did"]),
("carp", &["*.carp"]),
("cbor", &["*.cbor"]),
("ceylon", &["*.ceylon"]),
("clojure", &["*.clj", "*.cljc", "*.cljs", "*.cljx"]),
("cmake", &["*.cmake", "CMakeLists.txt"]),
("coffeescript", &["*.coffee"]),
("config", &["*.cfg", "*.conf", "*.config", "*.ini"]),
("coq", &["*.v"]),
("cpp", &[
(&["bitbake"], &["*.bb", "*.bbappend", "*.bbclass", "*.conf", "*.inc"]),
(&["brotli"], &["*.br"]),
(&["buildstream"], &["*.bst"]),
(&["bzip2"], &["*.bz2", "*.tbz2"]),
(&["c"], &["*.[chH]", "*.[chH].in", "*.cats"]),
(&["cabal"], &["*.cabal"]),
(&["candid"], &["*.did"]),
(&["carp"], &["*.carp"]),
(&["cbor"], &["*.cbor"]),
(&["ceylon"], &["*.ceylon"]),
(&["clojure"], &["*.clj", "*.cljc", "*.cljs", "*.cljx"]),
(&["cmake"], &["*.cmake", "CMakeLists.txt"]),
(&["cmd"], &["*.bat", "*.cmd"]),
(&["cml"], &["*.cml"]),
(&["coffeescript"], &["*.coffee"]),
(&["config"], &["*.cfg", "*.conf", "*.config", "*.ini"]),
(&["coq"], &["*.v"]),
(&["cpp"], &[
"*.[ChH]", "*.cc", "*.[ch]pp", "*.[ch]xx", "*.hh", "*.inl",
"*.[ChH].in", "*.cc.in", "*.[ch]pp.in", "*.[ch]xx.in", "*.hh.in",
]),
("creole", &["*.creole"]),
("crystal", &["Projectfile", "*.cr", "*.ecr", "shard.yml"]),
("cs", &["*.cs"]),
("csharp", &["*.cs"]),
("cshtml", &["*.cshtml"]),
("css", &["*.css", "*.scss"]),
("csv", &["*.csv"]),
("cuda", &["*.cu", "*.cuh"]),
("cython", &["*.pyx", "*.pxi", "*.pxd"]),
("d", &["*.d"]),
("dart", &["*.dart"]),
("devicetree", &["*.dts", "*.dtsi"]),
("dhall", &["*.dhall"]),
("diff", &["*.patch", "*.diff"]),
("docker", &["*Dockerfile*"]),
("dockercompose", &["docker-compose.yml", "docker-compose.*.yml"]),
("dts", &["*.dts", "*.dtsi"]),
("dvc", &["Dvcfile", "*.dvc"]),
("ebuild", &["*.ebuild"]),
("edn", &["*.edn"]),
("elisp", &["*.el"]),
("elixir", &["*.ex", "*.eex", "*.exs"]),
("elm", &["*.elm"]),
("erb", &["*.erb"]),
("erlang", &["*.erl", "*.hrl"]),
("fennel", &["*.fnl"]),
("fidl", &["*.fidl"]),
("fish", &["*.fish"]),
("flatbuffers", &["*.fbs"]),
("fortran", &[
(&["creole"], &["*.creole"]),
(&["crystal"], &["Projectfile", "*.cr", "*.ecr", "shard.yml"]),
(&["cs"], &["*.cs"]),
(&["csharp"], &["*.cs"]),
(&["cshtml"], &["*.cshtml"]),
(&["css"], &["*.css", "*.scss"]),
(&["csv"], &["*.csv"]),
(&["cuda"], &["*.cu", "*.cuh"]),
(&["cython"], &["*.pyx", "*.pxi", "*.pxd"]),
(&["d"], &["*.d"]),
(&["dart"], &["*.dart"]),
(&["devicetree"], &["*.dts", "*.dtsi"]),
(&["dhall"], &["*.dhall"]),
(&["diff"], &["*.patch", "*.diff"]),
(&["dita"], &["*.dita", "*.ditamap", "*.ditaval"]),
(&["docker"], &["*Dockerfile*"]),
(&["dockercompose"], &["docker-compose.yml", "docker-compose.*.yml"]),
(&["dts"], &["*.dts", "*.dtsi"]),
(&["dvc"], &["Dvcfile", "*.dvc"]),
(&["ebuild"], &["*.ebuild", "*.eclass"]),
(&["edn"], &["*.edn"]),
(&["elisp"], &["*.el"]),
(&["elixir"], &["*.ex", "*.eex", "*.exs", "*.heex", "*.leex", "*.livemd"]),
(&["elm"], &["*.elm"]),
(&["erb"], &["*.erb"]),
(&["erlang"], &["*.erl", "*.hrl"]),
(&["fennel"], &["*.fnl"]),
(&["fidl"], &["*.fidl"]),
(&["fish"], &["*.fish"]),
(&["flatbuffers"], &["*.fbs"]),
(&["fortran"], &[
"*.f", "*.F", "*.f77", "*.F77", "*.pfo",
"*.f90", "*.F90", "*.f95", "*.F95",
]),
("fsharp", &["*.fs", "*.fsx", "*.fsi"]),
("fut", &["*.fut"]),
("gap", &["*.g", "*.gap", "*.gi", "*.gd", "*.tst"]),
("gn", &["*.gn", "*.gni"]),
("go", &["*.go"]),
("gradle", &["*.gradle"]),
("groovy", &["*.groovy", "*.gradle"]),
("gzip", &["*.gz", "*.tgz"]),
("h", &["*.h", "*.hh", "*.hpp"]),
("haml", &["*.haml"]),
("hare", &["*.ha"]),
