twin/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-08-20 22:53:48 -07:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

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

147 Commits
14.0.3 ... ag/rollup

Author SHA1 Message Date
Andrew Gallant
13d6c7b1c1 doc: actually fix deb download link 
Amazingly, there were about a dozen PRs fixing this same thing, and I
happened to choose the one that didn't actually fix the URL completely.

Apparently some users found this "interesting":
https://github.com/BurntSushi/ripgrep/pull/3065#issuecomment-3204275122
 2025-08-20 07:04:36 -04:00
wackget
2da6e6d15b doc: update installation instructions for RHEL/CentOS/Rocky Linux 9 
Closes #2924, Closes #2981, Closes #3124
 2025-08-19 21:53:04 -04:00
emrebengue
aacc7c8a21 colors: add highlight type support for matching lines 
This lets users highlight non-matching text in matching lines.

Closes #3024, Closes #3107
 2025-08-19 21:42:40 -04:00
Andrew Gallant
3fc1f5f15f printer: fix handling of has_match for summary printer 
Previously, `Quiet` mode in the summary printer always acted like
"print matching paths," except without the printing. This happened even
if we wanted to "print non-matching paths." Since this only afflicted
quiet mode, this had the effect of flipping the exit status when
`--files-without-match --quiet` was used.

Fixes #3108, Ref #3118
 2025-08-19 21:09:14 -04:00
Ben Heidemann
d969ebc1e5 globset: make GlobSet::new public 
For users of globset who already have a `Vec<Glob>` (or similar),
the current API requires them to iterate over their `Vec<Glob>`,
calling `GlobSetBuilder::add` for each `Glob`, thus constructing a new
`Vec<Glob>` internal to the GlobSetBuilder. This makes the consuming
code unnecessarily verbose. (There is unlikely to be any meaningful
performance impact of this, however, since the cost of allocating a new
`Vec` is likely marginal compared to the cost of glob compilation.)

Instead of taking a `&[Glob]`, we accept an iterator of anything that
can be borrowed as a `&Glob`. This required some light refactoring of
the constructor, but nothing onerous.

Closes #3066
 2025-08-19 20:15:25 -04:00
David Tolnay
5a15029c04 globset: make GlobSet::empty const 
Closes #3098
 2025-08-19 20:01:12 -04:00
Lucas Garron
1ef939442f doc: clarify that .git is covered by --hidden and not --ignore-vcs 
Fixes #3121, Closes #3122
 2025-08-19 19:52:40 -04:00
Vishva Natarajan
2d5fb3a995 tests: increase sleep duration for sort file metadata tests on Windows AArch64 
Use `cfg!` to assign a 1000ms delay only on Windows Aarch64 targets.

This was done because it has been observed to be necessary on this
platform. The conditional logic is used because 1s is quite long to
wait on every other more sensible platform.

Closes #3071, Closes #3072
 2025-08-19 17:20:13 -04:00
Porkepix
1b1886a1fe ignore/types: include missing files for the tf type 
Existing matches were too restrictives, so we simplify those to every
type of tfvars file we can encounter.

Closes #3117
 2025-08-19 16:43:14 -04:00
Tomek
064e9ee30e ignore/types: add gleam 
[Gleam] is a general-purpose, concurrent, functional high-level
programming language that compiles to Erlang or JavaScript source code.

Closes #3105

[Gleam]: https://gleam.run/
 2025-08-19 16:39:33 -04:00
Andrew McNulty
7d2b87deea ignore/types: add LLVM to default types 
This PR adds llvm to the list of default types, matching files with
extension ll which is used widely for the textual form of LLVM's
Intermediate Representation.

Ref: https://llvm.org/docs/LangRef.html

Closes #3079
 2025-08-19 16:39:08 -04:00
James Moberg
8ff66992e1 ignore/types: add ColdFusion and BoxLang 
Closes #3090
 2025-08-19 16:36:45 -04:00
Lilian A. Moraru
0db9903c8d ignore/types: add .env to sh file type 
`.env` or "dotenv" is used quite often in cross-compilation/embedded
development environments to load environment variables, define shell
functions or even to execute shell commands. Just like `.zshenv` in
this list, I think `.env` should also be added here.

Closes #3063
 2025-08-19 16:29:36 -04:00
kevichi7
8ab9b6aba8 build: emit warning if git is missing during build 
Closes #3057
 2025-08-19 16:25:16 -04:00
Andrew Gallant
21261b8c4d doc: remove CentOS/RHEL installation instructions 
These distros, or their Docker images, appear FUBAR. The UX is so poor
that I cannot verify the correct installation instructions. So I'm
removing them.

Ref https://github.com/BurntSushi/ripgrep/pull/2981#issuecomment-3202063173

Closes #2981, Closes #3124
 2025-08-19 16:07:55 -04:00
Andrew Gallant
8c2014fe5c globset: fix bug where trailing . in file name was incorrectly handled 
I'm not sure why I did this, but I think I was trying to imitate the
contract of [`std::path::Path::file_name`]:

> Returns None if the path terminates in `..`.

But the status quo clearly did not implement this. And as a result, if
you have a glob that ends in a `.`, it was instead treated as the empty
string (which only matches the empty string).

We fix this by implementing the semantic from the standard library
correctly.

Fixes #2990

[`std::path::Path::file_name`]: https://doc.rust-lang.org/std/path/struct.Path.html#method.file_name
 2025-08-17 17:37:28 -04:00
bbb651
f6d46006d1 ignore/types: add scdoc 
Ref https://sr.ht/~sircmpwn/scdoc/

Closes #3007
 2025-08-17 17:37:28 -04:00
Nadir Ishiguro
1efa5c1e18 doc: fix nixpkgs link 
Closes #3006
 2025-08-17 17:37:28 -04:00
Andrew Gallant
1d1ca1aa5d test: check binary file detection when using memory maps 
This resolves a TODO comment I wrote a while back.

Memory maps behave a little differently in terms of detecting binary
data, so the tests have somewhat different results than the tests that
disable memory maps.

Closes #3002
 2025-08-17 17:37:27 -04:00
Alexander Weiss
6fb52964fc globset: add Candidate::from_bytes constructor 
This is already technically possible to do on Unix by going through
`OsStr` and `&[u8]` conversions. This just makes it easier to do in all
circumstances and is reasonable to intentionally support.

Closes #2954, Closes #2955
 2025-08-17 14:15:12 -04:00
Andrew Gallant
48bf394585 stats: fix case where "bytes searched" could be wrong 
Specifically, if the search was instructed to quit early, we might not
have correctly marked the number of bytes consumed.

I don't think this bug occurs when memory maps are used to read the
haystack.

Closes #2944
 2025-08-17 10:47:28 -04:00
Thomas Weißschuh
e99de53e31 ignore/types: add Kconfig 
Kconfig files are used to represent the configuration database of
Kbuild build system. Kbuild is developed as part of the Linux kernel.
There are numerous other users including OpenWrt and U-Boot.

Ref: https://docs.kernel.org/kbuild/index.html

Closes #2942
 2025-08-17 10:35:17 -04:00
ChristopherYoung
83ab0a6b53 printer: slightly simplify code 
I'm not sure why it was written with `map` previously. It almost looks
like I was trying to make it deref, but apparently that isn't needed.

Closes #2941
 2025-08-17 10:32:59 -04:00
Dmitry Gerasimov
c3828cb508 ignore/types: add *.dtso to devicetree type 
`dtso` files became recognized as devicetree a
couple of years ago with the following commit:
363547d219

Closes #2938
 2025-08-17 09:38:12 -04:00
Martin Pool
27f88139fa ignore/doc: explain that require_git(false) will ascend above git roots 
This should hopefully help avoid confusion about #2812 as encountered
in https://github.com/sourcefrog/cargo-mutants/issues/450.

Closes #2937
 2025-08-17 09:37:53 -04:00
Andrew Gallant
ca0aacd674 globset: remove __Nonexhaustive work-around 
This existed before the `#[non_exhaustive]` attribute was a thing. Since
it was not part of the API of the crate, it is not a semver incompatible
change.
 2025-08-17 09:37:53 -04:00
Luke Sandberg
43eff4397f globset: support nested alternates 
For example, `**/{node_modules/**/*/{ts,js},crates/**/*.{rs,toml}`.

I originally didn't add this I think for implementation simplicity, but
it turns out that it really isn't much work to do. There might have also
been some odd behavior in the regex engine for dealing with empty
alternates, but that has all been long fixed.

Closes #3048, Closes #3112
 2025-08-17 09:37:50 -04:00
Colin Heffernan
2d763a9a1b ignore/types: add *.svelte.ts to Svelte file type glob 
I was somewhat unsure about adding this, since `.svelte.ts` seems
primarily like a TypeScript file and it could be surprising to show up
in a search for Svelte files. In particular, ripgrep doesn't know how to
only search the Svelte stuff inside of a `.svelte.ts` file, so you could
end up with lots of false positives.

However, I was swayed[1] by the argument that the extension does
actually include `svelte` in it, so maybe this is fine. Please open an
issue if this change ends up being too annoying for most users.

Closes #2874, Closes #2909

[1]: https://github.com/BurntSushi/ripgrep/issues/2874#issuecomment-3126892931
 2025-07-28 07:58:09 -04:00
Andrew Gallant
afc820c9e9 cli: make rg -vf file behave sensibly 
Previously, when `file` is empty (literally empty, as in, zero byte),
`rg -f file` and `rg -vf file` would behave identically. This is odd
and also doesn't match how GNU grep behaves. It's also not logically
correct. An empty file means _zero_ patterns which is an empty set. An
empty set matches nothing. Inverting the empty set should result in
matching everything.

This was because of an errant optimization that lets ripgrep quit early
if it can statically detect that no matches are possible.

Moreover, there was *also* a bug in how we constructed the PCRE2 pattern
when there are zero patterns. PCRE2 doesn't have a concept of sets of
patterns (unlike the `regex` crate), so we need to fake it with an empty
character class.

Fixes #1332, Fixes #3001, Closes #3041
 2025-07-27 15:09:19 -04:00
Josh Cotton
b9f2da2782 ci: add aarch64 Windows 
This also adds a new release artifact for aarch64 Windows.

Closes #2943, Closes #3038
 2025-07-27 12:51:25 -04:00
Wilfred Hughes
823255b3fd doc: fix typo in FAQ 
Closes #3027
 2025-07-27 10:34:19 -04:00
squidfunk
fcfe98fe58 globset: compact Debug impl for GlobSetBuilder and Glob 
Ideally we'd have a compact impl for `GlobSet` too, but that's a lot
more work. In particular, the constituent types don't all store the
original pattern string, so that would need to be added.

Closes #3026
 2025-07-27 10:28:55 -04:00
Zach Ahn
0434b5034d ignore/types: add *.rake extension to list of Ruby file types 
This PR adds the .rake extension to the Ruby type. It's a pretty common
file extension in Rails apps—in my experience, the Rakefile is often
pretty empty and only sets some stuff up while most of the code lives
in various .rake files.

See: https://ruby.github.io/rake/doc/rakefile_rdoc.html#label-Multiple+Rake+Files

Closes #2921
 2025-07-26 11:55:30 -04:00
f3rn0s
b004eda8c8 ignore/types: add typst 
Closes #2914
 2025-07-26 11:54:01 -04:00
Hamir Mahal
f1b4b182f2 style: simplify string formatting 
Most of this code was written before this was supported by Rust.

Closes #2912
 2025-07-26 11:52:49 -04:00
Thayne McCombs
e169881a36 globset: add matches_all method 
This returns true if all globs in the set match the supplied file.

Fixes #2869, Closes #2900
 2025-07-26 11:44:51 -04:00
Aleksey Vasilenko
83a4af7cb8 deps: switch to tikv-jemallocator 
It is now a recommended crate for jemalloc and it contains an
[important fix for compilation on riscv64gc-unknown-linux-musl][fix],
I bumped into this when I was trying to
[build ripgrep on OpenWrt][openwrt].

Closes #2889

[fix]: https://github.com/tikv/jemallocator/pull/67
[openwrt]: https://github.com/openwrt/packages/pull/24961
 2025-07-26 11:41:17 -04:00
Stephan Badragan
cf91d6e67a printer: support -r/--replace with --json 
This adds a `replacement` field to each submatch object in the JSON
output. In effect, this extends the `-r/--replace` flag so that it works
with `--json`.

This adds a new field instead of replacing the match text (which is how
the standard printer works) for maximum flexibility. This way, consumers
of the JSON output can access the original match text (and always rely
on it corresponding to the original match text) while also getting the
replacement text without needing to do the replacement themselves.

Closes #1872, Closes #2883
 2025-07-26 11:35:08 -04:00
Melvin Wang
0904f55d3e ignore/types: include msbuild solution filters 
Closes #2871
 2025-07-26 10:50:59 -04:00
Lucas Trzesniewski
8ead46a3e5 printer: use std::path::absolute on Windows 
This specifically avoids touching the file system, which can lead to
fairly dramatic speed-ups in large repositories with lots of matches.

Closes #2865
 2025-07-26 10:49:52 -04:00
Alex Povel
d9744f3b03 ignore: improve multithreading heuristic 
This copies the one found in ripgrep.

See also:
71d71d2d98/crates/core/flags/hiargs.rs (L172)

Closes #2854, Closes #2856
 2025-07-26 10:42:29 -04:00
Thomas Otto
a6275648b3 ignore: don't process command line arguments in reverse order 
When searching in parallel with many more arguments than threads, the
first arguments are searched last -- unlike in the -j1 case.

This is unexpected for users who know about the parallel nature of rg
and think they can give the scheduler a hint by positioning larger
input files (L1, L2, ..) before smaller ones (█, ██). Instead, this can
result in sub-optimal thread usage and thus longer runtime (simplified
example with 2 threads):

 T1:  █ ██ █ █ █ █ ██ █ █ █ █ █ ██ ╠═════════════L1════════════╣
 T2:  █ █ ██ █ █ ██ █ █ █ ██ █ █ ╠═════L2════╣

                                       ┏━━━━┳━━━━┳━━━━┳━━━━┓
This is caused by assigning work to    ┃ T1 ┃ T2 ┃ T3 ┃ T4 ┃
 per-thread stacks in a round-robin    ┡━━━━╇━━━━╇━━━━╇━━━━┩
              manner, starting here  → │ L1 │ L2 │ L3 │ L4 │ ↵
                                       ├────├────┼────┼────┤
                                       │ s5 │ s6 │ s7 │ s8 │ ↵
                                       ├────┼────┼────┼────┤
                                       ╷ .. ╷ .. ╷ .. ╷ .. ╷
                                       ├────┼────┼────┼────┤
                                       │ st │ su │ sv │ sw │ ↵
                                       ├────┼────┼────┼────┘
                                       │ sx │ sy │ sz │
                                       └────┴────┴────┘
   and then processing them bottom-up:   ↥    ↥    ↥    ↥

                                       ╷ .. ╷ .. ╷ .. ╷ .. ╷
This patch reverses the input order    ├────┼────┼────┼────┤
so the two reversals cancel each other │ s7 │ s6 │ s5 │ L4 │ ↵
out. Now at least the first N          ├────┼────┼────┼────┘
arguments, N=number-of-threads, are    │ L3 │ L2 │ L1 │
processed before any others (then      └────┴────┴────┘
work-stealing may happen):

 T1:  ╠═════════════L1════════════╣ █ ██ █ █ █ █ █ █ ██
 T2:  ╠═════L2════╣ █ █ ██ █ █ ██ █ █ █ ██ █ █ ██ █ █ █

(With some more shuffling T1 could always be assigned L1 etc., but
that would mostly be for optics).

Closes #2849
 2025-07-26 10:42:29 -04:00
Christoph Badura
7fc48961ed ignore/types: add Makefile.* 
The *BSD build systems make use of "Makefile.inc" a lot. Make the
"make" type recognize this file by default. And more generally,
`Makefile.*` seems to be a convention, so just generalize it.

Closes #2846
 2025-07-26 10:42:28 -04:00
Matt Kulukundis
bd8a7ae793 ignore: support .jj as well as .git 
This makes it so the presence of `.jj` will cause ripgrep to treat it
as a VCS directory, just as if `.git` were present. This is useful for
ripgrep's default behavior when working with jj repositories that don't
have a `.git` but do have `.gitignore`. Namely, ripgrep requires the
presence of a VCS repository in order to respect `.gitignore`.

We don't handle clone-specific exclude rules for jj repositories without
`.git` though. It seems it isn't 100% set yet where we can find
those[1].

Closes #2842

[1]: https://github.com/BurntSushi/ripgrep/pull/2842#discussion_r2020076722
 2025-07-26 10:42:28 -04:00
Tor Shepherd
ff8afcf8aa color: add italic to style attributes 
Closes #2841
 2025-07-26 10:42:28 -04:00
robert-bryson
aebab44e3e core: add "total" to --stats output 
This makes it a little clearer. Apologies to anyone who is regex
matching on this output.

Closes #2797
 2025-07-26 10:42:28 -04:00
Stephen Albert-Moore
ca88b2fd95 ignore/gitignore: skip BOM at start of ignore file 
This matches Git's behavior.

Fixes #2177, Closes #2782
 2025-07-26 10:42:28 -04:00
Riccardo Attilio Galli
57e90533a0 searcher: add more tests for replace_bytes 
... and add a comment explaining an optimization.

Closes #2729
 2025-07-26 10:42:28 -04:00
Keith Smiley
fe07bd7669 ignore/types: detect WORKSPACE.bzlmod for bazel file type 
This file came alongside MODULE.bazel and I should have added it here
previously.

Closes #2726
 2025-07-26 10:42:28 -04:00
William Johnson
95979048c9 globset: add opt-in Arbitrary trait implementations 
This feature is mandatory when using `Glob` in fuzz testing.

Closes #2720
 2025-07-26 10:42:28 -04:00
Andrew Gallant
5548e538b1 tests: add test for filtering hidden files 
Note that this isn't a regression test. In particular, this didn't fail
with ripgrep 14.1.1. I couldn't figure out how to turn what the OP gave
me into a failing test.

With #829 fixed, if the OP can provide a better regression test, it
might make sense to re-investigate this.

Closes #2711
 2025-07-26 10:42:28 -04:00
ChristopherYoung
c2f1653ddd ignore: fix filtering searching subdir or .ignore in parent dir 
The previous code deleted too many parts of the path when constructing
the absolute path, resulting in a shortened final path. This patch
creates the correct absolute path by only removing the necessary parts.

Fixes #829, Fixes #2731, Fixes #2747, Fixes #2778, Fixes #2836, Fixes #2933
Closes #2933
 2025-07-26 10:42:27 -04:00
Jan Verbeek
78803979c5 complete/fish: Take RIPGREP_CONFIG_PATH into account 
The fish completions now also pay attention to the configuration file
to determine whether to suggest negation options and not just to the
current command line.

This doesn't cover all edge cases. For example the config file is
cached, and so changes may not take effect until the next shell
session. But the cases it doesn't cover are hopefully very rare.

Closes #2708
 2025-07-26 10:42:27 -04:00
wang384670111
85a86eba2b impl: switch most atomic ops to Relaxed ordering 
These all seem pretty straight-forward. Compared with #2706, I dropped
the changes to the atomic orderings used in `ignore` because I haven't
had time to think through that carefully. But the ops in this PR seem
fine.

Closes #2706
 2025-07-26 10:42:27 -04:00
Andrew Gallant
119a58a400 msrv: bump to Rust 1.88 
This is to prep for the next release. I don't know if the requirement
will actually be for Rust 1.88, but it is intended to support the latest
version of stable Rust.
 2025-07-26 10:41:47 -04:00
Andrew Gallant
3b7fd442a6 deps: update everything 
It looks like a new dependency on `getrandom` was added (which brings in
a few more dependencies itself) because of `jobserver`. Thankfully,
`jobserver` is only used when ripgrep's `pcre2` feature is enabled, so
this still keeps the default set of dependencies very small.
 2025-07-04 10:12:38 -04:00
wm
cbc598f245 doc: update version number in dpkg installation 
PR #3058
 2025-05-30 08:30:52 -04:00
dependabot[bot]
6dfaec03e8 deps: bump crossbeam-channel from 0.5.13 to 0.5.15 
Bumps [crossbeam-channel](https://github.com/crossbeam-rs/crossbeam) from 0.5.13 to 0.5.15.
- [Release notes](https://github.com/crossbeam-rs/crossbeam/releases)
- [Changelog](https://github.com/crossbeam-rs/crossbeam/blob/master/CHANGELOG.md)
- [Commits](https://github.com/crossbeam-rs/crossbeam/compare/crossbeam-channel-0.5.13...crossbeam-channel-0.5.15)

---
updated-dependencies:
- dependency-name: crossbeam-channel
  dependency-version: 0.5.15
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-04-10 10:55:32 -04:00
Pierre Rouleau
5fbc4fee64 ignore/types: fix Seed7 file extension 
PR #3023
 2025-04-07 10:53:32 -04:00
Pierre Rouleau
004370bd16 ignore/types: add support for Seed7 files 
For more info on the Seed7 programming Language see:

- on Wikipedia: https://en.wikipedia.org/wiki/Seed7
- Seed7 home:   https://seed7.sourceforge.net/
- Seed7 repo:   https://github.com/ThomasMertes/seed7

PR #3022
 2025-04-07 08:51:22 -04:00
Andrew Gallant
de4baa1002 globset-0.4.16 2025-02-27 12:46:58 -05:00
Andrew Gallant
163ac157d3 globset: escape { and } in escape 
This appears to be an oversight from when `escape` was
implemented in #2061.
 2025-02-27 12:46:48 -05:00
Andrew Gallant
e2362d4d51 searcher: add log message noting detected encoding 
This helps improve diagnostics. Otherwise it can be easy to miss that
ripgrep is doing transcoding.

Fixes #2979
 2025-01-25 14:27:00 -05:00
Kizhyk
d6b59feff8 github: update WASI compilation job 
Ref https://blog.rust-lang.org/2024/04/09/updates-to-rusts-wasi-targets.html

PR #2970
 2025-01-13 10:16:09 -05:00
Max Coplan
94305125ef zsh: support sourcing zsh completion dynamically 
Previously, you needed to save the completion script to a file and
then source it. Now, you can dynamically source completions in zsh by
running

    $ source <(rg --generate complete-zsh)

Before this commit, you would get an error after step 1.
After this commit, it should work as expected.

We also improve the FAQ item for zsh completions.

Fixes #2956
 2024-12-31 08:23:13 -05:00
Andrew Gallant
79cbe89deb doc: tweak wording for stdin detection 
This makes it slightly more precise to cover weird cases like trying to
pass a directory on stdin.

Closes #2906
 2024-09-30 07:38:05 -04:00
Thayne McCombs
bf63fe8f25 regex: add as_match method to Captures trait 
Ref https://github.com/rust-lang/regex/issues/1146

PR #2898
 2024-09-19 09:30:31 -04:00
Andrew Gallant
8bd5950296 changelog: add next section 2024-09-08 22:32:09 -04:00
Andrew Gallant
6e0539ab91 pkg/brew: update tap 2024-09-08 22:32:02 -04:00
Andrew Gallant
4649aa9700 14.1.1 2024-09-08 22:15:00 -04:00
Andrew Gallant
c009652e77 changelog: 14.1.1 2024-09-08 22:13:53 -04:00
Andrew Gallant
b9f7a9ba2b deps: bump grep to 0.3.2 2024-09-08 22:11:17 -04:00
Andrew Gallant
a1960877cf grep-0.3.2 2024-09-08 22:11:00 -04:00
Andrew Gallant
bb0925af91 deps: bump grep-printer to 0.2.2 2024-09-08 22:10:49 -04:00
Andrew Gallant
be117dbafa grep-printer-0.2.2 2024-09-08 22:10:29 -04:00
Andrew Gallant
06dc13ad2d deps: bump grep-searcher to 0.1.14 2024-09-08 22:09:55 -04:00
Andrew Gallant
c6c2e69b8f grep-searcher-0.1.14 2024-09-08 22:09:27 -04:00
Andrew Gallant
e67c868ddd deps: bump grep-pcre2 to 0.1.8 2024-09-08 22:09:23 -04:00
Andrew Gallant
d33f2e2f70 grep-pcre2-0.1.8 2024-09-08 22:08:41 -04:00
Andrew Gallant
082edafffa deps: bump grep-regex to 0.1.13 2024-09-08 22:08:22 -04:00
Andrew Gallant
7c8dc332b3 grep-regex-0.1.13 2024-09-08 22:07:52 -04:00
Andrew Gallant
ea961915b5 deps: bump grep-cli to 0.1.11 2024-09-08 22:07:30 -04:00
Andrew Gallant
7943bdfe82 grep-cli-0.1.11 2024-09-08 22:06:59 -04:00
Andrew Gallant
312a7884fc deps: bump ignore to 0.4.23 2024-09-08 22:06:39 -04:00
Andrew Gallant
ac02f54c89 ignore-0.4.23 2024-09-08 22:06:03 -04:00
Andrew Gallant
24b337b940 deps: bump globset to 0.4.15 2024-09-08 22:05:45 -04:00
Andrew Gallant
a5083f99ce globset-0.4.15 2024-09-08 22:04:48 -04:00
Andrew Gallant
f89cdba5df doc: update date in man page template 2024-09-08 22:04:11 -04:00
Andrew Gallant
f7b677d136 deps: update everything 2024-09-08 22:03:29 -04:00
Andrew Gallant
3f68a8f3d7 changelog: 14.1.1 2024-09-08 22:03:22 -04:00
Andrew Gallant
9d738ad0c0 regex: fix inner literal extraction that resulted in false negatives 
In some rare cases, it was possible for ripgrep's inner literal detector
to extract a set of literals that could produce a false negative. #2884
gives an example: `(?i:e.x|ex)`. In this case, the set extracted can be
discovered by running `rg '(?i:e.x|ex) --trace`:

    Seq[E("EX"), E("Ex"), E("eX"), E("ex")]

This extraction leads to building a multi-substring matcher for `EX`,
`Ex`, `eX` and `ex`. Searching the haystack `e-x` produces no match,
and thus, ripgrep shows no matches. But the regex `(?i:e.x|ex)` matches
`e-x`.

The issue at play here was that when two extracted literal sequences
were unioned, we were correctly unioning their "prefix" attribute.
And this in turn leads to those literal sequences being combined
incorrectly via cross product. This case in particular triggers it
because two different optimizations combine to produce an incorrect
result. Firslty, the regex has a common prefix extracted and is
rewritten as `(?i:e(?:.x|x))`. Secondly, the `x` in the first branch of
the alternation has its `prefix` attribute set to `false` (correctly),
which means it can't be cross producted with another concatenation. But
in this case, it is unioned with the `x` from the second branch, and
this results in the union result having `prefix` set to `true`. This
in turn pops up and lets it get cross producted with the `e` prefix,
producing an incorrect literal sequence.

We fix this by changing the implementation of `union` to return
`prefix` set to `true` only when *both* literal sequences being unioned
have `prefix` set to `true`.

Doing this exposed a second bug that was present, but was purely
cosmetic: the extracted literals in this case, after the fix, are
`X` and `x`. They were considered "exact" (i.e., lead to a match),
but of course they are not. Observing an `X` or an `x` does not mean
there is a match. This was fixed by making `choose` always return
an inexact literal sequence. This is perhaps too conservative in
aggregate in some cases, but always correct. The idea here is that if
one is choosing between two concatenations, then it is likely the case
that the sequence returned should be considered inexact. The issue
is that this can lead to avoiding cross products in some cases that
would otherwise be correct. This is bad because it means extracting
shorter literals in some cases. (In general, the longer the literal the
better.) But we prioritize correctness for now and fix it. You can see
a few tests where this shortens some extracted literals.

Fixes #2884
 2024-09-08 22:00:46 -04:00
Andrew Gallant
6c5108ed17 github: add FUNDING 2024-09-03 11:46:01 -04:00
Andrew Gallant
e0f1000df6 deps: update everything 
This removes `once_cell` (a dependency of `cc`) but adds `shlex` (also a
dependency of `cc`). AFAIK, ripgrep does not utilize anything in `cc`
that requires `shlex`, which is pretty unfortunate that we have to spend
time compiling it. (We use `cc` only when the `pcre2` feature is
enabled.)
 2024-08-28 11:38:43 -04:00
Henk-Jan Meijer
ea99421ec8 doc: fix transcription bug in ugrep benchmark command 
I re-ran the benchmark and the timing remains nearly
unchanged, so that part was correct.

PR #2876
 2024-08-21 13:58:36 -04:00
Cort Spellman
af8c386d5e doc: fix typo in --heading flag help 
PR #2864
 2024-08-02 17:32:42 -04:00
Naser Aleisa
71d71d2d98 doc: refer to correct flag name for --engine=auto 
PR #2850
 2024-07-04 07:25:13 -04:00
Tobias Decking
c9ebcbd8ab globset: optimize character escaping 
Rewrites the char_to_escaped_literal and bytes_to_escaped_literal
functions in a way that minimizes heap allocations. After this, the
resulting string is the only allocation remaining.

I believe when this code was originally written, the routines available
to avoid heap allocations didn't exist.

I'm skeptical that this matters in the grand scheme of things, but I
think this is still worth doing for "good sense" reasons.

PR #2833
 2024-06-05 09:56:00 -04:00
Pratham Verma
dec0dc3196 doc: update link for debian installation 
PR #2829
 2024-06-02 17:48:50 -04:00
Andrew Gallant
2f0a269f07 github: use an obviously old version of ripgrep in issue template 
This should hopefully avoid confusion where the use of the version
number in the issue template isn't mistaken for the implication that the
version must therefore be recent.

Ref #2824
 2024-05-27 18:22:11 -04:00
Andrew Gallant
0a0893a765 ignore: add debug log message when opening gitignore file 
I'm not sure why it took me this long to add this debug message, but
it's quite useful in determining where ignore rules are coming from.
 2024-05-27 14:53:19 -04:00
Bryan Honof
35160a1cdb doc: add Flox as an installation method 
Ref https://flox.dev/docs/

PR #2817
 2024-05-24 11:59:19 -04:00
Andrew Gallant
f1d23c06e3 cli: add more logging for stdin heuristic detection 
Stdin heuristic detection is complicated and opaque enough that it's
worth having easy access to the complete story that leads ripgrep to
decide whether to search stdin or not.

Ref #2806
 2024-05-13 09:43:04 -04:00
tgolang
22b677900f doc: fix some typos 
PR #2754
 2024-05-13 07:44:51 -04:00
NicoElbers
bb6f0f5519 doc: fix typo in --vimgrep help message 
PR #2802
 2024-05-11 07:02:24 -04:00
Andrew Gallant
b6ef99ee55 doc: remove unused man page template 
This seems to be causing confusion. And since we don't use it as of
ripgrep 14, let's just remove it.

Man page generation is now done by ripgrep itself. That is:

    rg --generate man > rg.1

Closes #2801
 2024-05-09 13:46:28 -04:00
Nicolas Holzschuch
bb8601b2ba printer: make compilation on non-unix, non-windows platforms work 
Some of the new hyperlink work caused ripgrep to stop compiling
on non-{Unix,Windows} platforms. The most popular of which is WASI.

