twin/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-07-26 09:42:00 -07:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: twin:ag/disable-bom-sniff
Branches Tags
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
..
compare: twin:ag/bstr-migration
Branches Tags
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

1 Commits
ag/disable ... ag/bstr-mi

Author SHA1 Message Date
Andrew Gallant
4b88e08f41 search: migrate to bstr 
This is an initial attempt at migrating grep-searcher to use the new
bstr crate (not yet published).

This is mostly an improvement, although a significant problem is that
the grep-matcher crate controls the `Index` impls for the `Match` type,
which we use quite heavily. Thus, in order to impl `Index` for `BStr`,
we need add bstr as a public dependency to grep-matcher. This is really
bad news because grep-matcher is supposed to be a light-weight core
crate that defines a matcher interface, which is itself intended to be a
public dependency. Thus, a semver bump on bstr will have very
undesirable ripple effects thoughout ripgrep's library crates.

This would be something we could stomach if bstr was solid at 1.0 and
committed to avoiding breaking changes. But it's not there yet.
 2019-01-20 12:32:09 -05:00
61 changed files with 962 additions and 1720 deletions
Expand all files Collapse all files

1
.travis.yml
View File

@@ -1,5 +1,4 @@
language: rust
dist: xenial
env:
global:
- PROJECT_NAME: ripgrep

62
CHANGELOG.md
View File

@@ -1,65 +1,3 @@
0.11.0 (TBD)
============
TODO.
**BREAKING CHANGES**:
* ripgrep has tweaked its exit status codes to be more like GNU grep's. Namely,
if a non-fatal error occurs during a search, then ripgrep will now always
emit a `2` exit status code, regardless of whether a match is found or not.
Previously, ripgrep would only emit a `2` exit status code for a catastrophic
error (e.g., regex syntax error). One exception to this is if ripgrep is run
with `-q/--quiet`. In that case, if an error occurs and a match is found,
then ripgrep will exit with a `0` exit status code.
* The `avx-accel` feature of ripgrep has been removed since it is no longer
necessary. All uses of AVX in ripgrep are now enabled automatically via
runtime CPU feature detection. The `simd-accel` feature does remain
available, however, it does increase compilation times substantially at the
moment.
Feature enhancements:
* [FEATURE #1099](https://github.com/BurntSushi/ripgrep/pull/1099):
Add support for Brotli and Zstd to the `-z/--search-zip` flag.
* [FEATURE #1138](https://github.com/BurntSushi/ripgrep/pull/1138):
Add `--no-ignore-dot` flag for ignoring `.ignore` files.
* [FEATURE #1159](https://github.com/BurntSushi/ripgrep/pull/1159):
ripgrep's exit status logic should now match GNU grep. See updated man page.
* [FEATURE #1170](https://github.com/BurntSushi/ripgrep/pull/1170):
Add `--ignore-file-case-insensitive` for case insensitive .ignore globs.
Bug fixes:
* [BUG #373](https://github.com/BurntSushi/ripgrep/issues/373),
[BUG #1098](https://github.com/BurntSushi/ripgrep/issues/1098):
`**` is now accepted as valid syntax anywhere in a glob.
* [BUG #916](https://github.com/BurntSushi/ripgrep/issues/916):
ripgrep no longer hangs when searching `/proc` with a zombie process present.
* [BUG #1091](https://github.com/BurntSushi/ripgrep/issues/1091):
Add note about inverted flags to the man page.
* [BUG #1095](https://github.com/BurntSushi/ripgrep/issues/1095):
Fix corner cases involving the `--crlf` flag.
* [BUG #1103](https://github.com/BurntSushi/ripgrep/issues/1103):
Clarify what `--encoding auto` does.
* [BUG #1106](https://github.com/BurntSushi/ripgrep/issues/1106):
`--files-with-matches` and `--files-without-match` work with one file.
* [BUG #1093](https://github.com/BurntSushi/ripgrep/pull/1093):
Fix handling of literal slashes in gitignore patterns.
* [BUG #1121](https://github.com/BurntSushi/ripgrep/issues/1121):
Fix bug that was triggering Windows antimalware when using the --files flag.
* [BUG #1125](https://github.com/BurntSushi/ripgrep/issues/1125),
[BUG #1159](https://github.com/BurntSushi/ripgrep/issues/1159):
ripgrep shouldn't panic for `rg -h | rg` and should emit correct exit status.
* [BUG #1154](https://github.com/BurntSushi/ripgrep/issues/1154):
Windows files with "hidden" attribute are now treated as hidden.
* [BUG #1173](https://github.com/BurntSushi/ripgrep/issues/1173):
Fix handling of `**` patterns in gitignore files.
* [BUG #1174](https://github.com/BurntSushi/ripgrep/issues/1174):
Fix handling of repeated `**` patterns in gitignore files.
* [BUG #1176](https://github.com/BurntSushi/ripgrep/issues/1176):
Fix bug where `-F`/`-x` weren't applied to patterns given via `-f`.
0.10.0 (2018-09-07)
===================
This is a new minor version release of ripgrep that contains some major new

506
Cargo.lock generated
View File

@@ -1,11 +1,9 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
[[package]]
name = "aho-corasick"
version = "0.7.3"
version = "0.6.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -13,9 +11,9 @@ name = "atty"
version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"termion 1.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -25,10 +23,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "base64"
version = "0.10.1"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"byteorder 1.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
"byteorder 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -38,42 +36,39 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "bstr"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
version = "0.0.1"
dependencies = [
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-automata 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "bytecount"
version = "0.5.1"
version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "byteorder"
version = "1.3.1"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "cc"
version = "1.0.34"
version = "1.0.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "cfg-if"
version = "0.1.7"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "clap"
version = "2.33.0"
version = "2.32.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"bitflags 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"strsim 0.8.0 (registry+https://github.com/rust-lang/crates.io-index)",
"textwrap 0.11.0 (registry+https://github.com/rust-lang/crates.io-index)",
"strsim 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)",
"textwrap 0.10.0 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-width 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
]
@@ -87,37 +82,38 @@ dependencies = [
[[package]]
name = "crossbeam-channel"
version = "0.3.8"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"crossbeam-utils 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)",
"smallvec 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)",
"crossbeam-utils 0.6.3 (registry+https://github.com/rust-lang/crates.io-index)",
"parking_lot 0.7.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)",
"smallvec 0.6.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "crossbeam-utils"
version = "0.6.5"
version = "0.6.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"cfg-if 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding_rs"
version = "0.8.17"
version = "0.8.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"packed_simd 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
"cfg-if 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"simd 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "encoding_rs_io"
version = "0.1.6"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"encoding_rs 0.8.17 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs 0.8.14 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -126,8 +122,17 @@ version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "fuchsia-cprng"
version = "0.1.1"
name = "fuchsia-zircon"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"bitflags 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"fuchsia-zircon-sys 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "fuchsia-zircon-sys"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
@@ -139,24 +144,27 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
name = "globset"
version = "0.4.2"
dependencies = [
"aho-corasick 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"aho-corasick 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)",
"fnv 1.0.6 (registry+https://github.com/rust-lang/crates.io-index)",
"glob 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep"
version = "0.2.3"
dependencies = [
"atty 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)",
"clap 2.32.0 (registry+https://github.com/rust-lang/crates.io-index)",
"grep-cli 0.1.1",
"grep-matcher 0.1.1",
"grep-pcre2 0.1.2",
"grep-printer 0.1.1",
"grep-regex 0.1.2",
"grep-searcher 0.1.3",
"grep-regex 0.1.1",
"grep-searcher 0.1.1",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"walkdir 2.2.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
@@ -166,22 +174,21 @@ name = "grep-cli"
version = "0.1.1"
dependencies = [
"atty 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"globset 0.4.2",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-matcher"
version = "0.1.1"
dependencies = [
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.0.1",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -196,59 +203,58 @@ dependencies = [
name = "grep-printer"
version = "0.1.1"
dependencies = [
"base64 0.10.1 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"base64 0.10.0 (registry+https://github.com/rust-lang/crates.io-index)",
"grep-matcher 0.1.1",
"grep-regex 0.1.2",
"grep-searcher 0.1.3",
"serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_derive 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_json 1.0.39 (registry+https://github.com/rust-lang/crates.io-index)",
"grep-regex 0.1.1",
"grep-searcher 0.1.1",
"serde 1.0.85 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_derive 1.0.85 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_json 1.0.36 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-regex"
version = "0.1.2"
version = "0.1.1"
dependencies = [
"grep-matcher 0.1.1",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.6.6 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"utf8-ranges 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-searcher"
version = "0.1.3"
version = "0.1.1"
dependencies = [
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"bytecount 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs 0.8.17 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs_io 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"bstr 0.0.1",
"bytecount 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs 0.8.14 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs_io 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"grep-matcher 0.1.1",
"grep-regex 0.1.2",
"grep-regex 0.1.1",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"memmap 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ignore"
version = "0.4.6"
dependencies = [
"crossbeam-channel 0.3.8 (registry+https://github.com/rust-lang/crates.io-index)",
"crossbeam-channel 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"globset 0.4.2",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"tempfile 3.0.7 (registry+https://github.com/rust-lang/crates.io-index)",
"tempfile 3.0.5 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"walkdir 2.2.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -258,50 +264,84 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "lazy_static"
version = "1.3.0"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "libc"
version = "0.2.51"
version = "0.2.47"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "lock_api"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"owning_ref 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"scopeguard 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "log"
version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"cfg-if 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "memchr"
version = "2.2.0"
version = "2.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "memmap"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "num_cpus"
version = "1.10.0"
version = "1.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "packed_simd"
version = "0.3.3"
name = "owning_ref"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"stable_deref_trait 1.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "parking_lot"
version = "0.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"lock_api 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"parking_lot_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "parking_lot_core"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"rand 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)",
"rustc_version 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)",
"smallvec 0.6.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -309,7 +349,7 @@ name = "pcre2"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"pcre2-sys 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -320,8 +360,8 @@ name = "pcre2-sys"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cc 1.0.34 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"cc 1.0.28 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"pkg-config 0.3.14 (registry+https://github.com/rust-lang/crates.io-index)",
]
@@ -332,7 +372,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "proc-macro2"
version = "0.4.27"
version = "0.4.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -340,28 +380,27 @@ dependencies = [
[[package]]
name = "quote"
version = "0.6.11"
version = "0.6.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)",
"proc-macro2 0.4.25 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand"
version = "0.6.5"
version = "0.6.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_chacha 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_hc 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_isaac 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_jitter 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_os 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_pcg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_os 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_pcg 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_xorshift 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -370,20 +409,12 @@ version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_core"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_core"
version = "0.4.0"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
@@ -391,7 +422,7 @@ name = "rand_hc"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -399,39 +430,29 @@ name = "rand_isaac"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_jitter"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_os"
version = "0.1.3"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cloudabi 0.0.3 (registry+https://github.com/rust-lang/crates.io-index)",
"fuchsia-cprng 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"fuchsia-zircon 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rdrand 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rand_pcg"
version = "0.1.2"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"rustc_version 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -439,7 +460,7 @@ name = "rand_xorshift"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -447,12 +468,12 @@ name = "rdrand"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
"rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "redox_syscall"
version = "0.1.52"
version = "0.1.50"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
@@ -460,32 +481,24 @@ name = "redox_termios"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_syscall 0.1.50 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex"
version = "1.1.5"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"aho-corasick 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.6.6 (registry+https://github.com/rust-lang/crates.io-index)",
"aho-corasick 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 2.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"utf8-ranges 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex-automata"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"byteorder 1.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex-syntax"
version = "0.6.6"
version = "0.6.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"ucd-util 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -496,27 +509,34 @@ name = "remove_dir_all"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ripgrep"
version = "0.10.0"
dependencies = [
"bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"clap 2.33.0 (registry+https://github.com/rust-lang/crates.io-index)",
"clap 2.32.0 (registry+https://github.com/rust-lang/crates.io-index)",
"grep 0.2.3",
"ignore 0.4.6",
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"num_cpus 1.10.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_derive 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_json 1.0.39 (registry+https://github.com/rust-lang/crates.io-index)",
"num_cpus 1.9.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.85 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_derive 1.0.85 (registry+https://github.com/rust-lang/crates.io-index)",
"serde_json 1.0.36 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "rustc_version"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"semver 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ryu"
version = "0.2.7"
@@ -527,65 +547,96 @@ name = "same-file"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "scopeguard"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "semver"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"semver-parser 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "semver-parser"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "serde"
version = "1.0.90"
version = "1.0.85"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "serde_derive"
version = "1.0.90"
version = "1.0.85"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 0.6.11 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 0.15.30 (registry+https://github.com/rust-lang/crates.io-index)",
"proc-macro2 0.4.25 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 0.6.10 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 0.15.26 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "serde_json"
version = "1.0.39"
version = "1.0.36"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"itoa 0.4.3 (registry+https://github.com/rust-lang/crates.io-index)",
"ryu 0.2.7 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.85 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "simd"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "smallvec"
version = "0.6.9"
version = "0.6.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"unreachable 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "stable_deref_trait"
version = "1.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "strsim"
version = "0.8.0"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "syn"
version = "0.15.30"
version = "0.15.26"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 0.6.11 (registry+https://github.com/rust-lang/crates.io-index)",
"proc-macro2 0.4.25 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 0.6.10 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "tempfile"
version = "3.0.7"
version = "3.0.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"rand 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)",
"cfg-if 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"rand 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_syscall 0.1.50 (registry+https://github.com/rust-lang/crates.io-index)",
"remove_dir_all 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -601,14 +652,14 @@ name = "termion"
version = "1.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_syscall 0.1.50 (registry+https://github.com/rust-lang/crates.io-index)",
"redox_termios 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "textwrap"
version = "0.11.0"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"unicode-width 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -619,7 +670,7 @@ name = "thread_local"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.2.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -637,24 +688,37 @@ name = "unicode-xid"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "unreachable"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "utf8-ranges"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "void"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "walkdir"
version = "2.2.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "winapi"
version = "0.3.7"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi-i686-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -668,10 +732,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "winapi-util"
version = "0.1.2"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -684,80 +748,88 @@ name = "wincolor"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-util 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[metadata]
"checksum aho-corasick 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)" = "e6f484ae0c99fec2e858eb6134949117399f222608d84cadb3f58c1f97c2364c"
"checksum aho-corasick 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)" = "1e9a933f4e58658d7b12defcf96dc5c720f20832deebe3e0a19efd3b6aaeeb9e"
"checksum atty 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)" = "9a7d5b8723950951411ee34d271d99dddcc2035a16ab25310ea2c8cfd4369652"
"checksum autocfg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "a6d640bee2da49f60a4068a7fae53acde8982514ab7bae8b8cea9e88cbcfd799"
"checksum base64 0.10.1 (registry+https://github.com/rust-lang/crates.io-index)" = "0b25d992356d2eb0ed82172f5248873db5560c4721f564b13cb5193bda5e668e"
"checksum base64 0.10.0 (registry+https://github.com/rust-lang/crates.io-index)" = "621fc7ecb8008f86d7fb9b95356cd692ce9514b80a86d85b397f32a22da7b9e2"
"checksum bitflags 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)" = "228047a76f468627ca71776ecdebd732a3423081fcf5125585bcd7c49886ce12"
"checksum bstr 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "6c8203ca06c502958719dae5f653a79e0cc6ba808ed02beffbf27d09610f2143"
"checksum bytecount 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)" = "be0fdd54b507df8f22012890aadd099979befdba27713c767993f8380112ca7c"
"checksum byteorder 1.3.1 (registry+https://github.com/rust-lang/crates.io-index)" = "a019b10a2a7cdeb292db131fc8113e57ea2a908f6e7894b0c3c671893b65dbeb"
"checksum cc 1.0.34 (registry+https://github.com/rust-lang/crates.io-index)" = "30f813bf45048a18eda9190fd3c6b78644146056740c43172a5a3699118588fd"
"checksum cfg-if 0.1.7 (registry+https://github.com/rust-lang/crates.io-index)" = "11d43355396e872eefb45ce6342e4374ed7bc2b3a502d1b28e36d6e23c05d1f4"
"checksum clap 2.33.0 (registry+https://github.com/rust-lang/crates.io-index)" = "5067f5bb2d80ef5d68b4c87db81601f0b75bca627bc2ef76b141d7b846a3c6d9"
"checksum bytecount 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)" = "c219c0335c21a8bd79587ce5aee9f64aff1d0bd7a2cca7a58a815f9780cd3b0d"
"checksum byteorder 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "60f0b0d4c0a382d2734228fd12b5a6b5dac185c60e938026fd31b265b94f9bd2"
"checksum cc 1.0.28 (registry+https://github.com/rust-lang/crates.io-index)" = "bb4a8b715cb4597106ea87c7c84b2f1d452c7492033765df7f32651e66fcf749"
"checksum cfg-if 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)" = "082bb9b28e00d3c9d39cc03e64ce4cea0f1bb9b3fde493f0cbc008472d22bdf4"
"checksum clap 2.32.0 (registry+https://github.com/rust-lang/crates.io-index)" = "b957d88f4b6a63b9d70d5f454ac8011819c6efa7727858f458ab71c756ce2d3e"
"checksum cloudabi 0.0.3 (registry+https://github.com/rust-lang/crates.io-index)" = "ddfc5b9aa5d4507acaf872de71051dfd0e309860e88966e1051e462a077aac4f"
"checksum crossbeam-channel 0.3.8 (registry+https://github.com/rust-lang/crates.io-index)" = "0f0ed1a4de2235cabda8558ff5840bffb97fcb64c97827f354a451307df5f72b"
"checksum crossbeam-utils 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)" = "f8306fcef4a7b563b76b7dd949ca48f52bc1141aa067d2ea09565f3e2652aa5c"
"checksum encoding_rs 0.8.17 (registry+https://github.com/rust-lang/crates.io-index)" = "4155785c79f2f6701f185eb2e6b4caf0555ec03477cb4c70db67b465311620ed"
"checksum encoding_rs_io 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)" = "9619ee7a2bf4e777e020b95c1439abaf008f8ea8041b78a0552c4f1bcf4df32c"
"checksum crossbeam-channel 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)" = "137bc235f622ffaa0428e3854e24acb53291fc0b3ff6fb2cb75a8be6fb02f06b"
"checksum crossbeam-utils 0.6.3 (registry+https://github.com/rust-lang/crates.io-index)" = "41ee4864f4797060e52044376f7d107429ce1fb43460021b126424b7180ee21a"
"checksum encoding_rs 0.8.14 (registry+https://github.com/rust-lang/crates.io-index)" = "a69d152eaa438a291636c1971b0a370212165ca8a75759eb66818c5ce9b538f7"
"checksum encoding_rs_io 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "098f6a0ab73a9ba256b71344dc82c6d7e252736ad9db7f4e35345f3a1f8713f5"
"checksum fnv 1.0.6 (registry+https://github.com/rust-lang/crates.io-index)" = "2fad85553e09a6f881f739c29f0b00b0f01357c743266d478b68951ce23285f3"
"checksum fuchsia-cprng 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "a06f77d526c1a601b7c4cdd98f54b5eaabffc14d5f2f0296febdc7f357c6d3ba"
"checksum fuchsia-zircon 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "2e9763c69ebaae630ba35f74888db465e49e259ba1bc0eda7d06f4a067615d82"
"checksum fuchsia-zircon-sys 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "3dcaa9ae7725d12cdb85b3ad99a434db70b468c09ded17e012d86b5c1010f7a7"
"checksum glob 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)" = "8be18de09a56b60ed0edf84bc9df007e30040691af7acd1c41874faac5895bfb"
"checksum itoa 0.4.3 (registry+https://github.com/rust-lang/crates.io-index)" = "1306f3464951f30e30d12373d31c79fbd52d236e5e896fd92f96ec7babbbe60b"
"checksum lazy_static 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "bc5729f27f159ddd61f4df6228e827e86643d4d3e7c32183cb30a1c08f604a14"
"checksum libc 0.2.51 (registry+https://github.com/rust-lang/crates.io-index)" = "bedcc7a809076656486ffe045abeeac163da1b558e963a31e29fbfbeba916917"
"checksum lazy_static 1.2.0 (registry+https://github.com/rust-lang/crates.io-index)" = "a374c89b9db55895453a74c1e38861d9deec0b01b405a82516e9d5de4820dea1"
"checksum libc 0.2.47 (registry+https://github.com/rust-lang/crates.io-index)" = "48450664a984b25d5b479554c29cc04e3150c97aa4c01da5604a2d4ed9151476"
"checksum lock_api 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)" = "62ebf1391f6acad60e5c8b43706dde4582df75c06698ab44511d15016bc2442c"
"checksum log 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)" = "c84ec4b527950aa83a329754b01dbe3f58361d1c5efacd1f6d68c494d08a17c6"
"checksum memchr 2.2.0 (registry+https://github.com/rust-lang/crates.io-index)" = "2efc7bc57c883d4a4d6e3246905283d8dae951bb3bd32f49d6ef297f546e1c39"
"checksum memchr 2.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "e1dd4eaac298c32ce07eb6ed9242eda7d82955b9170b7d6db59b2e02cc63fcb8"
"checksum memmap 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)" = "6585fd95e7bb50d6cc31e20d4cf9afb4e2ba16c5846fc76793f11218da9c475b"
"checksum num_cpus 1.10.0 (registry+https://github.com/rust-lang/crates.io-index)" = "1a23f0ed30a54abaa0c7e83b1d2d87ada7c3c23078d1d87815af3e3b6385fbba"
"checksum packed_simd 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "a85ea9fc0d4ac0deb6fe7911d38786b32fc11119afd9e9d38b84ff691ce64220"
"checksum num_cpus 1.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "5a69d464bdc213aaaff628444e99578ede64e9c854025aa43b9796530afa9238"
"checksum owning_ref 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "49a4b8ea2179e6a2e27411d3bca09ca6dd630821cf6894c6c7c8467a8ee7ef13"
"checksum parking_lot 0.7.1 (registry+https://github.com/rust-lang/crates.io-index)" = "ab41b4aed082705d1056416ae4468b6ea99d52599ecf3169b00088d43113e337"
"checksum parking_lot_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "94c8c7923936b28d546dfd14d4472eaf34c99b14e1c973a32b3e6d4eb04298c9"
"checksum pcre2 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "3ae0a2682105ec5ca0ee5910bbc7e926386d348a05166348f74007942983c319"
"checksum pcre2-sys 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "a9027f9474e4e13d3b965538aafcaebe48c803488ad76b3c97ef061a8324695f"
"checksum pkg-config 0.3.14 (registry+https://github.com/rust-lang/crates.io-index)" = "676e8eb2b1b4c9043511a9b7bea0915320d7e502b0a079fb03f9635a5252b18c"
"checksum proc-macro2 0.4.27 (registry+https://github.com/rust-lang/crates.io-index)" = "4d317f9caece796be1980837fd5cb3dfec5613ebdb04ad0956deea83ce168915"
"checksum quote 0.6.11 (registry+https://github.com/rust-lang/crates.io-index)" = "cdd8e04bd9c52e0342b406469d494fcb033be4bdbe5c606016defbb1681411e1"
"checksum rand 0.6.5 (registry+https://github.com/rust-lang/crates.io-index)" = "6d71dacdc3c88c1fde3885a3be3fbab9f35724e6ce99467f7d9c5026132184ca"
"checksum proc-macro2 0.4.25 (registry+https://github.com/rust-lang/crates.io-index)" = "d3797b7142c9aa74954e351fc089bbee7958cebbff6bf2815e7ffff0b19f547d"
"checksum quote 0.6.10 (registry+https://github.com/rust-lang/crates.io-index)" = "53fa22a1994bd0f9372d7a816207d8a2677ad0325b073f5c5332760f0fb62b5c"
"checksum rand 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)" = "3906503e80ac6cbcacb2c2973fa8e473f24d7e2747c8c92bb230c2441cad96b5"
"checksum rand_chacha 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "556d3a1ca6600bfcbab7c7c91ccb085ac7fbbcd70e008a98742e7847f4f7bcef"
"checksum rand_core 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)" = "7a6fdeb83b075e8266dcc8762c22776f6877a63111121f5f8c7411e5be7eed4b"
"checksum rand_core 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "d0e7a549d590831370895ab7ba4ea0c1b6b011d106b5ff2da6eee112615e6dc0"
"checksum rand_core 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "0905b6b7079ec73b314d4c748701f6931eb79fd97c668caa3f1899b22b32c6db"
"checksum rand_hc 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "7b40677c7be09ae76218dc623efbf7b18e34bced3f38883af07bb75630a21bc4"
"checksum rand_isaac 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "ded997c9d5f13925be2a6fd7e66bf1872597f759fd9dd93513dd7e92e5a5ee08"
"checksum rand_jitter 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "7b9ea758282efe12823e0d952ddb269d2e1897227e464919a554f2a03ef1b832"
"checksum rand_os 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "7b75f676a1e053fc562eafbb47838d67c84801e38fc1ba459e8f180deabd5071"
"checksum rand_pcg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "abf9b09b01790cfe0364f52bf32995ea3c39f4d2dd011eac241d2914146d0b44"
"checksum rand_os 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "f46fbd5550acf75b0c2730f5dd1873751daf9beb8f11b44027778fae50d7feca"
"checksum rand_pcg 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "086bd09a33c7044e56bb44d5bdde5a60e7f119a9e95b0775f545de759a32fe05"
"checksum rand_xorshift 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "cbf7e9e623549b0e21f6e97cf8ecf247c1a8fd2e8a992ae265314300b2455d5c"
"checksum rdrand 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "678054eb77286b51581ba43620cc911abf02758c91f93f479767aed0f90458b2"
"checksum redox_syscall 0.1.52 (registry+https://github.com/rust-lang/crates.io-index)" = "d32b3053e5ced86e4bc0411fec997389532bf56b000e66cb4884eeeb41413d69"
"checksum redox_syscall 0.1.50 (registry+https://github.com/rust-lang/crates.io-index)" = "52ee9a534dc1301776eff45b4fa92d2c39b1d8c3d3357e6eb593e0d795506fc2"
"checksum redox_termios 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "7e891cfe48e9100a70a3b6eb652fef28920c117d366339687bd5576160db0f76"
"checksum regex 1.1.5 (registry+https://github.com/rust-lang/crates.io-index)" = "559008764a17de49a3146b234641644ed37d118d1ef641a0bb573d146edc6ce0"
"checksum regex-automata 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)" = "a25a7daa2eea48550e9946133d6cc9621020d29cc7069089617234bf8b6a8693"
"checksum regex-syntax 0.6.6 (registry+https://github.com/rust-lang/crates.io-index)" = "dcfd8681eebe297b81d98498869d4aae052137651ad7b96822f09ceb690d0a96"
"checksum regex 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "37e7cbbd370869ce2e8dff25c7018702d10b21a20ef7135316f8daecd6c25b7f"
"checksum regex-syntax 0.6.4 (registry+https://github.com/rust-lang/crates.io-index)" = "4e47a2ed29da7a9e1960e1639e7a982e6edc6d49be308a3b02daf511504a16d1"
"checksum remove_dir_all 0.5.1 (registry+https://github.com/rust-lang/crates.io-index)" = "3488ba1b9a2084d38645c4c08276a1752dcbf2c7130d74f1569681ad5d2799c5"
"checksum rustc_version 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)" = "138e3e0acb6c9fb258b19b67cb8abd63c00679d2851805ea151465464fe9030a"
"checksum ryu 0.2.7 (registry+https://github.com/rust-lang/crates.io-index)" = "eb9e9b8cde282a9fe6a42dd4681319bfb63f121b8a8ee9439c6f4107e58a46f7"
"checksum same-file 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)" = "8f20c4be53a8a1ff4c1f1b2bd14570d2f634628709752f0702ecdd2b3f9a5267"
"checksum serde 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)" = "aa5f7c20820475babd2c077c3ab5f8c77a31c15e16ea38687b4c02d3e48680f4"
"checksum serde_derive 1.0.90 (registry+https://github.com/rust-lang/crates.io-index)" = "58fc82bec244f168b23d1963b45c8bf5726e9a15a9d146a067f9081aeed2de79"
"checksum serde_json 1.0.39 (registry+https://github.com/rust-lang/crates.io-index)" = "5a23aa71d4a4d43fdbfaac00eff68ba8a06a51759a89ac3304323e800c4dd40d"
"checksum smallvec 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)" = "c4488ae950c49d403731982257768f48fada354a5203fe81f9bb6f43ca9002be"
"checksum strsim 0.8.0 (registry+https://github.com/rust-lang/crates.io-index)" = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
"checksum syn 0.15.30 (registry+https://github.com/rust-lang/crates.io-index)" = "66c8865bf5a7cbb662d8b011950060b3c8743dca141b054bf7195b20d314d8e2"
"checksum tempfile 3.0.7 (registry+https://github.com/rust-lang/crates.io-index)" = "b86c784c88d98c801132806dadd3819ed29d8600836c4088e855cdf3e178ed8a"
"checksum scopeguard 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "94258f53601af11e6a49f722422f6e3425c52b06245a5cf9bc09908b174f5e27"
"checksum semver 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "1d7eb9ef2c18661902cc47e535f9bc51b78acd254da71d375c2f6720d9a40403"
"checksum semver-parser 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)" = "388a1df253eca08550bef6c72392cfe7c30914bf41df5269b68cbd6ff8f570a3"
"checksum serde 1.0.85 (registry+https://github.com/rust-lang/crates.io-index)" = "534b8b91a95e0f71bca3ed5824752d558da048d4248c91af873b63bd60519752"
"checksum serde_derive 1.0.85 (registry+https://github.com/rust-lang/crates.io-index)" = "a915306b0f1ac5607797697148c223bedeaa36bcc2e28a01441cd638cc6567b4"
"checksum serde_json 1.0.36 (registry+https://github.com/rust-lang/crates.io-index)" = "574378d957d6dcdf1bbb5d562a15cbd5e644159432f84634b94e485267abbcc7"
"checksum simd 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)" = "0048b17eb9577ac545c61d85c3559b41dfb4cbea41c9bd9ca6a4f73ff05fda84"
"checksum smallvec 0.6.7 (registry+https://github.com/rust-lang/crates.io-index)" = "b73ea3738b47563803ef814925e69be00799a8c07420be8b996f8e98fb2336db"
"checksum stable_deref_trait 1.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "dba1a27d3efae4351c8051072d619e3ade2820635c3958d826bfea39d59b54c8"
"checksum strsim 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)" = "bb4f380125926a99e52bc279241539c018323fab05ad6368b56f93d9369ff550"
"checksum syn 0.15.26 (registry+https://github.com/rust-lang/crates.io-index)" = "f92e629aa1d9c827b2bb8297046c1ccffc57c99b947a680d3ccff1f136a3bee9"
"checksum tempfile 3.0.5 (registry+https://github.com/rust-lang/crates.io-index)" = "7e91405c14320e5c79b3d148e1c86f40749a36e490642202a31689cb1a3452b2"
"checksum termcolor 1.0.4 (registry+https://github.com/rust-lang/crates.io-index)" = "4096add70612622289f2fdcdbd5086dc81c1e2675e6ae58d6c4f62a16c6d7f2f"
"checksum termion 1.5.1 (registry+https://github.com/rust-lang/crates.io-index)" = "689a3bdfaab439fd92bc87df5c4c78417d3cbe537487274e9b0b2dce76e92096"
"checksum textwrap 0.11.0 (registry+https://github.com/rust-lang/crates.io-index)" = "d326610f408c7a4eb6f51c37c330e496b08506c9457c9d34287ecc38809fb060"
"checksum textwrap 0.10.0 (registry+https://github.com/rust-lang/crates.io-index)" = "307686869c93e71f94da64286f9a9524c0f308a9e1c87a583de8e9c9039ad3f6"
"checksum thread_local 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)" = "c6b53e329000edc2b34dbe8545fd20e55a333362d0a321909685a19bd28c3f1b"
"checksum ucd-util 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "535c204ee4d8434478593480b8f86ab45ec9aae0e83c568ca81abf0fd0e88f86"
"checksum unicode-width 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)" = "882386231c45df4700b275c7ff55b6f3698780a650026380e72dabe76fa46526"
"checksum unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "fc72304796d0818e357ead4e000d19c9c174ab23dc11093ac919054d20a6a7fc"
"checksum unreachable 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "382810877fe448991dfc7f0dd6e3ae5d58088fd0ea5e35189655f84e6814fa56"
"checksum utf8-ranges 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "796f7e48bef87609f7ade7e06495a87d5cd06c7866e6a5cbfceffc558a243737"
"checksum void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "6a02e4885ed3bc0f2de90ea6dd45ebcbb66dacffe03547fadbb0eeae2770887d"
"checksum walkdir 2.2.7 (registry+https://github.com/rust-lang/crates.io-index)" = "9d9d7ed3431229a144296213105a390676cc49c9b6a72bd19f3176c98e129fa1"
"checksum winapi 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)" = "f10e386af2b13e47c89e7236a7a14a086791a2b88ebad6df9bf42040195cf770"
"checksum winapi 0.3.6 (registry+https://github.com/rust-lang/crates.io-index)" = "92c1eb33641e276cfa214a0522acad57be5c56b10cb348b3c5117db75f3ac4b0"
"checksum winapi-i686-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
"checksum winapi-util 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)" = "7168bab6e1daee33b4557efd0e95d5ca70a03706d39fa5f3fe7a236f584b03c9"
"checksum winapi-util 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "afc5508759c5bf4285e61feb862b6083c8480aec864fa17a81fdec6f69b461ab"
"checksum winapi-x86_64-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
"checksum wincolor 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)" = "561ed901ae465d6185fa7864d63fbd5720d0ef718366c9a4dc83cf6170d7e9ba"