("haskell", &["*.hs", "*.lhs", "*.cpphs", "*.c2hs", "*.hsc"]),
("hbs", &["*.hbs"]),
("hs", &["*.hs", "*.lhs"]),
("html", &["*.htm", "*.html", "*.ejs"]),
("hy", &["*.hy"]),
("idris", &["*.idr", "*.lidr"]),
("janet", &["*.janet"]),
("java", &["*.java", "*.jsp", "*.jspx", "*.properties"]),
("jinja", &["*.j2", "*.jinja", "*.jinja2"]),
("jl", &["*.jl"]),
("js", &["*.js", "*.jsx", "*.vue", "*.cjs", "*.mjs"]),
("json", &["*.json", "composer.lock"]),
("jsonl", &["*.jsonl"]),
("julia", &["*.jl"]),
("jupyter", &["*.ipynb", "*.jpynb"]),
("k", &["*.k"]),
("kotlin", &["*.kt", "*.kts"]),
("less", &["*.less"]),
("license", &[
(&["fsharp"], &["*.fs", "*.fsx", "*.fsi"]),
(&["fut"], &["*.fut"]),
(&["gap"], &["*.g", "*.gap", "*.gi", "*.gd", "*.tst"]),
(&["gn"], &["*.gn", "*.gni"]),
(&["go"], &["*.go"]),
(&["gprbuild"], &["*.gpr"]),
(&["gradle"], &["*.gradle"]),
(&["graphql"], &["*.graphql", "*.graphqls"]),
(&["groovy"], &["*.groovy", "*.gradle"]),
(&["gzip"], &["*.gz", "*.tgz"]),
(&["h"], &["*.h", "*.hh", "*.hpp"]),
(&["haml"], &["*.haml"]),
(&["hare"], &["*.ha"]),
(&["haskell"], &["*.hs", "*.lhs", "*.cpphs", "*.c2hs", "*.hsc"]),
(&["hbs"], &["*.hbs"]),
(&["hs"], &["*.hs", "*.lhs"]),
(&["html"], &["*.htm", "*.html", "*.ejs"]),
(&["hy"], &["*.hy"]),
(&["idris"], &["*.idr", "*.lidr"]),
(&["janet"], &["*.janet"]),
(&["java"], &["*.java", "*.jsp", "*.jspx", "*.properties"]),
(&["jinja"], &["*.j2", "*.jinja", "*.jinja2"]),
(&["jl"], &["*.jl"]),
(&["js"], &["*.js", "*.jsx", "*.vue", "*.cjs", "*.mjs"]),
(&["json"], &["*.json", "composer.lock"]),
(&["jsonl"], &["*.jsonl"]),
(&["julia"], &["*.jl"]),
(&["jupyter"], &["*.ipynb", "*.jpynb"]),
(&["k"], &["*.k"]),
(&["kotlin"], &["*.kt", "*.kts"]),
(&["less"], &["*.less"]),
(&["license"], &[
// General
"COPYING", "COPYING[.-]*",
"COPYRIGHT", "COPYRIGHT[.-]*",
@@ -134,80 +142,91 @@ pub const DEFAULT_TYPES: &[(&str, &[&str])] = &[
"MPL-*[0-9]*",
"OFL-*[0-9]*",
]),
("lilypond", &["*.ly", "*.ily"]),
("lisp", &["*.el", "*.jl", "*.lisp", "*.lsp", "*.sc", "*.scm"]),
("lock", &["*.lock", "package-lock.json"]),
("log", &["*.log"]),
("lua", &["*.lua"]),
("lz4", &["*.lz4"]),
("lzma", &["*.lzma"]),
("m4", &["*.ac", "*.m4"]),
("make", &[
(&["lilypond"], &["*.ly", "*.ily"]),
(&["lisp"], &["*.el", "*.jl", "*.lisp", "*.lsp", "*.sc", "*.scm"]),
(&["lock"], &["*.lock", "package-lock.json"]),
(&["log"], &["*.log"]),
(&["lua"], &["*.lua"]),
(&["lz4"], &["*.lz4"]),
(&["lzma"], &["*.lzma"]),
(&["m4"], &["*.ac", "*.m4"]),
(&["make"], &[
"[Gg][Nn][Uu]makefile", "[Mm]akefile",
"[Gg][Nn][Uu]makefile.am", "[Mm]akefile.am",
"[Gg][Nn][Uu]makefile.in", "[Mm]akefile.in",
"*.mk", "*.mak"
]),
("mako", &["*.mako", "*.mao"]),
("man", &["*.[0-9lnpx]", "*.[0-9][cEFMmpSx]"]),
("markdown", &["*.markdown", "*.md", "*.mdown", "*.mdwn", "*.mkd", "*.mkdn"]),
("matlab", &["*.m"]),
("md", &["*.markdown", "*.md", "*.mdown", "*.mdwn", "*.mkd", "*.mkdn"]),
("meson", &["meson.build", "meson_options.txt"]),
("minified", &["*.min.html", "*.min.css", "*.min.js"]),
("mint", &["*.mint"]),
("mk", &["mkfile"]),
("ml", &["*.ml"]),
("motoko", &["*.mo"]),
("msbuild", &[
(&["mako"], &["*.mako", "*.mao"]),
(&["man"], &["*.[0-9lnpx]", "*.[0-9][cEFMmpSx]"]),
(&["markdown", "md"], &[
"*.markdown",
"*.md",
"*.mdown",
"*.mdwn",
"*.mkd",
"*.mkdn",
"*.mdx",
]),
(&["matlab"], &["*.m"]),
(&["meson"], &["meson.build", "meson_options.txt"]),
(&["minified"], &["*.min.html", "*.min.css", "*.min.js"]),
(&["mint"], &["*.mint"]),
(&["mk"], &["mkfile"]),
(&["ml"], &["*.ml"]),
