twin/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2025-07-27 10:11:58 -07:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: twin:grep-cli-0.1.9
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/index
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
grep-cli-0 ... ag/index

Author SHA1 Message Date
Andrew Gallant
60a1db34a6 index: embarking on a most ambitious project... 2022-08-22 14:49:35 -04:00
71 changed files with 3255 additions and 3727 deletions
Expand all files Collapse all files

49
.github/workflows/ci.yml vendored
View File

@@ -42,31 +42,31 @@ jobs:
- win-gnu
include:
- build: pinned
os: ubuntu-latest
rust: 1.70.0
os: ubuntu-18.04
rust: 1.52.1
- build: stable
os: ubuntu-latest
os: ubuntu-18.04
rust: stable
- build: beta
os: ubuntu-latest
os: ubuntu-18.04
rust: beta
- build: nightly
os: ubuntu-latest
os: ubuntu-18.04
rust: nightly
- build: nightly-musl
os: ubuntu-latest
os: ubuntu-18.04
rust: nightly
target: x86_64-unknown-linux-musl
- build: nightly-32
os: ubuntu-latest
os: ubuntu-18.04
rust: nightly
target: i686-unknown-linux-gnu
- build: nightly-mips
os: ubuntu-latest
os: ubuntu-18.04
rust: nightly
target: mips64-unknown-linux-gnuabi64
- build: nightly-arm
os: ubuntu-latest
os: ubuntu-18.04
rust: nightly
# For stripping release binaries:
# docker run --rm -v $PWD/target:/target:Z \
@@ -78,17 +78,17 @@ jobs:
os: macos-latest
rust: nightly
- build: win-msvc
os: windows-2022
os: windows-2019
rust: nightly
- build: win-gnu
os: windows-2022
os: windows-2019
rust: nightly-x86_64-gnu
steps:
- name: Checkout repository
uses: actions/checkout@v3
uses: actions/checkout@v2
- name: Install packages (Ubuntu)
if: matrix.os == 'ubuntu-latest'
if: matrix.os == 'ubuntu-18.04'
run: |
ci/ubuntu-install-packages
@@ -98,7 +98,7 @@ jobs:
ci/macos-install-packages
- name: Install Rust
uses: dtolnay/rust-toolchain@master
uses: dtolnay/rust-toolchain@v1
with:
toolchain: ${{ matrix.rust }}
@@ -148,14 +148,14 @@ jobs:
run: ${{ env.CARGO }} test --verbose --workspace ${{ env.TARGET_FLAGS }}
- name: Test for existence of build artifacts (Windows)
if: matrix.os == 'windows-2022'
if: matrix.os == 'windows-2019'
shell: bash
run: |
outdir="$(ci/cargo-out-dir "${{ env.TARGET_DIR }}")"
ls "$outdir/_rg.ps1" && file "$outdir/_rg.ps1"
- name: Test for existence of build artifacts (Unix)
if: matrix.os != 'windows-2022'
if: matrix.os != 'windows-2019'
shell: bash
run: |
outdir="$(ci/cargo-out-dir "${{ env.TARGET_DIR }}")"
@@ -172,32 +172,33 @@ jobs:
# 'rg' binary (done in test-complete) with qemu, which is a pain and
# doesn't really gain us much. If shell completion works in one place,
# it probably works everywhere.
if: matrix.target == '' && matrix.os != 'windows-2022'
if: matrix.target == '' && matrix.os != 'windows-2019'
shell: bash
run: ci/test-complete
rustfmt:
name: rustfmt
runs-on: ubuntu-latest
runs-on: ubuntu-18.04
steps:
- name: Checkout repository
uses: actions/checkout@v3
uses: actions/checkout@v2
- name: Install Rust
uses: dtolnay/rust-toolchain@master
uses: dtolnay/rust-toolchain@v1
with:
toolchain: stable
components: rustfmt
- name: Check formatting
run: cargo fmt --all --check
run: |
cargo fmt --all -- --check
docs:
name: Docs
runs-on: ubuntu-latest
runs-on: ubuntu-20.04
steps:
- name: Checkout repository
uses: actions/checkout@v3
uses: actions/checkout@v2
- name: Install Rust
uses: dtolnay/rust-toolchain@master
uses: dtolnay/rust-toolchain@v1
with:
toolchain: stable
- name: Check documentation

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

@@ -29,19 +29,26 @@ jobs:
# Set to force version number, e.g., when no tag exists.
# RG_VERSION: TEST-0.0.0
outputs:
upload_url: ${{ steps.release.outputs.upload_url }}
rg_version: ${{ env.RG_VERSION }}
steps:
- uses: actions/checkout@v3
- name: Get the release version from the tag
shell: bash
if: env.RG_VERSION == ''
run: |
echo "RG_VERSION=$GITHUB_REF_NAME" >> $GITHUB_ENV
# Apparently, this is the right way to get a tag name. Really?
#
# See: https://github.community/t5/GitHub-Actions/How-to-get-just-the-tag-name/m-p/32167/highlight/true#M1027
echo "RG_VERSION=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
echo "version is: ${{ env.RG_VERSION }}"
- name: Create GitHub release
id: release
uses: actions/create-release@v1
env:
GH_TOKEN: ${{ github.token }}
run: gh release create ${{ env.RG_VERSION }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
tag_name: ${{ env.RG_VERSION }}
release_name: ${{ env.RG_VERSION }}
build-release:
name: build-release
@@ -64,11 +71,11 @@ jobs:
build: [linux, linux-arm, macos, win-msvc, win-gnu, win32-msvc]
include:
- build: linux
os: ubuntu-latest
os: ubuntu-18.04
rust: nightly
target: x86_64-unknown-linux-musl
- build: linux-arm
os: ubuntu-latest
os: ubuntu-18.04
rust: nightly
target: arm-unknown-linux-gnueabihf
- build: macos
@@ -76,24 +83,26 @@ jobs:
rust: nightly
target: x86_64-apple-darwin
- build: win-msvc
os: windows-latest
os: windows-2019
rust: nightly
target: x86_64-pc-windows-msvc
- build: win-gnu
os: windows-latest
os: windows-2019
rust: nightly-x86_64-gnu
target: x86_64-pc-windows-gnu
- build: win32-msvc
os: windows-latest
os: windows-2019
rust: nightly
target: i686-pc-windows-msvc
steps:
- name: Checkout repository
uses: actions/checkout@v3
uses: actions/checkout@v2
with:
fetch-depth: 1
- name: Install packages (Ubuntu)
if: matrix.os == 'ubuntu-latest'
if: matrix.os == 'ubuntu-18.04'
run: |
ci/ubuntu-install-packages
@@ -103,7 +112,7 @@ jobs:
ci/macos-install-packages
- name: Install Rust
uses: dtolnay/rust-toolchain@master
uses: dtolnay/rust-toolchain@v1
with:
toolchain: ${{ matrix.rust }}
target: ${{ matrix.target }}
@@ -125,8 +134,8 @@ jobs:
- name: Build release binary
run: ${{ env.CARGO }} build --verbose --release --features pcre2 ${{ env.TARGET_FLAGS }}
- name: Strip release binary (linux, macos and macos-arm)
if: matrix.build == 'linux' || matrix.os == 'macos'
- name: Strip release binary (linux and macos)
if: matrix.build == 'linux' || matrix.build == 'macos'
run: strip "target/${{ matrix.target }}/release/rg"
- name: Strip release binary (arm)
@@ -150,23 +159,24 @@ jobs:
cp "$outdir"/{rg.bash,rg.fish,_rg.ps1} "$staging/complete/"
cp complete/_rg "$staging/complete/"
if [ "${{ matrix.os }}" = "windows-latest" ]; then
if [ "${{ matrix.os }}" = "windows-2019" ]; then
cp "target/${{ matrix.target }}/release/rg.exe" "$staging/"
7z a "$staging.zip" "$staging"
certutil -hashfile "$staging.zip" SHA256 > "$staging.zip.sha256"
echo "ASSET=$staging.zip" >> $GITHUB_ENV
echo "ASSET_SUM=$staging.zip.sha256" >> $GITHUB_ENV
else
# The man page is only generated on Unix systems. ¯\_(ツ)_/¯
cp "$outdir"/rg.1 "$staging/doc/"
cp "target/${{ matrix.target }}/release/rg" "$staging/"
tar czf "$staging.tar.gz" "$staging"
shasum -a 256 "$staging.tar.gz" > "$staging.tar.gz.sha256"
echo "ASSET=$staging.tar.gz" >> $GITHUB_ENV
echo "ASSET_SUM=$staging.tar.gz.sha256" >> $GITHUB_ENV
fi
- name: Upload release archive
uses: actions/upload-release-asset@v1.0.1
env:
GH_TOKEN: ${{ github.token }}
run: gh release upload ${{ needs.create-release.outputs.rg_version }} ${{ env.ASSET }} ${{ env.ASSET_SUM }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
upload_url: ${{ needs.create-release.outputs.upload_url }}
asset_path: ${{ env.ASSET }}
asset_name: ${{ env.ASSET }}
asset_content_type: application/octet-stream

1
.ignore
View File

@@ -1 +0,0 @@
!/.github/

28
CHANGELOG.md
View File

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

243
Cargo.lock generated
View File

@@ -4,18 +4,29 @@ version = 3
[[package]]
name = "aho-corasick"
version = "1.0.2"
version = "0.7.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43f6cb1bf222025340178f382c426f13757b2960e89779dfcb319c32542a5a41"
checksum = "1e37cfd5e7657ada45f742d6e99ca5788580b5c529dc78faf11ece6dc702656f"
dependencies = [
"memchr",
]
[[package]]
name = "base64"
version = "0.20.0"
name = "atty"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0ea22880d78093b0cbe17c89f64a7d457941e65759157ec6cb31a31d652b05e5"
checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
dependencies = [
"hermit-abi",
"libc",
"winapi",
]
[[package]]
name = "base64"
version = "0.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "904dfeac50f3cdaba28fc6f57fdcddb75f49ed61346676a78c4ffe55877802fd"
[[package]]
name = "bitflags"
@@ -25,26 +36,26 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "bstr"
version = "1.6.0"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6798148dccfbff0fae41c7574d2fa8f1ef3492fba0face179de5d8d447d67b05"
checksum = "ba3569f383e8f1598449f1a423e72e99569137b47740b1da11ef19af3d5c3223"
dependencies = [
"lazy_static",
"memchr",
"regex-automata",
"serde",
]
[[package]]
name = "bytecount"
version = "0.6.3"
version = "0.6.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2c676a478f63e9fa2dd5368a42f28bba0d6c560b775f38583c8bbaa7fcd67c9c"
checksum = "72feb31ffc86498dacdbd0fcebb56138e7177a8cc5cea4516031d15ae85a742e"
[[package]]
name = "cc"
version = "1.0.79"
version = "1.0.73"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "50d30906286121d95be3d479533b458f87493b30a4b5f79a607db8f5d11aa91f"
checksum = "2fff2a6927b3bb87f9595d67196a70493f627687a71d87a0d692242c33f58c11"
dependencies = [
"jobserver",
]
@@ -69,9 +80,9 @@ dependencies = [
[[package]]
name = "crossbeam-channel"
version = "0.5.8"
version = "0.5.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a33c2bf77f2df06183c3aa30d1e96c0695a313d4f9c453cc3762a6db39f99200"
checksum = "5aaa7bd5fb665c6864b5f963dd9097905c54125909c7aa94c9e18507cdbe6c53"
dependencies = [
"cfg-if",
"crossbeam-utils",
@@ -79,18 +90,19 @@ dependencies = [
[[package]]
name = "crossbeam-utils"
version = "0.8.16"
version = "0.8.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a22b2d63d4d1dc0b7f1b6b2747dd0088008a9be28b6ddf0b1e7d335e3037294"
checksum = "0bf124c720b7686e3c2663cf54062ab0f68a88af2fb6a030e87e30bf721fcb38"
dependencies = [
"cfg-if",
"lazy_static",
]
[[package]]
name = "encoding_rs"
version = "0.8.32"
version = "0.8.30"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "071a31f4ee85403370b58aca746f01041ede6f0da2730960ad001edc2b71b394"
checksum = "7896dc8abb250ffdda33912550faa54c88ec8b998dec0b2c55ab224921ce11df"
dependencies = [
"cfg-if",
"packed_simd_2",
@@ -112,14 +124,20 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
[[package]]
name = "glob"
version = "0.3.1"
name = "fs_extra"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
checksum = "2022715d62ab30faffd124d40b76f4134a550a87792276512b18d63272333394"
[[package]]
name = "glob"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
[[package]]
name = "globset"
version = "0.4.11"
version = "0.4.9"
dependencies = [
"aho-corasick",
"bstr",
@@ -134,7 +152,7 @@ dependencies = [
[[package]]
name = "grep"
version = "0.2.12"
version = "0.2.10"
dependencies = [
"grep-cli",
"grep-matcher",
@@ -148,8 +166,9 @@ dependencies = [
[[package]]
name = "grep-cli"
version = "0.1.9"
version = "0.1.6"
dependencies = [
"atty",
"bstr",
"globset",
"lazy_static",
@@ -160,9 +179,17 @@ dependencies = [
"winapi-util",
]
[[package]]
name = "grep-index"
version = "0.0.1"
dependencies = [
"bstr 0.2.10 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.6.14 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep-matcher"
version = "0.1.6"
version = "0.1.5"
dependencies = [
"memchr",
"regex",
@@ -170,16 +197,15 @@ dependencies = [
[[package]]
name = "grep-pcre2"
version = "0.1.6"
version = "0.1.5"
dependencies = [
"grep-matcher",
"log",
"pcre2",
]
[[package]]
name = "grep-printer"
version = "0.1.7"
version = "0.1.6"
dependencies = [
"base64",
"bstr",
@@ -193,19 +219,20 @@ dependencies = [
[[package]]
name = "grep-regex"
version = "0.1.11"
version = "0.1.10"
dependencies = [
"aho-corasick",
"bstr",
"grep-matcher",
"log",
"regex-automata",
"regex",
"regex-syntax",
"thread_local",
]
[[package]]
name = "grep-searcher"
version = "0.1.11"
version = "0.1.10"
dependencies = [
"bstr",
"bytecount",
@@ -218,11 +245,21 @@ dependencies = [
"regex",
]
[[package]]
name = "hermit-abi"
version = "0.1.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
dependencies = [
"libc",
]
[[package]]
name = "ignore"
version = "0.4.20"
version = "0.4.18"
dependencies = [
"crossbeam-channel",
"crossbeam-utils",
"globset",
"lazy_static",
"log",
@@ -236,25 +273,26 @@ dependencies = [
[[package]]
name = "itoa"
version = "1.0.8"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62b02a5381cc465bd3041d84623d0fa3b66738b52b8e2fc3bab8ad63ab032f4a"
checksum = "1aab8fc367588b89dcee83ab0fd66b72b50b72fa1904d7095045ace2b0c81c35"
[[package]]
name = "jemalloc-sys"
version = "0.5.3+5.3.0-patched"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f9bd5d616ea7ed58b571b2e209a65759664d7fb021a0819d7a790afc67e47ca1"
checksum = "0d3b9f3f5c9b31aa0f5ed3260385ac205db665baa41d49bb8338008ae94ede45"
dependencies = [
"cc",
"fs_extra",
"libc",
]
[[package]]
name = "jemallocator"
version = "0.5.0"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "16c2514137880c52b0b4822b563fadd38257c1f380858addb74a400889696ea6"
checksum = "43ae63fcfc45e99ab3d1b29a46782ad679e98436c3169d15a167a1108a724b69"
dependencies = [
"jemalloc-sys",
"libc",
@@ -262,9 +300,9 @@ dependencies = [
[[package]]
name = "jobserver"
version = "0.1.26"
version = "0.1.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "936cfd212a0155903bcbc060e316fb6cc7cbf2e1907329391ebadc1fe0ce77c2"
checksum = "af25a77299a7f711a01975c35a6a424eb6862092cc2d6c72c4ed6cbc56dfc1fa"
dependencies = [
"libc",
]
@@ -277,9 +315,9 @@ checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
[[package]]
name = "libc"
version = "0.2.147"
version = "0.2.121"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4668fb0ea861c1df094127ac5f1da3409a82116a4ba74fca2e58ef927159bb3"
checksum = "efaa7b300f3b5fe8eb6bf21ce3895e1751d9665086af2d64b42f19701015ff4f"
[[package]]
name = "libm"
@@ -289,30 +327,43 @@ checksum = "7fc7aa29613bd6a620df431842069224d8bc9011086b1db4c0e0cd47fa03ec9a"
[[package]]
name = "log"
version = "0.4.19"
version = "0.4.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b06a4cde4c0f271a446782e3eff8de789548ce57dbc8eca9292c27f4a42004b4"
checksum = "51b9bbe6c47d51fc3e1a9b945965946b4c44142ab8792c50835a980d362c2710"
dependencies = [
"cfg-if",
]
[[package]]
name = "memchr"
version = "2.5.0"
version = "2.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
checksum = "308cc39be01b73d0d18f82a0e7b2a3df85245f84af96fdddc5d202d27e47b86a"
[[package]]
name = "memmap2"
version = "0.5.10"
version = "0.5.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "83faa42c0a078c393f6b29d5db232d8be22776a891f8f56e5284faee4a20b327"
checksum = "057a3db23999c867821a7a59feb06a578fcb03685e983dff90daf9e7d24ac08f"
dependencies = [
"libc",
]
[[package]]
name = "once_cell"
version = "1.18.0"
name = "num_cpus"
version = "1.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dd8b5dd2ae5ed71462c540258bedcb51965123ad7e7ccf4b9a8cafaa4a63576d"
checksum = "19e64526ebdee182341572e50e9ad03965aa510cd94427a4549448f285e957a1"
dependencies = [
"hermit-abi",
"libc",
]
[[package]]
name = "once_cell"
version = "1.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "87f3e037eac156d1775da914196f0f37741a274155e34a0b7e427c35d2a2ecb9"
[[package]]
name = "packed_simd_2"
@@ -326,9 +377,9 @@ dependencies = [
[[package]]
name = "pcre2"
version = "0.2.4"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "486aca7e74edb8cab09a48d461177f450a5cca3b55e61d139f7552190e2bbcf5"
checksum = "85b30f2f69903b439dd9dc9e824119b82a55bf113b29af8d70948a03c1b11ab1"
dependencies = [
"libc",
"log",
@@ -338,9 +389,9 @@ dependencies = [
[[package]]
name = "pcre2-sys"
version = "0.2.6"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae234f441970dbd52d4e29bee70f3b56ca83040081cb2b55b7df772b16e0b06e"
checksum = "dec30e5e9ec37eb8fbf1dea5989bc957fd3df56fbee5061aa7b7a99dbb37b722"
dependencies = [
"cc",
"libc",
@@ -349,56 +400,50 @@ dependencies = [
[[package]]
name = "pkg-config"
version = "0.3.27"
version = "0.3.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "26072860ba924cbfa98ea39c8c19b4dd6a4a25423dbdf219c1eca91aa0cf6964"
checksum = "58893f751c9b0412871a09abd62ecd2a00298c6c83befa223ef98c52aef40cbe"
[[package]]
name = "proc-macro2"
version = "1.0.63"
version = "1.0.36"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7b368fba921b0dce7e60f5e04ec15e565b3303972b42bcfde1d0713b881959eb"
checksum = "c7342d5883fbccae1cc37a2353b09c87c9b0f3afd73f5fb9bba687a1f733b029"
dependencies = [
"unicode-ident",
"unicode-xid",
]
[[package]]
name = "quote"
version = "1.0.29"
version = "1.0.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "573015e8ab27661678357f27dc26460738fd2b6c86e46f386fde94cb5d913105"
checksum = "b4af2ec4714533fcdf07e886f17025ace8b997b9ce51204ee69b6da831c3da57"
dependencies = [
"proc-macro2",
]
[[package]]
name = "regex"
version = "1.9.0"
version = "1.5.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "89089e897c013b3deb627116ae56a6955a72b8bed395c9526af31c9fe528b484"
checksum = "1a11647b6b25ff05a515cb92c365cec08801e83423a235b51e231e1808747286"
dependencies = [
"aho-corasick",
"memchr",
"regex-automata",
"regex-syntax",
]
[[package]]
name = "regex-automata"
version = "0.3.0"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa250384981ea14565685dea16a9ccc4d1c541a13f82b9c168572264d1df8c56"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
[[package]]
name = "regex-syntax"
version = "0.7.3"
version = "0.6.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2ab07dc67230e4a4718e70fd5c20055a4334b121f1f9db8fe63ef39ce9b8c846"
checksum = "f497285884f3fcff424ffc933e56d7cbca511def0c9831a7f9b5f6153e3cc89b"
[[package]]
name = "ripgrep"
@@ -411,6 +456,8 @@ dependencies = [
"jemallocator",
"lazy_static",
"log",
"num_cpus",
"regex",
"serde",
"serde_derive",
"serde_json",
@@ -420,9 +467,9 @@ dependencies = [
[[package]]
name = "ryu"
version = "1.0.14"
version = "1.0.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fe232bdf6be8c8de797b22184ee71118d63780ea42ac85b61d1baa6d3b782ae9"
checksum = "73b4b750c782965c211b42f022f59af1fbceabdd026623714f104152f1ec149f"
[[package]]
name = "same-file"
@@ -435,18 +482,18 @@ dependencies = [
[[package]]
name = "serde"
version = "1.0.166"
version = "1.0.136"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d01b7404f9d441d3ad40e6a636a7782c377d2abdbe4fa2440e2edcc2f4f10db8"
checksum = "ce31e24b01e1e524df96f1c2fdd054405f8d7376249a5110886fb4b658484789"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.166"
version = "1.0.136"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5dd83d6dde2b6b2d466e14d9d1acce8816dedee94f735eac6395808b3483c6d6"
checksum = "08597e7152fcd306f41838ed3e37be9eaeed2b61c42e2117266a554fab4662f9"
dependencies = [
"proc-macro2",
"quote",
@@ -455,9 +502,9 @@ dependencies = [
[[package]]
name = "serde_json"
version = "1.0.100"
version = "1.0.79"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0f1e14e89be7aa4c4b78bdbdc9eb5bf8517829a600ae8eaa39a6e1d960b5185c"
checksum = "8e8d9fa5c3b304765ce1fd9c4c8a3de2c8db365a5b91be52f186efc675681d95"
dependencies = [
"itoa",
"ryu",
@@ -472,20 +519,20 @@ checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
[[package]]
name = "syn"
version = "2.0.23"
version = "1.0.89"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "59fb7d6d8281a51045d62b8eb3a7d1ce347b76f312af50cd3dc0af39c87c1737"
checksum = "ea297be220d52398dcc07ce15a209fce436d361735ac1db700cab3b6cdfb9f54"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
"unicode-xid",
]
[[package]]
name = "termcolor"
version = "1.2.0"
version = "1.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "be55cf8942feac5c765c2c993422806843c9a9a45d4d5c407ad6dd2ea95eb9b6"
checksum = "bab24d30b911b2376f3a13cc2cd443142f0c81dda04c118693e35b3835757755"
dependencies = [
"winapi-util",
]
@@ -501,33 +548,33 @@ dependencies = [
[[package]]
name = "thread_local"
version = "1.1.7"
version = "1.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdd6f064ccff2d6567adcb3873ca630700f00b5ad3f060c25b5dcfd9a4ce152"
checksum = "5516c27b78311c50bf42c071425c560ac799b11c30b31f87e3081965fe5e0180"
dependencies = [
"cfg-if",
"once_cell",
]
[[package]]
name = "unicode-ident"
version = "1.0.10"
name = "unicode-width"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "22049a19f4a68748a168c0fc439f9516686aa045927ff767eca0a85101fb6e73"
checksum = "3ed742d4ea2bd1176e236172c8429aaf54486e7ac098db29ffe6529e0ce50973"
[[package]]
name = "unicode-width"
version = "0.1.10"
name = "unicode-xid"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c0edd1e5b14653f783770bce4a4dabb4a5108a5370a5f5d8cfe8710c361f6c8b"
checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3"
[[package]]
name = "walkdir"
version = "2.3.3"
version = "2.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "36df944cda56c7d8d8b7496af378e6b16de9284591917d307c9b4d313c44e698"
checksum = "808cf2735cd4b6866113f648b791c6adc5714537bc222d9347bb203386ffda56"
dependencies = [
"same-file",
"winapi",
"winapi-util",
]

21
Cargo.toml
View File

@@ -13,18 +13,10 @@ repository = "https://github.com/BurntSushi/ripgrep"
keywords = ["regex", "grep", "egrep", "search", "pattern"]
categories = ["command-line-utilities", "text-processing"]
license = "Unlicense OR MIT"
exclude = [
"HomebrewFormula",
"/.github/",
"/ci/",
"/pkg/",
"/benchsuite/",
"/scripts/",
]
exclude = ["HomebrewFormula"]
build = "build.rs"
autotests = false
edition = "2018"
rust-version = "1.70"
[[bin]]
bench = false
@@ -40,6 +32,7 @@ members = [
"crates/globset",
"crates/grep",
"crates/cli",
"crates/index",
"crates/matcher",
"crates/pcre2",
"crates/printer",
@@ -49,11 +42,13 @@ members = [
]
[dependencies]
bstr = "1.6.0"
grep = { version = "0.2.12", path = "crates/grep" }
ignore = { version = "0.4.19", path = "crates/ignore" }
bstr = "0.2.12"
grep = { version = "0.2.8", path = "crates/grep" }
ignore = { version = "0.4.18", path = "crates/ignore" }
lazy_static = "1.1.0"
log = "0.4.5"
num_cpus = "1.8.0"
regex = "1.3.5"
serde_json = "1.0.23"
termcolor = "1.1.0"
@@ -63,7 +58,7 @@ default-features = false
features = ["suggestions"]
[target.'cfg(all(target_env = "musl", target_pointer_width = "64"))'.dependencies.jemallocator]
version = "0.5.0"
version = "0.3.0"
[build-dependencies]
lazy_static = "1.1.0"

1
Cross.toml
View File

@@ -6,7 +6,6 @@ image = "burntsushi/cross:i686-unknown-linux-gnu"
[target.mips64-unknown-linux-gnuabi64]
image = "burntsushi/cross:mips64-unknown-linux-gnuabi64"
build-std = true
[target.arm-unknown-linux-gnueabihf]
image = "burntsushi/cross:arm-unknown-linux-gnueabihf"

10
GUIDE.md
View File

@@ -190,8 +190,7 @@ the following:
All of these things can be toggled using various flags provided by ripgrep:
1. You can disable all ignore-related filtering with the `--no-ignore` flag.
2. Hidden files and directories can be searched with the `--hidden` (`-.` for
short) flag.
2. Hidden files and directories can be searched with the `--hidden` flag.
3. Binary files can be searched via the `--text` (`-a` for short) flag.
Be careful with this flag! Binary files may emit control characters to your
terminal, which might cause strange behavior.
@@ -567,15 +566,12 @@ $ cat $HOME/.ripgreprc
--type-add
web:*.{html,css,js}*
# Search hidden files / directories (e.g. dotfiles) by default
--hidden
# Using glob patterns to include/exclude files or folders
--glob=!.git/*
--glob=!git/*
# or
--glob
!.git/*
!git/*
# Set the colors.
--colors=line:none

102
README.md
View File

@@ -2,11 +2,11 @@ ripgrep (rg)
------------
ripgrep is a line-oriented search tool that recursively searches the current
directory for a regex pattern. By default, ripgrep will respect gitignore rules
and automatically skip hidden files/directories and binary files. (To disable
all automatic filtering by default, use `rg -uuu`.) 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.
and automatically skip hidden files/directories and binary files. ripgrep
has first class support on Windows, macOS and Linux, with binary downloads
available for [every release](https://github.com/BurntSushi/ripgrep/releases).
ripgrep is similar to other popular search tools like The Silver Searcher, ack
and grep.
[![Build status](https://github.com/BurntSushi/ripgrep/workflows/ci/badge.svg)](https://github.com/BurntSushi/ripgrep/actions)
[![Crates.io](https://img.shields.io/crates/v/ripgrep.svg)](https://crates.io/crates/ripgrep)
@@ -90,16 +90,16 @@ times are unaffected by the presence or absence of `-n`.
because it contains most of their features and is generally faster. (See
[the FAQ](FAQ.md#posix4ever) for more details on whether ripgrep can truly
replace grep.)
* Like other tools specialized to code search, ripgrep defaults to
[recursive search](GUIDE.md#recursive-search) and does [automatic
filtering](GUIDE.md#automatic-filtering). Namely, ripgrep won't search files
ignored by your `.gitignore`/`.ignore`/`.rgignore` files, it won't search
hidden files and it won't search binary files. Automatic filtering can be
disabled with `rg -uuu`.
* ripgrep can [search specific types of files](GUIDE.md#manual-filtering-file-types).
For example, `rg -tpy foo` limits your search to Python files and `rg -Tjs
foo` excludes JavaScript files from your search. ripgrep can be taught about
new file types with custom matching rules.
* Like other tools specialized to code search, ripgrep defaults to recursive
directory search and won't search files ignored by your
`.gitignore`/`.ignore`/`.rgignore` files. It also ignores hidden and binary
files by default. ripgrep also implements full support for `.gitignore`,
whereas there are many bugs related to that functionality in other code
search tools claiming to provide the same functionality.
* ripgrep can search specific types of files. For example, `rg -tpy foo`
limits your search to Python files and `rg -Tjs foo` excludes JavaScript
files from your search. ripgrep can be taught about new file types with
custom matching rules.
* ripgrep supports many features found in `grep`, such as showing the context
of search results, searching multiple patterns, highlighting matches with
color and full Unicode support. Unlike GNU grep, ripgrep stays fast while
@@ -110,20 +110,16 @@ times are unaffected by the presence or absence of `-n`.
regex engine. PCRE2 support can be enabled with `-P/--pcre2` (use PCRE2
always) or `--auto-hybrid-regex` (use PCRE2 only if needed). An alternative
syntax is provided via the `--engine (default|pcre2|auto-hybrid)` option.
* ripgrep has [rudimentary support for replacements](GUIDE.md#replacements),
which permit rewriting output based on what was matched.
* ripgrep supports [searching files in text encodings](GUIDE.md#file-encoding)
other than UTF-8, such as UTF-16, latin-1, GBK, EUC-JP, Shift_JIS and more.
(Some support for automatically detecting UTF-16 is provided. Other text
encodings must be specifically specified with the `-E/--encoding` flag.)
* ripgrep supports searching files in text encodings other than UTF-8, such
as UTF-16, latin-1, GBK, EUC-JP, Shift_JIS and more. (Some support for
automatically detecting UTF-16 is provided. Other text encodings must be
specifically specified with the `-E/--encoding` flag.)
* ripgrep supports searching files compressed in a common format (brotli,
bzip2, gzip, lz4, lzma, xz, or zstandard) with the `-z/--search-zip` flag.
* ripgrep supports
[arbitrary input preprocessing filters](GUIDE.md#preprocessor)
which could be PDF text extraction, less supported decompression, decrypting,
automatic encoding detection and so on.
* ripgrep can be configured via a
[configuration file](GUIDE.md#configuration-file).
In other words, use ripgrep if you like speed, filtering by default, fewer
bugs and Unicode support.
@@ -228,25 +224,17 @@ If you're a **Windows Scoop** user, then you can install ripgrep from the
$ scoop install ripgrep
```
If you're a **Windows Winget** user, then you can install ripgrep from the
[winget-pkgs](https://github.com/microsoft/winget-pkgs/tree/master/manifests/b/BurntSushi/ripgrep)
repository:
```
$ winget install BurntSushi.ripgrep.MSVC
```
If you're an **Arch Linux** user, then you can install ripgrep from the official repos:
```
$ sudo pacman -S ripgrep
$ pacman -S ripgrep
```
If you're a **Gentoo** user, you can install ripgrep from the
[official repo](https://packages.gentoo.org/packages/sys-apps/ripgrep):
```
$ sudo emerge sys-apps/ripgrep
$ emerge sys-apps/ripgrep
```
If you're a **Fedora** user, you can install ripgrep from official
@@ -267,7 +255,6 @@ If you're a **RHEL/CentOS 7/8** user, you can install ripgrep from
[copr](https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/):
```
$ sudo yum install -y yum-utils
$ sudo yum-config-manager --add-repo=https://copr.fedorainfracloud.org/coprs/carlwgeorge/ripgrep/repo/epel-7/carlwgeorge-ripgrep-epel-7.repo
$ sudo yum install ripgrep
```
@@ -277,13 +264,7 @@ If you're a **Nix** user, you can install ripgrep from
```
$ nix-env --install ripgrep
```
If you're a **Guix** user, you can install ripgrep from the official
package collection:
```
$ sudo guix install ripgrep
$ # (Or using the attribute name, which is also ripgrep.)
```
If you're a **Debian** user (or a user of a Debian derivative like **Ubuntu**),
@@ -295,10 +276,8 @@ $ curl -LO https://github.com/BurntSushi/ripgrep/releases/download/13.0.0/ripgre
$ sudo dpkg -i ripgrep_13.0.0_amd64.deb
```
If you run Debian stable, ripgrep is [officially maintained by
Debian](https://tracker.debian.org/pkg/rust-ripgrep), although its version may
be older than the `deb` package available in the previous step.
If you run Debian Buster (currently Debian stable) or Debian sid, ripgrep is
[officially maintained by Debian](https://tracker.debian.org/pkg/rust-ripgrep).
```
$ sudo apt-get install ripgrep
```
@@ -316,18 +295,11 @@ seem to work right and generate a number of very strange bug reports that I
don't know how to fix and don't have the time to fix. Therefore, it is no
longer a recommended installation option.)
If you're an **ALT** user, you can install ripgrep from the
[official repo](https://packages.altlinux.org/en/search?name=ripgrep):
```
$ sudo apt-get install ripgrep
```
If you're a **FreeBSD** user, then you can install ripgrep from the
[official ports](https://www.freshports.org/textproc/ripgrep/):
```
$ sudo pkg install ripgrep
# pkg install ripgrep
```
If you're an **OpenBSD** user, then you can install ripgrep from the
@@ -341,26 +313,26 @@ If you're a **NetBSD** user, then you can install ripgrep from
[pkgsrc](https://pkgsrc.se/textproc/ripgrep):
```
$ sudo pkgin install ripgrep
# pkgin install ripgrep
```
If you're a **Haiku x86_64** user, then you can install ripgrep from the
[official ports](https://github.com/haikuports/haikuports/tree/master/sys-apps/ripgrep):
```
$ sudo pkgman install ripgrep
$ pkgman install ripgrep
```
If you're a **Haiku x86_gcc2** user, then you can install ripgrep from the
same port as Haiku x86_64 using the x86 secondary architecture build:
```
$ sudo pkgman install ripgrep_x86
$ pkgman install ripgrep_x86
```
If you're a **Rust programmer**, ripgrep can be installed with `cargo`.
* Note that the minimum supported version of Rust for ripgrep is **1.70.0**,
* Note that the minimum supported version of Rust for ripgrep is **1.34.0**,
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
@@ -375,7 +347,7 @@ $ cargo install ripgrep
ripgrep is written in Rust, so you'll need to grab a
[Rust installation](https://www.rust-lang.org/) in order to compile it.
ripgrep compiles with Rust 1.70.0 (stable) or newer. In general, ripgrep tracks
ripgrep compiles with Rust 1.34.0 (stable) or newer. In general, ripgrep tracks
the latest stable release of the Rust compiler.
To build ripgrep:
@@ -447,20 +419,12 @@ $ cargo test --all
from the repository root.
### Related tools
* [delta](https://github.com/dandavison/delta) is a syntax highlighting
pager that supports the `rg --json` output format. So all you need to do to
make it work is `rg --json pattern | delta`. See [delta's manual section on
grep](https://dandavison.github.io/delta/grep.html) for more details.
### Vulnerability reporting
For reporting a security vulnerability, please
[contact Andrew Gallant](https://blog.burntsushi.net/about/).
The contact page has my email address and PGP public key if you wish to send an
encrypted message.
[contact Andrew Gallant](https://blog.burntsushi.net/about/),
which has my email address and PGP public key if you wish to send an encrypted
message.
### Translations