This commit makes non-{Unix,Windows} compile again. And we add a
very basic WASI test in CI to catch regressions.

More work is needed to make tests on non-{Unix,Windows} platforms
work. And of course, this commit specifically takes the path of disabling
hyperlink support for non-{Unix,Windows} platforms.
 2024-04-23 13:12:19 -04:00
Andrew Gallant
02b47b7469 deps: update everything 
Notably, this removes winapi in favor of windows-sys, as a result of
winapi-util switching over to windows-sys[1].

Annoyingly, when PCRE2 is enabled, this brings in a dependency on
`once_cell`[2]. I had worked to remove it from my dependencies and now
it's back. Gah. I suppose I could disable the `parallel` feature of
`cc`, but that doesn't seem like a good trade-off.

[1]: https://github.com/BurntSushi/winapi-util/pull/13
[2]: https://github.com/rust-lang/cc-rs/pull/1037
 2024-04-23 10:46:12 -04:00
redistay
d922b7ac11 doc: fix typo 
PR #2776
 2024-04-02 09:10:25 -04:00
Linda_pp
2acf25c689 ignore/types: add WGSL to the default file types 
[WGSL][1] is a shading language for WebGPU. As defined in [Appendix
A][2], the file extension is `.wgsl`.

PR #2774 

[1]: https://www.w3.org/TR/WGSL/
[2]: https://www.w3.org/TR/WGSL/#text-wgsl-media-type
 2024-04-01 23:05:15 -04:00
Vadim Kostin
80007698d3 ignore/types: add Vue 
PR #2772
 2024-04-01 07:49:29 -04:00
cgzones
3ad0e83471 ignore/walk: correct build_parallel() documentation 
The returned closure should return `WalkState`, not `()`.

Closes #2767
 2024-03-27 14:50:05 -04:00
Andrew Gallant
eca13f08a2 deps: bump everything else 2024-03-24 18:58:28 -04:00
Andrew Gallant
4f99f82b19 deps: bump pcre2 and pcre2-sys 
This moves to PCRE2 10.43.
 2024-03-24 18:58:06 -04:00
Anton Zhiyanov
327d74f161 doc: add link to unofficial playground 
PR #2760
 2024-03-20 08:11:09 -04:00
Brent Williams
9da0995df4 ignore/types: add 'svelte' to the default file types 
Ref: https://svelte.dev/

PR #2759
 2024-03-19 13:36:08 -04:00
Andrew Gallant
e9abbc1a02 cargo: nuke 'simd-accel' from orbit 
This feature causes nothing but problems and is frequently broken. The
only optimization it was enabling were SIMD optimizations for
transcoding. In particular, for UTF-16 transcoding. This is performed by
the [`encoding_rs`](https://github.com/hsivonen/encoding_rs) crate,
which specifically uses unstable portable SIMD APIs instead of the
stable non-portable SIMD APIs.

SIMD optimizations that apply to search have long been making use of
stable APIs, and are automatically enabled when your target supports
them. This is, IMO, the correct user experience and one that
`encoding_rs` refuses to support. I'm done dealing with it, so
transcoding will only use scalar code until the SIMD optimizations in
`encoding_rs` work on stable. (This doesn't mean that `encoding_rs` has
to change. This could also be fixed by stabilizing `std::simd`.)

Fixes #2748
 2024-03-07 09:47:43 -05:00
Andrew Gallant
9bd30e8e48 deps: update everything 2024-03-07 09:38:22 -05:00
Andrew Gallant
59212d08d3 style: fix new lints 
The Rust compiler seems to have gotten smarter at finding unused or
redundant imports.
 2024-03-07 09:37:48 -05:00
SuperSpecialSweet
6ebebb2aaa doc: fix typo in comments 
PR #2741
 2024-02-22 06:57:58 -05:00
Andrew Gallant
e92e2ef813 cli: remove stray dbg! 
Whoops, forgot to review my commits before pushing.
 2024-02-15 12:02:15 -05:00
Andrew Gallant
4a30819302 cli: tweak how "is one file" predicate works 
In effect, we switch from `path.is_file()` to `!path.is_dir()`. In cases
where process substitution is used, for example, the path can actually
have type "fifo" instead of "file." Even if it's a fifo, we want to
treat it as-if it were a file. The real key here is that we basically
always want to consider a lone argument as a file so long as we know it
isn't a directory. Because a directory is the only thing that will
causes us to (potentially) search more than one thing.

Fixes #2736
 2024-02-15 11:59:59 -05:00
Wilfred Hughes
9b42af96f0 doc: fix typo in --hidden docs 
PR #2718
 2024-01-22 13:31:11 -05:00
Alex Touchet
648a65f197 doc: add missing date in changelog 
PR #2704
 2024-01-06 17:49:18 -05:00
Andrew Gallant
bdf01f46a6 changelog: start next section 2024-01-06 14:41:45 -05:00
Andrew Gallant
1c775f3a82 pkg/brew: update tap 2024-01-06 14:41:09 -05:00
Andrew Gallant
e50df40a19 14.1.0 2024-01-06 14:32:27 -05:00
Andrew Gallant
1fa76d2a42 changelog: add 14.1.0 blurb 2024-01-06 14:31:16 -05:00
Andrew Gallant
44aa5a417d deps: bump ignore to 0.4.22 2024-01-06 14:28:28 -05:00
Andrew Gallant
2c3897585d ignore-0.4.22 2024-01-06 14:27:44 -05:00
Andrew Gallant
6e9141a9ca deps: update everything 2024-01-06 14:26:52 -05:00
Andrew Gallant
c8e4a84519 cli: prefix all non-fatal error messages with 'rg: ' 
Fixes #2694
 2024-01-06 14:15:52 -05:00
Andrew Gallant
f02a50a69d changelog: various updates 2024-01-06 13:59:52 -05:00
fe9lix
b9c774937f ignore: fix reference cycle for compiled matchers 
It looks like there is a reference cycle caused by the compiled
matchers (compiled HashMap holds ref to Ignore and Ignore holds ref
to HashMap). Using weak refs fixes issue #2690 in my test project.
Also confirmed via before and after when profiling the code, see the
attached screenshots in #2692.

Fixes #2690
 2024-01-06 12:50:42 -05:00
Andrew Gallant
67dd809a80 ignore: add some 'allow(dead_code)' annotations 
I don't usually like doing this and would prefer to just delete unused
code, but I don't have the context required to understand why this code
is unused. A refresh of this crate is on the (distant) horizon, so I'll
just leave these here for now to squash the warnings.
 2024-01-06 12:25:06 -05:00
Jan Verbeek
e0a85678e1 complete/fish: improve shell completions for fish 
- Stop using `-n __fish_use_subcommand`. This had the effect of
ignoring options if a positional argument has already been given, but
that's not how ripgrep works.

- Only suggest negation options if the option they're negating is
passed (e.g., only complete `--no-pcre2` if `--pcre2` is present). The
zsh completions already do this.

- Take into account whether an option takes an argument. If an option
is not a switch then it won't suggest further options until the
argument is given, e.g. `-C<tab>` won't suggest options but `-i<tab>`
will.

- Suggest correct arguments for options. We already completed a fixed
set of choices where available, but now we go further:

  - Filenames are only suggested for options that take filenames.

  - `--pre` and `--hostname-bin` suggest binaries from `$PATH`.

  - `-t`/`--type`/&c use `--type-list` for suggestions, like in zsh,
  with a preview of the glob patterns.

  - `--encoding` uses a hardcoded list extracted from the zsh
  completions. This has been refactored into a separate file, and the
  range globs (`{1..5}`) replaced by comma globs (`{1,2,3,4,5}`) since
  those work in both shells. I verified that this produces the same
  list as before in zsh, and the same list in fish (albeit in a
  different order).

PR #2684
 2024-01-06 10:39:35 -05:00
David Gilman
23af5fb043 doc: update MSRV in README 
PR #2673
 2024-01-06 10:22:26 -05:00
Andrew Gallant
5dec4b8e37 ci: drop custom Cross images 
It looks like these aren't needed any more? I'm not sure why to be
honest. I suspect it's because we no longer need asciidoc(tor)? to
generate man pages. And I believe tests that require things like `zstd`
are automatically if `zstd` isn't installed.
 2024-01-06 10:21:34 -05:00
Younes El-karama
827082a33a ci: add more ARM build configurations to CI and release workflows 
... it turns out that rustembedded/cross:armv7-unknown-linux-musleabi
doesn't exist. And looking more closely, it looks like the Cross project
has decided to shake things up and publish images to ghcr instead. So we
migrate everything over to that.
 2024-01-06 10:21:34 -05:00
Andrew Gallant
6c2a550e1e deps: update everything 
This drops a dependency on memoffset due to a crossbeam-epoch update.
w00t.
 2024-01-04 19:46:29 -05:00
Andrew Gallant
8e8fc9c503 deps: bump pcre2-sys to 0.2.8 
This release contains some extra logic to disable the JIT on musleabi
targets.
 2024-01-04 19:44:28 -05:00
Andrew Gallant
2057023dc5 readme: update benchmarks 
We add a few more too.
 2024-01-03 16:21:04 -05:00
Andrew Gallant
3f2fe0afee deps: update everything 
This also drops a dependency on scopeguard, courtesy of crossbeam-epoch
dropping it. Not sure why they did, but fine by me.
 2023-12-17 09:37:33 -05:00
amesgen
56c7ad175a ignore/types: add Lean 
Ref: https://lean-lang.org/

PR #2678
 2023-12-07 11:46:00 -05:00
Timo Wilken
5b7a30846f doc: fix Guix install instructions 
`guix install` should not be run using `sudo`, as per
<https://packages.guix.gnu.org/packages/ripgrep/>.

PR #2669
 2023-11-30 10:54:54 -05:00
Patrick Williams
2a4dba3fbf ignore/types: add meson.options 
Starting with meson 1.1, there is a preference for using meson.options
instead of meson_options.txt.  Add the new filename to the meson set.

PR #2666
 2023-11-29 19:03:12 -05:00
liberodark
84d65865e6 doc: add Void Linux installation instructions 
PR #2665
 2023-11-29 07:49:20 -05:00
Andrew Gallant
d9aaa11873 pkg/brew: update tap 2023-11-28 16:23:16 -05:00
91 changed files with 2443 additions and 1032 deletions
Expand all files Collapse all files

1
.github/FUNDING.yml vendored Normal file
View File

@@ -0,0 +1 @@
github: [BurntSushi]

2
.github/ISSUE_TEMPLATE/bug_report.yml vendored
View File

@@ -24,7 +24,7 @@ body:
attributes:
label: What version of ripgrep are you using?
description: Enter the output of `rg --version`.
placeholder: ex. ripgrep 13.0.0
placeholder: ex. ripgrep 0.2.1
validations:
required: true

63
.github/workflows/ci.yml vendored
View File

@@ -53,7 +53,7 @@ jobs:
include:
- build: pinned
os: ubuntu-latest
rust: 1.74.0
rust: 1.88.0
- build: stable
os: ubuntu-latest
rust: stable
@@ -75,6 +75,18 @@ jobs:
os: ubuntu-latest
rust: stable
target: aarch64-unknown-linux-gnu
- build: stable-arm-gnueabihf
os: ubuntu-latest
rust: stable
target: armv7-unknown-linux-gnueabihf
- build: stable-arm-musleabihf
os: ubuntu-latest
rust: stable
target: armv7-unknown-linux-musleabihf
- build: stable-arm-musleabi
os: ubuntu-latest
rust: stable
target: armv7-unknown-linux-musleabi
- build: stable-powerpc64
os: ubuntu-latest
rust: stable
@@ -87,11 +99,14 @@ jobs:
os: macos-latest
rust: nightly
- build: win-msvc
os: windows-2022
os: windows-latest
rust: nightly
- build: win-gnu
os: windows-2022
os: windows-latest
rust: nightly-x86_64-gnu
- build: winaarch64-msvc
os: windows-11-arm
rust: nightly
steps:
- name: Checkout repository
uses: actions/checkout@v4
@@ -165,7 +180,7 @@ jobs:
# 'rg' binary (done in test-complete) with qemu, which is a pain and
# doesn't really gain us much. If shell completion works in one place,
# it probably works everywhere.
if: matrix.target == '' && matrix.os != 'windows-2022'
if: matrix.target == '' && !startsWith(matrix.os, 'windows')
shell: bash
run: ci/test-complete
@@ -177,6 +192,21 @@ jobs:
shell: bash
run: ${{ env.CARGO }} test --bin rg ${{ env.TARGET_FLAGS }} flags::defs::tests::available_shorts -- --nocapture
# Setup and compile on the wasm32-wasip1 target
wasm:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Install Rust
uses: dtolnay/rust-toolchain@master
with:
toolchain: stable
- name: Add wasm32-wasip1 target
run: rustup target add wasm32-wasip1
- name: Basic build
run: cargo build --verbose
rustfmt:
runs-on: ubuntu-latest
steps:
@@ -203,3 +233,28 @@ jobs:
env:
RUSTDOCFLAGS: -D warnings
run: cargo doc --no-deps --document-private-items --workspace
fuzz_testing:
name: Compile Fuzz Test Targets
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Install required packages (Ubuntu)
run: |
sudo apt-get update
sudo apt-get install g++ --yes
- name: Install Rust
uses: dtolnay/rust-toolchain@master
with:
toolchain: stable
- name: Install Fuzzer
run: cargo install cargo-fuzz
working-directory: fuzz
- name: Verify fuzz targets build
run: cargo check
working-directory: fuzz

44
.github/workflows/release.yml vendored
View File

@@ -80,6 +80,24 @@ jobs:
target: aarch64-unknown-linux-gnu
strip: aarch64-linux-gnu-strip
qemu: qemu-aarch64
- build: stable-arm-gnueabihf
os: ubuntu-latest
rust: stable
target: armv7-unknown-linux-gnueabihf
strip: arm-linux-gnueabihf-strip
qemu: qemu-arm
- build: stable-arm-musleabihf
os: ubuntu-latest
rust: stable
target: armv7-unknown-linux-musleabihf
strip: arm-linux-musleabihf-strip
qemu: qemu-arm
- build: stable-arm-musleabi
os: ubuntu-latest
rust: stable
target: armv7-unknown-linux-musleabi
strip: arm-linux-musleabi-strip
qemu: qemu-arm
- build: stable-powerpc64
os: ubuntu-latest
rust: stable
@@ -104,6 +122,10 @@ jobs:
os: windows-latest
rust: nightly-x86_64-gnu
target: x86_64-pc-windows-gnu
- build: winaarch64-msvc
os: windows-11-arm
rust: nightly
target: aarch64-pc-windows-msvc
- build: win32-msvc
os: windows-latest
rust: nightly
@@ -157,7 +179,7 @@ jobs:
shell: bash
run: |
${{ env.CARGO }} build --verbose --release --features pcre2 ${{ env.TARGET_FLAGS }}
if [ "${{ matrix.os }}" = "windows-latest" ]; then
if [[ "${{ matrix.os }}" == windows-* ]]; then
bin="target/${{ matrix.target }}/release/rg.exe"
else
bin="target/${{ matrix.target }}/release/rg"
@@ -175,9 +197,9 @@ jobs:
run: |
docker run --rm -v \
"$PWD/target:/target:Z" \
"rustembedded/cross:${{ matrix.target }}" \
"ghcr.io/cross-rs/${{ matrix.target }}:main" \
"${{ matrix.strip }}" \
"/target/${{ matrix.target }}/release/rg"
"/$BIN"
- name: Determine archive name
shell: bash
@@ -210,37 +232,37 @@ jobs:
run: |
docker run --rm -v \
"$PWD/target:/target:Z" \
"rustembedded/cross:${{ matrix.target }}" \
"ghcr.io/cross-rs/${{ matrix.target }}:main" \
"${{ matrix.qemu }}" "/$BIN" --version
docker run --rm -v \
"$PWD/target:/target:Z" \
"rustembedded/cross:${{ matrix.target }}" \
"ghcr.io/cross-rs/${{ matrix.target }}:main" \
"${{ matrix.qemu }}" "/$BIN" \
--generate complete-bash > "$ARCHIVE/complete/rg.bash"
docker run --rm -v \
"$PWD/target:/target:Z" \
"rustembedded/cross:${{ matrix.target }}" \
"ghcr.io/cross-rs/${{ matrix.target }}:main" \
"${{ matrix.qemu }}" "/$BIN" \
--generate complete-fish > "$ARCHIVE/complete/rg.fish"
docker run --rm -v \
"$PWD/target:/target:Z" \
"rustembedded/cross:${{ matrix.target }}" \
"ghcr.io/cross-rs/${{ matrix.target }}:main" \
"${{ matrix.qemu }}" "/$BIN" \
--generate complete-powershell > "$ARCHIVE/complete/_rg.ps1"
docker run --rm -v \
"$PWD/target:/target:Z" \
"rustembedded/cross:${{ matrix.target }}" \
"ghcr.io/cross-rs/${{ matrix.target }}:main" \
"${{ matrix.qemu }}" "/$BIN" \
--generate complete-zsh > "$ARCHIVE/complete/_rg"
docker run --rm -v \
"$PWD/target:/target:Z" \
"rustembedded/cross:${{ matrix.target }}" \
"ghcr.io/cross-rs/${{ matrix.target }}:main" \
"${{ matrix.qemu }}" "/$BIN" \
--generate man > "$ARCHIVE/doc/rg.1"
- name: Build archive (Windows)
shell: bash
if: matrix.os == 'windows-latest'
if: startsWith(matrix.os, 'windows')
run: |
7z a "$ARCHIVE.zip" "$ARCHIVE"
certutil -hashfile "$ARCHIVE.zip" SHA256 > "$ARCHIVE.zip.sha256"
@@ -249,7 +271,7 @@ jobs:
- name: Build archive (Unix)
shell: bash
if: matrix.os != 'windows-latest'
if: ${{ !startsWith(matrix.os, 'windows') }}
run: |
tar czf "$ARCHIVE.tar.gz" "$ARCHIVE"
shasum -a 256 "$ARCHIVE.tar.gz" > "$ARCHIVE.tar.gz.sha256"

95
CHANGELOG.md
View File

@@ -1,3 +1,98 @@
TBD
===
Unreleased changes. Release notes have not yet been written.
Performance improvements:
* [PERF #2865](https://github.com/BurntSushi/ripgrep/pull/2865):
Avoid using path canonicalization on Windows when emitting hyperlinks.
Bug fixes:
* [BUG #829](https://github.com/BurntSushi/ripgrep/issues/829),
[BUG #2731](https://github.com/BurntSushi/ripgrep/issues/2731),
[BUG #2747](https://github.com/BurntSushi/ripgrep/issues/2747),
[BUG #2778](https://github.com/BurntSushi/ripgrep/issues/2778),
[BUG #2836](https://github.com/BurntSushi/ripgrep/issues/2836),
[BUG #2933](https://github.com/BurntSushi/ripgrep/pull/2933):
Fix bug related to gitignores from parent directories.
* [BUG #1332](https://github.com/BurntSushi/ripgrep/issues/1332),
[BUG #3001](https://github.com/BurntSushi/ripgrep/issues/3001):
Make `rg -vf file` where `file` is empty match everything.
* [BUG #2177](https://github.com/BurntSushi/ripgrep/issues/2177):
Ignore a UTF-8 BOM marker at the start of `.gitignore` (and similar files).
* [BUG #2944](https://github.com/BurntSushi/ripgrep/pull/2944):
Fix a bug where the "bytes searched" in `--stats` output could be incorrect.
* [BUG #2990](https://github.com/BurntSushi/ripgrep/issues/2990):
Fix a bug where ripgrep would mishandle globs that ended with a `.`.
* [BUG #3108](https://github.com/BurntSushi/ripgrep/issues/3108):
Fix a bug where `-q --files-without-match` inverted the exit code.
Feature enhancements:
* Many enhancements to the default set of file types available for filtering.
* [FEATURE #1872](https://github.com/BurntSushi/ripgrep/issues/1872):
Make `-r/--replace` work with `--json`.
* [FEATURE #2708](https://github.com/BurntSushi/ripgrep/pull/2708):
Completions for the fish shell take ripgrep's config file into account.
* [FEATURE #2841](https://github.com/BurntSushi/ripgrep/pull/2841):
Add `italic` to the list of available style attributes in `--color`.
* [FEATURE #2842](https://github.com/BurntSushi/ripgrep/pull/2842):
Directories containing `.jj` are now treated as git repositories.
* [FEATURE #2849](https://github.com/BurntSushi/ripgrep/pull/2849):
When using multithreading, schedule files to search in order given on CLI.
* [FEATURE #2943](https://github.com/BurntSushi/ripgrep/issues/2943):
Add `aarch64` release artifacts for Windows.
* [FEATURE #3024](https://github.com/BurntSushi/ripgrep/issues/3024):
Add `highlight` color type, for styling non-matching text in a matching line.
* [FEATURE #3048](https://github.com/BurntSushi/ripgrep/pull/3048):
Globs in ripgrep (and the `globset` crate) now support nested alternates.
14.1.1 (2024-09-08)
===================
This is a minor release with a bug fix for a matching bug. In particular, a bug
was found that could cause ripgrep to ignore lines that should match. That is,
false negatives. It is difficult to characterize the specific set of regexes
in which this occurs as it requires multiple different optimization strategies
to collide and produce an incorrect result. But as one reported example, in
ripgrep, the regex `(?i:e.x|ex)` does not match `e-x` when it should. (This
bug is a result of an inner literal optimization performed in the `grep-regex`
crate and not in the `regex` crate.)
Bug fixes:
* [BUG #2884](https://github.com/BurntSushi/ripgrep/issues/2884):
Fix bug where ripgrep could miss some matches that it should report.
Miscellaneous:
* [MISC #2748](https://github.com/BurntSushi/ripgrep/issues/2748):
Remove ripgrep's `simd-accel` feature because it was frequently broken.
14.1.0 (2024-01-06)
===================
This is a minor release with a few small new features and bug fixes. This
release contains a bug fix for unbounded memory growth while walking a
directory tree. This release also includes improvements to the completions for
the `fish` shell, and release binaries for several additional ARM targets.
Bug fixes:
* [BUG #2664](https://github.com/BurntSushi/ripgrep/issues/2690):
Fix unbounded memory growth in the `ignore` crate.
Feature enhancements:
* Added or improved file type filtering for Lean and Meson.
* [FEATURE #2684](https://github.com/BurntSushi/ripgrep/issues/2684):
Improve completions for the `fish` shell.
* [FEATURE #2702](https://github.com/BurntSushi/ripgrep/pull/2702):
Add release binaries for `armv7-unknown-linux-gnueabihf`,
`armv7-unknown-linux-musleabihf` and `armv7-unknown-linux-musleabi`.
14.0.3 (2023-11-28)
===================
This is a patch release with a bug fix for the `--sortr` flag.

410
Cargo.lock generated
View File

@@ -4,30 +4,39 @@ version = 3
[[package]]
name = "aho-corasick"
version = "1.1.2"
version = "1.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b2969dcb958b36655471fc61f7e416fa76033bdd4bfed0678d8fee1e2d07a1f0"
checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
dependencies = [
"memchr",
]
[[package]]
name = "anyhow"
version = "1.0.75"
version = "1.0.98"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a4668cab20f66d8d020e1fbc0ebe47217433c1b6c8f2040faf858554e394ace6"
checksum = "e16d2d3311acee920a9eb8d33b8cbc1787ce4a264e85f964c2404b969bdcd487"
[[package]]
name = "autocfg"
version = "1.1.0"
name = "arbitrary"
version = "1.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
checksum = "dde20b3d026af13f561bdd0f15edf01fc734f0dafcedbaf42bba506a9517f223"
dependencies = [
"derive_arbitrary",
]
[[package]]
name = "bitflags"
version = "2.9.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1b8e56985ec62d17e9c1001dc89c88ecd7dc08e47eba5ec7c29c7b5eeecde967"
[[package]]
name = "bstr"
version = "1.8.0"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "542f33a8835a0884b006a0c3df3dadd99c0c3f296ed26c2fdc8028e01ad6230c"
checksum = "234113d19d0d7d613b40e86fb654acf958910802bcceab913a4f9e7cda03b1a4"
dependencies = [
"memchr",
"regex-automata",
@@ -36,71 +45,73 @@ dependencies = [
[[package]]
name = "cc"
version = "1.0.83"
version = "1.2.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f1174fb0b6ec23863f8b971027804a42614e347eafb0a95bf0b12cdae21fc4d0"
checksum = "4ad45f4f74e4e20eaa392913b7b33a7091c87e59628f4dd27888205ad888843c"
dependencies = [
"jobserver",
"libc",
"shlex",
]
[[package]]
name = "cfg-if"
version = "1.0.0"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
checksum = "9555578bc9e57714c812a1f84e4fc5b4d21fcb063490c624de019f7464c91268"
[[package]]
name = "crossbeam-channel"
version = "0.5.8"
version = "0.5.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a33c2bf77f2df06183c3aa30d1e96c0695a313d4f9c453cc3762a6db39f99200"
checksum = "82b8f8f868b36967f9606790d1903570de9ceaf870a7bf9fbbd3016d636a2cb2"
dependencies = [
"cfg-if",
"crossbeam-utils",
]
[[package]]
name = "crossbeam-deque"
version = "0.8.3"
version = "0.8.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce6fd6f855243022dcecf8702fef0c297d4338e226845fe067f6341ad9fa0cef"
checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
dependencies = [
"cfg-if",
"crossbeam-epoch",
"crossbeam-utils",
]
[[package]]
name = "crossbeam-epoch"
version = "0.9.15"
version = "0.9.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae211234986c545741a7dc064309f67ee1e5ad243d0e48335adc0484d960bcc7"
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
dependencies = [
"autocfg",
"cfg-if",
"crossbeam-utils",
"memoffset",
"scopeguard",
]
[[package]]
name = "crossbeam-utils"
version = "0.8.16"
version = "0.8.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a22b2d63d4d1dc0b7f1b6b2747dd0088008a9be28b6ddf0b1e7d335e3037294"
checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
[[package]]
name = "derive_arbitrary"
version = "1.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "30542c1ad912e0e3d22a1935c290e12e8a29d704a420177a31faad4a601a0800"
dependencies = [
"cfg-if",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "encoding_rs"
version = "0.8.33"
version = "0.8.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7268b386296a025e474d5140678f75d6de9493ae55a5d709eeb9dd08149945e1"
checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3"
dependencies = [
"cfg-if",
"packed_simd",
]
[[package]]
@@ -113,16 +124,29 @@ dependencies = [
]
[[package]]
name = "glob"
version = "0.3.1"
name = "getrandom"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4"
dependencies = [
"cfg-if",
"libc",
"r-efi",
"wasi",
]
[[package]]
name = "glob"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a8d1add55171497b4705a648c6b583acafb01d58050a51727785f0b2c8e0a2b2"
[[package]]
name = "globset"
version = "0.4.14"
version = "0.4.16"
dependencies = [
"aho-corasick",
"arbitrary",
"bstr",
"glob",
"log",
@@ -134,7 +158,7 @@ dependencies = [
[[package]]
name = "grep"
version = "0.3.1"
version = "0.3.2"
dependencies = [
"grep-cli",
"grep-matcher",
@@ -148,7 +172,7 @@ dependencies = [
[[package]]
name = "grep-cli"
version = "0.1.10"
version = "0.1.11"
dependencies = [
"bstr",
"globset",
@@ -168,7 +192,7 @@ dependencies = [
[[package]]
name = "grep-pcre2"
version = "0.1.7"
version = "0.1.8"
dependencies = [
"grep-matcher",
"log",
@@ -177,7 +201,7 @@ dependencies = [
[[package]]
name = "grep-printer"
version = "0.2.1"
version = "0.2.2"
dependencies = [
"bstr",
"grep-matcher",
@@ -191,7 +215,7 @@ dependencies = [
[[package]]
name = "grep-regex"
version = "0.1.12"
version = "0.1.13"
dependencies = [
"bstr",
"grep-matcher",
@@ -202,7 +226,7 @@ dependencies = [
[[package]]
name = "grep-searcher"
version = "0.1.13"
version = "0.1.14"
dependencies = [
"bstr",
"encoding_rs",
@@ -217,7 +241,7 @@ dependencies = [
[[package]]
name = "ignore"
version = "0.4.21"
version = "0.4.23"
dependencies = [
"bstr",
"crossbeam-channel",
@@ -233,112 +257,58 @@ dependencies = [
[[package]]
name = "itoa"
version = "1.0.9"
version = "1.0.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "af150ab688ff2122fcef229be89cb50dd66af9e01a4ff320cc137eecc9bacc38"
[[package]]
name = "jemalloc-sys"
version = "0.5.4+5.3.0-patched"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac6c1946e1cea1788cbfde01c993b52a10e2da07f4bac608228d1bed20bfebf2"
dependencies = [
"cc",
"libc",
]
[[package]]
name = "jemallocator"
version = "0.5.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a0de374a9f8e63150e6f5e8a60cc14c668226d7a347d8aee1a45766e3c4dd3bc"
dependencies = [
"jemalloc-sys",
"libc",
]
checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
[[package]]
name = "jobserver"
version = "0.1.27"
version = "0.1.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8c37f63953c4c63420ed5fd3d6d398c719489b9f872b9fa683262f8edd363c7d"
checksum = "38f262f097c174adebe41eb73d66ae9c06b2844fb0da69969647bbddd9b0538a"
dependencies = [
"getrandom",
"libc",
]
[[package]]
name = "lexopt"
version = "0.3.0"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baff4b617f7df3d896f97fe922b64817f6cd9a756bb81d40f8883f2f66dcb401"
checksum = "9fa0e2a1fcbe2f6be6c42e342259976206b383122fc152e872795338b5a3f3a7"
[[package]]
name = "libc"
version = "0.2.150"
version = "0.2.174"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "89d92a4743f9a61002fae18374ed11e7973f530cb3a3255fb354818118b2203c"
[[package]]
name = "libm"
version = "0.2.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4ec2a862134d2a7d32d7983ddcdd1c4923530833c9f2ea1a44fc5fa473989058"
checksum = "1171693293099992e19cddea4e8b849964e9846f4acee11b3948bcc337be8776"
[[package]]
name = "log"
version = "0.4.20"
version = "0.4.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94"
[[package]]
name = "memchr"
version = "2.6.4"
version = "2.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f665ee40bc4a3c5590afb1e9677db74a508659dfd71e126420da8274909a0167"
checksum = "32a282da65faaf38286cf3be983213fcf1d2e2a58700e808f83f4ea9a4804bc0"
[[package]]
name = "memmap2"
version = "0.9.0"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "deaba38d7abf1d4cca21cc89e932e542ba2b9258664d2a9ef0e61512039c9375"
checksum = "fd3f7eed9d3848f8b98834af67102b720745c4ec028fcd0aa0239277e7de374f"
dependencies = [
"libc",
]
[[package]]
name = "memoffset"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a634b1c61a95585bd15607c6ab0c4e5b226e695ff2800ba0cdccddf208c406c"
dependencies = [
"autocfg",
]
[[package]]
name = "num-traits"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39e3200413f237f41ab11ad6d161bc7239c84dcb631773ccd7de3dfe4b5c267c"
dependencies = [
"autocfg",
"libm",
]
[[package]]
name = "packed_simd"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1f9f08af0c877571712e2e3e686ad79efad9657dbf0f7c3c8ba943ff6c38932d"
dependencies = [
"cfg-if",
"num-traits",
]
[[package]]
name = "pcre2"
version = "0.2.6"
version = "0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4c9d53a8ea5fc3d3568d3de4bebc12606fd0eb8234c602576f1f1ee4880488a7"
checksum = "3be55c43ac18044541d58d897e8f4c55157218428953ebd39d86df3ba0286b2b"
dependencies = [
"libc",
"log",
@@ -347,9 +317,9 @@ dependencies = [
[[package]]
name = "pcre2-sys"
version = "0.2.7"
version = "0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f8f5556f23cf2c0b481949fdfc19a7cd9b27ddcb00ef3477b0f4935cbdaedf2"
checksum = "550f5d18fb1b90c20b87e161852c10cde77858c3900c5059b5ad2a1449f11d8a"
dependencies = [
"cc",
"libc",
@@ -358,33 +328,39 @@ dependencies = [
[[package]]
name = "pkg-config"
version = "0.3.27"
version = "0.3.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "26072860ba924cbfa98ea39c8c19b4dd6a4a25423dbdf219c1eca91aa0cf6964"
checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
[[package]]
name = "proc-macro2"
version = "1.0.70"
version = "1.0.95"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39278fbbf5fb4f646ce651690877f89d1c5811a3d4acb27700c1cb3cdb78fd3b"
checksum = "02b3e5e68a3a1a02aad3ec490a98007cbc13c37cbe84a3cd7b8e406d76e7f778"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.33"
version = "1.0.40"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5267fca4496028628a95160fc423a33e8b2e6af8a5302579e322e4b520293cae"
checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d"
dependencies = [
"proc-macro2",
]
[[package]]
name = "regex"
version = "1.10.2"
name = "r-efi"
version = "5.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "380b951a9c5e80ddfd6136919eef32310721aa4aacd4889a8d39124b026ab343"
checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
[[package]]
name = "regex"
version = "1.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b544ef1b4eac5dc2db33ea63606ae9ffcfac26c1416a2806ae0bf5f56b201191"
dependencies = [
"aho-corasick",
"memchr",
@@ -394,9 +370,9 @@ dependencies = [
[[package]]
name = "regex-automata"
version = "0.4.3"
version = "0.4.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5f804c7828047e88b2d32e2d7fe5a105da8ee3264f01902f796c8e067dc2483f"
checksum = "809e8dc61f6de73b46c85f4c96486310fe304c434cfa43669d7b40f711150908"
dependencies = [
"aho-corasick",
"memchr",
@@ -405,19 +381,18 @@ dependencies = [
[[package]]
name = "regex-syntax"
version = "0.8.2"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c08c74e62047bb2de4ff487b251e4a92e24f48745648451635cec7d591162d9f"
checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
[[package]]
name = "ripgrep"
version = "14.0.3"
version = "14.1.1"
dependencies = [
"anyhow",
"bstr",
"grep",
"ignore",
"jemallocator",
"lexopt",
"log",
"serde",
@@ -425,14 +400,15 @@ dependencies = [
"serde_json",
"termcolor",
"textwrap",
"tikv-jemallocator",
"walkdir",
]
[[package]]
name = "ryu"
version = "1.0.15"
version = "1.0.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1ad4cc8da4ef723ed60bced201181d83791ad433213d8c24efffda1eec85d741"
checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
[[package]]
name = "same-file"
@@ -443,26 +419,20 @@ dependencies = [
"winapi-util",
]
[[package]]
name = "scopeguard"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
[[package]]
name = "serde"
version = "1.0.193"
version = "1.0.219"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "25dd9975e68d0cb5aa1120c288333fc98731bd1dd12f561e468ea4728c042b89"
checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.193"
version = "1.0.219"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43576ca501357b9b071ac53cdc7da8ef0cbd9493d8df094cd821777ea6e894d3"
checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
dependencies = [
"proc-macro2",
"quote",
@@ -471,20 +441,27 @@ dependencies = [
[[package]]
name = "serde_json"
version = "1.0.108"
version = "1.0.140"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3d1c7e3eac408d115102c4c24ad393e0821bb3a5df4d506a80f85f7a742a526b"
checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
dependencies = [
"itoa",
"memchr",
"ryu",
"serde",
]
[[package]]
name = "syn"
version = "2.0.39"
name = "shlex"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "23e78b90f2fcf45d3e842032ce32e3f2d1545ba6636271dcbf24fa306d87be7a"
checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
[[package]]
name = "syn"
version = "2.0.104"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "17b6f705963418cdb9927482fa304bc562ece2fdd4f616084c50b7023b435a40"
dependencies = [
"proc-macro2",
"quote",
@@ -493,62 +470,151 @@ dependencies = [
[[package]]
name = "termcolor"
version = "1.4.0"
version = "1.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ff1bc3d3f05aff0403e8ac0d92ced918ec05b666a43f83297ccef5bea8a3d449"
checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
dependencies = [
"winapi-util",
]
[[package]]
name = "textwrap"
version = "0.16.0"
version = "0.16.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "222a222a5bfe1bba4a77b45ec488a741b3cb8872e5e499451fd7d0129c9c7c3d"
checksum = "c13547615a44dc9c452a8a534638acdf07120d4b6847c8178705da06306a3057"
[[package]]
name = "tikv-jemalloc-sys"
version = "0.6.0+5.3.0-1-ge13ca993e8ccb9ba9847cc330696e02839f328f7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cd3c60906412afa9c2b5b5a48ca6a5abe5736aec9eb48ad05037a677e52e4e2d"
dependencies = [
"cc",
"libc",
]
[[package]]
name = "tikv-jemallocator"
version = "0.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4cec5ff18518d81584f477e9bfdf957f5bb0979b0bac3af4ca30b5b3ae2d2865"
dependencies = [
"libc",
"tikv-jemalloc-sys",
]
[[package]]
name = "unicode-ident"
version = "1.0.12"
version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512"
[[package]]
name = "walkdir"
version = "2.4.0"
version = "2.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d71d857dc86794ca4c280d616f7da00d2dbfd8cd788846559a6813e6aa4b54ee"
checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b"
dependencies = [
"same-file",
"winapi-util",
]
[[package]]
name = "winapi"
version = "0.3.9"
name = "wasi"
version = "0.14.2+wasi-0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
"wit-bindgen-rt",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-util"
version = "0.1.6"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f29e6f9198ba0d26b4c9f07dbe6f9ed633e1f3d5b8b414090084349e46a52596"
checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
dependencies = [
"winapi",
"windows-sys",
]
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
name = "windows-sys"
version = "0.59.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
dependencies = [
"windows-targets",
]
[[package]]
name = "windows-targets"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_gnullvm",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
[[package]]
name = "windows_aarch64_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
[[package]]
name = "windows_i686_gnu"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
[[package]]
name = "windows_i686_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
[[package]]
name = "windows_i686_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
[[package]]
name = "windows_x86_64_gnu"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
[[package]]
name = "windows_x86_64_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
[[package]]
name = "wit-bindgen-rt"
version = "0.39.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
dependencies = [
"bitflags",
]