(&["motoko"], &["*.mo"]),
(&["msbuild"], &[
"*.csproj", "*.fsproj", "*.vcxproj", "*.proj", "*.props", "*.targets",
"*.sln",
]),
("nim", &["*.nim", "*.nimf", "*.nimble", "*.nims"]),
("nix", &["*.nix"]),
("objc", &["*.h", "*.m"]),
("objcpp", &["*.h", "*.mm"]),
("ocaml", &["*.ml", "*.mli", "*.mll", "*.mly"]),
("org", &["*.org", "*.org_archive"]),
("pants", &["BUILD"]),
("pascal", &["*.pas", "*.dpr", "*.lpr", "*.pp", "*.inc"]),
("pdf", &["*.pdf"]),
("perl", &["*.perl", "*.pl", "*.PL", "*.plh", "*.plx", "*.pm", "*.t"]),
("php", &[
(&["nim"], &["*.nim", "*.nimf", "*.nimble", "*.nims"]),
(&["nix"], &["*.nix"]),
(&["objc"], &["*.h", "*.m"]),
(&["objcpp"], &["*.h", "*.mm"]),
(&["ocaml"], &["*.ml", "*.mli", "*.mll", "*.mly"]),
(&["org"], &["*.org", "*.org_archive"]),
(&["pants"], &["BUILD"]),
(&["pascal"], &["*.pas", "*.dpr", "*.lpr", "*.pp", "*.inc"]),
(&["pdf"], &["*.pdf"]),
(&["perl"], &["*.perl", "*.pl", "*.PL", "*.plh", "*.plx", "*.pm", "*.t"]),
(&["php"], &[
// note that PHP 6 doesn't exist
// See: https://wiki.php.net/rfc/php6
"*.php", "*.php3", "*.php4", "*.php5", "*.php7", "*.php8",
"*.pht", "*.phtml"
]),
("po", &["*.po"]),
("pod", &["*.pod"]),
("postscript", &["*.eps", "*.ps"]),
("protobuf", &["*.proto"]),
("ps", &["*.cdxml", "*.ps1", "*.ps1xml", "*.psd1", "*.psm1"]),
("puppet", &["*.epp", "*.erb", "*.pp", "*.rb"]),
("purs", &["*.purs"]),
("py", &["*.py", "*.pyi"]),
("qmake", &["*.pro", "*.pri", "*.prf"]),
("qml", &["*.qml"]),
("r", &["*.R", "*.r", "*.Rmd", "*.Rnw"]),
("racket", &["*.rkt"]),
("rdoc", &["*.rdoc"]),
("readme", &["README*", "*README"]),
("reasonml", &["*.re", "*.rei"]),
("red", &["*.r", "*.red", "*.reds"]),
("rescript", &["*.res", "*.resi"]),
("robot", &["*.robot"]),
("rst", &["*.rst"]),
("ruby", &[
(&["po"], &["*.po"]),
(&["pod"], &["*.pod"]),
(&["postscript"], &["*.eps", "*.ps"]),
(&["protobuf"], &["*.proto"]),
(&["ps"], &["*.cdxml", "*.ps1", "*.ps1xml", "*.psd1", "*.psm1"]),
(&["puppet"], &["*.epp", "*.erb", "*.pp", "*.rb"]),
(&["purs"], &["*.purs"]),
(&["py", "python"], &["*.py", "*.pyi"]),
(&["qmake"], &["*.pro", "*.pri", "*.prf"]),
(&["qml"], &["*.qml"]),
(&["r"], &["*.R", "*.r", "*.Rmd", "*.Rnw"]),
(&["racket"], &["*.rkt"]),
(&["raku"], &[
"*.raku", "*.rakumod", "*.rakudoc", "*.rakutest",
"*.p6", "*.pl6", "*.pm6"
]),
(&["rdoc"], &["*.rdoc"]),
(&["readme"], &["README*", "*README"]),
(&["reasonml"], &["*.re", "*.rei"]),
(&["red"], &["*.r", "*.red", "*.reds"]),
(&["rescript"], &["*.res", "*.resi"]),
(&["robot"], &["*.robot"]),
(&["rst"], &["*.rst"]),
(&["ruby"], &[
// Idiomatic files
"config.ru", "Gemfile", ".irbrc", "Rakefile",
// Extensions
"*.gemspec", "*.rb", "*.rbw"
]),
("rust", &["*.rs"]),
("sass", &["*.sass", "*.scss"]),
("scala", &["*.scala", "*.sbt"]),
("sh", &[
(&["rust"], &["*.rs"]),
(&["sass"], &["*.sass", "*.scss"]),
(&["scala"], &["*.scala", "*.sbt"]),
(&["sh"], &[
// Portable/misc. init files
".login", ".logout", ".profile", "profile",
// bash-specific init files
@@ -230,64 +249,66 @@ pub const DEFAULT_TYPES: &[(&str, &[&str])] = &[
// Extensions
"*.bash", "*.csh", "*.ksh", "*.sh", "*.tcsh", "*.zsh",
]),
("slim", &["*.skim", "*.slim", "*.slime"]),
("smarty", &["*.tpl"]),
("sml", &["*.sml", "*.sig"]),
("solidity", &["*.sol"]),
("soy", &["*.soy"]),
("spark", &["*.spark"]),
("spec", &["*.spec"]),
("sql", &["*.sql", "*.psql"]),
("stylus", &["*.styl"]),
("sv", &["*.v", "*.vg", "*.sv", "*.svh", "*.h"]),
("svg", &["*.svg"]),
("swift", &["*.swift"]),
("swig", &["*.def", "*.i"]),