33
benchsuite/benchsuite
View File

@@ -26,13 +26,15 @@ SUBTITLES_DIR = 'subtitles'
SUBTITLES_EN_NAME = 'en.txt'
SUBTITLES_EN_NAME_SAMPLE = 'en.sample.txt'
SUBTITLES_EN_NAME_GZ = '%s.gz' % SUBTITLES_EN_NAME
# SUBTITLES_EN_URL = 'http://opus.lingfil.uu.se/OpenSubtitles2016/mono/OpenSubtitles2016.raw.en.gz' # noqa
SUBTITLES_EN_URL = 'https://object.pouta.csc.fi/OPUS-OpenSubtitles/v2016/mono/en.txt.gz' # noqa
SUBTITLES_RU_NAME = 'ru.txt'
SUBTITLES_RU_NAME_GZ = '%s.gz' % SUBTITLES_RU_NAME
# SUBTITLES_RU_URL = 'http://opus.lingfil.uu.se/OpenSubtitles2016/mono/OpenSubtitles2016.raw.ru.gz' # noqa
SUBTITLES_RU_URL = 'https://object.pouta.csc.fi/OPUS-OpenSubtitles/v2016/mono/ru.txt.gz' # noqa
LINUX_DIR = 'linux'
LINUX_CLONE = 'https://github.com/BurntSushi/linux'
LINUX_CLONE = 'git://github.com/BurntSushi/linux'
# Grep takes locale settings from the environment. There is a *substantial*
# performance impact for enabling Unicode, so we need to handle this explicitly
@@ -544,11 +546,7 @@ def bench_subtitles_ru_literal(suite_dir):
Command('rg (lines)', ['rg', '-n', pat, ru]),
Command('ag (lines)', ['ag', '-s', pat, ru]),
Command('grep (lines)', ['grep', '-n', pat, ru], env=GREP_ASCII),
# ugrep incorrectly identifies this corpus as binary, but it is
# entirely valid UTF-8. So we tell ugrep to always treat the corpus
# as text even though this technically gives it an edge over other
# tools. (It no longer needs to check for binary data.)
Command('ugrep (lines)', ['ugrep', '-a', '-n', pat, ru])
Command('ugrep (lines)', ['ugrep', '-n', pat, ru])
])
@@ -566,8 +564,7 @@ def bench_subtitles_ru_literal_casei(suite_dir):
Command('grep (ASCII)', ['grep', '-E', '-i', pat, ru], env=GREP_ASCII),
Command('rg (lines)', ['rg', '-n', '-i', pat, ru]),
Command('ag (lines) (ASCII)', ['ag', '-i', pat, ru]),
# See bench_subtitles_ru_literal for why we use '-a' here.
Command('ugrep (lines) (ASCII)', ['ugrep', '-a', '-n', '-i', pat, ru])
Command('ugrep (lines) (ASCII)', ['ugrep', '-n', '-i', pat, ru])
])
@@ -591,8 +588,7 @@ def bench_subtitles_ru_literal_word(suite_dir):
Command('grep (ASCII)', [
'grep', '-nw', pat, ru,
], env=GREP_ASCII),
# See bench_subtitles_ru_literal for why we use '-a' here.
Command('ugrep (ASCII)', ['ugrep', '-anw', pat, ru]),
Command('ugrep (ASCII)', ['ugrep', '-nw', pat, ru]),
Command('rg', ['rg', '-nw', pat, ru]),
Command('grep', ['grep', '-nw', pat, ru], env=GREP_UNICODE),
])
@@ -616,8 +612,7 @@ def bench_subtitles_ru_alternate(suite_dir):
Command('rg (lines)', ['rg', '-n', pat, ru]),
Command('ag (lines)', ['ag', '-s', pat, ru]),
Command('grep (lines)', ['grep', '-E', '-n', pat, ru], env=GREP_ASCII),
# See bench_subtitles_ru_literal for why we use '-a' here.
Command('ugrep (lines)', ['ugrep', '-an', pat, ru]),
Command('ugrep (lines)', ['ugrep', '-n', pat, ru]),
Command('rg', ['rg', pat, ru]),
Command('grep', ['grep', '-E', pat, ru], env=GREP_ASCII),
])
@@ -642,8 +637,7 @@ def bench_subtitles_ru_alternate_casei(suite_dir):
Command('grep (ASCII)', [
'grep', '-E', '-ni', pat, ru,
], env=GREP_ASCII),
# See bench_subtitles_ru_literal for why we use '-a' here.
Command('ugrep (ASCII)', ['ugrep', '-ani', pat, ru]),
Command('ugrep (ASCII)', ['ugrep', '-n', '-i', pat, ru]),
Command('rg', ['rg', '-n', '-i', pat, ru]),
Command('grep', ['grep', '-E', '-ni', pat, ru], env=GREP_UNICODE),
])
@@ -660,11 +654,10 @@ def bench_subtitles_ru_surrounding_words(suite_dir):
return Benchmark(pattern=pat, commands=[
Command('rg', ['rg', '-n', pat, ru]),
Command('grep', ['grep', '-E', '-n', pat, ru], env=GREP_UNICODE),
Command('ugrep', ['ugrep', '-an', pat, ru]),
Command('ugrep', ['ugrep', '-n', pat, ru]),
Command('ag (ASCII)', ['ag', '-s', pat, ru]),
Command('grep (ASCII)', ['grep', '-E', '-n', pat, ru], env=GREP_ASCII),
# See bench_subtitles_ru_literal for why we use '-a' here.
Command('ugrep (ASCII)', ['ugrep', '-a', '-n', '-U', pat, ru]),
Command('ugrep (ASCII)', ['ugrep', '-n', '-U', pat, ru]),
])
@@ -683,13 +676,11 @@ def bench_subtitles_ru_no_literal(suite_dir):
return Benchmark(pattern=pat, commands=[
Command('rg', ['rg', '-n', pat, ru]),
# See bench_subtitles_ru_literal for why we use '-a' here.
Command('ugrep', ['ugrep', '-an', pat, ru]),
Command('ugrep', ['ugrep', '-n', pat, ru]),
Command('rg (ASCII)', ['rg', '-n', '(?-u)' + pat, ru]),
Command('ag (ASCII)', ['ag', '-s', pat, ru]),
Command('grep (ASCII)', ['grep', '-E', '-n', pat, ru], env=GREP_ASCII),
# See bench_subtitles_ru_literal for why we use '-a' here.
Command('ugrep (ASCII)', ['ugrep', '-anU', pat, ru])
Command('ugrep (ASCII)', ['ugrep', '-n', '-U', pat, ru])
])

38
benchsuite/runs/2022-12-16-archlinux-duff/README.md
View File

@@ -1,38 +0,0 @@
This directory contains updated benchmarks as of 2022-12-16. They were captured
via the benchsuite script at `benchsuite/benchsuite` from the root of this
repository. The command that was run:
$ ./benchsuite \
--dir /dev/shm/benchsuite \
--raw runs/2022-12-16-archlinux-duff/raw.csv \
| tee runs/2022-12-16-archlinux-duff/summary
The versions of each tool are as follows:
$ rg --version
ripgrep 13.0.0 (rev 87c4a2b4b1)
-SIMD -AVX (compiled)
+SIMD +AVX (runtime)
$ grep -V
grep (GNU grep) 3.8
$ ag -V
ag version 2.2.0
Features:
+jit +lzma +zlib
$ git --version
git version 2.39.0
$ ugrep --version
ugrep 3.9.2 x86_64-pc-linux-gnu +avx2 +pcre2jit +zlib +bzip2 +lzma +lz4 +zstd
License BSD-3-Clause: <https://opensource.org/licenses/BSD-3-Clause>
Written by Robert van Engelen and others: <https://github.com/Genivia/ugrep>
The version of ripgrep used was compiled from source on commit 7f23cd63:
$ cargo build --release --features 'pcre2'
This was run on a machine with an Intel i9-12900K with 128GB of memory.