1
Cargo.toml
View File

@@ -46,7 +46,6 @@ members = [
]
[dependencies]
bstr = "0.1.2"
grep = { version = "0.2.3", path = "grep" }
ignore = { version = "0.4.4", path = "ignore" }
lazy_static = "1.1.0"

15
FAQ.md
View File

@@ -118,7 +118,7 @@ from run to run of ripgrep.
The only way to make the order of results consistent is to ask ripgrep to
sort the output. Currently, this will disable all parallelism. (On smaller
repositories, you might not notice much of a performance difference!) You
can achieve this with the `--sort path` flag.
can achieve this with the `--sort-files` flag.
There is more discussion on this topic here:
https://github.com/BurntSushi/ripgrep/issues/152
@@ -136,10 +136,10 @@ How do I search compressed files?
</h3>
ripgrep's `-z/--search-zip` flag will cause it to search compressed files
automatically. Currently, this supports gzip, bzip2, xz, lzma, lz4, Brotli and
Zstd. Each of these requires requires the corresponding `gzip`, `bzip2`, `xz`,
`lz4`, `brotli` and `zstd` binaries to be installed on your system. (That is,
ripgrep does decompression by shelling out to another process.)
automatically. Currently, this supports gzip, bzip2, lzma, lz4 and xz only and
requires the corresponding `gzip`, `bzip2` and `xz` binaries to be installed on
your system. (That is, ripgrep does decompression by shelling out to another
process.)
ripgrep currently does not search archive formats, so `*.tar.gz` files, for
example, are skipped.
@@ -149,8 +149,9 @@ example, are skipped.
How do I search over multiple lines?
</h3>
The `-U/--multiline` flag enables ripgrep to report results that span over
multiple lines.
This isn't currently possible. ripgrep is fundamentally a line-oriented search
tool. With that said,
[multiline search is a planned opt-in feature](https://github.com/BurntSushi/ripgrep/issues/176).
<h3 name="fancy">

52
GUIDE.md
View File

@@ -235,11 +235,6 @@ Like `.gitignore`, a `.ignore` file can be placed in any directory. Its rules
will be processed with respect to the directory it resides in, just like
`.gitignore`.
To process `.gitignore` and `.ignore` files case insensitively, use the flag
`--ignore-file-case-insensitive`. This is especially useful on case insensitive
file systems like those on Windows and macOS. Note though that this can come
with a significant performance penalty, and is therefore disabled by default.
For a more in depth description of how glob patterns in a `.gitignore` file
are interpreted, please see `man gitignore`.
@@ -525,9 +520,9 @@ config file. Once the environment variable is set, open the file and just type
in the flags you want set automatically. There are only two rules for
describing the format of the config file:
1. Every line is a shell argument, after trimming whitespace.
2. Lines starting with `#` (optionally preceded by any amount of whitespace)
are ignored.
1. Every line is a shell argument, after trimming ASCII whitespace.
2. Lines starting with `#` (optionally preceded by any amount of
ASCII whitespace) are ignored.
In particular, there is no escaping. Each line is given to ripgrep as a single
command line argument verbatim.
@@ -603,14 +598,13 @@ topic, but we can try to summarize its relevancy to ripgrep:
* Files are generally just a bundle of bytes. There is no reliable way to know
their encoding.
* Either the encoding of the pattern must match the encoding of the files being
searched, or a form of transcoding must be performed that converts either the
searched, or a form of transcoding must be performed converts either the
pattern or the file to the same encoding as the other.
* ripgrep tends to work best on plain text files, and among plain text files,
the most popular encodings likely consist of ASCII, latin1 or UTF-8. As
a special exception, UTF-16 is prevalent in Windows environments
In light of the above, here is how ripgrep behaves when `--encoding auto` is
given, which is the default:
In light of the above, here is how ripgrep behaves:
* All input is assumed to be ASCII compatible (which means every byte that
corresponds to an ASCII codepoint actually is an ASCII codepoint). This
@@ -626,15 +620,12 @@ given, which is the default:
they correspond to a UTF-16 BOM, then ripgrep will transcode the contents of
the file from UTF-16 to UTF-8, and then execute the search on the transcoded
version of the file. (This incurs a performance penalty since transcoding
is slower than regex searching.) If the file contains invalid UTF-16, then
the Unicode replacement codepoint is substituted in place of invalid code
units.
is slower than regex searching.)
* To handle other cases, ripgrep provides a `-E/--encoding` flag, which permits
you to specify an encoding from the
[Encoding Standard](https://encoding.spec.whatwg.org/#concept-encoding-get).
ripgrep will assume *all* files searched are the encoding specified (unless
the file has a BOM) and will perform a transcoding step just like in the
UTF-16 case described above.
ripgrep will assume *all* files searched are the encoding specified and
will perform a transcoding step just like in the UTF-16 case described above.
By default, ripgrep will not require its input be valid UTF-8. That is, ripgrep
can and will search arbitrary bytes. The key here is that if you're searching
@@ -644,26 +635,9 @@ pattern won't find anything. With all that said, this mode of operation is
important, because it lets you find ASCII or UTF-8 *within* files that are
otherwise arbitrary bytes.
As a special case, the `-E/--encoding` flag supports the value `none`, which
will completely disable all encoding related logic, including BOM sniffing.
When `-E/--encoding` is set to `none`, ripgrep will search the raw bytes of
the underlying file with no transcoding step. For example, here's how you might
search the raw UTF-16 encoding of the string `Шерлок`:
```
$ rg '(?-u)\(\x045\x04@\x04;\x04>\x04:\x04' -E none -a some-utf16-file
```
Of course, that's just an example meant to show how one can drop down into
raw bytes. Namely, the simpler command works as you might expect automatically:
```
$ rg 'Шерлок' some-utf16-file
```
Finally, it is possible to disable ripgrep's Unicode support from within the
regular expression. For example, let's say you wanted `.` to match any byte
rather than any Unicode codepoint. (You might want this while searching a
pattern regular expression. For example, let's say you wanted `.` to match any
byte rather than any Unicode codepoint. (You might want this while searching a
binary file, since `.` by default will not match invalid UTF-8.) You could do
this by disabling Unicode via a regular expression flag:
@@ -701,10 +675,10 @@ used options that will likely impact how you use ripgrep on a regular basis.
* `--files`: Print the files that ripgrep *would* search, but don't actually
search them.
* `-a/--text`: Search binary files as if they were plain text.
* `-z/--search-zip`: Search compressed files (gzip, bzip2, lzma, xz, lz4,
brotli, zstd). This is disabled by default.
* `-z/--search-zip`: Search compressed files (gzip, bzip2, lzma, xz). This is
disabled by default.
* `-C/--context`: Show the lines surrounding a match.
* `--sort path`: Force ripgrep to sort its output by file name. (This disables
* `--sort-files`: Force ripgrep to sort its output by file name. (This disables
parallelism, so it might be slower.)
* `-L/--follow`: Follow symbolic links while recursively searching.
* `-M/--max-columns`: Limit the length of lines printed by ripgrep.