14
Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "ripgrep"
version = "14.0.3" #:version
version = "14.1.1" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
ripgrep is a line-oriented search tool that recursively searches the current
@@ -20,11 +20,12 @@ exclude = [
"/pkg/brew",
"/benchsuite/",
"/scripts/",
"/crates/fuzz",
]
build = "build.rs"
autotests = false
edition = "2021"
rust-version = "1.72"
rust-version = "1.88"
[[bin]]
bench = false
@@ -51,16 +52,16 @@ members = [
[dependencies]
anyhow = "1.0.75"
bstr = "1.7.0"
grep = { version = "0.3.1", path = "crates/grep" }
ignore = { version = "0.4.21", path = "crates/ignore" }
grep = { version = "0.3.2", path = "crates/grep" }
ignore = { version = "0.4.23", path = "crates/ignore" }
lexopt = "0.3.0"
log = "0.4.5"
serde_json = "1.0.23"
termcolor = "1.1.0"
textwrap = { version = "0.16.0", default-features = false }
[target.'cfg(all(target_env = "musl", target_pointer_width = "64"))'.dependencies.jemallocator]
version = "0.5.0"
[target.'cfg(all(target_env = "musl", target_pointer_width = "64"))'.dependencies.tikv-jemallocator]
version = "0.6.0"
[dev-dependencies]
serde = "1.0.77"
@@ -68,7 +69,6 @@ serde_derive = "1.0.77"
walkdir = "2"
[features]
simd-accel = ["grep/simd-accel"]
pcre2 = ["grep/pcre2"]
[profile.release]

14
Cross.toml
View File

@@ -1,14 +0,0 @@
[target.x86_64-unknown-linux-musl]
image = "burntsushi/cross:x86_64-unknown-linux-musl"
[target.i686-unknown-linux-gnu]
image = "burntsushi/cross:i686-unknown-linux-gnu"
[target.aarch64-unknown-linux-gnu]
image = "burntsushi/cross:aarch64-unknown-linux-gnu"
[target.powerpc64-unknown-linux-gnu]
image = "burntsushi/cross:powerpc64-unknown-linux-gnu"
[target.s390x-unknown-linux-gnu]
image = "burntsushi/cross:s390x-unknown-linux-gnu"

33
FAQ.md
View File

@@ -94,7 +94,7 @@ Does ripgrep have support for shell auto-completion?
Yes! If you installed ripgrep through a package manager on a Unix system, then
the shell completion files included in the release archive should have been
installed for you automatically. If not, you can generate completes using
installed for you automatically. If not, you can generate completions using
ripgrep's command line interface.
For **bash**:
@@ -113,14 +113,31 @@ $ mkdir -p "$dir"
$ rg --generate complete-fish > "$dir/rg.fish"
```
For **zsh**:
For **zsh**, the recommended approach is:
```
```zsh
$ dir="$HOME/.zsh-complete"
$ mkdir -p "$dir"
$ rg --generate complete-zsh > "$dir/_rg"
```
And then add `$HOME/.zsh-complete` to your `fpath` in, e.g., your
`$HOME/.zshrc` file:
```zsh
fpath=($HOME/.zsh-complete $fpath)
```
Or if you'd prefer to load and generate completions at the same time, you can
add the following to your `$HOME/.zshrc` file:
```zsh
$ source <(rg --generate complete-zsh)
```
Note though that while this approach is easier to setup, is generally slower
than the previous method, and will add more time to loading your shell prompt.
For **PowerShell**, create the completions:
```
@@ -248,8 +265,8 @@ The `--colors` flag is a bit more complicated. The general format is:
to bold the output or not).
* `{value}` is determined by the value of `{attribute}`. If
`{attribute}` is `style`, then `{value}` should be one of `nobold`,
`bold`, `nointense`, `intense`, `nounderline` or `underline`. If
`{attribute}` is `fg` or `bg`, then `{value}` should be a color.
`bold`, `nointense`, `intense`, `nounderline`, `underline`, `noitalic` or
`italic`. If `{attribute}` is `fg` or `bg`, then `{value}` should be a color.
A color is specified by either one of eight of English names, a single 256-bit
number or an RGB triple (with over 16 million possible values, or "true
@@ -268,8 +285,8 @@ As a special case, `--colors '{type}:none'` will clear all colors and styles
associated with `{type}`, which lets you start with a clean slate (instead of
building on top of ripgrep's default color settings).
Here's an example that makes highlights the matches with a nice blue background
with bolded white text:
Here's an example that highlights the matches with a nice blue background with
bolded white text:
```
$ rg somepattern \
@@ -1038,7 +1055,7 @@ How can I donate to ripgrep or its maintainers?
I welcome [sponsorship](https://github.com/sponsors/BurntSushi/).
Or if you'd prefer, donating to a charitably organization that you like would
Or if you'd prefer, donating to a charitable organization that you like would
also be most welcome. My favorites are:
* [The Internet Archive](https://archive.org/donate/)

136
README.md
View File

@@ -42,7 +42,7 @@ This example searches the entire
[Linux kernel source tree](https://github.com/BurntSushi/linux)
(after running `make defconfig && make -j8`) for `[A-Z]+_SUSPEND`, where
all matches must be words. Timings were collected on a system with an Intel
i7-6900K 3.2 GHz.
i9-12900K 5.2 GHz.
Please remember that a single benchmark is never enough! See my
[blog post on ripgrep](https://blog.burntsushi.net/ripgrep/)
@@ -50,13 +50,14 @@ for a very detailed comparison with more benchmarks and analysis.
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep (Unicode) | `rg -n -w '[A-Z]+_SUSPEND'` | 452 | **0.136s** |
| [git grep](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `git grep -P -n -w '[A-Z]+_SUSPEND'` | 452 | 0.348s |
| [ugrep (Unicode)](https://github.com/Genivia/ugrep) | `ugrep -r --ignore-files --no-hidden -I -w '[A-Z]+_SUSPEND'` | 452 | 0.506s |
| [The Silver Searcher](https://github.com/ggreer/the_silver_searcher) | `ag -w '[A-Z]+_SUSPEND'` | 452 | 0.654s |
| [git grep](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=C git grep -E -n -w '[A-Z]+_SUSPEND'` | 452 | 1.150s |
| [ack](https://github.com/beyondgrep/ack3) | `ack -w '[A-Z]+_SUSPEND'` | 452 | 4.054s |
| [git grep (Unicode)](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=en_US.UTF-8 git grep -E -n -w '[A-Z]+_SUSPEND'` | 452 | 4.205s |
| ripgrep (Unicode) | `rg -n -w '[A-Z]+_SUSPEND'` | 536 | **0.082s** (1.00x) |
| [hypergrep](https://github.com/p-ranav/hypergrep) | `hgrep -n -w '[A-Z]+_SUSPEND'` | 536 | 0.167s (2.04x) |
| [git grep](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `git grep -P -n -w '[A-Z]+_SUSPEND'` | 536 | 0.273s (3.34x) |
| [The Silver Searcher](https://github.com/ggreer/the_silver_searcher) | `ag -w '[A-Z]+_SUSPEND'` | 534 | 0.443s (5.43x) |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep -r --ignore-files --no-hidden -I -w '[A-Z]+_SUSPEND'` | 536 | 0.639s (7.82x) |
| [git grep](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=C git grep -E -n -w '[A-Z]+_SUSPEND'` | 536 | 0.727s (8.91x) |
| [git grep (Unicode)](https://www.kernel.org/pub/software/scm/git/docs/git-grep.html) | `LC_ALL=en_US.UTF-8 git grep -E -n -w '[A-Z]+_SUSPEND'` | 536 | 2.670s (32.70x) |
| [ack](https://github.com/beyondgrep/ack3) | `ack -w '[A-Z]+_SUSPEND'` | 2677 | 2.935s (35.94x) |
Here's another benchmark on the same corpus as above that disregards gitignore
files and searches with a whitelist instead. The corpus is the same as in the
@@ -65,24 +66,52 @@ doing equivalent work:
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep | `rg -uuu -tc -n -w '[A-Z]+_SUSPEND'` | 388 | **0.096s** |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep -r -n --include='*.c' --include='*.h' -w '[A-Z]+_SUSPEND'` | 388 | 0.493s |
| [GNU grep](https://www.gnu.org/software/grep/) | `egrep -r -n --include='*.c' --include='*.h' -w '[A-Z]+_SUSPEND'` | 388 | 0.806s |
| ripgrep | `rg -uuu -tc -n -w '[A-Z]+_SUSPEND'` | 447 | **0.063s** (1.00x) |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep -r -n --include='*.c' --include='*.h' -w '[A-Z]+_SUSPEND'` | 447 | 0.607s (9.62x) |
| [GNU grep](https://www.gnu.org/software/grep/) | `grep -E -r -n --include='*.c' --include='*.h' -w '[A-Z]+_SUSPEND'` | 447 | 0.674s (10.69x) |
And finally, a straight-up comparison between ripgrep, ugrep and GNU grep on a
single large file cached in memory
(~13GB, [`OpenSubtitles.raw.en.gz`](http://opus.nlpl.eu/download.php?f=OpenSubtitles/v2018/mono/OpenSubtitles.raw.en.gz)):
Now we'll move to searching on single large file. Here is a straight-up
comparison between ripgrep, ugrep and GNU grep on a file cached in memory
(~13GB, [`OpenSubtitles.raw.en.gz`](http://opus.nlpl.eu/download.php?f=OpenSubtitles/v2018/mono/OpenSubtitles.raw.en.gz), decompressed):
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep | `rg -w 'Sherlock [A-Z]\w+'` | 7882 | **2.769s** |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep -w 'Sherlock [A-Z]\w+'` | 7882 | 6.802s |
| [GNU grep](https://www.gnu.org/software/grep/) | `LC_ALL=en_US.UTF-8 egrep -w 'Sherlock [A-Z]\w+'` | 7882 | 9.027s |
| ripgrep (Unicode) | `rg -w 'Sherlock [A-Z]\w+'` | 7882 | **1.042s** (1.00x) |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep -w 'Sherlock [A-Z]\w+'` | 7882 | 1.339s (1.28x) |
| [GNU grep (Unicode)](https://www.gnu.org/software/grep/) | `LC_ALL=en_US.UTF-8 egrep -w 'Sherlock [A-Z]\w+'` | 7882 | 6.577s (6.31x) |
In the above benchmark, passing the `-n` flag (for showing line numbers)
increases the times to `3.423s` for ripgrep and `13.031s` for GNU grep. ugrep
increases the times to `1.664s` for ripgrep and `9.484s` for GNU grep. ugrep
times are unaffected by the presence or absence of `-n`.
Beware of performance cliffs though:
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep (Unicode) | `rg -w '[A-Z]\w+ Sherlock [A-Z]\w+'` | 485 | **1.053s** (1.00x) |
| [GNU grep (Unicode)](https://www.gnu.org/software/grep/) | `LC_ALL=en_US.UTF-8 grep -E -w '[A-Z]\w+ Sherlock [A-Z]\w+'` | 485 | 6.234s (5.92x) |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep -w '[A-Z]\w+ Sherlock [A-Z]\w+'` | 485 | 28.973s (27.51x) |
And performance can drop precipitously across the board when searching big
files for patterns without any opportunities for literal optimizations:
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep | `rg '[A-Za-z]{30}'` | 6749 | **15.569s** (1.00x) |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep -E '[A-Za-z]{30}'` | 6749 | 21.857s (1.40x) |
| [GNU grep](https://www.gnu.org/software/grep/) | `LC_ALL=C grep -E '[A-Za-z]{30}'` | 6749 | 32.409s (2.08x) |
| [GNU grep (Unicode)](https://www.gnu.org/software/grep/) | `LC_ALL=en_US.UTF-8 grep -E '[A-Za-z]{30}'` | 6795 | 8m30s (32.74x) |
Finally, high match counts also tend to both tank performance and smooth
out the differences between tools (because performance is dominated by how
quickly one can handle a match and not the algorithm used to detect the match,
generally speaking):
| Tool | Command | Line count | Time |
| ---- | ------- | ---------- | ---- |
| ripgrep | `rg the` | 83499915 | **6.948s** (1.00x) |
| [ugrep](https://github.com/Genivia/ugrep) | `ugrep the` | 83499915 | 11.721s (1.69x) |
| [GNU grep](https://www.gnu.org/software/grep/) | `LC_ALL=C grep the` | 83499915 | 15.217s (2.19x) |
### Why should I use ripgrep?
@@ -109,7 +138,7 @@ times are unaffected by the presence or absence of `-n`.
backreferences in your patterns, which are not supported in ripgrep's default
regex engine. PCRE2 support can be enabled with `-P/--pcre2` (use PCRE2
always) or `--auto-hybrid-regex` (use PCRE2 only if needed). An alternative
syntax is provided via the `--engine (default|pcre2|auto-hybrid)` option.
syntax is provided via the `--engine (default|pcre2|auto)` option.
* ripgrep has [rudimentary support for replacements](GUIDE.md#replacements),
which permit rewriting output based on what was matched.
* ripgrep supports [searching files in text encodings](GUIDE.md#file-encoding)
@@ -191,6 +220,16 @@ configuration files, passthru, support for searching compressed files,
multiline search and opt-in fancy regex support via PCRE2.
### Playground
If you'd like to try ripgrep before installing, there's an unofficial
[playground](https://codapi.org/ripgrep/) and an [interactive
tutorial](https://codapi.org/try/ripgrep/).
If you have any questions about these, please open an issue in the [tutorial
repo](https://github.com/nalgeon/tryxinyminutes).
### Installation
The binary name for ripgrep is `rg`.
@@ -263,27 +302,35 @@ and **openSUSE Leap** since 15.1.
$ sudo zypper install ripgrep
```
If you're a **RHEL/CentOS 7/8** user, you can install ripgrep from
[copr](https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/):
If you're a **RHEL/CentOS/Rocky Linux 9** user, you can install ripgrep from
the [EPEL](https://docs.fedoraproject.org/en-US/epel/) repository:
```
$ 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
$ sudo dnf config-manager --set-enabled crb
$ sudo dnf install -y \
https://dl.fedoraproject.org/pub/epel/epel-release-latest-9.noarch.rpm \
https://dl.fedoraproject.org/pub/epel/epel-next-release-latest-9.noarch.rpm
$ sudo dnf install -y ripgrep
```
If you're a **Nix** user, you can install ripgrep from
[nixpkgs](https://github.com/NixOS/nixpkgs/blob/master/pkgs/tools/text/ripgrep/default.nix):
[nixpkgs](https://github.com/NixOS/nixpkgs/blob/master/pkgs/by-name/ri/ripgrep/package.nix):
```
$ nix-env --install ripgrep
```
If you're a **Flox** user, you can install ripgrep as follows:
```
$ flox install ripgrep
```
If you're a **Guix** user, you can install ripgrep from the official
package collection:
```
$ sudo guix install ripgrep
$ guix install ripgrep
```
If you're a **Debian** user (or a user of a Debian derivative like **Ubuntu**),
@@ -291,8 +338,8 @@ then ripgrep can be installed using a binary `.deb` file provided in each
[ripgrep release](https://github.com/BurntSushi/ripgrep/releases).
```
$ curl -LO https://github.com/BurntSushi/ripgrep/releases/download/13.0.0/ripgrep_13.0.0_amd64.deb
$ sudo dpkg -i ripgrep_13.0.0_amd64.deb
$ curl -LO https://github.com/BurntSushi/ripgrep/releases/download/14.1.1/ripgrep_14.1.1-1_amd64.deb
$ sudo dpkg -i ripgrep_14.1.1-1_amd64.deb
```
If you run Debian stable, ripgrep is [officially maintained by
@@ -358,9 +405,16 @@ same port as Haiku x86_64 using the x86 secondary architecture build:
$ sudo pkgman install ripgrep_x86
```
If you're a **Void Linux** user, then you can install ripgrep from the
[official repository](https://voidlinux.org/packages/?arch=x86_64&q=ripgrep):
```
$ sudo xbps-install -Syv ripgrep
```
If you're a **Rust programmer**, ripgrep can be installed with `cargo`.
* Note that the minimum supported version of Rust for ripgrep is **1.70.0**,
* Note that the minimum supported version of Rust for ripgrep is **1.88.0**,
although ripgrep may work with older versions.
* Note that the binary may be bigger than expected because it contains debug
symbols. This is intentional. To remove debug symbols and therefore reduce
@@ -383,7 +437,7 @@ $ cargo binstall 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 1.70.0 (stable) or newer. In general, ripgrep tracks
ripgrep compiles with Rust 1.88.0 (stable) or newer. In general, ripgrep tracks
the latest stable release of the Rust compiler.
To build ripgrep:
@@ -396,18 +450,13 @@ $ ./target/release/rg --version
0.1.3
```
If you have a Rust nightly compiler and a recent Intel CPU, then you can enable
additional optional SIMD acceleration like so:
```
RUSTFLAGS="-C target-cpu=native" cargo build --release --features 'simd-accel'
```
The `simd-accel` feature enables SIMD support in certain ripgrep dependencies
(responsible for transcoding). They are not necessary to get SIMD optimizations
for search; those are enabled automatically. Hopefully, some day, the
`simd-accel` feature will similarly become unnecessary. **WARNING:** Currently,
enabling this option can increase compilation times dramatically.
**NOTE:** In the past, ripgrep supported a `simd-accel` Cargo feature when
using a Rust nightly compiler. This only benefited UTF-16 transcoding.
Since it required unstable features, this build mode was prone to breakage.
Because of that, support for it has been removed. If you want SIMD
optimizations for UTF-16 transcoding, then you'll have to petition the
[`encoding_rs`](https://github.com/hsivonen/encoding_rs) project to use stable
APIs.
Finally, optional PCRE2 support can be built with ripgrep by enabling the
`pcre2` feature:
@@ -416,9 +465,6 @@ Finally, optional PCRE2 support can be built with ripgrep by enabling the
$ cargo build --release --features 'pcre2'
```
(Tip: use `--features 'pcre2 simd-accel'` to also include compile time SIMD
optimizations, which will only work with a nightly compiler.)
Enabling the PCRE2 feature works with a stable Rust compiler and will
attempt to automatically find and link with your system's PCRE2 library via
`pkg-config`. If one doesn't exist, then ripgrep will build PCRE2 from source

27
build.rs
View File

@@ -22,7 +22,7 @@ fn set_windows_exe_options() {
manifest.push(MANIFEST);
let Some(manifest) = manifest.to_str() else { return };
println!("cargo:rerun-if-changed={}", MANIFEST);
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}");
@@ -37,10 +37,25 @@ fn set_git_revision_hash() {
use std::process::Command;
let args = &["rev-parse", "--short=10", "HEAD"];
let Ok(output) = Command::new("git").args(args).output() else { return };
let rev = String::from_utf8_lossy(&output.stdout).trim().to_string();
if rev.is_empty() {
return;
let output = Command::new("git").args(args).output();
match output {
Ok(output) => {
let rev =
String::from_utf8_lossy(&output.stdout).trim().to_string();
if rev.is_empty() {
println!(
"cargo:warning=output from `git rev-parse` is empty, \
so skipping embedding of commit hash"
);
return;
}
println!("cargo:rustc-env=RIPGREP_BUILD_GIT_HASH={rev}");
}
Err(e) => {
println!(
"cargo:warning=failed to run `git rev-parse`, \
so skipping embedding of commit hash: {e}"
);
}
}
println!("cargo:rustc-env=RIPGREP_BUILD_GIT_HASH={}", rev);
}

23
ci/docker/README.md
View File

@@ -1,23 +0,0 @@
These are Docker images used for cross compilation in CI builds (or locally)
via the [Cross](https://github.com/rust-embedded/cross) tool.
The Cross tool actually provides its own Docker images, and all Docker images
in this directory are derived from one of them. We provide our own in order to
customize the environment. For example, we need to install compression tools
like `xz` so that tests for the `-z/--search-zip` flag are run.
If you make a change to a Docker image, then you can re-build it. `cd` into the
directory containing the `Dockerfile` and run:
$ cd x86_64-unknown-linux-musl
$ ./build
At this point, subsequent uses of `cross` will now use your built image since
Docker prefers local images over remote images. In order to make these changes
stick, they need to be pushed to Docker Hub:
$ docker push burntsushi/cross:x86_64-unknown-linux-musl
Of course, only I (BurntSushi) can push to that location. To make `cross` use
a different location, then edit `Cross.toml` in the root of this repo to use
a different image name for the desired target.

4
ci/docker/aarch64-unknown-linux-gnu/Dockerfile
View File

@@ -1,4 +0,0 @@
FROM rustembedded/cross:aarch64-unknown-linux-gnu
COPY stage/ubuntu-install-packages /
RUN /ubuntu-install-packages

5
ci/docker/aarch64-unknown-linux-gnu/build
View File

@@ -1,5 +0,0 @@
#!/bin/sh
mkdir -p stage
cp ../../ubuntu-install-packages ./stage/
docker build -t burntsushi/cross:aarch64-unknown-linux-gnu .

4
ci/docker/i686-unknown-linux-gnu/Dockerfile
View File

@@ -1,4 +0,0 @@
FROM rustembedded/cross:i686-unknown-linux-gnu
COPY stage/ubuntu-install-packages /
RUN /ubuntu-install-packages

5
ci/docker/i686-unknown-linux-gnu/build
View File

@@ -1,5 +0,0 @@
#!/bin/sh
mkdir -p stage
cp ../../ubuntu-install-packages ./stage/
docker build -t burntsushi/cross:i686-unknown-linux-gnu .

4
ci/docker/powerpc64-unknown-linux-gnu/Dockerfile
View File

@@ -1,4 +0,0 @@
FROM rustembedded/cross:powerpc64-unknown-linux-gnu
COPY stage/ubuntu-install-packages /
RUN /ubuntu-install-packages

5
ci/docker/powerpc64-unknown-linux-gnu/build
View File

@@ -1,5 +0,0 @@
#!/bin/sh
mkdir -p stage
cp ../../ubuntu-install-packages ./stage/
docker build -t burntsushi/cross:powerpc64-unknown-linux-gnu .

4
ci/docker/s390x-unknown-linux-gnu/Dockerfile
View File

@@ -1,4 +0,0 @@
FROM rustembedded/cross:s390x-unknown-linux-gnu
COPY stage/ubuntu-install-packages /
RUN /ubuntu-install-packages

5
ci/docker/s390x-unknown-linux-gnu/build
View File

@@ -1,5 +0,0 @@
#!/bin/sh
mkdir -p stage
cp ../../ubuntu-install-packages ./stage/
docker build -t burntsushi/cross:s390x-unknown-linux-gnu .

4
ci/docker/x86_64-unknown-linux-musl/Dockerfile
View File

@@ -1,4 +0,0 @@
FROM rustembedded/cross:x86_64-unknown-linux-musl
COPY stage/ubuntu-install-packages /
RUN /ubuntu-install-packages

5
ci/docker/x86_64-unknown-linux-musl/build
View File

@@ -1,5 +0,0 @@
#!/bin/sh
mkdir -p stage
cp ../../ubuntu-install-packages ./stage/
docker build -t burntsushi/cross:x86_64-unknown-linux-musl .