400
benchsuite/runs/2022-12-16-archlinux-duff/raw.csv
View File

@@ -1,400 +0,0 @@
benchmark,warmup_iter,iter,name,command,duration,lines,env
linux_literal_default,1,3,rg,rg PM_RESUME,0.08678817749023438,39,
linux_literal_default,1,3,rg,rg PM_RESUME,0.08307123184204102,39,
linux_literal_default,1,3,rg,rg PM_RESUME,0.08347964286804199,39,
linux_literal_default,1,3,ag,ag PM_RESUME,0.2955434322357178,39,
linux_literal_default,1,3,ag,ag PM_RESUME,0.2954287528991699,39,
linux_literal_default,1,3,ag,ag PM_RESUME,0.2938194274902344,39,
linux_literal_default,1,3,git grep,git grep PM_RESUME,0.23198556900024414,39,LC_ALL=en_US.UTF-8
linux_literal_default,1,3,git grep,git grep PM_RESUME,0.22356963157653809,39,LC_ALL=en_US.UTF-8
linux_literal_default,1,3,git grep,git grep PM_RESUME,0.2189793586730957,39,LC_ALL=en_US.UTF-8
linux_literal_default,1,3,ugrep,ugrep -r PM_RESUME ./,0.10710000991821289,39,
linux_literal_default,1,3,ugrep,ugrep -r PM_RESUME ./,0.10364222526550293,39,
linux_literal_default,1,3,ugrep,ugrep -r PM_RESUME ./,0.1052248477935791,39,
linux_literal_default,1,3,grep,grep -r PM_RESUME ./,0.9994468688964844,39,LC_ALL=en_US.UTF-8
linux_literal_default,1,3,grep,grep -r PM_RESUME ./,0.9939279556274414,39,LC_ALL=en_US.UTF-8
linux_literal_default,1,3,grep,grep -r PM_RESUME ./,0.9957931041717529,39,LC_ALL=en_US.UTF-8
linux_literal,1,3,rg,rg -n PM_RESUME,0.08603358268737793,39,
linux_literal,1,3,rg,rg -n PM_RESUME,0.0837090015411377,39,
linux_literal,1,3,rg,rg -n PM_RESUME,0.08435535430908203,39,
linux_literal,1,3,rg (mmap),rg -n --mmap PM_RESUME,0.3215503692626953,39,
linux_literal,1,3,rg (mmap),rg -n --mmap PM_RESUME,0.32426929473876953,39,
linux_literal,1,3,rg (mmap),rg -n --mmap PM_RESUME,0.3215982913970947,39,
linux_literal,1,3,ag (mmap),ag -s PM_RESUME,0.2894856929779053,39,
linux_literal,1,3,ag (mmap),ag -s PM_RESUME,0.2892603874206543,39,
linux_literal,1,3,ag (mmap),ag -s PM_RESUME,0.29217028617858887,39,
linux_literal,1,3,git grep,git grep -I -n PM_RESUME,0.206068754196167,39,LC_ALL=C
linux_literal,1,3,git grep,git grep -I -n PM_RESUME,0.2218036651611328,39,LC_ALL=C
linux_literal,1,3,git grep,git grep -I -n PM_RESUME,0.20590710639953613,39,LC_ALL=C
linux_literal,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n PM_RESUME ./,0.18692874908447266,39,
linux_literal,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n PM_RESUME ./,0.19518327713012695,39,
linux_literal,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n PM_RESUME ./,0.18577361106872559,39,
linux_literal_casei,1,3,rg,rg -n -i PM_RESUME,0.08709383010864258,536,
linux_literal_casei,1,3,rg,rg -n -i PM_RESUME,0.08861064910888672,536,
linux_literal_casei,1,3,rg,rg -n -i PM_RESUME,0.08769798278808594,536,
linux_literal_casei,1,3,rg (mmap),rg -n -i --mmap PM_RESUME,0.3218965530395508,536,
linux_literal_casei,1,3,rg (mmap),rg -n -i --mmap PM_RESUME,0.30869364738464355,536,
linux_literal_casei,1,3,rg (mmap),rg -n -i --mmap PM_RESUME,0.31044936180114746,536,
linux_literal_casei,1,3,ag (mmap),ag -i PM_RESUME,0.2989068031311035,536,
linux_literal_casei,1,3,ag (mmap),ag -i PM_RESUME,0.2996039390563965,536,
linux_literal_casei,1,3,ag (mmap),ag -i PM_RESUME,0.29817700386047363,536,
linux_literal_casei,1,3,git grep,git grep -I -n -i PM_RESUME,0.2122786045074463,536,LC_ALL=C
linux_literal_casei,1,3,git grep,git grep -I -n -i PM_RESUME,0.20763754844665527,536,LC_ALL=C
linux_literal_casei,1,3,git grep,git grep -I -n -i PM_RESUME,0.220794677734375,536,LC_ALL=C
linux_literal_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i PM_RESUME ./,0.17305850982666016,536,
linux_literal_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i PM_RESUME ./,0.1745915412902832,536,
linux_literal_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i PM_RESUME ./,0.17526865005493164,536,
linux_re_literal_suffix,1,3,rg,rg -n [A-Z]+_RESUME,0.08527851104736328,2160,
linux_re_literal_suffix,1,3,rg,rg -n [A-Z]+_RESUME,0.08487534523010254,2160,
linux_re_literal_suffix,1,3,rg,rg -n [A-Z]+_RESUME,0.0848684310913086,2160,
linux_re_literal_suffix,1,3,ag,ag -s [A-Z]+_RESUME,0.37945985794067383,2160,
linux_re_literal_suffix,1,3,ag,ag -s [A-Z]+_RESUME,0.36303210258483887,2160,
linux_re_literal_suffix,1,3,ag,ag -s [A-Z]+_RESUME,0.36359691619873047,2160,
linux_re_literal_suffix,1,3,git grep,git grep -E -I -n [A-Z]+_RESUME,0.9589834213256836,2160,LC_ALL=C
linux_re_literal_suffix,1,3,git grep,git grep -E -I -n [A-Z]+_RESUME,0.9206984043121338,2160,LC_ALL=C
linux_re_literal_suffix,1,3,git grep,git grep -E -I -n [A-Z]+_RESUME,0.8642933368682861,2160,LC_ALL=C
linux_re_literal_suffix,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n [A-Z]+_RESUME ./,0.40503501892089844,2160,
linux_re_literal_suffix,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n [A-Z]+_RESUME ./,0.4531714916229248,2160,
linux_re_literal_suffix,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n [A-Z]+_RESUME ./,0.4397866725921631,2160,
linux_word,1,3,rg,rg -n -w PM_RESUME,0.08639907836914062,9,
linux_word,1,3,rg,rg -n -w PM_RESUME,0.08583569526672363,9,
linux_word,1,3,rg,rg -n -w PM_RESUME,0.08414363861083984,9,
linux_word,1,3,ag,ag -s -w PM_RESUME,0.2853865623474121,9,
linux_word,1,3,ag,ag -s -w PM_RESUME,0.2871377468109131,9,
linux_word,1,3,ag,ag -s -w PM_RESUME,0.28753662109375,9,
linux_word,1,3,git grep,git grep -E -I -n -w PM_RESUME,0.20428204536437988,9,LC_ALL=C
linux_word,1,3,git grep,git grep -E -I -n -w PM_RESUME,0.20490717887878418,9,LC_ALL=C
linux_word,1,3,git grep,git grep -E -I -n -w PM_RESUME,0.20840072631835938,9,LC_ALL=C
linux_word,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -w PM_RESUME ./,0.18790841102600098,9,
linux_word,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -w PM_RESUME ./,0.18659543991088867,9,
linux_word,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -w PM_RESUME ./,0.19104933738708496,9,
linux_unicode_greek,1,3,rg,rg -n \p{Greek},0.19976496696472168,105,
linux_unicode_greek,1,3,rg,rg -n \p{Greek},0.20618367195129395,105,
linux_unicode_greek,1,3,rg,rg -n \p{Greek},0.19702935218811035,105,
linux_unicode_greek,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \p{Greek} ./,0.17758727073669434,105,
linux_unicode_greek,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \p{Greek} ./,0.17793798446655273,105,
linux_unicode_greek,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \p{Greek} ./,0.1872577667236328,105,
linux_unicode_greek_casei,1,3,rg,rg -n -i \p{Greek},0.19808244705200195,245,
linux_unicode_greek_casei,1,3,rg,rg -n -i \p{Greek},0.1979837417602539,245,
linux_unicode_greek_casei,1,3,rg,rg -n -i \p{Greek},0.1984400749206543,245,
linux_unicode_greek_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i \p{Greek} ./,0.1819148063659668,105,
linux_unicode_greek_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i \p{Greek} ./,0.17530512809753418,105,
linux_unicode_greek_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i \p{Greek} ./,0.17999005317687988,105,
linux_unicode_word,1,3,rg,rg -n \wAh,0.08527827262878418,247,
linux_unicode_word,1,3,rg,rg -n \wAh,0.08541679382324219,247,
linux_unicode_word,1,3,rg,rg -n \wAh,0.08553218841552734,247,
linux_unicode_word,1,3,rg (ASCII),rg -n (?-u)\wAh,0.08484745025634766,233,
linux_unicode_word,1,3,rg (ASCII),rg -n (?-u)\wAh,0.08466482162475586,233,
linux_unicode_word,1,3,rg (ASCII),rg -n (?-u)\wAh,0.08487439155578613,233,
linux_unicode_word,1,3,ag (ASCII),ag -s \wAh,0.3061795234680176,233,
linux_unicode_word,1,3,ag (ASCII),ag -s \wAh,0.2993617057800293,233,
linux_unicode_word,1,3,ag (ASCII),ag -s \wAh,0.29722046852111816,233,
linux_unicode_word,1,3,git grep,git grep -E -I -n \wAh,4.257144451141357,247,LC_ALL=en_US.UTF-8
linux_unicode_word,1,3,git grep,git grep -E -I -n \wAh,3.852163076400757,247,LC_ALL=en_US.UTF-8
linux_unicode_word,1,3,git grep,git grep -E -I -n \wAh,3.8293941020965576,247,LC_ALL=en_US.UTF-8
linux_unicode_word,1,3,git grep (ASCII),git grep -E -I -n \wAh,1.647632122039795,233,LC_ALL=C
linux_unicode_word,1,3,git grep (ASCII),git grep -E -I -n \wAh,1.6269629001617432,233,LC_ALL=C
linux_unicode_word,1,3,git grep (ASCII),git grep -E -I -n \wAh,1.5847914218902588,233,LC_ALL=C
linux_unicode_word,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \wAh ./,0.1802208423614502,247,
linux_unicode_word,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \wAh ./,0.17564702033996582,247,
linux_unicode_word,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \wAh ./,0.1746981143951416,247,
linux_unicode_word,1,3,ugrep (ASCII),ugrep -r --ignore-files --no-hidden -I -n -U \wAh ./,0.1799161434173584,233,
linux_unicode_word,1,3,ugrep (ASCII),ugrep -r --ignore-files --no-hidden -I -n -U \wAh ./,0.18733000755310059,233,
linux_unicode_word,1,3,ugrep (ASCII),ugrep -r --ignore-files --no-hidden -I -n -U \wAh ./,0.18859529495239258,233,
linux_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.26203155517578125,721,
linux_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.2615540027618408,721,
linux_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.2730247974395752,721,
linux_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.19902300834655762,720,
linux_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.20034146308898926,720,
linux_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.20192813873291016,720,
linux_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.8269081115722656,1134,
linux_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.8393104076385498,1134,
linux_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},0.8293666839599609,1134,
linux_no_literal,1,3,git grep,git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},7.334395408630371,721,LC_ALL=en_US.UTF-8
linux_no_literal,1,3,git grep,git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},7.338796854019165,721,LC_ALL=en_US.UTF-8
linux_no_literal,1,3,git grep,git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},7.36545991897583,721,LC_ALL=en_US.UTF-8
linux_no_literal,1,3,git grep (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},2.1588926315307617,720,LC_ALL=C
linux_no_literal,1,3,git grep (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},2.132209062576294,720,LC_ALL=C
linux_no_literal,1,3,git grep (ASCII),git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5},2.1407439708709717,720,LC_ALL=C
linux_no_literal,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./,3.410162925720215,723,
linux_no_literal,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./,3.405057668685913,723,
linux_no_literal,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./,3.3945884704589844,723,
linux_no_literal,1,3,ugrep (ASCII),ugrep -r --ignore-files --no-hidden -I -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./,0.23865604400634766,722,
linux_no_literal,1,3,ugrep (ASCII),ugrep -r --ignore-files --no-hidden -I -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./,0.23371148109436035,722,
linux_no_literal,1,3,ugrep (ASCII),ugrep -r --ignore-files --no-hidden -I -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./,0.2343149185180664,722,
linux_alternates,1,3,rg,rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.08691263198852539,140,
linux_alternates,1,3,rg,rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.08707070350646973,140,
linux_alternates,1,3,rg,rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.08713960647583008,140,
linux_alternates,1,3,ag,ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.32947278022766113,140,
linux_alternates,1,3,ag,ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.33203840255737305,140,
linux_alternates,1,3,ag,ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.3292670249938965,140,
linux_alternates,1,3,git grep,git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.4576725959777832,140,LC_ALL=C
linux_alternates,1,3,git grep,git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.41936421394348145,140,LC_ALL=C
linux_alternates,1,3,git grep,git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.3639688491821289,140,LC_ALL=C
linux_alternates,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./,0.17806458473205566,140,
linux_alternates,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./,0.18224716186523438,140,
linux_alternates,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./,0.17795038223266602,140,
linux_alternates_casei,1,3,rg,rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.12421393394470215,241,
linux_alternates_casei,1,3,rg,rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.12235784530639648,241,
linux_alternates_casei,1,3,rg,rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.12151455879211426,241,
linux_alternates_casei,1,3,ag,ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.529585599899292,241,
linux_alternates_casei,1,3,ag,ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.5305526256561279,241,
linux_alternates_casei,1,3,ag,ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.5311264991760254,241,
linux_alternates_casei,1,3,git grep,git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.7589735984802246,241,LC_ALL=C
linux_alternates_casei,1,3,git grep,git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.7852108478546143,241,LC_ALL=C
linux_alternates_casei,1,3,git grep,git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT,0.8308050632476807,241,LC_ALL=C
linux_alternates_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./,0.17955923080444336,241,
linux_alternates_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./,0.1745290756225586,241,
linux_alternates_casei,1,3,ugrep,ugrep -r --ignore-files --no-hidden -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./,0.1773686408996582,241,
subtitles_en_literal,1,3,rg,rg Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.1213979721069336,830,
subtitles_en_literal,1,3,rg,rg Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.1213991641998291,830,
subtitles_en_literal,1,3,rg,rg Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.12620782852172852,830,
subtitles_en_literal,1,3,rg (no mmap),rg --no-mmap Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18207263946533203,830,
subtitles_en_literal,1,3,rg (no mmap),rg --no-mmap Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.17281484603881836,830,
subtitles_en_literal,1,3,rg (no mmap),rg --no-mmap Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.17368507385253906,830,
subtitles_en_literal,1,3,grep,grep Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.560560941696167,830,LC_ALL=C
subtitles_en_literal,1,3,grep,grep Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.563499927520752,830,LC_ALL=C
subtitles_en_literal,1,3,grep,grep Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.5916609764099121,830,LC_ALL=C
subtitles_en_literal,1,3,rg (lines),rg -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.19600844383239746,830,
subtitles_en_literal,1,3,rg (lines),rg -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18436980247497559,830,
subtitles_en_literal,1,3,rg (lines),rg -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18594050407409668,830,
subtitles_en_literal,1,3,ag (lines),ag -s Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.871025562286377,830,
subtitles_en_literal,1,3,ag (lines),ag -s Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.8636960983276367,830,
subtitles_en_literal,1,3,ag (lines),ag -s Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.8680994510650635,830,
subtitles_en_literal,1,3,grep (lines),grep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.9978001117706299,830,LC_ALL=C
subtitles_en_literal,1,3,grep (lines),grep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.9385361671447754,830,LC_ALL=C
subtitles_en_literal,1,3,grep (lines),grep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.0036489963531494,830,LC_ALL=C
subtitles_en_literal,1,3,ugrep (lines),ugrep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18918490409851074,830,
subtitles_en_literal,1,3,ugrep (lines),ugrep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.1769108772277832,830,
subtitles_en_literal,1,3,ugrep (lines),ugrep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18808293342590332,830,
subtitles_en_literal_casei,1,3,rg,rg -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.21876287460327148,871,
subtitles_en_literal_casei,1,3,rg,rg -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.2044692039489746,871,
subtitles_en_literal_casei,1,3,rg,rg -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.2184743881225586,871,
subtitles_en_literal_casei,1,3,grep,grep -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,2.224027156829834,871,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,3,grep,grep -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,2.223188877105713,871,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,3,grep,grep -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,2.223966598510742,871,LC_ALL=en_US.UTF-8
subtitles_en_literal_casei,1,3,grep (ASCII),grep -E -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.671149492263794,871,LC_ALL=C
subtitles_en_literal_casei,1,3,grep (ASCII),grep -E -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.6705749034881592,871,LC_ALL=C
subtitles_en_literal_casei,1,3,grep (ASCII),grep -E -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.6700258255004883,871,LC_ALL=C
subtitles_en_literal_casei,1,3,rg (lines),rg -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.2624058723449707,871,
subtitles_en_literal_casei,1,3,rg (lines),rg -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.25513339042663574,871,
subtitles_en_literal_casei,1,3,rg (lines),rg -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.26088857650756836,871,
subtitles_en_literal_casei,1,3,ag (lines) (ASCII),ag -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.9144322872161865,871,
subtitles_en_literal_casei,1,3,ag (lines) (ASCII),ag -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.866628885269165,871,
subtitles_en_literal_casei,1,3,ag (lines) (ASCII),ag -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.9098389148712158,871,
subtitles_en_literal_casei,1,3,ugrep (lines),ugrep -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.7860472202301025,871,
subtitles_en_literal_casei,1,3,ugrep (lines),ugrep -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.7858343124389648,871,
subtitles_en_literal_casei,1,3,ugrep (lines),ugrep -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.782252311706543,871,
subtitles_en_literal_word,1,3,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /dev/shm/benchsuite/subtitles/en.sample.txt,0.18424677848815918,830,
subtitles_en_literal_word,1,3,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /dev/shm/benchsuite/subtitles/en.sample.txt,0.19610810279846191,830,
subtitles_en_literal_word,1,3,rg (ASCII),rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /dev/shm/benchsuite/subtitles/en.sample.txt,0.18711471557617188,830,
subtitles_en_literal_word,1,3,ag (ASCII),ag -sw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.8301315307617188,830,
subtitles_en_literal_word,1,3,ag (ASCII),ag -sw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.8689801692962646,830,
subtitles_en_literal_word,1,3,ag (ASCII),ag -sw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.8279321193695068,830,
subtitles_en_literal_word,1,3,grep (ASCII),grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.0036842823028564,830,LC_ALL=C
subtitles_en_literal_word,1,3,grep (ASCII),grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.002833604812622,830,LC_ALL=C
subtitles_en_literal_word,1,3,grep (ASCII),grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.9236147403717041,830,LC_ALL=C
subtitles_en_literal_word,1,3,ugrep (ASCII),ugrep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.17717313766479492,830,
subtitles_en_literal_word,1,3,ugrep (ASCII),ugrep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18994617462158203,830,
subtitles_en_literal_word,1,3,ugrep (ASCII),ugrep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.17972850799560547,830,
subtitles_en_literal_word,1,3,rg,rg -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18804550170898438,830,
subtitles_en_literal_word,1,3,rg,rg -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.18867778778076172,830,
subtitles_en_literal_word,1,3,rg,rg -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.19913530349731445,830,
subtitles_en_literal_word,1,3,grep,grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.0044364929199219,830,LC_ALL=en_US.UTF-8
subtitles_en_literal_word,1,3,grep,grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,1.0040032863616943,830,LC_ALL=en_US.UTF-8
subtitles_en_literal_word,1,3,grep,grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt,0.9627983570098877,830,LC_ALL=en_US.UTF-8
subtitles_en_alternate,1,3,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.24848055839538574,1094,
subtitles_en_alternate,1,3,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.24738383293151855,1094,
subtitles_en_alternate,1,3,rg (lines),rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.24789118766784668,1094,
subtitles_en_alternate,1,3,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,2.668708562850952,1094,
subtitles_en_alternate,1,3,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,2.57511305809021,1094,
subtitles_en_alternate,1,3,ag (lines),ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,2.6714110374450684,1094,
subtitles_en_alternate,1,3,grep (lines),grep -E -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,2.0586187839508057,1094,LC_ALL=C
subtitles_en_alternate,1,3,grep (lines),grep -E -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,2.0227150917053223,1094,LC_ALL=C
subtitles_en_alternate,1,3,grep (lines),grep -E -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,2.075378179550171,1094,LC_ALL=C
subtitles_en_alternate,1,3,ugrep (lines),ugrep -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.7863781452178955,1094,
subtitles_en_alternate,1,3,ugrep (lines),ugrep -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.7874250411987305,1094,
subtitles_en_alternate,1,3,ugrep (lines),ugrep -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.7867889404296875,1094,
subtitles_en_alternate,1,3,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.18195557594299316,1094,
subtitles_en_alternate,1,3,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.18239641189575195,1094,
subtitles_en_alternate,1,3,rg,rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.1625690460205078,1094,
subtitles_en_alternate,1,3,grep,grep -E Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,1.6601614952087402,1094,LC_ALL=C
subtitles_en_alternate,1,3,grep,grep -E Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,1.6617567539215088,1094,LC_ALL=C
subtitles_en_alternate,1,3,grep,grep -E Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,1.6584677696228027,1094,LC_ALL=C
subtitles_en_alternate_casei,1,3,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,4.0028722286224365,1136,
subtitles_en_alternate_casei,1,3,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,3.991217851638794,1136,
subtitles_en_alternate_casei,1,3,ag (ASCII),ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,4.00272274017334,1136,
subtitles_en_alternate_casei,1,3,grep (ASCII),grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,3.549154758453369,1136,LC_ALL=C
subtitles_en_alternate_casei,1,3,grep (ASCII),grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,3.5468921661376953,1136,LC_ALL=C
subtitles_en_alternate_casei,1,3,grep (ASCII),grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,3.5873491764068604,1136,LC_ALL=C
subtitles_en_alternate_casei,1,3,ugrep (ASCII),ugrep -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.7872169017791748,1136,
subtitles_en_alternate_casei,1,3,ugrep (ASCII),ugrep -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.784674882888794,1136,
subtitles_en_alternate_casei,1,3,ugrep (ASCII),ugrep -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.7882401943206787,1136,
subtitles_en_alternate_casei,1,3,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.4785435199737549,1136,
subtitles_en_alternate_casei,1,3,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.4940922260284424,1136,
subtitles_en_alternate_casei,1,3,rg,rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,0.4774627685546875,1136,
subtitles_en_alternate_casei,1,3,grep,grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,3.5677175521850586,1136,LC_ALL=en_US.UTF-8
subtitles_en_alternate_casei,1,3,grep,grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,3.603273391723633,1136,LC_ALL=en_US.UTF-8
subtitles_en_alternate_casei,1,3,grep,grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt,3.5834741592407227,1136,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,rg,rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.20238041877746582,278,
subtitles_ru_surrounding_words,1,3,rg,rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.2031264305114746,278,
subtitles_ru_surrounding_words,1,3,rg,rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.20475172996520996,278,
subtitles_ru_surrounding_words,1,3,grep,grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0288453102111816,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,grep,grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.044802188873291,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,grep,grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0432109832763672,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,ugrep,ugrep -an \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,43.00765633583069,278,
subtitles_ru_surrounding_words,1,3,ugrep,ugrep -an \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,42.832849740982056,278,
subtitles_ru_surrounding_words,1,3,ugrep,ugrep -an \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,42.915205240249634,278,
subtitles_ru_surrounding_words,1,3,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.083683967590332,,
subtitles_ru_surrounding_words,1,3,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0841526985168457,,
subtitles_ru_surrounding_words,1,3,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0850934982299805,,
subtitles_ru_surrounding_words,1,3,grep (ASCII),grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0116353034973145,,LC_ALL=C
subtitles_ru_surrounding_words,1,3,grep (ASCII),grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.9868073463439941,,LC_ALL=C
subtitles_ru_surrounding_words,1,3,grep (ASCII),grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0224814414978027,,LC_ALL=C
subtitles_ru_surrounding_words,1,3,ugrep (ASCII),ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.8892502784729004,,
subtitles_ru_surrounding_words,1,3,ugrep (ASCII),ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.8910088539123535,,
subtitles_ru_surrounding_words,1,3,ugrep (ASCII),ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.8897674083709717,,
subtitles_en_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,2.11850643157959,22,
subtitles_en_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,2.1359670162200928,22,
subtitles_en_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,2.103114128112793,22,
subtitles_en_no_literal,1,3,ugrep,ugrep -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,13.050881385803223,22,
subtitles_en_no_literal,1,3,ugrep,ugrep -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,13.050772190093994,22,
subtitles_en_no_literal,1,3,ugrep,ugrep -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,13.05719804763794,22,
subtitles_en_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,1.9961926937103271,22,
subtitles_en_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,2.019721508026123,22,
subtitles_en_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,1.9965126514434814,22,
subtitles_en_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,6.849602222442627,302,
subtitles_en_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,6.813834190368652,302,
subtitles_en_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,6.8263633251190186,302,
subtitles_en_no_literal,1,3,grep (ASCII),grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,4.42924165725708,22,LC_ALL=C
subtitles_en_no_literal,1,3,grep (ASCII),grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,4.378557205200195,22,LC_ALL=C
subtitles_en_no_literal,1,3,grep (ASCII),grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,4.376646518707275,22,LC_ALL=C
subtitles_en_no_literal,1,3,ugrep (ASCII),ugrep -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,3.5110037326812744,22,
subtitles_en_no_literal,1,3,ugrep (ASCII),ugrep -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,3.5137360095977783,22,
subtitles_en_no_literal,1,3,ugrep (ASCII),ugrep -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt,3.5051844120025635,22,
subtitles_ru_literal,1,3,rg,rg Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.13207745552062988,583,
subtitles_ru_literal,1,3,rg,rg Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.13084721565246582,583,
subtitles_ru_literal,1,3,rg,rg Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.13469862937927246,583,
subtitles_ru_literal,1,3,rg (no mmap),rg --no-mmap Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.18022370338439941,583,
subtitles_ru_literal,1,3,rg (no mmap),rg --no-mmap Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.1801767349243164,583,
subtitles_ru_literal,1,3,rg (no mmap),rg --no-mmap Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.17995166778564453,583,
subtitles_ru_literal,1,3,grep,grep Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.5151040554046631,583,LC_ALL=C
subtitles_ru_literal,1,3,grep,grep Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.5154542922973633,583,LC_ALL=C
subtitles_ru_literal,1,3,grep,grep Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.49927639961242676,583,LC_ALL=C
subtitles_ru_literal,1,3,rg (lines),rg -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.19464492797851562,583,
subtitles_ru_literal,1,3,rg (lines),rg -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.18920588493347168,583,
subtitles_ru_literal,1,3,rg (lines),rg -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.19465351104736328,583,
subtitles_ru_literal,1,3,ag (lines),ag -s Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,1.9595966339111328,583,
subtitles_ru_literal,1,3,ag (lines),ag -s Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,2.0014493465423584,583,
subtitles_ru_literal,1,3,ag (lines),ag -s Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,1.9567768573760986,583,
subtitles_ru_literal,1,3,grep (lines),grep -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.8119180202484131,583,LC_ALL=C
subtitles_ru_literal,1,3,grep (lines),grep -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.8111097812652588,583,LC_ALL=C
subtitles_ru_literal,1,3,grep (lines),grep -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.8006868362426758,583,LC_ALL=C
subtitles_ru_literal,1,3,ugrep (lines),ugrep -a -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.70003342628479,583,
subtitles_ru_literal,1,3,ugrep (lines),ugrep -a -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.650275468826294,583,
subtitles_ru_literal,1,3,ugrep (lines),ugrep -a -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.689772367477417,583,
subtitles_ru_literal_casei,1,3,rg,rg -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.267578125,604,
subtitles_ru_literal_casei,1,3,rg,rg -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.2665982246398926,604,
subtitles_ru_literal_casei,1,3,rg,rg -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.26861572265625,604,
subtitles_ru_literal_casei,1,3,grep,grep -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,4.764627456665039,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,3,grep,grep -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,4.767015695571899,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,3,grep,grep -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,4.7688889503479,604,LC_ALL=en_US.UTF-8
subtitles_ru_literal_casei,1,3,grep (ASCII),grep -E -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.5046737194061279,583,LC_ALL=C
subtitles_ru_literal_casei,1,3,grep (ASCII),grep -E -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.5139875411987305,583,LC_ALL=C
subtitles_ru_literal_casei,1,3,grep (ASCII),grep -E -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.4993159770965576,583,LC_ALL=C
subtitles_ru_literal_casei,1,3,rg (lines),rg -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.33438658714294434,604,
subtitles_ru_literal_casei,1,3,rg (lines),rg -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.3398289680480957,604,
subtitles_ru_literal_casei,1,3,rg (lines),rg -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.3298227787017822,604,
subtitles_ru_literal_casei,1,3,ag (lines) (ASCII),ag -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.4468214511871338,,
subtitles_ru_literal_casei,1,3,ag (lines) (ASCII),ag -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.44559574127197266,,
subtitles_ru_literal_casei,1,3,ag (lines) (ASCII),ag -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.47882938385009766,,
subtitles_ru_literal_casei,1,3,ugrep (lines) (ASCII),ugrep -a -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.7039575576782227,583,
subtitles_ru_literal_casei,1,3,ugrep (lines) (ASCII),ugrep -a -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.6490752696990967,583,
subtitles_ru_literal_casei,1,3,ugrep (lines) (ASCII),ugrep -a -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.8081104755401611,583,
subtitles_ru_literal_word,1,3,rg (ASCII),rg -n (?-u:^|\W)Шерлок Холмс(?-u:$|\W) /dev/shm/benchsuite/subtitles/ru.txt,0.20162224769592285,583,
subtitles_ru_literal_word,1,3,rg (ASCII),rg -n (?-u:^|\W)Шерлок Холмс(?-u:$|\W) /dev/shm/benchsuite/subtitles/ru.txt,0.18215250968933105,583,
subtitles_ru_literal_word,1,3,rg (ASCII),rg -n (?-u:^|\W)Шерлок Холмс(?-u:$|\W) /dev/shm/benchsuite/subtitles/ru.txt,0.20087671279907227,583,
subtitles_ru_literal_word,1,3,ag (ASCII),ag -sw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.48624587059020996,,
subtitles_ru_literal_word,1,3,ag (ASCII),ag -sw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.5212516784667969,,
subtitles_ru_literal_word,1,3,ag (ASCII),ag -sw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.520557165145874,,
subtitles_ru_literal_word,1,3,grep (ASCII),grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.8108196258544922,583,LC_ALL=C
subtitles_ru_literal_word,1,3,grep (ASCII),grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.8121066093444824,583,LC_ALL=C
subtitles_ru_literal_word,1,3,grep (ASCII),grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.7784581184387207,583,LC_ALL=C
subtitles_ru_literal_word,1,3,ugrep (ASCII),ugrep -anw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.7469344139099121,583,
subtitles_ru_literal_word,1,3,ugrep (ASCII),ugrep -anw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.6838233470916748,583,
subtitles_ru_literal_word,1,3,ugrep (ASCII),ugrep -anw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.6921679973602295,583,
subtitles_ru_literal_word,1,3,rg,rg -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.19918251037597656,579,
subtitles_ru_literal_word,1,3,rg,rg -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.2046656608581543,579,
subtitles_ru_literal_word,1,3,rg,rg -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.1984848976135254,579,
subtitles_ru_literal_word,1,3,grep,grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.794173002243042,579,LC_ALL=en_US.UTF-8
subtitles_ru_literal_word,1,3,grep,grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.7715346813201904,579,LC_ALL=en_US.UTF-8
subtitles_ru_literal_word,1,3,grep,grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt,0.8116705417633057,579,LC_ALL=en_US.UTF-8
subtitles_ru_alternate,1,3,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,0.6730976104736328,691,
subtitles_ru_alternate,1,3,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,0.7020411491394043,691,
subtitles_ru_alternate,1,3,rg (lines),rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,0.6693949699401855,691,
subtitles_ru_alternate,1,3,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,2.7100515365600586,691,
subtitles_ru_alternate,1,3,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,2.7458419799804688,691,
subtitles_ru_alternate,1,3,ag (lines),ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,2.7115116119384766,691,
subtitles_ru_alternate,1,3,grep (lines),grep -E -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.703738451004028,691,LC_ALL=C
subtitles_ru_alternate,1,3,grep (lines),grep -E -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.715883731842041,691,LC_ALL=C
subtitles_ru_alternate,1,3,grep (lines),grep -E -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.712724924087524,691,LC_ALL=C
subtitles_ru_alternate,1,3,ugrep (lines),ugrep -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,8.276995420455933,691,
subtitles_ru_alternate,1,3,ugrep (lines),ugrep -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,8.304608345031738,691,
subtitles_ru_alternate,1,3,ugrep (lines),ugrep -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,8.322760820388794,691,
subtitles_ru_alternate,1,3,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,0.6119842529296875,691,
subtitles_ru_alternate,1,3,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,0.6368775367736816,691,
subtitles_ru_alternate,1,3,rg,rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,0.6258070468902588,691,
subtitles_ru_alternate,1,3,grep,grep -E Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.4300291538238525,691,LC_ALL=C
subtitles_ru_alternate,1,3,grep,grep -E Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.418199300765991,691,LC_ALL=C
subtitles_ru_alternate,1,3,grep,grep -E Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.425868511199951,691,LC_ALL=C
subtitles_ru_alternate_casei,1,3,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,2.7216460704803467,691,
subtitles_ru_alternate_casei,1,3,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,2.7108607292175293,691,
subtitles_ru_alternate_casei,1,3,ag (ASCII),ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,2.747138500213623,691,
subtitles_ru_alternate_casei,1,3,grep (ASCII),grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.711230039596558,691,LC_ALL=C
subtitles_ru_alternate_casei,1,3,grep (ASCII),grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.709407329559326,691,LC_ALL=C
subtitles_ru_alternate_casei,1,3,grep (ASCII),grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.714034557342529,691,LC_ALL=C
subtitles_ru_alternate_casei,1,3,ugrep (ASCII),ugrep -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,8.305904626846313,691,
subtitles_ru_alternate_casei,1,3,ugrep (ASCII),ugrep -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,8.307406187057495,691,
subtitles_ru_alternate_casei,1,3,ugrep (ASCII),ugrep -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,8.288233995437622,691,
subtitles_ru_alternate_casei,1,3,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,3.673624277114868,735,
subtitles_ru_alternate_casei,1,3,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,3.6759188175201416,735,
subtitles_ru_alternate_casei,1,3,rg,rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,3.66877818107605,735,
subtitles_ru_alternate_casei,1,3,grep,grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.366282224655151,735,LC_ALL=en_US.UTF-8
subtitles_ru_alternate_casei,1,3,grep,grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.370524883270264,735,LC_ALL=en_US.UTF-8
subtitles_ru_alternate_casei,1,3,grep,grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt,5.342163324356079,735,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,rg,rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.20331382751464844,278,
subtitles_ru_surrounding_words,1,3,rg,rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.2034592628479004,278,
subtitles_ru_surrounding_words,1,3,rg,rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.20407724380493164,278,
subtitles_ru_surrounding_words,1,3,grep,grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0436389446258545,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,grep,grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0388383865356445,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,grep,grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0446207523345947,278,LC_ALL=en_US.UTF-8
subtitles_ru_surrounding_words,1,3,ugrep,ugrep -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.29245424270629883,1,
subtitles_ru_surrounding_words,1,3,ugrep,ugrep -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.29168128967285156,1,
subtitles_ru_surrounding_words,1,3,ugrep,ugrep -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.29593825340270996,1,
subtitles_ru_surrounding_words,1,3,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.085604190826416,,
subtitles_ru_surrounding_words,1,3,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.083526372909546,,
subtitles_ru_surrounding_words,1,3,ag (ASCII),ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.1223819255828857,,
subtitles_ru_surrounding_words,1,3,grep (ASCII),grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.9905192852020264,,LC_ALL=C
subtitles_ru_surrounding_words,1,3,grep (ASCII),grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0222513675689697,,LC_ALL=C
subtitles_ru_surrounding_words,1,3,grep (ASCII),grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,1.0216262340545654,,LC_ALL=C
subtitles_ru_surrounding_words,1,3,ugrep (ASCII),ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.8875806331634521,,
subtitles_ru_surrounding_words,1,3,ugrep (ASCII),ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.8861405849456787,,
subtitles_ru_surrounding_words,1,3,ugrep (ASCII),ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt,0.8898241519927979,,
subtitles_ru_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,2.237398147583008,41,
subtitles_ru_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,2.253706693649292,41,
subtitles_ru_no_literal,1,3,rg,rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,2.2161178588867188,41,
subtitles_ru_no_literal,1,3,ugrep,ugrep -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,28.85959553718567,41,
subtitles_ru_no_literal,1,3,ugrep,ugrep -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,28.666419982910156,41,
subtitles_ru_no_literal,1,3,ugrep,ugrep -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,28.90555214881897,41,
subtitles_ru_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,2.051813840866089,,
subtitles_ru_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,2.026675224304199,,
subtitles_ru_no_literal,1,3,rg (ASCII),rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,2.027498245239258,,
subtitles_ru_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,1.0998010635375977,,
subtitles_ru_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,1.0900018215179443,,
subtitles_ru_no_literal,1,3,ag (ASCII),ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,1.0901548862457275,,
subtitles_ru_no_literal,1,3,grep (ASCII),grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,1.0691263675689697,,LC_ALL=C
subtitles_ru_no_literal,1,3,grep (ASCII),grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,1.0875153541564941,,LC_ALL=C
subtitles_ru_no_literal,1,3,grep (ASCII),grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,1.0997354984283447,,LC_ALL=C
subtitles_ru_no_literal,1,3,ugrep (ASCII),ugrep -anU \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,0.8329172134399414,,
subtitles_ru_no_literal,1,3,ugrep (ASCII),ugrep -anU \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,0.8292679786682129,,
subtitles_ru_no_literal,1,3,ugrep (ASCII),ugrep -anU \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt,0.8326950073242188,,
1 benchmark warmup_iter iter name command duration lines env
2 linux_literal_default 1 3 rg rg PM_RESUME 0.08678817749023438 39
3 linux_literal_default 1 3 rg rg PM_RESUME 0.08307123184204102 39
4 linux_literal_default 1 3 rg rg PM_RESUME 0.08347964286804199 39
5 linux_literal_default 1 3 ag ag PM_RESUME 0.2955434322357178 39
6 linux_literal_default 1 3 ag ag PM_RESUME 0.2954287528991699 39
7 linux_literal_default 1 3 ag ag PM_RESUME 0.2938194274902344 39
8 linux_literal_default 1 3 git grep git grep PM_RESUME 0.23198556900024414 39 LC_ALL=en_US.UTF-8
9 linux_literal_default 1 3 git grep git grep PM_RESUME 0.22356963157653809 39 LC_ALL=en_US.UTF-8
10 linux_literal_default 1 3 git grep git grep PM_RESUME 0.2189793586730957 39 LC_ALL=en_US.UTF-8
11 linux_literal_default 1 3 ugrep ugrep -r PM_RESUME ./ 0.10710000991821289 39
12 linux_literal_default 1 3 ugrep ugrep -r PM_RESUME ./ 0.10364222526550293 39
13 linux_literal_default 1 3 ugrep ugrep -r PM_RESUME ./ 0.1052248477935791 39
14 linux_literal_default 1 3 grep grep -r PM_RESUME ./ 0.9994468688964844 39 LC_ALL=en_US.UTF-8
15 linux_literal_default 1 3 grep grep -r PM_RESUME ./ 0.9939279556274414 39 LC_ALL=en_US.UTF-8
16 linux_literal_default 1 3 grep grep -r PM_RESUME ./ 0.9957931041717529 39 LC_ALL=en_US.UTF-8
17 linux_literal 1 3 rg rg -n PM_RESUME 0.08603358268737793 39
18 linux_literal 1 3 rg rg -n PM_RESUME 0.0837090015411377 39
19 linux_literal 1 3 rg rg -n PM_RESUME 0.08435535430908203 39
20 linux_literal 1 3 rg (mmap) rg -n --mmap PM_RESUME 0.3215503692626953 39
21 linux_literal 1 3 rg (mmap) rg -n --mmap PM_RESUME 0.32426929473876953 39
22 linux_literal 1 3 rg (mmap) rg -n --mmap PM_RESUME 0.3215982913970947 39
23 linux_literal 1 3 ag (mmap) ag -s PM_RESUME 0.2894856929779053 39
24 linux_literal 1 3 ag (mmap) ag -s PM_RESUME 0.2892603874206543 39
25 linux_literal 1 3 ag (mmap) ag -s PM_RESUME 0.29217028617858887 39
26 linux_literal 1 3 git grep git grep -I -n PM_RESUME 0.206068754196167 39 LC_ALL=C
27 linux_literal 1 3 git grep git grep -I -n PM_RESUME 0.2218036651611328 39 LC_ALL=C
28 linux_literal 1 3 git grep git grep -I -n PM_RESUME 0.20590710639953613 39 LC_ALL=C
29 linux_literal 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n PM_RESUME ./ 0.18692874908447266 39
30 linux_literal 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n PM_RESUME ./ 0.19518327713012695 39
31 linux_literal 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n PM_RESUME ./ 0.18577361106872559 39
32 linux_literal_casei 1 3 rg rg -n -i PM_RESUME 0.08709383010864258 536
33 linux_literal_casei 1 3 rg rg -n -i PM_RESUME 0.08861064910888672 536
34 linux_literal_casei 1 3 rg rg -n -i PM_RESUME 0.08769798278808594 536
35 linux_literal_casei 1 3 rg (mmap) rg -n -i --mmap PM_RESUME 0.3218965530395508 536
36 linux_literal_casei 1 3 rg (mmap) rg -n -i --mmap PM_RESUME 0.30869364738464355 536
37 linux_literal_casei 1 3 rg (mmap) rg -n -i --mmap PM_RESUME 0.31044936180114746 536
38 linux_literal_casei 1 3 ag (mmap) ag -i PM_RESUME 0.2989068031311035 536
39 linux_literal_casei 1 3 ag (mmap) ag -i PM_RESUME 0.2996039390563965 536
40 linux_literal_casei 1 3 ag (mmap) ag -i PM_RESUME 0.29817700386047363 536
41 linux_literal_casei 1 3 git grep git grep -I -n -i PM_RESUME 0.2122786045074463 536 LC_ALL=C
42 linux_literal_casei 1 3 git grep git grep -I -n -i PM_RESUME 0.20763754844665527 536 LC_ALL=C
43 linux_literal_casei 1 3 git grep git grep -I -n -i PM_RESUME 0.220794677734375 536 LC_ALL=C
44 linux_literal_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i PM_RESUME ./ 0.17305850982666016 536
45 linux_literal_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i PM_RESUME ./ 0.1745915412902832 536
46 linux_literal_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i PM_RESUME ./ 0.17526865005493164 536
47 linux_re_literal_suffix 1 3 rg rg -n [A-Z]+_RESUME 0.08527851104736328 2160
48 linux_re_literal_suffix 1 3 rg rg -n [A-Z]+_RESUME 0.08487534523010254 2160
49 linux_re_literal_suffix 1 3 rg rg -n [A-Z]+_RESUME 0.0848684310913086 2160
50 linux_re_literal_suffix 1 3 ag ag -s [A-Z]+_RESUME 0.37945985794067383 2160
51 linux_re_literal_suffix 1 3 ag ag -s [A-Z]+_RESUME 0.36303210258483887 2160
52 linux_re_literal_suffix 1 3 ag ag -s [A-Z]+_RESUME 0.36359691619873047 2160
53 linux_re_literal_suffix 1 3 git grep git grep -E -I -n [A-Z]+_RESUME 0.9589834213256836 2160 LC_ALL=C
54 linux_re_literal_suffix 1 3 git grep git grep -E -I -n [A-Z]+_RESUME 0.9206984043121338 2160 LC_ALL=C
55 linux_re_literal_suffix 1 3 git grep git grep -E -I -n [A-Z]+_RESUME 0.8642933368682861 2160 LC_ALL=C
56 linux_re_literal_suffix 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n [A-Z]+_RESUME ./ 0.40503501892089844 2160
57 linux_re_literal_suffix 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n [A-Z]+_RESUME ./ 0.4531714916229248 2160
58 linux_re_literal_suffix 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n [A-Z]+_RESUME ./ 0.4397866725921631 2160
59 linux_word 1 3 rg rg -n -w PM_RESUME 0.08639907836914062 9
60 linux_word 1 3 rg rg -n -w PM_RESUME 0.08583569526672363 9
61 linux_word 1 3 rg rg -n -w PM_RESUME 0.08414363861083984 9
62 linux_word 1 3 ag ag -s -w PM_RESUME 0.2853865623474121 9
63 linux_word 1 3 ag ag -s -w PM_RESUME 0.2871377468109131 9
64 linux_word 1 3 ag ag -s -w PM_RESUME 0.28753662109375 9
65 linux_word 1 3 git grep git grep -E -I -n -w PM_RESUME 0.20428204536437988 9 LC_ALL=C
66 linux_word 1 3 git grep git grep -E -I -n -w PM_RESUME 0.20490717887878418 9 LC_ALL=C
67 linux_word 1 3 git grep git grep -E -I -n -w PM_RESUME 0.20840072631835938 9 LC_ALL=C
68 linux_word 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -w PM_RESUME ./ 0.18790841102600098 9
69 linux_word 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -w PM_RESUME ./ 0.18659543991088867 9
70 linux_word 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -w PM_RESUME ./ 0.19104933738708496 9
71 linux_unicode_greek 1 3 rg rg -n \p{Greek} 0.19976496696472168 105
72 linux_unicode_greek 1 3 rg rg -n \p{Greek} 0.20618367195129395 105
73 linux_unicode_greek 1 3 rg rg -n \p{Greek} 0.19702935218811035 105
74 linux_unicode_greek 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \p{Greek} ./ 0.17758727073669434 105
75 linux_unicode_greek 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \p{Greek} ./ 0.17793798446655273 105
76 linux_unicode_greek 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \p{Greek} ./ 0.1872577667236328 105
77 linux_unicode_greek_casei 1 3 rg rg -n -i \p{Greek} 0.19808244705200195 245
78 linux_unicode_greek_casei 1 3 rg rg -n -i \p{Greek} 0.1979837417602539 245
79 linux_unicode_greek_casei 1 3 rg rg -n -i \p{Greek} 0.1984400749206543 245
80 linux_unicode_greek_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i \p{Greek} ./ 0.1819148063659668 105
81 linux_unicode_greek_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i \p{Greek} ./ 0.17530512809753418 105
82 linux_unicode_greek_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i \p{Greek} ./ 0.17999005317687988 105
83 linux_unicode_word 1 3 rg rg -n \wAh 0.08527827262878418 247
84 linux_unicode_word 1 3 rg rg -n \wAh 0.08541679382324219 247
85 linux_unicode_word 1 3 rg rg -n \wAh 0.08553218841552734 247
86 linux_unicode_word 1 3 rg (ASCII) rg -n (?-u)\wAh 0.08484745025634766 233
87 linux_unicode_word 1 3 rg (ASCII) rg -n (?-u)\wAh 0.08466482162475586 233
88 linux_unicode_word 1 3 rg (ASCII) rg -n (?-u)\wAh 0.08487439155578613 233
89 linux_unicode_word 1 3 ag (ASCII) ag -s \wAh 0.3061795234680176 233
90 linux_unicode_word 1 3 ag (ASCII) ag -s \wAh 0.2993617057800293 233
91 linux_unicode_word 1 3 ag (ASCII) ag -s \wAh 0.29722046852111816 233
92 linux_unicode_word 1 3 git grep git grep -E -I -n \wAh 4.257144451141357 247 LC_ALL=en_US.UTF-8
93 linux_unicode_word 1 3 git grep git grep -E -I -n \wAh 3.852163076400757 247 LC_ALL=en_US.UTF-8
94 linux_unicode_word 1 3 git grep git grep -E -I -n \wAh 3.8293941020965576 247 LC_ALL=en_US.UTF-8
95 linux_unicode_word 1 3 git grep (ASCII) git grep -E -I -n \wAh 1.647632122039795 233 LC_ALL=C
96 linux_unicode_word 1 3 git grep (ASCII) git grep -E -I -n \wAh 1.6269629001617432 233 LC_ALL=C
97 linux_unicode_word 1 3 git grep (ASCII) git grep -E -I -n \wAh 1.5847914218902588 233 LC_ALL=C
98 linux_unicode_word 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \wAh ./ 0.1802208423614502 247
99 linux_unicode_word 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \wAh ./ 0.17564702033996582 247
100 linux_unicode_word 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \wAh ./ 0.1746981143951416 247
101 linux_unicode_word 1 3 ugrep (ASCII) ugrep -r --ignore-files --no-hidden -I -n -U \wAh ./ 0.1799161434173584 233
102 linux_unicode_word 1 3 ugrep (ASCII) ugrep -r --ignore-files --no-hidden -I -n -U \wAh ./ 0.18733000755310059 233
103 linux_unicode_word 1 3 ugrep (ASCII) ugrep -r --ignore-files --no-hidden -I -n -U \wAh ./ 0.18859529495239258 233
104 linux_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.26203155517578125 721
105 linux_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.2615540027618408 721
106 linux_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.2730247974395752 721
107 linux_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.19902300834655762 720
108 linux_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.20034146308898926 720
109 linux_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.20192813873291016 720
110 linux_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.8269081115722656 1134
111 linux_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.8393104076385498 1134
112 linux_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 0.8293666839599609 1134
113 linux_no_literal 1 3 git grep git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 7.334395408630371 721 LC_ALL=en_US.UTF-8
114 linux_no_literal 1 3 git grep git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 7.338796854019165 721 LC_ALL=en_US.UTF-8
115 linux_no_literal 1 3 git grep git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 7.36545991897583 721 LC_ALL=en_US.UTF-8
116 linux_no_literal 1 3 git grep (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 2.1588926315307617 720 LC_ALL=C
117 linux_no_literal 1 3 git grep (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 2.132209062576294 720 LC_ALL=C
118 linux_no_literal 1 3 git grep (ASCII) git grep -E -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} 2.1407439708709717 720 LC_ALL=C
119 linux_no_literal 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./ 3.410162925720215 723
120 linux_no_literal 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./ 3.405057668685913 723
121 linux_no_literal 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./ 3.3945884704589844 723
122 linux_no_literal 1 3 ugrep (ASCII) ugrep -r --ignore-files --no-hidden -I -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./ 0.23865604400634766 722
123 linux_no_literal 1 3 ugrep (ASCII) ugrep -r --ignore-files --no-hidden -I -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./ 0.23371148109436035 722
124 linux_no_literal 1 3 ugrep (ASCII) ugrep -r --ignore-files --no-hidden -I -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} ./ 0.2343149185180664 722
125 linux_alternates 1 3 rg rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.08691263198852539 140
126 linux_alternates 1 3 rg rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.08707070350646973 140
127 linux_alternates 1 3 rg rg -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.08713960647583008 140
128 linux_alternates 1 3 ag ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.32947278022766113 140
129 linux_alternates 1 3 ag ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.33203840255737305 140
130 linux_alternates 1 3 ag ag -s ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.3292670249938965 140
131 linux_alternates 1 3 git grep git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.4576725959777832 140 LC_ALL=C
132 linux_alternates 1 3 git grep git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.41936421394348145 140 LC_ALL=C
133 linux_alternates 1 3 git grep git grep -E -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.3639688491821289 140 LC_ALL=C
134 linux_alternates 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./ 0.17806458473205566 140
135 linux_alternates 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./ 0.18224716186523438 140
136 linux_alternates 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./ 0.17795038223266602 140
137 linux_alternates_casei 1 3 rg rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.12421393394470215 241
138 linux_alternates_casei 1 3 rg rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.12235784530639648 241
139 linux_alternates_casei 1 3 rg rg -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.12151455879211426 241
140 linux_alternates_casei 1 3 ag ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.529585599899292 241
141 linux_alternates_casei 1 3 ag ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.5305526256561279 241
142 linux_alternates_casei 1 3 ag ag -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.5311264991760254 241
143 linux_alternates_casei 1 3 git grep git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.7589735984802246 241 LC_ALL=C
144 linux_alternates_casei 1 3 git grep git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.7852108478546143 241 LC_ALL=C
145 linux_alternates_casei 1 3 git grep git grep -E -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT 0.8308050632476807 241 LC_ALL=C
146 linux_alternates_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./ 0.17955923080444336 241
147 linux_alternates_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./ 0.1745290756225586 241
148 linux_alternates_casei 1 3 ugrep ugrep -r --ignore-files --no-hidden -I -n -i ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT ./ 0.1773686408996582 241
149 subtitles_en_literal 1 3 rg rg Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.1213979721069336 830
150 subtitles_en_literal 1 3 rg rg Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.1213991641998291 830
151 subtitles_en_literal 1 3 rg rg Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.12620782852172852 830
152 subtitles_en_literal 1 3 rg (no mmap) rg --no-mmap Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18207263946533203 830
153 subtitles_en_literal 1 3 rg (no mmap) rg --no-mmap Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.17281484603881836 830
154 subtitles_en_literal 1 3 rg (no mmap) rg --no-mmap Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.17368507385253906 830
155 subtitles_en_literal 1 3 grep grep Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.560560941696167 830 LC_ALL=C
156 subtitles_en_literal 1 3 grep grep Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.563499927520752 830 LC_ALL=C
157 subtitles_en_literal 1 3 grep grep Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.5916609764099121 830 LC_ALL=C
158 subtitles_en_literal 1 3 rg (lines) rg -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.19600844383239746 830
159 subtitles_en_literal 1 3 rg (lines) rg -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18436980247497559 830
160 subtitles_en_literal 1 3 rg (lines) rg -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18594050407409668 830
161 subtitles_en_literal 1 3 ag (lines) ag -s Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.871025562286377 830
162 subtitles_en_literal 1 3 ag (lines) ag -s Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.8636960983276367 830
163 subtitles_en_literal 1 3 ag (lines) ag -s Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.8680994510650635 830
164 subtitles_en_literal 1 3 grep (lines) grep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.9978001117706299 830 LC_ALL=C
165 subtitles_en_literal 1 3 grep (lines) grep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.9385361671447754 830 LC_ALL=C
166 subtitles_en_literal 1 3 grep (lines) grep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.0036489963531494 830 LC_ALL=C
167 subtitles_en_literal 1 3 ugrep (lines) ugrep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18918490409851074 830
168 subtitles_en_literal 1 3 ugrep (lines) ugrep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.1769108772277832 830
169 subtitles_en_literal 1 3 ugrep (lines) ugrep -n Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18808293342590332 830
170 subtitles_en_literal_casei 1 3 rg rg -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.21876287460327148 871
171 subtitles_en_literal_casei 1 3 rg rg -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.2044692039489746 871
172 subtitles_en_literal_casei 1 3 rg rg -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.2184743881225586 871
173 subtitles_en_literal_casei 1 3 grep grep -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 2.224027156829834 871 LC_ALL=en_US.UTF-8
174 subtitles_en_literal_casei 1 3 grep grep -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 2.223188877105713 871 LC_ALL=en_US.UTF-8
175 subtitles_en_literal_casei 1 3 grep grep -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 2.223966598510742 871 LC_ALL=en_US.UTF-8
176 subtitles_en_literal_casei 1 3 grep (ASCII) grep -E -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.671149492263794 871 LC_ALL=C
177 subtitles_en_literal_casei 1 3 grep (ASCII) grep -E -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.6705749034881592 871 LC_ALL=C
178 subtitles_en_literal_casei 1 3 grep (ASCII) grep -E -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.6700258255004883 871 LC_ALL=C
179 subtitles_en_literal_casei 1 3 rg (lines) rg -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.2624058723449707 871
180 subtitles_en_literal_casei 1 3 rg (lines) rg -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.25513339042663574 871
181 subtitles_en_literal_casei 1 3 rg (lines) rg -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.26088857650756836 871
182 subtitles_en_literal_casei 1 3 ag (lines) (ASCII) ag -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.9144322872161865 871
183 subtitles_en_literal_casei 1 3 ag (lines) (ASCII) ag -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.866628885269165 871
184 subtitles_en_literal_casei 1 3 ag (lines) (ASCII) ag -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.9098389148712158 871
185 subtitles_en_literal_casei 1 3 ugrep (lines) ugrep -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.7860472202301025 871
186 subtitles_en_literal_casei 1 3 ugrep (lines) ugrep -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.7858343124389648 871
187 subtitles_en_literal_casei 1 3 ugrep (lines) ugrep -n -i Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.782252311706543 871
188 subtitles_en_literal_word 1 3 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /dev/shm/benchsuite/subtitles/en.sample.txt 0.18424677848815918 830
189 subtitles_en_literal_word 1 3 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /dev/shm/benchsuite/subtitles/en.sample.txt 0.19610810279846191 830
190 subtitles_en_literal_word 1 3 rg (ASCII) rg -n (?-u:\b)Sherlock Holmes(?-u:\b) /dev/shm/benchsuite/subtitles/en.sample.txt 0.18711471557617188 830
191 subtitles_en_literal_word 1 3 ag (ASCII) ag -sw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.8301315307617188 830
192 subtitles_en_literal_word 1 3 ag (ASCII) ag -sw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.8689801692962646 830
193 subtitles_en_literal_word 1 3 ag (ASCII) ag -sw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.8279321193695068 830
194 subtitles_en_literal_word 1 3 grep (ASCII) grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.0036842823028564 830 LC_ALL=C
195 subtitles_en_literal_word 1 3 grep (ASCII) grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.002833604812622 830 LC_ALL=C
196 subtitles_en_literal_word 1 3 grep (ASCII) grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.9236147403717041 830 LC_ALL=C
197 subtitles_en_literal_word 1 3 ugrep (ASCII) ugrep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.17717313766479492 830
198 subtitles_en_literal_word 1 3 ugrep (ASCII) ugrep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18994617462158203 830
199 subtitles_en_literal_word 1 3 ugrep (ASCII) ugrep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.17972850799560547 830
200 subtitles_en_literal_word 1 3 rg rg -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18804550170898438 830
201 subtitles_en_literal_word 1 3 rg rg -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.18867778778076172 830
202 subtitles_en_literal_word 1 3 rg rg -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.19913530349731445 830
203 subtitles_en_literal_word 1 3 grep grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.0044364929199219 830 LC_ALL=en_US.UTF-8
204 subtitles_en_literal_word 1 3 grep grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 1.0040032863616943 830 LC_ALL=en_US.UTF-8
205 subtitles_en_literal_word 1 3 grep grep -nw Sherlock Holmes /dev/shm/benchsuite/subtitles/en.sample.txt 0.9627983570098877 830 LC_ALL=en_US.UTF-8
206 subtitles_en_alternate 1 3 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.24848055839538574 1094
207 subtitles_en_alternate 1 3 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.24738383293151855 1094
208 subtitles_en_alternate 1 3 rg (lines) rg -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.24789118766784668 1094
209 subtitles_en_alternate 1 3 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 2.668708562850952 1094
210 subtitles_en_alternate 1 3 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 2.57511305809021 1094
211 subtitles_en_alternate 1 3 ag (lines) ag -s Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 2.6714110374450684 1094
212 subtitles_en_alternate 1 3 grep (lines) grep -E -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 2.0586187839508057 1094 LC_ALL=C
213 subtitles_en_alternate 1 3 grep (lines) grep -E -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 2.0227150917053223 1094 LC_ALL=C
214 subtitles_en_alternate 1 3 grep (lines) grep -E -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 2.075378179550171 1094 LC_ALL=C
215 subtitles_en_alternate 1 3 ugrep (lines) ugrep -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.7863781452178955 1094
216 subtitles_en_alternate 1 3 ugrep (lines) ugrep -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.7874250411987305 1094
217 subtitles_en_alternate 1 3 ugrep (lines) ugrep -n Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.7867889404296875 1094
218 subtitles_en_alternate 1 3 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.18195557594299316 1094
219 subtitles_en_alternate 1 3 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.18239641189575195 1094
220 subtitles_en_alternate 1 3 rg rg Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.1625690460205078 1094
221 subtitles_en_alternate 1 3 grep grep -E Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 1.6601614952087402 1094 LC_ALL=C
222 subtitles_en_alternate 1 3 grep grep -E Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 1.6617567539215088 1094 LC_ALL=C
223 subtitles_en_alternate 1 3 grep grep -E Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 1.6584677696228027 1094 LC_ALL=C
224 subtitles_en_alternate_casei 1 3 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 4.0028722286224365 1136
225 subtitles_en_alternate_casei 1 3 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 3.991217851638794 1136
226 subtitles_en_alternate_casei 1 3 ag (ASCII) ag -s -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 4.00272274017334 1136
227 subtitles_en_alternate_casei 1 3 grep (ASCII) grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 3.549154758453369 1136 LC_ALL=C
228 subtitles_en_alternate_casei 1 3 grep (ASCII) grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 3.5468921661376953 1136 LC_ALL=C
229 subtitles_en_alternate_casei 1 3 grep (ASCII) grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 3.5873491764068604 1136 LC_ALL=C
230 subtitles_en_alternate_casei 1 3 ugrep (ASCII) ugrep -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.7872169017791748 1136
231 subtitles_en_alternate_casei 1 3 ugrep (ASCII) ugrep -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.784674882888794 1136
232 subtitles_en_alternate_casei 1 3 ugrep (ASCII) ugrep -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.7882401943206787 1136
233 subtitles_en_alternate_casei 1 3 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.4785435199737549 1136
234 subtitles_en_alternate_casei 1 3 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.4940922260284424 1136
235 subtitles_en_alternate_casei 1 3 rg rg -n -i Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 0.4774627685546875 1136
236 subtitles_en_alternate_casei 1 3 grep grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 3.5677175521850586 1136 LC_ALL=en_US.UTF-8
237 subtitles_en_alternate_casei 1 3 grep grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 3.603273391723633 1136 LC_ALL=en_US.UTF-8
238 subtitles_en_alternate_casei 1 3 grep grep -E -ni Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty /dev/shm/benchsuite/subtitles/en.sample.txt 3.5834741592407227 1136 LC_ALL=en_US.UTF-8
239 subtitles_ru_surrounding_words 1 3 rg rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.20238041877746582 278
240 subtitles_ru_surrounding_words 1 3 rg rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.2031264305114746 278
241 subtitles_ru_surrounding_words 1 3 rg rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.20475172996520996 278
242 subtitles_ru_surrounding_words 1 3 grep grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0288453102111816 278 LC_ALL=en_US.UTF-8
243 subtitles_ru_surrounding_words 1 3 grep grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.044802188873291 278 LC_ALL=en_US.UTF-8
244 subtitles_ru_surrounding_words 1 3 grep grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0432109832763672 278 LC_ALL=en_US.UTF-8
245 subtitles_ru_surrounding_words 1 3 ugrep ugrep -an \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 43.00765633583069 278
246 subtitles_ru_surrounding_words 1 3 ugrep ugrep -an \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 42.832849740982056 278
247 subtitles_ru_surrounding_words 1 3 ugrep ugrep -an \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 42.915205240249634 278
248 subtitles_ru_surrounding_words 1 3 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.083683967590332
249 subtitles_ru_surrounding_words 1 3 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0841526985168457
250 subtitles_ru_surrounding_words 1 3 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0850934982299805
251 subtitles_ru_surrounding_words 1 3 grep (ASCII) grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0116353034973145 LC_ALL=C
252 subtitles_ru_surrounding_words 1 3 grep (ASCII) grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.9868073463439941 LC_ALL=C
253 subtitles_ru_surrounding_words 1 3 grep (ASCII) grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0224814414978027 LC_ALL=C
254 subtitles_ru_surrounding_words 1 3 ugrep (ASCII) ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.8892502784729004
255 subtitles_ru_surrounding_words 1 3 ugrep (ASCII) ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.8910088539123535
256 subtitles_ru_surrounding_words 1 3 ugrep (ASCII) ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.8897674083709717
257 subtitles_en_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 2.11850643157959 22
258 subtitles_en_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 2.1359670162200928 22
259 subtitles_en_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 2.103114128112793 22
260 subtitles_en_no_literal 1 3 ugrep ugrep -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 13.050881385803223 22
261 subtitles_en_no_literal 1 3 ugrep ugrep -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 13.050772190093994 22
262 subtitles_en_no_literal 1 3 ugrep ugrep -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 13.05719804763794 22
263 subtitles_en_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 1.9961926937103271 22
264 subtitles_en_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 2.019721508026123 22
265 subtitles_en_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 1.9965126514434814 22
266 subtitles_en_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 6.849602222442627 302
267 subtitles_en_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 6.813834190368652 302
268 subtitles_en_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 6.8263633251190186 302
269 subtitles_en_no_literal 1 3 grep (ASCII) grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 4.42924165725708 22 LC_ALL=C
270 subtitles_en_no_literal 1 3 grep (ASCII) grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 4.378557205200195 22 LC_ALL=C
271 subtitles_en_no_literal 1 3 grep (ASCII) grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 4.376646518707275 22 LC_ALL=C
272 subtitles_en_no_literal 1 3 ugrep (ASCII) ugrep -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 3.5110037326812744 22
273 subtitles_en_no_literal 1 3 ugrep (ASCII) ugrep -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 3.5137360095977783 22
274 subtitles_en_no_literal 1 3 ugrep (ASCII) ugrep -n -U \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/en.sample.txt 3.5051844120025635 22
275 subtitles_ru_literal 1 3 rg rg Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.13207745552062988 583
276 subtitles_ru_literal 1 3 rg rg Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.13084721565246582 583
277 subtitles_ru_literal 1 3 rg rg Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.13469862937927246 583
278 subtitles_ru_literal 1 3 rg (no mmap) rg --no-mmap Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.18022370338439941 583
279 subtitles_ru_literal 1 3 rg (no mmap) rg --no-mmap Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.1801767349243164 583
280 subtitles_ru_literal 1 3 rg (no mmap) rg --no-mmap Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.17995166778564453 583
281 subtitles_ru_literal 1 3 grep grep Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.5151040554046631 583 LC_ALL=C
282 subtitles_ru_literal 1 3 grep grep Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.5154542922973633 583 LC_ALL=C
283 subtitles_ru_literal 1 3 grep grep Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.49927639961242676 583 LC_ALL=C
284 subtitles_ru_literal 1 3 rg (lines) rg -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.19464492797851562 583
285 subtitles_ru_literal 1 3 rg (lines) rg -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.18920588493347168 583
286 subtitles_ru_literal 1 3 rg (lines) rg -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.19465351104736328 583
287 subtitles_ru_literal 1 3 ag (lines) ag -s Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 1.9595966339111328 583
288 subtitles_ru_literal 1 3 ag (lines) ag -s Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 2.0014493465423584 583
289 subtitles_ru_literal 1 3 ag (lines) ag -s Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 1.9567768573760986 583
290 subtitles_ru_literal 1 3 grep (lines) grep -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.8119180202484131 583 LC_ALL=C
291 subtitles_ru_literal 1 3 grep (lines) grep -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.8111097812652588 583 LC_ALL=C
292 subtitles_ru_literal 1 3 grep (lines) grep -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.8006868362426758 583 LC_ALL=C
293 subtitles_ru_literal 1 3 ugrep (lines) ugrep -a -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.70003342628479 583
294 subtitles_ru_literal 1 3 ugrep (lines) ugrep -a -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.650275468826294 583
295 subtitles_ru_literal 1 3 ugrep (lines) ugrep -a -n Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.689772367477417 583
296 subtitles_ru_literal_casei 1 3 rg rg -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.267578125 604
297 subtitles_ru_literal_casei 1 3 rg rg -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.2665982246398926 604
298 subtitles_ru_literal_casei 1 3 rg rg -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.26861572265625 604
299 subtitles_ru_literal_casei 1 3 grep grep -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 4.764627456665039 604 LC_ALL=en_US.UTF-8
300 subtitles_ru_literal_casei 1 3 grep grep -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 4.767015695571899 604 LC_ALL=en_US.UTF-8
301 subtitles_ru_literal_casei 1 3 grep grep -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 4.7688889503479 604 LC_ALL=en_US.UTF-8
302 subtitles_ru_literal_casei 1 3 grep (ASCII) grep -E -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.5046737194061279 583 LC_ALL=C
303 subtitles_ru_literal_casei 1 3 grep (ASCII) grep -E -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.5139875411987305 583 LC_ALL=C
304 subtitles_ru_literal_casei 1 3 grep (ASCII) grep -E -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.4993159770965576 583 LC_ALL=C
305 subtitles_ru_literal_casei 1 3 rg (lines) rg -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.33438658714294434 604
306 subtitles_ru_literal_casei 1 3 rg (lines) rg -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.3398289680480957 604
307 subtitles_ru_literal_casei 1 3 rg (lines) rg -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.3298227787017822 604
308 subtitles_ru_literal_casei 1 3 ag (lines) (ASCII) ag -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.4468214511871338
309 subtitles_ru_literal_casei 1 3 ag (lines) (ASCII) ag -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.44559574127197266
310 subtitles_ru_literal_casei 1 3 ag (lines) (ASCII) ag -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.47882938385009766
311 subtitles_ru_literal_casei 1 3 ugrep (lines) (ASCII) ugrep -a -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.7039575576782227 583
312 subtitles_ru_literal_casei 1 3 ugrep (lines) (ASCII) ugrep -a -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.6490752696990967 583
313 subtitles_ru_literal_casei 1 3 ugrep (lines) (ASCII) ugrep -a -n -i Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.8081104755401611 583
314 subtitles_ru_literal_word 1 3 rg (ASCII) rg -n (?-u:^|\W)Шерлок Холмс(?-u:$|\W) /dev/shm/benchsuite/subtitles/ru.txt 0.20162224769592285 583
315 subtitles_ru_literal_word 1 3 rg (ASCII) rg -n (?-u:^|\W)Шерлок Холмс(?-u:$|\W) /dev/shm/benchsuite/subtitles/ru.txt 0.18215250968933105 583
316 subtitles_ru_literal_word 1 3 rg (ASCII) rg -n (?-u:^|\W)Шерлок Холмс(?-u:$|\W) /dev/shm/benchsuite/subtitles/ru.txt 0.20087671279907227 583
317 subtitles_ru_literal_word 1 3 ag (ASCII) ag -sw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.48624587059020996
318 subtitles_ru_literal_word 1 3 ag (ASCII) ag -sw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.5212516784667969
319 subtitles_ru_literal_word 1 3 ag (ASCII) ag -sw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.520557165145874
320 subtitles_ru_literal_word 1 3 grep (ASCII) grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.8108196258544922 583 LC_ALL=C
321 subtitles_ru_literal_word 1 3 grep (ASCII) grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.8121066093444824 583 LC_ALL=C
322 subtitles_ru_literal_word 1 3 grep (ASCII) grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.7784581184387207 583 LC_ALL=C
323 subtitles_ru_literal_word 1 3 ugrep (ASCII) ugrep -anw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.7469344139099121 583
324 subtitles_ru_literal_word 1 3 ugrep (ASCII) ugrep -anw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.6838233470916748 583
325 subtitles_ru_literal_word 1 3 ugrep (ASCII) ugrep -anw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.6921679973602295 583
326 subtitles_ru_literal_word 1 3 rg rg -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.19918251037597656 579
327 subtitles_ru_literal_word 1 3 rg rg -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.2046656608581543 579
328 subtitles_ru_literal_word 1 3 rg rg -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.1984848976135254 579
329 subtitles_ru_literal_word 1 3 grep grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.794173002243042 579 LC_ALL=en_US.UTF-8
330 subtitles_ru_literal_word 1 3 grep grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.7715346813201904 579 LC_ALL=en_US.UTF-8
331 subtitles_ru_literal_word 1 3 grep grep -nw Шерлок Холмс /dev/shm/benchsuite/subtitles/ru.txt 0.8116705417633057 579 LC_ALL=en_US.UTF-8
332 subtitles_ru_alternate 1 3 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 0.6730976104736328 691
333 subtitles_ru_alternate 1 3 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 0.7020411491394043 691
334 subtitles_ru_alternate 1 3 rg (lines) rg -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 0.6693949699401855 691
335 subtitles_ru_alternate 1 3 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 2.7100515365600586 691
336 subtitles_ru_alternate 1 3 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 2.7458419799804688 691
337 subtitles_ru_alternate 1 3 ag (lines) ag -s Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 2.7115116119384766 691
338 subtitles_ru_alternate 1 3 grep (lines) grep -E -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.703738451004028 691 LC_ALL=C
339 subtitles_ru_alternate 1 3 grep (lines) grep -E -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.715883731842041 691 LC_ALL=C
340 subtitles_ru_alternate 1 3 grep (lines) grep -E -n Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.712724924087524 691 LC_ALL=C
341 subtitles_ru_alternate 1 3 ugrep (lines) ugrep -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 8.276995420455933 691
342 subtitles_ru_alternate 1 3 ugrep (lines) ugrep -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 8.304608345031738 691
343 subtitles_ru_alternate 1 3 ugrep (lines) ugrep -an Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 8.322760820388794 691
344 subtitles_ru_alternate 1 3 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 0.6119842529296875 691
345 subtitles_ru_alternate 1 3 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 0.6368775367736816 691
346 subtitles_ru_alternate 1 3 rg rg Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 0.6258070468902588 691
347 subtitles_ru_alternate 1 3 grep grep -E Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.4300291538238525 691 LC_ALL=C
348 subtitles_ru_alternate 1 3 grep grep -E Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.418199300765991 691 LC_ALL=C
349 subtitles_ru_alternate 1 3 grep grep -E Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.425868511199951 691 LC_ALL=C
350 subtitles_ru_alternate_casei 1 3 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 2.7216460704803467 691
351 subtitles_ru_alternate_casei 1 3 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 2.7108607292175293 691
352 subtitles_ru_alternate_casei 1 3 ag (ASCII) ag -s -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 2.747138500213623 691
353 subtitles_ru_alternate_casei 1 3 grep (ASCII) grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.711230039596558 691 LC_ALL=C
354 subtitles_ru_alternate_casei 1 3 grep (ASCII) grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.709407329559326 691 LC_ALL=C
355 subtitles_ru_alternate_casei 1 3 grep (ASCII) grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.714034557342529 691 LC_ALL=C
356 subtitles_ru_alternate_casei 1 3 ugrep (ASCII) ugrep -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 8.305904626846313 691
357 subtitles_ru_alternate_casei 1 3 ugrep (ASCII) ugrep -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 8.307406187057495 691
358 subtitles_ru_alternate_casei 1 3 ugrep (ASCII) ugrep -ani Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 8.288233995437622 691
359 subtitles_ru_alternate_casei 1 3 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 3.673624277114868 735
360 subtitles_ru_alternate_casei 1 3 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 3.6759188175201416 735
361 subtitles_ru_alternate_casei 1 3 rg rg -n -i Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 3.66877818107605 735
362 subtitles_ru_alternate_casei 1 3 grep grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.366282224655151 735 LC_ALL=en_US.UTF-8
363 subtitles_ru_alternate_casei 1 3 grep grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.370524883270264 735 LC_ALL=en_US.UTF-8
364 subtitles_ru_alternate_casei 1 3 grep grep -E -ni Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти /dev/shm/benchsuite/subtitles/ru.txt 5.342163324356079 735 LC_ALL=en_US.UTF-8
365 subtitles_ru_surrounding_words 1 3 rg rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.20331382751464844 278
366 subtitles_ru_surrounding_words 1 3 rg rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.2034592628479004 278
367 subtitles_ru_surrounding_words 1 3 rg rg -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.20407724380493164 278
368 subtitles_ru_surrounding_words 1 3 grep grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0436389446258545 278 LC_ALL=en_US.UTF-8
369 subtitles_ru_surrounding_words 1 3 grep grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0388383865356445 278 LC_ALL=en_US.UTF-8
370 subtitles_ru_surrounding_words 1 3 grep grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0446207523345947 278 LC_ALL=en_US.UTF-8
371 subtitles_ru_surrounding_words 1 3 ugrep ugrep -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.29245424270629883 1
372 subtitles_ru_surrounding_words 1 3 ugrep ugrep -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.29168128967285156 1
373 subtitles_ru_surrounding_words 1 3 ugrep ugrep -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.29593825340270996 1
374 subtitles_ru_surrounding_words 1 3 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.085604190826416
375 subtitles_ru_surrounding_words 1 3 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.083526372909546
376 subtitles_ru_surrounding_words 1 3 ag (ASCII) ag -s \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.1223819255828857
377 subtitles_ru_surrounding_words 1 3 grep (ASCII) grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.9905192852020264 LC_ALL=C
378 subtitles_ru_surrounding_words 1 3 grep (ASCII) grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0222513675689697 LC_ALL=C
379 subtitles_ru_surrounding_words 1 3 grep (ASCII) grep -E -n \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 1.0216262340545654 LC_ALL=C
380 subtitles_ru_surrounding_words 1 3 ugrep (ASCII) ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.8875806331634521
381 subtitles_ru_surrounding_words 1 3 ugrep (ASCII) ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.8861405849456787
382 subtitles_ru_surrounding_words 1 3 ugrep (ASCII) ugrep -a -n -U \w+\s+Холмс\s+\w+ /dev/shm/benchsuite/subtitles/ru.txt 0.8898241519927979
383 subtitles_ru_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 2.237398147583008 41
384 subtitles_ru_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 2.253706693649292 41
385 subtitles_ru_no_literal 1 3 rg rg -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 2.2161178588867188 41
386 subtitles_ru_no_literal 1 3 ugrep ugrep -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 28.85959553718567 41
387 subtitles_ru_no_literal 1 3 ugrep ugrep -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 28.666419982910156 41
388 subtitles_ru_no_literal 1 3 ugrep ugrep -an \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 28.90555214881897 41
389 subtitles_ru_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 2.051813840866089
390 subtitles_ru_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 2.026675224304199
391 subtitles_ru_no_literal 1 3 rg (ASCII) rg -n (?-u)\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 2.027498245239258
392 subtitles_ru_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 1.0998010635375977
393 subtitles_ru_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 1.0900018215179443
394 subtitles_ru_no_literal 1 3 ag (ASCII) ag -s \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 1.0901548862457275
395 subtitles_ru_no_literal 1 3 grep (ASCII) grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 1.0691263675689697 LC_ALL=C
396 subtitles_ru_no_literal 1 3 grep (ASCII) grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 1.0875153541564941 LC_ALL=C
397 subtitles_ru_no_literal 1 3 grep (ASCII) grep -E -n \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 1.0997354984283447 LC_ALL=C
398 subtitles_ru_no_literal 1 3 ugrep (ASCII) ugrep -anU \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 0.8329172134399414
399 subtitles_ru_no_literal 1 3 ugrep (ASCII) ugrep -anU \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 0.8292679786682129
400 subtitles_ru_no_literal 1 3 ugrep (ASCII) ugrep -anU \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5} /dev/shm/benchsuite/subtitles/ru.txt 0.8326950073242188