42
README.md
View File

@@ -1,12 +1,11 @@
ripgrep (rg)
------------
ripgrep is a line-oriented search tool that recursively searches your current
directory for a regex pattern. By default, ripgrep will respect your .gitignore
and automatically skip hidden files/directories and binary files. ripgrep
directory for a regex pattern while respecting your gitignore rules. ripgrep
has first class support on Windows, macOS and Linux, with binary downloads
available for [every release](https://github.com/BurntSushi/ripgrep/releases).
ripgrep is similar to other popular search tools like The Silver Searcher, ack
and grep.
ripgrep is similar to other popular search tools like The Silver Searcher,
ack and grep.
[![Linux build status](https://travis-ci.org/BurntSushi/ripgrep.svg)](https://travis-ci.org/BurntSushi/ripgrep)
[![Windows build status](https://ci.appveyor.com/api/projects/status/github/BurntSushi/ripgrep?svg=true)](https://ci.appveyor.com/project/BurntSushi/ripgrep)
@@ -249,22 +248,21 @@ If you're a **Gentoo** user, you can install ripgrep from the
$ emerge sys-apps/ripgrep
```
If you're a **Fedora** user, you can install ripgrep from official
If you're a **Fedora 27+** user, you can install ripgrep from official
repositories.
```
$ sudo dnf install ripgrep
```
If you're an **openSUSE Leap 15.0** user, you can install ripgrep from the
[utilities repo](https://build.opensuse.org/package/show/utilities/ripgrep):
If you're a **Fedora 24+** user, you can install ripgrep from
[copr](https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/):
```
$ sudo zypper ar https://download.opensuse.org/repositories/utilities/openSUSE_Leap_15.0/utilities.repo
$ sudo zypper install ripgrep
$ sudo dnf copr enable carlwgeorge/ripgrep
$ sudo dnf install ripgrep
```
If you're an **openSUSE Tumbleweed** user, you can install ripgrep from the
[official repo](http://software.opensuse.org/package/ripgrep):
@@ -339,7 +337,7 @@ If you're a **NetBSD** user, then you can install ripgrep from
If you're a **Rust programmer**, ripgrep can be installed with `cargo`.
* Note that the minimum supported version of Rust for ripgrep is **1.32.0**,
* Note that the minimum supported version of Rust for ripgrep is **1.28.0**,
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
@@ -360,7 +358,7 @@ ripgrep isn't currently in any other package repositories.
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 1.32.0 (stable) or newer. In general, ripgrep tracks
ripgrep compiles with Rust 1.28.0 (stable) or newer. In general, ripgrep tracks
the latest stable release of the Rust compiler.
To build ripgrep:
@@ -377,14 +375,18 @@ 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'
RUSTFLAGS="-C target-cpu=native" cargo build --release --features 'simd-accel avx-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.
If your machine doesn't support AVX instructions, then simply remove
`avx-accel` from the features list. Similarly for SIMD (which corresponds
roughly to SSE instructions).
The `simd-accel` and `avx-accel` features enable SIMD support in certain
ripgrep dependencies (responsible for counting lines and transcoding). They
are not necessary to get SIMD optimizations for search; those are enabled
automatically. Hopefully, some day, the `simd-accel` and `avx-accel` features
will similarly become unnecessary.
Finally, optional PCRE2 support can be built with ripgrep by enabling the
`pcre2` feature:
@@ -393,8 +395,8 @@ 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.)
(Tip: use `--features 'pcre2 simd-accel avx-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

2
appveyor.yml
View File

@@ -77,5 +77,5 @@ deploy:
branches:
only:
- /^\d+\.\d+\.\d+$/
- /\d+\.\d+\.\d+/
- master

14
complete/_rg
View File

@@ -112,12 +112,8 @@ _rg() {
$no"--no-hidden[don't search hidden files and directories]"
+ '(ignore)' # Ignore-file options
"(--no-ignore-global --no-ignore-parent --no-ignore-vcs --no-ignore-dot)--no-ignore[don't respect ignore files]"
$no'(--ignore-global --ignore-parent --ignore-vcs --ignore-dot)--ignore[respect ignore files]'
+ '(ignore-file-case-insensitive)' # Ignore-file case sensitivity options
'--ignore-file-case-insensitive[process ignore files case insensitively]'
$no'--no-ignore-file-case-insensitive[process ignore files case sensitively]'
"(--no-ignore-global --no-ignore-parent --no-ignore-vcs)--no-ignore[don't respect ignore files]"
$no'(--ignore-global --ignore-parent --ignore-vcs)--ignore[respect ignore files]'
+ '(ignore-global)' # Global ignore-file options
"--no-ignore-global[don't respect global ignore files]"
@@ -131,10 +127,6 @@ _rg() {
"--no-ignore-vcs[don't respect version control ignore files]"
$no'--ignore-vcs[respect version control ignore files]'
+ '(ignore-dot)' # .ignore-file options
"--no-ignore-dot[don't respect .ignore files]"
$no'--ignore-dot[respect .ignore files]'
+ '(json)' # JSON options
'--json[output results in JSON Lines format]'
$no"--no-json[don't output results in JSON Lines format]"
@@ -378,7 +370,7 @@ _rg_encodings() {
shift{-,_}jis csshiftjis {,x-}sjis ms_kanji ms932
utf{,-}8 utf-16{,be,le} unicode-1-1-utf-8
windows-{31j,874,949,125{0..8}} dos-874 tis-620 ansi_x3.4-1968
x-user-defined auto none
x-user-defined auto
)
_wanted encodings expl encoding compadd -a "$@" - _encodings

59
doc/rg.1.txt.tpl
View File

@@ -34,12 +34,12 @@ 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.
the --pcre2 flag can be used to enable backreferences and look-around.
ripgrep supports configuration files. Set *RIPGREP_CONFIG_PATH* to a
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*.
starting with '#' are ignored. For more details, see the man page or the
README.
REGEX SYNTAX
@@ -52,10 +52,10 @@ 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
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
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.
@@ -73,32 +73,13 @@ _PATH_::
OPTIONS
-------
Note that for many options, there exist flags to disable them. In some cases,
those flags are not listed in a first class way below. For example, the
*--column* flag (listed below) enables column numbers in ripgrep's output, but
the *--no-column* flag (not listed below) disables them. The reverse can also
exist. For example, the *--no-ignore* flag (listed below) disables ripgrep's
*gitignore* logic, but the *--ignore* flag (not listed below) enables it. These
flags are useful for overriding a ripgrep configuration file on the command
line. Each flag's documentation notes whether an inverted flag exists. In all
cases, the flag specified last takes precedence.
{OPTIONS}
EXIT STATUS
-----------
If ripgrep finds a match, then the exit status of the program is 0. If no match
could be found, then the exit status is 1. If an error occurred, then the exit
status is always 2 unless ripgrep was run with the *--quiet* flag and a match
was found. In summary:
* `0` exit status occurs only when at least one match was found, and if
no error occurred, unless *--quiet* was given.
* `1` exit status occurs only when no match was found and no error occurred.
* `2` exit status occurs when an error occurred. This is true for both
catastrophic errors (e.g., a regex syntax error) and for soft errors (e.g.,
unable to read a file).
could be found, then the exit status is non-zero.
CONFIGURATION FILES
@@ -107,12 +88,12 @@ 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.
1. Every line is a shell argument, after trimming ASCII whitespace.
2. Lines starting with _#_ (optionally preceded by any amount of
ASCII whitespace) are ignored.
ripgrep will look for a single configuration file if and only if the
*RIPGREP_CONFIG_PATH* environment variable is set and is non-empty.
_RIPGREP_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.
@@ -174,20 +155,20 @@ SHELL COMPLETION
Shell completion files are included in the release tarball for Bash, Fish, Zsh
and PowerShell.
For *bash*, move *rg.bash* to *$XDG_CONFIG_HOME/bash_completion*
or */etc/bash_completion.d/*.
For *bash*, move `rg.bash` to `$XDG_CONFIG_HOME/bash_completion`
or `/etc/bash_completion.d/`.
For *fish*, move *rg.fish* to *$HOME/.config/fish/completions*.
For *fish*, move `rg.fish` to `$HOME/.config/fish/completions`.
For *zsh*, move *_rg* to one of your *$fpath* directories.
For *zsh*, move `_rg` to one of your `$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.
the --no-mmap flag which will forcefully disable the use of memory maps in all
cases.
VERSION
@@ -199,11 +180,7 @@ 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.
Please report bugs and feature requests in the issue tracker.
AUTHORS

6
globset/Cargo.toml
View File

@@ -19,11 +19,11 @@ name = "globset"
bench = false
[dependencies]
aho-corasick = "0.7.3"
bstr = { version = "0.1.2", default-features = false, features = ["std"] }
aho-corasick = "0.6.8"
fnv = "1.0.6"
log = "0.4.5"
regex = "1.1.5"
memchr = "2.1.0"
regex = "1.1.0"
[dev-dependencies]
glob = "0.2.11"

103
globset/src/glob.rs
View File

@@ -120,7 +120,7 @@ impl GlobMatcher {
/// Tests whether the given path matches this pattern or not.
pub fn is_match_candidate(&self, path: &Candidate) -> bool {
self.re.is_match(path.path.as_bytes())
self.re.is_match(&path.path)
}
}
@@ -145,7 +145,7 @@ impl GlobStrategic {
/// Tests whether the given path matches this pattern or not.
fn is_match_candidate(&self, candidate: &Candidate) -> bool {
let byte_path = candidate.path.as_bytes();
let byte_path = &*candidate.path;
match self.strategy {
MatchStrategy::Literal(ref lit) => lit.as_bytes() == byte_path,
@@ -837,66 +837,40 @@ impl<'a> Parser<'a> {
fn parse_star(&mut self) -> Result<(), Error> {
let prev = self.prev;
if self.peek() != Some('*') {
if self.chars.peek() != Some(&'*') {
self.push_token(Token::ZeroOrMore)?;
return Ok(());
}
assert!(self.bump() == Some('*'));
if !self.have_tokens()? {
if !self.peek().map_or(true, is_separator) {
self.push_token(Token::ZeroOrMore)?;
self.push_token(Token::ZeroOrMore)?;
} else {
self.push_token(Token::RecursivePrefix)?;
assert!(self.bump().map_or(true, is_separator));
self.push_token(Token::RecursivePrefix)?;
let next = self.bump();
if !next.map(is_separator).unwrap_or(true) {
return Err(self.error(ErrorKind::InvalidRecursive));
}
return Ok(());
}
self.pop_token()?;
if !prev.map(is_separator).unwrap_or(false) {
if self.stack.len() <= 1
|| (prev != Some(',') && prev != Some('{'))
{
self.push_token(Token::ZeroOrMore)?;
self.push_token(Token::ZeroOrMore)?;
return Ok(());
|| (prev != Some(',') && prev != Some('{')) {
return Err(self.error(ErrorKind::InvalidRecursive));
}
}
let is_suffix =
match self.peek() {
None => {
assert!(self.bump().is_none());
true
}
Some(',') | Some('}') if self.stack.len() >= 2 => {
true
}
Some(c) if is_separator(c) => {
assert!(self.bump().map(is_separator).unwrap_or(false));
false
}
_ => {
self.push_token(Token::ZeroOrMore)?;
self.push_token(Token::ZeroOrMore)?;
return Ok(());
}
};
match self.pop_token()? {
Token::RecursivePrefix => {
self.push_token(Token::RecursivePrefix)?;
match self.chars.peek() {
None => {
assert!(self.bump().is_none());
self.push_token(Token::RecursiveSuffix)
}
Token::RecursiveSuffix => {
self.push_token(Token::RecursiveSuffix)?;
Some(&',') | Some(&'}') if self.stack.len() >= 2 => {
self.push_token(Token::RecursiveSuffix)
}
_ => {
if is_suffix {
self.push_token(Token::RecursiveSuffix)?;
} else {
self.push_token(Token::RecursiveZeroOrMore)?;
}
Some(&c) if is_separator(c) => {
assert!(self.bump().map(is_separator).unwrap_or(false));
self.push_token(Token::RecursiveZeroOrMore)
}
_ => Err(self.error(ErrorKind::InvalidRecursive)),
}
Ok(())
}
fn parse_class(&mut self) -> Result<(), Error> {
@@ -985,10 +959,6 @@ impl<'a> Parser<'a> {
self.cur = self.chars.next();
self.cur
}
fn peek(&mut self) -> Option<char> {
self.chars.peek().map(|&ch| ch)
}
}
#[cfg(test)]
@@ -1174,6 +1144,13 @@ mod tests {
syntax!(cls20, "[^a]", vec![classn('a', 'a')]);
syntax!(cls21, "[^a-z]", vec![classn('a', 'z')]);
syntaxerr!(err_rseq1, "a**", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq2, "**a", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq3, "a**b", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq4, "***", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq5, "/a**", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq6, "/**a", ErrorKind::InvalidRecursive);
syntaxerr!(err_rseq7, "/a**b", ErrorKind::InvalidRecursive);
syntaxerr!(err_unclosed1, "[", ErrorKind::UnclosedClass);
syntaxerr!(err_unclosed2, "[]", ErrorKind::UnclosedClass);
syntaxerr!(err_unclosed3, "[!", ErrorKind::UnclosedClass);
@@ -1217,30 +1194,8 @@ mod tests {
toregex!(re8, "[*]", r"^[\*]$");
toregex!(re9, "[+]", r"^[\+]$");
toregex!(re10, "+", r"^\+$");
toregex!(re11, "☃", r"^\xe2\x98\x83$");
toregex!(re12, "**", r"^.*$");
toregex!(re13, "**/", r"^.*$");
toregex!(re14, "**/*", r"^(?:/?|.*/).*$");
toregex!(re15, "**/**", r"^.*$");
toregex!(re16, "**/**/*", r"^(?:/?|.*/).*$");
toregex!(re17, "**/**/**", r"^.*$");
toregex!(re18, "**/**/**/*", r"^(?:/?|.*/).*$");
toregex!(re19, "a/**", r"^a(?:/?|/.*)$");
toregex!(re20, "a/**/**", r"^a(?:/?|/.*)$");
toregex!(re21, "a/**/**/**", r"^a(?:/?|/.*)$");
toregex!(re22, "a/**/b", r"^a(?:/|/.*/)b$");
toregex!(re23, "a/**/**/b", r"^a(?:/|/.*/)b$");
toregex!(re24, "a/**/**/**/b", r"^a(?:/|/.*/)b$");
toregex!(re25, "**/b", r"^(?:/?|.*/)b$");
toregex!(re26, "**/**/b", r"^(?:/?|.*/)b$");
toregex!(re27, "**/**/**/b", r"^(?:/?|.*/)b$");
toregex!(re28, "a**", r"^a.*.*$");
toregex!(re29, "**a", r"^.*.*a$");
toregex!(re30, "a**b", r"^a.*.*b$");
toregex!(re31, "***", r"^.*.*.*$");
toregex!(re32, "/a**", r"^/a.*.*$");
toregex!(re33, "/**a", r"^/.*.*a$");
toregex!(re34, "/a**b", r"^/a.*.*b$");
toregex!(re11, "**", r"^.*$");
toregex!(re12, "☃", r"^\xe2\x98\x83$");
matches!(match1, "a", "a");
matches!(match2, "a*b", "a_b");

97
globset/src/lib.rs
View File

@@ -104,25 +104,27 @@ or to enable case insensitive matching.
#![deny(missing_docs)]
extern crate aho_corasick;
extern crate bstr;
extern crate fnv;
#[macro_use]
extern crate log;
extern crate memchr;
extern crate regex;
use std::borrow::Cow;
use std::collections::{BTreeMap, HashMap};
use std::error::Error as StdError;
use std::ffi::OsStr;
use std::fmt;
use std::hash;
use std::path::Path;
use std::str;
use aho_corasick::AhoCorasick;
use bstr::{B, BStr, BString};
use aho_corasick::{Automaton, AcAutomaton, FullAcAutomaton};
use regex::bytes::{Regex, RegexBuilder, RegexSet};
use pathutil::{file_name, file_name_ext, normalize_path};
use pathutil::{
file_name, file_name_ext, normalize_path, os_str_bytes, path_bytes,
};
use glob::MatchStrategy;
pub use glob::{Glob, GlobBuilder, GlobMatcher};
@@ -141,13 +143,8 @@ pub struct Error {
/// The kind of error that can occur when parsing a glob pattern.
#[derive(Clone, Debug, Eq, PartialEq)]
pub enum ErrorKind {
/// **DEPRECATED**.
///
/// This error used to occur for consistency with git's glob specification,
/// but the specification now accepts all uses of `**`. When `**` does not
/// appear adjacent to a path separator or at the beginning/end of a glob,
/// it is now treated as two consecutive `*` patterns. As such, this error
/// is no longer used.
/// Occurs when a use of `**` is invalid. Namely, `**` can only appear
/// adjacent to a path separator, or the beginning/end of a glob.
InvalidRecursive,
/// Occurs when a character class (e.g., `[abc]`) is not closed.
UnclosedClass,
@@ -292,7 +289,6 @@ pub struct GlobSet {
impl GlobSet {
/// Create an empty `GlobSet`. An empty set matches nothing.
#[inline]
pub fn empty() -> GlobSet {
GlobSet {
len: 0,
@@ -301,13 +297,11 @@ impl GlobSet {
}
/// Returns true if this set is empty, and therefore matches nothing.
#[inline]
pub fn is_empty(&self) -> bool {
self.len == 0
}
/// Returns the number of globs in this set.
#[inline]
pub fn len(&self) -> usize {
self.len
}
@@ -490,25 +484,24 @@ impl GlobSetBuilder {
/// path against multiple globs or sets of globs.
#[derive(Clone, Debug)]
pub struct Candidate<'a> {
path: Cow<'a, BStr>,
basename: Cow<'a, BStr>,
ext: Cow<'a, BStr>,
path: Cow<'a, [u8]>,
basename: Cow<'a, [u8]>,
ext: Cow<'a, [u8]>,
}
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(BString::from_path_lossy(path.as_ref()));
let basename = file_name(&path).unwrap_or(Cow::Borrowed(B("")));
let ext = file_name_ext(&basename).unwrap_or(Cow::Borrowed(B("")));
let path = path.as_ref();
let basename = file_name(path).unwrap_or(OsStr::new(""));
Candidate {
path: path,
basename: basename,
ext: ext,
path: normalize_path(path_bytes(path)),
basename: os_str_bytes(basename),
ext: file_name_ext(basename).unwrap_or(Cow::Borrowed(b"")),
}
}
fn path_prefix(&self, max: usize) -> &BStr {
fn path_prefix(&self, max: usize) -> &[u8] {
if self.path.len() <= max {
&*self.path
} else {
@@ -516,7 +509,7 @@ impl<'a> Candidate<'a> {
}
}
fn path_suffix(&self, max: usize) -> &BStr {
fn path_suffix(&self, max: usize) -> &[u8] {
if self.path.len() <= max {
&*self.path
} else {
@@ -577,12 +570,12 @@ impl LiteralStrategy {
}
fn is_match(&self, candidate: &Candidate) -> bool {
self.0.contains_key(candidate.path.as_bytes())
self.0.contains_key(&*candidate.path)
}
#[inline(never)]
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
if let Some(hits) = self.0.get(candidate.path.as_bytes()) {
if let Some(hits) = self.0.get(&*candidate.path) {
matches.extend(hits);
}
}
@@ -604,7 +597,7 @@ impl BasenameLiteralStrategy {
if candidate.basename.is_empty() {
return false;
}
self.0.contains_key(candidate.basename.as_bytes())
self.0.contains_key(&*candidate.basename)
}
#[inline(never)]
@@ -612,7 +605,7 @@ impl BasenameLiteralStrategy {
if candidate.basename.is_empty() {
return;
}
if let Some(hits) = self.0.get(candidate.basename.as_bytes()) {
if let Some(hits) = self.0.get(&*candidate.basename) {
matches.extend(hits);
}
}
@@ -634,7 +627,7 @@ impl ExtensionStrategy {
if candidate.ext.is_empty() {
return false;
}
self.0.contains_key(candidate.ext.as_bytes())
self.0.contains_key(&*candidate.ext)
}
#[inline(never)]
@@ -642,7 +635,7 @@ impl ExtensionStrategy {
if candidate.ext.is_empty() {
return;
}
if let Some(hits) = self.0.get(candidate.ext.as_bytes()) {
if let Some(hits) = self.0.get(&*candidate.ext) {
matches.extend(hits);
}
}
@@ -650,7 +643,7 @@ impl ExtensionStrategy {
#[derive(Clone, Debug)]
struct PrefixStrategy {
matcher: AhoCorasick,
matcher: FullAcAutomaton<Vec<u8>>,
map: Vec<usize>,
longest: usize,
}
@@ -658,8 +651,8 @@ struct PrefixStrategy {
impl PrefixStrategy {
fn is_match(&self, candidate: &Candidate) -> bool {
let path = candidate.path_prefix(self.longest);
for m in self.matcher.find_overlapping_iter(path) {
if m.start() == 0 {
for m in self.matcher.find_overlapping(path) {
if m.start == 0 {
return true;
}
}
@@ -668,9 +661,9 @@ impl PrefixStrategy {
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
let path = candidate.path_prefix(self.longest);
for m in self.matcher.find_overlapping_iter(path) {
if m.start() == 0 {
matches.push(self.map[m.pattern()]);
for m in self.matcher.find_overlapping(path) {
if m.start == 0 {
matches.push(self.map[m.pati]);
}
}
}
@@ -678,7 +671,7 @@ impl PrefixStrategy {
#[derive(Clone, Debug)]
struct SuffixStrategy {
matcher: AhoCorasick,
matcher: FullAcAutomaton<Vec<u8>>,
map: Vec<usize>,
longest: usize,
}
@@ -686,8 +679,8 @@ struct SuffixStrategy {
impl SuffixStrategy {
fn is_match(&self, candidate: &Candidate) -> bool {
let path = candidate.path_suffix(self.longest);
for m in self.matcher.find_overlapping_iter(path) {
if m.end() == path.len() {
for m in self.matcher.find_overlapping(path) {
if m.end == path.len() {
return true;
}
}
@@ -696,9 +689,9 @@ impl SuffixStrategy {
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
let path = candidate.path_suffix(self.longest);
for m in self.matcher.find_overlapping_iter(path) {
if m.end() == path.len() {
matches.push(self.map[m.pattern()]);
for m in self.matcher.find_overlapping(path) {
if m.end == path.len() {
matches.push(self.map[m.pati]);
}
}
}
@@ -712,11 +705,11 @@ impl RequiredExtensionStrategy {
if candidate.ext.is_empty() {
return false;
}
match self.0.get(candidate.ext.as_bytes()) {
match self.0.get(&*candidate.ext) {
None => false,
Some(regexes) => {
for &(_, ref re) in regexes {
if re.is_match(candidate.path.as_bytes()) {
if re.is_match(&*candidate.path) {
return true;
}
}
@@ -730,9 +723,9 @@ impl RequiredExtensionStrategy {
if candidate.ext.is_empty() {
return;
}
if let Some(regexes) = self.0.get(candidate.ext.as_bytes()) {
if let Some(regexes) = self.0.get(&*candidate.ext) {
for &(global_index, ref re) in regexes {
if re.is_match(candidate.path.as_bytes()) {
if re.is_match(&*candidate.path) {
matches.push(global_index);
}
}
@@ -748,11 +741,11 @@ struct RegexSetStrategy {
impl RegexSetStrategy {
fn is_match(&self, candidate: &Candidate) -> bool {
self.matcher.is_match(candidate.path.as_bytes())
self.matcher.is_match(&*candidate.path)
}
fn matches_into(&self, candidate: &Candidate, matches: &mut Vec<usize>) {