("systemd", &[
(&["slim"], &["*.skim", "*.slim", "*.slime"]),
(&["smarty"], &["*.tpl"]),
(&["sml"], &["*.sml", "*.sig"]),
(&["solidity"], &["*.sol"]),
(&["soy"], &["*.soy"]),
(&["spark"], &["*.spark"]),
(&["spec"], &["*.spec"]),
(&["sql"], &["*.sql", "*.psql"]),
(&["stylus"], &["*.styl"]),
(&["sv"], &["*.v", "*.vg", "*.sv", "*.svh", "*.h"]),
(&["svg"], &["*.svg"]),
(&["swift"], &["*.swift"]),
(&["swig"], &["*.def", "*.i"]),
(&["systemd"], &[
"*.automount", "*.conf", "*.device", "*.link", "*.mount", "*.path",
"*.scope", "*.service", "*.slice", "*.socket", "*.swap", "*.target",
"*.timer",
]),
("taskpaper", &["*.taskpaper"]),
("tcl", &["*.tcl"]),
("tex", &["*.tex", "*.ltx", "*.cls", "*.sty", "*.bib", "*.dtx", "*.ins"]),
("texinfo", &["*.texi"]),
("textile", &["*.textile"]),
("tf", &[
(&["taskpaper"], &["*.taskpaper"]),
(&["tcl"], &["*.tcl"]),
(&["tex"], &["*.tex", "*.ltx", "*.cls", "*.sty", "*.bib", "*.dtx", "*.ins"]),
(&["texinfo"], &["*.texi"]),
(&["textile"], &["*.textile"]),
(&["tf"], &[
"*.tf", "*.auto.tfvars", "terraform.tfvars", "*.tf.json",
"*.auto.tfvars.json", "terraform.tfvars.json", "*.terraformrc",
"terraform.rc", "*.tfrc", "*.terraform.lock.hcl",
]),
("thrift", &["*.thrift"]),
("toml", &["*.toml", "Cargo.lock"]),
("ts", &["*.ts", "*.tsx", "*.cts", "*.mts"]),
("twig", &["*.twig"]),
("txt", &["*.txt"]),
("typoscript", &["*.typoscript", "*.ts"]),
("vala", &["*.vala"]),
("vb", &["*.vb"]),
("vcl", &["*.vcl"]),
("verilog", &["*.v", "*.vh", "*.sv", "*.svh"]),
("vhdl", &["*.vhd", "*.vhdl"]),
("vim", &[
(&["thrift"], &["*.thrift"]),
(&["toml"], &["*.toml", "Cargo.lock"]),
(&["ts", "typescript"], &["*.ts", "*.tsx", "*.cts", "*.mts"]),
(&["twig"], &["*.twig"]),
(&["txt"], &["*.txt"]),
(&["typoscript"], &["*.typoscript", "*.ts"]),
(&["usd"], &["*.usd", "*.usda", "*.usdc"]),
(&["v"], &["*.v"]),
(&["vala"], &["*.vala"]),
(&["vb"], &["*.vb"]),
(&["vcl"], &["*.vcl"]),
(&["verilog"], &["*.v", "*.vh", "*.sv", "*.svh"]),
(&["vhdl"], &["*.vhd", "*.vhdl"]),
(&["vim"], &[
"*.vim", ".vimrc", ".gvimrc", "vimrc", "gvimrc", "_vimrc", "_gvimrc",
]),
("vimscript", &[
(&["vimscript"], &[
"*.vim", ".vimrc", ".gvimrc", "vimrc", "gvimrc", "_vimrc", "_gvimrc",
]),
("webidl", &["*.idl", "*.webidl", "*.widl"]),
("wiki", &["*.mediawiki", "*.wiki"]),
("xml", &[
(&["webidl"], &["*.idl", "*.webidl", "*.widl"]),
(&["wiki"], &["*.mediawiki", "*.wiki"]),
(&["xml"], &[
"*.xml", "*.xml.dist", "*.dtd", "*.xsl", "*.xslt", "*.xsd", "*.xjb",
"*.rng", "*.sch", "*.xhtml",
]),
("xz", &["*.xz", "*.txz"]),
("yacc", &["*.y"]),
("yaml", &["*.yaml", "*.yml"]),
("yang", &["*.yang"]),
("z", &["*.Z"]),
("zig", &["*.zig"]),
("zsh", &[
(&["xz"], &["*.xz", "*.txz"]),
(&["yacc"], &["*.y"]),
(&["yaml"], &["*.yaml", "*.yml"]),
(&["yang"], &["*.yang"]),
(&["z"], &["*.Z"]),
(&["zig"], &["*.zig"]),
(&["zsh"], &[
".zshenv", "zshenv",
".zlogin", "zlogin",
".zlogout", "zlogout",
@@ -295,7 +316,7 @@ pub const DEFAULT_TYPES: &[(&str, &[&str])] = &[
".zshrc", "zshrc",
"*.zsh",
]),
("zstd", &["*.zst", "*.zstd"]),
(&["zstd"], &["*.zst", "*.zstd"]),
];
#[cfg(test)]
@@ -304,10 +325,8 @@ mod tests {
#[test]
fn default_types_are_sorted() {
let mut names = DEFAULT_TYPES.iter().map(|(name, _exts)| name);
let mut names = DEFAULT_TYPES.iter().map(|(aliases, _)| aliases[0]);
let Some(mut previous_name) = names.next() else { return; };
for name in names {
assert!(
name > previous_name,
@@ -315,7 +334,6 @@ mod tests {
name,
previous_name
);
previous_name = name;
}
}