208
benchsuite/runs/2022-12-16-archlinux-duff/summary
View File

@@ -1,208 +0,0 @@
linux_literal_default (pattern: PM_RESUME)
------------------------------------------
rg* 0.084 +/- 0.002 (lines: 39)*
ag 0.295 +/- 0.001 (lines: 39)
git grep 0.225 +/- 0.007 (lines: 39)
ugrep 0.105 +/- 0.002 (lines: 39)
grep 0.996 +/- 0.003 (lines: 39)
linux_literal (pattern: PM_RESUME)
----------------------------------
rg* 0.085 +/- 0.001 (lines: 39)*
rg (mmap) 0.322 +/- 0.002 (lines: 39)
ag (mmap) 0.290 +/- 0.002 (lines: 39)
git grep 0.211 +/- 0.009 (lines: 39)
ugrep 0.189 +/- 0.005 (lines: 39)
linux_literal_casei (pattern: PM_RESUME)
----------------------------------------
rg* 0.088 +/- 0.001 (lines: 536)*
rg (mmap) 0.314 +/- 0.007 (lines: 536)
ag (mmap) 0.299 +/- 0.001 (lines: 536)
git grep 0.214 +/- 0.007 (lines: 536)
ugrep 0.174 +/- 0.001 (lines: 536)
linux_re_literal_suffix (pattern: [A-Z]+_RESUME)
------------------------------------------------
rg* 0.085 +/- 0.000 (lines: 2160)*
ag 0.369 +/- 0.009 (lines: 2160)
git grep 0.915 +/- 0.048 (lines: 2160)
ugrep 0.433 +/- 0.025 (lines: 2160)
linux_word (pattern: PM_RESUME)
-------------------------------
rg* 0.085 +/- 0.001 (lines: 9)*
ag 0.287 +/- 0.001 (lines: 9)
git grep 0.206 +/- 0.002 (lines: 9)
ugrep 0.189 +/- 0.002 (lines: 9)
linux_unicode_greek (pattern: \p{Greek})
----------------------------------------
rg 0.201 +/- 0.005 (lines: 105)
ugrep* 0.181 +/- 0.005 (lines: 105)*
linux_unicode_greek_casei (pattern: \p{Greek})
----------------------------------------------
rg 0.198 +/- 0.000 (lines: 245)
ugrep* 0.179 +/- 0.003 (lines: 105)*
linux_unicode_word (pattern: \wAh)
----------------------------------
rg 0.085 +/- 0.000 (lines: 247)
rg (ASCII)* 0.085 +/- 0.000 (lines: 233)*
ag (ASCII) 0.301 +/- 0.005 (lines: 233)
git grep 3.980 +/- 0.241 (lines: 247)
git grep (ASCII) 1.620 +/- 0.032 (lines: 233)
ugrep 0.177 +/- 0.003 (lines: 247)
ugrep (ASCII) 0.185 +/- 0.005 (lines: 233)
linux_no_literal (pattern: \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5})
-----------------------------------------------------------------
rg 0.266 +/- 0.006 (lines: 721)
rg (ASCII)* 0.200 +/- 0.001 (lines: 720)*
ag (ASCII) 0.832 +/- 0.007 (lines: 1134)
git grep 7.346 +/- 0.017 (lines: 721)
git grep (ASCII) 2.144 +/- 0.014 (lines: 720)
ugrep 3.403 +/- 0.008 (lines: 723)
ugrep (ASCII) 0.236 +/- 0.003 (lines: 722)
linux_alternates (pattern: ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT)
-------------------------------------------------------------------------
rg* 0.087 +/- 0.000 (lines: 140)*
ag 0.330 +/- 0.002 (lines: 140)
git grep 0.414 +/- 0.047 (lines: 140)
ugrep 0.179 +/- 0.002 (lines: 140)
linux_alternates_casei (pattern: ERR_SYS|PME_TURN_OFF|LINK_REQ_RST|CFG_BME_EVT)
-------------------------------------------------------------------------------
rg* 0.123 +/- 0.001 (lines: 241)*
ag 0.530 +/- 0.001 (lines: 241)
git grep 0.792 +/- 0.036 (lines: 241)
ugrep 0.177 +/- 0.003 (lines: 241)
subtitles_en_literal (pattern: Sherlock Holmes)
-----------------------------------------------
rg* 0.123 +/- 0.003 (lines: 830)*
rg (no mmap) 0.176 +/- 0.005 (lines: 830)
grep 0.572 +/- 0.017 (lines: 830)
rg (lines) 0.189 +/- 0.006 (lines: 830)
ag (lines) 1.868 +/- 0.004 (lines: 830)
grep (lines) 0.980 +/- 0.036 (lines: 830)
ugrep (lines) 0.185 +/- 0.007 (lines: 830)
subtitles_en_literal_casei (pattern: Sherlock Holmes)
-----------------------------------------------------
rg* 0.214 +/- 0.008 (lines: 871)*
grep 2.224 +/- 0.000 (lines: 871)
grep (ASCII) 0.671 +/- 0.001 (lines: 871)
rg (lines) 0.259 +/- 0.004 (lines: 871)
ag (lines) (ASCII) 1.897 +/- 0.026 (lines: 871)
ugrep (lines) 0.785 +/- 0.002 (lines: 871)
subtitles_en_literal_word (pattern: Sherlock Holmes)
----------------------------------------------------
rg (ASCII) 0.189 +/- 0.006 (lines: 830)
ag (ASCII) 1.842 +/- 0.023 (lines: 830)
grep (ASCII) 0.977 +/- 0.046 (lines: 830)
ugrep (ASCII)* 0.182 +/- 0.007 (lines: 830)*
rg 0.192 +/- 0.006 (lines: 830)
grep 0.990 +/- 0.024 (lines: 830)
subtitles_en_alternate (pattern: Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty)
---------------------------------------------------------------------------------------------------------------
rg (lines) 0.248 +/- 0.001 (lines: 1094)
ag (lines) 2.638 +/- 0.055 (lines: 1094)
grep (lines) 2.052 +/- 0.027 (lines: 1094)
ugrep (lines) 0.787 +/- 0.001 (lines: 1094)
rg* 0.176 +/- 0.011 (lines: 1094)*
grep 1.660 +/- 0.002 (lines: 1094)
subtitles_en_alternate_casei (pattern: Sherlock Holmes|John Watson|Irene Adler|Inspector Lestrade|Professor Moriarty)
---------------------------------------------------------------------------------------------------------------------
ag (ASCII) 3.999 +/- 0.007 (lines: 1136)
grep (ASCII) 3.561 +/- 0.023 (lines: 1136)
ugrep (ASCII) 0.787 +/- 0.002 (lines: 1136)
rg* 0.483 +/- 0.009 (lines: 1136)*
grep 3.585 +/- 0.018 (lines: 1136)
subtitles_en_surrounding_words (pattern: \w+\s+Holmes\s+\w+)
------------------------------------------------------------
rg 0.200 +/- 0.001 (lines: 483)
grep 1.303 +/- 0.040 (lines: 483)
ugrep 43.220 +/- 0.047 (lines: 483)
rg (ASCII)* 0.197 +/- 0.000 (lines: 483)*
ag (ASCII) 5.223 +/- 0.056 (lines: 489)
grep (ASCII) 1.316 +/- 0.043 (lines: 483)
ugrep (ASCII) 17.647 +/- 0.219 (lines: 483)
subtitles_en_no_literal (pattern: \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5})
----------------------------------------------------------------------------------------
rg 2.119 +/- 0.016 (lines: 22)
ugrep 13.053 +/- 0.004 (lines: 22)
rg (ASCII)* 2.004 +/- 0.013 (lines: 22)*
ag (ASCII) 6.830 +/- 0.018 (lines: 302)
grep (ASCII) 4.395 +/- 0.030 (lines: 22)
ugrep (ASCII) 3.510 +/- 0.004 (lines: 22)
subtitles_ru_literal (pattern: Шерлок Холмс)
--------------------------------------------
rg* 0.133 +/- 0.002 (lines: 583)*
rg (no mmap) 0.180 +/- 0.000 (lines: 583)
grep 0.510 +/- 0.009 (lines: 583)
rg (lines) 0.193 +/- 0.003 (lines: 583)
ag (lines) 1.973 +/- 0.025 (lines: 583)
grep (lines) 0.808 +/- 0.006 (lines: 583)
ugrep (lines) 0.680 +/- 0.026 (lines: 583)
subtitles_ru_literal_casei (pattern: Шерлок Холмс)
--------------------------------------------------
rg* 0.268 +/- 0.001 (lines: 604)*
grep 4.767 +/- 0.002 (lines: 604)
grep (ASCII) 0.506 +/- 0.007 (lines: 583)
rg (lines) 0.335 +/- 0.005 (lines: 604)
ag (lines) (ASCII) 0.457 +/- 0.019 (lines: 0)
ugrep (lines) (ASCII) 0.720 +/- 0.081 (lines: 583)
subtitles_ru_literal_word (pattern: Шерлок Холмс)
-------------------------------------------------
rg (ASCII)* 0.195 +/- 0.011 (lines: 583)*
ag (ASCII) 0.509 +/- 0.020 (lines: 0)
grep (ASCII) 0.800 +/- 0.019 (lines: 583)
ugrep (ASCII) 0.708 +/- 0.034 (lines: 583)
rg 0.201 +/- 0.003 (lines: 579)
grep 0.792 +/- 0.020 (lines: 579)
subtitles_ru_alternate (pattern: Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти)
-----------------------------------------------------------------------------------------------------------
rg (lines) 0.682 +/- 0.018 (lines: 691)
ag (lines) 2.722 +/- 0.020 (lines: 691)
grep (lines) 5.711 +/- 0.006 (lines: 691)
ugrep (lines) 8.301 +/- 0.023 (lines: 691)
rg* 0.625 +/- 0.012 (lines: 691)*
grep 5.425 +/- 0.006 (lines: 691)
subtitles_ru_alternate_casei (pattern: Шерлок Холмс|Джон Уотсон|Ирен Адлер|инспектор Лестрейд|профессор Мориарти)
-----------------------------------------------------------------------------------------------------------------
ag (ASCII)* 2.727 +/- 0.019 (lines: 691)*
grep (ASCII) 5.712 +/- 0.002 (lines: 691)
ugrep (ASCII) 8.301 +/- 0.011 (lines: 691)
rg 3.673 +/- 0.004 (lines: 735)
grep 5.360 +/- 0.015 (lines: 735)
subtitles_ru_surrounding_words (pattern: \w+\s+Холмс\s+\w+)
-----------------------------------------------------------
rg* 0.203 +/- 0.001 (lines: 278)*
grep 1.039 +/- 0.009 (lines: 278)
ugrep 42.919 +/- 0.087 (lines: 278)
ag (ASCII) 1.084 +/- 0.001 (lines: 0)
grep (ASCII) 1.007 +/- 0.018 (lines: 0)
ugrep (ASCII) 0.890 +/- 0.001 (lines: 0)
subtitles_ru_no_literal (pattern: \w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5}\s+\w{5})
----------------------------------------------------------------------------------------
rg 2.236 +/- 0.019 (lines: 41)
ugrep 28.811 +/- 0.127 (lines: 41)
rg (ASCII) 2.035 +/- 0.014 (lines: 0)
ag (ASCII) 1.093 +/- 0.006 (lines: 0)
grep (ASCII) 1.085 +/- 0.015 (lines: 0)
ugrep (ASCII)* 0.832 +/- 0.002 (lines: 0)*

28
build.rs
View File

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

11
complete/_rg
View File

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

7
crates/cli/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-cli"
version = "0.1.9" #:version
version = "0.1.6" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Utilities for search oriented command line applications.
@@ -14,8 +14,9 @@ license = "Unlicense OR MIT"
edition = "2018"
[dependencies]
bstr = "1.6.0"
globset = { version = "0.4.10", path = "../globset" }
atty = "0.2.11"
bstr = "0.2.0"
globset = { version = "0.4.9", path = "../globset" }
lazy_static = "1.1.0"
log = "0.4.5"
regex = "1.1"

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

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

8
crates/cli/src/lib.rs
View File

@@ -165,8 +165,6 @@ mod pattern;
mod process;
mod wtr;
use std::io::IsTerminal;
pub use crate::decompress::{
resolve_binary, DecompressionMatcher, DecompressionMatcherBuilder,
DecompressionReader, DecompressionReaderBuilder,
@@ -217,7 +215,7 @@ pub fn is_readable_stdin() -> bool {
/// Returns true if and only if stdin is believed to be connected to a tty
/// or a console.
pub fn is_tty_stdin() -> bool {
std::io::stdin().is_terminal()
atty::is(atty::Stream::Stdin)
}
/// Returns true if and only if stdout is believed to be connected to a tty
@@ -229,11 +227,11 @@ pub fn is_tty_stdin() -> bool {
/// implementations of `ls` will often show one item per line when stdout is
/// redirected, but will condensed output when printing to a tty.
pub fn is_tty_stdout() -> bool {
std::io::stdout().is_terminal()
atty::is(atty::Stream::Stdout)
}
/// Returns true if and only if stderr is believed to be connected to a tty
/// or a console.
pub fn is_tty_stderr() -> bool {
std::io::stderr().is_terminal()
atty::is(atty::Stream::Stderr)
}

67
crates/core/app.rs
View File

@@ -632,7 +632,6 @@ pub fn all_args_and_flags() -> Vec<RGArg> {
flag_sort(&mut args);
flag_sortr(&mut args);
flag_stats(&mut args);
flag_stop_on_nonmatch(&mut args);
flag_text(&mut args);
flag_threads(&mut args);
flag_trim(&mut args);
@@ -699,7 +698,7 @@ fn flag_after_context(args: &mut Vec<RGArg>) {
"\
Show NUM lines after each match.
This overrides the --passthru flag and partially overrides --context.
This overrides the --context and --passthru flags.
"
);
let arg = RGArg::flag("after-context", "NUM")
@@ -707,7 +706,8 @@ This overrides the --passthru flag and partially overrides --context.
.help(SHORT)
.long_help(LONG)
.number()
.overrides("passthru");
.overrides("passthru")
.overrides("context");
args.push(arg);
}
@@ -768,7 +768,7 @@ fn flag_before_context(args: &mut Vec<RGArg>) {
"\
Show NUM lines before each match.
This overrides the --passthru flag and partially overrides --context.
This overrides the --context and --passthru flags.
"
);
let arg = RGArg::flag("before-context", "NUM")
@@ -776,7 +776,8 @@ This overrides the --passthru flag and partially overrides --context.
.help(SHORT)
.long_help(LONG)
.number()
.overrides("passthru");
.overrides("passthru")
.overrides("context");
args.push(arg);
}
@@ -874,8 +875,8 @@ Print the 0-based byte offset within the input file before each line of output.
If -o (--only-matching) is specified, print the offset of the matching part
itself.
If ripgrep does transcoding, then the byte offset is in terms of the result of
transcoding and not the original data. This applies similarly to another
If ripgrep does transcoding, then the byte offset is in terms of the the result
of transcoding and not the original data. This applies similarly to another
transformation on the source, such as decompression or a --pre filter. Note
that when the PCRE2 regex engine is used, then UTF-8 transcoding is done by
default.
@@ -969,7 +970,7 @@ or, equivalently,
rg --colors 'match:bg:0x0,0x80,0xFF'
Note that the intense and nointense style flags will have no effect when
Note that the the intense and nointense style flags will have no effect when
used alongside these extended color codes.
"
);
@@ -1008,7 +1009,8 @@ fn flag_context(args: &mut Vec<RGArg>) {
Show NUM lines before and after each match. This is equivalent to providing
both the -B/--before-context and -A/--after-context flags with the same value.
This overrides the --passthru flag.
This overrides both the -B/--before-context and -A/--after-context flags,
in addition to the --passthru flag.
"
);
let arg = RGArg::flag("context", "NUM")
@@ -1016,7 +1018,9 @@ This overrides the --passthru flag.
.help(SHORT)
.long_help(LONG)
.number()
.overrides("passthru");
.overrides("passthru")
.overrides("before-context")
.overrides("after-context");
args.push(arg);
}
@@ -1707,8 +1711,6 @@ fn flag_line_number(args: &mut Vec<RGArg>) {
"\
Show line numbers (1-based). This is enabled by default when searching in a
terminal.
This flag overrides --no-line-number.
"
);
let arg = RGArg::switch("line-number")
@@ -1723,8 +1725,6 @@ This flag overrides --no-line-number.
"\
Suppress line numbers. This is enabled by default when not searching in a
terminal.
This flag overrides --line-number.
"
);
let arg = RGArg::switch("no-line-number")
@@ -1927,16 +1927,13 @@ Nevertheless, if you only care about matches spanning at most one line, then it
is always better to disable multiline mode.
This flag can be disabled with --no-multiline.
This overrides the --stop-on-nonmatch flag.
"
);
let arg = RGArg::switch("multiline")
.short("U")
.help(SHORT)
.long_help(LONG)
.overrides("no-multiline")
.overrides("stop-on-nonmatch");
.overrides("no-multiline");
args.push(arg);
let arg = RGArg::switch("no-multiline").hidden().overrides("multiline");
@@ -2586,8 +2583,8 @@ Do not print anything to stdout. If a match is found in a file, then ripgrep
will stop searching. This is useful when ripgrep is used only for its exit
code (which will be an error if no matches are found).
When --files is used, ripgrep will stop finding files after finding the
first file that does not match any ignore rules.
When --files is used, then ripgrep will stop finding files after finding the
first file that matches all ignore rules.
"
);
let arg = RGArg::switch("quiet").short("q").help(SHORT).long_help(LONG);
@@ -2650,17 +2647,6 @@ replacement string. Capture group indices are numbered based on the position of
the opening parenthesis of the group, where the leftmost such group is $1. The
special $0 group corresponds to the entire match.
The name of a group is formed by taking the longest string of letters, numbers
and underscores (i.e. [_0-9A-Za-z]) after the $. For example, $1a will be
replaced with the group named '1a', not the group at index 1. If the group's
name contains characters that aren't letters, numbers or underscores, or you
want to immediately follow the group with another string, the name should be
put inside braces. For example, ${1}a will take the content of the group at
index 1 and append 'a' to the end of it.
If an index or name does not refer to a valid capture group, it will be
replaced with an empty string.
In shells such as Bash and zsh, you should wrap the pattern in single quotes
instead of double quotes. Otherwise, capture group indices will be replaced by
expanded shell variables which will most likely be empty.
@@ -2858,25 +2844,6 @@ This flag can be disabled with --no-stats.
args.push(arg);
}
fn flag_stop_on_nonmatch(args: &mut Vec<RGArg>) {
const SHORT: &str = "Stop searching after a non-match.";
const LONG: &str = long!(
"\
Enabling this option will cause ripgrep to stop reading a file once it
encounters a non-matching line after it has encountered a matching line.
This is useful if it is expected that all matches in a given file will be on
sequential lines, for example due to the lines being sorted.
This overrides the -U/--multiline flag.
"
);
let arg = RGArg::switch("stop-on-nonmatch")
.help(SHORT)
.long_help(LONG)
.overrides("multiline");
args.push(arg);
}
fn flag_text(args: &mut Vec<RGArg>) {
const SHORT: &str = "Search binary files as if they were text.";
const LONG: &str = long!(