for i in self.matcher.matches(candidate.path.as_bytes()) {
for i in self.matcher.matches(&*candidate.path) {
matches.push(self.map[i]);
}
}
@@ -783,16 +776,18 @@ impl MultiStrategyBuilder {
}
fn prefix(self) -> PrefixStrategy {
let it = self.literals.into_iter().map(|s| s.into_bytes());
PrefixStrategy {
matcher: AhoCorasick::new_auto_configured(&self.literals),
matcher: AcAutomaton::new(it).into_full(),
map: self.map,
longest: self.longest,
}
}
fn suffix(self) -> SuffixStrategy {
let it = self.literals.into_iter().map(|s| s.into_bytes());
SuffixStrategy {
matcher: AhoCorasick::new_auto_configured(&self.literals),
matcher: AcAutomaton::new(it).into_full(),
map: self.map,
longest: self.longest,
}

103
globset/src/pathutil.rs
View File

@@ -1,26 +1,41 @@
use std::borrow::Cow;
use bstr::BStr;
use std::ffi::OsStr;
use std::path::Path;
/// 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.
pub fn file_name<'a>(path: &Cow<'a, BStr>) -> Option<Cow<'a, BStr>> {
#[cfg(unix)]
pub fn file_name<'a, P: AsRef<Path> + ?Sized>(
path: &'a P,
) -> Option<&'a OsStr> {
use std::os::unix::ffi::OsStrExt;
use memchr::memrchr;
let path = path.as_ref().as_os_str().as_bytes();
if path.is_empty() {
return None;
} else if path.last() == Some(b'.') {
} else if path.len() == 1 && path[0] == b'.' {
return None;
} else if path.last() == Some(&b'.') {
return None;
} else if path.len() >= 2 && &path[path.len() - 2..] == &b".."[..] {
return None;
}
let last_slash = path.rfind_byte(b'/').map(|i| i + 1).unwrap_or(0);
Some(match *path {
Cow::Borrowed(path) => Cow::Borrowed(&path[last_slash..]),
Cow::Owned(ref path) => {
let mut path = path.clone();
path.drain_bytes(..last_slash);
Cow::Owned(path)
}
})
let last_slash = memrchr(b'/', path).map(|i| i + 1).unwrap_or(0);
Some(OsStr::from_bytes(&path[last_slash..]))
}
/// The final component of the path, if it is a normal file.
///
/// If the path terminates in ., .., or consists solely of a root of prefix,
/// file_name will return None.
#[cfg(not(unix))]
pub fn file_name<'a, P: AsRef<Path> + ?Sized>(
path: &'a P,
) -> Option<&'a OsStr> {
path.as_ref().file_name()
}
/// Return a file extension given a path's file name.
@@ -39,28 +54,59 @@ pub fn file_name<'a>(path: &Cow<'a, BStr>) -> Option<Cow<'a, BStr>> {
/// a pattern like `*.rs` is obviously trying to match files with a `rs`
/// extension, but it also matches files like `.rs`, which doesn't have an
/// extension according to std::path::Path::extension.
pub fn file_name_ext<'a>(name: &Cow<'a, BStr>) -> Option<Cow<'a, BStr>> {
pub fn file_name_ext(name: &OsStr) -> Option<Cow<[u8]>> {
if name.is_empty() {
return None;
}
let last_dot_at = match name.rfind_byte(b'.') {
None => return None,
Some(i) => i,
let name = os_str_bytes(name);
let last_dot_at = {
let result = name
.iter().enumerate().rev()
.find(|&(_, &b)| b == b'.')
.map(|(i, _)| i);
match result {
None => return None,
Some(i) => i,
}
};
Some(match *name {
Some(match name {
Cow::Borrowed(name) => Cow::Borrowed(&name[last_dot_at..]),
Cow::Owned(ref name) => {
let mut name = name.clone();
name.drain_bytes(..last_dot_at);
Cow::Owned(mut name) => {
name.drain(..last_dot_at);
Cow::Owned(name)
}
})
}
/// Return raw bytes of a path, transcoded to UTF-8 if necessary.
pub fn path_bytes(path: &Path) -> Cow<[u8]> {
os_str_bytes(path.as_os_str())
}
/// Return the raw bytes of the given OS string, possibly transcoded to UTF-8.
#[cfg(unix)]
pub fn os_str_bytes(s: &OsStr) -> Cow<[u8]> {
use std::os::unix::ffi::OsStrExt;
Cow::Borrowed(s.as_bytes())
}
/// Return the raw bytes of the given OS string, possibly transcoded to UTF-8.
#[cfg(not(unix))]
pub fn os_str_bytes(s: &OsStr) -> Cow<[u8]> {
// TODO(burntsushi): On Windows, OS strings are WTF-8, which is a superset
// of UTF-8, so even if we could get at the raw bytes, they wouldn't
// be useful. We *must* convert to UTF-8 before doing path matching.
// Unfortunate, but necessary.
match s.to_string_lossy() {
Cow::Owned(s) => Cow::Owned(s.into_bytes()),
Cow::Borrowed(s) => Cow::Borrowed(s.as_bytes()),
}
}
/// Normalizes a path to use `/` as a separator everywhere, even on platforms
/// that recognize other characters as separators.
#[cfg(unix)]
pub fn normalize_path(path: Cow<BStr>) -> Cow<BStr> {
pub fn normalize_path(path: Cow<[u8]>) -> Cow<[u8]> {
// UNIX only uses /, so we're good.
path
}
@@ -68,7 +114,7 @@ pub fn normalize_path(path: Cow<BStr>) -> Cow<BStr> {
/// Normalizes a path to use `/` as a separator everywhere, even on platforms
/// that recognize other characters as separators.
#[cfg(not(unix))]
pub fn normalize_path(mut path: Cow<BStr>) -> Cow<BStr> {
pub fn normalize_path(mut path: Cow<[u8]>) -> Cow<[u8]> {
use std::path::is_separator;
for i in 0..path.len() {
@@ -83,8 +129,7 @@ pub fn normalize_path(mut path: Cow<BStr>) -> Cow<BStr> {
#[cfg(test)]
mod tests {
use std::borrow::Cow;
use bstr::{B, BString};
use std::ffi::OsStr;
use super::{file_name_ext, normalize_path};
@@ -92,9 +137,8 @@ mod tests {
($name:ident, $file_name:expr, $ext:expr) => {
#[test]
fn $name() {
let bs = BString::from($file_name);
let got = file_name_ext(&Cow::Owned(bs));
assert_eq!($ext.map(|s| Cow::Borrowed(B(s))), got);
let got = file_name_ext(OsStr::new($file_name));
assert_eq!($ext.map(|s| Cow::Borrowed(s.as_bytes())), got);
}
};
}
@@ -109,8 +153,7 @@ mod tests {
($name:ident, $path:expr, $expected:expr) => {
#[test]
fn $name() {
let bs = BString::from_slice($path);
let got = normalize_path(Cow::Owned(bs));
let got = normalize_path(Cow::Owned($path.to_vec()));
assert_eq!($expected.to_vec(), got.into_owned());
}
};

1
grep-cli/Cargo.toml
View File

@@ -14,7 +14,6 @@ license = "Unlicense/MIT"
[dependencies]
atty = "0.2.11"
bstr = "0.1.2"
globset = { version = "0.4.2", path = "../globset" }
lazy_static = "1.1.0"
log = "0.4.5"

9
grep-cli/src/decompress.rs
View File

@@ -352,8 +352,6 @@ fn default_decompression_commands() -> Vec<DecompressionCommand> {
const ARGS_XZ: &[&str] = &["xz", "-d", "-c"];
const ARGS_LZ4: &[&str] = &["lz4", "-d", "-c"];
const ARGS_LZMA: &[&str] = &["xz", "--format=lzma", "-d", "-c"];
const ARGS_BROTLI: &[&str] = &["brotli", "-d", "-c"];
const ARGS_ZSTD: &[&str] = &["zstd", "-q", "-d", "-c"];
fn cmd(glob: &str, args: &[&str]) -> DecompressionCommand {
DecompressionCommand {
@@ -369,14 +367,15 @@ fn default_decompression_commands() -> Vec<DecompressionCommand> {
vec![
cmd("*.gz", ARGS_GZIP),
cmd("*.tgz", ARGS_GZIP),
cmd("*.bz2", ARGS_BZIP),
cmd("*.tbz2", ARGS_BZIP),
cmd("*.xz", ARGS_XZ),
cmd("*.txz", ARGS_XZ),
cmd("*.lz4", ARGS_LZ4),
cmd("*.lzma", ARGS_LZMA),
cmd("*.br", ARGS_BROTLI),
cmd("*.zst", ARGS_ZSTD),
cmd("*.zstd", ARGS_ZSTD),
]
}

74
grep-cli/src/escape.rs
View File

@@ -1,8 +1,6 @@
use std::ffi::OsStr;
use std::str;
use bstr::{BStr, BString};
/// A single state in the state machine used by `unescape`.
#[derive(Clone, Copy, Eq, PartialEq)]
enum State {
@@ -37,16 +35,18 @@ enum State {
///
/// assert_eq!(r"foo\nbar\xFFbaz", escape(b"foo\nbar\xFFbaz"));
/// ```
pub fn escape(bytes: &[u8]) -> String {
let bytes = BStr::new(bytes);
pub fn escape(mut bytes: &[u8]) -> String {
let mut escaped = String::new();
for (s, e, ch) in bytes.char_indices() {
if ch == '\u{FFFD}' {
for b in bytes[s..e].bytes() {
escape_byte(b, &mut escaped);
while let Some(result) = decode_utf8(bytes) {
match result {
Ok(cp) => {
escape_char(cp, &mut escaped);
bytes = &bytes[cp.len_utf8()..];
}
Err(byte) => {
escape_byte(byte, &mut escaped);
bytes = &bytes[1..];
}
} else {
escape_char(ch, &mut escaped);
}
}
escaped
@@ -56,7 +56,19 @@ pub fn escape(bytes: &[u8]) -> String {
///
/// This is like [`escape`](fn.escape.html), but accepts an OS string.
pub fn escape_os(string: &OsStr) -> String {
escape(BString::from_os_str_lossy(string).as_bytes())
#[cfg(unix)]
fn imp(string: &OsStr) -> String {
use std::os::unix::ffi::OsStrExt;
escape(string.as_bytes())
}
#[cfg(not(unix))]
fn imp(string: &OsStr) -> String {
escape(string.to_string_lossy().as_bytes())
}
imp(string)
}
/// Unescapes a string.
@@ -183,6 +195,46 @@ fn escape_byte(byte: u8, into: &mut String) {
}
}
/// Decodes the next UTF-8 encoded codepoint from the given byte slice.
///
/// If no valid encoding of a codepoint exists at the beginning of the given
/// byte slice, then the first byte is returned instead.
///
/// This returns `None` if and only if `bytes` is empty.
fn decode_utf8(bytes: &[u8]) -> Option<Result<char, u8>> {
if bytes.is_empty() {
return None;
}
let len = match utf8_len(bytes[0]) {
None => return Some(Err(bytes[0])),
Some(len) if len > bytes.len() => return Some(Err(bytes[0])),
Some(len) => len,
};
match str::from_utf8(&bytes[..len]) {
Ok(s) => Some(Ok(s.chars().next().unwrap())),
Err(_) => Some(Err(bytes[0])),
}
}
/// Given a UTF-8 leading byte, this returns the total number of code units
/// in the following encoded codepoint.
///
/// If the given byte is not a valid UTF-8 leading byte, then this returns
/// `None`.
fn utf8_len(byte: u8) -> Option<usize> {
if byte <= 0x7F {
Some(1)
} else if byte <= 0b110_11111 {
Some(2)
} else if byte <= 0b1110_1111 {
Some(3)
} else if byte <= 0b1111_0111 {
Some(4)
} else {
None
}
}
#[cfg(test)]
mod tests {
use super::{escape, unescape};

1
grep-cli/src/lib.rs
View File

@@ -159,7 +159,6 @@ error message is crafted that typically tells the user how to fix the problem.
#![deny(missing_docs)]
extern crate atty;
extern crate bstr;
extern crate globset;
#[macro_use]
extern crate lazy_static;

7
grep-matcher/Cargo.toml
View File

@@ -13,8 +13,11 @@ keywords = ["regex", "pattern", "trait"]
license = "Unlicense/MIT"
autotests = false
[dependencies]
memchr = "2.1"
[dependencies.bstr]
version = "*"
path = "/home/andrew/rust/bstr"
default-features = false
features = ["std"]
[dev-dependencies]
regex = "1.1"

4
grep-matcher/src/interpolate.rs
View File

@@ -1,6 +1,6 @@
use std::str;
use memchr::memchr;
use bstr::B;
/// Interpolate capture references in `replacement` and write the interpolation
/// result to `dst`. References in `replacement` take the form of $N or $name,
@@ -22,7 +22,7 @@ pub fn interpolate<A, N>(
N: FnMut(&str) -> Option<usize>
{
while !replacement.is_empty() {
match memchr(b'$', replacement) {
match B(replacement).find_byte(b'$') {
None => break,
Some(i) => {
dst.extend(&replacement[..i]);

20
grep-matcher/src/lib.rs
View File

@@ -38,13 +38,15 @@ implementations.
#![deny(missing_docs)]
extern crate memchr;
extern crate bstr;
use std::fmt;
use std::io;
use std::ops;
use std::u64;
use bstr::BStr;
use interpolate::interpolate;
mod interpolate;
@@ -180,6 +182,22 @@ impl ops::IndexMut<Match> for [u8] {
}
}
impl ops::Index<Match> for BStr {
type Output = BStr;
#[inline]
fn index(&self, index: Match) -> &BStr {
&self[index.start..index.end]
}
}
impl ops::IndexMut<Match> for BStr {
#[inline]
fn index_mut(&mut self, index: Match) -> &mut BStr {
&mut self[index.start..index.end]
}
}
impl ops::Index<Match> for str {
type Output = str;

1
grep-printer/Cargo.toml
View File

@@ -19,7 +19,6 @@ serde1 = ["base64", "serde", "serde_derive", "serde_json"]
[dependencies]
base64 = { version = "0.10.0", optional = true }
bstr = "0.1.2"
grep-matcher = { version = "0.1.1", path = "../grep-matcher" }
grep-searcher = { version = "0.1.1", path = "../grep-searcher" }
termcolor = "1.0.4"

44
grep-printer/src/json.rs
View File

@@ -817,8 +817,7 @@ impl<'a> SubMatches<'a> {
#[cfg(test)]
mod tests {
use grep_regex::{RegexMatcher, RegexMatcherBuilder};
use grep_matcher::LineTerminator;
use grep_regex::RegexMatcher;
use grep_searcher::SearcherBuilder;
use super::{JSON, JSONBuilder};
@@ -919,45 +918,4 @@ and exhibited clearly, with a label attached.\
assert_eq!(got.lines().count(), 2);
assert!(got.contains("begin") && got.contains("end"));
}
#[test]
fn missing_crlf() {
let haystack = "test\r\n".as_bytes();
let matcher = RegexMatcherBuilder::new()
.build("test")
.unwrap();
let mut printer = JSONBuilder::new()
.build(vec![]);
SearcherBuilder::new()
.build()
.search_reader(&matcher, haystack, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert_eq!(got.lines().count(), 3);
assert!(
got.lines().nth(1).unwrap().contains(r"test\r\n"),
r"missing 'test\r\n' in '{}'",
got.lines().nth(1).unwrap(),
);
let matcher = RegexMatcherBuilder::new()
.crlf(true)
.build("test")
.unwrap();
let mut printer = JSONBuilder::new()
.build(vec![]);
SearcherBuilder::new()
.line_terminator(LineTerminator::crlf())
.build()
.search_reader(&matcher, haystack, printer.sink(&matcher))
.unwrap();
let got = printer_contents(&mut printer);
assert_eq!(got.lines().count(), 3);
assert!(
got.lines().nth(1).unwrap().contains(r"test\r\n"),
r"missing 'test\r\n' in '{}'",
got.lines().nth(1).unwrap(),
);
}
}

1
grep-printer/src/lib.rs
View File

@@ -70,7 +70,6 @@ fn example() -> Result<(), Box<Error>> {
#[cfg(feature = "serde1")]
extern crate base64;
extern crate bstr;
extern crate grep_matcher;
#[cfg(test)]
extern crate grep_regex;

7
grep-printer/src/summary.rs
View File

@@ -403,7 +403,7 @@ impl<W: WriteColor> Summary<W> {
where M: Matcher,
P: ?Sized + AsRef<Path>,
{
if !self.config.path && !self.config.kind.requires_path() {
if !self.config.path {
return self.sink(matcher);
}
let stats =
@@ -477,10 +477,7 @@ impl<'p, 's, M: Matcher, W: WriteColor> SummarySink<'p, 's, M, W> {
/// This is unaffected by the result of searches before the previous
/// search.
pub fn has_match(&self) -> bool {
match self.summary.config.kind {
SummaryKind::PathWithoutMatch => self.match_count == 0,
_ => self.match_count > 0,
}
self.match_count > 0
}
/// If binary data was found in the previous search, this returns the

23
grep-printer/src/util.rs
View File

@@ -4,7 +4,6 @@ use std::io;
use std::path::Path;
use std::time;
use bstr::{BStr, BString};
use grep_matcher::{Captures, LineTerminator, Match, Matcher};
use grep_searcher::{
LineIter,
@@ -263,12 +262,26 @@ impl<'a> Sunk<'a> {
/// portability with a small cost: on Windows, paths that are not valid UTF-16
/// will not roundtrip correctly.
#[derive(Clone, Debug)]
pub struct PrinterPath<'a>(Cow<'a, BStr>);
pub struct PrinterPath<'a>(Cow<'a, [u8]>);
impl<'a> PrinterPath<'a> {
/// Create a new path suitable for printing.
pub fn new(path: &'a Path) -> PrinterPath<'a> {
PrinterPath(BString::from_path_lossy(path))
PrinterPath::new_impl(path)
}
#[cfg(unix)]
fn new_impl(path: &'a Path) -> PrinterPath<'a> {
use std::os::unix::ffi::OsStrExt;
PrinterPath(Cow::Borrowed(path.as_os_str().as_bytes()))
}
#[cfg(not(unix))]
fn new_impl(path: &'a Path) -> PrinterPath<'a> {
PrinterPath(match path.to_string_lossy() {
Cow::Owned(path) => Cow::Owned(path.into_bytes()),
Cow::Borrowed(path) => Cow::Borrowed(path.as_bytes()),
})
}
/// Create a new printer path from the given path which can be efficiently
@@ -289,7 +302,7 @@ impl<'a> PrinterPath<'a> {
/// path separators that are both replaced by `new_sep`. In all other
/// environments, only `/` is treated as a path separator.
fn replace_separator(&mut self, new_sep: u8) {
let transformed_path: BString = self.0.bytes().map(|b| {
let transformed_path: Vec<_> = self.as_bytes().iter().map(|&b| {
if b == b'/' || (cfg!(windows) && b == b'\\') {
new_sep
} else {
@@ -301,7 +314,7 @@ impl<'a> PrinterPath<'a> {
/// Return the raw bytes for this path.
pub fn as_bytes(&self) -> &[u8] {
self.0.as_bytes()
&*self.0
}
}

4
grep-regex/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-regex"
version = "0.1.2" #:version
version = "0.1.1" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Use Rust's regex library with the 'grep' crate.
@@ -16,6 +16,6 @@ license = "Unlicense/MIT"
log = "0.4.5"
grep-matcher = { version = "0.1.1", path = "../grep-matcher" }
regex = "1.1"
regex-syntax = "0.6.5"
regex-syntax = "0.6.4"
thread_local = "0.3.6"
utf8-ranges = "1.0.1"

10
grep-regex/src/config.rs
View File

@@ -160,14 +160,6 @@ impl ConfiguredHIR {
non_matching_bytes(&self.expr)
}
/// Returns true if and only if this regex needs to have its match offsets
/// tweaked because of CRLF support. Specifically, this occurs when the
/// CRLF hack is enabled and the regex is line anchored at the end. In
/// this case, matches that end with a `\r` have the `\r` stripped.
pub fn needs_crlf_stripped(&self) -> bool {
self.config.crlf && self.expr.is_line_anchored_end()
}
/// Builds a regular expression from this HIR expression.
pub fn regex(&self) -> Result<Regex, Error> {
self.pattern_to_regex(&self.expr.to_string())
@@ -207,7 +199,7 @@ impl ConfiguredHIR {
if self.config.line_terminator.is_none() {
return Ok(None);
}
match LiteralSets::new(&self.expr).one_regex(self.config.word) {
match LiteralSets::new(&self.expr).one_regex() {
None => Ok(None),
Some(pattern) => self.pattern_to_regex(&pattern).map(Some),
}

105
grep-regex/src/crlf.rs
View File

@@ -1,110 +1,5 @@
use std::collections::HashMap;
use grep_matcher::{Match, Matcher, NoError};
use regex::bytes::Regex;
use regex_syntax::hir::{self, Hir, HirKind};
use config::ConfiguredHIR;
use error::Error;
use matcher::RegexCaptures;
/// A matcher for implementing "word match" semantics.
#[derive(Clone, Debug)]
pub struct CRLFMatcher {
/// The regex.
regex: Regex,
/// A map from capture group name to capture group index.
names: HashMap<String, usize>,
}
impl CRLFMatcher {
/// Create a new matcher from the given pattern that strips `\r` from the
/// end of every match.
///
/// This panics if the given expression doesn't need its CRLF stripped.
pub fn new(expr: &ConfiguredHIR) -> Result<CRLFMatcher, Error> {
assert!(expr.needs_crlf_stripped());
let regex = expr.regex()?;
let mut names = HashMap::new();
for (i, optional_name) in regex.capture_names().enumerate() {
if let Some(name) = optional_name {
names.insert(name.to_string(), i.checked_sub(1).unwrap());
}
}
Ok(CRLFMatcher { regex, names })
}
/// Return the underlying regex used by this matcher.
pub fn regex(&self) -> &Regex {
&self.regex
}
}
impl Matcher for CRLFMatcher {
type Captures = RegexCaptures;
type Error = NoError;
fn find_at(
&self,
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, NoError> {
let m = match self.regex.find_at(haystack, at) {
None => return Ok(None),
Some(m) => Match::new(m.start(), m.end()),
};
Ok(Some(adjust_match(haystack, m)))
}
fn new_captures(&self) -> Result<RegexCaptures, NoError> {
Ok(RegexCaptures::new(self.regex.capture_locations()))
}
fn capture_count(&self) -> usize {
self.regex.captures_len().checked_sub(1).unwrap()
}
fn capture_index(&self, name: &str) -> Option<usize> {
self.names.get(name).map(|i| *i)
}
fn captures_at(
&self,
haystack: &[u8],
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
caps.strip_crlf(false);
let r = self.regex.captures_read_at(caps.locations(), haystack, at);
if !r.is_some() {
return Ok(false);
}
// If the end of our match includes a `\r`, then strip it from all
// capture groups ending at the same location.
let end = caps.locations().get(0).unwrap().1;
if end > 0 && haystack.get(end - 1) == Some(&b'\r') {
caps.strip_crlf(true);
}
Ok(true)
}
// We specifically do not implement other methods like find_iter or
// captures_iter. Namely, the iter methods are guaranteed to be correct
// by virtue of implementing find_at and captures_at above.
}
/// If the given match ends with a `\r`, then return a new match that ends
/// immediately before the `\r`.
pub fn adjust_match(haystack: &[u8], m: Match) -> Match {
if m.end() > 0 && haystack.get(m.end() - 1) == Some(&b'\r') {
m.with_end(m.end() - 1)
} else {
m
}
}
/// Substitutes all occurrences of multi-line enabled `$` with `(?:\r?$)`.
///
/// This does not preserve the exact semantics of the given expression,

19
grep-regex/src/literal.rs
View File

@@ -47,23 +47,18 @@ impl LiteralSets {
/// generated these literal sets. The idea here is that the pattern
/// returned by this method is much cheaper to search for. i.e., It is
/// usually a single literal or an alternation of literals.
pub fn one_regex(&self, word: bool) -> Option<String> {
pub fn one_regex(&self) -> Option<String> {
// TODO: The logic in this function is basically inscrutable. It grew
// organically in the old grep 0.1 crate. Ideally, it would be
// re-worked. In fact, the entire inner literal extraction should be
// re-worked. Actually, most of regex-syntax's literal extraction
// should also be re-worked. Alas... only so much time in the day.
if !word {
if self.prefixes.all_complete() && !self.prefixes.is_empty() {
debug!("literal prefixes detected: {:?}", self.prefixes);
// When this is true, the regex engine will do a literal scan,
// so we don't need to return anything. But we only do this
// if we aren't doing a word regex, since a word regex adds
// a `(?:\W|^)` to the beginning of the regex, thereby
// defeating the regex engine's literal detection.
return None;
}
if self.prefixes.all_complete() && !self.prefixes.is_empty() {
debug!("literal prefixes detected: {:?}", self.prefixes);
// When this is true, the regex engine will do a literal scan,
// so we don't need to return anything.
return None;
}
// Out of inner required literals, prefixes and suffixes, which one