11
crates/ignore/src/gitignore.rs
View File

@@ -533,7 +533,7 @@ impl GitignoreBuilder {
/// Return the file path of the current environment's global gitignore file.
///
/// Note that the file path returned may not exist.
fn gitconfig_excludes_path() -> Option<PathBuf> {
pub fn gitconfig_excludes_path() -> Option<PathBuf> {
// git supports $HOME/.gitconfig and $XDG_CONFIG_HOME/git/config. Notably,
// both can be active at the same time, where $HOME/.gitconfig takes
// precedent. So if $HOME/.gitconfig defines a `core.excludesFile`, then
@@ -596,8 +596,13 @@ fn parse_excludes_file(data: &[u8]) -> Option<PathBuf> {
// probably works in more circumstances. I guess we would ideally have
// a full INI parser. Yuck.
lazy_static::lazy_static! {
static ref RE: Regex =
Regex::new(r"(?im)^\s*excludesfile\s*=\s*(.+)\s*$").unwrap();
static ref RE: Regex = Regex::new(
r"(?xim-u)
^[[:space:]]*excludesfile[[:space:]]*
=
[[:space:]]*(.+)[[:space:]]*$
"
).unwrap();
};
let caps = match RE.captures(data) {
None => return None,

16
crates/ignore/src/types.rs
View File

@@ -488,9 +488,11 @@ impl TypesBuilder {
/// Add a set of default file type definitions.
pub fn add_defaults(&mut self) -> &mut TypesBuilder {
static MSG: &'static str = "adding a default type should never fail";
for &(name, exts) in DEFAULT_TYPES {
for ext in exts {
self.add(name, ext).expect(MSG);
for &(names, exts) in DEFAULT_TYPES {
for name in names {
for ext in exts {
self.add(name, ext).expect(MSG);
}
}
}
self
@@ -537,6 +539,8 @@ mod tests {
"html:*.htm",
"rust:*.rs",
"js:*.js",
"py:*.py",
"python:*.py",
"foo:*.{rs,foo}",
"combo:include:html,rust",
]
@@ -551,6 +555,8 @@ mod tests {
matched!(match7, types(), vec!["foo"], vec!["rust"], "main.foo");
matched!(match8, types(), vec!["combo"], vec![], "index.html");
matched!(match9, types(), vec!["combo"], vec![], "lib.rs");
matched!(match10, types(), vec!["py"], vec![], "main.py");
matched!(match11, types(), vec!["python"], vec![], "main.py");
matched!(not, matchnot1, types(), vec!["rust"], vec![], "index.html");
matched!(not, matchnot2, types(), vec![], vec!["rust"], "main.rs");
@@ -558,6 +564,8 @@ mod tests {
matched!(not, matchnot4, types(), vec!["rust"], vec!["foo"], "main.rs");
matched!(not, matchnot5, types(), vec!["rust"], vec!["foo"], "main.foo");
matched!(not, matchnot6, types(), vec!["combo"], vec![], "leftpad.js");
matched!(not, matchnot7, types(), vec!["py"], vec![], "index.html");
matched!(not, matchnot8, types(), vec!["python"], vec![], "doc.md");
#[test]
fn test_invalid_defs() {
@@ -569,7 +577,7 @@ mod tests {
let original_defs = btypes.definitions();
let bad_defs = vec![
// Reference to type that does not exist
"combo:include:html,python",
"combo:include:html,qwerty",
// Bad format
"combo:foobar:html,rust",
"",