341
crates/core/args.rs
View File

@@ -31,6 +31,8 @@ use ignore::overrides::{Override, OverrideBuilder};
use ignore::types::{FileTypeDef, Types, TypesBuilder};
use ignore::{Walk, WalkBuilder, WalkParallel};
use log;
use num_cpus;
use regex;
use termcolor::{BufferWriter, ColorChoice, WriteColor};
use crate::app;
@@ -41,7 +43,7 @@ use crate::path_printer::{PathPrinter, PathPrinterBuilder};
use crate::search::{
PatternMatcher, Printer, SearchWorker, SearchWorkerBuilder,
};
use crate::subject::{Subject, SubjectBuilder};
use crate::subject::SubjectBuilder;
use crate::Result;
/// The command that ripgrep should execute based on the command line
@@ -95,12 +97,9 @@ pub struct Args(Arc<ArgsImp>);
struct ArgsImp {
/// Mid-to-low level routines for extracting CLI arguments.
matches: ArgMatches,
/// The command we want to execute.
command: Command,
/// The number of threads to use. This is based in part on available
/// threads, in part on the number of threads requested and in part on the
/// command we're running.
threads: usize,
/// The patterns provided at the command line and/or via the -f/--file
/// flag. This may be empty.
patterns: Vec<String>,
/// A matcher built from the patterns.
///
/// It's important that this is only built once, since building this goes
@@ -166,6 +165,12 @@ impl Args {
&self.0.matches
}
/// Return the patterns found in the command line arguments. This includes
/// patterns read via the -f/--file flags.
fn patterns(&self) -> &[String] {
&self.0.patterns
}
/// Return the matcher builder from the patterns.
fn matcher(&self) -> &PatternMatcher {
&self.0.matcher
@@ -192,7 +197,7 @@ impl Args {
fn printer<W: WriteColor>(&self, wtr: W) -> Result<Printer<W>> {
match self.matches().output_kind() {
OutputKind::Standard => {
let separator_search = self.command() == Command::Search;
let separator_search = self.command()? == Command::Search;
self.matches()
.printer_standard(self.paths(), wtr, separator_search)
.map(Printer::Standard)
@@ -220,8 +225,28 @@ impl Args {
}
/// Return the high-level command that ripgrep should run.
pub fn command(&self) -> Command {
self.0.command
pub fn command(&self) -> Result<Command> {
let is_one_search = self.matches().is_one_search(self.paths());
let threads = self.matches().threads()?;
let one_thread = is_one_search || threads == 1;
Ok(if self.matches().is_present("pcre2-version") {
Command::PCRE2Version
} else if self.matches().is_present("type-list") {
Command::Types
} else if self.matches().is_present("files") {
if one_thread {
Command::Files
} else {
Command::FilesParallel
}
} else if self.matches().can_never_match(self.patterns()) {
Command::SearchNever
} else if one_thread {
Command::Search
} else {
Command::SearchParallel
})
}
/// Builder a path printer that can be used for printing just file paths,
@@ -279,7 +304,7 @@ impl Args {
/// When this returns a `Stats` value, then it is guaranteed that the
/// search worker will be configured to track statistics as well.
pub fn stats(&self) -> Result<Option<Stats>> {
Ok(if self.command().is_search() && self.matches().stats() {
Ok(if self.command()?.is_search() && self.matches().stats() {
Some(Stats::new())
} else {
None
@@ -318,58 +343,12 @@ impl Args {
/// Return a walker that never uses additional threads.
pub fn walker(&self) -> Result<Walk> {
Ok(self
.matches()
.walker_builder(self.paths(), self.0.threads)?
.build())
}
/// Returns true if and only if `stat`-related sorting is required
pub fn needs_stat_sort(&self) -> bool {
return self.matches().sort_by().map_or(
false,
|sort_by| match sort_by.kind {
SortByKind::LastModified
| SortByKind::Created
| SortByKind::LastAccessed => sort_by.check().is_ok(),
_ => false,
},
);
}
/// Sort subjects if a sorter is specified, but only if the sort requires
/// stat calls. Non-stat related sorts are handled during file traversal
///
/// This function assumes that it is known that a stat-related sort is
/// required, and does not check for it again.
///
/// It is important that that precondition is fulfilled, since this function
/// consumes the subjects iterator, and is therefore a blocking function.
pub fn sort_by_stat<I>(&self, subjects: I) -> Vec<Subject>
where
I: Iterator<Item = Subject>,
{
let sorter = match self.matches().sort_by() {
Ok(v) => v,
Err(_) => return subjects.collect(),
};
use SortByKind::*;
let mut keyed = match sorter.kind {
LastModified => load_timestamps(subjects, |m| m.modified()),
LastAccessed => load_timestamps(subjects, |m| m.accessed()),
Created => load_timestamps(subjects, |m| m.created()),
_ => return subjects.collect(),
};
keyed.sort_by(|a, b| sort_by_option(&a.0, &b.0, sorter.reverse));
keyed.into_iter().map(|v| v.1).collect()
Ok(self.matches().walker_builder(self.paths())?.build())
}
/// Return a parallel walker that may use additional threads.
pub fn walker_parallel(&self) -> Result<WalkParallel> {
Ok(self
.matches()
.walker_builder(self.paths(), self.0.threads)?
.build_parallel())
Ok(self.matches().walker_builder(self.paths())?.build_parallel())
}
}
@@ -444,23 +423,44 @@ impl SortBy {
Ok(())
}
/// Load sorters only if they are applicable at the walk stage.
///
/// In particular, sorts that involve `stat` calls are not loaded because
/// the walk inherently assumes that parent directories are aware of all its
/// decendent properties, but `stat` does not work that way.
fn configure_builder_sort(self, builder: &mut WalkBuilder) {
use SortByKind::*;
fn configure_walk_builder(self, builder: &mut WalkBuilder) {
// This isn't entirely optimal. In particular, we will wind up issuing
// a stat for many files redundantly. Aside from having potentially
// inconsistent results with respect to sorting, this is also slow.
// We could fix this here at the expense of memory by caching stat
// calls. A better fix would be to find a way to push this down into
// directory traversal itself, but that's a somewhat nasty change.
match self.kind {
Path if self.reverse => {
builder.sort_by_file_name(|a, b| a.cmp(b).reverse());
SortByKind::None => {}
SortByKind::Path => {
if self.reverse {
builder.sort_by_file_name(|a, b| a.cmp(b).reverse());
} else {
builder.sort_by_file_name(|a, b| a.cmp(b));
}
}
Path => {
builder.sort_by_file_name(|a, b| a.cmp(b));
SortByKind::LastModified => {
builder.sort_by_file_path(move |a, b| {
sort_by_metadata_time(a, b, self.reverse, |md| {
md.modified()
})
});
}
// these use `stat` calls and will be sorted in Args::sort_by_stat()
LastModified | LastAccessed | Created | None => {}
};
SortByKind::LastAccessed => {
builder.sort_by_file_path(move |a, b| {
sort_by_metadata_time(a, b, self.reverse, |md| {
md.accessed()
})
});
}
SortByKind::Created => {
builder.sort_by_file_path(move |a, b| {
sort_by_metadata_time(a, b, self.reverse, |md| {
md.created()
})
});
}
}
}
}
@@ -490,6 +490,24 @@ enum EncodingMode {
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 {
@@ -539,36 +557,9 @@ impl ArgMatches {
} else {
false
};
// Now figure out the number of threads we'll use and which
// command will run.
let is_one_search = self.is_one_search(&paths);
let threads = if is_one_search { 1 } else { self.threads()? };
if threads == 1 {
log::debug!("running in single threaded mode");
} else {
log::debug!("running with {threads} threads for parallelism");
}
let command = if self.is_present("pcre2-version") {
Command::PCRE2Version
} else if self.is_present("type-list") {
Command::Types
} else if self.is_present("files") {
if threads == 1 {
Command::Files
} else {
Command::FilesParallel
}
} else if self.can_never_match(&patterns) {
Command::SearchNever
} else if threads == 1 {
Command::Search
} else {
Command::SearchParallel
};
Ok(Args(Arc::new(ArgsImp {
matches: self,
command,
threads,
patterns,
matcher,
paths,
using_default_path,
@@ -671,8 +662,6 @@ impl ArgMatches {
.multi_line(true)
.unicode(self.unicode())
.octal(false)
.fixed_strings(self.is_present("fixed-strings"))
.whole_line(self.is_present("line-regexp"))
.word(self.is_present("word-regexp"));
if self.is_present("multiline") {
builder.dot_matches_new_line(self.is_present("multiline-dotall"));
@@ -699,7 +688,12 @@ impl ArgMatches {
if let Some(limit) = self.dfa_size_limit()? {
builder.dfa_size_limit(limit);
}
match builder.build_many(patterns) {
let res = if self.is_present("fixed-strings") {
builder.build_literals(patterns)
} else {
builder.build(&patterns.join("|"))
};
match res {
Ok(m) => Ok(m),
Err(err) => Err(From::from(suggest_multiline(err.to_string()))),
}
@@ -716,8 +710,6 @@ impl ArgMatches {
.case_smart(self.case_smart())
.caseless(self.case_insensitive())
.multi_line(true)
.fixed_strings(self.is_present("fixed-strings"))
.whole_line(self.is_present("line-regexp"))
.word(self.is_present("word-regexp"));
// For whatever reason, the JIT craps out during regex compilation with
// a "no more memory" error on 32 bit systems. So don't use it there.
@@ -731,6 +723,14 @@ impl ArgMatches {
}
if self.unicode() {
builder.utf(true).ucp(true);
if self.encoding()?.has_explicit_encoding() {
// 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.)
unsafe {
builder.disable_utf_check();
}
}
}
if self.is_present("multiline") {
builder.dotall(self.is_present("multiline-dotall"));
@@ -738,7 +738,7 @@ impl ArgMatches {
if self.is_present("crlf") {
builder.crlf(true);
}
Ok(builder.build_many(patterns)?)
Ok(builder.build(&patterns.join("|"))?)
}
/// Build a JSON printer that writes results to the given writer.
@@ -840,8 +840,7 @@ impl ArgMatches {
.before_context(ctx_before)
.after_context(ctx_after)
.passthru(self.is_present("passthru"))
.memory_map(self.mmap_choice(paths))
.stop_on_nonmatch(self.is_present("stop-on-nonmatch"));
.memory_map(self.mmap_choice(paths));
match self.encoding()? {
EncodingMode::Some(enc) => {
builder.encoding(Some(enc));
@@ -859,11 +858,7 @@ impl ArgMatches {
///
/// If there was a problem parsing the CLI arguments necessary for
/// constructing the builder, then this returns an error.
fn walker_builder(
&self,
paths: &[PathBuf],
threads: usize,
) -> Result<WalkBuilder> {
fn walker_builder(&self, paths: &[PathBuf]) -> Result<WalkBuilder> {
let mut builder = WalkBuilder::new(&paths[0]);
for path in &paths[1..] {
builder.add(path);
@@ -879,7 +874,7 @@ impl ArgMatches {
.max_depth(self.usize_of("max-depth")?)
.follow_links(self.is_present("follow"))
.max_filesize(self.max_file_size()?)
.threads(threads)
.threads(self.threads()?)
.same_file_system(self.is_present("one-file-system"))
.skip_stdout(!self.is_present("files"))
.overrides(self.overrides()?)
@@ -892,10 +887,12 @@ impl ArgMatches {
.git_exclude(!self.no_ignore_vcs() && !self.no_ignore_exclude())
.require_git(!self.is_present("no-require-git"))
.ignore_case_insensitive(self.ignore_file_case_insensitive());
if !self.no_ignore() && !self.no_ignore_dot() {
if !self.no_ignore() {
builder.add_custom_ignore_filename(".rgignore");
}
self.sort_by()?.configure_builder_sort(&mut builder);
let sortby = self.sort_by()?;
sortby.check()?;
sortby.configure_walk_builder(&mut builder);
Ok(builder)
}
}
@@ -1010,10 +1007,10 @@ impl ArgMatches {
/// If there was a problem parsing the values from the user as an integer,
/// then an error is returned.
fn contexts(&self) -> Result<(usize, usize)> {
let after = self.usize_of("after-context")?.unwrap_or(0);
let before = self.usize_of("before-context")?.unwrap_or(0);
let both = self.usize_of("context")?.unwrap_or(0);
let after = self.usize_of("after-context")?.unwrap_or(both);
let before = self.usize_of("before-context")?.unwrap_or(both);
Ok((before, after))
Ok(if both > 0 { (both, both) } else { (before, after) })
}
/// Returns the unescaped context separator in UTF-8 bytes.
@@ -1070,6 +1067,7 @@ impl ArgMatches {
}
let label = match self.value_of_lossy("encoding") {
None if self.pcre2_unicode() => "utf-8".to_string(),
None => return Ok(EncodingMode::Auto),
Some(label) => label,
};
@@ -1401,6 +1399,11 @@ impl ArgMatches {
/// Get a sequence of all available patterns from the command line.
/// This includes reading the -e/--regexp and -f/--file flags.
///
/// Note that if -F/--fixed-strings is set, then all patterns will be
/// escaped. If -x/--line-regexp is set, then all patterns are surrounded
/// by `^...$`. Other things, such as --word-regexp, are handled by the
/// regex matcher itself.
///
/// If any pattern is invalid UTF-8, then an error is returned.
fn patterns(&self) -> Result<Vec<String>> {
if self.is_present("files") || self.is_present("type-list") {
@@ -1441,6 +1444,16 @@ impl ArgMatches {
Ok(pats)
}
/// Returns a pattern that is guaranteed to produce an empty regular
/// expression that is valid in any position.
fn pattern_empty(&self) -> String {
// This would normally just be an empty string, which works on its
// own, but if the patterns are joined in a set of alternations, then
// you wind up with `foo|`, which is currently invalid in Rust's regex
// engine.
"(?:z{0})*".to_string()
}
/// Converts an OsStr pattern to a String pattern. The pattern is escaped
/// if -F/--fixed-strings is set.
///
@@ -1459,12 +1472,30 @@ impl ArgMatches {
/// Applies additional processing on the given pattern if necessary
/// (such as escaping meta characters or turning it into a line regex).
fn pattern_from_string(&self, pat: String) -> String {
let pat = self.pattern_line(self.pattern_literal(pat));
if pat.is_empty() {
// This would normally just be an empty string, which works on its
// own, but if the patterns are joined in a set of alternations,
// then you wind up with `foo|`, which is currently invalid in
// Rust's regex engine.
"(?:)".to_string()
self.pattern_empty()
} else {
pat
}
}
/// Returns the given pattern as a line pattern if the -x/--line-regexp
/// flag is set. Otherwise, the pattern is returned unchanged.
fn pattern_line(&self, pat: String) -> String {
if self.is_present("line-regexp") {
format!(r"^(?:{})$", pat)
} else {
pat
}
}
/// Returns the given pattern as a literal pattern if the
/// -F/--fixed-strings flag is set. Otherwise, the pattern is returned
/// unchanged.
fn pattern_literal(&self, pat: String) -> String {
if self.is_present("fixed-strings") {
regex::escape(&pat)
} else {
pat
}
@@ -1561,9 +1592,7 @@ impl ArgMatches {
return Ok(1);
}
let threads = self.usize_of("threads")?.unwrap_or(0);
let available =
std::thread::available_parallelism().map_or(1, |n| n.get());
Ok(if threads == 0 { cmp::min(12, available) } else { threads })
Ok(if threads == 0 { cmp::min(12, num_cpus::get()) } else { threads })
}
/// Builds a file type matcher from the command line flags.
@@ -1597,6 +1626,12 @@ impl ArgMatches {
!(self.is_present("no-unicode") || self.is_present("no-pcre2-unicode"))
}
/// Returns true if and only if PCRE2 is enabled and its Unicode mode is
/// enabled.
fn pcre2_unicode(&self) -> bool {
self.is_present("pcre2") && self.unicode()
}
/// Returns true if and only if file names containing each match should
/// be emitted.
fn with_filename(&self, paths: &[PathBuf]) -> bool {
@@ -1757,18 +1792,32 @@ fn u64_to_usize(arg_name: &str, value: Option<u64>) -> Result<Option<usize>> {
}
}
/// Sorts by an optional parameter.
//
/// If parameter is found to be `None`, both entries compare equal.
fn sort_by_option<T: Ord>(
p1: &Option<T>,
p2: &Option<T>,
/// Builds a comparator for sorting two files according to a system time
/// extracted from the file's metadata.
///
/// If there was a problem extracting the metadata or if the time is not
/// available, then both entries compare equal.
fn sort_by_metadata_time<G>(
p1: &Path,
p2: &Path,
reverse: bool,
) -> cmp::Ordering {
match (p1, p2, reverse) {
(Some(p1), Some(p2), true) => p1.cmp(&p2).reverse(),
(Some(p1), Some(p2), false) => p1.cmp(&p2),
_ => cmp::Ordering::Equal,
get_time: G,
) -> cmp::Ordering
where
G: Fn(&fs::Metadata) -> io::Result<SystemTime>,
{
let t1 = match p1.metadata().and_then(|md| get_time(&md)) {
Ok(t) => t,
Err(_) => return cmp::Ordering::Equal,
};
let t2 = match p2.metadata().and_then(|md| get_time(&md)) {
Ok(t) => t,
Err(_) => return cmp::Ordering::Equal,
};
if reverse {
t1.cmp(&t2).reverse()
} else {
t1.cmp(&t2)
}
}
@@ -1822,17 +1871,3 @@ fn current_dir() -> Result<PathBuf> {
)
.into())
}
/// Tries to assign a timestamp to every `Subject` in the vector to help with
/// sorting Subjects by time.
fn load_timestamps<G>(
subjects: impl Iterator<Item = Subject>,
get_time: G,
) -> Vec<(Option<SystemTime>, Subject)>
where
G: Fn(&fs::Metadata) -> io::Result<SystemTime>,
{
subjects
.map(|s| (s.path().metadata().and_then(|m| get_time(&m)).ok(), s))
.collect()
}

2
crates/core/config.rs
View File

@@ -80,7 +80,7 @@ fn parse<P: AsRef<Path>>(
fn parse_reader<R: io::Read>(
rdr: R,
) -> Result<(Vec<OsString>, Vec<Box<dyn Error>>)> {
let mut bufrdr = io::BufReader::new(rdr);
let bufrdr = io::BufReader::new(rdr);
let (mut args, mut errs) = (vec![], vec![]);
let mut line_number = 0;
bufrdr.for_byte_line_with_terminator(|line| {

8
crates/core/logger.rs
View File

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

158
crates/core/main.rs
View File

@@ -47,7 +47,7 @@ type Result<T> = ::std::result::Result<T, Box<dyn error::Error>>;
fn main() {
if let Err(err) = Args::parse().and_then(try_main) {
eprintln_locked!("{}", err);
eprintln!("{}", err);
process::exit(2);
}
}
@@ -55,7 +55,7 @@ fn main() {
fn try_main(args: Args) -> Result<()> {
use args::Command::*;
let matched = match args.command() {
let matched = match args.command()? {
Search => search(&args),
SearchParallel => search_parallel(&args),
SearchNever => Ok(false),
@@ -77,70 +77,53 @@ fn try_main(args: Args) -> Result<()> {
/// steps through the file list (current directory by default) and searches
/// each file sequentially.
fn search(args: &Args) -> Result<bool> {
/// The meat of the routine is here. This lets us call the same iteration
/// code over each file regardless of whether we stream over the files
/// as they're produced by the underlying directory traversal or whether
/// they've been collected and sorted (for example) first.
fn iter(
args: &Args,
subjects: impl Iterator<Item = Subject>,
started_at: std::time::Instant,
) -> Result<bool> {
let quit_after_match = args.quit_after_match()?;
let mut stats = args.stats()?;
let mut searcher = args.search_worker(args.stdout())?;
let mut matched = false;
let mut searched = false;
for subject in subjects {
searched = true;
let search_result = match searcher.search(&subject) {
Ok(search_result) => search_result,
// A broken pipe means graceful termination.
Err(err) if err.kind() == io::ErrorKind::BrokenPipe => break,
Err(err) => {
err_message!("{}: {}", subject.path().display(), err);
continue;
}
};
matched |= search_result.has_match();
if let Some(ref mut stats) = stats {
*stats += search_result.stats().unwrap();
}
if matched && quit_after_match {
break;
}
}
if args.using_default_path() && !searched {
eprint_nothing_searched();
}
if let Some(ref stats) = stats {
let elapsed = Instant::now().duration_since(started_at);
// We don't care if we couldn't print this successfully.
let _ = searcher.print_stats(elapsed, stats);
}
Ok(matched)
}
let started_at = Instant::now();
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
let subjects = args
.walker()?
.filter_map(|result| subject_builder.build_from_result(result));
if args.needs_stat_sort() {
let subjects = args.sort_by_stat(subjects).into_iter();
iter(args, subjects, started_at)
} else {
iter(args, subjects, started_at)
let mut stats = args.stats()?;
let mut searcher = args.search_worker(args.stdout())?;
let mut matched = false;
let mut searched = false;
for result in args.walker()? {
let subject = match subject_builder.build_from_result(result) {
Some(subject) => subject,
None => continue,
};
searched = true;
let search_result = match searcher.search(&subject) {
Ok(search_result) => search_result,
Err(err) => {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
break;
}
err_message!("{}: {}", subject.path().display(), err);
continue;
}
};
matched = matched || search_result.has_match();
if let Some(ref mut stats) = stats {
*stats += search_result.stats().unwrap();
}
if matched && quit_after_match {
break;
}
}
if args.using_default_path() && !searched {
eprint_nothing_searched();
}
if let Some(ref stats) = stats {
let elapsed = Instant::now().duration_since(started_at);
// We don't care if we couldn't print this successfully.
let _ = searcher.print_stats(elapsed, stats);
}
Ok(matched)
}
/// The top-level entry point for multi-threaded search. The parallelism is
/// itself achieved by the recursive directory traversal. All we need to do is
/// feed it a worker for performing a search on each file.
///
/// Requesting a sorted output from ripgrep (such as with `--sort path`) will
/// automatically disable parallelism and hence sorting is not handled here.
fn search_parallel(args: &Args) -> Result<bool> {
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering::SeqCst;
@@ -231,54 +214,35 @@ fn eprint_nothing_searched() {
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using a single thread.
fn files(args: &Args) -> Result<bool> {
/// The meat of the routine is here. This lets us call the same iteration
/// code over each file regardless of whether we stream over the files
/// as they're produced by the underlying directory traversal or whether
/// they've been collected and sorted (for example) first.
fn iter(
args: &Args,
subjects: impl Iterator<Item = Subject>,
) -> Result<bool> {
let quit_after_match = args.quit_after_match()?;
let mut matched = false;
let mut path_printer = args.path_printer(args.stdout())?;
for subject in subjects {
matched = true;
if quit_after_match {
let quit_after_match = args.quit_after_match()?;
let subject_builder = args.subject_builder();
let mut matched = false;
let mut path_printer = args.path_printer(args.stdout())?;
for result in args.walker()? {
let subject = match subject_builder.build_from_result(result) {
Some(subject) => subject,
None => continue,
};
matched = true;
if quit_after_match {
break;
}
if let Err(err) = path_printer.write_path(subject.path()) {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
break;
}
if let Err(err) = path_printer.write_path(subject.path()) {
// A broken pipe means graceful termination.
if err.kind() == io::ErrorKind::BrokenPipe {
break;
}
// Otherwise, we have some other error that's preventing us from
// writing to stdout, so we should bubble it up.
return Err(err.into());
}
// Otherwise, we have some other error that's preventing us from
// writing to stdout, so we should bubble it up.
return Err(err.into());
}
Ok(matched)
}
let subject_builder = args.subject_builder();
let subjects = args
.walker()?
.filter_map(|result| subject_builder.build_from_result(result));
if args.needs_stat_sort() {
let subjects = args.sort_by_stat(subjects).into_iter();
iter(args, subjects)
} else {
iter(args, subjects)
}
Ok(matched)
}
/// The top-level entry point for listing files without searching them. This
/// recursively steps through the file list (current directory by default) and
/// prints each path sequentially using multiple threads.
///
/// Requesting a sorted output from ripgrep (such as with `--sort path`) will
/// automatically disable parallelism and hence sorting is not handled here.
fn files_parallel(args: &Args) -> Result<bool> {
use std::sync::atomic::AtomicBool;
use std::sync::atomic::Ordering::SeqCst;

20
crates/core/messages.rs
View File

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

8
crates/globset/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "globset"
version = "0.4.11" #:version
version = "0.4.9" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Cross platform single glob and glob set matching. Glob set matching is the
@@ -20,11 +20,11 @@ name = "globset"
bench = false
[dependencies]
aho-corasick = "1.0.2"
bstr = { version = "1.6.0", default-features = false, features = ["std"] }
aho-corasick = "0.7.3"
bstr = { version = "0.2.0", default-features = false, features = ["std"] }
fnv = "1.0.6"
log = { version = "0.4.5", optional = true }
regex = { version = "1.8.3", default-features = false, features = ["perf", "std"] }
regex = { version = "1.1.5", default-features = false, features = ["perf", "std"] }
serde = { version = "1.0.104", optional = true }
[dev-dependencies]

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

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

51
crates/globset/src/lib.rs
View File

@@ -498,23 +498,13 @@ impl GlobSetBuilder {
/// Constructing candidates has a very small cost associated with it, so
/// callers may find it beneficial to amortize that cost when matching a single
/// path against multiple globs or sets of globs.
#[derive(Clone)]
#[derive(Clone, Debug)]
pub struct Candidate<'a> {
path: Cow<'a, [u8]>,
basename: Cow<'a, [u8]>,
ext: Cow<'a, [u8]>,
}
impl<'a> std::fmt::Debug for Candidate<'a> {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
f.debug_struct("Candidate")
.field("path", &self.path.as_bstr())
.field("basename", &self.basename.as_bstr())
.field("ext", &self.ext.as_bstr())
.finish()
}
}
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> {
@@ -828,7 +818,7 @@ impl MultiStrategyBuilder {
fn prefix(self) -> PrefixStrategy {
PrefixStrategy {
matcher: AhoCorasick::new(&self.literals).unwrap(),
matcher: AhoCorasick::new_auto_configured(&self.literals),
map: self.map,
longest: self.longest,
}
@@ -836,7 +826,7 @@ impl MultiStrategyBuilder {
fn suffix(self) -> SuffixStrategy {
SuffixStrategy {
matcher: AhoCorasick::new(&self.literals).unwrap(),
matcher: AhoCorasick::new_auto_configured(&self.literals),
map: self.map,
longest: self.longest,
}
@@ -880,29 +870,6 @@ impl RequiredExtensionStrategyBuilder {
}
}
/// Escape meta-characters within the given glob pattern.
///
/// The escaping works by surrounding meta-characters with brackets. For
/// example, `*` becomes `[*]`.
pub fn escape(s: &str) -> String {
let mut escaped = String::with_capacity(s.len());
for c in s.chars() {
match c {
// note that ! does not need escaping because it is only special
// inside brackets
'?' | '*' | '[' | ']' => {
escaped.push('[');
escaped.push(c);
escaped.push(']');
}
c => {
escaped.push(c);
}
}
}
escaped
}
#[cfg(test)]
mod tests {
use super::{GlobSet, GlobSetBuilder};
@@ -942,16 +909,4 @@ mod tests {
assert!(!set.is_match(""));
assert!(!set.is_match("a"));
}
#[test]
fn escape() {
use super::escape;
assert_eq!("foo", escape("foo"));
assert_eq!("foo[*]", escape("foo*"));
assert_eq!("[[][]]", escape("[]"));
assert_eq!("[*][?]", escape("*?"));
assert_eq!("src/[*][*]/[*].rs", escape("src/**/*.rs"));
assert_eq!("bar[[]ab[]]baz", escape("bar[ab]baz"));
assert_eq!("bar[[]!![]]!baz", escape("bar[!!]!baz"));
}
}

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

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

60
crates/globset/src/serde_impl.rs
View File

@@ -1,7 +1,5 @@
use serde::{
de::{Error, Visitor},
{Deserialize, Deserializer, Serialize, Serializer},
};
use serde::de::Error;
use serde::{Deserialize, Deserializer, Serialize, Serializer};
use crate::Glob;
@@ -14,66 +12,18 @@ impl Serialize for Glob {
}
}
struct GlobVisitor;
impl<'a> Visitor<'a> for GlobVisitor {
type Value = Glob;
fn expecting(
&self,
formatter: &mut std::fmt::Formatter,
) -> std::fmt::Result {
formatter.write_str("a glob pattern")
}
fn visit_str<E>(self, v: &str) -> Result<Self::Value, E>
where
E: Error,
{
Glob::new(v).map_err(serde::de::Error::custom)
}
}
impl<'de> Deserialize<'de> for Glob {
fn deserialize<D: Deserializer<'de>>(
deserializer: D,
) -> Result<Self, D::Error> {
deserializer.deserialize_str(GlobVisitor)
let glob = <&str as Deserialize>::deserialize(deserializer)?;
Glob::new(glob).map_err(D::Error::custom)
}
}
#[cfg(test)]
mod tests {
use std::collections::HashMap;
use crate::Glob;
#[test]
fn glob_deserialize_borrowed() {
let string = r#"{"markdown": "*.md"}"#;
let map: HashMap<String, Glob> =
serde_json::from_str(&string).unwrap();
assert_eq!(map["markdown"], Glob::new("*.md").unwrap());
}
#[test]
fn glob_deserialize_owned() {
let string = r#"{"markdown": "*.md"}"#;
let v: serde_json::Value = serde_json::from_str(&string).unwrap();
let map: HashMap<String, Glob> = serde_json::from_value(v).unwrap();
assert_eq!(map["markdown"], Glob::new("*.md").unwrap());
}
#[test]
fn glob_deserialize_error() {
let string = r#"{"error": "["}"#;
let map = serde_json::from_str::<HashMap<String, Glob>>(&string);
assert!(map.is_err());
}
use Glob;
#[test]
fn glob_json_works() {

14
crates/grep/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep"
version = "0.2.12" #:version
version = "0.2.10" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Fast line oriented regex searching as a library.
@@ -14,12 +14,12 @@ license = "Unlicense OR MIT"
edition = "2018"
[dependencies]
grep-cli = { version = "0.1.7", path = "../cli" }
grep-matcher = { version = "0.1.6", path = "../matcher" }
grep-pcre2 = { version = "0.1.6", path = "../pcre2", optional = true }
grep-printer = { version = "0.1.7", path = "../printer" }
grep-regex = { version = "0.1.11", path = "../regex" }
grep-searcher = { version = "0.1.11", path = "../searcher" }
grep-cli = { version = "0.1.6", path = "../cli" }
grep-matcher = { version = "0.1.5", path = "../matcher" }
grep-pcre2 = { version = "0.1.5", path = "../pcre2", optional = true }
grep-printer = { version = "0.1.6", path = "../printer" }
grep-regex = { version = "0.1.10", path = "../regex" }
grep-searcher = { version = "0.1.10", path = "../searcher" }
[dev-dependencies]
termcolor = "1.0.4"

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

@@ -12,6 +12,8 @@ are sparse.
A cookbook and a guide are planned.
*/
#![deny(missing_docs)]
pub extern crate grep_cli as cli;
pub extern crate grep_matcher as matcher;
#[cfg(feature = "pcre2")]

9
crates/ignore/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "ignore"
version = "0.4.20" #:version
version = "0.4.18" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
A fast library for efficiently matching ignore files such as `.gitignore`
@@ -19,11 +19,12 @@ name = "ignore"
bench = false
[dependencies]
globset = { version = "0.4.10", path = "../globset" }
crossbeam-utils = "0.8.0"
globset = { version = "0.4.9", path = "../globset" }
lazy_static = "1.1"
log = "0.4.5"
memchr = "2.5"
regex = { version = "1.9.0", default-features = false, features = ["perf", "std", "unicode-gencat"] }
memchr = "2.1"
regex = "1.1"
same-file = "1.0.4"
thread_local = "1"
walkdir = "2.2.7"