@@ -290,7 +285,7 @@ mod tests {
}
fn one_regex(pattern: &str) -> Option<String> {
sets(pattern).one_regex(false)
sets(pattern).one_regex()
}
// Put a pattern into the same format as the one returned by `one_regex`.

71
grep-regex/src/matcher.rs
View File

@@ -6,7 +6,6 @@ use grep_matcher::{
use regex::bytes::{CaptureLocations, Regex};
use config::{Config, ConfiguredHIR};
use crlf::CRLFMatcher;
use error::Error;
use word::WordMatcher;
@@ -50,12 +49,9 @@ impl RegexMatcherBuilder {
if let Some(ref re) = fast_line_regex {
trace!("extracted fast line regex: {:?}", re);
}
let matcher = RegexMatcherImpl::new(&chir)?;
trace!("final regex: {:?}", matcher.regex().to_string());
Ok(RegexMatcher {
config: self.config.clone(),
matcher: matcher,
matcher: RegexMatcherImpl::new(&chir)?,
fast_line_regex: fast_line_regex,
non_matching_bytes: non_matching_bytes,
})
@@ -348,11 +344,6 @@ impl RegexMatcher {
enum RegexMatcherImpl {
/// The standard matcher used for all regular expressions.
Standard(StandardMatcher),
/// A matcher that strips `\r` from the end of matches.
///
/// This is only used when the CRLF hack is enabled and the regex is line
/// anchored at the end.
CRLF(CRLFMatcher),
/// A matcher that only matches at word boundaries. This transforms the
/// regex to `(^|\W)(...)($|\W)` instead of the more intuitive `\b(...)\b`.
/// Because of this, the WordMatcher provides its own implementation of
@@ -367,21 +358,10 @@ impl RegexMatcherImpl {
fn new(expr: &ConfiguredHIR) -> Result<RegexMatcherImpl, Error> {
if expr.config().word {
Ok(RegexMatcherImpl::Word(WordMatcher::new(expr)?))
} else if expr.needs_crlf_stripped() {
Ok(RegexMatcherImpl::CRLF(CRLFMatcher::new(expr)?))
} else {
Ok(RegexMatcherImpl::Standard(StandardMatcher::new(expr)?))
}
}
/// Return the underlying regex object used.
fn regex(&self) -> &Regex {
match *self {
RegexMatcherImpl::Word(ref x) => x.regex(),
RegexMatcherImpl::CRLF(ref x) => x.regex(),
RegexMatcherImpl::Standard(ref x) => &x.regex,
}
}
}
// This implementation just dispatches on the internal matcher impl except
@@ -399,7 +379,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find_at(haystack, at),
CRLF(ref m) => m.find_at(haystack, at),
Word(ref m) => m.find_at(haystack, at),
}
}
@@ -408,7 +387,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.new_captures(),
CRLF(ref m) => m.new_captures(),
Word(ref m) => m.new_captures(),
}
}
@@ -417,7 +395,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.capture_count(),
CRLF(ref m) => m.capture_count(),
Word(ref m) => m.capture_count(),
}
}
@@ -426,7 +403,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.capture_index(name),
CRLF(ref m) => m.capture_index(name),
Word(ref m) => m.capture_index(name),
}
}
@@ -435,7 +411,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find(haystack),
CRLF(ref m) => m.find(haystack),
Word(ref m) => m.find(haystack),
}
}
@@ -450,7 +425,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find_iter(haystack, matched),
CRLF(ref m) => m.find_iter(haystack, matched),
Word(ref m) => m.find_iter(haystack, matched),
}
}
@@ -465,7 +439,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.try_find_iter(haystack, matched),
CRLF(ref m) => m.try_find_iter(haystack, matched),
Word(ref m) => m.try_find_iter(haystack, matched),
}
}
@@ -478,7 +451,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures(haystack, caps),
CRLF(ref m) => m.captures(haystack, caps),
Word(ref m) => m.captures(haystack, caps),
}
}
@@ -494,7 +466,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures_iter(haystack, caps, matched),
CRLF(ref m) => m.captures_iter(haystack, caps, matched),
Word(ref m) => m.captures_iter(haystack, caps, matched),
}
}
@@ -510,7 +481,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.try_captures_iter(haystack, caps, matched),
CRLF(ref m) => m.try_captures_iter(haystack, caps, matched),
Word(ref m) => m.try_captures_iter(haystack, caps, matched),
}
}
@@ -524,7 +494,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures_at(haystack, at, caps),
CRLF(ref m) => m.captures_at(haystack, at, caps),
Word(ref m) => m.captures_at(haystack, at, caps),
}
}
@@ -540,7 +509,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.replace(haystack, dst, append),
CRLF(ref m) => m.replace(haystack, dst, append),
Word(ref m) => m.replace(haystack, dst, append),
}
}
@@ -559,9 +527,6 @@ impl Matcher for RegexMatcher {
Standard(ref m) => {
m.replace_with_captures(haystack, caps, dst, append)
}
CRLF(ref m) => {
m.replace_with_captures(haystack, caps, dst, append)
}
Word(ref m) => {
m.replace_with_captures(haystack, caps, dst, append)
}
@@ -572,7 +537,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.is_match(haystack),
CRLF(ref m) => m.is_match(haystack),
Word(ref m) => m.is_match(haystack),
}
}
@@ -585,7 +549,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.is_match_at(haystack, at),
CRLF(ref m) => m.is_match_at(haystack, at),
Word(ref m) => m.is_match_at(haystack, at),
}
}
@@ -597,7 +560,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.shortest_match(haystack),
CRLF(ref m) => m.shortest_match(haystack),
Word(ref m) => m.shortest_match(haystack),
}
}
@@ -610,7 +572,6 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.shortest_match_at(haystack, at),
CRLF(ref m) => m.shortest_match_at(haystack, at),
Word(ref m) => m.shortest_match_at(haystack, at),
}
}
@@ -751,9 +712,6 @@ pub struct RegexCaptures {
/// and the capturing groups must behave as if `(re)` is the `0`th capture
/// group.
offset: usize,
/// When enable, the end of a match has `\r` stripped from it, if one
/// exists.
strip_crlf: bool,
}
impl Captures for RegexCaptures {
@@ -762,25 +720,8 @@ impl Captures for RegexCaptures {
}
fn get(&self, i: usize) -> Option<Match> {
if !self.strip_crlf {
let actual = i.checked_add(self.offset).unwrap();
return self.locs.pos(actual).map(|(s, e)| Match::new(s, e));
}
// currently don't support capture offsetting with CRLF stripping
assert_eq!(self.offset, 0);
let m = match self.locs.pos(i).map(|(s, e)| Match::new(s, e)) {
None => return None,
Some(m) => m,
};
// If the end position of this match corresponds to the end position
// of the overall match, then we apply our CRLF stripping. Otherwise,
// we cannot assume stripping is correct.
if i == 0 || m.end() == self.locs.pos(0).unwrap().1 {
Some(m.with_end(m.end() - 1))
} else {
Some(m)
}
let actual = i.checked_add(self.offset).unwrap();
self.locs.pos(actual).map(|(s, e)| Match::new(s, e))
}
}
@@ -793,16 +734,12 @@ impl RegexCaptures {
locs: CaptureLocations,
offset: usize,
) -> RegexCaptures {
RegexCaptures { locs, offset, strip_crlf: false }
RegexCaptures { locs, offset }
}
pub(crate) fn locations(&mut self) -> &mut CaptureLocations {
&mut self.locs
}
pub(crate) fn strip_crlf(&mut self, yes: bool) {
self.strip_crlf = yes;
}
}
#[cfg(test)]

5
grep-regex/src/word.rs
View File

@@ -55,11 +55,6 @@ impl WordMatcher {
}
Ok(WordMatcher { regex, names, locs })
}
/// Return the underlying regex used by this matcher.
pub fn regex(&self) -> &Regex {
&self.regex
}
}
impl Matcher for WordMatcher {

11
grep-searcher/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-searcher"
version = "0.1.3" #:version
version = "0.1.1" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Fast line oriented regex searching as a library.
@@ -13,14 +13,19 @@ keywords = ["regex", "grep", "egrep", "search", "pattern"]
license = "Unlicense/MIT"
[dependencies]
bstr = { version = "0.1.2", default-features = false, features = ["std"] }
bytecount = "0.5"
encoding_rs = "0.8.14"
encoding_rs_io = "0.1.6"
encoding_rs_io = "0.1.3"
grep-matcher = { version = "0.1.1", path = "../grep-matcher" }
log = "0.4.5"
memmap = "0.7"
[dependencies.bstr]
version = "*"
path = "/home/andrew/rust/bstr"
default-features = false
features = ["std"]
[dev-dependencies]
grep-regex = { version = "0.1.1", path = "../grep-regex" }
regex = "1.1"

54
grep-searcher/src/line_buffer.rs
View File

@@ -253,13 +253,7 @@ impl<'b, R: io::Read> LineBufferReader<'b, R> {
}
/// Return the contents of this buffer.
pub fn buffer(&self) -> &[u8] {
self.line_buffer.buffer().as_bytes()
}
/// Return the underlying buffer as a byte string. Used for tests only.
#[cfg(test)]
fn bstr(&self) -> &BStr {
pub fn buffer(&self) -> &BStr {
self.line_buffer.buffer()
}
@@ -578,7 +572,7 @@ and exhibited clearly, with a label attached.\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\n");
assert_eq!(rdr.buffer(), "homer\nlisa\n");
assert_eq!(rdr.absolute_byte_offset(), 0);
rdr.consume(5);
assert_eq!(rdr.absolute_byte_offset(), 5);
@@ -586,7 +580,7 @@ and exhibited clearly, with a label attached.\
assert_eq!(rdr.absolute_byte_offset(), 11);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "maggie");
assert_eq!(rdr.buffer(), "maggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -601,7 +595,7 @@ and exhibited clearly, with a label attached.\
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n");
assert_eq!(rdr.buffer(), "homer\nlisa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -616,7 +610,7 @@ and exhibited clearly, with a label attached.\
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\n");
assert_eq!(rdr.buffer(), "\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -631,7 +625,7 @@ and exhibited clearly, with a label attached.\
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\n\n");
assert_eq!(rdr.buffer(), "\n\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -689,11 +683,11 @@ and exhibited clearly, with a label attached.\
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\n");
assert_eq!(rdr.buffer(), "homer\n");
rdr.consume_all();
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "lisa\n");
assert_eq!(rdr.buffer(), "lisa\n");
rdr.consume_all();
// This returns an error because while we have just enough room to
@@ -703,11 +697,11 @@ and exhibited clearly, with a label attached.\
assert!(rdr.fill().is_err());
// We can mush on though!
assert_eq!(rdr.bstr(), "m");
assert_eq!(rdr.buffer(), "m");
rdr.consume_all();
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "aggie");
assert_eq!(rdr.buffer(), "aggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -723,16 +717,16 @@ and exhibited clearly, with a label attached.\
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\n");
assert_eq!(rdr.buffer(), "homer\n");
rdr.consume_all();
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "lisa\n");
assert_eq!(rdr.buffer(), "lisa\n");
rdr.consume_all();
// We have just enough space.
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "maggie");
assert_eq!(rdr.buffer(), "maggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -748,7 +742,7 @@ and exhibited clearly, with a label attached.\
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(rdr.fill().is_err());
assert_eq!(rdr.bstr(), "");
assert_eq!(rdr.buffer(), "");
}
#[test]
@@ -760,7 +754,7 @@ and exhibited clearly, with a label attached.\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nli\x00sa\nmaggie\n");
assert_eq!(rdr.buffer(), "homer\nli\x00sa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -779,7 +773,7 @@ and exhibited clearly, with a label attached.\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nli");
assert_eq!(rdr.buffer(), "homer\nli");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -796,7 +790,7 @@ and exhibited clearly, with a label attached.\
let mut rdr = LineBufferReader::new(bytes.as_bytes(), &mut linebuf);
assert!(!rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "");
assert_eq!(rdr.buffer(), "");
assert_eq!(rdr.absolute_byte_offset(), 0);
assert_eq!(rdr.binary_byte_offset(), Some(0));
}
@@ -812,7 +806,7 @@ and exhibited clearly, with a label attached.\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n");
assert_eq!(rdr.buffer(), "homer\nlisa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -831,7 +825,7 @@ and exhibited clearly, with a label attached.\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie");
assert_eq!(rdr.buffer(), "homer\nlisa\nmaggie");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -849,7 +843,7 @@ and exhibited clearly, with a label attached.\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\
assert_eq!(rdr.buffer(), "\
For the Doctor Watsons of this world, as opposed to the Sherlock
Holmeses, s\
");
@@ -872,7 +866,7 @@ Holmeses, s\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nli\nsa\nmaggie\n");
assert_eq!(rdr.buffer(), "homer\nli\nsa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -891,7 +885,7 @@ Holmeses, s\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "\nhomer\nlisa\nmaggie\n");
assert_eq!(rdr.buffer(), "\nhomer\nlisa\nmaggie\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -910,7 +904,7 @@ Holmeses, s\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n\n");
assert_eq!(rdr.buffer(), "homer\nlisa\nmaggie\n\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());
@@ -929,7 +923,7 @@ Holmeses, s\
assert!(rdr.buffer().is_empty());
assert!(rdr.fill().unwrap());
assert_eq!(rdr.bstr(), "homer\nlisa\nmaggie\n\n");
assert_eq!(rdr.buffer(), "homer\nlisa\nmaggie\n\n");
rdr.consume_all();
assert!(!rdr.fill().unwrap());

57
grep-searcher/src/lines.rs
View File

@@ -2,7 +2,7 @@
A collection of routines for performing operations on lines.
*/
use bstr::B;
use bstr::{B, BStr};
use bytecount;
use grep_matcher::{LineTerminator, Match};
@@ -14,7 +14,7 @@ use grep_matcher::{LineTerminator, Match};
/// `'b` refers to the lifetime of the underlying bytes.
#[derive(Debug)]
pub struct LineIter<'b> {
bytes: &'b [u8],
bytes: &'b BStr,
stepper: LineStep,
}
@@ -23,7 +23,7 @@ impl<'b> LineIter<'b> {
/// are terminated by `line_term`.
pub fn new(line_term: u8, bytes: &'b [u8]) -> LineIter<'b> {
LineIter {
bytes: bytes,
bytes: B(bytes),
stepper: LineStep::new(line_term, 0, bytes.len()),
}
}
@@ -33,7 +33,7 @@ impl<'b> Iterator for LineIter<'b> {
type Item = &'b [u8];
fn next(&mut self) -> Option<&'b [u8]> {
self.stepper.next_match(self.bytes).map(|m| &self.bytes[m])
self.stepper.next_match(self.bytes).map(|m| self.bytes[m].as_bytes())
}
}
@@ -73,19 +73,19 @@ impl LineStep {
/// The range returned includes the line terminator. Ranges are always
/// non-empty.
pub fn next(&mut self, bytes: &[u8]) -> Option<(usize, usize)> {
self.next_impl(bytes)
self.next_impl(B(bytes))
}
/// Like next, but returns a `Match` instead of a tuple.
#[inline(always)]
pub(crate) fn next_match(&mut self, bytes: &[u8]) -> Option<Match> {
pub(crate) fn next_match(&mut self, bytes: &BStr) -> Option<Match> {
self.next_impl(bytes).map(|(s, e)| Match::new(s, e))
}
#[inline(always)]
fn next_impl(&mut self, mut bytes: &[u8]) -> Option<(usize, usize)> {
fn next_impl(&mut self, mut bytes: &BStr) -> Option<(usize, usize)> {
bytes = &bytes[..self.end];
match B(&bytes[self.pos..]).find_byte(self.line_term) {
match bytes[self.pos..].find_byte(self.line_term) {
None => {
if self.pos < bytes.len() {
let m = (self.pos, bytes.len());
@@ -109,15 +109,15 @@ impl LineStep {
}
/// Count the number of occurrences of `line_term` in `bytes`.
pub fn count(bytes: &[u8], line_term: u8) -> u64 {
bytecount::count(bytes, line_term) as u64
pub fn count(bytes: &BStr, line_term: u8) -> u64 {
bytecount::count(bytes.as_bytes(), line_term) as u64
}
/// Given a line that possibly ends with a terminator, return that line without
/// the terminator.
#[inline(always)]
pub fn without_terminator(bytes: &[u8], line_term: LineTerminator) -> &[u8] {
let line_term = line_term.as_bytes();
pub fn without_terminator(bytes: &BStr, line_term: LineTerminator) -> &BStr {
let line_term = BStr::new(line_term.as_bytes());
let start = bytes.len().saturating_sub(line_term.len());
if bytes.get(start..) == Some(line_term) {
return &bytes[..bytes.len() - line_term.len()];
@@ -131,18 +131,18 @@ pub fn without_terminator(bytes: &[u8], line_term: LineTerminator) -> &[u8] {
/// Line terminators are considered part of the line they terminate.
#[inline(always)]
pub fn locate(
bytes: &[u8],
bytes: &BStr,
line_term: u8,
range: Match,
) -> Match {
let line_start = B(&bytes[..range.start()])
let line_start = bytes[..range.start()]
.rfind_byte(line_term)
.map_or(0, |i| i + 1);
let line_end =
if range.end() > line_start && bytes[range.end() - 1] == line_term {
range.end()
} else {
B(&bytes[range.end()..])
bytes[range.end()..]
.find_byte(line_term)
.map_or(bytes.len(), |i| range.end() + i + 1)
};
@@ -157,7 +157,7 @@ pub fn locate(
///
/// If `bytes` ends with a line terminator, then the terminator itself is
/// considered part of the last line.
pub fn preceding(bytes: &[u8], line_term: u8, count: usize) -> usize {
pub fn preceding(bytes: &BStr, line_term: u8, count: usize) -> usize {
preceding_by_pos(bytes, bytes.len(), line_term, count)
}
@@ -171,7 +171,7 @@ pub fn preceding(bytes: &[u8], line_term: u8, count: usize) -> usize {
/// and `pos = 7`, `preceding(bytes, pos, b'\n', 0)` returns `4` (as does `pos
/// = 8`) and `preceding(bytes, pos, `b'\n', 1)` returns `0`.
fn preceding_by_pos(
bytes: &[u8],
bytes: &BStr,
mut pos: usize,
line_term: u8,
mut count: usize,
@@ -182,7 +182,7 @@ fn preceding_by_pos(
pos -= 1;
}
loop {
match B(&bytes[..pos]).rfind_byte(line_term) {
match bytes[..pos].rfind_byte(line_term) {
None => {
return 0;
}
@@ -203,7 +203,10 @@ fn preceding_by_pos(
mod tests {
use std::ops::Range;
use std::str;
use bstr::B;
use grep_matcher::Match;
use super::*;
const SHERLOCK: &'static str = "\
@@ -222,7 +225,7 @@ and exhibited clearly, with a label attached.\
fn lines(text: &str) -> Vec<&str> {
let mut results = vec![];
let mut it = LineStep::new(b'\n', 0, text.len());
while let Some(m) = it.next_match(text.as_bytes()) {
while let Some(m) = it.next_match(B(text)) {
results.push(&text[m]);
}
results
@@ -231,26 +234,26 @@ and exhibited clearly, with a label attached.\
fn line_ranges(text: &str) -> Vec<Range<usize>> {
let mut results = vec![];
let mut it = LineStep::new(b'\n', 0, text.len());
while let Some(m) = it.next_match(text.as_bytes()) {
while let Some(m) = it.next_match(B(text)) {
results.push(m.start()..m.end());
}
results
}
fn prev(text: &str, pos: usize, count: usize) -> usize {
preceding_by_pos(text.as_bytes(), pos, b'\n', count)
preceding_by_pos(B(text), pos, b'\n', count)
}
fn loc(text: &str, start: usize, end: usize) -> Match {
locate(text.as_bytes(), b'\n', Match::new(start, end))
locate(B(text), b'\n', Match::new(start, end))
}
#[test]
fn line_count() {
assert_eq!(0, count(b"", b'\n'));
assert_eq!(1, count(b"\n", b'\n'));
assert_eq!(2, count(b"\n\n", b'\n'));
assert_eq!(2, count(b"a\nb\nc", b'\n'));
assert_eq!(0, count(B(""), b'\n'));
assert_eq!(1, count(B("\n"), b'\n'));
assert_eq!(2, count(B("\n\n"), b'\n'));
assert_eq!(2, count(B("a\nb\nc"), b'\n'));
}
#[test]
@@ -333,7 +336,7 @@ and exhibited clearly, with a label attached.\
#[test]
fn preceding_lines_doc() {
// These are the examples mentions in the documentation of `preceding`.
let bytes = b"abc\nxyz\n";
let bytes = B("abc\nxyz\n");
assert_eq!(4, preceding_by_pos(bytes, 7, b'\n', 0));
assert_eq!(4, preceding_by_pos(bytes, 8, b'\n', 0));
assert_eq!(0, preceding_by_pos(bytes, 7, b'\n', 1));

61
grep-searcher/src/searcher/core.rs
View File

@@ -1,6 +1,6 @@
use std::cmp;
use bstr::B;
use bstr::BStr;
use grep_matcher::{LineMatchKind, Matcher};
use lines::{self, LineStep};
@@ -84,7 +84,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
pub fn matched(
&mut self,
buf: &[u8],
buf: &BStr,
range: &Range,
) -> Result<bool, S::Error> {
self.sink_matched(buf, range)
@@ -107,7 +107,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
})
}
pub fn match_by_line(&mut self, buf: &[u8]) -> Result<bool, S::Error> {
pub fn match_by_line(&mut self, buf: &BStr) -> Result<bool, S::Error> {
if self.is_line_by_line_fast() {
self.match_by_line_fast(buf)
} else {
@@ -115,7 +115,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
}
}
pub fn roll(&mut self, buf: &[u8]) -> usize {
pub fn roll(&mut self, buf: &BStr) -> usize {
let consumed =
if self.config.max_context() == 0 {
buf.len()
@@ -141,7 +141,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
consumed
}
pub fn detect_binary(&mut self, buf: &[u8], range: &Range) -> bool {
pub fn detect_binary(&mut self, buf: &BStr, range: &Range) -> bool {
if self.binary_byte_offset.is_some() {
return true;
}
@@ -149,7 +149,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
BinaryDetection::Quit(b) => b,
_ => return false,
};
if let Some(i) = B(&buf[*range]).find_byte(binary_byte) {
if let Some(i) = buf[*range].find_byte(binary_byte) {
self.binary_byte_offset = Some(range.start() + i);
true
} else {
@@ -159,7 +159,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
pub fn before_context_by_line(
&mut self,
buf: &[u8],
buf: &BStr,
upto: usize,
) -> Result<bool, S::Error> {
if self.config.before_context == 0 {
@@ -194,7 +194,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
pub fn after_context_by_line(
&mut self,
buf: &[u8],
buf: &BStr,
upto: usize,
) -> Result<bool, S::Error> {
if self.after_context_left == 0 {