2
ci/ubuntu-install-packages
View File

@@ -11,4 +11,4 @@ if ! command -V sudo; then
fi
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
zsh xz-utils liblz4-tool musl-tools brotli zstd
zsh xz-utils liblz4-tool musl-tools brotli zstd g++

4
crates/cli/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-cli"
version = "0.1.10" #:version
version = "0.1.11" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Utilities for search oriented command line applications.
@@ -15,7 +15,7 @@ edition = "2021"
[dependencies]
bstr = { version = "1.6.2", features = ["std"] }
globset = { version = "0.4.14", path = "../globset" }
globset = { version = "0.4.15", path = "../globset" }
log = "0.4.20"
termcolor = "1.3.0"

4
crates/cli/src/hostname.rs
View File

@@ -25,10 +25,10 @@ pub fn hostname() -> io::Result<OsString> {
}
#[cfg(not(any(windows, unix)))]
{
io::Error::new(
Err(io::Error::new(
io::ErrorKind::Other,
"hostname could not be found on unsupported platform",
)
))
}
}

61
crates/cli/src/lib.rs
View File

@@ -178,22 +178,71 @@ pub fn is_readable_stdin() -> bool {
};
let stdin = std::io::stdin();
let Ok(fd) = stdin.as_fd().try_clone_to_owned() else { return false };
let fd = match stdin.as_fd().try_clone_to_owned() {
Ok(fd) => fd,
Err(err) => {
log::debug!(
"for heuristic stdin detection on Unix, \
could not clone stdin file descriptor \
(thus assuming stdin is not readable): {err}",
);
return false;
}
};
let file = File::from(fd);
let Ok(md) = file.metadata() else { return false };
let md = match file.metadata() {
Ok(md) => md,
Err(err) => {
log::debug!(
"for heuristic stdin detection on Unix, \
could not get file metadata for stdin \
(thus assuming stdin is not readable): {err}",
);
return false;
}
};
let ft = md.file_type();
ft.is_file() || ft.is_fifo() || ft.is_socket()
let is_file = ft.is_file();
let is_fifo = ft.is_fifo();
let is_socket = ft.is_socket();
let is_readable = is_file || is_fifo || is_socket;
log::debug!(
"for heuristic stdin detection on Unix, \
found that \
is_file={is_file}, is_fifo={is_fifo} and is_socket={is_socket}, \
and thus concluded that is_stdin_readable={is_readable}",
);
is_readable
}
#[cfg(windows)]
fn imp() -> bool {
winapi_util::file::typ(winapi_util::HandleRef::stdin())
.map(|t| t.is_disk() || t.is_pipe())
.unwrap_or(false)
let stdin = winapi_util::HandleRef::stdin();
let typ = match winapi_util::file::typ(stdin) {
Ok(typ) => typ,
Err(err) => {
log::debug!(
"for heuristic stdin detection on Windows, \
could not get file type of stdin \
(thus assuming stdin is not readable): {err}",
);
return false;
}
};
let is_disk = typ.is_disk();
let is_pipe = typ.is_pipe();
let is_readable = is_disk || is_pipe;
log::debug!(
"for heuristic stdin detection on Windows, \
found that is_disk={is_disk} and is_pipe={is_pipe}, \
and thus concluded that is_stdin_readable={is_readable}",
);
is_readable
}
#[cfg(not(any(unix, windows)))]
fn imp() -> bool {
log::debug!("on non-{{Unix,Windows}}, assuming stdin is not readable");
false
}

2
crates/cli/src/wtr.rs
View File

@@ -1,6 +1,6 @@
use std::io::{self, IsTerminal};
use termcolor::{self, HyperlinkSpec};
use termcolor::HyperlinkSpec;
/// A writer that supports coloring with either line or block buffering.
#[derive(Debug)]

29
crates/core/flags/complete/encodings.sh Normal file
View File

@@ -0,0 +1,29 @@
# This is impossible to read, but these encodings rarely if ever change, so
# it probably does not matter. They are derived from the list given here:
# https://encoding.spec.whatwg.org/#concept-encoding-get
#
# The globbing here works in both fish and zsh (though they expand it in
# different orders). It may work in other shells too.
{{,us-}ascii,arabic,chinese,cyrillic,greek{,8},hebrew,korean}
logical visual mac {,cs}macintosh x-mac-{cyrillic,roman,ukrainian}
866 ibm{819,866} csibm866
big5{,-hkscs} {cn-,cs}big5 x-x-big5
cp{819,866,125{0,1,2,3,4,5,6,7,8}} x-cp125{0,1,2,3,4,5,6,7,8}
csiso2022{jp,kr} csiso8859{6,8}{e,i}
csisolatin{1,2,3,4,5,6,9} csisolatin{arabic,cyrillic,greek,hebrew}
ecma-{114,118} asmo-708 elot_928 sun_eu_greek
euc-{jp,kr} x-euc-jp cseuckr cseucpkdfmtjapanese
{,x-}gbk csiso58gb231280 gb18030 {,cs}gb2312 gb_2312{,-80} hz-gb-2312
iso-2022-{cn,cn-ext,jp,kr}
iso8859{,-}{1,2,3,4,5,6,7,8,9,10,11,13,14,15}
iso-8859-{1,2,3,4,5,6,7,8,9,10,11,{6,8}-{e,i},13,14,15,16} iso_8859-{1,2,3,4,5,6,7,8,9,15}
iso_8859-{1,2,6,7}:1987 iso_8859-{3,4,5,8}:1988 iso_8859-9:1989
iso-ir-{58,100,101,109,110,126,127,138,144,148,149,157}
koi{,8,8-r,8-ru,8-u,8_r} cskoi8r
ks_c_5601-{1987,1989} ksc{,_}5691 csksc56011987
latin{1,2,3,4,5,6} l{1,2,3,4,5,6,9}
shift{-,_}jis csshiftjis {,x-}sjis ms_kanji ms932
utf{,-}8 utf-16{,be,le} unicode-1-1-utf-8
windows-{31j,874,949,125{0,1,2,3,4,5,6,7,8}} dos-874 tis-620 ansi_x3.4-1968
x-user-defined auto none

76
crates/core/flags/complete/fish.rs
View File

@@ -2,43 +2,71 @@
Provides completions for ripgrep's CLI for the fish shell.
*/
use crate::flags::defs::FLAGS;
use crate::flags::{defs::FLAGS, CompletionType};
const TEMPLATE: &'static str =
"complete -c rg -n '__fish_use_subcommand' !SHORT! !LONG! !DOC!\n";
const TEMPLATE_CHOICES: &'static str =
"complete -c rg -n '__fish_use_subcommand' !SHORT! !LONG! !DOC! -r -f -a '!CHOICES!'\n";
const TEMPLATE: &'static str = "complete -c rg !SHORT! -l !LONG! -d '!DOC!'";
const TEMPLATE_NEGATED: &'static str =
"complete -c rg -l !NEGATED! -n '__rg_contains_opt !LONG! !SHORT!' -d '!DOC!'\n";
/// Generate completions for Fish.
///
/// Note that these completions are based on what was produced for ripgrep <=13
/// using Clap 2.x. Improvements on this are welcome.
/// Reference: <https://fishshell.com/docs/current/completions.html>
pub(crate) fn generate() -> String {
let mut out = String::new();
out.push_str(include_str!("prelude.fish"));
out.push('\n');
for flag in FLAGS.iter() {
let short = match flag.name_short() {
None => "".to_string(),
Some(byte) => format!("-s {}", char::from(byte)),
};
let long = format!("-l '{}'", flag.name_long().replace("'", "\\'"));
let doc = format!("-d '{}'", flag.doc_short().replace("'", "\\'"));
let template = if flag.doc_choices().is_empty() {
TEMPLATE.to_string()
} else {
TEMPLATE_CHOICES
.replace("!CHOICES!", &flag.doc_choices().join(" "))
};
out.push_str(
&template
.replace("!SHORT!", &short)
.replace("!LONG!", &long)
.replace("!DOC!", &doc),
);
let long = flag.name_long();
let doc = flag.doc_short().replace("'", "\\'");
let mut completion = TEMPLATE
.replace("!SHORT!", &short)
.replace("!LONG!", &long)
.replace("!DOC!", &doc);
match flag.completion_type() {
CompletionType::Filename => {
completion.push_str(" -r -F");
}
CompletionType::Executable => {
completion.push_str(" -r -f -a '(__fish_complete_command)'");
}
CompletionType::Filetype => {
completion.push_str(
" -r -f -a '(rg --type-list | string replace : \\t)'",
);
}
CompletionType::Encoding => {
completion.push_str(" -r -f -a '");
completion.push_str(super::ENCODINGS);
completion.push_str("'");
}
CompletionType::Other if !flag.doc_choices().is_empty() => {
completion.push_str(" -r -f -a '");
completion.push_str(&flag.doc_choices().join(" "));
completion.push_str("'");
}
CompletionType::Other if !flag.is_switch() => {
completion.push_str(" -r -f");
}
CompletionType::Other => (),
}
completion.push('\n');
out.push_str(&completion);
if let Some(negated) = flag.name_negated() {
let long = format!("-l '{}'", negated.replace("'", "\\'"));
let short = match flag.name_short() {
None => "".to_string(),
Some(byte) => char::from(byte).to_string(),
};
out.push_str(
&TEMPLATE
.replace("!SHORT!", "")
&TEMPLATE_NEGATED
.replace("!NEGATED!", &negated)
.replace("!SHORT!", &short)
.replace("!LONG!", &long)
.replace("!DOC!", &doc),
);

2
crates/core/flags/complete/mod.rs
View File

@@ -2,6 +2,8 @@
Modules for generating completions for various shells.
*/
static ENCODINGS: &'static str = include_str!("encodings.sh");
pub(super) mod bash;
pub(super) mod fish;
pub(super) mod powershell;

2
crates/core/flags/complete/powershell.rs
View File

@@ -72,7 +72,7 @@ pub(crate) fn generate() -> String {
}
if let Some(negated) = flag.name_negated() {
let dash_name = format!("--{}", negated);
let dash_name = format!("--{negated}");
flags.push_str("\n ");
flags.push_str(
&TEMPLATE_FLAG

31
crates/core/flags/complete/prelude.fish Normal file
View File

@@ -0,0 +1,31 @@
# Usage: __rg_contains_opt LONG [SHORT]
function __rg_contains_opt --description 'Specialized __fish_contains_opt'
# Cache the config file because this function is called many times per
# completion attempt.
# The cache will persist for the entire shell session (even if the
# variable or the file contents change).
if not set -q __rg_config
set -g __rg_config
if set -qx RIPGREP_CONFIG_PATH
set __rg_config (
cat -- $RIPGREP_CONFIG_PATH 2>/dev/null \
| string trim \
| string match -rv '^$|^#'
)
end
end
set -l commandline (commandline -cpo) (commandline -ct) $__rg_config
if contains -- "--$argv[1]" $commandline
return 0
end
if set -q argv[2]
if string match -qr -- "^-[^-]*$argv[2]" $commandline
return 0
end
end
return 1
end

39
crates/core/flags/complete/rg.zsh
View File

@@ -363,10 +363,11 @@ _rg() {
'column:specify coloring for column numbers'
'line:specify coloring for line numbers'
'match:specify coloring for match text'
'highlight:specify coloring for matching lines'
'path:specify coloring for file names'
)
descr='color/style type'
elif [[ ${IPREFIX#--*=}$PREFIX == (column|line|match|path):[^:]# ]]; then
elif [[ ${IPREFIX#--*=}$PREFIX == (column|line|match|highlight|path):[^:]# ]]; then
suf=( -qS: )
tmp=(
'none:clear color/style for type'
@@ -413,32 +414,8 @@ _rg_encodings() {
local -a expl
local -aU _encodings
# This is impossible to read, but these encodings rarely if ever change, so it
# probably doesn't matter. They are derived from the list given here:
# https://encoding.spec.whatwg.org/#concept-encoding-get
_encodings=(
{{,us-}ascii,arabic,chinese,cyrillic,greek{,8},hebrew,korean}
logical visual mac {,cs}macintosh x-mac-{cyrillic,roman,ukrainian}
866 ibm{819,866} csibm866
big5{,-hkscs} {cn-,cs}big5 x-x-big5
cp{819,866,125{0..8}} x-cp125{0..8}
csiso2022{jp,kr} csiso8859{6,8}{e,i}
csisolatin{{1..6},9} csisolatin{arabic,cyrillic,greek,hebrew}
ecma-{114,118} asmo-708 elot_928 sun_eu_greek
euc-{jp,kr} x-euc-jp cseuckr cseucpkdfmtjapanese
{,x-}gbk csiso58gb231280 gb18030 {,cs}gb2312 gb_2312{,-80} hz-gb-2312
iso-2022-{cn,cn-ext,jp,kr}
iso8859{,-}{{1..11},13,14,15}
iso-8859-{{1..11},{6,8}-{e,i},13,14,15,16} iso_8859-{{1..9},15}
iso_8859-{1,2,6,7}:1987 iso_8859-{3,4,5,8}:1988 iso_8859-9:1989
iso-ir-{58,100,101,109,110,126,127,138,144,148,149,157}
koi{,8,8-r,8-ru,8-u,8_r} cskoi8r
ks_c_5601-{1987,1989} ksc{,_}5691 csksc56011987
latin{1..6} l{{1..6},9}
shift{-,_}jis csshiftjis {,x-}sjis ms_kanji ms932
utf{,-}8 utf-16{,be,le} unicode-1-1-utf-8
windows-{31j,874,949,125{0..8}} dos-874 tis-620 ansi_x3.4-1968
x-user-defined auto none
!ENCODINGS!
)
_wanted encodings expl encoding compadd -a "$@" - _encodings
@@ -458,7 +435,15 @@ _rg_types() {
fi
}
_rg "$@"
# Don't run the completion function when being sourced by itself.
#
# See https://github.com/BurntSushi/ripgrep/issues/2956
# See https://github.com/BurntSushi/ripgrep/pull/2957
if [[ $funcstack[1] == _rg ]] || (( ! $+functions[compdef] )); then
_rg "$@"
else
compdef _rg rg
fi
################################################################################
# ZSH COMPLETION REFERENCE

2
crates/core/flags/complete/zsh.rs
View File

@@ -19,5 +19,5 @@ long as it meets criteria 3 and 4 above.
/// Generate completions for zsh.
pub(crate) fn generate() -> String {
include_str!("rg.zsh").to_string()
include_str!("rg.zsh").replace("!ENCODINGS!", super::ENCODINGS.trim_end())
}

96
crates/core/flags/defs.rs
View File

@@ -34,6 +34,8 @@ use crate::flags::{
#[cfg(test)]
use crate::flags::parse::parse_low_raw;
use super::CompletionType;
/// A list of all flags in ripgrep via implementations of `Flag`.
///
/// The order of these flags matter. It determines the order of the flags in
@@ -749,7 +751,8 @@ the \flag{colors} flag to manually set all color styles to \fBnone\fP:
\-\-colors 'path:none' \\
\-\-colors 'line:none' \\
\-\-colors 'column:none' \\
\-\-colors 'match:none'
\-\-colors 'match:none' \\
\-\-colors 'highlight:none'
.EE
.sp
"
@@ -827,21 +830,21 @@ impl Flag for Colors {
"Configure color settings and styles."
}
fn doc_long(&self) -> &'static str {
r"
r#"
This flag specifies color settings for use in the output. This flag may be
provided multiple times. Settings are applied iteratively. Pre-existing color
labels are limited to one of eight choices: \fBred\fP, \fBblue\fP, \fBgreen\fP,
\fBcyan\fP, \fBmagenta\fP, \fByellow\fP, \fBwhite\fP and \fBblack\fP. Styles
are limited to \fBnobold\fP, \fBbold\fP, \fBnointense\fP, \fBintense\fP,
\fBnounderline\fP or \fBunderline\fP.
\fBnounderline\fP, \fBunderline\fP, \fBnoitalic\fP or \fBitalic\fP.
.sp
The format of the flag is
\fB{\fP\fItype\fP\fB}:{\fP\fIattribute\fP\fB}:{\fP\fIvalue\fP\fB}\fP.
\fItype\fP should be one of \fBpath\fP, \fBline\fP, \fBcolumn\fP or
\fBmatch\fP. \fIattribute\fP can be \fBfg\fP, \fBbg\fP or \fBstyle\fP.
\fIvalue\fP is either a color (for \fBfg\fP and \fBbg\fP) or a text style. A
special format, \fB{\fP\fItype\fP\fB}:none\fP, will clear all color settings
for \fItype\fP.
\fItype\fP should be one of \fBpath\fP, \fBline\fP, \fBcolumn\fP,
\fBhighlight\fP or \fBmatch\fP. \fIattribute\fP can be \fBfg\fP, \fBbg\fP or
\fBstyle\fP. \fIvalue\fP is either a color (for \fBfg\fP and \fBbg\fP) or a
text style. A special format, \fB{\fP\fItype\fP\fB}:none\fP, will clear all
color settings for \fItype\fP.
.sp
For example, the following command will change the match color to magenta and
the background color for line numbers to yellow:
@@ -850,6 +853,17 @@ the background color for line numbers to yellow:
rg \-\-colors 'match:fg:magenta' \-\-colors 'line:bg:yellow'
.EE
.sp
Another example, the following command will "highlight" the non-matching text
in matching lines:
.sp
.EX
rg \-\-colors 'highlight:bg:yellow' \-\-colors 'highlight:fg:black'
.EE
.sp
The "highlight" color type is particularly useful for contrasting matching
lines with surrounding context printed by the \flag{before-context},
\flag{after-context}, \flag{context} or \flag{passthru} flags.
.sp
Extended colors can be used for \fIvalue\fP when the tty supports ANSI color
sequences. These are specified as either \fIx\fP (256-color) or
.IB x , x , x
@@ -872,7 +886,7 @@ or, equivalently,
.sp
Note that the \fBintense\fP and \fBnointense\fP styles will have no effect when
used alongside these extended color codes.
"
"#
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
@@ -906,6 +920,24 @@ fn test_colors() {
"line:bg:yellow".parse().unwrap()
]
);
let args = parse_low_raw(["--colors", "highlight:bg:240"]).unwrap();
assert_eq!(args.colors, vec!["highlight:bg:240".parse().unwrap()]);
let args = parse_low_raw([
"--colors",
"match:fg:magenta",
"--colors",
"highlight:bg:blue",
])
.unwrap();
assert_eq!(
args.colors,
vec![
"match:fg:magenta".parse().unwrap(),
"highlight:bg:blue".parse().unwrap()
]
);
}
/// --column
@@ -1582,6 +1614,9 @@ The encoding detection that ripgrep uses can be reverted to its automatic mode
via the \flag-negate{encoding} flag.
"
}
fn completion_type(&self) -> CompletionType {
CompletionType::Encoding
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
let value = match v {
@@ -1977,6 +2012,9 @@ When \flag{file} or \flag{regexp} is used, then ripgrep treats all positional
arguments as files or directories to search.
"
}
fn completion_type(&self) -> CompletionType {
CompletionType::Filename
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
let path = PathBuf::from(v.unwrap_value());
@@ -2619,7 +2657,7 @@ of printing the file path as a prefix for each matched line.
This is the default mode when printing to a tty.
.sp
When \fBstdout\fP is not a tty, then ripgrep will default to the standard
grep-like format. Once can force this format in Unix-like environments by
grep-like format. One can force this format in Unix-like environments by
piping the output of ripgrep to \fBcat\fP. For example, \fBrg\fP \fIfoo\fP \fB|
cat\fP.
"
@@ -2738,12 +2776,17 @@ impl Flag for Hidden {
Search hidden files and directories. By default, hidden files and directories
are skipped. Note that if a hidden file or a directory is whitelisted in
an ignore file, then it will be searched even if this flag isn't provided.
Similarly if a hidden file or directory is given explicitly as an argumnet to
Similarly if a hidden file or directory is given explicitly as an argument to
ripgrep.
.sp
A file or directory is considered hidden if its base name starts with a dot
character (\fB.\fP). On operating systems which support a "hidden" file
attribute, like Windows, files with this attribute are also considered hidden.
.sp
Note that \flag{hidden} will include files and folders like \fB.git\fP
regardless of \flag{no-ignore-vcs}. To exclude such paths when using
\flag{hidden}, you must explicitly ignore them using another flag or ignore
file.
"#
}
@@ -2808,6 +2851,9 @@ to calling \fBgethostname\fP. On Windows, this corresponds to calling
ripgrep uses your system's hostname for producing hyperlinks.
"#
}
fn completion_type(&self) -> CompletionType {
CompletionType::Executable
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
let path = PathBuf::from(v.unwrap_value());
@@ -3141,6 +3187,9 @@ If you are looking for a way to include or exclude files and directories
directly on the command line, then use \flag{glob} instead.
"
}
fn completion_type(&self) -> CompletionType {
CompletionType::Filename
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
let path = PathBuf::from(v.unwrap_value());
@@ -4589,11 +4638,15 @@ impl Flag for NoIgnoreVcs {
}
fn doc_long(&self) -> &'static str {
r"
When given, filter rules from source control ignore files (e.g., \fB.gitignore\fP)
are not respected. By default, ripgrep respects \fBgit\fP's ignore rules for
automatic filtering. In some cases, it may not be desirable to respect the
source control's ignore rules and instead only respect rules in \fB.ignore\fP
or \fB.rgignore\fP.
When given, filter rules from source control ignore files (e.g.,
\fB.gitignore\fP) are not respected. By default, ripgrep respects \fBgit\fP's
ignore rules for automatic filtering. In some cases, it may not be desirable
to respect the source control's ignore rules and instead only respect rules in
\fB.ignore\fP or \fB.rgignore\fP.
.sp
Note that this flag does not directly affect the filtering of source control
files or folders that start with a dot (\fB.\fP), like \fB.git\fP. These are
affected by \flag{hidden} and its related flags instead.
.sp
This flag implies \flag{no-ignore-parent} for source control ignore files as
well.
@@ -5410,6 +5463,9 @@ format, then \fBpzstd\fP is used to decompress the contents to stdout.
This overrides the \flag{search-zip} flag.
"#
}
fn completion_type(&self) -> CompletionType {
CompletionType::Executable
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
let path = match v {
@@ -6781,6 +6837,9 @@ any rules found in ignore files.
To see the list of available file types, use the \flag{type-list} flag.
"#
}
fn completion_type(&self) -> CompletionType {
CompletionType::Filetype
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
args.type_changes.push(TypeChange::Select {
@@ -7000,6 +7059,9 @@ will only search files that are unrecognized by its type definitions.
To see the list of available file types, use the \flag{type-list} flag.
"#
}
fn completion_type(&self) -> CompletionType {
CompletionType::Filetype
}
fn update(&self, v: FlagValue, args: &mut LowArgs) -> anyhow::Result<()> {
args.type_changes.push(TypeChange::Negate {
@@ -7238,7 +7300,7 @@ impl Flag for Vimgrep {
Category::Output
}
fn doc_short(&self) -> &'static str {
r"Print results im a vim compatible format."
r"Print results in a vim compatible format."
}
fn doc_long(&self) -> &'static str {
r"

10
crates/core/flags/doc/template.rg.1
View File

@@ -1,4 +1,4 @@
.TH RG 1 2023-11-26 "!!VERSION!!" "User Commands"
.TH RG 1 2024-09-08 "!!VERSION!!" "User Commands"
.
.
.SH NAME
@@ -43,10 +43,10 @@ configuration file. The file can specify one shell argument per line. Lines
starting with \fB#\fP are ignored. For more details, see \fBCONFIGURATION
FILES\fP below.
.sp
ripgrep will automatically detect if stdin exists and search stdin for a regex
pattern, e.g. \fBls | rg foo\fP. In some environments, stdin may exist when
it shouldn't. To turn off stdin detection, one can explicitly specify the
directory to search, e.g. \fBrg foo ./\fP.
ripgrep will automatically detect if stdin is a readable file and search stdin
for a regex pattern, e.g. \fBls | rg foo\fP. In some environments, stdin may
exist when it shouldn't. To turn off stdin detection, one can explicitly
specify the directory to search, e.g. \fBrg foo ./\fP.
.sp
Like other tools such as \fBls\fP, ripgrep will alter its output depending on
whether stdout is connected to a tty. By default, when printing a tty, ripgrep

3
crates/core/flags/doc/version.rs
View File

@@ -161,9 +161,6 @@ fn compile_cpu_features() -> Vec<String> {
fn features() -> Vec<String> {
let mut features = vec![];
let simd_accel = cfg!(feature = "simd-accel");
features.push(format!("{sign}simd-accel", sign = sign(simd_accel)));
let pcre2 = cfg!(feature = "pcre2");
features.push(format!("{sign}pcre2", sign = sign(pcre2)));

29
crates/core/flags/hiargs.rs
View File

@@ -484,9 +484,9 @@ impl HiArgs {
if self.crlf {
builder.crlf(true);
}
// We don't need to set this in multiline mode since mulitline
// We don't need to set this in multiline mode since multiline
// matchers don't use optimizations related to line terminators.
// Moreover, a mulitline regex used with --null-data should
// Moreover, a multiline regex used with --null-data should
// be allowed to match NUL bytes explicitly, which this would
// otherwise forbid.
if self.null_data {
@@ -517,7 +517,7 @@ impl HiArgs {
/// When this returns false, it is impossible for ripgrep to ever report
/// a match.
pub(crate) fn matches_possible(&self) -> bool {
if self.patterns.patterns.is_empty() {
if self.patterns.patterns.is_empty() && !self.invert_match {
return false;
}
if self.max_count == Some(0) {
@@ -562,7 +562,16 @@ impl HiArgs {
wtr: W,
) -> Printer<W> {
let summary_kind = if self.quiet {
SummaryKind::Quiet
match search_mode {
SearchMode::FilesWithMatches
| SearchMode::Count
| SearchMode::CountMatches
| SearchMode::JSON
| SearchMode::Standard => SummaryKind::QuietWithMatch,
SearchMode::FilesWithoutMatch => {
SummaryKind::QuietWithoutMatch
}
}
} else {
match search_mode {
SearchMode::FilesWithMatches => SummaryKind::PathWithMatch,
@@ -589,6 +598,7 @@ impl HiArgs {
.pretty(false)
.max_matches(self.max_count)
.always_begin_end(false)
.replacement(self.replace.clone().map(|r| r.into()))
.build(wtr)
}
@@ -1080,9 +1090,18 @@ impl Paths {
}
paths.push(path);
}
log::debug!("number of paths given to search: {}", paths.len());
if !paths.is_empty() {
let is_one_file = paths.len() == 1
&& (paths[0] == Path::new("-") || paths[0].is_file());
// Note that we specifically use `!paths[0].is_dir()` here
// instead of `paths[0].is_file()`. Namely, the latter can
// return `false` even when the path is something resembling
// a file. So instead, we just consider the path a file as
// long as we know it isn't a directory.
//
// See: https://github.com/BurntSushi/ripgrep/issues/2736
&& (paths[0] == Path::new("-") || !paths[0].is_dir());
log::debug!("is_one_file? {is_one_file:?}");
return Ok(Paths { paths, has_implicit_path: false, is_one_file });
}
// N.B. is_readable_stdin is a heuristic! Part of the issue is that a

21
crates/core/flags/mod.rs
View File

@@ -70,7 +70,7 @@ mod parse;
/// value. Flags that accept multiple values are an unsupported abberation.
trait Flag: Debug + Send + Sync + UnwindSafe + RefUnwindSafe + 'static {
/// Returns true if this flag is a switch. When a flag is a switch, the
/// CLI parser will look for a value after the flag is seen.
/// CLI parser will not look for a value after the flag is seen.
fn is_switch(&self) -> bool;
/// A short single byte name for this flag. This returns `None` by default,
@@ -150,6 +150,10 @@ trait Flag: Debug + Send + Sync + UnwindSafe + RefUnwindSafe + 'static {
&[]
}
fn completion_type(&self) -> CompletionType {
CompletionType::Other
}
/// Given the parsed value (which might just be a switch), this should
/// update the state in `args` based on the value given for this flag.
///
@@ -228,6 +232,21 @@ impl Category {
}
}
/// The kind of argument a flag accepts, to be used for shell completions.
#[derive(Clone, Copy, Debug)]
enum CompletionType {
/// No special category. is_switch() and doc_choices() may apply.
Other,
/// A path to a file.
Filename,
/// A command in $PATH.
Executable,
/// The name of a file type, as used by e.g. --type.
Filetype,
/// The name of an encoding_rs encoding, as used by --encoding.
Encoding,
}
/// Represents a value parsed from the command line.
///
/// This doesn't include the corresponding flag, but values come in one of

2
crates/core/flags/parse.rs
View File

@@ -323,7 +323,7 @@ enum FlagLookup<'a> {
UnrecognizedLong(String),
}
/// The info about a flag associated with a flag's ID in the the flag map.
/// The info about a flag associated with a flag's ID in the flag map.
#[derive(Debug)]
struct FlagInfo {
/// The flag object and its associated metadata.