412
crates/ignore/src/default_types.rs
View File

@@ -9,113 +9,101 @@
/// Please try to keep this list sorted lexicographically and wrapped to 79
/// columns (inclusive).
#[rustfmt::skip]
pub const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
(&["ada"], &["*.adb", "*.ads"]),
(&["agda"], &["*.agda", "*.lagda"]),
(&["aidl"], &["*.aidl"]),
(&["alire"], &["alire.toml"]),
(&["amake"], &["*.mk", "*.bp"]),
(&["asciidoc"], &["*.adoc", "*.asc", "*.asciidoc"]),
(&["asm"], &["*.asm", "*.s", "*.S"]),
(&["asp"], &[
pub const DEFAULT_TYPES: &[(&str, &[&str])] = &[
("agda", &["*.agda", "*.lagda"]),
("aidl", &["*.aidl"]),
("amake", &["*.mk", "*.bp"]),
("asciidoc", &["*.adoc", "*.asc", "*.asciidoc"]),
("asm", &["*.asm", "*.s", "*.S"]),
("asp", &[
"*.aspx", "*.aspx.cs", "*.aspx.vb", "*.ascx", "*.ascx.cs",
"*.ascx.vb", "*.asp"
]),
(&["ats"], &["*.ats", "*.dats", "*.sats", "*.hats"]),
(&["avro"], &["*.avdl", "*.avpr", "*.avsc"]),
(&["awk"], &["*.awk"]),
(&["bat", "batch"], &["*.bat"]),
(&["bazel"], &[
("ats", &["*.ats", "*.dats", "*.sats", "*.hats"]),
("avro", &["*.avdl", "*.avpr", "*.avsc"]),
("awk", &["*.awk"]),
("bazel", &[
"*.bazel", "*.bzl", "*.BUILD", "*.bazelrc", "BUILD", "MODULE.bazel",
"WORKSPACE", "WORKSPACE.bazel",
]),
(&["bitbake"], &["*.bb", "*.bbappend", "*.bbclass", "*.conf", "*.inc"]),
(&["brotli"], &["*.br"]),
(&["buildstream"], &["*.bst"]),
(&["bzip2"], &["*.bz2", "*.tbz2"]),
(&["c"], &["*.[chH]", "*.[chH].in", "*.cats"]),
(&["cabal"], &["*.cabal"]),
(&["candid"], &["*.did"]),
(&["carp"], &["*.carp"]),
(&["cbor"], &["*.cbor"]),
(&["ceylon"], &["*.ceylon"]),
(&["clojure"], &["*.clj", "*.cljc", "*.cljs", "*.cljx"]),
(&["cmake"], &["*.cmake", "CMakeLists.txt"]),
(&["cmd"], &["*.bat", "*.cmd"]),
(&["cml"], &["*.cml"]),
(&["coffeescript"], &["*.coffee"]),
(&["config"], &["*.cfg", "*.conf", "*.config", "*.ini"]),
(&["coq"], &["*.v"]),
(&["cpp"], &[
("bitbake", &["*.bb", "*.bbappend", "*.bbclass", "*.conf", "*.inc"]),
("brotli", &["*.br"]),
("buildstream", &["*.bst"]),
("bzip2", &["*.bz2", "*.tbz2"]),
("c", &["*.[chH]", "*.[chH].in", "*.cats"]),
("cabal", &["*.cabal"]),
("cbor", &["*.cbor"]),
("ceylon", &["*.ceylon"]),
("clojure", &["*.clj", "*.cljc", "*.cljs", "*.cljx"]),
("cmake", &["*.cmake", "CMakeLists.txt"]),
("coffeescript", &["*.coffee"]),
("config", &["*.cfg", "*.conf", "*.config", "*.ini"]),
("coq", &["*.v"]),
("cpp", &[
"*.[ChH]", "*.cc", "*.[ch]pp", "*.[ch]xx", "*.hh", "*.inl",
"*.[ChH].in", "*.cc.in", "*.[ch]pp.in", "*.[ch]xx.in", "*.hh.in",
]),
(&["creole"], &["*.creole"]),
(&["crystal"], &["Projectfile", "*.cr", "*.ecr", "shard.yml"]),
(&["cs"], &["*.cs"]),
(&["csharp"], &["*.cs"]),
(&["cshtml"], &["*.cshtml"]),
(&["css"], &["*.css", "*.scss"]),
(&["csv"], &["*.csv"]),
(&["cuda"], &["*.cu", "*.cuh"]),
(&["cython"], &["*.pyx", "*.pxi", "*.pxd"]),
(&["d"], &["*.d"]),
(&["dart"], &["*.dart"]),
(&["devicetree"], &["*.dts", "*.dtsi"]),
(&["dhall"], &["*.dhall"]),
(&["diff"], &["*.patch", "*.diff"]),
(&["dita"], &["*.dita", "*.ditamap", "*.ditaval"]),
(&["docker"], &["*Dockerfile*"]),
(&["dockercompose"], &["docker-compose.yml", "docker-compose.*.yml"]),
(&["dts"], &["*.dts", "*.dtsi"]),
(&["dvc"], &["Dvcfile", "*.dvc"]),
(&["ebuild"], &["*.ebuild", "*.eclass"]),
(&["edn"], &["*.edn"]),
(&["elisp"], &["*.el"]),
(&["elixir"], &["*.ex", "*.eex", "*.exs", "*.heex", "*.leex", "*.livemd"]),
(&["elm"], &["*.elm"]),
(&["erb"], &["*.erb"]),
(&["erlang"], &["*.erl", "*.hrl"]),
(&["fennel"], &["*.fnl"]),
(&["fidl"], &["*.fidl"]),
(&["fish"], &["*.fish"]),
(&["flatbuffers"], &["*.fbs"]),
(&["fortran"], &[
("creole", &["*.creole"]),
("crystal", &["Projectfile", "*.cr", "*.ecr", "shard.yml"]),
("cs", &["*.cs"]),
("csharp", &["*.cs"]),
("cshtml", &["*.cshtml"]),
("css", &["*.css", "*.scss"]),
("csv", &["*.csv"]),
("cuda", &["*.cu", "*.cuh"]),
("cython", &["*.pyx", "*.pxi", "*.pxd"]),
("d", &["*.d"]),
("dart", &["*.dart"]),
("dhall", &["*.dhall"]),
("diff", &["*.patch", "*.diff"]),
("docker", &["*Dockerfile*"]),
("dts", &["*.dts", "*.dtsi"]),
("dvc", &["Dvcfile", "*.dvc"]),
("ebuild", &["*.ebuild"]),
("edn", &["*.edn"]),
("elisp", &["*.el"]),
("elixir", &["*.ex", "*.eex", "*.exs"]),
("elm", &["*.elm"]),
("erb", &["*.erb"]),
("erlang", &["*.erl", "*.hrl"]),
("fennel", &["*.fnl"]),
("fidl", &["*.fidl"]),
("fish", &["*.fish"]),
("flatbuffers", &["*.fbs"]),
("fortran", &[
"*.f", "*.F", "*.f77", "*.F77", "*.pfo",
"*.f90", "*.F90", "*.f95", "*.F95",
]),
(&["fsharp"], &["*.fs", "*.fsx", "*.fsi"]),
(&["fut"], &["*.fut"]),
(&["gap"], &["*.g", "*.gap", "*.gi", "*.gd", "*.tst"]),
(&["gn"], &["*.gn", "*.gni"]),
(&["go"], &["*.go"]),
(&["gprbuild"], &["*.gpr"]),
(&["gradle"], &["*.gradle"]),
(&["graphql"], &["*.graphql", "*.graphqls"]),
(&["groovy"], &["*.groovy", "*.gradle"]),
(&["gzip"], &["*.gz", "*.tgz"]),
(&["h"], &["*.h", "*.hh", "*.hpp"]),
(&["haml"], &["*.haml"]),
(&["hare"], &["*.ha"]),
(&["haskell"], &["*.hs", "*.lhs", "*.cpphs", "*.c2hs", "*.hsc"]),
(&["hbs"], &["*.hbs"]),
(&["hs"], &["*.hs", "*.lhs"]),
(&["html"], &["*.htm", "*.html", "*.ejs"]),
(&["hy"], &["*.hy"]),
(&["idris"], &["*.idr", "*.lidr"]),
(&["janet"], &["*.janet"]),
(&["java"], &["*.java", "*.jsp", "*.jspx", "*.properties"]),
(&["jinja"], &["*.j2", "*.jinja", "*.jinja2"]),
(&["jl"], &["*.jl"]),
(&["js"], &["*.js", "*.jsx", "*.vue", "*.cjs", "*.mjs"]),
(&["json"], &["*.json", "composer.lock"]),
(&["jsonl"], &["*.jsonl"]),
(&["julia"], &["*.jl"]),
(&["jupyter"], &["*.ipynb", "*.jpynb"]),
(&["k"], &["*.k"]),
(&["kotlin"], &["*.kt", "*.kts"]),
(&["less"], &["*.less"]),
(&["license"], &[
("fsharp", &["*.fs", "*.fsx", "*.fsi"]),
("fut", &["*.fut"]),
("gap", &["*.g", "*.gap", "*.gi", "*.gd", "*.tst"]),
("gn", &["*.gn", "*.gni"]),
("go", &["*.go"]),
("gradle", &["*.gradle"]),
("groovy", &["*.groovy", "*.gradle"]),
("gzip", &["*.gz", "*.tgz"]),
("h", &["*.h", "*.hh", "*.hpp"]),
("haml", &["*.haml"]),
("hare", &["*.ha"]),
("haskell", &["*.hs", "*.lhs", "*.cpphs", "*.c2hs", "*.hsc"]),
("hbs", &["*.hbs"]),
("hs", &["*.hs", "*.lhs"]),
("html", &["*.htm", "*.html", "*.ejs"]),
("hy", &["*.hy"]),
("idris", &["*.idr", "*.lidr"]),
("janet", &["*.janet"]),
("java", &["*.java", "*.jsp", "*.jspx", "*.properties"]),
("jinja", &["*.j2", "*.jinja", "*.jinja2"]),
("jl", &["*.jl"]),
("js", &["*.js", "*.jsx", "*.vue"]),
("json", &["*.json", "composer.lock"]),
("jsonl", &["*.jsonl"]),
("julia", &["*.jl"]),
("jupyter", &["*.ipynb", "*.jpynb"]),
("k", &["*.k"]),
("kotlin", &["*.kt", "*.kts"]),
("less", &["*.less"]),
("license", &[
// General
"COPYING", "COPYING[.-]*",
"COPYRIGHT", "COPYRIGHT[.-]*",
@@ -142,91 +130,76 @@ pub const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
"MPL-*[0-9]*",
"OFL-*[0-9]*",
]),
(&["lilypond"], &["*.ly", "*.ily"]),
(&["lisp"], &["*.el", "*.jl", "*.lisp", "*.lsp", "*.sc", "*.scm"]),
(&["lock"], &["*.lock", "package-lock.json"]),
(&["log"], &["*.log"]),
(&["lua"], &["*.lua"]),
(&["lz4"], &["*.lz4"]),
(&["lzma"], &["*.lzma"]),
(&["m4"], &["*.ac", "*.m4"]),
(&["make"], &[
("lilypond", &["*.ly", "*.ily"]),
("lisp", &["*.el", "*.jl", "*.lisp", "*.lsp", "*.sc", "*.scm"]),
("lock", &["*.lock", "package-lock.json"]),
("log", &["*.log"]),
("lua", &["*.lua"]),
("lz4", &["*.lz4"]),
("lzma", &["*.lzma"]),
("m4", &["*.ac", "*.m4"]),
("make", &[
"[Gg][Nn][Uu]makefile", "[Mm]akefile",
"[Gg][Nn][Uu]makefile.am", "[Mm]akefile.am",
"[Gg][Nn][Uu]makefile.in", "[Mm]akefile.in",
"*.mk", "*.mak"
]),
(&["mako"], &["*.mako", "*.mao"]),
(&["man"], &["*.[0-9lnpx]", "*.[0-9][cEFMmpSx]"]),
(&["markdown", "md"], &[
"*.markdown",
"*.md",
"*.mdown",
"*.mdwn",
"*.mkd",
"*.mkdn",
"*.mdx",
]),
(&["matlab"], &["*.m"]),
(&["meson"], &["meson.build", "meson_options.txt"]),
(&["minified"], &["*.min.html", "*.min.css", "*.min.js"]),
(&["mint"], &["*.mint"]),
(&["mk"], &["mkfile"]),
(&["ml"], &["*.ml"]),
(&["motoko"], &["*.mo"]),
(&["msbuild"], &[
("mako", &["*.mako", "*.mao"]),
("man", &["*.[0-9lnpx]", "*.[0-9][cEFMmpSx]"]),
("markdown", &["*.markdown", "*.md", "*.mdown", "*.mkd", "*.mkdn"]),
("matlab", &["*.m"]),
("md", &["*.markdown", "*.md", "*.mdown", "*.mkd", "*.mkdn"]),
("meson", &["meson.build", "meson_options.txt"]),
("minified", &["*.min.html", "*.min.css", "*.min.js"]),
("mint", &["*.mint"]),
("mk", &["mkfile"]),
("ml", &["*.ml"]),
("msbuild", &[
"*.csproj", "*.fsproj", "*.vcxproj", "*.proj", "*.props", "*.targets",
"*.sln",
]),
(&["nim"], &["*.nim", "*.nimf", "*.nimble", "*.nims"]),
(&["nix"], &["*.nix"]),
(&["objc"], &["*.h", "*.m"]),
(&["objcpp"], &["*.h", "*.mm"]),
(&["ocaml"], &["*.ml", "*.mli", "*.mll", "*.mly"]),
(&["org"], &["*.org", "*.org_archive"]),
(&["pants"], &["BUILD"]),
(&["pascal"], &["*.pas", "*.dpr", "*.lpr", "*.pp", "*.inc"]),
(&["pdf"], &["*.pdf"]),
(&["perl"], &["*.perl", "*.pl", "*.PL", "*.plh", "*.plx", "*.pm", "*.t"]),
(&["php"], &[
("nim", &["*.nim", "*.nimf", "*.nimble", "*.nims"]),
("nix", &["*.nix"]),
("objc", &["*.h", "*.m"]),
("objcpp", &["*.h", "*.mm"]),
("ocaml", &["*.ml", "*.mli", "*.mll", "*.mly"]),
("org", &["*.org", "*.org_archive"]),
("pants", &["BUILD"]),
("pascal", &["*.pas", "*.dpr", "*.lpr", "*.pp", "*.inc"]),
("pdf", &["*.pdf"]),
("perl", &["*.perl", "*.pl", "*.PL", "*.plh", "*.plx", "*.pm", "*.t"]),
("php", &[
// note that PHP 6 doesn't exist
// See: https://wiki.php.net/rfc/php6
"*.php", "*.php3", "*.php4", "*.php5", "*.php7", "*.php8",
"*.pht", "*.phtml"
]),
(&["po"], &["*.po"]),
(&["pod"], &["*.pod"]),
(&["postscript"], &["*.eps", "*.ps"]),
(&["protobuf"], &["*.proto"]),
(&["ps"], &["*.cdxml", "*.ps1", "*.ps1xml", "*.psd1", "*.psm1"]),
(&["puppet"], &["*.epp", "*.erb", "*.pp", "*.rb"]),
(&["purs"], &["*.purs"]),
(&["py", "python"], &["*.py", "*.pyi"]),
(&["qmake"], &["*.pro", "*.pri", "*.prf"]),
(&["qml"], &["*.qml"]),
(&["r"], &["*.R", "*.r", "*.Rmd", "*.Rnw"]),
(&["racket"], &["*.rkt"]),
(&["raku"], &[
"*.raku", "*.rakumod", "*.rakudoc", "*.rakutest",
"*.p6", "*.pl6", "*.pm6"
]),
(&["rdoc"], &["*.rdoc"]),
(&["readme"], &["README*", "*README"]),
(&["reasonml"], &["*.re", "*.rei"]),
(&["red"], &["*.r", "*.red", "*.reds"]),
(&["rescript"], &["*.res", "*.resi"]),
(&["robot"], &["*.robot"]),
(&["rst"], &["*.rst"]),
(&["ruby"], &[
("po", &["*.po"]),
("pod", &["*.pod"]),
("postscript", &["*.eps", "*.ps"]),
("protobuf", &["*.proto"]),
("ps", &["*.cdxml", "*.ps1", "*.ps1xml", "*.psd1", "*.psm1"]),
("puppet", &["*.erb", "*.pp", "*.rb"]),
("purs", &["*.purs"]),
("py", &["*.py"]),
("qmake", &["*.pro", "*.pri", "*.prf"]),
("qml", &["*.qml"]),
("r", &["*.R", "*.r", "*.Rmd", "*.Rnw"]),
("racket", &["*.rkt"]),
("rdoc", &["*.rdoc"]),
("readme", &["README*", "*README"]),
("red", &["*.r", "*.red", "*.reds"]),
("robot", &["*.robot"]),
("rst", &["*.rst"]),
("ruby", &[
// Idiomatic files
"config.ru", "Gemfile", ".irbrc", "Rakefile",
// Extensions
"*.gemspec", "*.rb", "*.rbw"
]),
(&["rust"], &["*.rs"]),
(&["sass"], &["*.sass", "*.scss"]),
(&["scala"], &["*.scala", "*.sbt"]),
(&["sh"], &[
("rust", &["*.rs"]),
("sass", &["*.sass", "*.scss"]),
("scala", &["*.scala", "*.sbt"]),
("sh", &[
// Portable/misc. init files
".login", ".logout", ".profile", "profile",
// bash-specific init files
@@ -249,66 +222,59 @@ pub const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
// Extensions
"*.bash", "*.csh", "*.ksh", "*.sh", "*.tcsh", "*.zsh",
]),
(&["slim"], &["*.skim", "*.slim", "*.slime"]),
(&["smarty"], &["*.tpl"]),
(&["sml"], &["*.sml", "*.sig"]),
(&["solidity"], &["*.sol"]),
(&["soy"], &["*.soy"]),
(&["spark"], &["*.spark"]),
(&["spec"], &["*.spec"]),
(&["sql"], &["*.sql", "*.psql"]),
(&["stylus"], &["*.styl"]),
(&["sv"], &["*.v", "*.vg", "*.sv", "*.svh", "*.h"]),
(&["svg"], &["*.svg"]),
(&["swift"], &["*.swift"]),
(&["swig"], &["*.def", "*.i"]),
(&["systemd"], &[
("slim", &["*.skim", "*.slim", "*.slime"]),
("smarty", &["*.tpl"]),
("sml", &["*.sml", "*.sig"]),
("soy", &["*.soy"]),
("spark", &["*.spark"]),
("spec", &["*.spec"]),
("sql", &["*.sql", "*.psql"]),
("stylus", &["*.styl"]),
("sv", &["*.v", "*.vg", "*.sv", "*.svh", "*.h"]),
("svg", &["*.svg"]),
("swift", &["*.swift"]),
("swig", &["*.def", "*.i"]),
("systemd", &[
"*.automount", "*.conf", "*.device", "*.link", "*.mount", "*.path",
"*.scope", "*.service", "*.slice", "*.socket", "*.swap", "*.target",
"*.timer",
]),
(&["taskpaper"], &["*.taskpaper"]),
(&["tcl"], &["*.tcl"]),
(&["tex"], &["*.tex", "*.ltx", "*.cls", "*.sty", "*.bib", "*.dtx", "*.ins"]),
(&["texinfo"], &["*.texi"]),
(&["textile"], &["*.textile"]),
(&["tf"], &[
"*.tf", "*.auto.tfvars", "terraform.tfvars", "*.tf.json",
"*.auto.tfvars.json", "terraform.tfvars.json", "*.terraformrc",
"terraform.rc", "*.tfrc", "*.terraform.lock.hcl",
]),
(&["thrift"], &["*.thrift"]),
(&["toml"], &["*.toml", "Cargo.lock"]),
(&["ts", "typescript"], &["*.ts", "*.tsx", "*.cts", "*.mts"]),
(&["twig"], &["*.twig"]),
(&["txt"], &["*.txt"]),
(&["typoscript"], &["*.typoscript", "*.ts"]),
(&["usd"], &["*.usd", "*.usda", "*.usdc"]),
(&["v"], &["*.v"]),
(&["vala"], &["*.vala"]),
(&["vb"], &["*.vb"]),
(&["vcl"], &["*.vcl"]),
(&["verilog"], &["*.v", "*.vh", "*.sv", "*.svh"]),
(&["vhdl"], &["*.vhd", "*.vhdl"]),
(&["vim"], &[
("taskpaper", &["*.taskpaper"]),
("tcl", &["*.tcl"]),
("tex", &["*.tex", "*.ltx", "*.cls", "*.sty", "*.bib", "*.dtx", "*.ins"]),
("texinfo", &["*.texi"]),
("textile", &["*.textile"]),
("tf", &["*.tf"]),
("thrift", &["*.thrift"]),
("toml", &["*.toml", "Cargo.lock"]),
("ts", &["*.ts", "*.tsx"]),
("twig", &["*.twig"]),
("txt", &["*.txt"]),
("typoscript", &["*.typoscript", "*.ts"]),
("vala", &["*.vala"]),
("vb", &["*.vb"]),
("vcl", &["*.vcl"]),
("verilog", &["*.v", "*.vh", "*.sv", "*.svh"]),
("vhdl", &["*.vhd", "*.vhdl"]),
("vim", &[
"*.vim", ".vimrc", ".gvimrc", "vimrc", "gvimrc", "_vimrc", "_gvimrc",
]),
(&["vimscript"], &[
("vimscript", &[
"*.vim", ".vimrc", ".gvimrc", "vimrc", "gvimrc", "_vimrc", "_gvimrc",
]),
(&["webidl"], &["*.idl", "*.webidl", "*.widl"]),
(&["wiki"], &["*.mediawiki", "*.wiki"]),
(&["xml"], &[
("webidl", &["*.idl", "*.webidl", "*.widl"]),
("wiki", &["*.mediawiki", "*.wiki"]),
("xml", &[
"*.xml", "*.xml.dist", "*.dtd", "*.xsl", "*.xslt", "*.xsd", "*.xjb",
"*.rng", "*.sch", "*.xhtml",
]),
(&["xz"], &["*.xz", "*.txz"]),
(&["yacc"], &["*.y"]),
(&["yaml"], &["*.yaml", "*.yml"]),
(&["yang"], &["*.yang"]),
(&["z"], &["*.Z"]),
(&["zig"], &["*.zig"]),
(&["zsh"], &[
("xz", &["*.xz", "*.txz"]),
("yacc", &["*.y"]),
("yaml", &["*.yaml", "*.yml"]),
("yang", &["*.yang"]),
("z", &["*.Z"]),
("zig", &["*.zig"]),
("zsh", &[
".zshenv", "zshenv",
".zlogin", "zlogin",
".zlogout", "zlogout",
@@ -316,25 +282,5 @@ pub const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
".zshrc", "zshrc",
"*.zsh",
]),
(&["zstd"], &["*.zst", "*.zstd"]),
("zstd", &["*.zst", "*.zstd"]),
];
#[cfg(test)]
mod tests {
use super::DEFAULT_TYPES;
#[test]
fn default_types_are_sorted() {
let mut names = DEFAULT_TYPES.iter().map(|(aliases, _)| aliases[0]);
let Some(mut previous_name) = names.next() else { return; };
for name in names {
assert!(
name > previous_name,
r#""{}" should be sorted before "{}" in `DEFAULT_TYPES`"#,
name,
previous_name
);
previous_name = name;
}
}
}

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

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

1
crates/ignore/src/overrides.rs
View File

@@ -106,7 +106,6 @@ impl Override {
}
/// Builds a matcher for a set of glob overrides.
#[derive(Clone, Debug)]
pub struct OverrideBuilder {
builder: GitignoreBuilder,
}

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

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

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

@@ -941,7 +941,7 @@ impl Walk {
// overheads; an example of this was a bespoke filesystem layer in
// Windows that hosted files remotely and would download them on-demand
// when particular filesystem operations occurred. Users of this system
// who ensured correct file-type filters were being used could still
// who ensured correct file-type fileters were being used could still
// get unnecessary file access resulting in large downloads.
if should_skip_entry(&self.ig, ent) {
return Ok(true);
@@ -1282,7 +1282,7 @@ impl WalkParallel {
let quit_now = Arc::new(AtomicBool::new(false));
let num_pending =
Arc::new(AtomicUsize::new(stack.lock().unwrap().len()));
std::thread::scope(|s| {
crossbeam_utils::thread::scope(|s| {
let mut handles = vec![];
for _ in 0..threads {
let worker = Worker {
@@ -1296,12 +1296,13 @@ impl WalkParallel {
skip: self.skip.clone(),
filter: self.filter.clone(),
};
handles.push(s.spawn(|| worker.run()));
handles.push(s.spawn(|_| worker.run()));
}
for handle in handles {
handle.join().unwrap();
}
});
})
.unwrap(); // Pass along panics from threads
}
fn threads(&self) -> usize {
@@ -1681,7 +1682,7 @@ impl<'s> Worker<'s> {
stack.pop()
}
/// Signal that work has been finished.
/// Signal that work has been received.
fn work_done(&self) {
self.num_pending.fetch_sub(1, Ordering::SeqCst);
}

19
crates/index/Cargo.toml Normal file
View File

@@ -0,0 +1,19 @@
[package]
publish = false
name = "grep-index"
version = "0.0.1" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Grep, but with an index.
"""
documentation = "https://docs.rs/grep-index"
homepage = "https://github.com/BurntSushi/ripgrep"
repository = "https://github.com/BurntSushi/ripgrep"
readme = "README.md"
keywords = ["regex", "grep", "search", "index", "ngram"]
license = "Unlicense/MIT"
edition = "2018"
[dependencies]
bstr = "0.2"
regex-syntax = "0.6.14"

21
crates/index/LICENSE-MIT Normal file
View File

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

8
crates/index/README.md Normal file
View File

@@ -0,0 +1,8 @@
grep-index
----------
WIP.
[![Build status](https://github.com/BurntSushi/ripgrep/workflows/ci/badge.svg)](https://github.com/BurntSushi/ripgrep/actions)
[![](https://img.shields.io/crates/v/grep-regex.svg)](https://crates.io/crates/grep-index)
Dual-licensed under MIT or the [UNLICENSE](http://unlicense.org).

24
crates/index/UNLICENSE Normal file
View File

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

7
crates/index/src/lib.rs Normal file
View File

@@ -0,0 +1,7 @@
/*!
TODO
*/
#![allow(warnings)]
mod literal;

1040
crates/index/src/literal.rs Normal file
View File

File diff suppressed because it is too large Load Diff

2
crates/matcher/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-matcher"
version = "0.1.6" #:version
version = "0.1.5" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
A trait for regular expressions, with a focus on line oriented search.

7
crates/pcre2/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-pcre2"
version = "0.1.6" #:version
version = "0.1.5" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Use PCRE2 with the 'grep' crate.
@@ -14,6 +14,5 @@ license = "Unlicense OR MIT"
edition = "2018"
[dependencies]
grep-matcher = { version = "0.1.6", path = "../matcher" }
log = "0.4.19"
pcre2 = "0.2.4"
grep-matcher = { version = "0.1.5", path = "../matcher" }
pcre2 = "0.2.3"

87
crates/pcre2/src/matcher.rs
View File

@@ -11,8 +11,6 @@ pub struct RegexMatcherBuilder {
builder: RegexBuilder,
case_smart: bool,
word: bool,
fixed_strings: bool,
whole_line: bool,
}
impl RegexMatcherBuilder {
@@ -22,8 +20,6 @@ impl RegexMatcherBuilder {
builder: RegexBuilder::new(),
case_smart: false,
word: false,
fixed_strings: false,
whole_line: false,
}
}
@@ -33,40 +29,17 @@ impl RegexMatcherBuilder {
/// If there was a problem compiling the pattern, then an error is
/// returned.
pub fn build(&self, pattern: &str) -> Result<RegexMatcher, Error> {
self.build_many(&[pattern])
}
/// Compile all of the given patterns into a single regex that matches when
/// at least one of the patterns matches.
///
/// If there was a problem building the regex, then an error is returned.
pub fn build_many<P: AsRef<str>>(
&self,
patterns: &[P],
) -> Result<RegexMatcher, Error> {
let mut builder = self.builder.clone();
let mut pats = Vec::with_capacity(patterns.len());
for p in patterns.iter() {
pats.push(if self.fixed_strings {
format!("(?:{})", pcre2::escape(p.as_ref()))
} else {
format!("(?:{})", p.as_ref())
});
}
let mut singlepat = pats.join("|");
if self.case_smart && !has_uppercase_literal(&singlepat) {
if self.case_smart && !has_uppercase_literal(pattern) {
builder.caseless(true);
}
if self.whole_line {
singlepat = format!(r"(?m:^)(?:{})(?m:$)", singlepat);
} else if self.word {
// We make this option exclusive with whole_line because when
// whole_line is enabled, all matches necessary fall on word
// boundaries. So this extra goop is strictly redundant.
singlepat = format!(r"(?<!\w)(?:{})(?!\w)", singlepat);
}
log::trace!("final regex: {:?}", singlepat);
builder.build(&singlepat).map_err(Error::regex).map(|regex| {
let res = if self.word {
let pattern = format!(r"(?<!\w)(?:{})(?!\w)", pattern);
builder.build(&pattern)
} else {
builder.build(pattern)
};
res.map_err(Error::regex).map(|regex| {
let mut names = HashMap::new();
for (i, name) in regex.capture_names().iter().enumerate() {
if let Some(ref name) = *name {
@@ -171,21 +144,6 @@ impl RegexMatcherBuilder {
self
}
/// Whether the patterns should be treated as literal strings or not. When
/// this is active, all characters, including ones that would normally be
/// special regex meta characters, are matched literally.
pub fn fixed_strings(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.fixed_strings = yes;
self
}
/// Whether each pattern should match the entire line or not. This is
/// equivalent to surrounding the pattern with `(?m:^)` and `(?m:$)`.
pub fn whole_line(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.whole_line = yes;
self
}
/// Enable Unicode matching mode.
///
/// When enabled, the following patterns become Unicode aware: `\b`, `\B`,
@@ -220,22 +178,23 @@ impl RegexMatcherBuilder {
self
}
/// This is now deprecated and is a no-op.
/// When UTF matching mode is enabled, this will disable the UTF checking
/// that PCRE2 will normally perform automatically. If UTF matching mode
/// is not enabled, then this has no effect.
///
/// Previously, this option permitted disabling PCRE2's UTF-8 validity
/// check, which could result in undefined behavior if the haystack was
/// not valid UTF-8. But PCRE2 introduced a new option, `PCRE2_MATCH_INVALID_UTF`,
/// in 10.34 which this crate always sets. When this option is enabled,
/// PCRE2 claims to not have undefined behavior when the haystack is
/// invalid UTF-8.
/// UTF checking is enabled by default when UTF matching mode is enabled.
/// If UTF matching mode is enabled and UTF checking is enabled, then PCRE2
/// will return an error if you attempt to search a subject string that is
/// not valid UTF-8.
///
/// Therefore, disabling the UTF-8 check is not something that is exposed
/// by this crate.
#[deprecated(
since = "0.2.4",
note = "now a no-op due to new PCRE2 features"
)]
pub fn disable_utf_check(&mut self) -> &mut RegexMatcherBuilder {
/// # Safety
///
/// It is undefined behavior to disable the UTF check in UTF matching mode
/// and search a subject string that is not valid UTF-8. When the UTF check
/// is disabled, callers must guarantee that the subject string is valid
/// UTF-8.
pub unsafe fn disable_utf_check(&mut self) -> &mut RegexMatcherBuilder {
self.builder.disable_utf_check();
self
}

12
crates/printer/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-printer"
version = "0.1.7" #:version
version = "0.1.6" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
An implementation of the grep crate's Sink trait that provides standard
@@ -19,13 +19,13 @@ default = ["serde1"]
serde1 = ["base64", "serde", "serde_json"]
[dependencies]
base64 = { version = "0.20.0", optional = true }
bstr = "1.6.0"
grep-matcher = { version = "0.1.6", path = "../matcher" }
grep-searcher = { version = "0.1.11", path = "../searcher" }
base64 = { version = "0.13.0", optional = true }
bstr = "0.2.0"
grep-matcher = { version = "0.1.5", path = "../matcher" }
grep-searcher = { version = "0.1.8", path = "../searcher" }
termcolor = "1.0.4"
serde = { version = "1.0.77", optional = true, features = ["derive"] }
serde_json = { version = "1.0.27", optional = true }
[dev-dependencies]
grep-regex = { version = "0.1.11", path = "../regex" }
grep-regex = { version = "0.1.9", path = "../regex" }

17
crates/regex/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-regex"
version = "0.1.11" #:version
version = "0.1.10" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Use Rust's regex library with the 'grep' crate.
@@ -11,12 +11,13 @@ repository = "https://github.com/BurntSushi/ripgrep/tree/master/crates/regex"
readme = "README.md"
keywords = ["regex", "grep", "search", "pattern", "line"]
license = "Unlicense OR MIT"
edition = "2021"
edition = "2018"
[dependencies]
aho-corasick = "1.0.2"
bstr = "1.6.0"
grep-matcher = { version = "0.1.6", path = "../matcher" }
log = "0.4.19"
regex-automata = { version = "0.3.0" }
regex-syntax = "0.7.2"
aho-corasick = "0.7.3"
bstr = "0.2.10"
grep-matcher = { version = "0.1.5", path = "../matcher" }
log = "0.4.5"
regex = "1.1"
regex-syntax = "0.6.5"
thread_local = "1.1.2"

67
crates/regex/src/ast.rs
View File

@@ -1,13 +1,17 @@
use regex_syntax::ast::parse::Parser;
use regex_syntax::ast::{self, Ast};
/// The results of analyzing AST of a regular expression (e.g., for supporting
/// smart case).
#[derive(Clone, Debug)]
pub(crate) struct AstAnalysis {
pub struct AstAnalysis {
/// True if and only if a literal uppercase character occurs in the regex.
any_uppercase: bool,
/// True if and only if the regex contains any literal at all.
any_literal: bool,
/// True if and only if the regex consists entirely of a literal and no
/// other special regex characters.
all_verbatim_literal: bool,
}
impl AstAnalysis {
@@ -15,16 +19,16 @@ impl AstAnalysis {
///
/// If `pattern` is not a valid regular expression, then `None` is
/// returned.
#[cfg(test)]
pub(crate) fn from_pattern(pattern: &str) -> Option<AstAnalysis> {
regex_syntax::ast::parse::Parser::new()
#[allow(dead_code)]
pub fn from_pattern(pattern: &str) -> Option<AstAnalysis> {
Parser::new()
.parse(pattern)
.map(|ast| AstAnalysis::from_ast(&ast))
.ok()
}
/// Perform an AST analysis given the AST.
pub(crate) fn from_ast(ast: &Ast) -> AstAnalysis {
pub fn from_ast(ast: &Ast) -> AstAnalysis {
let mut analysis = AstAnalysis::new();
analysis.from_ast_impl(ast);
analysis
@@ -36,7 +40,7 @@ impl AstAnalysis {
/// For example, a pattern like `\pL` contains no uppercase literals,
/// even though `L` is uppercase and the `\pL` class contains uppercase
/// characters.
pub(crate) fn any_uppercase(&self) -> bool {
pub fn any_uppercase(&self) -> bool {
self.any_uppercase
}
@@ -44,13 +48,32 @@ impl AstAnalysis {
///
/// For example, a pattern like `\pL` reports `false`, but a pattern like
/// `\pLfoo` reports `true`.
pub(crate) fn any_literal(&self) -> bool {
pub fn any_literal(&self) -> bool {
self.any_literal
}
/// Returns true if and only if the entire pattern is a verbatim literal
/// with no special meta characters.
///
/// When this is true, then the pattern satisfies the following law:
/// `escape(pattern) == pattern`. Notable examples where this returns
/// `false` include patterns like `a\u0061` even though `\u0061` is just
/// a literal `a`.
///
/// The purpose of this flag is to determine whether the patterns can be
/// given to non-regex substring search algorithms as-is.
#[allow(dead_code)]
pub fn all_verbatim_literal(&self) -> bool {
self.all_verbatim_literal
}
/// Creates a new `AstAnalysis` value with an initial configuration.
fn new() -> AstAnalysis {
AstAnalysis { any_uppercase: false, any_literal: false }
AstAnalysis {
any_uppercase: false,
any_literal: false,
all_verbatim_literal: true,
}
}
fn from_ast_impl(&mut self, ast: &Ast) {
@@ -63,20 +86,26 @@ impl AstAnalysis {
| Ast::Dot(_)
| Ast::Assertion(_)
| Ast::Class(ast::Class::Unicode(_))
| Ast::Class(ast::Class::Perl(_)) => {}
| Ast::Class(ast::Class::Perl(_)) => {
self.all_verbatim_literal = false;
}
Ast::Literal(ref x) => {
self.from_ast_literal(x);
}
Ast::Class(ast::Class::Bracketed(ref x)) => {
self.all_verbatim_literal = false;
self.from_ast_class_set(&x.kind);
}
Ast::Repetition(ref x) => {
self.all_verbatim_literal = false;
self.from_ast_impl(&x.ast);
}
Ast::Group(ref x) => {
self.all_verbatim_literal = false;
self.from_ast_impl(&x.ast);
}
Ast::Alternation(ref alt) => {
self.all_verbatim_literal = false;
for x in &alt.asts {
self.from_ast_impl(x);
}
@@ -132,6 +161,9 @@ impl AstAnalysis {
}
fn from_ast_literal(&mut self, ast: &ast::Literal) {
if ast.kind != ast::LiteralKind::Verbatim {
self.all_verbatim_literal = false;
}
self.any_literal = true;
self.any_uppercase = self.any_uppercase || ast.c.is_uppercase();
}
@@ -139,7 +171,7 @@ impl AstAnalysis {
/// Returns true if and only if the attributes can never change no matter
/// what other AST it might see.
fn done(&self) -> bool {
self.any_uppercase && self.any_literal
self.any_uppercase && self.any_literal && !self.all_verbatim_literal
}
}
@@ -156,61 +188,76 @@ mod tests {
let x = analysis("");
assert!(!x.any_uppercase);
assert!(!x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis("foo");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis("Foo");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis("foO");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(x.all_verbatim_literal);
let x = analysis(r"foo\\");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\w");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\S");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\p{Ll}");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo[a-z]");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo[A-Z]");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo[\S\t]");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"foo\\S");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"\p{Ll}");
assert!(!x.any_uppercase);
assert!(!x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"aBc\w");
assert!(x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
let x = analysis(r"a\u0061");
assert!(!x.any_uppercase);
assert!(x.any_literal);
assert!(!x.all_verbatim_literal);
}
}