@@ -219,7 +219,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
pub fn other_context_by_line(
&mut self,
buf: &[u8],
buf: &BStr,
upto: usize,
) -> Result<bool, S::Error> {
let range = Range::new(self.last_line_visited, upto);
@@ -236,7 +236,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
Ok(true)
}
fn match_by_line_slow(&mut self, buf: &[u8]) -> Result<bool, S::Error> {
fn match_by_line_slow(&mut self, buf: &BStr) -> Result<bool, S::Error> {
debug_assert!(!self.searcher.multi_line_with_matcher(&self.matcher));
let range = Range::new(self.pos(), buf.len());
@@ -255,7 +255,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
&buf[line],
self.config.line_term,
);
match self.matcher.shortest_match(slice) {
match self.matcher.shortest_match(slice.as_bytes()) {
Err(err) => return Err(S::Error::error_message(err)),
Ok(result) => result.is_some(),
}
@@ -281,7 +281,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
Ok(true)
}
fn match_by_line_fast(&mut self, buf: &[u8]) -> Result<bool, S::Error> {
fn match_by_line_fast(&mut self, buf: &BStr) -> Result<bool, S::Error> {
debug_assert!(!self.config.passthru);
while !buf[self.pos()..].is_empty() {
@@ -316,7 +316,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
#[inline(always)]
fn match_by_line_fast_invert(
&mut self,
buf: &[u8],
buf: &BStr,
) -> Result<bool, S::Error> {
assert!(self.config.invert_match);
@@ -357,14 +357,14 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
#[inline(always)]
fn find_by_line_fast(
&self,
buf: &[u8],
buf: &BStr,
) -> Result<Option<Range>, S::Error> {
debug_assert!(!self.searcher.multi_line_with_matcher(&self.matcher));
debug_assert!(self.is_line_by_line_fast());
let mut pos = self.pos();
while !buf[pos..].is_empty() {
match self.matcher.find_candidate_line(&buf[pos..]) {
match self.matcher.find_candidate_line(buf[pos..].as_bytes()) {
Err(err) => return Err(S::Error::error_message(err)),
Ok(None) => return Ok(None),
Ok(Some(LineMatchKind::Confirmed(i))) => {
@@ -396,7 +396,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
&buf[line],
self.config.line_term,
);
match self.matcher.is_match(slice) {
match self.matcher.is_match(slice.as_bytes()) {
Err(err) => return Err(S::Error::error_message(err)),
Ok(true) => return Ok(Some(line)),
Ok(false) => {
@@ -413,7 +413,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
#[inline(always)]
fn sink_matched(
&mut self,
buf: &[u8],
buf: &BStr,
range: &Range,
) -> Result<bool, S::Error> {
if self.binary && self.detect_binary(buf, range) {
@@ -424,12 +424,21 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
}
self.count_lines(buf, range.start());
let offset = self.absolute_byte_offset + range.start() as u64;
let linebuf = &buf[*range];
let linebuf =
if self.config.line_term.is_crlf() {
// Normally, a line terminator is never part of a match, but
// if the line terminator is CRLF, then it's possible for `\r`
// to end up in the match, which we generally don't want. So
// we strip it here.
lines::without_terminator(&buf[*range], self.config.line_term)
} else {
&buf[*range]
};
let keepgoing = self.sink.matched(
&self.searcher,
&SinkMatch {
line_term: self.config.line_term,
bytes: linebuf,
bytes: linebuf.as_bytes(),
absolute_byte_offset: offset,
line_number: self.line_number,
},
@@ -445,7 +454,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
fn sink_before_context(
&mut self,
buf: &[u8],
buf: &BStr,
range: &Range,
) -> Result<bool, S::Error> {
if self.binary && self.detect_binary(buf, range) {
@@ -457,7 +466,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
&self.searcher,
&SinkContext {
line_term: self.config.line_term,
bytes: &buf[*range],
bytes: buf[*range].as_bytes(),
kind: SinkContextKind::Before,
absolute_byte_offset: offset,
line_number: self.line_number,
@@ -473,7 +482,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
fn sink_after_context(
&mut self,
buf: &[u8],
buf: &BStr,
range: &Range,
) -> Result<bool, S::Error> {
assert!(self.after_context_left >= 1);
@@ -487,7 +496,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
&self.searcher,
&SinkContext {
line_term: self.config.line_term,
bytes: &buf[*range],
bytes: buf[*range].as_bytes(),
kind: SinkContextKind::After,
absolute_byte_offset: offset,
line_number: self.line_number,
@@ -504,7 +513,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
fn sink_other_context(
&mut self,
buf: &[u8],
buf: &BStr,
range: &Range,
) -> Result<bool, S::Error> {
if self.binary && self.detect_binary(buf, range) {
@@ -516,7 +525,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
&self.searcher,
&SinkContext {
line_term: self.config.line_term,
bytes: &buf[*range],
bytes: buf[*range].as_bytes(),
kind: SinkContextKind::Other,
absolute_byte_offset: offset,
line_number: self.line_number,
@@ -546,7 +555,7 @@ impl<'s, M: Matcher, S: Sink> Core<'s, M, S> {
}
}
fn count_lines(&mut self, buf: &[u8], upto: usize) {
fn count_lines(&mut self, buf: &BStr, upto: usize) {
if let Some(ref mut line_number) = self.line_number {
if self.last_line_counted >= upto {
return;

13
grep-searcher/src/searcher/glue.rs
View File

@@ -1,7 +1,9 @@
use std::cmp;
use std::io;
use bstr::BStr;
use grep_matcher::Matcher;
use lines::{self, LineStep};
use line_buffer::{DEFAULT_BUFFER_CAPACITY, LineBufferReader};
use sink::{Sink, SinkError};
@@ -77,14 +79,14 @@ where M: Matcher,
pub struct SliceByLine<'s, M: 's, S> {
config: &'s Config,
core: Core<'s, M, S>,
slice: &'s [u8],
slice: &'s BStr,
}
impl<'s, M: Matcher, S: Sink> SliceByLine<'s, M, S> {
pub fn new(
searcher: &'s Searcher,
matcher: M,
slice: &'s [u8],
slice: &'s BStr,
write_to: S,
) -> SliceByLine<'s, M, S> {
debug_assert!(!searcher.multi_line_with_matcher(&matcher));
@@ -127,7 +129,7 @@ impl<'s, M: Matcher, S: Sink> SliceByLine<'s, M, S> {
pub struct MultiLine<'s, M: 's, S> {
config: &'s Config,
core: Core<'s, M, S>,
slice: &'s [u8],
slice: &'s BStr,
last_match: Option<Range>,
}
@@ -135,7 +137,7 @@ impl<'s, M: Matcher, S: Sink> MultiLine<'s, M, S> {
pub fn new(
searcher: &'s Searcher,
matcher: M,
slice: &'s [u8],
slice: &'s BStr,
write_to: S,
) -> MultiLine<'s, M, S> {
debug_assert!(searcher.multi_line_with_matcher(&matcher));
@@ -306,7 +308,8 @@ impl<'s, M: Matcher, S: Sink> MultiLine<'s, M, S> {
}
fn find(&mut self) -> Result<Option<Range>, S::Error> {
match self.core.matcher().find(&self.slice[self.core.pos()..]) {
let haystack = &self.slice[self.core.pos()..];
match self.core.matcher().find(haystack.as_bytes()) {
Err(err) => Err(S::Error::error_message(err)),
Ok(None) => Ok(None),
Ok(Some(m)) => Ok(Some(m.offset(self.core.pos()))),

67
grep-searcher/src/searcher/mod.rs
View File

@@ -5,6 +5,7 @@ use std::fs::File;
use std::io::{self, Read};
use std::path::Path;
use bstr::{B, BStr, BString};
use encoding_rs;
use encoding_rs_io::DecodeReaderBytesBuilder;
use grep_matcher::{LineTerminator, Match, Matcher};
@@ -155,8 +156,6 @@ pub struct Config {
/// An encoding that, when present, causes the searcher to transcode all
/// input from the encoding to UTF-8.
encoding: Option<Encoding>,
/// Whether to do automatic transcoding based on a BOM or not.
bom_sniffing: bool,
}
impl Default for Config {
@@ -173,7 +172,6 @@ impl Default for Config {
binary: BinaryDetection::default(),
multi_line: false,
encoding: None,
bom_sniffing: true,
}
}
}
@@ -306,21 +304,17 @@ impl SearcherBuilder {
config.before_context = 0;
config.after_context = 0;
}
let mut decode_builder = DecodeReaderBytesBuilder::new();
decode_builder
.encoding(self.config.encoding.as_ref().map(|e| e.0))
.utf8_passthru(true)
.strip_bom(self.config.bom_sniffing)
.bom_override(true)
.bom_sniffing(self.config.bom_sniffing);
.bom_override(true);
Searcher {
config: config,
decode_builder: decode_builder,
decode_buffer: RefCell::new(vec![0; 8 * (1<<10)]),
decode_buffer: RefCell::new(BString::from(vec![0; 8 * (1<<10)])),
line_buffer: RefCell::new(self.config.line_buffer()),
multi_line_buffer: RefCell::new(vec![]),
multi_line_buffer: RefCell::new(BString::new()),
}
}
@@ -512,13 +506,12 @@ impl SearcherBuilder {
/// transcoding process encounters an error, then bytes are replaced with
/// the Unicode replacement codepoint.
///
/// When no encoding is specified (the default), then BOM sniffing is
/// used (if it's enabled, which it is, by default) to determine whether
/// the source data is UTF-8 or UTF-16, and transcoding will be performed
/// automatically. If no BOM could be found, then the source data is
/// searched _as if_ it were UTF-8. However, so long as the source data is
/// at least ASCII compatible, then it is possible for a search to produce
/// useful results.
/// When no encoding is specified (the default), then BOM sniffing is used
/// to determine whether the source data is UTF-8 or UTF-16, and
/// transcoding will be performed automatically. If no BOM could be found,
/// then the source data is searched _as if_ it were UTF-8. However, so
/// long as the source data is at least ASCII compatible, then it is
/// possible for a search to produce useful results.
pub fn encoding(
&mut self,
encoding: Option<Encoding>,
@@ -526,23 +519,6 @@ impl SearcherBuilder {
self.config.encoding = encoding;
self
}
/// Enable automatic transcoding based on BOM sniffing.
///
/// When this is enabled and an explicit encoding is not set, then this
/// searcher will try to detect the encoding of the bytes being searched
/// by sniffing its byte-order mark (BOM). In particular, when this is
/// enabled, UTF-16 encoded files will be searched seamlessly.
///
/// When this is disabled and if an explicit encoding is not set, then
/// the bytes from the source stream will be passed through unchanged,
/// including its BOM, if one is present.
///
/// This is enabled by default.
pub fn bom_sniffing(&mut self, yes: bool) -> &mut SearcherBuilder {
self.config.bom_sniffing = yes;
self
}
}
/// A searcher executes searches over a haystack and writes results to a caller
@@ -568,7 +544,7 @@ pub struct Searcher {
/// through the underlying bytes with no additional overhead.
decode_builder: DecodeReaderBytesBuilder,
/// A buffer that is used for transcoding scratch space.
decode_buffer: RefCell<Vec<u8>>,
decode_buffer: RefCell<BString>,
/// A line buffer for use in line oriented searching.
///
/// We wrap it in a RefCell to permit lending out borrows of `Searcher`
@@ -580,7 +556,7 @@ pub struct Searcher {
/// multi line search. In particular, multi line searches cannot be
/// performed incrementally, and need the entire haystack in memory at
/// once.
multi_line_buffer: RefCell<Vec<u8>>,
multi_line_buffer: RefCell<BString>,
}
impl Searcher {
@@ -691,7 +667,7 @@ impl Searcher {
let mut decode_buffer = self.decode_buffer.borrow_mut();
let read_from = self.decode_builder
.build_with_buffer(read_from, &mut *decode_buffer)
.build_with_buffer(read_from, decode_buffer.as_mut_vec())
.map_err(S::Error::error_io)?;
if self.multi_line_with_matcher(&matcher) {
@@ -723,12 +699,13 @@ impl Searcher {
where M: Matcher,
S: Sink,
{
let slice = B(slice);
self.check_config(&matcher).map_err(S::Error::error_config)?;
// We can search the slice directly, unless we need to do transcoding.
if self.slice_needs_transcoding(slice) {
trace!("slice reader: needs transcoding, using generic reader");
return self.search_reader(matcher, slice, write_to);
return self.search_reader(matcher, slice.as_bytes(), write_to);
}
if self.multi_line_with_matcher(&matcher) {
trace!("slice reader: searching via multiline strategy");
@@ -761,9 +738,8 @@ impl Searcher {
}
/// Returns true if and only if the given slice needs to be transcoded.
fn slice_needs_transcoding(&self, slice: &[u8]) -> bool {
self.config.encoding.is_some()
|| (self.config.bom_sniffing && slice_has_utf16_bom(slice))
fn slice_needs_transcoding(&self, slice: &BStr) -> bool {
self.config.encoding.is_some() || slice_has_utf16_bom(slice)
}
}
@@ -877,7 +853,9 @@ impl Searcher {
.map(|m| m.len() as usize + 1)
.unwrap_or(0);
buf.reserve(cap);
read_from.read_to_end(&mut *buf).map_err(S::Error::error_io)?;
read_from
.read_to_end(buf.as_mut_vec())
.map_err(S::Error::error_io)?;
return Ok(());
}
self.fill_multi_line_buffer_from_reader::<_, S>(read_from)
@@ -894,6 +872,7 @@ impl Searcher {
assert!(self.config.multi_line);
let mut buf = self.multi_line_buffer.borrow_mut();
let buf = buf.as_mut_vec();
buf.clear();
// If we don't have a heap limit, then we can defer to std's
@@ -945,8 +924,8 @@ impl Searcher {
///
/// This is used by the searcher to determine if a transcoder is necessary.
/// Otherwise, it is advantageous to search the slice directly.
fn slice_has_utf16_bom(slice: &[u8]) -> bool {
let enc = match encoding_rs::Encoding::for_bom(slice) {
fn slice_has_utf16_bom(slice: &BStr) -> bool {
let enc = match encoding_rs::Encoding::for_bom(slice.as_bytes()) {
None => return false,
Some((enc, _)) => enc,
};

1
grep-searcher/src/testutil.rs
View File

@@ -96,7 +96,6 @@ impl Matcher for RegexMatcher {
// line.
let i = B(haystack)
.find_byte(self.line_term.unwrap().as_byte())
.map(|i| i)
.unwrap_or(haystack.len() - 1);
Ok(Some(LineMatchKind::Candidate(i)))
} else {

7
grep/Cargo.toml
View File

@@ -21,9 +21,16 @@ grep-regex = { version = "0.1.1", path = "../grep-regex" }
grep-searcher = { version = "0.1.1", path = "../grep-searcher" }
[dev-dependencies]
atty = "0.2.11"
regex = "1.1"
termcolor = "1.0.4"
walkdir = "2.2.7"
[dev-dependencies.clap]
version = "2.32.0"
default-features = false
features = ["suggestions"]
[features]
simd-accel = ["grep-searcher/simd-accel"]
pcre2 = ["grep-pcre2"]

2
ignore/Cargo.toml
View File

@@ -29,7 +29,7 @@ thread_local = "0.3.6"
walkdir = "2.2.7"
[target.'cfg(windows)'.dependencies.winapi-util]
version = "0.1.2"
version = "0.1.1"
[dev-dependencies]
tempfile = "3.0.5"

77
ignore/src/dir.rs
View File

@@ -22,7 +22,6 @@ use gitignore::{self, Gitignore, GitignoreBuilder};
use pathutil::{is_hidden, strip_prefix};
use overrides::{self, Override};
use types::{self, Types};
use walk::DirEntry;
use {Error, Match, PartialErrorBuilder};
/// IgnoreMatch represents information about where a match came from when using
@@ -74,8 +73,6 @@ struct IgnoreOptions {
git_ignore: bool,
/// Whether to read .git/info/exclude files.
git_exclude: bool,
/// Whether to ignore files case insensitively
ignore_case_insensitive: bool,
}
/// Ignore is a matcher useful for recursively walking one or more directories.
@@ -228,11 +225,7 @@ impl Ignore {
Gitignore::empty()
} else {
let (m, err) =
create_gitignore(
&dir,
&self.0.custom_ignore_filenames,
self.0.opts.ignore_case_insensitive,
);
create_gitignore(&dir, &self.0.custom_ignore_filenames);
errs.maybe_push(err);
m
};
@@ -240,12 +233,7 @@ impl Ignore {
if !self.0.opts.ignore {
Gitignore::empty()
} else {
let (m, err) =
create_gitignore(
&dir,
&[".ignore"],
self.0.opts.ignore_case_insensitive,
);
let (m, err) = create_gitignore(&dir, &[".ignore"]);
errs.maybe_push(err);
m
};
@@ -253,12 +241,7 @@ impl Ignore {
if !self.0.opts.git_ignore {
Gitignore::empty()
} else {
let (m, err) =
create_gitignore(
&dir,
&[".gitignore"],
self.0.opts.ignore_case_insensitive,
);
let (m, err) = create_gitignore(&dir, &[".gitignore"]);
errs.maybe_push(err);
m
};
@@ -266,12 +249,7 @@ impl Ignore {
if !self.0.opts.git_exclude {
Gitignore::empty()
} else {
let (m, err) =
create_gitignore(
&dir,
&[".git/info/exclude"],
self.0.opts.ignore_case_insensitive,
);
let (m, err) = create_gitignore(&dir, &[".git/info/exclude"]);
errs.maybe_push(err);
m
};
@@ -307,23 +285,11 @@ impl Ignore {
|| has_explicit_ignores
}
/// Like `matched`, but works with a directory entry instead.
pub fn matched_dir_entry<'a>(
&'a self,
dent: &DirEntry,
) -> Match<IgnoreMatch<'a>> {
let m = self.matched(dent.path(), dent.is_dir());
if m.is_none() && self.0.opts.hidden && is_hidden(dent) {
return Match::Ignore(IgnoreMatch::hidden());
}
m
}
/// Returns a match indicating whether the given file path should be
/// ignored or not.
///
/// The match contains information about its origin.
fn matched<'a, P: AsRef<Path>>(
pub fn matched<'a, P: AsRef<Path>>(
&'a self,
path: P,
is_dir: bool,
@@ -364,6 +330,9 @@ impl Ignore {
whitelisted = mat;
}
}
if whitelisted.is_none() && self.0.opts.hidden && is_hidden(path) {
return Match::Ignore(IgnoreMatch::hidden());
}
whitelisted
}
@@ -514,7 +483,6 @@ impl IgnoreBuilder {
git_global: true,
git_ignore: true,
git_exclude: true,
ignore_case_insensitive: false,
},
}
}
@@ -528,11 +496,7 @@ impl IgnoreBuilder {
if !self.opts.git_global {
Gitignore::empty()
} else {
let mut builder = GitignoreBuilder::new("");
builder
.case_insensitive(self.opts.ignore_case_insensitive)
.unwrap();
let (gi, err) = builder.build_global();
let (gi, err) = Gitignore::global();
if let Some(err) = err {
debug!("{}", err);
}
@@ -663,17 +627,6 @@ impl IgnoreBuilder {
self.opts.git_exclude = yes;
self
}
/// Process ignore files case insensitively
///
/// This is disabled by default.
pub fn ignore_case_insensitive(
&mut self,
yes: bool,
) -> &mut IgnoreBuilder {
self.opts.ignore_case_insensitive = yes;
self
}
}
/// Creates a new gitignore matcher for the directory given.
@@ -685,11 +638,9 @@ impl IgnoreBuilder {
pub fn create_gitignore<T: AsRef<OsStr>>(
dir: &Path,
names: &[T],
case_insensitive: bool,
) -> (Gitignore, Option<Error>) {
let mut builder = GitignoreBuilder::new(dir);
let mut errs = PartialErrorBuilder::default();
builder.case_insensitive(case_insensitive).unwrap();
for name in names {
let gipath = dir.join(name.as_ref());
errs.maybe_push_ignore_io(builder.add(gipath));
@@ -879,7 +830,7 @@ mod tests {
#[test]
fn errored() {
let td = tmpdir("ignore-test-");
wfile(td.path().join(".gitignore"), "{foo");
wfile(td.path().join(".gitignore"), "f**oo");
let (_, err) = IgnoreBuilder::new().build().add_child(td.path());
assert!(err.is_some());
@@ -888,8 +839,8 @@ mod tests {
#[test]
fn errored_both() {
let td = tmpdir("ignore-test-");
wfile(td.path().join(".gitignore"), "{foo");
wfile(td.path().join(".ignore"), "{bar");
wfile(td.path().join(".gitignore"), "f**oo");
wfile(td.path().join(".ignore"), "fo**o");
let (_, err) = IgnoreBuilder::new().build().add_child(td.path());
assert_eq!(2, partial(err.expect("an error")).len());
@@ -899,7 +850,7 @@ mod tests {
fn errored_partial() {
let td = tmpdir("ignore-test-");
mkdirp(td.path().join(".git"));
wfile(td.path().join(".gitignore"), "{foo\nbar");
wfile(td.path().join(".gitignore"), "f**oo\nbar");
let (ig, err) = IgnoreBuilder::new().build().add_child(td.path());
assert!(err.is_some());
@@ -909,7 +860,7 @@ mod tests {
#[test]
fn errored_partial_and_ignore() {
let td = tmpdir("ignore-test-");
wfile(td.path().join(".gitignore"), "{foo\nbar");
wfile(td.path().join(".gitignore"), "f**oo\nbar");
wfile(td.path().join(".ignore"), "!bar");
let (ig, err) = IgnoreBuilder::new().build().add_child(td.path());

73
ignore/src/gitignore.rs
View File

@@ -69,7 +69,8 @@ impl Glob {
/// Returns true if and only if this glob has a `**/` prefix.
fn has_doublestar_prefix(&self) -> bool {
self.actual.starts_with("**/") || self.actual == "**"
self.actual.starts_with("**/")
|| (self.actual == "**" && self.is_only_dir)
}
}
@@ -126,7 +127,16 @@ impl Gitignore {
/// `$XDG_CONFIG_HOME/git/ignore` is read. If `$XDG_CONFIG_HOME` is not
/// set or is empty, then `$HOME/.config/git/ignore` is used instead.
pub fn global() -> (Gitignore, Option<Error>) {
GitignoreBuilder::new("").build_global()
match gitconfig_excludes_path() {
None => (Gitignore::empty(), None),
Some(path) => {
if !path.is_file() {
(Gitignore::empty(), None)
} else {
Gitignore::new(path)
}
}
}
}
/// Creates a new empty gitignore matcher that never matches anything.
@@ -349,36 +359,6 @@ impl GitignoreBuilder {
})
}
/// Build a global gitignore matcher using the configuration in this
/// builder.
///
/// This consumes ownership of the builder unlike `build` because it
/// must mutate the builder to add the global gitignore globs.
///
/// Note that this ignores the path given to this builder's constructor
/// and instead derives the path automatically from git's global
/// configuration.
pub fn build_global(mut self) -> (Gitignore, Option<Error>) {
match gitconfig_excludes_path() {
None => (Gitignore::empty(), None),
Some(path) => {
if !path.is_file() {
(Gitignore::empty(), None)
} else {
let mut errs = PartialErrorBuilder::default();
errs.maybe_push_ignore_io(self.add(path));
match self.build() {
Ok(gi) => (gi, errs.into_error_option()),
Err(err) => {
errs.push(err);
(Gitignore::empty(), errs.into_error_option())
}
}
}
}
}
}
/// Add each glob from the file path given.
///
/// The file given should be formatted as a `gitignore` file.
@@ -457,6 +437,7 @@ impl GitignoreBuilder {
is_whitelist: false,
is_only_dir: false,
};
let mut literal_separator = false;
let mut is_absolute = false;
if line.starts_with("\\!") || line.starts_with("\\#") {
line = &line[1..];
@@ -471,6 +452,7 @@ impl GitignoreBuilder {
// then the glob can only match the beginning of a path
// (relative to the location of gitignore). We achieve this by