2
crates/ignore/src/walk.rs
View File

@@ -1681,7 +1681,7 @@ impl<'s> Worker<'s> {
stack.pop()
}
/// Signal that work has been received.
/// Signal that work has been finished.
fn work_done(&self) {
self.num_pending.fetch_sub(1, Ordering::SeqCst);
}

2
crates/regex/src/literal.rs
View File

@@ -91,7 +91,7 @@ impl InnerLiterals {
InnerLiterals { seq: Seq::infinite() }
}
/// If it is deemed advantageuous to do so (via various suspicious
/// If it is deemed advantageous 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

49
crates/searcher/src/searcher/core.rs
View File

@@ -10,6 +10,12 @@ use crate::sink::{
};
use grep_matcher::{LineMatchKind, Matcher};
enum FastMatchResult {
Continue,
Stop,
SwitchToSlow,
}
#[derive(Debug)]
pub struct Core<'s, M: 's, S> {
config: &'s Config,
@@ -25,6 +31,7 @@ pub struct Core<'s, M: 's, S> {
last_line_visited: usize,
after_context_left: usize,
has_sunk: bool,
has_matched: bool,
}
impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
@@ -50,6 +57,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
last_line_visited: 0,
after_context_left: 0,
has_sunk: false,
has_matched: false,
};
if !core.searcher.multi_line_with_matcher(&core.matcher) {
if core.is_line_by_line_fast() {
@@ -109,7 +117,11 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
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)
match self.match_by_line_fast(buf)? {
FastMatchResult::SwitchToSlow => self.match_by_line_slow(buf),
FastMatchResult::Continue => Ok(true),
FastMatchResult::Stop => Ok(false),
}
} else {
self.match_by_line_slow(buf)
}
@@ -270,7 +282,9 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
}
};
self.set_pos(line.end());
if matched != self.config.invert_match {
let success = matched != self.config.invert_match;
if success {
self.has_matched = true;
if !self.before_context_by_line(buf, line.start())? {
return Ok(false);
}
@@ -286,40 +300,51 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
return Ok(false);
}
}
if self.config.stop_on_nonmatch && !success && self.has_matched {
return Ok(false);
}
}
Ok(true)
}
fn match_by_line_fast(&mut self, buf: &[u8]) -> Result<bool, S::Error> {
debug_assert!(!self.config.passthru);
fn match_by_line_fast(
&mut self,
buf: &[u8],
) -> Result<FastMatchResult, S::Error> {
use FastMatchResult::*;
debug_assert!(!self.config.passthru);
while !buf[self.pos()..].is_empty() {
if self.config.stop_on_nonmatch && self.has_matched {
return Ok(SwitchToSlow);
}
if self.config.invert_match {
if !self.match_by_line_fast_invert(buf)? {
return Ok(false);
return Ok(Stop);
}
} else if let Some(line) = self.find_by_line_fast(buf)? {
self.has_matched = true;
if self.config.max_context() > 0 {
if !self.after_context_by_line(buf, line.start())? {
return Ok(false);
return Ok(Stop);
}
if !self.before_context_by_line(buf, line.start())? {
return Ok(false);
return Ok(Stop);
}
}
self.set_pos(line.end());
if !self.sink_matched(buf, &line)? {
return Ok(false);
return Ok(Stop);
}
} else {
break;
}
}
if !self.after_context_by_line(buf, buf.len())? {
return Ok(false);
return Ok(Stop);
}
self.set_pos(buf.len());
Ok(true)
Ok(Continue)
}
#[inline(always)]
@@ -344,6 +369,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
if invert_match.is_empty() {
return Ok(true);
}
self.has_matched = true;
if !self.after_context_by_line(buf, invert_match.start())? {
return Ok(false);
}
@@ -577,6 +603,9 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
if self.config.passthru {
return false;
}
if self.config.stop_on_nonmatch && self.has_matched {
return false;
}
if let Some(line_term) = self.matcher.line_terminator() {
if line_term == self.config.line_term {
return true;

24
crates/searcher/src/searcher/mod.rs
View File

@@ -173,6 +173,9 @@ pub struct Config {
encoding: Option<Encoding>,
/// Whether to do automatic transcoding based on a BOM or not.
bom_sniffing: bool,
/// Whether to stop searching when a non-matching line is found after a
/// matching line.
stop_on_nonmatch: bool,
}
impl Default for Config {
@@ -190,6 +193,7 @@ impl Default for Config {
multi_line: false,
encoding: None,
bom_sniffing: true,
stop_on_nonmatch: false,
}
}
}
@@ -555,6 +559,19 @@ impl SearcherBuilder {
self.config.bom_sniffing = yes;
self
}
/// Stop searching a file when a non-matching line is found after a
/// matching line.
///
/// This is useful for searching sorted files where it is expected that all
/// the matches will be on adjacent lines.
pub fn stop_on_nonmatch(
&mut self,
stop_on_nonmatch: bool,
) -> &mut SearcherBuilder {
self.config.stop_on_nonmatch = stop_on_nonmatch;
self
}
}
/// A searcher executes searches over a haystack and writes results to a caller
@@ -838,6 +855,13 @@ impl Searcher {
self.config.multi_line
}
/// Returns true if and only if this searcher is configured to stop when in
/// finds a non-matching line after a matching one.
#[inline]
pub fn stop_on_nonmatch(&self) -> bool {
self.config.stop_on_nonmatch
}
/// Returns true if and only if this searcher will choose a multi-line
/// strategy given the provided matcher.
///

10
doc/rg.1.txt.tpl
View File

@@ -232,6 +232,16 @@ would behave identically to the following command
rg --glob '!.git' foo
The bottom line is that every shell argument needs to be on its own line. So
for example, a config file containing
-j 4
is probably not doing what you intend. Instead, you want
-j
4
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.