542
crates/regex/src/config.rs
View File

@@ -1,16 +1,15 @@
use {
grep_matcher::{ByteSet, LineTerminator},
regex_automata::meta::Regex,
regex_syntax::{
ast,
hir::{self, Hir, HirKind},
},
};
use grep_matcher::{ByteSet, LineTerminator};
use regex::bytes::{Regex, RegexBuilder};
use regex_syntax::ast::{self, Ast};
use regex_syntax::hir::{self, Hir};
use crate::{
ast::AstAnalysis, error::Error, non_matching::non_matching_bytes,
strip::strip_from_match,
};
use crate::ast::AstAnalysis;
use crate::crlf::crlfify;
use crate::error::Error;
use crate::literal::LiteralSets;
use crate::multi::alternation_literals;
use crate::non_matching::non_matching_bytes;
use crate::strip::strip_from_match;
/// Config represents the configuration of a regex matcher in this crate.
/// The configuration is itself a rough combination of the knobs found in
@@ -22,23 +21,21 @@ use crate::{
/// configuration which generated it, and provides transformation on that HIR
/// such that the configuration is preserved.
#[derive(Clone, Debug)]
pub(crate) struct Config {
pub(crate) case_insensitive: bool,
pub(crate) case_smart: bool,
pub(crate) multi_line: bool,
pub(crate) dot_matches_new_line: bool,
pub(crate) swap_greed: bool,
pub(crate) ignore_whitespace: bool,
pub(crate) unicode: bool,
pub(crate) octal: bool,
pub(crate) size_limit: usize,
pub(crate) dfa_size_limit: usize,
pub(crate) nest_limit: u32,
pub(crate) line_terminator: Option<LineTerminator>,
pub(crate) crlf: bool,
pub(crate) word: bool,
pub(crate) fixed_strings: bool,
pub(crate) whole_line: bool,
pub struct Config {
pub case_insensitive: bool,
pub case_smart: bool,
pub multi_line: bool,
pub dot_matches_new_line: bool,
pub swap_greed: bool,
pub ignore_whitespace: bool,
pub unicode: bool,
pub octal: bool,
pub size_limit: usize,
pub dfa_size_limit: usize,
pub nest_limit: u32,
pub line_terminator: Option<LineTerminator>,
pub crlf: bool,
pub word: bool,
}
impl Default for Config {
@@ -53,28 +50,47 @@ impl Default for Config {
unicode: true,
octal: false,
// These size limits are much bigger than what's in the regex
// crate by default.
// crate.
size_limit: 100 * (1 << 20),
dfa_size_limit: 1000 * (1 << 20),
nest_limit: 250,
line_terminator: None,
crlf: false,
word: false,
fixed_strings: false,
whole_line: false,
}
}
}
impl Config {
/// Use this configuration to build an HIR from the given patterns. The HIR
/// returned corresponds to a single regex that is an alternation of the
/// patterns given.
pub(crate) fn build_many<P: AsRef<str>>(
&self,
patterns: &[P],
) -> Result<ConfiguredHIR, Error> {
ConfiguredHIR::new(self.clone(), patterns)
/// Parse the given pattern and returned its HIR expression along with
/// the current configuration.
///
/// If there was a problem parsing the given expression then an error
/// is returned.
pub fn hir(&self, pattern: &str) -> Result<ConfiguredHIR, Error> {
let ast = self.ast(pattern)?;
let analysis = self.analysis(&ast)?;
let expr = hir::translate::TranslatorBuilder::new()
.allow_invalid_utf8(true)
.case_insensitive(self.is_case_insensitive(&analysis))
.multi_line(self.multi_line)
.dot_matches_new_line(self.dot_matches_new_line)
.swap_greed(self.swap_greed)
.unicode(self.unicode)
.build()
.translate(pattern, &ast)
.map_err(Error::regex)?;
let expr = match self.line_terminator {
None => expr,
Some(line_term) => strip_from_match(expr, line_term)?,
};
Ok(ConfiguredHIR {
original: pattern.to_string(),
config: self.clone(),
analysis,
// If CRLF mode is enabled, replace `$` with `(?:\r?$)`.
expr: if self.crlf { crlfify(expr) } else { expr },
})
}
/// Accounting for the `smart_case` config knob, return true if and only if
@@ -89,55 +105,35 @@ impl Config {
analysis.any_literal() && !analysis.any_uppercase()
}
/// Returns whether the given patterns should be treated as "fixed strings"
/// literals. This is different from just querying the `fixed_strings` knob
/// in that if the knob is false, this will still return true in some cases
/// if the patterns are themselves indistinguishable from literals.
/// Returns true if and only if this config is simple enough such that
/// if the pattern is a simple alternation of literals, then it can be
/// constructed via a plain Aho-Corasick automaton.
///
/// The main idea here is that if this returns true, then it is safe
/// to build an `regex_syntax::hir::Hir` value directly from the given
/// patterns as an alternation of `hir::Literal` values.
fn is_fixed_strings<P: AsRef<str>>(&self, patterns: &[P]) -> bool {
// When these are enabled, we really need to parse the patterns and
// let them go through the standard HIR translation process in order
// for case folding transforms to be applied.
if self.case_insensitive || self.case_smart {
return false;
}
// Even if whole_line or word is enabled, both of those things can
// be implemented by wrapping the Hir generated by an alternation of
// fixed string literals. So for here at least, we don't care about the
// word or whole_line settings.
if self.fixed_strings {
// ... but if any literal contains a line terminator, then we've
// got to bail out because this will ultimately result in an error.
if let Some(lineterm) = self.line_terminator {
for p in patterns.iter() {
if has_line_terminator(lineterm, p.as_ref()) {
return false;
}
}
}
return true;
}
// In this case, the only way we can hand construct the Hir is if none
// of the patterns contain meta characters. If they do, then we need to
// send them through the standard parsing/translation process.
for p in patterns.iter() {
let p = p.as_ref();
if p.chars().any(regex_syntax::is_meta_character) {
return false;
}
// Same deal as when fixed_strings is set above. If the pattern has
// a line terminator anywhere, then we need to bail out and let
// an error occur.
if let Some(lineterm) = self.line_terminator {
if has_line_terminator(lineterm, p) {
return false;
}
}
}
true
/// Note that it is OK to return true even when settings like `multi_line`
/// are enabled, since if multi-line can impact the match semantics of a
/// regex, then it is by definition not a simple alternation of literals.
pub fn can_plain_aho_corasick(&self) -> bool {
!self.word && !self.case_insensitive && !self.case_smart
}
/// Perform analysis on the AST of this pattern.
///
/// This returns an error if the given pattern failed to parse.
fn analysis(&self, ast: &Ast) -> Result<AstAnalysis, Error> {
Ok(AstAnalysis::from_ast(ast))
}
/// Parse the given pattern into its abstract syntax.
///
/// This returns an error if the given pattern failed to parse.
fn ast(&self, pattern: &str) -> Result<Ast, Error> {
ast::parse::ParserBuilder::new()
.nest_limit(self.nest_limit)
.octal(self.octal)
.ignore_whitespace(self.ignore_whitespace)
.build()
.parse(pattern)
.map_err(Error::regex)
}
}
@@ -153,268 +149,170 @@ impl Config {
/// size limits set on the configured HIR will be propagated out to any
/// subsequently constructed HIR or regular expression.
#[derive(Clone, Debug)]
pub(crate) struct ConfiguredHIR {
pub struct ConfiguredHIR {
original: String,
config: Config,
hir: Hir,
analysis: AstAnalysis,
expr: Hir,
}
impl ConfiguredHIR {
/// Parse the given patterns into a single HIR expression that represents
/// an alternation of the patterns given.
fn new<P: AsRef<str>>(
config: Config,
patterns: &[P],
) -> Result<ConfiguredHIR, Error> {
let hir = if config.is_fixed_strings(patterns) {
let mut alts = vec![];
for p in patterns.iter() {
alts.push(Hir::literal(p.as_ref().as_bytes()));
}
log::debug!(
"assembling HIR from {} fixed string literals",
alts.len()
);
let hir = Hir::alternation(alts);
hir
} else {
let mut alts = vec![];
for p in patterns.iter() {
alts.push(if config.fixed_strings {
format!("(?:{})", regex_syntax::escape(p.as_ref()))
} else {
format!("(?:{})", p.as_ref())
});
}
let pattern = alts.join("|");
let ast = ast::parse::ParserBuilder::new()
.nest_limit(config.nest_limit)
.octal(config.octal)
.ignore_whitespace(config.ignore_whitespace)
.build()
.parse(&pattern)
.map_err(Error::generic)?;
let analysis = AstAnalysis::from_ast(&ast);
let mut hir = hir::translate::TranslatorBuilder::new()
.utf8(false)
.case_insensitive(config.is_case_insensitive(&analysis))
.multi_line(config.multi_line)
.dot_matches_new_line(config.dot_matches_new_line)
.crlf(config.crlf)
.swap_greed(config.swap_greed)
.unicode(config.unicode)
.build()
.translate(&pattern, &ast)
.map_err(Error::generic)?;
// We don't need to do this for the fixed-strings case above
// because is_fixed_strings will return false if any pattern
// contains a line terminator. Therefore, we don't need to strip
// it.
//
// We go to some pains to avoid doing this in the fixed-strings
// case because this can result in building a new HIR when ripgrep
// is given a huge set of literals to search for. And this can
// actually take a little time. It's not huge, but it's noticeable.
hir = match config.line_terminator {
None => hir,
Some(line_term) => strip_from_match(hir, line_term)?,
};
hir
};
Ok(ConfiguredHIR { config, hir })
}
/// Return a reference to the underlying configuration.
pub(crate) fn config(&self) -> &Config {
/// Return the configuration for this HIR expression.
pub fn config(&self) -> &Config {
&self.config
}
/// Return a reference to the underyling HIR.
pub(crate) fn hir(&self) -> &Hir {
&self.hir
}
/// Convert this HIR to a regex that can be used for matching.
pub(crate) fn to_regex(&self) -> Result<Regex, Error> {
let meta = Regex::config()
.utf8_empty(false)
.nfa_size_limit(Some(self.config.size_limit))
// We don't expose a knob for this because the one-pass DFA is
// usually not a perf bottleneck for ripgrep. But we give it some
// extra room than the default.
.onepass_size_limit(Some(10 * (1 << 20)))
// Same deal here. The default limit for full DFAs is VERY small,
// but with ripgrep we can afford to spend a bit more time on
// building them I think.
.dfa_size_limit(Some(1 * (1 << 20)))
.dfa_state_limit(Some(1_000))
.hybrid_cache_capacity(self.config.dfa_size_limit);
Regex::builder()
.configure(meta)
.build_from_hir(&self.hir)
.map_err(Error::regex)
}
/// Compute the set of non-matching bytes for this HIR expression.
pub(crate) fn non_matching_bytes(&self) -> ByteSet {
non_matching_bytes(&self.hir)
pub fn non_matching_bytes(&self) -> ByteSet {
non_matching_bytes(&self.expr)
}
/// Returns true if and only if this regex needs to have its match offsets
/// tweaked because of CRLF support. Specifically, this occurs when the
/// CRLF hack is enabled and the regex is line anchored at the end. In
/// this case, matches that end with a `\r` have the `\r` stripped.
pub fn needs_crlf_stripped(&self) -> bool {
self.config.crlf && self.expr.is_line_anchored_end()
}
/// Returns the line terminator configured on this expression.
///
/// When we have beginning/end anchors (NOT line anchors), the fast line
/// searching path isn't quite correct. Or at least, doesn't match the slow
/// path. Namely, the slow path strips line terminators while the fast path
/// does not. Since '$' (when multi-line mode is disabled) doesn't match at
/// line boundaries, the existence of a line terminator might cause it to
/// not match when it otherwise would with the line terminator stripped.
/// searching path isn't quite correct. Or at least, doesn't match the
/// slow path. Namely, the slow path strips line terminators while the
/// fast path does not. Since '$' (when multi-line mode is disabled)
/// doesn't match at line boundaries, the existence of a line terminator
/// might cause it to not match when it otherwise would with the line
/// terminator stripped.
///
/// Since searching with text anchors is exceptionally rare in the context
/// of line oriented searching (multi-line mode is basically always
/// enabled), we just disable this optimization when there are text
/// anchors. We disable it by not returning a line terminator, since
/// Since searching with text anchors is exceptionally rare in the
/// context of line oriented searching (multi-line mode is basically
/// always enabled), we just disable this optimization when there are
/// text anchors. We disable it by not returning a line terminator, since
/// without a line terminator, the fast search path can't be executed.
///
/// Actually, the above is no longer quite correct. Later on, another
/// optimization was added where if the line terminator was in the set of
/// bytes that was guaranteed to never be part of a match, then the higher
/// level search infrastructure assumes that the fast line-by-line search
/// path can still be taken. This optimization applies when multi-line
/// search (not multi-line mode) is enabled. In that case, there is no
/// configured line terminator since the regex is permitted to match a
/// line terminator. But if the regex is guaranteed to never match across
/// multiple lines despite multi-line search being requested, we can still
/// do the faster and more flexible line-by-line search. This is why the
/// non-matching extraction routine removes `\n` when `\A` and `\z` are
/// present even though that's not quite correct...
///
/// See: <https://github.com/BurntSushi/ripgrep/issues/2260>
pub(crate) fn line_terminator(&self) -> Option<LineTerminator> {
if self.hir.properties().look_set().contains_anchor_haystack() {
pub fn line_terminator(&self) -> Option<LineTerminator> {
if self.is_any_anchored() {
None
} else {
self.config.line_terminator
}
}
/// Turns this configured HIR into one that only matches when both sides of
/// the match correspond to a word boundary.
/// Returns true if and only if the underlying HIR has any text anchors.
fn is_any_anchored(&self) -> bool {
self.expr.is_any_anchored_start() || self.expr.is_any_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())
}
/// If this HIR corresponds to an alternation of literals with no
/// capturing groups, then this returns those literals.
pub fn alternation_literals(&self) -> Option<Vec<Vec<u8>>> {
if !self.config.can_plain_aho_corasick() {
return None;
}
alternation_literals(&self.expr)
}
/// Applies the given function to the concrete syntax of this HIR and then
/// generates a new HIR based on the result of the function in a way that
/// preserves the configuration.
///
/// Note that the HIR returned is like turning `pat` into
/// `(?m:^|\W)(pat)(?m:$|\W)`. That is, the true match is at capture group
/// `1` and not `0`.
pub(crate) fn into_word(self) -> Result<ConfiguredHIR, Error> {
// In theory building the HIR for \W should never fail, but there are
// likely some pathological cases (particularly with respect to certain
// values of limits) where it could in theory fail.
let non_word = {
let mut config = self.config.clone();
config.fixed_strings = false;
ConfiguredHIR::new(config, &[r"\W"])?
};
let line_anchor_start = Hir::look(self.line_anchor_start());
let line_anchor_end = Hir::look(self.line_anchor_end());
let hir = Hir::concat(vec![
Hir::alternation(vec![line_anchor_start, non_word.hir.clone()]),
Hir::capture(hir::Capture {
index: 1,
name: None,
sub: Box::new(renumber_capture_indices(self.hir)?),
}),
Hir::alternation(vec![non_word.hir, line_anchor_end]),
]);
Ok(ConfiguredHIR { config: self.config, hir })
/// For example, this can be used to wrap a user provided regular
/// expression with additional semantics. e.g., See the `WordMatcher`.
pub fn with_pattern<F: FnMut(&str) -> String>(
&self,
mut f: F,
) -> Result<ConfiguredHIR, Error> {
self.pattern_to_hir(&f(&self.expr.to_string()))
}
/// Turns this configured HIR into an equivalent one, but where it must
/// match at the start and end of a line.
pub(crate) fn into_whole_line(self) -> ConfiguredHIR {
let line_anchor_start = Hir::look(self.line_anchor_start());
let line_anchor_end = Hir::look(self.line_anchor_end());
let hir =
Hir::concat(vec![line_anchor_start, self.hir, line_anchor_end]);
ConfiguredHIR { config: self.config, hir }
}
/// Turns this configured HIR into an equivalent one, but where it must
/// match at the start and end of the haystack.
pub(crate) fn into_anchored(self) -> ConfiguredHIR {
let hir = Hir::concat(vec![
Hir::look(hir::Look::Start),
self.hir,
Hir::look(hir::Look::End),
]);
ConfiguredHIR { config: self.config, hir }
}
/// Returns the "start line" anchor for this configuration.
fn line_anchor_start(&self) -> hir::Look {
if self.config.crlf {
hir::Look::StartCRLF
} else {
hir::Look::StartLF
/// If the current configuration has a line terminator set and if useful
/// literals could be extracted, then a regular expression matching those
/// literals is returned. If no line terminator is set, then `None` is
/// returned.
///
/// If compiling the resulting regular expression failed, then an error
/// is returned.
///
/// This method only returns something when a line terminator is set
/// because matches from this regex are generally candidates that must be
/// confirmed before reporting a match. When performing a line oriented
/// search, confirmation is easy: just extend the candidate match to its
/// respective line boundaries and then re-search that line for a full
/// match. This only works when the line terminator is set because the line
/// terminator setting guarantees that the regex itself can never match
/// through the line terminator byte.
pub fn fast_line_regex(&self) -> Result<Option<Regex>, Error> {
if self.config.line_terminator.is_none() {
return Ok(None);
}
match LiteralSets::new(&self.expr).one_regex(self.config.word) {
None => Ok(None),
Some(pattern) => self.pattern_to_regex(&pattern).map(Some),
}
}
/// Returns the "end line" anchor for this configuration.
fn line_anchor_end(&self) -> hir::Look {
if self.config.crlf {
hir::Look::EndCRLF
} else {
hir::Look::EndLF
}
}
}
/// This increments the index of every capture group in the given hir by 1. If
/// any increment results in an overflow, then an error is returned.
fn renumber_capture_indices(hir: Hir) -> Result<Hir, Error> {
Ok(match hir.into_kind() {
HirKind::Empty => Hir::empty(),
HirKind::Literal(hir::Literal(lit)) => Hir::literal(lit),
HirKind::Class(cls) => Hir::class(cls),
HirKind::Look(x) => Hir::look(x),
HirKind::Repetition(mut x) => {
x.sub = Box::new(renumber_capture_indices(*x.sub)?);
Hir::repetition(x)
}
HirKind::Capture(mut cap) => {
cap.index = match cap.index.checked_add(1) {
Some(index) => index,
None => {
// This error message kind of sucks, but it's probably
// impossible for it to happen. The only way a capture
// index can overflow addition is if the regex is huge
// (or something else has gone horribly wrong).
let msg = "could not renumber capture index, too big";
return Err(Error::any(msg));
}
};
cap.sub = Box::new(renumber_capture_indices(*cap.sub)?);
Hir::capture(cap)
}
HirKind::Concat(subs) => {
let subs = subs
.into_iter()
.map(|sub| renumber_capture_indices(sub))
.collect::<Result<Vec<Hir>, Error>>()?;
Hir::concat(subs)
}
HirKind::Alternation(subs) => {
let subs = subs
.into_iter()
.map(|sub| renumber_capture_indices(sub))
.collect::<Result<Vec<Hir>, Error>>()?;
Hir::alternation(subs)
}
})
}
/// Returns true if the given literal string contains any byte from the line
/// terminator given.
fn has_line_terminator(lineterm: LineTerminator, literal: &str) -> bool {
if lineterm.is_crlf() {
literal.as_bytes().iter().copied().any(|b| b == b'\r' || b == b'\n')
} else {
literal.as_bytes().iter().copied().any(|b| b == lineterm.as_byte())
/// Create a regex from the given pattern using this HIR's configuration.
fn pattern_to_regex(&self, pattern: &str) -> Result<Regex, Error> {
// The settings we explicitly set here are intentionally a subset
// of the settings we have. The key point here is that our HIR
// expression is computed with the settings in mind, such that setting
// them here could actually lead to unintended behavior. For example,
// consider the pattern `(?U)a+`. This will get folded into the HIR
// as a non-greedy repetition operator which will in turn get printed
// to the concrete syntax as `a+?`, which is correct. But if we
// set the `swap_greed` option again, then we'll wind up with `(?U)a+?`
// which is equal to `a+` which is not the same as what we were given.
//
// We also don't need to apply `case_insensitive` since this gets
// folded into the HIR and would just cause us to do redundant work.
//
// Finally, we don't need to set `ignore_whitespace` since the concrete
// syntax emitted by the HIR printer never needs it.
//
// We set the rest of the options. Some of them are important, such as
// the size limit, and some of them are necessary to preserve the
// intention of the original pattern. For example, the Unicode flag
// will impact how the WordMatcher functions, namely, whether its
// word boundaries are Unicode aware or not.
RegexBuilder::new(&pattern)
.nest_limit(self.config.nest_limit)
.octal(self.config.octal)
.multi_line(self.config.multi_line)
.dot_matches_new_line(self.config.dot_matches_new_line)
.unicode(self.config.unicode)
.size_limit(self.config.size_limit)
.dfa_size_limit(self.config.dfa_size_limit)
.build()
.map_err(Error::regex)
}
/// Create an HIR expression from the given pattern using this HIR's
/// configuration.
fn pattern_to_hir(&self, pattern: &str) -> Result<ConfiguredHIR, Error> {
// See `pattern_to_regex` comment for explanation of why we only set
// a subset of knobs here. e.g., `swap_greed` is explicitly left out.
let expr = ::regex_syntax::ParserBuilder::new()
.nest_limit(self.config.nest_limit)
.octal(self.config.octal)
.allow_invalid_utf8(true)
.multi_line(self.config.multi_line)
.dot_matches_new_line(self.config.dot_matches_new_line)
.unicode(self.config.unicode)
.build()
.parse(pattern)
.map_err(Error::regex)?;
Ok(ConfiguredHIR {
original: self.original.clone(),
config: self.config.clone(),
analysis: self.analysis.clone(),
expr,
})
}
}

189
crates/regex/src/crlf.rs Normal file
View File

@@ -0,0 +1,189 @@
use std::collections::HashMap;
use grep_matcher::{Match, Matcher, NoError};
use regex::bytes::Regex;
use regex_syntax::hir::{self, Hir, HirKind};
use crate::config::ConfiguredHIR;
use crate::error::Error;
use crate::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_mut(), haystack, at);
if !r.is_some() {
return Ok(false);
}
// If the end of our match includes a `\r`, then strip it from all
// capture groups ending at the same location.
let end = caps.locations().get(0).unwrap().1;
if end > 0 && haystack.get(end - 1) == Some(&b'\r') {
caps.strip_crlf(true);
}
Ok(true)
}
// We specifically do not implement other methods like find_iter or
// captures_iter. Namely, the iter methods are guaranteed to be correct
// by virtue of implementing find_at and captures_at above.
}
/// If the given match ends with a `\r`, then return a new match that ends
/// immediately before the `\r`.
pub fn adjust_match(haystack: &[u8], m: Match) -> Match {
if m.end() > 0 && haystack.get(m.end() - 1) == Some(&b'\r') {
m.with_end(m.end() - 1)
} else {
m
}
}
/// Substitutes all occurrences of multi-line enabled `$` with `(?:\r?$)`.
///
/// This does not preserve the exact semantics of the given expression,
/// however, it does have the useful property that anything that matched the
/// given expression will also match the returned expression. The difference is
/// that the returned expression can match possibly other things as well.
///
/// The principle reason why we do this is because the underlying regex engine
/// doesn't support CRLF aware `$` look-around. It's planned to fix it at that
/// level, but we perform this kludge in the mean time.
///
/// Note that while the match preserving semantics are nice and neat, the
/// match position semantics are quite a bit messier. Namely, `$` only ever
/// matches the position between characters where as `\r??` can match a
/// character and change the offset. This is regretable, but works out pretty
/// nicely in most cases, especially when a match is limited to a single line.
pub fn crlfify(expr: Hir) -> Hir {
match expr.into_kind() {
HirKind::Anchor(hir::Anchor::EndLine) => {
let concat = Hir::concat(vec![
Hir::repetition(hir::Repetition {
kind: hir::RepetitionKind::ZeroOrOne,
greedy: false,
hir: Box::new(Hir::literal(hir::Literal::Unicode('\r'))),
}),
Hir::anchor(hir::Anchor::EndLine),
]);
Hir::group(hir::Group {
kind: hir::GroupKind::NonCapturing,
hir: Box::new(concat),
})
}
HirKind::Empty => Hir::empty(),
HirKind::Literal(x) => Hir::literal(x),
HirKind::Class(x) => Hir::class(x),
HirKind::Anchor(x) => Hir::anchor(x),
HirKind::WordBoundary(x) => Hir::word_boundary(x),
HirKind::Repetition(mut x) => {
x.hir = Box::new(crlfify(*x.hir));
Hir::repetition(x)
}
HirKind::Group(mut x) => {
x.hir = Box::new(crlfify(*x.hir));
Hir::group(x)
}
HirKind::Concat(xs) => {
Hir::concat(xs.into_iter().map(crlfify).collect())
}
HirKind::Alternation(xs) => {
Hir::alternation(xs.into_iter().map(crlfify).collect())
}
}
}
#[cfg(test)]
mod tests {
use super::crlfify;
use regex_syntax::Parser;
fn roundtrip(pattern: &str) -> String {
let expr1 = Parser::new().parse(pattern).unwrap();
let expr2 = crlfify(expr1);
expr2.to_string()
}
#[test]
fn various() {
assert_eq!(roundtrip(r"(?m)$"), "(?:\r??(?m:$))");
assert_eq!(roundtrip(r"(?m)$$"), "(?:\r??(?m:$))(?:\r??(?m:$))");
assert_eq!(
roundtrip(r"(?m)(?:foo$|bar$)"),
"(?:foo(?:\r??(?m:$))|bar(?:\r??(?m:$)))"
);
assert_eq!(roundtrip(r"(?m)$a"), "(?:\r??(?m:$))a");
// Not a multiline `$`, so no crlfifying occurs.
assert_eq!(roundtrip(r"$"), "\\z");
// It's a literal, derp.
assert_eq!(roundtrip(r"\$"), "\\$");
}
}

71
crates/regex/src/error.rs
View File

@@ -1,3 +1,8 @@
use std::error;
use std::fmt;
use crate::util;
/// An error that can occur in this crate.
///
/// Generally, this error corresponds to problems building a regular
@@ -13,27 +18,10 @@ impl Error {
Error { kind }
}
pub(crate) fn regex(err: regex_automata::meta::BuildError) -> Error {
if let Some(size_limit) = err.size_limit() {
let kind = ErrorKind::Regex(format!(
"compiled regex exceeds size limit of {size_limit}",
));
Error { kind }
} else if let Some(ref err) = err.syntax_error() {
Error::generic(err)
} else {
Error::generic(err)
}
}
pub(crate) fn generic<E: std::error::Error>(err: E) -> Error {
pub(crate) fn regex<E: error::Error>(err: E) -> Error {
Error { kind: ErrorKind::Regex(err.to_string()) }
}
pub(crate) fn any<E: ToString>(msg: E) -> Error {
Error { kind: ErrorKind::Regex(msg.to_string()) }
}
/// Return the kind of this error.
pub fn kind(&self) -> &ErrorKind {
&self.kind
@@ -42,7 +30,6 @@ impl Error {
/// The kind of an error that can occur.
#[derive(Clone, Debug)]
#[non_exhaustive]
pub enum ErrorKind {
/// An error that occurred as a result of parsing a regular expression.
/// This can be a syntax error or an error that results from attempting to
@@ -64,26 +51,38 @@ pub enum ErrorKind {
///
/// The invalid byte is included in this error.
InvalidLineTerminator(u8),
/// Hints that destructuring should not be exhaustive.
///
/// This enum may grow additional variants, so this makes sure clients
/// don't count on exhaustive matching. (Otherwise, adding a new variant
/// could break existing code.)
#[doc(hidden)]
__Nonexhaustive,
}
impl std::error::Error for Error {}
impl std::fmt::Display for Error {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
use bstr::ByteSlice;
impl error::Error for Error {
fn description(&self) -> &str {
match self.kind {
ErrorKind::Regex(ref s) => write!(f, "{}", s),
ErrorKind::NotAllowed(ref lit) => {
write!(f, "the literal {:?} is not allowed in a regex", lit)
}
ErrorKind::InvalidLineTerminator(byte) => {
write!(
f,
"line terminators must be ASCII, but {} is not",
[byte].as_bstr()
)
}
ErrorKind::Regex(_) => "regex error",
ErrorKind::NotAllowed(_) => "literal not allowed",
ErrorKind::InvalidLineTerminator(_) => "invalid line terminator",
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}
impl fmt::Display for Error {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self.kind {
ErrorKind::Regex(ref s) => write!(f, "{}", s),
ErrorKind::NotAllowed(ref lit) => {
write!(f, "the literal '{:?}' is not allowed in a regex", lit)
}
ErrorKind::InvalidLineTerminator(byte) => {
let x = util::show_bytes(&[byte]);
write!(f, "line terminators must be ASCII, but '{}' is not", x)
}
ErrorKind::__Nonexhaustive => unreachable!(),
}
}
}

3
crates/regex/src/lib.rs
View File

@@ -8,9 +8,12 @@ pub use crate::matcher::{RegexCaptures, RegexMatcher, RegexMatcherBuilder};
mod ast;
mod config;
mod crlf;
mod error;
mod literal;
mod matcher;
mod multi;
mod non_matching;
mod strip;
mod util;
mod word;