2
crates/core/logger.rs
View File

@@ -6,7 +6,7 @@ print to stderr. We therefore avoid bringing in extra dependencies just for
this functionality.
*/
use log::{self, Log};
use log::Log;
/// The simplest possible logger that logs to stderr.
///

4
crates/core/main.rs
View File

@@ -37,7 +37,7 @@ mod search;
// i686.
#[cfg(all(target_env = "musl", target_pointer_width = "64"))]
#[global_allocator]
static ALLOC: jemallocator::Jemalloc = jemallocator::Jemalloc;
static ALLOC: tikv_jemallocator::Jemalloc = tikv_jemallocator::Jemalloc;
/// Then, as it was, then again it will be.
fn main() -> ExitCode {
@@ -468,7 +468,7 @@ fn print_stats<W: Write>(
{bytes_printed} bytes printed
{bytes_searched} bytes searched
{search_time:0.6} seconds spent searching
{process_time:0.6} seconds
{process_time:0.6} seconds total
",
matches = stats.matches(),
lines = stats.matched_lines(),

28
crates/core/messages.rs
View File

@@ -28,7 +28,7 @@ static ERRORED: AtomicBool = AtomicBool::new(false);
///
/// This locks stdout, not stderr, even though this prints to stderr. This
/// avoids the appearance of interleaving output when stdout and stderr both
/// correspond to a tty.)
/// correspond to a tty.
#[macro_export]
macro_rules! eprintln_locked {
($($tt:tt)*) => {{
@@ -39,21 +39,29 @@ macro_rules! eprintln_locked {
// 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();
let stdout = std::io::stdout().lock();
let mut stderr = std::io::stderr().lock();
// We specifically ignore any errors here. One plausible error we
// can get in some cases is a broken pipe error. And when that
// occurs, we should exit gracefully. Otherwise, just abort with
// an error code because there isn't much else we can do.
//
// See: https://github.com/BurntSushi/ripgrep/issues/1966
if let Err(err) = writeln!(std::io::stderr(), $($tt)*) {
if let Err(err) = write!(stderr, "rg: ") {
if err.kind() == std::io::ErrorKind::BrokenPipe {
std::process::exit(0);
} else {
std::process::exit(2);
}
}
if let Err(err) = writeln!(stderr, $($tt)*) {
if err.kind() == std::io::ErrorKind::BrokenPipe {
std::process::exit(0);
} else {
std::process::exit(2);
}
}
drop(stdout);
}
}}
}
@@ -91,19 +99,19 @@ macro_rules! ignore_message {
/// Returns true if and only if messages should be shown.
pub(crate) fn messages() -> bool {
MESSAGES.load(Ordering::SeqCst)
MESSAGES.load(Ordering::Relaxed)
}
/// Set whether messages should be shown or not.
///
/// By default, they are not shown.
pub(crate) fn set_messages(yes: bool) {
MESSAGES.store(yes, Ordering::SeqCst)
MESSAGES.store(yes, Ordering::Relaxed)
}
/// Returns true if and only if "ignore" related messages should be shown.
pub(crate) fn ignore_messages() -> bool {
IGNORE_MESSAGES.load(Ordering::SeqCst)
IGNORE_MESSAGES.load(Ordering::Relaxed)
}
/// Set whether "ignore" related messages should be shown or not.
@@ -114,12 +122,12 @@ pub(crate) fn ignore_messages() -> bool {
/// `messages` is disabled, then "ignore" messages are never shown, regardless
/// of this setting.
pub(crate) fn set_ignore_messages(yes: bool) {
IGNORE_MESSAGES.store(yes, Ordering::SeqCst)
IGNORE_MESSAGES.store(yes, Ordering::Relaxed)
}
/// Returns true if and only if ripgrep came across a non-fatal error.
pub(crate) fn errored() -> bool {
ERRORED.load(Ordering::SeqCst)
ERRORED.load(Ordering::Relaxed)
}
/// Indicate that ripgrep has come across a non-fatal error.
@@ -127,5 +135,5 @@ pub(crate) fn errored() -> bool {
/// Callers should not use this directly. Instead, it is called automatically
/// via the `err_message` macro.
pub(crate) fn set_errored() {
ERRORED.store(true, Ordering::SeqCst);
ERRORED.store(true, Ordering::Relaxed);
}

5
crates/core/search.rs
View File

@@ -307,15 +307,14 @@ impl<W: WriteColor> SearchWorker<W> {
io::Error::new(
io::ErrorKind::Other,
format!(
"preprocessor command could not start: '{:?}': {}",
cmd, err,
"preprocessor command could not start: '{cmd:?}': {err}",
),
)
})?;
let result = self.search_reader(path, &mut rdr).map_err(|err| {
io::Error::new(
io::ErrorKind::Other,
format!("preprocessor command failed: '{:?}': {}", cmd, err),
format!("preprocessor command failed: '{cmd:?}': {err}"),
)
});
let close_result = rdr.close();

4
crates/globset/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "globset"
version = "0.4.14" #:version
version = "0.4.16" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Cross platform single glob and glob set matching. Glob set matching is the
@@ -21,6 +21,7 @@ bench = false
[dependencies]
aho-corasick = "1.1.1"
arbitrary = { version = "1.3.2", optional = true, features = ["derive"] }
bstr = { version = "1.6.2", default-features = false, features = ["std"] }
log = { version = "0.4.20", optional = true }
serde = { version = "1.0.188", optional = true }
@@ -41,6 +42,7 @@ serde_json = "1.0.107"
[features]
default = ["log"]
arbitrary = ["dep:arbitrary"]
# DEPRECATED. It is a no-op. SIMD is done automatically through runtime
# dispatch.
simd-accel = []

110
crates/globset/src/glob.rs
View File

@@ -1,3 +1,4 @@
use std::fmt::Write;
use std::path::{is_separator, Path};
use regex_automata::meta::Regex;
@@ -70,7 +71,8 @@ impl MatchStrategy {
///
/// It cannot be used directly to match file paths, but it can be converted
/// to a regular expression string or a matcher.
#[derive(Clone, Debug, Eq)]
#[derive(Clone, Eq)]
#[cfg_attr(feature = "arbitrary", derive(arbitrary::Arbitrary))]
pub struct Glob {
glob: String,
re: String,
@@ -78,6 +80,12 @@ pub struct Glob {
tokens: Tokens,
}
impl AsRef<Glob> for Glob {
fn as_ref(&self) -> &Glob {
self
}
}
impl PartialEq for Glob {
fn eq(&self, other: &Glob) -> bool {
self.glob == other.glob && self.opts == other.opts
@@ -91,6 +99,21 @@ impl std::hash::Hash for Glob {
}
}
impl std::fmt::Debug for Glob {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
if f.alternate() {
f.debug_struct("Glob")
.field("glob", &self.glob)
.field("re", &self.re)
.field("opts", &self.opts)
.field("tokens", &self.tokens)
.finish()
} else {
f.debug_tuple("Glob").field(&self.glob).finish()
}
}
}
impl std::fmt::Display for Glob {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
self.glob.fmt(f)
@@ -193,6 +216,7 @@ pub struct GlobBuilder<'a> {
}
#[derive(Clone, Copy, Debug, Eq, Hash, PartialEq)]
#[cfg_attr(feature = "arbitrary", derive(arbitrary::Arbitrary))]
struct GlobOptions {
/// Whether to match case insensitively.
case_insensitive: bool,
@@ -219,6 +243,7 @@ impl GlobOptions {
}
#[derive(Clone, Debug, Default, Eq, PartialEq)]
#[cfg_attr(feature = "arbitrary", derive(arbitrary::Arbitrary))]
struct Tokens(Vec<Token>);
impl std::ops::Deref for Tokens {
@@ -235,6 +260,7 @@ impl std::ops::DerefMut for Tokens {
}
#[derive(Clone, Debug, Eq, PartialEq)]
#[cfg_attr(feature = "arbitrary", derive(arbitrary::Arbitrary))]
enum Token {
Literal(char),
Any,
@@ -563,25 +589,26 @@ impl<'a> GlobBuilder<'a> {
pub fn build(&self) -> Result<Glob, Error> {
let mut p = Parser {
glob: &self.glob,
stack: vec![Tokens::default()],
alternates_stack: Vec::new(),
branches: vec![Tokens::default()],
chars: self.glob.chars().peekable(),
prev: None,
cur: None,
opts: &self.opts,
};
p.parse()?;
if p.stack.is_empty() {
Err(Error {
glob: Some(self.glob.to_string()),
kind: ErrorKind::UnopenedAlternates,
})
} else if p.stack.len() > 1 {
if p.branches.is_empty() {
// OK because of how the the branches/alternate_stack are managed.
// If we end up here, then there *must* be a bug in the parser
// somewhere.
unreachable!()
} else if p.branches.len() > 1 {
Err(Error {
glob: Some(self.glob.to_string()),
kind: ErrorKind::UnclosedAlternates,
})
} else {
let tokens = p.stack.pop().unwrap();
let tokens = p.branches.pop().unwrap();
Ok(Glob {
glob: self.glob.to_string(),
re: tokens.to_regex_with(&self.opts),
@@ -732,7 +759,9 @@ impl Tokens {
/// Convert a Unicode scalar value to an escaped string suitable for use as
/// a literal in a non-Unicode regex.
fn char_to_escaped_literal(c: char) -> String {
bytes_to_escaped_literal(&c.to_string().into_bytes())
let mut buf = [0; 4];
let bytes = c.encode_utf8(&mut buf).as_bytes();
bytes_to_escaped_literal(bytes)
}
/// Converts an arbitrary sequence of bytes to a UTF-8 string. All non-ASCII
@@ -741,11 +770,12 @@ fn bytes_to_escaped_literal(bs: &[u8]) -> String {
let mut s = String::with_capacity(bs.len());
for &b in bs {
if b <= 0x7F {
s.push_str(&regex_syntax::escape(
regex_syntax::escape_into(
char::from(b).encode_utf8(&mut [0; 4]),
));
&mut s,
);
} else {
s.push_str(&format!("\\x{:02x}", b));
write!(&mut s, "\\x{:02x}", b).unwrap();
}
}
s
@@ -753,7 +783,11 @@ fn bytes_to_escaped_literal(bs: &[u8]) -> String {
struct Parser<'a> {
glob: &'a str,
stack: Vec<Tokens>,
// Marks the index in `stack` where the alternation started.
alternates_stack: Vec<usize>,
// The set of active alternation branches being parsed.
// Tokens are added to the end of the last one.
branches: Vec<Tokens>,
chars: std::iter::Peekable<std::str::Chars<'a>>,
prev: Option<char>,
cur: Option<char>,
@@ -782,36 +816,37 @@ impl<'a> Parser<'a> {
}
fn push_alternate(&mut self) -> Result<(), Error> {
if self.stack.len() > 1 {
return Err(self.error(ErrorKind::NestedAlternates));
}
Ok(self.stack.push(Tokens::default()))
self.alternates_stack.push(self.branches.len());
self.branches.push(Tokens::default());
Ok(())
}
fn pop_alternate(&mut self) -> Result<(), Error> {
let mut alts = vec![];
while self.stack.len() >= 2 {
alts.push(self.stack.pop().unwrap());
}
self.push_token(Token::Alternates(alts))
let Some(start) = self.alternates_stack.pop() else {
return Err(self.error(ErrorKind::UnopenedAlternates));
};
assert!(start <= self.branches.len());
let alts = Token::Alternates(self.branches.drain(start..).collect());
self.push_token(alts)?;
Ok(())
}
fn push_token(&mut self, tok: Token) -> Result<(), Error> {
if let Some(ref mut pat) = self.stack.last_mut() {
if let Some(ref mut pat) = self.branches.last_mut() {
return Ok(pat.push(tok));
}
Err(self.error(ErrorKind::UnopenedAlternates))
}
fn pop_token(&mut self) -> Result<Token, Error> {
if let Some(ref mut pat) = self.stack.last_mut() {
if let Some(ref mut pat) = self.branches.last_mut() {
return Ok(pat.pop().unwrap());
}
Err(self.error(ErrorKind::UnopenedAlternates))
}
fn have_tokens(&self) -> Result<bool, Error> {
match self.stack.last() {
match self.branches.last() {
None => Err(self.error(ErrorKind::UnopenedAlternates)),
Some(ref pat) => Ok(!pat.is_empty()),
}
@@ -820,11 +855,11 @@ impl<'a> Parser<'a> {
fn parse_comma(&mut self) -> Result<(), Error> {
// If we aren't inside a group alternation, then don't
// treat commas specially. Otherwise, we need to start
// a new alternate.
if self.stack.len() <= 1 {
// a new alternate branch.
if self.alternates_stack.is_empty() {
self.push_token(Token::Literal(','))
} else {
Ok(self.stack.push(Tokens::default()))
Ok(self.branches.push(Tokens::default()))
}
}
@@ -861,7 +896,7 @@ impl<'a> Parser<'a> {
}
if !prev.map(is_separator).unwrap_or(false) {
if self.stack.len() <= 1
if self.branches.len() <= 1
|| (prev != Some(',') && prev != Some('{'))
{
self.push_token(Token::ZeroOrMore)?;
@@ -874,7 +909,7 @@ impl<'a> Parser<'a> {
assert!(self.bump().is_none());
true
}
Some(',') | Some('}') if self.stack.len() >= 2 => true,
Some(',') | Some('}') if self.branches.len() >= 2 => true,
Some(c) if is_separator(c) => {
assert!(self.bump().map(is_separator).unwrap_or(false));
false
@@ -1202,6 +1237,10 @@ mod tests {
syntaxerr!(err_unclosed4, "[!]", ErrorKind::UnclosedClass);
syntaxerr!(err_range1, "[z-a]", ErrorKind::InvalidRange('z', 'a'));
syntaxerr!(err_range2, "[z--]", ErrorKind::InvalidRange('z', '-'));
syntaxerr!(err_alt1, "{a,b", ErrorKind::UnclosedAlternates);
syntaxerr!(err_alt2, "{a,{b,c}", ErrorKind::UnclosedAlternates);
syntaxerr!(err_alt3, "a,b}", ErrorKind::UnopenedAlternates);
syntaxerr!(err_alt4, "{a,b}}", ErrorKind::UnopenedAlternates);
const CASEI: Options =
Options { casei: Some(true), litsep: None, bsesc: None, ealtre: None };
@@ -1222,6 +1261,8 @@ mod tests {
ealtre: Some(true),
};
toregex!(re_empty, "", "^$");
toregex!(re_casei, "a", "(?i)^a$", &CASEI);
toregex!(re_slash1, "?", r"^[^/]$", SLASHLIT);
@@ -1261,7 +1302,9 @@ mod tests {
toregex!(re32, "/a**", r"^/a.*.*$");
toregex!(re33, "/**a", r"^/.*.*a$");
toregex!(re34, "/a**b", r"^/a.*.*b$");
toregex!(re35, "{a,b}", r"^(?:b|a)$");
toregex!(re35, "{a,b}", r"^(?:a|b)$");
toregex!(re36, "{a,{b,c}}", r"^(?:a|(?:b|c))$");
toregex!(re37, "{{a,b},{c,d}}", r"^(?:(?:a|b)|(?:c|d))$");
matches!(match1, "a", "a");
matches!(match2, "a*b", "a_b");
@@ -1349,6 +1392,9 @@ mod tests {
matches!(matchalt14, "foo{,.txt}", "foo.txt");
nmatches!(matchalt15, "foo{,.txt}", "foo");
matches!(matchalt16, "foo{,.txt}", "foo", EALTRE);
matches!(matchalt17, "{a,b{c,d}}", "bc");
matches!(matchalt18, "{a,b{c,d}}", "bd");
matches!(matchalt19, "{a,b{c,d}}", "a");
matches!(matchslash1, "abc/def", "abc/def", SLASHLIT);
#[cfg(unix)]

183
crates/globset/src/lib.rs
View File

@@ -94,6 +94,19 @@ Standard Unix-style glob syntax is supported:
A `GlobBuilder` can be used to prevent wildcards from matching path separators,
or to enable case insensitive matching.
# Crate Features
This crate includes optional features that can be enabled if necessary.
These features are not required but may be useful depending on the use case.
The following features are available:
* **arbitrary** -
Enabling this feature introduces a public dependency on the
[`arbitrary`](https://crates.io/crates/arbitrary)
crate. Namely, it implements the `Arbitrary` trait from that crate for the
[`Glob`] type. This feature is disabled by default.
*/
#![deny(missing_docs)]
@@ -150,6 +163,7 @@ pub struct Error {
/// The kind of error that can occur when parsing a glob pattern.
#[derive(Clone, Debug, Eq, PartialEq)]
#[non_exhaustive]
pub enum ErrorKind {
/// **DEPRECATED**.
///
@@ -169,20 +183,16 @@ pub enum ErrorKind {
UnopenedAlternates,
/// Occurs when a `{` is found without a matching `}`.
UnclosedAlternates,
/// Occurs when an alternating group is nested inside another alternating
/// group, e.g., `{{a,b},{c,d}}`.
/// **DEPRECATED**.
///
/// This error used to occur when an alternating group was nested inside
/// another alternating group, e.g., `{{a,b},{c,d}}`. However, this is now
/// supported and as such this error cannot occur.
NestedAlternates,
/// Occurs when an unescaped '\' is found at the end of a glob.
DanglingEscape,
/// An error associated with parsing or compiling a regex.
Regex(String),
/// Hints that destructuring should not be exhaustive.
///
/// This enum may grow additional variants, so this makes sure clients
/// don't count on exhaustive matching. (Otherwise, adding a new variant
/// could break existing code.)
#[doc(hidden)]
__Nonexhaustive,
}
impl std::error::Error for Error {
@@ -226,7 +236,6 @@ impl ErrorKind {
}
ErrorKind::DanglingEscape => "dangling '\\'",
ErrorKind::Regex(ref err) => err,
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}
@@ -255,7 +264,6 @@ impl std::fmt::Display for ErrorKind {
ErrorKind::InvalidRange(s, e) => {
write!(f, "invalid range; '{}' > '{}'", s, e)
}
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}
@@ -314,7 +322,7 @@ impl GlobSet {
/// Create an empty `GlobSet`. An empty set matches nothing.
#[inline]
pub fn empty() -> GlobSet {
pub const fn empty() -> GlobSet {
GlobSet { len: 0, strats: vec![] }
}
@@ -351,6 +359,43 @@ impl GlobSet {
false
}
/// Returns true if all globs in this set match the path given.
///
/// This will return true if the set of globs is empty, as in that case all
/// `0` of the globs will match.
///
/// ```
/// use globset::{Glob, GlobSetBuilder};
///
/// let mut builder = GlobSetBuilder::new();
/// builder.add(Glob::new("src/*").unwrap());
/// builder.add(Glob::new("**/*.rs").unwrap());
/// let set = builder.build().unwrap();
///
/// assert!(set.matches_all("src/foo.rs"));
/// assert!(!set.matches_all("src/bar.c"));
/// assert!(!set.matches_all("test.rs"));
/// ```
pub fn matches_all<P: AsRef<Path>>(&self, path: P) -> bool {
self.matches_all_candidate(&Candidate::new(path.as_ref()))
}
/// Returns ture if all globs in this set match the path given.
///
/// This takes a Candidate as input, which can be used to amortize the cost
/// of peparing a path for matching.
///
/// This will return true if the set of globs is empty, as in that case all
/// `0` of the globs will match.
pub fn matches_all_candidate(&self, path: &Candidate<'_>) -> bool {
for strat in &self.strats {
if !strat.is_match(path) {
return false;
}
}
true
}
/// Returns the sequence number of every glob pattern that matches the
/// given path.
pub fn matches<P: AsRef<Path>>(&self, path: P) -> Vec<usize> {
@@ -410,10 +455,20 @@ impl GlobSet {
into.dedup();
}
fn new(pats: &[Glob]) -> Result<GlobSet, Error> {
if pats.is_empty() {
return Ok(GlobSet { len: 0, strats: vec![] });
/// Builds a new matcher from a collection of Glob patterns.
///
/// Once a matcher is built, no new patterns can be added to it.
pub fn new<I, G>(globs: I) -> Result<GlobSet, Error>
where
I: IntoIterator<Item = G>,
G: AsRef<Glob>,
{
let mut it = globs.into_iter().peekable();
if it.peek().is_none() {
return Ok(GlobSet::empty());
}
let mut len = 0;
let mut lits = LiteralStrategy::new();
let mut base_lits = BasenameLiteralStrategy::new();
let mut exts = ExtensionStrategy::new();
@@ -421,7 +476,10 @@ impl GlobSet {
let mut suffixes = MultiStrategyBuilder::new();
let mut required_exts = RequiredExtensionStrategyBuilder::new();
let mut regexes = MultiStrategyBuilder::new();
for (i, p) in pats.iter().enumerate() {
for (i, p) in it.enumerate() {
len += 1;
let p = p.as_ref();
match MatchStrategy::new(p) {
MatchStrategy::Literal(lit) => {
lits.add(i, lit);
@@ -461,20 +519,33 @@ impl GlobSet {
required_exts.0.len(),
regexes.literals.len()
);
Ok(GlobSet {
len: pats.len(),
strats: vec![
GlobSetMatchStrategy::Extension(exts),
GlobSetMatchStrategy::BasenameLiteral(base_lits),
GlobSetMatchStrategy::Literal(lits),
GlobSetMatchStrategy::Suffix(suffixes.suffix()),
GlobSetMatchStrategy::Prefix(prefixes.prefix()),
GlobSetMatchStrategy::RequiredExtension(
required_exts.build()?,
),
GlobSetMatchStrategy::Regex(regexes.regex_set()?),
],
})
let mut strats = Vec::with_capacity(7);
// Only add strategies that are populated
if !exts.0.is_empty() {
strats.push(GlobSetMatchStrategy::Extension(exts));
}
if !base_lits.0.is_empty() {
strats.push(GlobSetMatchStrategy::BasenameLiteral(base_lits));
}
if !lits.0.is_empty() {
strats.push(GlobSetMatchStrategy::Literal(lits));
}
if !suffixes.is_empty() {
strats.push(GlobSetMatchStrategy::Suffix(suffixes.suffix()));
}
if !prefixes.is_empty() {
strats.push(GlobSetMatchStrategy::Prefix(prefixes.prefix()));
}
if !required_exts.0.is_empty() {
strats.push(GlobSetMatchStrategy::RequiredExtension(
required_exts.build()?,
));
}
if !regexes.is_empty() {
strats.push(GlobSetMatchStrategy::Regex(regexes.regex_set()?));
}
Ok(GlobSet { len, strats })
}
}
@@ -504,7 +575,7 @@ impl GlobSetBuilder {
///
/// Once a matcher is built, no new patterns can be added to it.
pub fn build(&self) -> Result<GlobSet, Error> {
GlobSet::new(&self.pats)
GlobSet::new(self.pats.iter())
}
/// Add a new pattern to this set.
@@ -540,7 +611,23 @@ impl<'a> std::fmt::Debug for Candidate<'a> {
impl<'a> Candidate<'a> {
/// Create a new candidate for matching from the given path.
pub fn new<P: AsRef<Path> + ?Sized>(path: &'a P) -> Candidate<'a> {
let path = normalize_path(Vec::from_path_lossy(path.as_ref()));
Self::from_cow(Vec::from_path_lossy(path.as_ref()))
}
/// Create a new candidate for matching from the given path as a sequence
/// of bytes.
///
/// Generally speaking, this routine expects the bytes to be
/// _conventionally_ UTF-8. It is legal for the byte sequence to contain
/// invalid UTF-8. However, if the bytes are in some other encoding that
/// isn't ASCII compatible (for example, UTF-16), then the results of
/// matching are unspecified.
pub fn from_bytes<P: AsRef<[u8]> + ?Sized>(path: &'a P) -> Candidate<'a> {
Self::from_cow(Cow::Borrowed(path.as_ref()))
}
fn from_cow(path: Cow<'a, [u8]>) -> Candidate<'a> {
let path = normalize_path(path);
let basename = file_name(&path).unwrap_or(Cow::Borrowed(B("")));
let ext = file_name_ext(&basename).unwrap_or(Cow::Borrowed(B("")));
Candidate { path, basename, ext }
@@ -892,6 +979,10 @@ impl MultiStrategyBuilder {
patset: Arc::new(Pool::new(create)),
})
}
fn is_empty(&self) -> bool {
self.literals.is_empty()
}
}
#[derive(Clone, Debug)]
@@ -928,13 +1019,26 @@ impl RequiredExtensionStrategyBuilder {
///
/// The escaping works by surrounding meta-characters with brackets. For
/// example, `*` becomes `[*]`.
///
/// # Example
///
/// ```
/// use globset::escape;
///
/// assert_eq!(escape("foo*bar"), "foo[*]bar");
/// assert_eq!(escape("foo?bar"), "foo[?]bar");
/// assert_eq!(escape("foo[bar"), "foo[[]bar");
/// assert_eq!(escape("foo]bar"), "foo[]]bar");
/// assert_eq!(escape("foo{bar"), "foo[{]bar");
/// assert_eq!(escape("foo}bar"), "foo[}]bar");
/// ```
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(']');
@@ -979,6 +1083,7 @@ mod tests {
let set = GlobSetBuilder::new().build().unwrap();
assert!(!set.is_match(""));
assert!(!set.is_match("a"));
assert!(set.matches_all("a"));
}
#[test]
@@ -1019,4 +1124,16 @@ mod tests {
let matches = set.matches("nada");
assert_eq!(0, matches.len());
}
#[test]
fn debug() {
let mut builder = GlobSetBuilder::new();
builder.add(Glob::new("*foo*").unwrap());
builder.add(Glob::new("*bar*").unwrap());
builder.add(Glob::new("*quux*").unwrap());
assert_eq!(
format!("{builder:?}"),
"GlobSetBuilder { pats: [Glob(\"*foo*\"), Glob(\"*bar*\"), Glob(\"*quux*\")] }",
);
}
}

14
crates/globset/src/pathutil.rs
View File

@@ -4,21 +4,25 @@ use bstr::{ByteSlice, ByteVec};
/// The final component of the path, if it is a normal file.
///
/// If the path terminates in `.`, `..`, or consists solely of a root of
/// prefix, file_name will return None.
/// If the path terminates in `..`, or consists solely of a root of prefix,
/// file_name will return `None`.
pub(crate) fn file_name<'a>(path: &Cow<'a, [u8]>) -> Option<Cow<'a, [u8]>> {
if path.last_byte().map_or(true, |b| b == b'.') {
if path.is_empty() {
return None;
}
let last_slash = path.rfind_byte(b'/').map(|i| i + 1).unwrap_or(0);
Some(match *path {
let got = match *path {
Cow::Borrowed(path) => Cow::Borrowed(&path[last_slash..]),
Cow::Owned(ref path) => {
let mut path = path.clone();
path.drain_bytes(..last_slash);
Cow::Owned(path)
}
})
};
if got == &b".."[..] {
return None;
}
Some(got)
}
/// Return a file extension given a path's file name.

16
crates/grep/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep"
version = "0.3.1" #:version
version = "0.3.2" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Fast line oriented regex searching as a library.
@@ -14,20 +14,20 @@ license = "Unlicense OR MIT"
edition = "2021"
[dependencies]
grep-cli = { version = "0.1.10", path = "../cli" }
grep-cli = { version = "0.1.11", path = "../cli" }
grep-matcher = { version = "0.1.7", path = "../matcher" }
grep-pcre2 = { version = "0.1.7", path = "../pcre2", optional = true }
grep-printer = { version = "0.2.1", path = "../printer" }
grep-regex = { version = "0.1.12", path = "../regex" }
grep-searcher = { version = "0.1.13", path = "../searcher" }
grep-pcre2 = { version = "0.1.8", path = "../pcre2", optional = true }
grep-printer = { version = "0.2.2", path = "../printer" }
grep-regex = { version = "0.1.13", path = "../regex" }
grep-searcher = { version = "0.1.14", path = "../searcher" }
[dev-dependencies]
termcolor = "1.0.4"
walkdir = "2.2.7"
[features]
simd-accel = ["grep-searcher/simd-accel"]
pcre2 = ["grep-pcre2"]
# This feature is DEPRECATED. Runtime dispatch is used for SIMD now.
# These features are DEPRECATED. Runtime dispatch is used for SIMD now.
simd-accel = []
avx-accel = []

6
crates/ignore/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "ignore"
version = "0.4.21" #:version
version = "0.4.23" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
A fast library for efficiently matching ignore files such as `.gitignore`
@@ -20,7 +20,7 @@ bench = false
[dependencies]
crossbeam-deque = "0.8.3"
globset = { version = "0.4.14", path = "../globset" }
globset = { version = "0.4.15", path = "../globset" }
log = "0.4.20"
memchr = "2.6.3"
same-file = "1.0.6"
@@ -36,7 +36,7 @@ version = "0.1.2"
[dev-dependencies]
bstr = { version = "1.6.2", default-features = false, features = ["std"] }
crossbeam-channel = "0.5.8"
crossbeam-channel = "0.5.15"
[features]
# DEPRECATED. It is a no-op. SIMD is done automatically through runtime

32
crates/ignore/src/default_types.rs
View File

@@ -27,9 +27,10 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["bat", "batch"], &["*.bat"]),
(&["bazel"], &[
"*.bazel", "*.bzl", "*.BUILD", "*.bazelrc", "BUILD", "MODULE.bazel",
"WORKSPACE", "WORKSPACE.bazel",
"WORKSPACE", "WORKSPACE.bazel", "WORKSPACE.bzlmod",
]),
(&["bitbake"], &["*.bb", "*.bbappend", "*.bbclass", "*.conf", "*.inc"]),
(&["boxlang"], &["*.bx", "*.bxm", "*.bxs"]),
(&["brotli"], &["*.br"]),
(&["buildstream"], &["*.bst"]),
(&["bzip2"], &["*.bz2", "*.tbz2"]),
@@ -39,6 +40,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["carp"], &["*.carp"]),
(&["cbor"], &["*.cbor"]),
(&["ceylon"], &["*.ceylon"]),
(&["cfml"], &["*.cfc", "*.cfm"]),
(&["clojure"], &["*.clj", "*.cljc", "*.cljs", "*.cljx"]),
(&["cmake"], &["*.cmake", "CMakeLists.txt"]),
(&["cmd"], &["*.bat", "*.cmd"]),
@@ -62,7 +64,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["cython"], &["*.pyx", "*.pxi", "*.pxd"]),
(&["d"], &["*.d"]),
(&["dart"], &["*.dart"]),
(&["devicetree"], &["*.dts", "*.dtsi"]),
(&["devicetree"], &["*.dts", "*.dtsi", "*.dtso"]),
(&["dhall"], &["*.dhall"]),
(&["diff"], &["*.patch", "*.diff"]),
(&["dita"], &["*.dita", "*.ditamap", "*.ditaval"]),
@@ -88,6 +90,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["fsharp"], &["*.fs", "*.fsx", "*.fsi"]),
(&["fut"], &["*.fut"]),
(&["gap"], &["*.g", "*.gap", "*.gi", "*.gd", "*.tst"]),
(&["gleam"], &["*.gleam"]),
(&["gn"], &["*.gn", "*.gni"]),
(&["go"], &["*.go"]),
(&["gprbuild"], &["*.gpr"]),
@@ -117,7 +120,9 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["julia"], &["*.jl"]),
(&["jupyter"], &["*.ipynb", "*.jpynb"]),
(&["k"], &["*.k"]),
(&["kconfig"], &["Kconfig", "Kconfig.*"]),
(&["kotlin"], &["*.kt", "*.kts"]),
(&["lean"], &["*.lean"]),
(&["less"], &["*.less"]),
(&["license"], &[
// General
@@ -148,6 +153,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
]),
(&["lilypond"], &["*.ly", "*.ily"]),
(&["lisp"], &["*.el", "*.jl", "*.lisp", "*.lsp", "*.sc", "*.scm"]),
(&["llvm"], &["*.ll"]),
(&["lock"], &["*.lock", "package-lock.json"]),
(&["log"], &["*.log"]),
(&["lua"], &["*.lua"]),
@@ -158,6 +164,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
"[Gg][Nn][Uu]makefile", "[Mm]akefile",
"[Gg][Nn][Uu]makefile.am", "[Mm]akefile.am",
"[Gg][Nn][Uu]makefile.in", "[Mm]akefile.in",
"Makefile.*",
"*.mk", "*.mak"
]),
(&["mako"], &["*.mako", "*.mao"]),
@@ -172,7 +179,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
"*.mdx",
]),
(&["matlab"], &["*.m"]),
(&["meson"], &["meson.build", "meson_options.txt"]),
(&["meson"], &["meson.build", "meson_options.txt", "meson.options"]),
(&["minified"], &["*.min.html", "*.min.css", "*.min.js"]),
(&["mint"], &["*.mint"]),
(&["mk"], &["mkfile"]),
@@ -180,7 +187,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["motoko"], &["*.mo"]),
(&["msbuild"], &[
"*.csproj", "*.fsproj", "*.vcxproj", "*.proj", "*.props", "*.targets",
"*.sln",
"*.sln", "*.slnf"
]),
(&["nim"], &["*.nim", "*.nimf", "*.nimble", "*.nims"]),
(&["nix"], &["*.nix"]),
@@ -226,14 +233,16 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
// Idiomatic files
"config.ru", "Gemfile", ".irbrc", "Rakefile",
// Extensions
"*.gemspec", "*.rb", "*.rbw"
"*.gemspec", "*.rb", "*.rbw", "*.rake"
]),
(&["rust"], &["*.rs"]),
(&["sass"], &["*.sass", "*.scss"]),
(&["scala"], &["*.scala", "*.sbt"]),
(&["scdoc"], &["*.scd", "*.scdoc"]),
(&["seed7"], &["*.sd7", "*.s7i"]),
(&["sh"], &[
// Portable/misc. init files
".login", ".logout", ".profile", "profile",
".env", ".login", ".logout", ".profile", "profile",
// bash-specific init files
".bash_login", "bash_login",
".bash_logout", "bash_logout",
@@ -252,7 +261,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
".zprofile", "zprofile",
".zshrc", "zshrc",
// Extensions
"*.bash", "*.csh", "*.ksh", "*.sh", "*.tcsh", "*.zsh",
"*.bash", "*.csh", "*.env", "*.ksh", "*.sh", "*.tcsh", "*.zsh",
]),
(&["slim"], &["*.skim", "*.slim", "*.slime"]),
(&["smarty"], &["*.tpl"]),
@@ -264,6 +273,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["sql"], &["*.sql", "*.psql"]),
(&["stylus"], &["*.styl"]),
(&["sv"], &["*.v", "*.vg", "*.sv", "*.svh", "*.h"]),
(&["svelte"], &["*.svelte", "*.svelte.ts"]),
(&["svg"], &["*.svg"]),
(&["swift"], &["*.swift"]),
(&["swig"], &["*.def", "*.i"]),
@@ -278,9 +288,8 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["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",
"*.tf", "*.tf.json", "*.tfvars", "*.tfvars.json",
"*.terraformrc", "terraform.rc", "*.tfrc", "*.terraform.lock.hcl",
]),
(&["thrift"], &["*.thrift"]),
(&["toml"], &["*.toml", "Cargo.lock"]),
@@ -288,6 +297,7 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["twig"], &["*.twig"]),
(&["txt"], &["*.txt"]),
(&["typoscript"], &["*.typoscript", "*.ts"]),
(&["typst"], &["*.typ"]),
(&["usd"], &["*.usd", "*.usda", "*.usdc"]),
(&["v"], &["*.v", "*.vsh"]),
(&["vala"], &["*.vala"]),
@@ -301,7 +311,9 @@ pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["vimscript"], &[
"*.vim", ".vimrc", ".gvimrc", "vimrc", "gvimrc", "_vimrc", "_gvimrc",
]),
(&["vue"], &["*.vue"]),
(&["webidl"], &["*.idl", "*.webidl", "*.widl"]),
(&["wgsl"], &["*.wgsl"]),
(&["wiki"], &["*.mediawiki", "*.wiki"]),
(&["xml"], &[
"*.xml", "*.xml.dist", "*.dtd", "*.xsl", "*.xslt", "*.xsd", "*.xjb",