// simply banning wildcards from matching /.
literal_separator = true;
line = &line[1..];
is_absolute = true;
}
@@ -483,11 +465,16 @@ impl GitignoreBuilder {
line = &line[..i];
}
}
// If there is a literal slash, then we note that so that globbing
// doesn't let wildcards match slashes.
glob.actual = line.to_string();
// If there is a literal slash, then this is a glob that must match the
// entire path name. Otherwise, we should let it match anywhere, so use
// a **/ prefix.
if !is_absolute && !line.chars().any(|c| c == '/') {
if is_absolute || line.chars().any(|c| c == '/') {
literal_separator = true;
}
// If there was a slash, then this is a glob that must match the entire
// path name. Otherwise, we should let it match anywhere, so use a **/
// prefix.
if !literal_separator {
// ... but only if we don't already have a **/ prefix.
if !glob.has_doublestar_prefix() {
glob.actual = format!("**/{}", glob.actual);
@@ -501,7 +488,7 @@ impl GitignoreBuilder {
}
let parsed =
GlobBuilder::new(&glob.actual)
.literal_separator(true)
.literal_separator(literal_separator)
.case_insensitive(self.case_insensitive)
.backslash_escape(true)
.build()
@@ -518,16 +505,12 @@ impl GitignoreBuilder {
/// Toggle whether the globs should be matched case insensitively or not.
///
/// When this option is changed, only globs added after the change will be
/// affected.
/// When this option is changed, only globs added after the change will be affected.
///
/// This is disabled by default.
pub fn case_insensitive(
&mut self,
yes: bool,
&mut self, yes: bool
) -> Result<&mut GitignoreBuilder, Error> {
// TODO: This should not return a `Result`. Fix this in the next semver
// release.
self.case_insensitive = yes;
Ok(self)
}
@@ -708,9 +691,6 @@ mod tests {
ignored!(ig39, ROOT, "\\?", "?");
ignored!(ig40, ROOT, "\\*", "*");
ignored!(ig41, ROOT, "\\a", "a");
ignored!(ig42, ROOT, "s*.rs", "sfoo.rs");
ignored!(ig43, ROOT, "**", "foo.rs");
ignored!(ig44, ROOT, "**/**/*", "a/foo.rs");
not_ignored!(ignot1, ROOT, "amonths", "months");
not_ignored!(ignot2, ROOT, "monthsa", "months");
@@ -732,7 +712,6 @@ mod tests {
not_ignored!(ignot16, ROOT, "*\n!**/", "foo", true);
not_ignored!(ignot17, ROOT, "src/*.rs", "src/grep/src/main.rs");
not_ignored!(ignot18, ROOT, "path1/*", "path2/path1/foo");
not_ignored!(ignot19, ROOT, "s*.rs", "src/foo.rs");
fn bytes(s: &str) -> Vec<u8> {
s.to_string().into_bytes()

7
ignore/src/overrides.rs
View File

@@ -139,16 +139,13 @@ impl OverrideBuilder {
}
/// Toggle whether the globs should be matched case insensitively or not.
///
///
/// When this option is changed, only globs added after the change will be affected.
///
/// This is disabled by default.
pub fn case_insensitive(
&mut self,
yes: bool,
&mut self, yes: bool
) -> Result<&mut OverrideBuilder, Error> {
// TODO: This should not return a `Result`. Fix this in the next semver
// release.
self.builder.case_insensitive(yes)?;
Ok(self)
}

48
ignore/src/pathutil.rs
View File

@@ -1,56 +1,22 @@
use std::ffi::OsStr;
use std::path::Path;
use walk::DirEntry;
/// Returns true if and only if this entry is considered to be hidden.
///
/// This only returns true if the base name of the path starts with a `.`.
///
/// On Unix, this implements a more optimized check.
/// Returns true if and only if this file path is considered to be hidden.
#[cfg(unix)]
pub fn is_hidden(dent: &DirEntry) -> bool {
pub fn is_hidden<P: AsRef<Path>>(path: P) -> bool {
use std::os::unix::ffi::OsStrExt;
if let Some(name) = file_name(dent.path()) {
if let Some(name) = file_name(path.as_ref()) {
name.as_bytes().get(0) == Some(&b'.')
} else {
false
}
}
/// Returns true if and only if this entry is considered to be hidden.
///
/// On Windows, this returns true if one of the following is true:
///
/// * The base name of the path starts with a `.`.
/// * The file attributes have the `HIDDEN` property set.
#[cfg(windows)]
pub fn is_hidden(dent: &DirEntry) -> bool {
use std::os::windows::fs::MetadataExt;
use winapi_util::file;
// This looks like we're doing an extra stat call, but on Windows, the
// directory traverser reuses the metadata retrieved from each directory
// entry and stores it on the DirEntry itself. So this is "free."
if let Ok(md) = dent.metadata() {
if file::is_hidden(md.file_attributes() as u64) {
return true;
}
}
if let Some(name) = file_name(dent.path()) {
name.to_str().map(|s| s.starts_with(".")).unwrap_or(false)
} else {
false
}
}
/// Returns true if and only if this entry is considered to be hidden.
///
/// This only returns true if the base name of the path starts with a `.`.
#[cfg(not(any(unix, windows)))]
pub fn is_hidden(dent: &DirEntry) -> bool {
if let Some(name) = file_name(dent.path()) {
/// Returns true if and only if this file path is considered to be hidden.
#[cfg(not(unix))]
pub fn is_hidden<P: AsRef<Path>>(path: P) -> bool {
if let Some(name) = file_name(path.as_ref()) {
name.to_str().map(|s| s.starts_with(".")).unwrap_or(false)
} else {
false

23
ignore/src/types.rs
View File

@@ -108,9 +108,8 @@ const DEFAULT_TYPES: &'static [(&'static str, &'static [&'static str])] = &[
("awk", &["*.awk"]),
("bazel", &["*.bzl", "WORKSPACE", "BUILD", "BUILD.bazel"]),
("bitbake", &["*.bb", "*.bbappend", "*.bbclass", "*.conf", "*.inc"]),
("brotli", &["*.br"]),
("buildstream", &["*.bst"]),
("bzip2", &["*.bz2", "*.tbz2"]),
("bzip2", &["*.bz2"]),
("c", &["*.c", "*.h", "*.H", "*.cats"]),
("cabal", &["*.cabal"]),
("cbor", &["*.cbor"]),
@@ -148,7 +147,7 @@ const DEFAULT_TYPES: &'static [(&'static str, &'static [&'static str])] = &[
("fsharp", &["*.fs", "*.fsx", "*.fsi"]),
("gn", &["*.gn", "*.gni"]),
("go", &["*.go"]),
("gzip", &["*.gz", "*.tgz"]),
("gzip", &["*.gz"]),
("groovy", &["*.groovy", "*.gradle"]),
("h", &["*.h", "*.hpp"]),
("hbs", &["*.hbs"]),
@@ -283,7 +282,7 @@ const DEFAULT_TYPES: &'static [(&'static str, &'static [&'static str])] = &[
]),
("taskpaper", &["*.taskpaper"]),
("tcl", &["*.tcl"]),
("tex", &["*.tex", "*.ltx", "*.cls", "*.sty", "*.bib", "*.dtx", "*.ins"]),
("tex", &["*.tex", "*.ltx", "*.cls", "*.sty", "*.bib"]),
("textile", &["*.textile"]),
("thrift", &["*.thrift"]),
("tf", &["*.tf"]),
@@ -300,10 +299,9 @@ const DEFAULT_TYPES: &'static [(&'static str, &'static [&'static str])] = &[
("wiki", &["*.mediawiki", "*.wiki"]),
("webidl", &["*.idl", "*.webidl", "*.widl"]),
("xml", &["*.xml", "*.xml.dist"]),
("xz", &["*.xz", "*.txz"]),
("xz", &["*.xz"]),
("yacc", &["*.y"]),
("yaml", &["*.yaml", "*.yml"]),
("zig", &["*.zig"]),
("zsh", &[
".zshenv", "zshenv",
".zlogin", "zlogin",
@@ -312,7 +310,6 @@ const DEFAULT_TYPES: &'static [(&'static str, &'static [&'static str])] = &[
".zshrc", "zshrc",
"*.zsh",
]),
("zstd", &["*.zst", "*.zstd"]),
];
/// Glob represents a single glob in a set of file type definitions.
@@ -351,18 +348,6 @@ impl<'a> Glob<'a> {
fn unmatched() -> Glob<'a> {
Glob(GlobInner::UnmatchedIgnore)
}
/// Return the file type defintion that matched, if one exists. A file type
/// definition always exists when a specific definition matches a file
/// path.
pub fn file_type_def(&self) -> Option<&FileTypeDef> {
match self {
Glob(GlobInner::UnmatchedIgnore) => None,
Glob(GlobInner::Matched { def, .. }) => {
Some(def)
},
}
}
}
/// A single file type definition.

50
ignore/src/walk.rs
View File

@@ -99,7 +99,7 @@ impl DirEntry {
}
/// Returns true if and only if this entry points to a directory.
pub(crate) fn is_dir(&self) -> bool {
fn is_dir(&self) -> bool {
self.dent.is_dir()
}
@@ -764,14 +764,6 @@ impl WalkBuilder {
self
}
/// Process ignore files case insensitively
///
/// This is disabled by default.
pub fn ignore_case_insensitive(&mut self, yes: bool) -> &mut WalkBuilder {
self.ig_builder.ignore_case_insensitive(yes);
self
}
/// Set a function for sorting directory entries by their path.
///
/// If a compare function is set, the resulting iterator will return all
@@ -883,17 +875,16 @@ impl Walk {
return Ok(true);
}
}
if should_skip_entry(&self.ig, ent) {
return Ok(true);
}
if self.max_filesize.is_some() && !ent.is_dir() {
return Ok(skip_filesize(
self.max_filesize.unwrap(),
ent.path(),
&ent.metadata().ok(),
));
}
Ok(false)
let is_dir = ent.file_type().map_or(false, |ft| ft.is_dir());
let max_size = self.max_filesize;
let should_skip_path = skip_path(&self.ig, ent.path(), is_dir);
let should_skip_filesize = if !is_dir && max_size.is_some() {
skip_filesize(max_size.unwrap(), ent.path(), &ent.metadata().ok())
} else {
false
};
Ok(should_skip_path || should_skip_filesize)
}
}
@@ -1421,11 +1412,13 @@ impl Worker {
return WalkState::Continue;
}
}
let should_skip_path = should_skip_entry(ig, &dent);
let is_dir = dent.is_dir();
let max_size = self.max_filesize;
let should_skip_path = skip_path(ig, dent.path(), is_dir);
let should_skip_filesize =
if self.max_filesize.is_some() && !dent.is_dir() {
if !is_dir && max_size.is_some() {
skip_filesize(
self.max_filesize.unwrap(),
max_size.unwrap(),
dent.path(),
&dent.metadata().ok(),
)
@@ -1608,16 +1601,17 @@ fn skip_filesize(
}
}
fn should_skip_entry(
fn skip_path(
ig: &Ignore,
dent: &DirEntry,
path: &Path,
is_dir: bool,
) -> bool {
let m = ig.matched_dir_entry(dent);
let m = ig.matched(path, is_dir);
if m.is_ignore() {
debug!("ignoring {}: {:?}", dent.path().display(), m);
debug!("ignoring {}: {:?}", path.display(), m);
true
} else if m.is_whitelist() {
debug!("whitelisting {}: {:?}", dent.path().display(), m);
debug!("whitelisting {}: {:?}", path.display(), m);
false
} else {
false

1
rustfmt.toml
View File

@@ -1 +0,0 @@
disable_all_formatting = true

59
src/app.rs
View File

@@ -571,7 +571,6 @@ pub fn all_args_and_flags() -> Vec<RGArg> {
flag_iglob(&mut args);
flag_ignore_case(&mut args);
flag_ignore_file(&mut args);
flag_ignore_file_case_insensitive(&mut args);
flag_invert_match(&mut args);
flag_json(&mut args);
flag_line_buffered(&mut args);
@@ -586,7 +585,6 @@ pub fn all_args_and_flags() -> Vec<RGArg> {
flag_multiline_dotall(&mut args);
flag_no_config(&mut args);
flag_no_ignore(&mut args);
flag_no_ignore_dot(&mut args);
flag_no_ignore_global(&mut args);
flag_no_ignore_messages(&mut args);
flag_no_ignore_parent(&mut args);
@@ -982,17 +980,10 @@ fn flag_encoding(args: &mut Vec<RGArg>) {
const LONG: &str = long!("\
Specify the text encoding that ripgrep will use on all files searched. The
default value is 'auto', which will cause ripgrep to do a best effort automatic
detection of encoding on a per-file basis. Automatic detection in this case
only applies to files that begin with a UTF-8 or UTF-16 byte-order mark (BOM).
No other automatic detection is performed. One can also specify 'none' which
will then completely disable BOM sniffing and always result in searching the
raw bytes, including a BOM if it's present, regardless of its encoding.
Other supported values can be found in the list of labels here:
detection of encoding on a per-file basis. Other supported values can be found
in the list of labels here:
https://encoding.spec.whatwg.org/#concept-encoding-get
For more details on encoding and how ripgrep deals with it, see GUIDE.md.
This flag can be disabled with --no-encoding.
");
let arg = RGArg::flag("encoding", "ENCODING").short("E")
@@ -1218,26 +1209,6 @@ directly on the command line, then used -g instead.
args.push(arg);
}
fn flag_ignore_file_case_insensitive(args: &mut Vec<RGArg>) {
const SHORT: &str = "Process ignore files case insensitively.";
const LONG: &str = long!("\
Process ignore files (.gitignore, .ignore, etc.) case insensitively. Note that
this comes with a performance penalty and is most useful on case insensitive
file systems (such as Windows).
This flag can be disabled with the --no-ignore-file-case-insensitive flag.
");
let arg = RGArg::switch("ignore-file-case-insensitive")
.help(SHORT).long_help(LONG)
.overrides("no-ignore-file-case-insensitive");
args.push(arg);
let arg = RGArg::switch("no-ignore-file-case-insensitive")
.hidden()
.overrides("ignore-file-case-insensitive");
args.push(arg);
}
fn flag_invert_match(args: &mut Vec<RGArg>) {
const SHORT: &str = "Invert matching.";
const LONG: &str = long!("\
@@ -1565,7 +1536,7 @@ fn flag_no_ignore(args: &mut Vec<RGArg>) {
const SHORT: &str = "Don't respect ignore files.";
const LONG: &str = long!("\
Don't respect ignore files (.gitignore, .ignore, etc.). This implies
--no-ignore-parent, --no-ignore-dot and --no-ignore-vcs.
--no-ignore-parent and --no-ignore-vcs.
This flag can be disabled with the --ignore flag.
");
@@ -1580,24 +1551,6 @@ This flag can be disabled with the --ignore flag.
args.push(arg);
}
fn flag_no_ignore_dot(args: &mut Vec<RGArg>) {
const SHORT: &str = "Don't respect .ignore files.";
const LONG: &str = long!("\
Don't respect .ignore files.
This flag can be disabled with the --ignore-dot flag.
");
let arg = RGArg::switch("no-ignore-dot")
.help(SHORT).long_help(LONG)
.overrides("ignore-dot");
args.push(arg);
let arg = RGArg::switch("ignore-dot")
.hidden()
.overrides("no-ignore-dot");
args.push(arg);
}
fn flag_no_ignore_global(args: &mut Vec<RGArg>) {
const SHORT: &str = "Don't respect global ignore files.";
const LONG: &str = long!("\
@@ -2046,9 +1999,9 @@ This flag can be used with the -o/--only-matching flag.
fn flag_search_zip(args: &mut Vec<RGArg>) {
const SHORT: &str = "Search in compressed files.";
const LONG: &str = long!("\
Search in compressed files. Currently gzip, bzip2, xz, LZ4, LZMA, Brotli and
Zstd files are supported. This option expects the decompression binaries to be
available in your PATH.
Search in compressed files. Currently gz, bz2, xz, lzma and lz4 files are
supported. This option expects the decompression binaries to be available in
your PATH.
This flag can be disabled with --no-search-zip.
");

168
src/args.rs
View File

@@ -1,10 +1,9 @@
use std::cmp;
use std::env;
use std::ffi::{OsStr, OsString};
use std::ffi::OsStr;
use std::fs;
use std::io::{self, Write};
use std::io;
use std::path::{Path, PathBuf};
use std::process;
use std::sync::Arc;
use std::time::SystemTime;
@@ -131,7 +130,7 @@ impl Args {
// trying to parse config files. If a config file exists and has
// arguments, then we re-parse argv, otherwise we just use the matches
// we have here.
let early_matches = ArgMatches::new(clap_matches(env::args_os())?);
let early_matches = ArgMatches::new(app::app().get_matches());
set_messages(!early_matches.is_present("no-messages"));
set_ignore_messages(!early_matches.is_present("no-ignore-messages"));
@@ -146,7 +145,7 @@ impl Args {
log::set_max_level(log::LevelFilter::Warn);
}
let matches = early_matches.reconfigure()?;
let matches = early_matches.reconfigure();
// The logging level may have changed if we brought in additional
// arguments from a configuration file, so recheck it and set the log
// level as appropriate.
@@ -268,11 +267,6 @@ impl Args {
Ok(builder.build(wtr))
}
/// Returns true if and only if ripgrep should be "quiet."
pub fn quiet(&self) -> bool {
self.matches().is_present("quiet")
}
/// Returns true if and only if the search should quit after finding the
/// first match.
pub fn quit_after_match(&self) -> Result<bool> {
@@ -483,37 +477,6 @@ impl SortByKind {
}
}
/// Encoding mode the searcher will use.
#[derive(Clone, Debug)]
enum EncodingMode {
/// Use an explicit encoding forcefully, but let BOM sniffing override it.
Some(Encoding),
/// Use only BOM sniffing to auto-detect an encoding.
Auto,
/// Use no explicit encoding and disable all BOM sniffing. This will
/// always result in searching the raw bytes, regardless of their
/// true encoding.
Disabled,
}
impl EncodingMode {
/// Checks if an explicit encoding has been set. Returns false for
/// automatic BOM sniffing and no sniffing.
///
/// This is only used to determine whether PCRE2 needs to have its own
/// UTF-8 checking enabled. If we have an explicit encoding set, then
/// we're always guaranteed to get UTF-8, so we can disable PCRE2's check.
/// Otherwise, we have no such guarantee, and must enable PCRE2' UTF-8
/// check.
#[cfg(feature = "pcre2")]
fn has_explicit_encoding(&self) -> bool {
match self {
EncodingMode::Some(_) => true,
_ => false
}
}
}
impl ArgMatches {
/// Create an ArgMatches from clap's parse result.
fn new(clap_matches: clap::ArgMatches<'static>) -> ArgMatches {
@@ -527,19 +490,19 @@ impl ArgMatches {
///
/// If there are no additional arguments from the environment (e.g., a
/// config file), then the given matches are returned as is.
fn reconfigure(self) -> Result<ArgMatches> {
fn reconfigure(self) -> ArgMatches {
// If the end user says no config, then respect it.
if self.is_present("no-config") {
log::debug!(
"not reading config files because --no-config is present"
);
return Ok(self);
return self;
}
// If the user wants ripgrep to use a config file, then parse args
// from that first.
let mut args = config::args();
if args.is_empty() {
return Ok(self);
return self;
}
let mut cliargs = env::args_os();
if let Some(bin) = cliargs.next() {
@@ -547,7 +510,7 @@ impl ArgMatches {
}
args.extend(cliargs);
log::debug!("final argv: {:?}", args);
Ok(ArgMatches(clap_matches(args)?))
ArgMatches::new(app::app().get_matches_from(args))
}
/// Convert the result of parsing CLI arguments into ripgrep's higher level
@@ -681,7 +644,7 @@ impl ArgMatches {
}
if self.pcre2_unicode() {
builder.utf(true).ucp(true);
if self.encoding()?.has_explicit_encoding() {
if self.encoding()?.is_some() {
// SAFETY: If an encoding was specified, then we're guaranteed
// to get valid UTF-8, so we can disable PCRE2's UTF checking.
// (Feeding invalid UTF-8 to PCRE2 is undefined behavior.)
@@ -797,16 +760,8 @@ impl ArgMatches {
.after_context(ctx_after)
.passthru(self.is_present("passthru"))
.memory_map(self.mmap_choice(paths))
.binary_detection(self.binary_detection());
match self.encoding()? {
EncodingMode::Some(enc) => {
builder.encoding(Some(enc));
}
EncodingMode::Auto => {} // default for the searcher
EncodingMode::Disabled => {
builder.bom_sniffing(false);
}
}
.binary_detection(self.binary_detection())
.encoding(self.encoding()?);
Ok(builder.build())
}
@@ -831,16 +786,18 @@ impl ArgMatches {
.max_filesize(self.max_file_size()?)
.threads(self.threads()?)
.same_file_system(self.is_present("one-file-system"))
.skip_stdout(!self.is_present("files"))
.skip_stdout(true)
.overrides(self.overrides()?)
.types(self.types()?)
.hidden(!self.hidden())
.parents(!self.no_ignore_parent())
.ignore(!self.no_ignore_dot())
.git_global(!self.no_ignore_vcs() && !self.no_ignore_global())
.git_ignore(!self.no_ignore_vcs())
.git_exclude(!self.no_ignore_vcs())
.ignore_case_insensitive(self.ignore_file_case_insensitive());
.ignore(!self.no_ignore())
.git_global(
!self.no_ignore()
&& !self.no_ignore_vcs()
&& !self.no_ignore_global())
.git_ignore(!self.no_ignore() && !self.no_ignore_vcs())
.git_exclude(!self.no_ignore() && !self.no_ignore_vcs());
if !self.no_ignore() {
builder.add_custom_ignore_filename(".rgignore");
}
@@ -991,30 +948,24 @@ impl ArgMatches {
u64_to_usize("dfa-size-limit", r)
}
/// Returns the encoding mode to use.
/// Returns the type of encoding to use.
///
/// This only returns an encoding if one is explicitly specified. Otherwise
/// if set to automatic, the Searcher will do BOM sniffing for UTF-16
/// and transcode seamlessly. If disabled, no BOM sniffing nor transcoding
/// will occur.
fn encoding(&self) -> Result<EncodingMode> {
/// This only returns an encoding if one is explicitly specified. When no
/// encoding is present, the Searcher will still do BOM sniffing for UTF-16
/// and transcode seamlessly.
fn encoding(&self) -> Result<Option<Encoding>> {
if self.is_present("no-encoding") {
return Ok(EncodingMode::Auto);
return Ok(None);
}
let label = match self.value_of_lossy("encoding") {
None if self.pcre2_unicode() => "utf-8".to_string(),
None => return Ok(EncodingMode::Auto),
None => return Ok(None),
Some(label) => label,
};
if label == "auto" {
return Ok(EncodingMode::Auto);
} else if label == "none" {
return Ok(EncodingMode::Disabled);
return Ok(None);
}
Ok(EncodingMode::Some(Encoding::new(&label)?))
Ok(Some(Encoding::new(&label)?))
}
/// Return the file separator to use based on the CLI configuration.
@@ -1052,11 +1003,6 @@ impl ArgMatches {
self.is_present("hidden") || self.unrestricted_count() >= 2
}
/// Returns true if ignore files should be processed case insensitively.
fn ignore_file_case_insensitive(&self) -> bool {
self.is_present("ignore-file-case-insensitive")
}
/// Return all of the ignore file paths given on the command line.
fn ignore_paths(&self) -> Vec<PathBuf> {
let paths = match self.values_of_os("ignore-file") {
@@ -1151,11 +1097,6 @@ impl ArgMatches {
self.is_present("no-ignore") || self.unrestricted_count() >= 1
}
/// Returns true if .ignore files should be ignored.
fn no_ignore_dot(&self) -> bool {
self.is_present("no-ignore-dot") || self.no_ignore()
}
/// Returns true if global ignore files should be ignored.
fn no_ignore_global(&self) -> bool {
self.is_present("no-ignore-global") || self.no_ignore()
@@ -1202,7 +1143,7 @@ impl ArgMatches {
builder.add(&glob)?;
}