28
pkg/windows/Manifest.xml Normal file
View File

@@ -0,0 +1,28 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<!--
This is a Windows application manifest file.
See: https://docs.microsoft.com/en-us/windows/win32/sbscs/application-manifests
-->
<assembly xmlns="urn:schemas-microsoft-com:asm.v1" manifestVersion="1.0" xmlns:asmv3="urn:schemas-microsoft-com:asm.v3">
<!-- Versions rustc supports as compiler hosts -->
<compatibility xmlns="urn:schemas-microsoft-com:compatibility.v1">
<application>
<!-- Windows 7 --><supportedOS Id="{35138b9a-5d96-4fbd-8e2d-a2440225f93a}"/>
<!-- Windows 8 --><supportedOS Id="{4a2f28e3-53b9-4441-ba9c-d69d4a4a6e38}"/>
<!-- Windows 8.1 --><supportedOS Id="{1f676c76-80e1-4239-95bb-83d0f6d0da78}"/>
<!-- Windows 10 and 11 --><supportedOS Id="{8e0f7a12-bfb3-4fe8-b9a5-48fd50a15a9a}"/>
</application>
</compatibility>
<!-- Use UTF-8 code page -->
<asmv3:application>
<asmv3:windowsSettings xmlns="http://schemas.microsoft.com/SMI/2019/WindowsSettings">
<activeCodePage>UTF-8</activeCodePage>
</asmv3:windowsSettings>
</asmv3:application>
<!-- Remove (most) legacy path limits -->
<asmv3:application>
<asmv3:windowsSettings xmlns:ws2="http://schemas.microsoft.com/SMI/2016/WindowsSettings">
<ws2:longPathAware>true</ws2:longPathAware>
</asmv3:windowsSettings>
</asmv3:application>
</assembly>

15
pkg/windows/README.md Normal file
View File

@@ -0,0 +1,15 @@
This directory contains a Windows manifest for various Windows-specific
settings.
The main thing we enable here is [`longPathAware`], which permits paths of the
form `C:\` to be longer than 260 characters.
The approach taken here was modeled off of a [similar change for `rustc`][rustc pr].
In particular, this manifest gets linked into the final binary. Those linker
arguments are applied in `build.rs`.
This currently only applies to MSVC builds. If there's an easy way to make this
apply to GNU builds as well, then patches are welcome.
[`longPathAware`]: https://learn.microsoft.com/en-us/windows/win32/sbscs/application-manifests#longpathaware
[rustc pr]: https://github.com/rust-lang/rust/pull/96737

46
tests/feature.rs
View File

@@ -787,6 +787,28 @@ rgtest!(f1466_no_ignore_files, |dir: Dir, mut cmd: TestCommand| {
eqnice!("foo\n", cmd.arg("-u").stdout());
});
// See: https://github.com/BurntSushi/ripgrep/pull/2361
rgtest!(f2361_sort_nested_files, |dir: Dir, mut cmd: TestCommand| {
use std::{thread::sleep, time::Duration};
dir.create("foo", "1");
sleep(Duration::from_millis(100));
dir.create_dir("dir");
sleep(Duration::from_millis(100));
dir.create(dir.path().join("dir").join("bar"), "1");
cmd.arg("--sort").arg("accessed").arg("--files");
eqnice!("foo\ndir/bar\n", cmd.stdout());
dir.create("foo", "2");
sleep(Duration::from_millis(100));
dir.create(dir.path().join("dir").join("bar"), "2");
sleep(Duration::from_millis(100));
cmd.arg("--sort").arg("accessed").arg("--files");
eqnice!("foo\ndir/bar\n", cmd.stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/1404
rgtest!(f1404_nothing_searched_warning, |dir: Dir, mut cmd: TestCommand| {
dir.create(".ignore", "ignored-dir/**");
@@ -921,6 +943,23 @@ rgtest!(f1842_field_match_separator, |dir: Dir, _: TestCommand| {
eqnice!(expected, dir.command().args(&args).stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/2288
rgtest!(f2288_context_partial_override, |dir: Dir, mut cmd: TestCommand| {
dir.create("test", "1\n2\n3\n4\n5\n6\n7\n8\n9\n");
cmd.args(&["-C1", "-A2", "5", "test"]);
eqnice!("4\n5\n6\n7\n", cmd.stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/2288
rgtest!(
f2288_context_partial_override_rev,
|dir: Dir, mut cmd: TestCommand| {
dir.create("test", "1\n2\n3\n4\n5\n6\n7\n8\n9\n");
cmd.args(&["-A2", "-C1", "5", "test"]);
eqnice!("4\n5\n6\n7\n", cmd.stdout());
}
);
rgtest!(no_context_sep, |dir: Dir, mut cmd: TestCommand| {
dir.create("test", "foo\nctx\nbar\nctx\nfoo\nctx");
cmd.args(&["-A1", "--no-context-separator", "foo", "test"]);
@@ -975,3 +1014,10 @@ rgtest!(no_unicode, |dir: Dir, mut cmd: TestCommand| {
dir.create("test", "δ");
cmd.arg("-i").arg("--no-unicode").arg("Δ").assert_err();
});
// See: https://github.com/BurntSushi/ripgrep/issues/1790
rgtest!(stop_on_nonmatch, |dir: Dir, mut cmd: TestCommand| {
dir.create("test", "line1\nline2\nline3\nline4\nline5");
cmd.args(&["--stop-on-nonmatch", "[235]"]);
eqnice!("test:line2\ntest:line3\n", cmd.stdout());
});