81
crates/ignore/src/dir.rs
View File

@@ -19,7 +19,7 @@ use std::{
fs::{File, FileType},
io::{self, BufRead},
path::{Path, PathBuf},
sync::{Arc, RwLock},
sync::{Arc, RwLock, Weak},
};
use crate::{
@@ -34,11 +34,13 @@ use crate::{
/// IgnoreMatch represents information about where a match came from when using
/// the `Ignore` matcher.
#[derive(Clone, Debug)]
#[allow(dead_code)]
pub(crate) struct IgnoreMatch<'a>(IgnoreMatchInner<'a>);
/// IgnoreMatchInner describes precisely where the match information came from.
/// This is private to allow expansion to more matchers in the future.
#[derive(Clone, Debug)]
#[allow(dead_code)]
enum IgnoreMatchInner<'a> {
Override(overrides::Glob<'a>),
Gitignore(&'a gitignore::Glob),
@@ -99,7 +101,7 @@ struct IgnoreInner {
/// Note that this is never used during matching, only when adding new
/// parent directory matchers. This avoids needing to rebuild glob sets for
/// parent directories if many paths are being searched.
compiled: Arc<RwLock<HashMap<OsString, Ignore>>>,
compiled: Arc<RwLock<HashMap<OsString, Weak<IgnoreInner>>>>,
/// The path to the directory that this matcher was built from.
dir: PathBuf,
/// An override matcher (default is empty).
@@ -198,9 +200,11 @@ impl Ignore {
let mut ig = self.clone();
for parent in parents.into_iter().rev() {
let mut compiled = self.0.compiled.write().unwrap();
if let Some(prebuilt) = compiled.get(parent.as_os_str()) {
ig = prebuilt.clone();
continue;
if let Some(weak) = compiled.get(parent.as_os_str()) {
if let Some(prebuilt) = weak.upgrade() {
ig = Ignore(prebuilt);
continue;
}
}
let (mut igtmp, err) = ig.add_child_path(parent);
errs.maybe_push(err);
@@ -208,12 +212,16 @@ impl Ignore {
igtmp.absolute_base = Some(absolute_base.clone());
igtmp.has_git =
if self.0.opts.require_git && self.0.opts.git_ignore {
parent.join(".git").exists()
parent.join(".git").exists() || parent.join(".jj").exists()
} else {
false
};
ig = Ignore(Arc::new(igtmp));
compiled.insert(parent.as_os_str().to_os_string(), ig.clone());
let ig_arc = Arc::new(igtmp);
ig = Ignore(ig_arc.clone());
compiled.insert(
parent.as_os_str().to_os_string(),
Arc::downgrade(&ig_arc),
);
}
(ig, errs.into_error_option())
}
@@ -243,7 +251,7 @@ impl Ignore {
} else {
None
};
let has_git = git_type.map(|_| true).unwrap_or(false);
let has_git = git_type.is_some() || dir.join(".jj").exists();
let mut errs = PartialErrorBuilder::default();
let custom_ig_matcher = if self.0.custom_ignore_filenames.is_empty() {
@@ -282,6 +290,7 @@ impl Ignore {
errs.maybe_push(err);
m
};
let gi_exclude_matcher = if !self.0.opts.git_exclude {
Gitignore::empty()
} else {
@@ -453,21 +462,23 @@ impl Ignore {
// off of `path`. Overall, this seems a little ham-fisted, but
// it does fix a nasty bug. It should do fine until we overhaul
// this crate.
let dirpath = self.0.dir.as_path();
let path_prefix = match strip_prefix("./", dirpath) {
None => dirpath,
Some(stripped_dot_slash) => stripped_dot_slash,
};
let path = match strip_prefix(path_prefix, path) {
None => abs_parent_path.join(path),
Some(p) => {
let p = match strip_prefix("/", p) {
None => p,
Some(p) => p,
};
abs_parent_path.join(p)
}
};
let path = abs_parent_path.join(
self.parents()
.take_while(|ig| !ig.0.is_absolute_parent)
.last()
.map_or(path, |ig| {
strip_if_is_prefix(
"/",
strip_if_is_prefix(
strip_if_is_prefix(
"./",
ig.0.dir.as_path(),
),
path,
),
)
}),
);
for ig in
self.parents().skip_while(|ig| !ig.0.is_absolute_parent)
@@ -866,6 +877,15 @@ fn resolve_git_commondir(
Ok(commondir_abs)
}
/// Strips `prefix` from `path` if it's a prefix, otherwise returns `path`
/// unchanged.
fn strip_if_is_prefix<'a, P: AsRef<Path> + ?Sized>(
prefix: &'a P,
path: &'a Path,
) -> &'a Path {
strip_prefix(prefix, path).map_or(path, |p| p)
}
#[cfg(test)]
mod tests {
use std::{io::Write, path::Path};
@@ -935,6 +955,19 @@ mod tests {
assert!(ig.matched("baz", false).is_none());
}
#[test]
fn gitignore_with_jj() {
let td = tmpdir();
mkdirp(td.path().join(".jj"));
wfile(td.path().join(".gitignore"), "foo\n!bar");
let (ig, err) = IgnoreBuilder::new().build().add_child(td.path());
assert!(err.is_none());
assert!(ig.matched("foo", false).is_ignore());
assert!(ig.matched("bar", false).is_whitelist());
assert!(ig.matched("baz", false).is_none());
}
#[test]
fn gitignore_no_git() {
let td = tmpdir();

7
crates/ignore/src/gitignore.rs
View File

@@ -390,6 +390,7 @@ impl GitignoreBuilder {
Err(err) => return Some(Error::Io(err).with_path(path)),
Ok(file) => file,
};
log::debug!("opened gitignore file: {}", path.display());
let rdr = BufReader::new(file);
let mut errs = PartialErrorBuilder::default();
for (i, line) in rdr.lines().enumerate() {
@@ -401,6 +402,12 @@ impl GitignoreBuilder {
break;
}
};
// Match Git's handling of .gitignore files that begin with the Unicode BOM
const UTF8_BOM: &str = "\u{feff}";
let line =
if i == 0 { line.trim_start_matches(UTF8_BOM) } else { &line };
if let Err(err) = self.add_line(Some(path.to_path_buf()), &line) {
errs.push(err.tagged(path, lineno));
}

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

@@ -527,7 +527,7 @@ mod tests {
let tmpdir = env::temp_dir();
for _ in 0..TRIES {
let count = COUNTER.fetch_add(1, Ordering::SeqCst);
let count = COUNTER.fetch_add(1, Ordering::Relaxed);
let path = tmpdir.join("rust-ignore").join(count.to_string());
if path.is_dir() {
continue;

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

@@ -23,9 +23,11 @@ use crate::{
/// The lifetime `'a` refers to the lifetime of the matcher that produced
/// this glob.
#[derive(Clone, Debug)]
#[allow(dead_code)]
pub struct Glob<'a>(GlobInner<'a>);
#[derive(Clone, Debug)]
#[allow(dead_code)]
enum GlobInner<'a> {
/// No glob matched, but the file path should still be ignored.
UnmatchedIgnore,

15
crates/ignore/src/walk.rs
View File

@@ -11,7 +11,7 @@ use std::{
use {
crossbeam_deque::{Stealer, Worker as Deque},
same_file::Handle,
walkdir::{self, WalkDir},
walkdir::WalkDir,
};
use crate::{
@@ -591,7 +591,7 @@ impl WalkBuilder {
///
/// Note that this *doesn't* return something that implements `Iterator`.
/// Instead, the returned value must be run with a closure. e.g.,
/// `builder.build_parallel().run(|| |path| println!("{:?}", path))`.
/// `builder.build_parallel().run(|| |path| { println!("{path:?}"); WalkState::Continue })`.
pub fn build_parallel(&self) -> WalkParallel {
WalkParallel {
paths: self.paths.clone().into_iter(),
@@ -798,6 +798,10 @@ impl WalkBuilder {
///
/// When disabled, git-related ignore rules are applied even when searching
/// outside a git repository.
///
/// In particular, if this is `false` then `.gitignore` files will be read
/// from parent directories above the git root directory containing `.git`,
/// which is different from the git behavior.
pub fn require_git(&mut self, yes: bool) -> &mut WalkBuilder {
self.ig_builder.require_git(yes);
self
@@ -1305,7 +1309,7 @@ impl WalkParallel {
fn threads(&self) -> usize {
if self.threads == 0 {
2
std::thread::available_parallelism().map_or(1, |n| n.get()).min(12)
} else {
self.threads
}
@@ -1420,8 +1424,11 @@ impl Stack {
stealers: stealers.clone(),
})
.collect();
// Distribute the initial messages.
// Distribute the initial messages, reverse the order to cancel out
// the other reversal caused by the inherent LIFO processing of the
// per-thread stacks which are filled here.
init.into_iter()
.rev()
.zip(stacks.iter().cycle())
.for_each(|(m, s)| s.push(m));
stacks

2
crates/ignore/tests/gitignore_skip_bom.gitignore Normal file
View File

@@ -0,0 +1,2 @@
ignore/this/path
# This file begins with a BOM (U+FEFF)

17
crates/ignore/tests/gitignore_skip_bom.rs Normal file
View File

@@ -0,0 +1,17 @@
use ignore::gitignore::GitignoreBuilder;
const IGNORE_FILE: &'static str = "tests/gitignore_skip_bom.gitignore";
/// Skip a Byte-Order Mark (BOM) at the beginning of the file, matching Git's
/// behavior.
///
/// Ref: <https://github.com/BurntSushi/ripgrep/issues/2177>
#[test]
fn gitignore_skip_bom() {
let mut builder = GitignoreBuilder::new("ROOT");
let error = builder.add(IGNORE_FILE);
assert!(error.is_none(), "failed to open gitignore file");
let g = builder.build().unwrap();
assert!(g.matched("ignore/this/path", false).is_ignore());
}

9
crates/matcher/src/lib.rs
View File

@@ -389,6 +389,15 @@ pub trait Captures {
/// for the overall match.
fn get(&self, i: usize) -> Option<Match>;
/// Return the overall match for the capture.
///
/// This returns the match for index `0`. That is it is equivalent to
/// `get(0).unwrap()`
#[inline]
fn as_match(&self) -> Match {
self.get(0).unwrap()
}
/// Returns true if and only if these captures are empty. This occurs
/// when `len` is `0`.
///

2
crates/pcre2/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-pcre2"
version = "0.1.7" #:version
version = "0.1.8" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Use PCRE2 with the 'grep' crate.

9
crates/pcre2/src/matcher.rs
View File

@@ -55,7 +55,12 @@ impl RegexMatcherBuilder {
format!("(?:{})", p.as_ref())
});
}
let mut singlepat = pats.join("|");
let mut singlepat = if patterns.is_empty() {
// A way to spell a pattern that can never match anything.
r"[^\S\s]".to_string()
} else {
pats.join("|")
};
if self.case_smart && !has_uppercase_literal(&singlepat) {
builder.caseless(true);
}
@@ -428,7 +433,7 @@ fn has_uppercase_literal(pattern: &str) -> bool {
#[cfg(test)]
mod tests {
use grep_matcher::{LineMatchKind, Matcher};
use grep_matcher::LineMatchKind;
use super::*;

6
crates/printer/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-printer"
version = "0.2.1" #:version
version = "0.2.2" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
An implementation of the grep crate's Sink trait that provides standard
@@ -21,14 +21,14 @@ serde = ["dep:serde", "dep:serde_json"]
[dependencies]
bstr = "1.6.2"
grep-matcher = { version = "0.1.7", path = "../matcher" }
grep-searcher = { version = "0.1.13", path = "../searcher" }
grep-searcher = { version = "0.1.14", path = "../searcher" }
log = "0.4.5"
termcolor = "1.3.0"
serde = { version = "1.0.193", optional = true }
serde_json = { version = "1.0.107", optional = true }
[dev-dependencies]
grep-regex = { version = "0.1.12", path = "../regex" }
grep-regex = { version = "0.1.13", path = "../regex" }
[package.metadata.docs.rs]
# We want to document all features.

34
crates/printer/src/color.rs
View File

@@ -51,13 +51,13 @@ impl std::fmt::Display for ColorError {
ColorError::UnrecognizedOutType(ref name) => write!(
f,
"unrecognized output type '{}'. Choose from: \
path, line, column, match.",
path, line, column, match, highlight.",
name,
),
ColorError::UnrecognizedSpecType(ref name) => write!(
f,
"unrecognized spec type '{}'. Choose from: \
fg, bg, style, none.",
fg, bg, style, none.",
name,
),
ColorError::UnrecognizedColor(_, ref msg) => write!(f, "{}", msg),
@@ -65,13 +65,13 @@ impl std::fmt::Display for ColorError {
f,
"unrecognized style attribute '{}'. Choose from: \
nobold, bold, nointense, intense, nounderline, \
underline.",
underline, noitalic, italic.",
name,
),
ColorError::InvalidFormat(ref original) => write!(
f,
"invalid color spec format: '{}'. Valid format \
is '(path|line|column|match):(fg|bg|style):(value)'.",
"invalid color spec format: '{}'. Valid format is \
'(path|line|column|match|highlight):(fg|bg|style):(value)'.",
original,
),
}
@@ -90,6 +90,7 @@ pub struct ColorSpecs {
line: ColorSpec,
column: ColorSpec,
matched: ColorSpec,
highlight: ColorSpec,
}
/// A single color specification provided by the user.
@@ -99,7 +100,7 @@ pub struct ColorSpecs {
/// The format of a `Spec` is a triple: `{type}:{attribute}:{value}`. Each
/// component is defined as follows:
///
/// * `{type}` can be one of `path`, `line`, `column` or `match`.
/// * `{type}` can be one of `path`, `line`, `column`, `match` or `highlight`.
/// * `{attribute}` can be one of `fg`, `bg` or `style`. `{attribute}` may also
/// be the special value `none`, in which case, `{value}` can be omitted.
/// * `{value}` is either a color name (for `fg`/`bg`) or a style instruction.
@@ -121,7 +122,7 @@ pub struct ColorSpecs {
/// `0x`.
///
/// Valid style instructions are `nobold`, `bold`, `intense`, `nointense`,
/// `underline`, `nounderline`.
/// `underline`, `nounderline`, `italic`, `noitalic`.
///
/// ## Example
///
@@ -181,6 +182,7 @@ enum OutType {
Line,
Column,
Match,
Highlight,
}
/// The specification type.
@@ -201,6 +203,8 @@ enum Style {
NoIntense,
Underline,
NoUnderline,
Italic,
NoItalic,
}
impl ColorSpecs {
@@ -214,6 +218,7 @@ impl ColorSpecs {
OutType::Line => spec.merge_into(&mut merged.line),
OutType::Column => spec.merge_into(&mut merged.column),
OutType::Match => spec.merge_into(&mut merged.matched),
OutType::Highlight => spec.merge_into(&mut merged.highlight),
}
}
merged
@@ -247,6 +252,12 @@ impl ColorSpecs {
pub fn matched(&self) -> &ColorSpec {
&self.matched
}
/// Return the color specification for coloring entire line if there is a
/// matched text.
pub fn highlight(&self) -> &ColorSpec {
&self.highlight
}
}
impl UserColorSpec {
@@ -286,6 +297,12 @@ impl SpecValue {
Style::NoUnderline => {
cspec.set_underline(false);
}
Style::Italic => {
cspec.set_italic(true);
}
Style::NoItalic => {
cspec.set_italic(false);
}
},
}
}
@@ -340,6 +357,7 @@ impl std::str::FromStr for OutType {
"line" => Ok(OutType::Line),
"column" => Ok(OutType::Column),
"match" => Ok(OutType::Match),
"highlight" => Ok(OutType::Highlight),
_ => Err(ColorError::UnrecognizedOutType(s.to_string())),
}
}
@@ -370,6 +388,8 @@ impl std::str::FromStr for Style {
"nointense" => Ok(Style::NoIntense),
"underline" => Ok(Style::Underline),
"nounderline" => Ok(Style::NoUnderline),
"italic" => Ok(Style::Italic),
"noitalic" => Ok(Style::NoItalic),
_ => Err(ColorError::UnrecognizedStyle(s.to_string())),
}
}

89
crates/printer/src/hyperlink.rs
View File

@@ -702,16 +702,20 @@ impl HyperlinkPath {
/// Returns a hyperlink path from an OS path.
#[cfg(windows)]
pub(crate) fn from_path(original_path: &Path) -> Option<HyperlinkPath> {
// On Windows, Path::canonicalize returns the result of
// GetFinalPathNameByHandleW with VOLUME_NAME_DOS,
// which produces paths such as the following:
// On Windows, we use `std::path::absolute` instead of `Path::canonicalize`
// as it can be much faster since it does not touch the file system.
// It wraps the [`GetFullPathNameW`][1] API, except for verbatim paths
// (those which start with `\\?\`, see [the documentation][2] for details).
//
// Here, we strip any verbatim path prefixes since we cannot use them
// in hyperlinks anyway. This can only happen if the user explicitly
// supplies a verbatim path as input, which already needs to be absolute:
//
// \\?\C:\dir\file.txt (local path)
// \\?\UNC\server\dir\file.txt (network share)
//
// The \\?\ prefix comes from VOLUME_NAME_DOS and is constant.
// It is followed either by the drive letter, or by UNC\
// (universal naming convention), which denotes a network share.
// The `\\?\` prefix is constant for verbatim paths, and can be followed
// by `UNC\` (universal naming convention), which denotes a network share.
//
// Given that the default URL format on Windows is file://{path}
// we need to return the following from this function:
@@ -750,18 +754,19 @@ impl HyperlinkPath {
//
// It doesn't parse any other number of slashes in "file//server" as a
// network path.
//
// [1]: https://learn.microsoft.com/en-us/windows/win32/api/fileapi/nf-fileapi-getfullpathnamew
// [2]: https://learn.microsoft.com/en-us/windows/win32/fileio/naming-a-file
const WIN32_NAMESPACE_PREFIX: &str = r"\\?\";
const UNC_PREFIX: &str = r"UNC\";
// As for Unix, we canonicalize the path to make sure we have an
// absolute path.
let path = match original_path.canonicalize() {
let path = match std::path::absolute(original_path) {
Ok(path) => path,
Err(err) => {
log::debug!(
"hyperlink creation for {:?} failed, error occurred \
during path canonicalization: {}",
during conversion to absolute path: {}",
original_path,
err,
);
@@ -784,24 +789,20 @@ impl HyperlinkPath {
return None;
}
};
// As the comment above says, we expect all canonicalized paths to
// begin with a \\?\. If it doesn't, then something weird is happening
// and we should just give up.
if !string.starts_with(WIN32_NAMESPACE_PREFIX) {
log::debug!(
"hyperlink creation for {:?} failed, canonicalization \
returned {:?}, which does not start with \\\\?\\",
original_path,
path,
);
return None;
}
string = &string[WIN32_NAMESPACE_PREFIX.len()..];
// And as above, drop the UNC prefix too, but keep the leading slash.
if string.starts_with(UNC_PREFIX) {
string = &string[(UNC_PREFIX.len() - 1)..];
// Strip verbatim path prefixes (see the comment above for details).
if string.starts_with(WIN32_NAMESPACE_PREFIX) {
string = &string[WIN32_NAMESPACE_PREFIX.len()..];
// Drop the UNC prefix if there is one, but keep the leading slash.
if string.starts_with(UNC_PREFIX) {
string = &string[(UNC_PREFIX.len() - 1)..];
}
} else if string.starts_with(r"\\") || string.starts_with(r"//") {
// Drop one of the two leading slashes of network paths, it will be added back.
string = &string[1..];
}
// Finally, add a leading slash. In the local file case, this turns
// C:\foo\bar into /C:\foo\bar (and then percent encoding turns it into
// /C:/foo/bar). In the network share case, this turns \share\foo\bar
@@ -811,6 +812,13 @@ impl HyperlinkPath {
Some(HyperlinkPath::encode(with_slash.as_bytes()))
}
/// For other platforms (not windows, not unix), return None and log a debug message.
#[cfg(not(any(windows, unix)))]
pub(crate) fn from_path(original_path: &Path) -> Option<HyperlinkPath> {
log::debug!("hyperlinks are not supported on this platform");
None
}
/// Percent-encodes a path.
///
/// The alphanumeric ASCII characters and "-", ".", "_", "~" are unreserved
@@ -999,4 +1007,33 @@ mod tests {
err(InvalidVariable("bar{{".to_string())),
);
}
#[test]
#[cfg(windows)]
fn convert_to_hyperlink_path() {
let convert = |path| {
String::from_utf8(
HyperlinkPath::from_path(Path::new(path)).unwrap().0,
)
.unwrap()
};
assert_eq!(convert(r"C:\dir\file.txt"), "/C:/dir/file.txt");
assert_eq!(
convert(r"C:\foo\bar\..\other\baz.txt"),
"/C:/foo/other/baz.txt"
);
assert_eq!(convert(r"\\server\dir\file.txt"), "//server/dir/file.txt");
assert_eq!(
convert(r"\\server\dir\foo\..\other\file.txt"),
"//server/dir/other/file.txt"
);
assert_eq!(convert(r"\\?\C:\dir\file.txt"), "/C:/dir/file.txt");
assert_eq!(
convert(r"\\?\UNC\server\dir\file.txt"),
"//server/dir/file.txt"
);
}
}

112
crates/printer/src/json.rs
View File

@@ -1,6 +1,7 @@
use std::{
io::{self, Write},
path::Path,
sync::Arc,
time::Instant,
};
@@ -13,7 +14,8 @@ use {
};
use crate::{
counter::CounterWriter, jsont, stats::Stats, util::find_iter_at_in_context,
counter::CounterWriter, jsont, stats::Stats,
util::find_iter_at_in_context, util::Replacer,
};
/// The configuration for the JSON printer.
@@ -26,11 +28,17 @@ struct Config {
pretty: bool,
max_matches: Option<u64>,
always_begin_end: bool,
replacement: Arc<Option<Vec<u8>>>,
}
impl Default for Config {
fn default() -> Config {
Config { pretty: false, max_matches: None, always_begin_end: false }
Config {
pretty: false,
max_matches: None,
always_begin_end: false,
replacement: Arc::new(None),
}
}
}
@@ -98,6 +106,24 @@ impl JSONBuilder {
self.config.always_begin_end = yes;
self
}
/// Set the bytes that will be used to replace each occurrence of a match
/// found.
///
/// The replacement bytes given may include references to capturing groups,
/// which may either be in index form (e.g., `$2`) or can reference named
/// capturing groups if present in the original pattern (e.g., `$foo`).
///
/// For documentation on the full format, please see the `Capture` trait's
/// `interpolate` method in the
/// [grep-printer](https://docs.rs/grep-printer) crate.
pub fn replacement(
&mut self,
replacement: Option<Vec<u8>>,
) -> &mut JSONBuilder {
self.config.replacement = Arc::new(replacement);
self
}
}
/// The JSON printer, which emits results in a JSON lines format.
@@ -256,7 +282,8 @@ impl JSONBuilder {
/// encoded, then the byte offsets correspond to the data after base64
/// decoding.) The `submatch` objects are guaranteed to be sorted by their
/// starting offsets. Note that it is possible for this array to be empty,
/// for example, when searching reports inverted matches.
/// for example, when searching reports inverted matches. If the configuration
/// specifies a replacement, the resulting replacement text is also present.
///
/// #### Message: **context**
///
@@ -286,7 +313,9 @@ impl JSONBuilder {
/// decoding.) The `submatch` objects are guaranteed to be sorted by
/// their starting offsets. Note that it is possible for this array to be
/// non-empty, for example, when searching reports inverted matches such that
/// the original matcher could match things in the contextual lines.
/// the original matcher could match things in the contextual lines. If the
/// configuration specifies a replacemement, the resulting replacement text
/// is also present.
///
/// #### Object: **submatch**
///
@@ -308,6 +337,10 @@ impl JSONBuilder {
/// the `lines` field in the
/// [`match`](#message-match) or [`context`](#message-context)
/// messages.
/// * **replacement** (optional) - An
/// [arbitrary data object](#object-arbitrary-data) corresponding to the
/// replacement text for this submatch, if the configuration specifies
/// a replacement.
///
/// #### Object: **stats**
///
@@ -447,6 +480,23 @@ impl JSONBuilder {
/// }
/// }
/// ```
/// and here's what a match type item would looks like if a replacement text
/// of 'Moriarity' was given as a parameter:
/// ```json
/// {
/// "type": "match",
/// "data": {
/// "path": {"text": "/home/andrew/sherlock"},
/// "lines": {"text": "For the Doctor Watsons of this world, as opposed to the Sherlock\n"},
/// "line_number": 1,
/// "absolute_offset": 0,
/// "submatches": [
/// {"match": {"text": "Watson"}, "replacement": {"text": "Moriarity"}, "start": 15, "end": 21}
/// ]
/// }
/// }
/// ```
#[derive(Clone, Debug)]
pub struct JSON<W> {
config: Config,
@@ -471,6 +521,7 @@ impl<W: io::Write> JSON<W> {
) -> JSONSink<'static, 's, M, W> {
JSONSink {
matcher,
replacer: Replacer::new(),
json: self,
path: None,
start_time: Instant::now(),
@@ -497,6 +548,7 @@ impl<W: io::Write> JSON<W> {
{
JSONSink {
matcher,
replacer: Replacer::new(),
json: self,
path: Some(path.as_ref()),
start_time: Instant::now(),
@@ -559,6 +611,7 @@ impl<W> JSON<W> {
#[derive(Debug)]
pub struct JSONSink<'p, 's, M: Matcher, W> {
matcher: M,
replacer: Replacer<M>,
json: &'s mut JSON<W>,
path: Option<&'p Path>,
start_time: Instant,
@@ -643,6 +696,31 @@ impl<'p, 's, M: Matcher, W: io::Write> JSONSink<'p, 's, M, W> {
Ok(())
}
/// If the configuration specifies a replacement, then this executes the
/// replacement, lazily allocating memory if necessary.
///
/// To access the result of a replacement, use `replacer.replacement()`.
fn replace(
&mut self,
searcher: &Searcher,
bytes: &[u8],
range: std::ops::Range<usize>,
) -> io::Result<()> {
self.replacer.clear();
if self.json.config.replacement.is_some() {
let replacement =
(*self.json.config.replacement).as_ref().map(|r| &*r).unwrap();
self.replacer.replace_all(
searcher,
&self.matcher,
bytes,
range,
replacement,
)?;
}
Ok(())
}
/// Returns true if this printer should quit.
///
/// This implements the logic for handling quitting after seeing a certain
@@ -711,10 +789,15 @@ impl<'p, 's, M: Matcher, W: io::Write> Sink for JSONSink<'p, 's, M, W> {
mat.buffer(),
mat.bytes_range_in_buffer(),
)?;
self.replace(searcher, mat.buffer(), mat.bytes_range_in_buffer())?;
self.stats.add_matches(self.json.matches.len() as u64);
self.stats.add_matched_lines(mat.lines().count() as u64);
let submatches = SubMatches::new(mat.bytes(), &self.json.matches);
let submatches = SubMatches::new(
mat.bytes(),
&self.json.matches,
self.replacer.replacement(),
);
let msg = jsont::Message::Match(jsont::Match {
path: self.path,
lines: mat.bytes(),
@@ -740,7 +823,12 @@ impl<'p, 's, M: Matcher, W: io::Write> Sink for JSONSink<'p, 's, M, W> {
}
let submatches = if searcher.invert_match() {
self.record_matches(searcher, ctx.bytes(), 0..ctx.bytes().len())?;
SubMatches::new(ctx.bytes(), &self.json.matches)
self.replace(searcher, ctx.bytes(), 0..ctx.bytes().len())?;
SubMatches::new(
ctx.bytes(),
&self.json.matches,
self.replacer.replacement(),
)
} else {
SubMatches::empty()
};
@@ -831,19 +919,27 @@ enum SubMatches<'a> {
impl<'a> SubMatches<'a> {
/// Create a new set of match ranges from a set of matches and the
/// corresponding bytes that those matches apply to.
fn new(bytes: &'a [u8], matches: &[Match]) -> SubMatches<'a> {
fn new(
bytes: &'a [u8],
matches: &[Match],
replacement: Option<(&'a [u8], &'a [Match])>,
) -> SubMatches<'a> {
if matches.len() == 1 {
let mat = matches[0];
SubMatches::Small([jsont::SubMatch {
m: &bytes[mat],
replacement: replacement
.map(|(rbuf, rmatches)| &rbuf[rmatches[0]]),
start: mat.start(),
end: mat.end(),
}])
} else {
let mut match_ranges = vec![];
for &mat in matches {
for (i, &mat) in matches.iter().enumerate() {
match_ranges.push(jsont::SubMatch {
m: &bytes[mat],
replacement: replacement
.map(|(rbuf, rmatches)| &rbuf[rmatches[i]]),
start: mat.start(),
end: mat.end(),
});