// This only enables case insensitivity for subsequent globs.
builder.case_insensitive(true).unwrap();
builder.case_insensitive(true)?;
for glob in self.values_of_lossy_vec("iglob") {
builder.add(&glob)?;
}
@@ -1316,15 +1257,9 @@ impl ArgMatches {
if let Some(paths) = self.values_of_os("file") {
for path in paths {
if path == "-" {
pats.extend(cli::patterns_from_stdin()?
.into_iter()
.map(|p| self.pattern_from_string(p))
);
pats.extend(cli::patterns_from_stdin()?);
} else {
pats.extend(cli::patterns_from_path(path)?
.into_iter()
.map(|p| self.pattern_from_string(p))
);
pats.extend(cli::patterns_from_path(path)?);
}
}
}
@@ -1353,17 +1288,13 @@ impl ArgMatches {
/// Converts a &str pattern to a String pattern. The pattern is escaped
/// if -F/--fixed-strings is set.
fn pattern_from_str(&self, pat: &str) -> String {
self.pattern_from_string(pat.to_string())
}
let litpat = self.pattern_literal(pat.to_string());
let s = self.pattern_line(litpat);
/// Applies additional processing on the given pattern if necessary
/// (such as escaping meta characters or turning it into a line regex).
fn pattern_from_string(&self, pat: String) -> String {
let pat = self.pattern_line(self.pattern_literal(pat));
if pat.is_empty() {
if s.is_empty() {
self.pattern_empty()
} else {
pat
s
}
}
@@ -1679,32 +1610,3 @@ where G: Fn(&fs::Metadata) -> io::Result<SystemTime>
t1.cmp(&t2)
}
}
/// Returns a clap matches object if the given arguments parse successfully.
///
/// Otherwise, if an error occurred, then it is returned unless the error
/// corresponds to a `--help` or `--version` request. In which case, the
/// corresponding output is printed and the current process is exited
/// successfully.
fn clap_matches<I, T>(
args: I,
) -> Result<clap::ArgMatches<'static>>
where I: IntoIterator<Item=T>,
T: Into<OsString> + Clone
{
let err = match app::app().get_matches_from_safe(args) {
Ok(matches) => return Ok(matches),
Err(err) => err,
};
if err.use_stderr() {
return Err(err.into());
}
// Explicitly ignore any error returned by writeln!. The most likely error
// at this point is a broken pipe error, in which case, we want to ignore
// it and exit quietly.
//
// (This is the point of this helper function. clap's functionality for
// doing this will panic on a broken pipe error.)
let _ = writeln!(io::stdout(), "{}", err);
process::exit(0);
}

54
src/config.rs
View File

@@ -5,11 +5,10 @@
use std::env;
use std::error::Error;
use std::fs::File;
use std::io;
use std::io::{self, BufRead};
use std::ffi::OsString;
use std::path::{Path, PathBuf};
use bstr::io::BufReadExt;
use log;
use crate::Result;
@@ -77,29 +76,62 @@ fn parse<P: AsRef<Path>>(
fn parse_reader<R: io::Read>(
rdr: R,
) -> Result<(Vec<OsString>, Vec<Box<Error>>)> {
let bufrdr = io::BufReader::new(rdr);
let mut bufrdr = io::BufReader::new(rdr);
let (mut args, mut errs) = (vec![], vec![]);
let mut line = vec![];
let mut line_number = 0;
bufrdr.for_byte_line_with_terminator(|line| {
while {
line.clear();
line_number += 1;
let line = line.trim();
bufrdr.read_until(b'\n', &mut line)? > 0
} {
trim(&mut line);
if line.is_empty() || line[0] == b'#' {
return Ok(true);
continue;
}
match line.to_os_str() {
match bytes_to_os_string(&line) {
Ok(osstr) => {
args.push(osstr.to_os_string());
args.push(osstr);
}
Err(err) => {
errs.push(format!("{}: {}", line_number, err).into());
}
}
Ok(true)
})?;
}
Ok((args, errs))
}
/// Trim the given bytes of whitespace according to the ASCII definition.
fn trim(x: &mut Vec<u8>) {
let upto = x.iter().take_while(|b| is_space(**b)).count();
x.drain(..upto);
let revto = x.len() - x.iter().rev().take_while(|b| is_space(**b)).count();
x.drain(revto..);
}
/// Returns true if and only if the given byte is an ASCII space character.
fn is_space(b: u8) -> bool {
b == b'\t'
|| b == b'\n'
|| b == b'\x0B'
|| b == b'\x0C'
|| b == b'\r'
|| b == b' '
}
/// On Unix, get an OsString from raw bytes.
#[cfg(unix)]
fn bytes_to_os_string(bytes: &[u8]) -> Result<OsString> {
use std::os::unix::ffi::OsStringExt;
Ok(OsString::from_vec(bytes.to_vec()))
}
/// On non-Unix (like Windows), require UTF-8.
#[cfg(not(unix))]
fn bytes_to_os_string(bytes: &[u8]) -> Result<OsString> {
String::from_utf8(bytes.to_vec()).map(OsString::from).map_err(From::from)
}
#[cfg(test)]
mod tests {
use std::ffi::OsString;

50
src/main.rs
View File

@@ -22,37 +22,33 @@ mod subject;
type Result<T> = ::std::result::Result<T, Box<::std::error::Error>>;
fn main() {
if let Err(err) = Args::parse().and_then(try_main) {
eprintln!("{}", err);
process::exit(2);
match Args::parse().and_then(try_main) {
Ok(true) => process::exit(0),
Ok(false) => process::exit(1),
Err(err) => {
eprintln!("{}", err);
process::exit(2);
}
}
}
fn try_main(args: Args) -> Result<()> {
fn try_main(args: Args) -> Result<bool> {
use args::Command::*;
let matched =
match args.command()? {
Search => search(&args),
SearchParallel => search_parallel(&args),
SearchNever => Ok(false),
Files => files(&args),
FilesParallel => files_parallel(&args),
Types => types(&args),
}?;
if matched && (args.quiet() || !messages::errored()) {
process::exit(0)
} else if messages::errored() {
process::exit(2)
} else {
process::exit(1)
match args.command()? {
Search => search(args),
SearchParallel => search_parallel(args),
SearchNever => Ok(false),
Files => files(args),
FilesParallel => files_parallel(args),
Types => types(args),
}
}
/// The top-level entry point for single-threaded search. This recursively
/// steps through the file list (current directory by default) and searches
/// each file sequentially.
fn search(args: &Args) -> Result<bool> {
fn search(args: Args) -> Result<bool> {
let started_at = Instant::now();
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
@@ -72,7 +68,7 @@ fn search(args: &Args) -> Result<bool> {
if err.kind() == io::ErrorKind::BrokenPipe {
break;
}
err_message!("{}: {}", subject.path().display(), err);
message!("{}: {}", subject.path().display(), err);
continue;
}
};
@@ -95,7 +91,7 @@ fn search(args: &Args) -> Result<bool> {
/// The top-level entry point for multi-threaded search. The parallelism is
/// itself achieved by the recursive directory traversal. All we need to do is
/// feed it a worker for performing a search on each file.
fn search_parallel(args: &Args) -> Result<bool> {
fn search_parallel(args: Args) -> Result<bool> {
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering::SeqCst;
@@ -131,7 +127,7 @@ fn search_parallel(args: &Args) -> Result<bool> {
let search_result = match searcher.search(&subject) {
Ok(search_result) => search_result,
Err(err) => {
err_message!("{}: {}", subject.path().display(), err);
message!("{}: {}", subject.path().display(), err);
return WalkState::Continue;
}
};
@@ -148,7 +144,7 @@ fn search_parallel(args: &Args) -> Result<bool> {
return WalkState::Quit;
}
// Otherwise, we continue on our merry way.
err_message!("{}: {}", subject.path().display(), err);
message!("{}: {}", subject.path().display(), err);
}
if matched.load(SeqCst) && quit_after_match {
WalkState::Quit
@@ -173,7 +169,7 @@ fn search_parallel(args: &Args) -> Result<bool> {
/// The top-level entry point for listing files without searching them. This
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using a single thread.
fn files(args: &Args) -> Result<bool> {
fn files(args: Args) -> Result<bool> {
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
let mut matched = false;
@@ -203,7 +199,7 @@ fn files(args: &Args) -> Result<bool> {
/// The top-level entry point for listing files without searching them. This
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using multiple threads.
fn files_parallel(args: &Args) -> Result<bool> {
fn files_parallel(args: Args) -> Result<bool> {
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering::SeqCst;
use std::sync::mpsc;
@@ -255,7 +251,7 @@ fn files_parallel(args: &Args) -> Result<bool> {
}
/// The top-level entry point for --type-list.
fn types(args: &Args) -> Result<bool> {
fn types(args: Args) -> Result<bool> {
let mut count = 0;
let mut stdout = args.stdout();
for def in args.type_defs()? {

30
src/messages.rs
View File

@@ -1,10 +1,8 @@
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::atomic::{ATOMIC_BOOL_INIT, AtomicBool, Ordering};
static MESSAGES: AtomicBool = AtomicBool::new(false);
static IGNORE_MESSAGES: AtomicBool = AtomicBool::new(false);
static ERRORED: AtomicBool = AtomicBool::new(false);
static MESSAGES: AtomicBool = ATOMIC_BOOL_INIT;
static IGNORE_MESSAGES: AtomicBool = ATOMIC_BOOL_INIT;
/// Emit a non-fatal error message, unless messages were disabled.
#[macro_export]
macro_rules! message {
($($tt:tt)*) => {
@@ -14,18 +12,6 @@ macro_rules! message {
}
}
/// Like message, but sets ripgrep's "errored" flag, which controls the exit
/// status.
#[macro_export]
macro_rules! err_message {
($($tt:tt)*) => {
crate::messages::set_errored();
message!($($tt)*);
}
}
/// Emit a non-fatal ignore-related error message (like a parse error), unless
/// ignore-messages were disabled.
#[macro_export]
macro_rules! ignore_message {
($($tt:tt)*) => {
@@ -62,13 +48,3 @@ pub fn ignore_messages() -> bool {
pub fn set_ignore_messages(yes: bool) {
IGNORE_MESSAGES.store(yes, Ordering::SeqCst)
}
/// Returns true if and only if ripgrep came across a non-fatal error.
pub fn errored() -> bool {
ERRORED.load(Ordering::SeqCst)
}
/// Indicate that ripgrep has come across a non-fatal error.
pub fn set_errored() {
ERRORED.store(true, Ordering::SeqCst);
}

16
src/subject.rs
View File

@@ -41,7 +41,7 @@ impl SubjectBuilder {
match result {
Ok(dent) => self.build(dent),
Err(err) => {
err_message!("{}", err);
message!("{}", err);
None
}
}
@@ -127,19 +127,9 @@ impl Subject {
self.dent.is_stdin()
}
/// Returns true if and only if this subject points to a directory after
/// following symbolic links.
/// Returns true if and only if this subject points to a directory.
fn is_dir(&self) -> bool {
let ft = match self.dent.file_type() {
None => return false,
Some(ft) => ft,
};
if ft.is_dir() {
return true;
}
// If this is a symlink, then we want to follow it to determine
// whether it's a directory or not.
self.dent.path_is_symlink() && self.dent.path().is_dir()
self.dent.file_type().map_or(false, |ft| ft.is_dir())
}
/// Returns true if and only if this subject points to a file.

2
tests/data/sherlock.br
View File

@@ -1,2 +0,0 @@
n<01><><EFBFBD>-_<>.<2E> <0C><><11><>cM<63><4D><EFBFBD><EFBFBD>Y<EFBFBD>4<08><><EFBFBD><EFBFBD><EFBFBD>Ya <0B>-L<>O(<28>8<EFBFBD>sn^Gwш!,<2C>
KD<EFBFBD><EFBFBD>/7<><37>th<74><1A> <0C><10>]j<02><><EFBFBD><EFBFBD><EFBFBD>E_;d<1E>rF<72>Qs<51>/:DIVB}<7D>T7<54><37>ѵ<04><16>H<EFBFBD>2<EFBFBD><32><EFBFBD>)<29><>M[u<><75><EFBFBD>i<EFBFBD><69><EFBFBD><0F>50ڮ<30>Y6<><36><EFBFBD><EFBFBD><17><><EFBFBD><EFBFBD><07>%<25>ר_<D7A8><5F>U by<62>4<EFBFBD><34>Ϡ<EFBFBD>!&<26>g<><15>#<23>

BIN
tests/data/sherlock.zst
View File

Binary file not shown.

48
tests/feature.rs
View File

@@ -629,51 +629,3 @@ rgtest!(f993_null_data, |dir: Dir, mut cmd: TestCommand| {
let expected = "foo\x00bar\x00baz\x00";
eqnice!(expected, cmd.stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/1138
rgtest!(f1138_no_ignore_dot, |dir: Dir, mut cmd: TestCommand| {
dir.create_dir(".git");
dir.create(".gitignore", "foo");
dir.create(".ignore", "bar");
dir.create(".fzf-ignore", "quux");
dir.create("foo", "");
dir.create("bar", "");
dir.create("quux", "");
cmd.arg("--sort").arg("path").arg("--files");
eqnice!("quux\n", cmd.stdout());
eqnice!("bar\nquux\n", cmd.arg("--no-ignore-dot").stdout());
eqnice!("bar\n", cmd.arg("--ignore-file").arg(".fzf-ignore").stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/1207
//
// Tests if without encoding 'none' flag null bytes are consumed by automatic
// encoding detection.
rgtest!(f1207_auto_encoding, |dir: Dir, mut cmd: TestCommand| {
dir.create_bytes(
"foo",
b"\xFF\xFE\x00\x62"
);
cmd.arg("-a").arg("\\x00").arg("foo");
cmd.assert_exit_code(1);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1207
//
// Tests if encoding 'none' flag does treat file as raw bytes
rgtest!(f1207_ignore_encoding, |dir: Dir, mut cmd: TestCommand| {
// PCRE2 chokes on this test because it can't search invalid non-UTF-8
// and the point of this test is to search raw UTF-16.
if dir.is_pcre2() {
return;
}
dir.create_bytes(
"foo",
b"\xFF\xFE\x00\x62"
);
cmd.arg("--encoding").arg("none").arg("-a").arg("\\x00").arg("foo");
eqnice!("\u{FFFD}\u{FFFD}\x00b\n", cmd.stdout());
});

63
tests/json.rs
View File

@@ -153,10 +153,7 @@ rgtest!(basic, |dir: Dir, mut cmd: TestCommand| {
msgs[1].unwrap_context(),
Context {
path: Some(Data::text("sherlock")),
lines: Data::text(
"Holmeses, success in the province of \
detective work must always\n",
),
lines: Data::text("Holmeses, success in the province of detective work must always\n"),
line_number: Some(2),
absolute_offset: 65,
submatches: vec![],
@@ -166,10 +163,7 @@ rgtest!(basic, |dir: Dir, mut cmd: TestCommand| {
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",
),
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![
@@ -218,9 +212,7 @@ rgtest!(notutf8, |dir: Dir, mut cmd: TestCommand| {
let contents = &b"quux\xFFbaz"[..];
// APFS does not support creating files with invalid UTF-8 bytes, so just
// skip the test if we can't create our file. Presumably we don't need this
// check if we're already skipping it on macOS, but maybe other file
// systems won't like this test either?
// skip the test if we can't create our file.
if !dir.try_create_bytes(OsStr::from_bytes(name), contents).is_ok() {
return;
}
@@ -313,52 +305,3 @@ rgtest!(crlf, |dir: Dir, mut cmd: TestCommand| {
},
);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1095
//
// This test checks that we don't drop the \r\n in a matching line when --crlf
// mode is enabled.
rgtest!(r1095_missing_crlf, |dir: Dir, mut cmd: TestCommand| {
dir.create("foo", "test\r\n");
// Check without --crlf flag.
let msgs = json_decode(&cmd.arg("--json").arg("test").stdout());
assert_eq!(msgs.len(), 4);
assert_eq!(msgs[1].unwrap_match().lines, Data::text("test\r\n"));
// Now check with --crlf flag.
let msgs = json_decode(&cmd.arg("--crlf").stdout());
assert_eq!(msgs.len(), 4);
assert_eq!(msgs[1].unwrap_match().lines, Data::text("test\r\n"));
});
// See: https://github.com/BurntSushi/ripgrep/issues/1095
//
// This test checks that we don't return empty submatches when matching a `\n`
// in CRLF mode.
rgtest!(r1095_crlf_empty_match, |dir: Dir, mut cmd: TestCommand| {
dir.create("foo", "test\r\n\n");
// Check without --crlf flag.
let msgs = json_decode(&cmd.arg("-U").arg("--json").arg("\n").stdout());
assert_eq!(msgs.len(), 5);
let m = msgs[1].unwrap_match();
assert_eq!(m.lines, Data::text("test\r\n"));
assert_eq!(m.submatches[0].m, Data::text("\n"));
let m = msgs[2].unwrap_match();
assert_eq!(m.lines, Data::text("\n"));
assert_eq!(m.submatches[0].m, Data::text("\n"));
// Now check with --crlf flag.
let msgs = json_decode(&cmd.arg("--crlf").stdout());
let m = msgs[1].unwrap_match();
assert_eq!(m.lines, Data::text("test\r\n"));
assert_eq!(m.submatches[0].m, Data::text("\n"));
let m = msgs[2].unwrap_match();
assert_eq!(m.lines, Data::text("\n"));
assert_eq!(m.submatches[0].m, Data::text("\n"));
});

30
tests/misc.rs
View File

@@ -909,36 +909,6 @@ be, to a very large extent, the result of luck. Sherlock Holmes
eqnice!(expected, cmd.stdout());
});
rgtest!(compressed_brotli, |dir: Dir, mut cmd: TestCommand| {
if !cmd_exists("brotli") {
return;
}
dir.create_bytes("sherlock.br", include_bytes!("./data/sherlock.br"));
cmd.arg("-z").arg("Sherlock").arg("sherlock.br");
let expected = "\
For the Doctor Watsons of this world, as opposed to the Sherlock
be, to a very large extent, the result of luck. Sherlock Holmes
";
eqnice!(expected, cmd.stdout());
});
rgtest!(compressed_zstd, |dir: Dir, mut cmd: TestCommand| {
if !cmd_exists("zstd") {
return;
}
dir.create_bytes("sherlock.zst", include_bytes!("./data/sherlock.zst"));
cmd.arg("-z").arg("Sherlock").arg("sherlock.zst");
let expected = "\
For the Doctor Watsons of this world, as opposed to the Sherlock
be, to a very large extent, the result of luck. Sherlock Holmes
";
eqnice!(expected, cmd.stdout());
});
rgtest!(compressed_failing_gzip, |dir: Dir, mut cmd: TestCommand| {
if !cmd_exists("gzip") {
return;

137
tests/regression.rs
View File

@@ -568,140 +568,3 @@ rgtest!(r1064, |dir: Dir, mut cmd: TestCommand| {
dir.create("input", "abc");
eqnice!("input:abc\n", cmd.arg("a(.*c)").stdout());
});
// See: https://github.com/BurntSushi/ripgrep/issues/1174
rgtest!(r1098, |dir: Dir, mut cmd: TestCommand| {
dir.create_dir(".git");
dir.create(".gitignore", "a**b");
dir.create("afoob", "test");
cmd.arg("test").assert_err();
});
// See: https://github.com/BurntSushi/ripgrep/issues/1130
rgtest!(r1130, |dir: Dir, mut cmd: TestCommand| {
dir.create("foo", "test");
eqnice!(
"foo\n",
cmd.arg("--files-with-matches").arg("test").arg("foo").stdout()
);
let mut cmd = dir.command();
eqnice!(
"foo\n",
cmd.arg("--files-without-match").arg("nada").arg("foo").stdout()
);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1159
rgtest!(r1159_invalid_flag, |_: Dir, mut cmd: TestCommand| {
cmd.arg("--wat").assert_exit_code(2);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1159
rgtest!(r1159_exit_status, |dir: Dir, _: TestCommand| {
dir.create("foo", "test");
// search with a match gets 0 exit status.
let mut cmd = dir.command();
cmd.arg("test").assert_exit_code(0);
// search with --quiet and a match gets 0 exit status.
let mut cmd = dir.command();
cmd.arg("-q").arg("test").assert_exit_code(0);
// search with a match and an error gets 2 exit status.
let mut cmd = dir.command();
cmd.arg("test").arg("no-file").assert_exit_code(2);
// search with a match in --quiet mode and an error gets 0 exit status.
let mut cmd = dir.command();
cmd.arg("-q").arg("test").arg("foo").arg("no-file").assert_exit_code(0);
// search with no match gets 1 exit status.
let mut cmd = dir.command();
cmd.arg("nada").assert_exit_code(1);
// search with --quiet and no match gets 1 exit status.
let mut cmd = dir.command();
cmd.arg("-q").arg("nada").assert_exit_code(1);
// search with no match and an error gets 2 exit status.
let mut cmd = dir.command();
cmd.arg("nada").arg("no-file").assert_exit_code(2);
// search with no match in --quiet mode and an error gets 2 exit status.
let mut cmd = dir.command();
cmd.arg("-q").arg("nada").arg("foo").arg("no-file").assert_exit_code(2);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1163
rgtest!(r1163, |dir: Dir, mut cmd: TestCommand| {
dir.create("bom.txt", "\u{FEFF}test123\ntest123");
eqnice!(
"bom.txt:test123\nbom.txt:test123\n",
cmd.arg("^test123").stdout()
);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1164
rgtest!(r1164, |dir: Dir, mut cmd: TestCommand| {
dir.create_dir(".git");
dir.create(".gitignore", "myfile");
dir.create("MYFILE", "test");
cmd.arg("--ignore-file-case-insensitive").arg("test").assert_err();
eqnice!(
"MYFILE:test\n",
cmd.arg("--no-ignore-file-case-insensitive").stdout()
);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1173
rgtest!(r1173, |dir: Dir, mut cmd: TestCommand| {
dir.create_dir(".git");
dir.create(".gitignore", "**");
dir.create("foo", "test");
cmd.arg("test").assert_err();
});
// See: https://github.com/BurntSushi/ripgrep/issues/1174
rgtest!(r1174, |dir: Dir, mut cmd: TestCommand| {
dir.create_dir(".git");
dir.create(".gitignore", "**/**/*");
dir.create_dir("a");
dir.create("a/foo", "test");
cmd.arg("test").assert_err();
});
// See: https://github.com/BurntSushi/ripgrep/issues/1176
rgtest!(r1176_literal_file, |dir: Dir, mut cmd: TestCommand| {
dir.create("patterns", "foo(bar\n");
dir.create("test", "foo(bar");
eqnice!(
"foo(bar\n",
cmd.arg("-F").arg("-f").arg("patterns").arg("test").stdout()
);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1176
rgtest!(r1176_line_regex, |dir: Dir, mut cmd: TestCommand| {
dir.create("patterns", "foo\n");
dir.create("test", "foobar\nfoo\nbarfoo\n");
eqnice!(
"foo\n",
cmd.arg("-x").arg("-f").arg("patterns").arg("test").stdout()
);
});
// See: https://github.com/BurntSushi/ripgrep/issues/1203
rgtest!(r1203_reverse_suffix_literal, |dir: Dir, _: TestCommand| {
dir.create("test", "153.230000\n");
let mut cmd = dir.command();
eqnice!("153.230000\n", cmd.arg(r"\d\d\d00").arg("test").stdout());
let mut cmd = dir.command();
eqnice!("153.230000\n", cmd.arg(r"\d\d\d000").arg("test").stdout());
});

4
tests/util.rs
View File

@@ -5,12 +5,12 @@ use std::fs::{self, File};
use std::io::{self, Write};
use std::path::{Path, PathBuf};
use std::process::{self, Command};
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::atomic::{ATOMIC_USIZE_INIT, AtomicUsize, Ordering};
use std::thread;
use std::time::Duration;
static TEST_DIR: &'static str = "ripgrep-tests";
static NEXT_ID: AtomicUsize = AtomicUsize::new(0);
static NEXT_ID: AtomicUsize = ATOMIC_USIZE_INIT;
/// Setup an empty work directory and return a command pointing to the ripgrep
/// executable whose CWD is set to the work directory.