45
tests/misc.rs
View File

@@ -1065,3 +1065,48 @@ rgtest!(type_list, |_: Dir, mut cmd: TestCommand| {
// This can change over time, so just make sure we print something.
assert!(!cmd.stdout().is_empty());
});
// The following series of tests seeks to test all permutations of ripgrep's
// sorted queries.
//
// They all rely on this setup function, which sets up this particular file
// structure with a particular creation order:
// ├── a # 1
// ├── b # 4
// └── dir # 2
// ├── c # 3
// └── d # 5
//
// This order is important when sorting them by system time-stamps.
fn sort_setup(dir: Dir) {
use std::{thread::sleep, time::Duration};
let sub_dir = dir.path().join("dir");
dir.create("a", "test");
sleep(Duration::from_millis(100));
dir.create_dir(&sub_dir);
sleep(Duration::from_millis(100));
dir.create(sub_dir.join("c"), "test");
sleep(Duration::from_millis(100));
dir.create("b", "test");
sleep(Duration::from_millis(100));
dir.create(sub_dir.join("d"), "test");
}
rgtest!(sort_files, |dir: Dir, mut cmd: TestCommand| {
sort_setup(dir);
let expected = "a:test\nb:test\ndir/c:test\ndir/d:test\n";
eqnice!(expected, cmd.args(["--sort", "path", "test"]).stdout());
});
rgtest!(sort_accessed, |dir: Dir, mut cmd: TestCommand| {
sort_setup(dir);
let expected = "a:test\ndir/c:test\nb:test\ndir/d:test\n";
eqnice!(expected, cmd.args(["--sort", "accessed", "test"]).stdout());
});
rgtest!(sortr_accessed, |dir: Dir, mut cmd: TestCommand| {
sort_setup(dir);
let expected = "dir/d:test\nb:test\ndir/c:test\na:test\n";
eqnice!(expected, cmd.args(["--sortr", "accessed", "test"]).stdout());
});

47
tests/regression.rs
View File

@@ -1090,6 +1090,19 @@ b=one
eqnice!(expected, cmd.stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/2198
rgtest!(r2198, |dir: Dir, mut cmd: TestCommand| {
dir.create(".ignore", "a");
dir.create(".rgignore", "b");
dir.create("a", "");
dir.create("b", "");
dir.create("c", "");
cmd.arg("--files").arg("--sort").arg("path");
eqnice!("c\n", cmd.stdout());
eqnice!("a\nb\nc\n", cmd.arg("--no-ignore-dot").stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/2208
rgtest!(r2208, |dir: Dir, mut cmd: TestCommand| {
dir.create("test", "# Compile requirements.txt files from all found or specified requirements.in files (compile).
@@ -1126,3 +1139,37 @@ rgtest!(r2236, |dir: Dir, mut cmd: TestCommand| {
dir.create("foo/bar", "test\n");
cmd.args(&["test"]).assert_err();
});
// See: https://github.com/BurntSushi/ripgrep/issues/2480
rgtest!(r2480, |dir: Dir, mut cmd: TestCommand| {
dir.create("file", "FooBar\n");
// no regression in empty pattern behavior
cmd.args(&["-e", "", "file"]);
eqnice!("FooBar\n", cmd.stdout());
// no regression in single pattern behavior
let mut cmd = dir.command();
cmd.args(&["-e", ")(", "file"]);
eqnice!("FooBar\n", cmd.stdout());
// no regression in multiple patterns behavior
let mut cmd = dir.command();
cmd.args(&["--only-matching", "-e", "Foo", "-e", "Bar", "file"]);
eqnice!("Foo\nBar\n", cmd.stdout());
// no regression in capture groups behavior
let mut cmd = dir.command();
cmd.args(&["-e", "Fo(oB)a(r)", "--replace", "${0}_${1}_${2}${3}", "file"]);
eqnice!("FooBar_oB_r\n", cmd.stdout()); // note: ${3} expected to be empty
// flag does not leak into next pattern on match
let mut cmd = dir.command();
cmd.args(&["--only-matching", "-e", "(?i)foo", "-e", "bar", "file"]);
eqnice!("Foo\n", cmd.stdout());
// flag does not leak into next pattern on mismatch
let mut cmd = dir.command();
cmd.args(&["--only-matching", "-e", "(?i)notfoo", "-e", "bar", "file"]);
cmd.assert_err();
});