4
crates/printer/src/jsont.rs
View File

@@ -135,6 +135,7 @@ impl<'a> serde::Serialize for Context<'a> {
pub(crate) struct SubMatch<'a> {
pub(crate) m: &'a [u8],
pub(crate) replacement: Option<&'a [u8]>,
pub(crate) start: usize,
pub(crate) end: usize,
}
@@ -148,6 +149,9 @@ impl<'a> serde::Serialize for SubMatch<'a> {
let mut state = s.serialize_struct("SubMatch", 3)?;
state.serialize_field("match", &Data::from_bytes(self.m))?;
if let Some(r) = self.replacement {
state.serialize_field("replacement", &Data::from_bytes(r))?;
}
state.serialize_field("start", &self.start)?;
state.serialize_field("end", &self.end)?;
state.end()

36
crates/printer/src/standard.rs
View File

@@ -762,10 +762,8 @@ impl<'p, 's, M: Matcher, W: WriteColor> StandardSink<'p, 's, M, W> {
) -> io::Result<()> {
self.replacer.clear();
if self.standard.config.replacement.is_some() {
let replacement = (*self.standard.config.replacement)
.as_ref()
.map(|r| &*r)
.unwrap();
let replacement =
(*self.standard.config.replacement).as_ref().unwrap();
self.replacer.replace_all(
searcher,
&self.matcher,
@@ -1322,6 +1320,7 @@ impl<'a, M: Matcher, W: WriteColor> StandardImpl<'a, M, W> {
self.write(&bytes[line])?;
return Ok(());
}
self.start_line_highlight()?;
while !line.is_empty() {
if matches[*match_index].end() <= line.start() {
if *match_index + 1 < matches.len() {
@@ -1348,6 +1347,7 @@ impl<'a, M: Matcher, W: WriteColor> StandardImpl<'a, M, W> {
}
}
self.end_color_match()?;
self.end_line_highlight()?;
Ok(())
}
@@ -1549,11 +1549,37 @@ impl<'a, M: Matcher, W: WriteColor> StandardImpl<'a, M, W> {
if !self.in_color_match.get() {
return Ok(());
}
self.wtr().borrow_mut().reset()?;
if self.highlight_on() {
self.wtr()
.borrow_mut()
.set_color(self.config().colors.highlight())?;
} else {
self.wtr().borrow_mut().reset()?;
}
self.in_color_match.set(false);
Ok(())
}
fn highlight_on(&self) -> bool {
!self.config().colors.highlight().is_none() && !self.is_context()
}
fn start_line_highlight(&self) -> io::Result<()> {
if self.highlight_on() {
self.wtr()
.borrow_mut()
.set_color(self.config().colors.highlight())?;
}
Ok(())
}
fn end_line_highlight(&self) -> io::Result<()> {
if self.highlight_on() {
self.wtr().borrow_mut().reset()?;
}
Ok(())
}
fn write(&self, buf: &[u8]) -> io::Result<()> {
self.wtr().borrow_mut().write_all(buf)
}

45
crates/printer/src/summary.rs
View File

@@ -87,7 +87,13 @@ pub enum SummaryKind {
///
/// Note that if `stats` is enabled, then searching continues in order to
/// compute statistics.
Quiet,
QuietWithMatch,
/// Don't show any output and the stop the search once a non-matching file
/// is found.
///
/// Note that if `stats` is enabled, then searching continues in order to
/// compute statistics.
QuietWithoutMatch,
}
impl SummaryKind {
@@ -101,7 +107,7 @@ impl SummaryKind {
match *self {
PathWithMatch | PathWithoutMatch => true,
Count | CountMatches | Quiet => false,
Count | CountMatches | QuietWithMatch | QuietWithoutMatch => false,
}
}
@@ -112,7 +118,8 @@ impl SummaryKind {
match *self {
CountMatches => true,
Count | PathWithMatch | PathWithoutMatch | Quiet => false,
Count | PathWithMatch | PathWithoutMatch | QuietWithMatch
| QuietWithoutMatch => false,
}
}
@@ -122,8 +129,10 @@ impl SummaryKind {
use self::SummaryKind::*;
match *self {
PathWithMatch | Quiet => true,
Count | CountMatches | PathWithoutMatch => false,
PathWithMatch | QuietWithMatch => true,
Count | CountMatches | PathWithoutMatch | QuietWithoutMatch => {
false
}
}
}
}
@@ -246,9 +255,9 @@ impl SummaryBuilder {
///
/// When this is enabled, this printer may need to do extra work in order
/// to compute certain statistics, which could cause the search to take
/// longer. For example, in `Quiet` mode, a search can quit after finding
/// the first match, but if `stats` is enabled, then the search will
/// continue after the first match in order to compute statistics.
/// longer. For example, in `QuietWithMatch` mode, a search can quit after
/// finding the first match, but if `stats` is enabled, then the search
/// will continue after the first match in order to compute statistics.
///
/// For a complete description of available statistics, see [`Stats`].
///
@@ -505,7 +514,9 @@ impl<'p, 's, M: Matcher, W: WriteColor> SummarySink<'p, 's, M, W> {
/// search.
pub fn has_match(&self) -> bool {
match self.summary.config.kind {
SummaryKind::PathWithoutMatch => self.match_count == 0,
SummaryKind::PathWithoutMatch | SummaryKind::QuietWithoutMatch => {
self.match_count == 0
}
_ => self.match_count > 0,
}
}
@@ -749,14 +760,14 @@ impl<'p, 's, M: Matcher, W: WriteColor> Sink for SummarySink<'p, 's, M, W> {
// don't quit and therefore search the entire contents of the file.
//
// There is an unfortunate inconsistency here. Namely, when using
// Quiet or PathWithMatch, then the printer can quit after the first
// match seen, which could be long before seeing binary data. This
// means that using PathWithMatch can print a path where as using
// QuietWithMatch or PathWithMatch, then the printer can quit after the
// first match seen, which could be long before seeing binary data.
// This means that using PathWithMatch can print a path where as using
// Count might not print it at all because of binary data.
//
// It's not possible to fix this without also potentially significantly
// impacting the performance of Quiet or PathWithMatch, so we accept
// the bug.
// impacting the performance of QuietWithMatch or PathWithMatch, so we
// accept the bug.
if self.binary_byte_offset.is_some()
&& searcher.binary_detection().quit_byte().is_some()
{
@@ -798,7 +809,7 @@ impl<'p, 's, M: Matcher, W: WriteColor> Sink for SummarySink<'p, 's, M, W> {
self.write_path_line(searcher)?;
}
}
SummaryKind::Quiet => {}
SummaryKind::QuietWithMatch | SummaryKind::QuietWithoutMatch => {}
}
Ok(())
}
@@ -1122,7 +1133,7 @@ and exhibited clearly, with a label attached.
fn quiet() {
let matcher = RegexMatcher::new(r"Watson|Sherlock").unwrap();
let mut printer = SummaryBuilder::new()
.kind(SummaryKind::Quiet)
.kind(SummaryKind::QuietWithMatch)
.build_no_color(vec![]);
let match_count = {
let mut sink = printer.sink_with_path(&matcher, "sherlock");
@@ -1144,7 +1155,7 @@ and exhibited clearly, with a label attached.
fn quiet_with_stats() {
let matcher = RegexMatcher::new(r"Watson|Sherlock").unwrap();
let mut printer = SummaryBuilder::new()
.kind(SummaryKind::Quiet)
.kind(SummaryKind::QuietWithMatch)
.stats(true)
.build_no_color(vec![]);
let match_count = {

2
crates/regex/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-regex"
version = "0.1.12" #:version
version = "0.1.13" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Use Rust's regex library with the 'grep' crate.

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

@@ -233,7 +233,7 @@ impl ConfiguredHIR {
&self.config
}
/// Return a reference to the underyling HIR.
/// Return a reference to the underlying HIR.
pub(crate) fn hir(&self) -> &Hir {
&self.hir
}

31
crates/regex/src/literal.rs
View File

@@ -15,7 +15,7 @@ use crate::{config::ConfiguredHIR, error::Error};
/// that are in turn used to build a simpler regex that is more amenable to
/// optimization.
///
/// The main idea underyling the validity of this technique is the fact
/// The main idea underlying the validity of this technique is the fact
/// that ripgrep searches individuals lines and not across lines. (Unless
/// -U/--multiline is enabled.) Namely, we can pluck literals out of the regex,
/// search for them, find the bounds of the line in which that literal occurs
@@ -430,6 +430,7 @@ impl Extractor {
}
seq1.union(seq2);
assert!(seq1.len().map_or(true, |x| x <= self.limit_total));
seq1.prefix = seq1.prefix && seq2.prefix;
seq1
}
@@ -586,10 +587,15 @@ impl TSeq {
lits.iter().any(is_poisonous)
}
/// Compare the two sequences and return the one that is believed to be best
/// according to a hodge podge of heuristics.
/// Compare the two sequences and return the one that is believed to be
/// best according to a hodge podge of heuristics.
fn choose(self, other: TSeq) -> TSeq {
let (seq1, seq2) = (self, other);
let (mut seq1, mut seq2) = (self, other);
// Whichever one we pick, by virtue of picking one, we choose
// to not take the other. So we must consider the result inexact.
seq1.make_inexact();
seq2.make_inexact();
if !seq1.is_finite() {
return seq2;
} else if !seq2.is_finite() {
@@ -681,7 +687,7 @@ mod tests {
assert_eq!(e(r"foo"), seq([E("foo")]));
assert_eq!(e(r"[a-z]foo[a-z]"), seq([I("foo")]));
assert_eq!(e(r"[a-z](foo)(bar)[a-z]"), seq([I("foobar")]));
assert_eq!(e(r"[a-z]([a-z]foo)(bar[a-z])[a-z]"), seq([I("foobar")]));
assert_eq!(e(r"[a-z]([a-z]foo)(bar[a-z])[a-z]"), seq([I("foo")]));
assert_eq!(e(r"[a-z]([a-z]foo)([a-z]foo)[a-z]"), seq([I("foo")]));
assert_eq!(e(r"(\d{1,3}\.){3}\d{1,3}"), seq([I(".")]));
assert_eq!(e(r"[a-z]([a-z]foo){3}[a-z]"), seq([I("foo")]));
@@ -689,7 +695,7 @@ mod tests {
assert_eq!(e(r"[a-z]([a-z]foo[a-z]){3}[a-z]"), seq([I("foo")]));
assert_eq!(
e(r"[a-z]([a-z]foo){3}(bar[a-z]){3}[a-z]"),
seq([I("foobar")])
seq([I("foo")])
);
}
@@ -935,14 +941,14 @@ mod tests {
assert_eq!(Seq::infinite(), e(r"[A-Z]+"));
assert_eq!(seq([I("1")]), e(r"1[A-Z]"));
assert_eq!(seq([I("1")]), e(r"1[A-Z]2"));
assert_eq!(seq([E("123")]), e(r"[A-Z]+123"));
assert_eq!(seq([I("123")]), e(r"[A-Z]+123"));
assert_eq!(seq([I("123")]), e(r"[A-Z]+123[A-Z]+"));
assert_eq!(Seq::infinite(), e(r"1|[A-Z]|3"));
assert_eq!(seq([E("1"), I("2"), E("3")]), e(r"1|2[A-Z]|3"),);
assert_eq!(seq([E("1"), I("2"), E("3")]), e(r"1|[A-Z]2[A-Z]|3"),);
assert_eq!(seq([E("1"), E("2"), E("3")]), e(r"1|[A-Z]2|3"),);
assert_eq!(seq([E("1"), I("2"), E("3")]), e(r"1|[A-Z]2|3"),);
assert_eq!(seq([E("1"), I("2"), E("4")]), e(r"1|2[A-Z]3|4"),);
assert_eq!(seq([E("2")]), e(r"(?:|1)[A-Z]2"));
assert_eq!(seq([I("2")]), e(r"(?:|1)[A-Z]2"));
assert_eq!(inexact([I("a")]), e(r"a.z"));
}
@@ -1005,4 +1011,11 @@ mod tests {
let s = e(r"foobarfoo|foo| |foofoo");
assert_eq!(Seq::infinite(), s);
}
// Regression test for: https://github.com/BurntSushi/ripgrep/issues/2884
#[test]
fn case_insensitive_alternation() {
let s = e(r"(?i:e.x|ex)");
assert_eq!(s, seq([I("X"), I("x")]));
}
}

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

@@ -552,8 +552,6 @@ impl RegexCaptures {
#[cfg(test)]
mod tests {
use grep_matcher::{LineMatchKind, Matcher};
use super::*;
// Test that enabling word matches does the right thing and demonstrate

9
crates/searcher/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-searcher"
version = "0.1.13" #:version
version = "0.1.14" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Fast line oriented regex searching as a library.
@@ -23,11 +23,10 @@ memchr = "2.6.3"
memmap = { package = "memmap2", version = "0.9.0" }
[dev-dependencies]
grep-regex = { version = "0.1.12", path = "../regex" }
grep-regex = { version = "0.1.13", path = "../regex" }
regex = "1.9.5"
[features]
simd-accel = ["encoding_rs/simd-accel"]
# This feature is DEPRECATED. Runtime dispatch is used for SIMD now.
# These features are DEPRECATED. Runtime dispatch is used for SIMD now.
simd-accel = []
avx-accel = []

10
crates/searcher/src/line_buffer.rs
View File

@@ -538,6 +538,11 @@ fn replace_bytes(
while let Some(i) = bytes.find_byte(src) {
bytes[i] = replacement;
bytes = &mut bytes[i + 1..];
// To search for adjacent `src` bytes we use a different strategy.
// Since binary data tends to have long runs of NUL terminators,
// it is faster to compare one-byte-at-a-time than to stop and start
// memchr (through `find_byte`) for every byte in a sequence.
while bytes.get(0) == Some(&src) {
bytes[0] = replacement;
bytes = &mut bytes[1..];
@@ -548,7 +553,7 @@ fn replace_bytes(
#[cfg(test)]
mod tests {
use bstr::{ByteSlice, ByteVec};
use bstr::ByteVec;
use super::*;
@@ -577,6 +582,9 @@ and exhibited clearly, with a label attached.\
#[test]
fn replace() {
assert_eq!(replace_str("", b'b', b'z'), (s(""), None));
assert_eq!(replace_str("a", b'a', b'a'), (s("a"), None));
assert_eq!(replace_str("a", b'b', b'z'), (s("a"), None));
assert_eq!(replace_str("abc", b'b', b'z'), (s("azc"), Some(1)));
assert_eq!(replace_str("abb", b'b', b'z'), (s("azz"), Some(1)));
assert_eq!(replace_str("aba", b'a', b'z'), (s("zbz"), Some(0)));

2
crates/searcher/src/lines.rs
View File

@@ -198,8 +198,6 @@ fn preceding_by_pos(
#[cfg(test)]
mod tests {
use grep_matcher::Match;
use super::*;
const SHERLOCK: &'static str = "\

11
crates/searcher/src/searcher/glue.rs
View File

@@ -37,7 +37,11 @@ where
pub(crate) fn run(mut self) -> Result<(), S::Error> {
if self.core.begin()? {
while self.fill()? && self.core.match_by_line(self.rdr.buffer())? {
while self.fill()? {
if !self.core.match_by_line(self.rdr.buffer())? {
self.consume_remaining();
break;
}
}
}
self.core.finish(
@@ -46,6 +50,11 @@ where
)
}
fn consume_remaining(&mut self) {
let consumed = self.core.pos();
self.rdr.consume(consumed);
}
fn fill(&mut self) -> Result<bool, S::Error> {
assert!(self.rdr.buffer()[self.core.pos()..].is_empty());

2
crates/searcher/src/searcher/mod.rs
View File

@@ -7,7 +7,6 @@ use std::{
};
use {
encoding_rs,
encoding_rs_io::DecodeReaderBytesBuilder,
grep_matcher::{LineTerminator, Match, Matcher},
};
@@ -1005,6 +1004,7 @@ fn slice_has_bom(slice: &[u8]) -> bool {
None => return false,
Some((enc, _)) => enc,
};
log::trace!("found byte-order mark (BOM) for encoding {enc:?}");
[encoding_rs::UTF_16LE, encoding_rs::UTF_16BE, encoding_rs::UTF_8]
.contains(&enc)
}

2
crates/searcher/src/testutil.rs
View File

@@ -725,8 +725,6 @@ impl TesterConfig {
#[cfg(test)]
mod tests {
use grep_matcher::{Match, Matcher};
use super::*;
fn m(start: usize, end: usize) -> Match {

317
doc/rg.1.txt.tpl
View File

@@ -1,317 +0,0 @@
rg(1)
=====
Name
----
rg - recursively search the current directory for lines matching a pattern
Synopsis
--------
*rg* [_OPTIONS_] _PATTERN_ [_PATH_...]
*rg* [_OPTIONS_] *-e* _PATTERN_... [_PATH_...]
*rg* [_OPTIONS_] *-f* _PATTERNFILE_... [_PATH_...]
*rg* [_OPTIONS_] *--files* [_PATH_...]
*rg* [_OPTIONS_] *--type-list*
*command* | *rg* [_OPTIONS_] _PATTERN_
*rg* [_OPTIONS_] *--help*
*rg* [_OPTIONS_] *--version*
DESCRIPTION
-----------
ripgrep (rg) recursively searches the current directory for a regex pattern.
By default, ripgrep will respect your .gitignore and automatically skip hidden
files/directories and binary files.
ripgrep's default regex engine uses finite automata and guarantees linear
time searching. Because of this, features like backreferences and arbitrary
look-around are not supported. However, if ripgrep is built with PCRE2, then
the *--pcre2* flag can be used to enable backreferences and look-around.
ripgrep supports configuration files. Set *RIPGREP_CONFIG_PATH* to a
configuration file. The file can specify one shell argument per line. Lines
starting with *#* are ignored. For more details, see the man page or the
*README*.
ripgrep will automatically detect if stdin exists and search stdin for a regex
pattern, e.g. *ls | rg foo*. In some environments, stdin may exist when it
shouldn't. To turn off stdin detection explicitly specify the directory to
search, e.g. *rg foo ./*.
Tip: to disable all smart filtering and make ripgrep behave a bit more like
classical grep, use *rg -uuu*.
REGEX SYNTAX
------------
ripgrep uses Rust's regex engine by default, which documents its syntax:
https://docs.rs/regex/*/regex/#syntax
ripgrep uses byte-oriented regexes, which has some additional documentation:
https://docs.rs/regex/*/regex/bytes/index.html#syntax
To a first approximation, ripgrep uses Perl-like regexes without look-around or
backreferences. This makes them very similar to the "extended" (ERE) regular
expressions supported by *egrep*, but with a few additional features like
Unicode character classes.
If you're using ripgrep with the *--pcre2* flag, then please consult
https://www.pcre.org or the PCRE2 man pages for documentation on the supported
syntax.
POSITIONAL ARGUMENTS
--------------------
_PATTERN_::
A regular expression used for searching. To match a pattern beginning with a
dash, use the -e/--regexp option.
_PATH_::
A file or directory to search. Directories are searched recursively. File
paths specified explicitly on the command line override glob and ignore
rules.
OPTIONS
-------
Note that many options can be disabled via flags. In some cases, those flags
are not listed in a first class way below. For example, the *--column*
flag (listed below) enables column numbers in ripgrep's output, but the
*--no-column* flag (not listed below) disables them. The reverse can also
exist. For example, the *--no-ignore* flag (listed below) disables ripgrep's
*gitignore* logic, but the *--ignore* flag (not listed below) enables it. These
flags are useful for overriding a ripgrep configuration file on the command
line. Each flag's documentation notes whether an inverted flag exists. In all
cases, the flag specified last takes precedence.
{OPTIONS}
EXIT STATUS
-----------
If ripgrep finds a match, then the exit status of the program is 0. If no match
could be found, then the exit status is 1. If an error occurred, then the exit
status is always 2 unless ripgrep was run with the *--quiet* flag and a match
was found. In summary:
* `0` exit status occurs only when at least one match was found, and if
no error occurred, unless *--quiet* was given.
* `1` exit status occurs only when no match was found and no error occurred.
* `2` exit status occurs when an error occurred. This is true for both
catastrophic errors (e.g., a regex syntax error) and for soft errors (e.g.,
unable to read a file).
AUTOMATIC FILTERING
-------------------
TL;DR - To disable automatic filtering, use 'rg -uuu'.
One of ripgrep's most important features is its automatic smart filtering.
It is the most apparent differentiating feature between ripgrep and other tools
like 'grep'. As such, its behavior may be surprising to users that aren't
expecting it.
ripgrep does four types of filtering automatically:
1. Files and directories that match ignore rules are not searched.
2. Hidden files and directories are not searched.
3. Binary files (files with a 'NUL' byte) are not searched.
4. Symbolic links are not followed.
The first type of filtering is the most sophisticated. ripgrep will attempt to
respect your gitignore rules as faithfully as possible. In particular, this
includes the following:
* Any global rules, e.g., in '$HOME/.config/git/ignore'.
* Any rules in '.gitignore'.
* Any local rules, e.g., in '.git/info/exclude'.
In some cases, ripgrep and git will not always be in sync in terms of which
files are ignored. For example, a file that is ignored via '.gitignore' but is
tracked by git would not be searched by ripgrep even though git tracks it. This
is unlikely to ever be fixed. Instead, you should either make sure your exclude
rules match the files you track precisely, or otherwise use 'git grep' for
search.
Additional ignore rules can be provided outside of a git context:
* Any rules in '.ignore'.
* Any rules in '.rgignore'.
* Any rules in files specified with the '--ignore-file' flag.
The precedence of ignore rules is as follows, with later items overriding
earlier items:
* Files given by '--ignore-file'.
* Global gitignore rules, e.g., from '$HOME/.config/git/ignore'.
* Local rules from '.git/info/exclude'.
* Rules from '.gitignore'.
* Rules from '.ignore'.
* Rules from '.rgignore'.
So for example, if 'foo' were in a '.gitignore' and '!foo' were in an
'.rgignore', then 'foo' would not be ignored since '.rgignore' takes precedence
over '.gitignore'.
Each of the types of filtering can be configured via command line flags:
* There are several flags starting with '--no-ignore' that toggle which,
if any, ignore rules are respected. '--no-ignore' by itself will disable
all of them.
* '-./--hidden' will force ripgrep to search hidden files and directories.
* '--binary' will force ripgrep to search binary files.
* '-L/--follow' will force ripgrep to follow symlinks.
As a special short hand, the `-u` flag can be specified up to three times. Each
additional time incrementally decreases filtering:
* '-u' is equivalent to '--no-ignore'.
* '-uu' is equivalent to '--no-ignore --hidden'.
* '-uuu' is equivalent to '--no-ignore --hidden --binary'.
In particular, 'rg -uuu' should search the same exact content as 'grep -r'.
CONFIGURATION FILES
-------------------
ripgrep supports reading configuration files that change ripgrep's default
behavior. The format of the configuration file is an "rc" style and is very
simple. It is defined by two rules:
1. Every line is a shell argument, after trimming whitespace.
2. Lines starting with *#* (optionally preceded by any amount of
whitespace) are ignored.
ripgrep will look for a single configuration file if and only if the
*RIPGREP_CONFIG_PATH* environment variable is set and is non-empty. ripgrep
will parse shell arguments from this file on startup and will behave as if
the arguments in this file were prepended to any explicit arguments given to
ripgrep on the command line. Note though that the 'rg' command you run must
still be valid. That is, it must always contain at least one pattern at the
command line, even if the configuration file uses the '-e/--regexp' flag.
For example, if your ripgreprc file contained a single line:
--smart-case
then the following command
RIPGREP_CONFIG_PATH=wherever/.ripgreprc rg foo
would behave identically to the following command
rg --smart-case foo
another example is adding types
--type-add
web:*.{html,css,js}*
would behave identically to the following command
rg --type-add 'web:*.{html,css,js}*' foo
same with using globs
--glob=!.git
or
--glob
!.git
would behave identically to the following command
rg --glob '!.git' foo
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.
Conflicts between configuration files and explicit arguments are handled
exactly like conflicts in the same command line invocation. That is,
this command:
RIPGREP_CONFIG_PATH=wherever/.ripgreprc rg foo --case-sensitive
is exactly equivalent to
rg --smart-case foo --case-sensitive
in which case, the *--case-sensitive* flag would override the *--smart-case*
flag.
SHELL COMPLETION
----------------
Shell completion files are included in the release tarball for Bash, Fish, Zsh
and PowerShell.
For *bash*, move *rg.bash* to *$XDG_CONFIG_HOME/bash_completion*
or */etc/bash_completion.d/*.
For *fish*, move *rg.fish* to *$HOME/.config/fish/completions*.
For *zsh*, move *_rg* to one of your *$fpath* directories.
CAVEATS
-------
ripgrep may abort unexpectedly when using default settings if it searches a
file that is simultaneously truncated. This behavior can be avoided by passing
the *--no-mmap* flag which will forcefully disable the use of memory maps in
all cases.
ripgrep may use a large amount of memory depending on a few factors. Firstly,
if ripgrep uses parallelism for search (the default), then the entire output
for each individual file is buffered into memory in order to prevent
interleaving matches in the output. To avoid this, you can disable parallelism
with the *-j1* flag. Secondly, ripgrep always needs to have at least a single
line in memory in order to execute a search. A file with a very long line can
thus cause ripgrep to use a lot of memory. Generally, this only occurs when
searching binary data with the *-a* flag enabled. (When the *-a* flag isn't
enabled, ripgrep will replace all NUL bytes with line terminators, which
typically prevents exorbitant memory usage.) Thirdly, when ripgrep searches
a large file using a memory map, the process will report its resident memory
usage as the size of the file. However, this does not mean ripgrep actually
needed to use that much memory; the operating system will generally handle this
for you.
VERSION
-------
{VERSION}
HOMEPAGE
--------
https://github.com/BurntSushi/ripgrep
Please report bugs and feature requests in the issue tracker. Please do your
best to provide a reproducible test case for bugs. This should include the
corpus being searched, the *rg* command, the actual output and the expected
output. Please also include the output of running the same *rg* command but
with the *--debug* flag.
AUTHORS
-------
Andrew Gallant <jamslam@gmail.com>

4
fuzz/.gitignore vendored Normal file
View File

@@ -0,0 +1,4 @@
target
corpus
artifacts
coverage

188
fuzz/Cargo.lock generated Normal file
View File

@@ -0,0 +1,188 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 4
[[package]]
name = "aho-corasick"
version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b2969dcb958b36655471fc61f7e416fa76033bdd4bfed0678d8fee1e2d07a1f0"
dependencies = [
"memchr",
]
[[package]]
name = "arbitrary"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7d5a26814d8dcb93b0e5a0ff3c6d80a8843bafb21b39e8e18a6f05471870e110"
dependencies = [
"derive_arbitrary",
]
[[package]]
name = "bstr"
version = "1.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c48f0051a4b4c5e0b6d365cd04af53aeaa209e3cc15ec2cdb69e73cc87fbd0dc"
dependencies = [
"memchr",
"serde",
]
[[package]]
name = "cc"
version = "1.0.83"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f1174fb0b6ec23863f8b971027804a42614e347eafb0a95bf0b12cdae21fc4d0"
dependencies = [
"jobserver",
"libc",
]
[[package]]
name = "derive_arbitrary"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "67e77553c4162a157adbf834ebae5b415acbecbeafc7a74b0e886657506a7611"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "fuzz"
version = "0.0.1"
dependencies = [
"globset",
"libfuzzer-sys",
]
[[package]]
name = "globset"
version = "0.4.16"
dependencies = [
"aho-corasick",
"arbitrary",
"bstr",
"log",
"regex-automata",
"regex-syntax",
]
[[package]]
name = "jobserver"
version = "0.1.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8c37f63953c4c63420ed5fd3d6d398c719489b9f872b9fa683262f8edd363c7d"
dependencies = [
"libc",
]
[[package]]
name = "libc"
version = "0.2.152"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13e3bf6590cbc649f4d1a3eefc9d5d6eb746f5200ffb04e5e142700b8faa56e7"
[[package]]
name = "libfuzzer-sys"
version = "0.4.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a96cfd5557eb82f2b83fed4955246c988d331975a002961b07c81584d107e7f7"
dependencies = [
"arbitrary",
"cc",
"once_cell",
]
[[package]]
name = "log"
version = "0.4.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
[[package]]
name = "memchr"
version = "2.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "523dc4f511e55ab87b694dc30d0f820d60906ef06413f93d4d7a1385599cc149"
[[package]]
name = "once_cell"
version = "1.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
[[package]]
name = "proc-macro2"
version = "1.0.78"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e2422ad645d89c99f8f3e6b88a9fdeca7fabeac836b1002371c4367c8f984aae"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
dependencies = [
"proc-macro2",
]
[[package]]
name = "regex-automata"
version = "0.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3b7fa1134405e2ec9353fd416b17f8dacd46c473d7d3fd1cf202706a14eb792a"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
[[package]]
name = "regex-syntax"
version = "0.8.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c08c74e62047bb2de4ff487b251e4a92e24f48745648451635cec7d591162d9f"
[[package]]
name = "serde"
version = "1.0.195"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "63261df402c67811e9ac6def069e4786148c4563f4b50fd4bf30aa370d626b02"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.195"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "46fe8f8603d81ba86327b23a2e9cdf49e1255fb94a4c5f297f6ee0547178ea2c"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "syn"
version = "2.0.48"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0f3531638e407dfc0814761abb7c00a5b54992b849452a0646b7f65c9f770f3f"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "unicode-ident"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"

25
fuzz/Cargo.toml Normal file
View File

@@ -0,0 +1,25 @@
[package]
name = "fuzz"
version = "0.0.1"
publish = false
edition = "2021"
[package.metadata]
cargo-fuzz = true
[dependencies]
libfuzzer-sys = "0.4"
globset = { path = "../crates/globset", features = ["arbitrary"] }
# Prevent this from interfering with workspaces
[workspace]
members = ["."]
[profile.release]
debug = 1
[[bin]]
name = "fuzz_glob"
path = "fuzz_targets/fuzz_glob.rs"
test = false
doc = false

52
fuzz/README.md Normal file
View File

@@ -0,0 +1,52 @@
# Fuzz Testing
## Introduction
Fuzz testing produces pseudo-random / arbitrary data that is used to find
stability issues within a code base. While Rust provides a strong type system,
this does not guarantee that an object will convert properly from one struct
to another. It is the responsibility of the developer to ensure that a struct
is converted properly. Fuzz testing will generate input within the domain of
each property. This arbitrary data can then be used to convert from ObjectA
to ObjectB and then back. This type of testing will help catch bugs that the
type system is not able to see.
## Installation
This crate relies on the `cargo-fuzz` component. To install this component,
run the following from the `fuzz` directory:
```bash
cargo install cargo-fuzz
```
## Listing Targets
Once installed, fuzz targets can be listed by running the following command:
```bash
cargo fuzz list
```
This command will print out a list of all targets that can be tested.
## Running Fuzz Tests
To run a fuzz test, the target must be specified:
```bash
cargo fuzz run <target>
```
Note that the above will run the fuzz test indefinitely. Use the
`-max_total_time=<num seconds>` flag to specify how many seconds the test
should run for:
```bash
cargo fuzz run <target> -- -max_total_time=5
```
The above command will run the fuzz test for five seconds. If the test
completes without error it will show how many tests were run successfully.
The test will abort and return a non-zero error code if it is able to produce
an error. The arbitrary input will be displayed in the event of a failure.

22
fuzz/fuzz_targets/fuzz_glob.rs Normal file
View File

@@ -0,0 +1,22 @@
#![no_main]
use std::str::FromStr;
use globset::Glob;
libfuzzer_sys::fuzz_target!(|glob_str: &str| {
let Ok(glob) = Glob::new(glob_str) else {
return;
};
let Ok(glob2) = Glob::from_str(glob_str) else {
return;
};
// Verify that a `Glob` constructed with `new` is the same as a `Glob`` constructed
// with `from_str`.
assert_eq!(glob, glob2);
// Verify that `Glob::glob` produces the same string as the original.
assert_eq!(glob.glob(), glob_str);
});

6
pkg/brew/ripgrep-bin.rb
View File

@@ -1,14 +1,14 @@
class RipgrepBin < Formula
version '14.0.2'
version '14.1.1'
desc "Recursively search directories for a regex pattern."
homepage "https://github.com/BurntSushi/ripgrep"
if OS.mac?
url "https://github.com/BurntSushi/ripgrep/releases/download/#{version}/ripgrep-#{version}-x86_64-apple-darwin.tar.gz"
sha256 "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
sha256 "fc87e78f7cb3fea12d69072e7ef3b21509754717b746368fd40d88963630e2b3"
elsif OS.linux?
url "https://github.com/BurntSushi/ripgrep/releases/download/#{version}/ripgrep-#{version}-x86_64-unknown-linux-musl.tar.gz"
sha256 "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
sha256 "4cf9f2741e6c465ffdb7c26f38056a59e2a2544b51f7cc128ef28337eeae4d8e"
end
conflicts_with "ripgrep"

122
tests/binary.rs
View File

@@ -4,8 +4,8 @@ use crate::util::{Dir, TestCommand};
// handling of binary files. There's quite a bit of discussion on this in this
// bug report: https://github.com/BurntSushi/ripgrep/issues/306
// Our haystack is the first 500 lines of Gutenberg's copy of "A Study in
// Scarlet," with a NUL byte at line 1898: `abcdef\x00`.
// Our haystack is the first 2,133 lines of Gutenberg's copy of "A Study in
// Scarlet," with a NUL byte at line 1870: `abcdef\x00`.
//
// The position and size of the haystack is, unfortunately, significant. In
// particular, the NUL byte is specifically inserted at some point *after* the
@@ -21,10 +21,124 @@ use crate::util::{Dir, TestCommand};
// detection with memory maps is a bit different. Namely, NUL bytes are only
// searched for in the first few KB of the file and in a match. Normally, NUL
// bytes are searched for everywhere.
//
// TODO: Add tests for binary file detection when using memory maps.
const HAY: &'static [u8] = include_bytes!("./data/sherlock-nul.txt");
// Tests for binary file detection when using memory maps.
// As noted in the original comments, with memory maps binary detection
// works differently - NUL bytes are only searched for in the first few KB
// of the file and in matches.
// Test that matches in a binary file with memory maps work as expected
// with implicit file search (via glob pattern).
rgtest!(mmap_match_implicit, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
cmd.args(&["--mmap", "-n", "Project Gutenberg EBook", "-g", "hay"]);
// With mmap, we get a match and a warning about binary content
let expected = "\
hay:1:The Project Gutenberg EBook of A Study In Scarlet, by Arthur Conan Doyle
";
eqnice!(expected, cmd.stdout());
});
// Test with an explicit file argument when using memory maps.
rgtest!(mmap_match_explicit, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
cmd.args(&["--mmap", "-n", "Project Gutenberg EBook", "hay"]);
let expected = "\
1:The Project Gutenberg EBook of A Study In Scarlet, by Arthur Conan Doyle
";
eqnice!(expected, cmd.stdout());
});
// Test specifically with a pattern that matches near the NUL byte which should
// trigger binary detection with memory maps.
rgtest!(mmap_match_near_nul, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
// Pattern that matches around line 1898 where the NUL byte is.
// Note: Using direct file path instead of glob.
cmd.args(&["--mmap", "-n", "abcdef", "hay"]);
let expected = "\
binary file matches (found \"\\0\" byte around offset 77041)
";
eqnice!(expected, cmd.stdout());
});
// Test with --count option to ensure full file scanning works with mmap.
rgtest!(mmap_match_count, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
cmd.args(&["--mmap", "-c", "Project Gutenberg EBook|Heaven", "hay"]);
// With mmap, since we're counting all matches and might not
// encounter the NUL byte during initial detection, the count
// should still be reported.
eqnice!("2\n", cmd.stdout());
});
// Test binary detection with mmap when pattern would match before and after NUL
// byte.
rgtest!(mmap_match_multiple, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
// Use explicit file path.
cmd.args(&["--mmap", "-n", "Project Gutenberg EBook|Heaven", "hay"]);
// With explicit file and memory maps, matches before and after NUL byte
// are shown.
let expected = "\
1:The Project Gutenberg EBook of A Study In Scarlet, by Arthur Conan Doyle
1871:\"No. Heaven knows what the objects of his studies are. But here we
";
eqnice!(expected, cmd.stdout());
});
// Test that --binary flag can have odd results when searching with a memory
// map.
rgtest!(mmap_binary_flag, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
// Use glob pattern.
cmd.args(&["--mmap", "-n", "--binary", "Heaven", "-g", "hay"]);
let expected = "\
hay:1871:\"No. Heaven knows what the objects of his studies are. But here we
";
eqnice!(expected, cmd.stdout());
});
// Test that using -a/--text flag works as expected with mmap.
rgtest!(mmap_text_flag, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
cmd.args(&["--mmap", "-n", "--text", "Heaven", "-g", "hay"]);
// With --text flag, binary detection should be disabled.
let expected = "\
hay:1871:\"No. Heaven knows what the objects of his studies are. But here we
";
eqnice!(expected, cmd.stdout());
});
// Test pattern that matches before and after the NUL byte with memory maps.
rgtest!(mmap_after_nul_match, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes("hay", HAY);
// Use explicit file path.
cmd.args(&["--mmap", "-n", "medical student", "hay"]);
// With explicit file and memory maps, all matches are shown
let expected = "\
176:\"A medical student, I suppose?\" said I.
409:\"A medical student, I suppose?\" said I.
642:\"A medical student, I suppose?\" said I.
875:\"A medical student, I suppose?\" said I.
1108:\"A medical student, I suppose?\" said I.
1341:\"A medical student, I suppose?\" said I.
1574:\"A medical student, I suppose?\" said I.
1807:\"A medical student, I suppose?\" said I.
1867:\"And yet you say he is not a medical student?\"
";
eqnice!(expected, cmd.stdout());
});
// This tests that ripgrep prints a warning message if it finds and prints a
// match in a binary file before detecting that it is a binary file. The point
// here is to notify that user that the search of the file is only partially

6
tests/feature.rs
View File

@@ -972,10 +972,10 @@ rgtest!(f1404_nothing_searched_warning, |dir: Dir, mut cmd: TestCommand| {
cmd.assert_err();
// Test that we actually get an error message that we expect.
let output = cmd.cmd().output().unwrap();
let output = cmd.raw_output();
let stderr = String::from_utf8_lossy(&output.stderr);
let expected = "\
No files were searched, which means ripgrep probably applied \
rg: No files were searched, which means ripgrep probably applied \
a filter you didn't expect.\n\
Running with --debug will show why files are being skipped.\n\
";
@@ -995,7 +995,7 @@ rgtest!(f1404_nothing_searched_ignored, |dir: Dir, mut cmd: TestCommand| {
// But since --no-messages is given, there should not be any error message
// printed.
let output = cmd.cmd().output().unwrap();
let output = cmd.raw_output();
let stderr = String::from_utf8_lossy(&output.stderr);
let expected = "";
eqnice!(expected, stderr);

80
tests/json.rs
View File

@@ -21,45 +21,47 @@ impl Message {
fn unwrap_begin(&self) -> Begin {
match *self {
Message::Begin(ref x) => x.clone(),
ref x => panic!("expected Message::Begin but got {:?}", x),
ref x => panic!("expected Message::Begin but got {x:?}"),
}
}
fn unwrap_end(&self) -> End {
match *self {
Message::End(ref x) => x.clone(),
ref x => panic!("expected Message::End but got {:?}", x),
ref x => panic!("expected Message::End but got {x:?}"),
}
}
fn unwrap_match(&self) -> Match {
match *self {
Message::Match(ref x) => x.clone(),
ref x => panic!("expected Message::Match but got {:?}", x),
ref x => panic!("expected Message::Match but got {x:?}"),
}
}
fn unwrap_context(&self) -> Context {
match *self {
Message::Context(ref x) => x.clone(),
ref x => panic!("expected Message::Context but got {:?}", x),
ref x => panic!("expected Message::Context but got {x:?}"),
}
}
fn unwrap_summary(&self) -> Summary {
match *self {
Message::Summary(ref x) => x.clone(),
ref x => panic!("expected Message::Summary but got {:?}", x),
ref x => panic!("expected Message::Summary but got {x:?}"),
}
}
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct Begin {
path: Option<Data>,
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct End {
path: Option<Data>,
binary_offset: Option<u64>,
@@ -67,12 +69,14 @@ struct End {
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct Summary {
elapsed_total: Duration,
stats: Stats,
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct Match {
path: Option<Data>,
lines: Data,
@@ -82,6 +86,7 @@ struct Match {
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct Context {
path: Option<Data>,
lines: Data,
@@ -91,9 +96,11 @@ struct Context {
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct SubMatch {
#[serde(rename = "match")]
m: Data,
replacement: Option<Data>,
start: usize,
end: usize,
}
@@ -117,6 +124,7 @@ impl Data {
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct Stats {
elapsed: Duration,
searches: u64,
@@ -128,6 +136,7 @@ struct Stats {
}
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
#[serde(deny_unknown_fields)]
struct Duration {
#[serde(flatten)]
duration: time::Duration,
@@ -178,6 +187,7 @@ rgtest!(basic, |dir: Dir, mut cmd: TestCommand| {
absolute_offset: 129,
submatches: vec![SubMatch {
m: Data::text("Sherlock Holmes"),
replacement: None,
start: 48,
end: 63,
},],
@@ -189,6 +199,57 @@ rgtest!(basic, |dir: Dir, mut cmd: TestCommand| {
assert_eq!(msgs[4].unwrap_summary().stats.bytes_printed, 494);
});
rgtest!(replacement, |dir: Dir, mut cmd: TestCommand| {
dir.create("sherlock", SHERLOCK);
cmd.arg("--json")
.arg("-B1")
.arg("Sherlock Holmes")
.args(["-r", "John Watson"])
.arg("sherlock");
let msgs = json_decode(&cmd.stdout());
assert_eq!(
msgs[0].unwrap_begin(),
Begin { path: Some(Data::text("sherlock")) }
);
assert_eq!(
msgs[1].unwrap_context(),
Context {
path: Some(Data::text("sherlock")),
lines: Data::text(
"Holmeses, success in the province of \
detective work must always\n",
),
line_number: Some(2),
absolute_offset: 65,
submatches: vec![],
}
);
assert_eq!(
msgs[2].unwrap_match(),
Match {
path: Some(Data::text("sherlock")),
lines: Data::text(
"be, to a very large extent, the result of luck. \
Sherlock Holmes\n",
),
line_number: Some(3),
absolute_offset: 129,
submatches: vec![SubMatch {
m: Data::text("Sherlock Holmes"),
replacement: Some(Data::text("John Watson")),
start: 48,
end: 63,
},],
}
);
assert_eq!(msgs[3].unwrap_end().path, Some(Data::text("sherlock")));
assert_eq!(msgs[3].unwrap_end().binary_offset, None);
assert_eq!(msgs[4].unwrap_summary().stats.searches_with_match, 1);
assert_eq!(msgs[4].unwrap_summary().stats.bytes_printed, 531);
});
rgtest!(quiet_stats, |dir: Dir, mut cmd: TestCommand| {
dir.create("sherlock", SHERLOCK);
cmd.arg("--json")
@@ -244,6 +305,7 @@ rgtest!(notutf8, |dir: Dir, mut cmd: TestCommand| {
absolute_offset: 0,
submatches: vec![SubMatch {
m: Data::bytes("/w=="),
replacement: None,
start: 4,
end: 5,
},],
@@ -285,6 +347,7 @@ rgtest!(notutf8_file, |dir: Dir, mut cmd: TestCommand| {
absolute_offset: 0,
submatches: vec![SubMatch {
m: Data::bytes("/w=="),
replacement: None,
start: 4,
end: 5,
},],
@@ -305,7 +368,12 @@ rgtest!(crlf, |dir: Dir, mut cmd: TestCommand| {
assert_eq!(
msgs[1].unwrap_match().submatches[0].clone(),
SubMatch { m: Data::text("Sherlock"), start: 56, end: 64 },
SubMatch {
m: Data::text("Sherlock"),
replacement: None,
start: 56,
end: 64
},
);
});

20
tests/misc.rs
View File

@@ -411,7 +411,7 @@ rgtest!(include_zero, |dir: Dir, mut cmd: TestCommand| {
cmd.args(&["--count", "--include-zero", "nada"]);
cmd.assert_err();
let output = cmd.cmd().output().unwrap();
let output = cmd.raw_output();
let stdout = String::from_utf8_lossy(&output.stdout);
let expected = "sherlock:0\n";
@@ -423,7 +423,7 @@ rgtest!(include_zero_override, |dir: Dir, mut cmd: TestCommand| {
cmd.args(&["--count", "--include-zero", "--no-include-zero", "nada"]);
cmd.assert_err();
let output = cmd.cmd().output().unwrap();
let output = cmd.raw_output();
let stdout = String::from_utf8_lossy(&output.stdout);
assert!(stdout.is_empty());
});
@@ -1092,16 +1092,22 @@ rgtest!(type_list, |_: Dir, mut cmd: TestCommand| {
// This order is important when sorting them by system time-stamps.
fn sort_setup(dir: Dir) {
use std::{thread::sleep, time::Duration};
// As reported in https://github.com/BurntSushi/ripgrep/issues/3071
// this test fails if sufficient delay is not given on Windows/Aarch64.
let delay = if cfg!(all(windows, target_arch = "aarch64")) {
Duration::from_millis(1000)
} else {
Duration::from_millis(100)
};
let sub_dir = dir.path().join("dir");
dir.create("a", "test");
sleep(Duration::from_millis(100));
sleep(delay);
dir.create_dir(&sub_dir);
sleep(Duration::from_millis(100));
sleep(delay);
dir.create(sub_dir.join("c"), "test");
sleep(Duration::from_millis(100));
sleep(delay);
dir.create("b", "test");
sleep(Duration::from_millis(100));
sleep(delay);
dir.create(sub_dir.join("d"), "test");
}

306
tests/regression.rs
View File

@@ -399,12 +399,12 @@ rgtest!(r428_unrecognized_style, |dir: Dir, mut cmd: TestCommand| {
cmd.arg("--colors=match:style:").arg("Sherlock");
cmd.assert_err();
let output = cmd.cmd().output().unwrap();
let output = cmd.raw_output();
let stderr = String::from_utf8_lossy(&output.stderr);
let expected = "\
error parsing flag --colors: \
rg: error parsing flag --colors: \
unrecognized style attribute ''. Choose from: nobold, bold, nointense, \
intense, nounderline, underline.
intense, nounderline, underline, noitalic, italic.
";
eqnice!(expected, stderr);
});
@@ -569,6 +569,197 @@ rgtest!(r807, |dir: Dir, mut cmd: TestCommand| {
eqnice!(".a/c/file:test\n", cmd.arg("--hidden").arg("test").stdout());
});
// See: https://github.com/BurntSushi/ripgrep/pull/2711
//
// Note that this isn't a regression test. In particular, this didn't fail
// with ripgrep 14.1.1. I couldn't figure out how to turn what the OP gave me
// into a failing test.
rgtest!(r2711, |dir: Dir, _cmd: TestCommand| {
dir.create_dir("a/b");
dir.create("a/.ignore", ".foo");
dir.create("a/b/.foo", "");
{
let mut cmd = dir.command();
eqnice!("a/.ignore\n", cmd.arg("--hidden").arg("--files").stdout());
}
{
let mut cmd = dir.command();
eqnice!(
"./a/.ignore\n",
cmd.arg("--hidden").arg("--files").arg("./").stdout()
);
}
{
let mut cmd = dir.command();
eqnice!(
"a/.ignore\n",
cmd.arg("--hidden").arg("--files").arg("a").stdout()
);
}
{
let mut cmd = dir.command();
cmd.arg("--hidden").arg("--files").arg("a/b").assert_err();
}
{
let mut cmd = dir.command();
eqnice!(
"./a/.ignore\n",
cmd.arg("--hidden").arg("--files").arg("./a").stdout()
);
}
{
let mut cmd = dir.command();
cmd.current_dir(dir.path().join("a"));
eqnice!(".ignore\n", cmd.arg("--hidden").arg("--files").stdout());
}
{
let mut cmd = dir.command();
cmd.current_dir(dir.path().join("a").join("b"));
cmd.arg("--hidden").arg("--files").assert_err();
}
{
let mut cmd = dir.command();
cmd.current_dir(dir.path().join("./a"));
eqnice!(".ignore\n", cmd.arg("--hidden").arg("--files").stdout());
}
});
// See: https://github.com/BurntSushi/ripgrep/issues/829
rgtest!(r829_original, |dir: Dir, _cmd: TestCommand| {
dir.create_dir("a/b");
dir.create(".ignore", "/a/b");
dir.create("a/b/test.txt", "Sample text");
{
let mut cmd = dir.command();
cmd.args(&["Sample"]).assert_err();
}
{
let mut cmd = dir.command();
cmd.args(&["Sample", "a"]).assert_err();
}
{
let mut cmd = dir.command();
cmd.current_dir(dir.path().join("a"));
cmd.args(&["Sample"]).assert_err();
}
});
// See: https://github.com/BurntSushi/ripgrep/issues/2731
rgtest!(r829_2731, |dir: Dir, _cmd: TestCommand| {
dir.create_dir("some_dir/build");
dir.create("some_dir/build/foo", "string");
dir.create(".ignore", "build/\n!/some_dir/build/");
{
let mut cmd = dir.command();
eqnice!("some_dir/build/foo\n", cmd.arg("-l").arg("string").stdout());
}
{
let mut cmd = dir.command();
eqnice!(
"some_dir/build/foo\n",
cmd.arg("-l").arg("string").arg("some_dir").stdout()
);
}
{
let mut cmd = dir.command();
eqnice!(
"./some_dir/build/foo\n",
cmd.arg("-l").arg("string").arg("./some_dir").stdout()
);
}
{
let mut cmd = dir.command();
eqnice!(
"some_dir/build/foo\n",
cmd.arg("-l").arg("string").arg("some_dir/build").stdout()
);
}
{
let mut cmd = dir.command();
eqnice!(
"./some_dir/build/foo\n",
cmd.arg("-l").arg("string").arg("./some_dir/build").stdout()
);
}
});
// See: https://github.com/BurntSushi/ripgrep/issues/2747
rgtest!(r829_2747, |dir: Dir, _cmd: TestCommand| {
dir.create_dir("a/c/b");
dir.create_dir("a/src/f/b");
dir.create("a/c/b/foo", "");
dir.create("a/src/f/b/foo", "");
dir.create(".ignore", "/a/*/b");
{
let mut cmd = dir.command();
eqnice!("a/src/f/b/foo\n", cmd.arg("--files").stdout());
}
{
let mut cmd = dir.command();
eqnice!("a/src/f/b/foo\n", cmd.arg("--files").arg("a/src").stdout());
}
{
let mut cmd = dir.command();
cmd.current_dir(dir.path().join("a/src"));
eqnice!("f/b/foo\n", cmd.arg("--files").stdout());
}
});
// See: https://github.com/BurntSushi/ripgrep/issues/2778
rgtest!(r829_2778, |dir: Dir, _cmd: TestCommand| {
dir.create_dir("parent/subdir");
dir.create(".ignore", "/parent/*.txt");
dir.create("parent/ignore-me.txt", "");
dir.create("parent/subdir/dont-ignore-me.txt", "");
{
let mut cmd = dir.command();
eqnice!(
"parent/subdir/dont-ignore-me.txt\n",
cmd.arg("--files").stdout()
);
}
{
let mut cmd = dir.command();
cmd.current_dir(dir.path().join("parent"));
eqnice!("subdir/dont-ignore-me.txt\n", cmd.arg("--files").stdout());
}
});
// See: https://github.com/BurntSushi/ripgrep/issues/2836
rgtest!(r829_2836, |dir: Dir, _cmd: TestCommand| {
dir.create_dir("testdir/sub/sub2");
dir.create(".ignore", "/testdir/sub/sub2/\n");
dir.create("testdir/sub/sub2/foo", "");
{
let mut cmd = dir.command();
cmd.arg("--files").assert_err();
}
{
let mut cmd = dir.command();
cmd.current_dir(dir.path().join("testdir"));
cmd.arg("--files").assert_err();
}
});
// See: https://github.com/BurntSushi/ripgrep/pull/2933
rgtest!(r829_2933, |dir: Dir, mut cmd: TestCommand| {
dir.create_dir("testdir/sub/sub2");
dir.create(".ignore", "/testdir/sub/sub2/");
dir.create("testdir/sub/sub2/testfile", "needle");
let args = &["--files-with-matches", "needle"];
cmd.current_dir(dir.path().join("testdir"));
cmd.args(args).assert_err();
});
// See: https://github.com/BurntSushi/ripgrep/issues/900
rgtest!(r900, |dir: Dir, mut cmd: TestCommand| {
dir.create("sherlock", SHERLOCK);
@@ -764,6 +955,43 @@ rgtest!(r1319, |dir: Dir, mut cmd: TestCommand| {
);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1332
rgtest!(r1334_invert_empty_patterns, |dir: Dir, _cmd: TestCommand| {
dir.create("zero-patterns", "");
dir.create("one-pattern", "\n");
dir.create("haystack", "one\ntwo\nthree\n");
// zero patterns matches nothing
{
let mut cmd = dir.command();
cmd.arg("-f").arg("zero-patterns").arg("haystack").assert_err();
}
// one pattern that matches empty string matches everything
{
let mut cmd = dir.command();
eqnice!(
"one\ntwo\nthree\n",
cmd.arg("-f").arg("one-pattern").arg("haystack").stdout()
);
}
// inverting zero patterns matches everything
// (This is the regression. ripgrep used to match nothing because of an
// incorrect optimization.)
{
let mut cmd = dir.command();
eqnice!(
"one\ntwo\nthree\n",
cmd.arg("-vf").arg("zero-patterns").arg("haystack").stdout()
);
}
// inverting one pattern that matches empty string matches nothing
{
let mut cmd = dir.command();
cmd.arg("-vf").arg("one-pattern").arg("haystack").assert_err();
}
});
// See: https://github.com/BurntSushi/ripgrep/issues/1334
rgtest!(r1334_crazy_literals, |dir: Dir, mut cmd: TestCommand| {
dir.create("patterns", &"1.208.0.0/12\n".repeat(40));
@@ -965,6 +1193,15 @@ rgtest!(f1757, |dir: Dir, _: TestCommand| {
eqnice!("rust/source.rs\n", dir.command().args(args).stdout());
let args = &["--files-with-matches", "needle", "./rust"];
eqnice!("./rust/source.rs\n", dir.command().args(args).stdout());
dir.create_dir("rust1/target/onemore");
dir.create(".ignore", "rust1/target/onemore");
dir.create("rust1/source.rs", "needle");
dir.create("rust1/target/onemore/rustdoc-output.html", "needle");
let args = &["--files-with-matches", "needle", "rust1"];
eqnice!("rust1/source.rs\n", dir.command().args(args).stdout());
let args = &["--files-with-matches", "needle", "./rust1"];
eqnice!("./rust1/source.rs\n", dir.command().args(args).stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/1765
@@ -1217,3 +1454,66 @@ rgtest!(r2658_null_data_line_regexp, |dir: Dir, mut cmd: TestCommand| {
let got = cmd.args(&["--null-data", "--line-regexp", r"bar"]).stdout();
eqnice!("haystack:bar\0", got);
});
// See: https://github.com/BurntSushi/ripgrep/pull/2944
rgtest!(r2944_incorrect_bytes_searched, |dir: Dir, mut cmd: TestCommand| {
dir.create("haystack", "foo1\nfoo2\nfoo3\nfoo4\nfoo5\n");
let got = cmd.args(&["--stats", "-m2", "foo", "."]).stdout();
assert!(got.contains("10 bytes searched\n"));
});
// See: https://github.com/BurntSushi/ripgrep/issues/2990
rgtest!(r2990_trip_over_trailing_dot, |dir: Dir, _cmd: TestCommand| {
dir.create_dir("asdf");
dir.create_dir("asdf.");
dir.create("asdf/foo", "");
dir.create("asdf./foo", "");
let got = dir.command().args(&["--files", "-g", "!asdf/"]).stdout();
eqnice!("asdf./foo\n", got);
// This used to ignore the glob given and included `asdf./foo` in output.
let got = dir.command().args(&["--files", "-g", "!asdf./"]).stdout();
eqnice!("asdf/foo\n", got);
});
// See: https://github.com/BurntSushi/ripgrep/issues/3108
rgtest!(r3108_files_without_match_quiet_exit, |dir: Dir, _: TestCommand| {
dir.create("yes-match", "abc");
dir.create("non-match", "xyz");
dir.command().args(&["-q", "abc", "non-match"]).assert_exit_code(1);
dir.command().args(&["-q", "abc", "yes-match"]).assert_exit_code(0);
dir.command()
.args(&["--files-with-matches", "-q", "abc", "non-match"])
.assert_exit_code(1);
dir.command()
.args(&["--files-with-matches", "-q", "abc", "yes-match"])
.assert_exit_code(0);
dir.command()
.args(&["--files-without-match", "abc", "non-match"])
.assert_exit_code(0);
dir.command()
.args(&["--files-without-match", "abc", "yes-match"])
.assert_exit_code(1);
let got = dir
.command()
.args(&["--files-without-match", "abc", "non-match"])
.stdout();
eqnice!("non-match\n", got);
dir.command()
.args(&["--files-without-match", "-q", "abc", "non-match"])
.assert_exit_code(0);
dir.command()
.args(&["--files-without-match", "-q", "abc", "yes-match"])
.assert_exit_code(1);
let got = dir
.command()
.args(&["--files-without-match", "-q", "abc", "non-match"])
.stdout();
eqnice!("", got);
});

56
tests/util.rs
View File

@@ -9,6 +9,8 @@ use std::sync::atomic::{AtomicUsize, Ordering};
use std::thread;
use std::time::Duration;
use bstr::ByteSlice;
static TEST_DIR: &'static str = "ripgrep-tests";
static NEXT_ID: AtomicUsize = AtomicUsize::new(0);
@@ -66,14 +68,14 @@ impl Dir {
/// does not need to be distinct for each invocation, but should correspond
/// to a logical grouping of tests.
pub fn new(name: &str) -> Dir {
let id = NEXT_ID.fetch_add(1, Ordering::SeqCst);
let id = NEXT_ID.fetch_add(1, Ordering::Relaxed);
let root = env::current_exe()
.unwrap()
.parent()
.expect("executable's directory")
.to_path_buf();
let dir =
env::temp_dir().join(TEST_DIR).join(name).join(&format!("{}", id));
env::temp_dir().join(TEST_DIR).join(name).join(&format!("{id}"));
if dir.exists() {
nice_err(&dir, fs::remove_dir_all(&dir));
}
@@ -282,16 +284,7 @@ impl TestCommand {
/// Runs and captures the stdout of the given command.
pub fn stdout(&mut self) -> String {
let o = self.output();
let stdout = String::from_utf8_lossy(&o.stdout);
match stdout.parse() {
Ok(t) => t,
Err(err) => {
panic!(
"could not convert from string: {:?}\n\n{}",
err, stdout
);
}
}
String::from_utf8_lossy(&o.stdout).into_owned()
}
/// Pipe `input` to a command, and collect the output.
@@ -311,27 +304,26 @@ impl TestCommand {
let output = self.expect_success(child.wait_with_output().unwrap());
worker.join().unwrap().unwrap();
let stdout = String::from_utf8_lossy(&output.stdout);
match stdout.parse() {
Ok(t) => t,
Err(err) => {
panic!(
"could not convert from string: {:?}\n\n{}",
err, stdout
);
}
}
String::from_utf8_lossy(&output.stdout).into_owned()
}
/// Gets the output of a command. If the command failed, then this panics.
pub fn output(&mut self) -> process::Output {
let output = self.cmd.output().unwrap();
let output = self.raw_output();
self.expect_success(output)
}
/// Gets the raw output of a command after filtering nonsense like jemalloc
/// error messages from stderr.
pub fn raw_output(&mut self) -> process::Output {
let mut output = self.cmd.output().unwrap();
output.stderr = strip_jemalloc_nonsense(&output.stderr);
output
}
/// Runs the command and asserts that it resulted in an error exit code.
pub fn assert_err(&mut self) {
let o = self.cmd.output().unwrap();
let o = self.raw_output();
if o.status.success() {
panic!(
"\n\n===== {:?} =====\n\
@@ -479,7 +471,7 @@ fn dir_list<P: AsRef<Path>>(dir: P) -> Vec<String> {
/// So... we just manually handle these cases. So fucking fun.
fn cross_runner() -> Option<String> {
let runner = std::env::var("CROSS_RUNNER").ok()?;
if runner.is_empty() {
if runner.is_empty() || runner == "empty" {
return None;
}
if cfg!(target_arch = "powerpc64") {
@@ -500,3 +492,17 @@ fn cross_runner() -> Option<String> {
pub fn is_cross() -> bool {
std::env::var("CROSS_RUNNER").ok().map_or(false, |v| !v.is_empty())
}
/// Strips absolutely fucked `<jemalloc>:` lines from the output.
///
/// In theory this only happens under qemu, which is where our tests run under
/// `cross`. But is messes with our tests, because... they don't expect the
/// allocator to fucking write to stderr. I mean, what the fuck? Who prints a
/// warning message with absolutely no instruction for what to do with it or
/// how to disable it. Absolutely fucking bonkers.
fn strip_jemalloc_nonsense(data: &[u8]) -> Vec<u8> {
let lines = data
.lines_with_terminator()
.filter(|line| !line.starts_with_str("<jemalloc>:"));
bstr::concat(lines)
}