1311
crates/regex/src/literal.rs
View File

File diff suppressed because it is too large Load Diff

414
crates/regex/src/matcher.rs
View File

@@ -1,22 +1,15 @@
use std::sync::Arc;
use std::collections::HashMap;
use {
grep_matcher::{
ByteSet, Captures, LineMatchKind, LineTerminator, Match, Matcher,
NoError,
},
regex_automata::{
meta::Regex, util::captures::Captures as AutomataCaptures, Input,
PatternID,
},
use grep_matcher::{
ByteSet, Captures, LineMatchKind, LineTerminator, Match, Matcher, NoError,
};
use regex::bytes::{CaptureLocations, Regex};
use crate::{
config::{Config, ConfiguredHIR},
error::Error,
literal::InnerLiterals,
word::WordMatcher,
};
use crate::config::{Config, ConfiguredHIR};
use crate::crlf::CRLFMatcher;
use crate::error::Error;
use crate::multi::MultiLiteralMatcher;
use crate::word::WordMatcher;
/// A builder for constructing a `Matcher` using regular expressions.
///
@@ -50,37 +43,18 @@ impl RegexMatcherBuilder {
/// The syntax supported is documented as part of the regex crate:
/// <https://docs.rs/regex/#syntax>.
pub fn build(&self, pattern: &str) -> Result<RegexMatcher, Error> {
self.build_many(&[pattern])
}
/// Build a new matcher using the current configuration for the provided
/// patterns. The resulting matcher behaves as if all of the patterns
/// given are joined together into a single alternation. That is, it
/// reports matches where at least one of the given patterns matches.
pub fn build_many<P: AsRef<str>>(
&self,
patterns: &[P],
) -> Result<RegexMatcher, Error> {
let chir = self.config.build_many(patterns)?;
let matcher = RegexMatcherImpl::new(chir)?;
let (chir, re) = (matcher.chir(), matcher.regex());
log::trace!("final regex: {:?}", chir.hir().to_string());
let chir = self.config.hir(pattern)?;
let fast_line_regex = chir.fast_line_regex()?;
let non_matching_bytes = chir.non_matching_bytes();
// If we can pick out some literals from the regex, then we might be
// able to build a faster regex that quickly identifies candidate
// matching lines. The regex engine will do what it can on its own, but
// we can specifically do a little more when a line terminator is set.
// For example, for a regex like `\w+foo\w+`, we can look for `foo`,
// and when a match is found, look for the line containing `foo` and
// then run the original regex on only that line. (In this case, the
// regex engine is likely to handle this case for us since it's so
// simple, but the idea applies.)
let fast_line_regex = InnerLiterals::new(chir, re).one_regex()?;
if let Some(ref re) = fast_line_regex {
log::debug!("extracted fast line regex: {:?}", re);
}
// We override the line terminator in case the configured HIR doesn't
// support it.
let matcher = RegexMatcherImpl::new(&chir)?;
log::trace!("final regex: {:?}", matcher.regex());
let mut config = self.config.clone();
// We override the line terminator in case the configured expr doesn't
// support it.
config.line_terminator = chir.line_terminator();
Ok(RegexMatcher {
config,
@@ -99,7 +73,39 @@ impl RegexMatcherBuilder {
&self,
literals: &[B],
) -> Result<RegexMatcher, Error> {
self.build_many(literals)
let mut has_escape = false;
let mut slices = vec![];
for lit in literals {
slices.push(lit.as_ref());
has_escape = has_escape || lit.as_ref().contains('\\');
}
// Even when we have a fixed set of literals, we might still want to
// use the regex engine. Specifically, if any string has an escape
// in it, then we probably can't feed it to Aho-Corasick without
// removing the escape. Additionally, if there are any particular
// special match semantics we need to honor, that Aho-Corasick isn't
// enough. Finally, the regex engine can do really well with a small
// number of literals (at time of writing, this is changing soon), so
// we use it when there's a small set.
//
// Yes, this is one giant hack. Ideally, this entirely separate literal
// matcher that uses Aho-Corasick would be pushed down into the regex
// engine.
if has_escape
|| !self.config.can_plain_aho_corasick()
|| literals.len() < 40
{
return self.build(&slices.join("|"));
}
let matcher = MultiLiteralMatcher::new(&slices)?;
let imp = RegexMatcherImpl::MultiLiteral(matcher);
Ok(RegexMatcher {
config: self.config.clone(),
matcher: imp,
fast_line_regex: None,
non_matching_bytes: ByteSet::empty(),
})
}
/// Set the value for the case insensitive (`i`) flag.
@@ -300,15 +306,20 @@ impl RegexMatcherBuilder {
/// 1. It causes the line terminator for the matcher to be `\r\n`. Namely,
/// this prevents the matcher from ever producing a match that contains
/// a `\r` or `\n`.
/// 2. It enables CRLF mode for `^` and `$`. This means that line anchors
/// will treat both `\r` and `\n` as line terminators, but will never
/// match between a `\r` and `\n`.
/// 2. It translates all instances of `$` in the pattern to `(?:\r??$)`.
/// This works around the fact that the regex engine does not support
/// matching CRLF as a line terminator when using `$`.
///
/// Note that if you do not wish to set the line terminator but would
/// still like `$` to match `\r\n` line terminators, then it is valid to
/// call `crlf(true)` followed by `line_terminator(None)`. Ordering is
/// important, since `crlf` sets the line terminator, but `line_terminator`
/// does not touch the `crlf` setting.
/// In particular, because of (2), the matches produced by the matcher may
/// be slightly different than what one would expect given the pattern.
/// This is the trade off made: in many cases, `$` will "just work" in the
/// presence of `\r\n` line terminators, but matches may require some
/// trimming to faithfully represent the intended match.
///
/// Note that if you do not wish to set the line terminator but would still
/// like `$` to match `\r\n` line terminators, then it is valid to call
/// `crlf(true)` followed by `line_terminator(None)`. Ordering is
/// important, since `crlf` and `line_terminator` override each other.
pub fn crlf(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
if yes {
self.config.line_terminator = Some(LineTerminator::crlf());
@@ -334,21 +345,6 @@ impl RegexMatcherBuilder {
self.config.word = yes;
self
}
/// Whether the patterns should be treated as literal strings or not. When
/// this is active, all characters, including ones that would normally be
/// special regex meta characters, are matched literally.
pub fn fixed_strings(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.fixed_strings = yes;
self
}
/// Whether each pattern should match the entire line or not. This is
/// equivalent to surrounding the pattern with `(?m:^)` and `(?m:$)`.
pub fn whole_line(&mut self, yes: bool) -> &mut RegexMatcherBuilder {
self.config.whole_line = yes;
self
}
}
/// An implementation of the `Matcher` trait using Rust's standard regex
@@ -378,10 +374,10 @@ impl RegexMatcher {
/// Create a new matcher from the given pattern using the default
/// configuration, but matches lines terminated by `\n`.
///
/// This is meant to be a convenience constructor for
/// using a `RegexMatcherBuilder` and setting its
/// [`line_terminator`](RegexMatcherBuilder::method.line_terminator) to
/// `\n`. The purpose of using this constructor is to permit special
/// This is meant to be a convenience constructor for using a
/// `RegexMatcherBuilder` and setting its
/// [`line_terminator`](struct.RegexMatcherBuilder.html#method.line_terminator)
/// to `\n`. The purpose of using this constructor is to permit special
/// optimizations that help speed up line oriented search. These types of
/// optimizations are only appropriate when matches span no more than one
/// line. For this reason, this constructor will return an error if the
@@ -397,6 +393,13 @@ impl RegexMatcher {
enum RegexMatcherImpl {
/// The standard matcher used for all regular expressions.
Standard(StandardMatcher),
/// A matcher for an alternation of plain literals.
MultiLiteral(MultiLiteralMatcher),
/// 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)(...)($|\W)` instead of the more intuitive `\b(...)\b`.
/// Because of this, the WordMatcher provides its own implementation of
@@ -408,33 +411,29 @@ enum RegexMatcherImpl {
impl RegexMatcherImpl {
/// Based on the configuration, create a new implementation of the
/// `Matcher` trait.
fn new(mut chir: ConfiguredHIR) -> Result<RegexMatcherImpl, Error> {
// When whole_line is set, we don't use a word matcher even if word
// matching was requested. Why? Because `(?m:^)(pat)(?m:$)` implies
// word matching.
Ok(if chir.config().word && !chir.config().whole_line {
RegexMatcherImpl::Word(WordMatcher::new(chir)?)
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 {
if chir.config().whole_line {
chir = chir.into_whole_line();
if let Some(lits) = expr.alternation_literals() {
if lits.len() >= 40 {
let matcher = MultiLiteralMatcher::new(&lits)?;
return Ok(RegexMatcherImpl::MultiLiteral(matcher));
}
}
RegexMatcherImpl::Standard(StandardMatcher::new(chir)?)
})
}
/// Return the underlying regex object used.
fn regex(&self) -> &Regex {
match *self {
RegexMatcherImpl::Word(ref x) => x.regex(),
RegexMatcherImpl::Standard(ref x) => &x.regex,
Ok(RegexMatcherImpl::Standard(StandardMatcher::new(expr)?))
}
}
/// Return the underlying HIR of the regex used for searching.
fn chir(&self) -> &ConfiguredHIR {
/// Return the underlying regex object used.
fn regex(&self) -> String {
match *self {
RegexMatcherImpl::Word(ref x) => x.chir(),
RegexMatcherImpl::Standard(ref x) => &x.chir,
RegexMatcherImpl::Word(ref x) => x.regex().to_string(),
RegexMatcherImpl::CRLF(ref x) => x.regex().to_string(),
RegexMatcherImpl::MultiLiteral(_) => "<N/A>".to_string(),
RegexMatcherImpl::Standard(ref x) => x.regex.to_string(),
}
}
}
@@ -454,6 +453,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find_at(haystack, at),
MultiLiteral(ref m) => m.find_at(haystack, at),
CRLF(ref m) => m.find_at(haystack, at),
Word(ref m) => m.find_at(haystack, at),
}
}
@@ -462,6 +463,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.new_captures(),
MultiLiteral(ref m) => m.new_captures(),
CRLF(ref m) => m.new_captures(),
Word(ref m) => m.new_captures(),
}
}
@@ -470,6 +473,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.capture_count(),
MultiLiteral(ref m) => m.capture_count(),
CRLF(ref m) => m.capture_count(),
Word(ref m) => m.capture_count(),
}
}
@@ -478,6 +483,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.capture_index(name),
MultiLiteral(ref m) => m.capture_index(name),
CRLF(ref m) => m.capture_index(name),
Word(ref m) => m.capture_index(name),
}
}
@@ -486,6 +493,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find(haystack),
MultiLiteral(ref m) => m.find(haystack),
CRLF(ref m) => m.find(haystack),
Word(ref m) => m.find(haystack),
}
}
@@ -497,6 +506,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.find_iter(haystack, matched),
MultiLiteral(ref m) => m.find_iter(haystack, matched),
CRLF(ref m) => m.find_iter(haystack, matched),
Word(ref m) => m.find_iter(haystack, matched),
}
}
@@ -512,6 +523,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.try_find_iter(haystack, matched),
MultiLiteral(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),
}
}
@@ -524,6 +537,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures(haystack, caps),
MultiLiteral(ref m) => m.captures(haystack, caps),
CRLF(ref m) => m.captures(haystack, caps),
Word(ref m) => m.captures(haystack, caps),
}
}
@@ -540,6 +555,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures_iter(haystack, caps, matched),
MultiLiteral(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),
}
}
@@ -556,6 +573,10 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.try_captures_iter(haystack, caps, matched),
MultiLiteral(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),
}
}
@@ -569,6 +590,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.captures_at(haystack, at, caps),
MultiLiteral(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),
}
}
@@ -585,6 +608,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.replace(haystack, dst, append),
MultiLiteral(ref m) => m.replace(haystack, dst, append),
CRLF(ref m) => m.replace(haystack, dst, append),
Word(ref m) => m.replace(haystack, dst, append),
}
}
@@ -604,6 +629,12 @@ impl Matcher for RegexMatcher {
Standard(ref m) => {
m.replace_with_captures(haystack, caps, dst, append)
}
MultiLiteral(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)
}
@@ -614,6 +645,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.is_match(haystack),
MultiLiteral(ref m) => m.is_match(haystack),
CRLF(ref m) => m.is_match(haystack),
Word(ref m) => m.is_match(haystack),
}
}
@@ -626,6 +659,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.is_match_at(haystack, at),
MultiLiteral(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),
}
}
@@ -637,6 +672,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.shortest_match(haystack),
MultiLiteral(ref m) => m.shortest_match(haystack),
CRLF(ref m) => m.shortest_match(haystack),
Word(ref m) => m.shortest_match(haystack),
}
}
@@ -649,6 +686,8 @@ impl Matcher for RegexMatcher {
use self::RegexMatcherImpl::*;
match self.matcher {
Standard(ref m) => m.shortest_match_at(haystack, at),
MultiLiteral(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),
}
}
@@ -667,10 +706,7 @@ impl Matcher for RegexMatcher {
) -> Result<Option<LineMatchKind>, NoError> {
Ok(match self.fast_line_regex {
Some(ref regex) => {
let input = Input::new(haystack);
regex
.search_half(&input)
.map(|hm| LineMatchKind::Candidate(hm.offset()))
regex.shortest_match(haystack).map(LineMatchKind::Candidate)
}
None => {
self.shortest_match(haystack)?.map(LineMatchKind::Confirmed)
@@ -685,19 +721,20 @@ struct StandardMatcher {
/// The regular expression compiled from the pattern provided by the
/// caller.
regex: Regex,
/// The HIR that produced this regex.
///
/// We put this in an `Arc` because by the time it gets here, it won't
/// change. And because cloning and dropping an `Hir` is somewhat expensive
/// due to its deep recursive representation.
chir: Arc<ConfiguredHIR>,
/// A map from capture group name to its corresponding index.
names: HashMap<String, usize>,
}
impl StandardMatcher {
fn new(chir: ConfiguredHIR) -> Result<StandardMatcher, Error> {
let chir = Arc::new(chir);
let regex = chir.to_regex()?;
Ok(StandardMatcher { regex, chir })
fn new(expr: &ConfiguredHIR) -> Result<StandardMatcher, Error> {
let regex = expr.regex()?;
let mut names = HashMap::new();
for (i, optional_name) in regex.capture_names().enumerate() {
if let Some(name) = optional_name {
names.insert(name.to_string(), i);
}
}
Ok(StandardMatcher { regex, names })
}
}
@@ -710,12 +747,14 @@ impl Matcher for StandardMatcher {
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, NoError> {
let input = Input::new(haystack).span(at..haystack.len());
Ok(self.regex.find(input).map(|m| Match::new(m.start(), m.end())))
Ok(self
.regex
.find_at(haystack, at)
.map(|m| Match::new(m.start(), m.end())))
}
fn new_captures(&self) -> Result<RegexCaptures, NoError> {
Ok(RegexCaptures::new(self.regex.create_captures()))
Ok(RegexCaptures::new(self.regex.capture_locations()))
}
fn capture_count(&self) -> usize {
@@ -723,7 +762,7 @@ impl Matcher for StandardMatcher {
}
fn capture_index(&self, name: &str) -> Option<usize> {
self.regex.group_info().to_index(PatternID::ZERO, name)
self.names.get(name).map(|i| *i)
}
fn try_find_iter<F, E>(
@@ -750,10 +789,10 @@ impl Matcher for StandardMatcher {
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
let input = Input::new(haystack).span(at..haystack.len());
let caps = caps.captures_mut();
self.regex.search_captures(&input, caps);
Ok(caps.is_match())
Ok(self
.regex
.captures_read_at(&mut caps.locations_mut(), haystack, at)
.is_some())
}
fn shortest_match_at(
@@ -761,8 +800,7 @@ impl Matcher for StandardMatcher {
haystack: &[u8],
at: usize,
) -> Result<Option<usize>, NoError> {
let input = Input::new(haystack).span(at..haystack.len());
Ok(self.regex.search_half(&input).map(|hm| hm.offset()))
Ok(self.regex.shortest_match_at(haystack, at))
}
}
@@ -781,51 +819,137 @@ impl Matcher for StandardMatcher {
/// index of the group using the corresponding matcher's `capture_index`
/// method, and then use that index with `RegexCaptures::get`.
#[derive(Clone, Debug)]
pub struct RegexCaptures {
/// Where the captures are stored.
caps: AutomataCaptures,
/// These captures behave as if the capturing groups begin at the given
/// offset. When set to `0`, this has no affect and capture groups are
/// indexed like normal.
///
/// This is useful when building matchers that wrap arbitrary regular
/// expressions. For example, `WordMatcher` takes an existing regex
/// `re` and creates `(?:^|\W)(re)(?:$|\W)`, but hides the fact that
/// the regex has been wrapped from the caller. In order to do this,
/// the matcher and the capturing groups must behave as if `(re)` is
/// the `0`th capture group.
offset: usize,
pub struct RegexCaptures(RegexCapturesImp);
#[derive(Clone, Debug)]
enum RegexCapturesImp {
AhoCorasick {
/// The start and end of the match, corresponding to capture group 0.
mat: Option<Match>,
},
Regex {
/// Where the locations are stored.
locs: CaptureLocations,
/// These captures behave as if the capturing groups begin at the given
/// offset. When set to `0`, this has no affect and capture groups are
/// indexed like normal.
///
/// This is useful when building matchers that wrap arbitrary regular
/// expressions. For example, `WordMatcher` takes an existing regex
/// `re` and creates `(?:^|\W)(re)(?:$|\W)`, but hides the fact that
/// the regex has been wrapped from the caller. In order to do this,
/// the matcher and the capturing groups must behave as if `(re)` is
/// the `0`th capture group.
offset: usize,
/// When enable, the end of a match has `\r` stripped from it, if one
/// exists.
strip_crlf: bool,
},
}
impl Captures for RegexCaptures {
fn len(&self) -> usize {
self.caps
.group_info()
.all_group_len()
.checked_sub(self.offset)
.unwrap()
match self.0 {
RegexCapturesImp::AhoCorasick { .. } => 1,
RegexCapturesImp::Regex { ref locs, offset, .. } => {
locs.len().checked_sub(offset).unwrap()
}
}
}
fn get(&self, i: usize) -> Option<Match> {
let actual = i.checked_add(self.offset).unwrap();
self.caps.get_group(actual).map(|sp| Match::new(sp.start, sp.end))
match self.0 {
RegexCapturesImp::AhoCorasick { mat, .. } => {
if i == 0 {
mat
} else {
None
}
}
RegexCapturesImp::Regex { ref locs, offset, strip_crlf } => {
if !strip_crlf {
let actual = i.checked_add(offset).unwrap();
return locs.pos(actual).map(|(s, e)| Match::new(s, e));
}
// currently don't support capture offsetting with CRLF
// stripping
assert_eq!(offset, 0);
let m = match 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() == locs.pos(0).unwrap().1 {
Some(m.with_end(m.end() - 1))
} else {
Some(m)
}
}
}
}
}
impl RegexCaptures {
pub(crate) fn new(caps: AutomataCaptures) -> RegexCaptures {
RegexCaptures::with_offset(caps, 0)
pub(crate) fn simple() -> RegexCaptures {
RegexCaptures(RegexCapturesImp::AhoCorasick { mat: None })
}
pub(crate) fn new(locs: CaptureLocations) -> RegexCaptures {
RegexCaptures::with_offset(locs, 0)
}
pub(crate) fn with_offset(
caps: AutomataCaptures,
locs: CaptureLocations,
offset: usize,
) -> RegexCaptures {
RegexCaptures { caps, offset }
RegexCaptures(RegexCapturesImp::Regex {
locs,
offset,
strip_crlf: false,
})
}
pub(crate) fn captures_mut(&mut self) -> &mut AutomataCaptures {
&mut self.caps
pub(crate) fn locations(&self) -> &CaptureLocations {
match self.0 {
RegexCapturesImp::AhoCorasick { .. } => {
panic!("getting locations for simple captures is invalid")
}
RegexCapturesImp::Regex { ref locs, .. } => locs,
}
}
pub(crate) fn locations_mut(&mut self) -> &mut CaptureLocations {
match self.0 {
RegexCapturesImp::AhoCorasick { .. } => {
panic!("getting locations for simple captures is invalid")
}
RegexCapturesImp::Regex { ref mut locs, .. } => locs,
}
}
pub(crate) fn strip_crlf(&mut self, yes: bool) {
match self.0 {
RegexCapturesImp::AhoCorasick { .. } => {
panic!("setting strip_crlf for simple captures is invalid")
}
RegexCapturesImp::Regex { ref mut strip_crlf, .. } => {
*strip_crlf = yes;
}
}
}
pub(crate) fn set_simple(&mut self, one: Option<Match>) {
match self.0 {
RegexCapturesImp::AhoCorasick { ref mut mat } => {
*mat = one;
}
RegexCapturesImp::Regex { .. } => {
panic!("setting simple captures for regex is invalid")
}
}
}
}
@@ -912,9 +1036,7 @@ mod tests {
}
// Test that finding candidate lines works as expected.
// FIXME: Re-enable this test once inner literal extraction works.
#[test]
#[ignore]
fn candidate_lines() {
fn is_confirmed(m: LineMatchKind) -> bool {
match m {

29
crates/regex/src/multi.rs
View File

@@ -1,6 +1,6 @@
use aho_corasick::{AhoCorasick, MatchKind};
use aho_corasick::{AhoCorasick, AhoCorasickBuilder, MatchKind};
use grep_matcher::{Match, Matcher, NoError};
use regex_syntax::hir::{Hir, HirKind};
use regex_syntax::hir::Hir;
use crate::error::Error;
use crate::matcher::RegexCaptures;
@@ -23,10 +23,11 @@ impl MultiLiteralMatcher {
pub fn new<B: AsRef<[u8]>>(
literals: &[B],
) -> Result<MultiLiteralMatcher, Error> {
let ac = AhoCorasick::builder()
let ac = AhoCorasickBuilder::new()
.match_kind(MatchKind::LeftmostFirst)
.build(literals)
.map_err(Error::generic)?;
.auto_configure(literals)
.build_with_size::<usize, _, _>(literals)
.map_err(Error::regex)?;
Ok(MultiLiteralMatcher { ac })
}
}
@@ -78,11 +79,13 @@ impl Matcher for MultiLiteralMatcher {
/// Alternation literals checks if the given HIR is a simple alternation of
/// literals, and if so, returns them. Otherwise, this returns None.
pub fn alternation_literals(expr: &Hir) -> Option<Vec<Vec<u8>>> {
use regex_syntax::hir::{HirKind, Literal};
// This is pretty hacky, but basically, if `is_alternation_literal` is
// true, then we can make several assumptions about the structure of our
// HIR. This is what justifies the `unreachable!` statements below.
if !expr.properties().is_alternation_literal() {
if !expr.is_alternation_literal() {
return None;
}
let alts = match *expr.kind() {
@@ -90,16 +93,26 @@ pub fn alternation_literals(expr: &Hir) -> Option<Vec<Vec<u8>>> {
_ => return None, // one literal isn't worth it
};
let extendlit = |lit: &Literal, dst: &mut Vec<u8>| match *lit {
Literal::Unicode(c) => {
let mut buf = [0; 4];
dst.extend_from_slice(c.encode_utf8(&mut buf).as_bytes());
}
Literal::Byte(b) => {
dst.push(b);
}
};
let mut lits = vec![];
for alt in alts {
let mut lit = vec![];
match *alt.kind() {
HirKind::Empty => {}
HirKind::Literal(ref x) => lit.extend_from_slice(&x.0),
HirKind::Literal(ref x) => extendlit(x, &mut lit),
HirKind::Concat(ref exprs) => {
for e in exprs {
match *e.kind() {
HirKind::Literal(ref x) => lit.extend_from_slice(&x.0),
HirKind::Literal(ref x) => extendlit(x, &mut lit),
_ => unreachable!("expected literal, got {:?}", e),
}
}

55
crates/regex/src/non_matching.rs
View File

@@ -1,13 +1,9 @@
use {
grep_matcher::ByteSet,
regex_syntax::{
hir::{self, Hir, HirKind, Look},
utf8::Utf8Sequences,
},
};
use grep_matcher::ByteSet;
use regex_syntax::hir::{self, Hir, HirKind};
use regex_syntax::utf8::Utf8Sequences;
/// Return a confirmed set of non-matching bytes from the given expression.
pub(crate) fn non_matching_bytes(expr: &Hir) -> ByteSet {
pub fn non_matching_bytes(expr: &Hir) -> ByteSet {
let mut set = ByteSet::full();
remove_matching_bytes(expr, &mut set);
set
@@ -17,27 +13,18 @@ pub(crate) fn non_matching_bytes(expr: &Hir) -> ByteSet {
/// the given expression.
fn remove_matching_bytes(expr: &Hir, set: &mut ByteSet) {
match *expr.kind() {
HirKind::Empty
| HirKind::Look(Look::WordAscii | Look::WordAsciiNegate)
| HirKind::Look(Look::WordUnicode | Look::WordUnicodeNegate) => {}
HirKind::Look(Look::Start | Look::End) => {
// FIXME: This is wrong, but not doing this leads to incorrect
// results because of how anchored searches are implemented in
// the 'grep-searcher' crate.
HirKind::Empty | HirKind::WordBoundary(_) => {}
HirKind::Anchor(_) => {
set.remove(b'\n');
}
HirKind::Look(Look::StartLF | Look::EndLF) => {
set.remove(b'\n');
}
HirKind::Look(Look::StartCRLF | Look::EndCRLF) => {
set.remove(b'\r');
set.remove(b'\n');
}
HirKind::Literal(hir::Literal(ref lit)) => {
for &b in lit.iter() {
HirKind::Literal(hir::Literal::Unicode(c)) => {
for &b in c.encode_utf8(&mut [0; 4]).as_bytes() {
set.remove(b);
}
}
HirKind::Literal(hir::Literal::Byte(b)) => {
set.remove(b);
}
HirKind::Class(hir::Class::Unicode(ref cls)) => {
for range in cls.iter() {
// This is presumably faster than encoding every codepoint
@@ -55,10 +42,10 @@ fn remove_matching_bytes(expr: &Hir, set: &mut ByteSet) {
}
}
HirKind::Repetition(ref x) => {
remove_matching_bytes(&x.sub, set);
remove_matching_bytes(&x.hir, set);
}
HirKind::Capture(ref x) => {
remove_matching_bytes(&x.sub, set);
HirKind::Group(ref x) => {
remove_matching_bytes(&x.hir, set);
}
HirKind::Concat(ref xs) => {
for x in xs {
@@ -75,13 +62,17 @@ fn remove_matching_bytes(expr: &Hir, set: &mut ByteSet) {
#[cfg(test)]
mod tests {
use {grep_matcher::ByteSet, regex_syntax::ParserBuilder};
use grep_matcher::ByteSet;
use regex_syntax::ParserBuilder;
use super::non_matching_bytes;
fn extract(pattern: &str) -> ByteSet {
let expr =
ParserBuilder::new().utf8(false).build().parse(pattern).unwrap();
let expr = ParserBuilder::new()
.allow_invalid_utf8(true)
.build()
.parse(pattern)
.unwrap();
non_matching_bytes(&expr)
}
@@ -140,13 +131,9 @@ mod tests {
#[test]
fn anchor() {
// FIXME: The first four tests below should correspond to a full set
// of bytes for the non-matching bytes I think.
assert_eq!(sparse(&extract(r"^")), sparse_except(&[b'\n']));
assert_eq!(sparse(&extract(r"$")), sparse_except(&[b'\n']));
assert_eq!(sparse(&extract(r"\A")), sparse_except(&[b'\n']));
assert_eq!(sparse(&extract(r"\z")), sparse_except(&[b'\n']));
assert_eq!(sparse(&extract(r"(?m)^")), sparse_except(&[b'\n']));
assert_eq!(sparse(&extract(r"(?m)$")), sparse_except(&[b'\n']));
}
}

91
crates/regex/src/strip.rs
View File

@@ -1,7 +1,5 @@
use {
grep_matcher::LineTerminator,
regex_syntax::hir::{self, Hir, HirKind},
};
use grep_matcher::LineTerminator;
use regex_syntax::hir::{self, Hir, HirKind};
use crate::error::{Error, ErrorKind};
@@ -17,26 +15,7 @@ use crate::error::{Error, ErrorKind};
///
/// If the given line terminator is not ASCII, then this function returns an
/// error.
///
/// Note that as of regex 1.9, this routine could theoretically be implemented
/// without returning an error. Namely, for example, we could turn
/// `foo\nbar` into `foo[a&&b]bar`. That is, replace line terminators with a
/// sub-expression that can never match anything. Thus, ripgrep would accept
/// such regexes and just silently not match anything. Regex versions prior to 1.8
/// don't support such constructs. I ended up deciding to leave the existing
/// behavior of returning an error instead. For example:
///
/// ```text
/// $ echo -n 'foo\nbar\n' | rg 'foo\nbar'
/// the literal '"\n"' is not allowed in a regex
///
/// Consider enabling multiline mode with the --multiline flag (or -U for short).
/// When multiline mode is enabled, new line characters can be matched.
/// ```
///
/// This looks like a good error message to me, and even suggests a flag that
/// the user can use instead.
pub(crate) fn strip_from_match(
pub fn strip_from_match(
expr: Hir,
line_term: LineTerminator,
) -> Result<Hir, Error> {
@@ -44,34 +23,40 @@ pub(crate) fn strip_from_match(
let expr1 = strip_from_match_ascii(expr, b'\r')?;
strip_from_match_ascii(expr1, b'\n')
} else {
strip_from_match_ascii(expr, line_term.as_byte())
let b = line_term.as_byte();
if b > 0x7F {
return Err(Error::new(ErrorKind::InvalidLineTerminator(b)));
}
strip_from_match_ascii(expr, b)
}
}
/// The implementation of strip_from_match. The given byte must be ASCII.
/// This function returns an error otherwise. It also returns an error if
/// it couldn't remove `\n` from the given regex without leaving an empty
/// character class in its place.
/// The implementation of strip_from_match. The given byte must be ASCII. This
/// function panics otherwise.
fn strip_from_match_ascii(expr: Hir, byte: u8) -> Result<Hir, Error> {
if !byte.is_ascii() {
return Err(Error::new(ErrorKind::InvalidLineTerminator(byte)));
}
let ch = char::from(byte);
let invalid = || Err(Error::new(ErrorKind::NotAllowed(ch.to_string())));
assert!(byte <= 0x7F);
let chr = byte as char;
assert_eq!(chr.len_utf8(), 1);
let invalid = || Err(Error::new(ErrorKind::NotAllowed(chr.to_string())));
Ok(match expr.into_kind() {
HirKind::Empty => Hir::empty(),
HirKind::Literal(hir::Literal(lit)) => {
if lit.iter().find(|&&b| b == byte).is_some() {
HirKind::Literal(hir::Literal::Unicode(c)) => {
if c == chr {
return invalid();
}
Hir::literal(lit)
Hir::literal(hir::Literal::Unicode(c))
}
HirKind::Literal(hir::Literal::Byte(b)) => {
if b as char == chr {
return invalid();
}
Hir::literal(hir::Literal::Byte(b))
}
HirKind::Class(hir::Class::Unicode(mut cls)) => {
if cls.ranges().is_empty() {
return Ok(Hir::class(hir::Class::Unicode(cls)));
}
let remove = hir::ClassUnicode::new(Some(
hir::ClassUnicodeRange::new(ch, ch),
hir::ClassUnicodeRange::new(chr, chr),
));
cls.difference(&remove);
if cls.ranges().is_empty() {
@@ -80,9 +65,6 @@ fn strip_from_match_ascii(expr: Hir, byte: u8) -> Result<Hir, Error> {
Hir::class(hir::Class::Unicode(cls))
}
HirKind::Class(hir::Class::Bytes(mut cls)) => {
if cls.ranges().is_empty() {
return Ok(Hir::class(hir::Class::Bytes(cls)));
}
let remove = hir::ClassBytes::new(Some(
hir::ClassBytesRange::new(byte, byte),
));
@@ -92,14 +74,15 @@ fn strip_from_match_ascii(expr: Hir, byte: u8) -> Result<Hir, Error> {
}
Hir::class(hir::Class::Bytes(cls))
}
HirKind::Look(x) => Hir::look(x),
HirKind::Anchor(x) => Hir::anchor(x),
HirKind::WordBoundary(x) => Hir::word_boundary(x),
HirKind::Repetition(mut x) => {
x.sub = Box::new(strip_from_match_ascii(*x.sub, byte)?);
x.hir = Box::new(strip_from_match_ascii(*x.hir, byte)?);
Hir::repetition(x)
}
HirKind::Capture(mut x) => {
x.sub = Box::new(strip_from_match_ascii(*x.sub, byte)?);
Hir::capture(x)
HirKind::Group(mut x) => {
x.hir = Box::new(strip_from_match_ascii(*x.hir, byte)?);
Hir::group(x)
}
HirKind::Concat(xs) => {
let xs = xs
@@ -148,11 +131,11 @@ mod tests {
#[test]
fn various() {
assert_eq!(roundtrip(r"[a\n]", b'\n'), "a");
assert_eq!(roundtrip(r"[a\n]", b'a'), "\n");
assert_eq!(roundtrip_crlf(r"[a\n]"), "a");
assert_eq!(roundtrip_crlf(r"[a\r]"), "a");
assert_eq!(roundtrip_crlf(r"[a\r\n]"), "a");
assert_eq!(roundtrip(r"[a\n]", b'\n'), "[a]");
assert_eq!(roundtrip(r"[a\n]", b'a'), "[\n]");
assert_eq!(roundtrip_crlf(r"[a\n]"), "[a]");
assert_eq!(roundtrip_crlf(r"[a\r]"), "[a]");
assert_eq!(roundtrip_crlf(r"[a\r\n]"), "[a]");
assert_eq!(roundtrip(r"(?-u)\s", b'a'), r"(?-u:[\x09-\x0D\x20])");
assert_eq!(roundtrip(r"(?-u)\s", b'\n'), r"(?-u:[\x09\x0B-\x0D\x20])");

29
crates/regex/src/util.rs Normal file
View File

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

126
crates/regex/src/word.rs
View File

@@ -1,59 +1,39 @@
use std::{
collections::HashMap,
panic::{RefUnwindSafe, UnwindSafe},
sync::Arc,
};
use std::cell::RefCell;
use std::collections::HashMap;
use std::sync::Arc;
use {
grep_matcher::{Match, Matcher, NoError},
regex_automata::{
meta::Regex, util::captures::Captures, util::pool::Pool, Input,
PatternID,
},
};
use grep_matcher::{Match, Matcher, NoError};
use regex::bytes::{CaptureLocations, Regex};
use thread_local::ThreadLocal;
use crate::{config::ConfiguredHIR, error::Error, matcher::RegexCaptures};
type PoolFn =
Box<dyn Fn() -> Captures + Send + Sync + UnwindSafe + RefUnwindSafe>;
use crate::config::ConfiguredHIR;
use crate::error::Error;
use crate::matcher::RegexCaptures;
/// A matcher for implementing "word match" semantics.
#[derive(Debug)]
pub(crate) struct WordMatcher {
pub struct WordMatcher {
/// The regex which is roughly `(?:^|\W)(<original pattern>)(?:$|\W)`.
regex: Regex,
/// The HIR that produced the regex above. We don't keep the HIR for the
/// `original` regex.
///
/// We put this in an `Arc` because by the time it gets here, it won't
/// change. And because cloning and dropping an `Hir` is somewhat expensive
/// due to its deep recursive representation.
chir: Arc<ConfiguredHIR>,
/// The original regex supplied by the user, which we use in a fast path
/// to try and detect matches before deferring to slower engines.
original: Regex,
/// A map from capture group name to capture group index.
names: HashMap<String, usize>,
/// A thread-safe pool of reusable buffers for finding the match offset of
/// the inner group.
caps: Arc<Pool<Captures, PoolFn>>,
/// A reusable buffer for finding the match location of the inner group.
locs: Arc<ThreadLocal<RefCell<CaptureLocations>>>,
}
impl Clone for WordMatcher {
fn clone(&self) -> WordMatcher {
// We implement Clone manually so that we get a fresh Pool such that it
// can set its own thread owner. This permits each thread usings `caps`
// to hit the fast path.
//
// Note that cloning a regex is "cheap" since it uses reference
// counting internally.
let re = self.regex.clone();
// We implement Clone manually so that we get a fresh ThreadLocal such
// that it can set its own thread owner. This permits each thread
// usings `locs` to hit the fast path.
WordMatcher {
regex: self.regex.clone(),
chir: Arc::clone(&self.chir),
original: self.original.clone(),
names: self.names.clone(),
caps: Arc::new(Pool::new(Box::new(move || re.create_captures()))),
locs: Arc::new(ThreadLocal::new()),
}
}
}
@@ -64,38 +44,31 @@ impl WordMatcher {
///
/// The given options are used to construct the regular expression
/// internally.
pub(crate) fn new(chir: ConfiguredHIR) -> Result<WordMatcher, Error> {
let original = chir.clone().into_anchored().to_regex()?;
let chir = Arc::new(chir.into_word()?);
let regex = chir.to_regex()?;
let caps = Arc::new(Pool::new({
let regex = regex.clone();
Box::new(move || regex.create_captures()) as PoolFn
}));
pub fn new(expr: &ConfiguredHIR) -> Result<WordMatcher, Error> {
let original =
expr.with_pattern(|pat| format!("^(?:{})$", pat))?.regex()?;
let word_expr = expr.with_pattern(|pat| {
let pat = format!(r"(?:(?m:^)|\W)({})(?:\W|(?m:$))", pat);
log::debug!("word regex: {:?}", pat);
pat
})?;
let regex = word_expr.regex()?;
let locs = Arc::new(ThreadLocal::new());
let mut names = HashMap::new();
let it = regex.group_info().pattern_names(PatternID::ZERO);
for (i, optional_name) in it.enumerate() {
for (i, optional_name) in regex.capture_names().enumerate() {
if let Some(name) = optional_name {
names.insert(name.to_string(), i.checked_sub(1).unwrap());
}
}
Ok(WordMatcher { regex, chir, original, names, caps })
Ok(WordMatcher { regex, original, names, locs })
}
/// Return the underlying regex used to match at word boundaries.
///
/// The original regex is in the capture group at index 1.
pub(crate) fn regex(&self) -> &Regex {
/// Return the underlying regex used by this matcher.
pub fn regex(&self) -> &Regex {
&self.regex
}
/// Return the underlying HIR for the regex used to match at word
/// boundaries.
pub(crate) fn chir(&self) -> &ConfiguredHIR {
&self.chir
}
/// Attempt to do a fast confirmation of a word match that covers a subset
/// (but hopefully a big subset) of most cases. Ok(Some(..)) is returned
/// when a match is found. Ok(None) is returned when there is definitively
@@ -106,11 +79,12 @@ impl WordMatcher {
haystack: &[u8],
at: usize,
) -> Result<Option<Match>, ()> {
// This is a bit hairy. The whole point here is to avoid running a
// slower regex engine to extract capture groups. Remember, our word
// regex looks like this:
// This is a bit hairy. The whole point here is to avoid running an
// NFA simulation in the regex engine. Remember, our word regex looks
// like this:
//
// (^|\W)(<original regex>)(\W|$)
// (^|\W)(<original regex>)($|\W)
// where ^ and $ have multiline mode DISABLED
//
// What we want are the match offsets of <original regex>. So in the
// easy/common case, the original regex will be sandwiched between
@@ -128,8 +102,7 @@ impl WordMatcher {
// The reason why we cannot handle the ^/$ cases here is because we
// can't assume anything about the original pattern. (Try commenting
// out the checks for ^/$ below and run the tests to see examples.)
let input = Input::new(haystack).span(at..haystack.len());
let mut cand = match self.regex.find(input) {
let mut cand = match self.regex.find_at(haystack, at) {
None => return Ok(None),
Some(m) => Match::new(m.start(), m.end()),
};
@@ -172,23 +145,23 @@ impl Matcher for WordMatcher {
//
// OK, well, it turns out that it is worth it! But it is quite tricky.
// See `fast_find` for details. Effectively, this lets us skip running
// a slower regex engine to extract capture groups in the vast majority
// of cases. However, the slower engine is I believe required for full
// correctness.
// the NFA simulation in the regex engine in the vast majority of
// cases. However, the NFA simulation is required for full correctness.
match self.fast_find(haystack, at) {
Ok(Some(m)) => return Ok(Some(m)),
Ok(None) => return Ok(None),
Err(()) => {}
}
let input = Input::new(haystack).span(at..haystack.len());
let mut caps = self.caps.get();
self.regex.search_captures(&input, &mut caps);
Ok(caps.get_group(1).map(|sp| Match::new(sp.start, sp.end)))
let cell =
self.locs.get_or(|| RefCell::new(self.regex.capture_locations()));
let mut caps = cell.borrow_mut();
self.regex.captures_read_at(&mut caps, haystack, at);
Ok(caps.get(1).map(|m| Match::new(m.0, m.1)))
}
fn new_captures(&self) -> Result<RegexCaptures, NoError> {
Ok(RegexCaptures::with_offset(self.regex.create_captures(), 1))
Ok(RegexCaptures::with_offset(self.regex.capture_locations(), 1))
}
fn capture_count(&self) -> usize {
@@ -205,10 +178,9 @@ impl Matcher for WordMatcher {
at: usize,
caps: &mut RegexCaptures,
) -> Result<bool, NoError> {
let input = Input::new(haystack).span(at..haystack.len());
let caps = caps.captures_mut();
self.regex.search_captures(&input, caps);
Ok(caps.is_match())
let r =
self.regex.captures_read_at(caps.locations_mut(), haystack, at);
Ok(r.is_some())
}
// We specifically do not implement other methods like find_iter or
@@ -223,8 +195,8 @@ mod tests {
use grep_matcher::{Captures, Match, Matcher};
fn matcher(pattern: &str) -> WordMatcher {
let chir = Config::default().build_many(&[pattern]).unwrap();
WordMatcher::new(chir).unwrap()
let chir = Config::default().hir(pattern).unwrap();
WordMatcher::new(&chir).unwrap()
}
fn find(pattern: &str, haystack: &str) -> Option<(usize, usize)> {

8
crates/searcher/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "grep-searcher"
version = "0.1.11" #:version
version = "0.1.10" #:version
authors = ["Andrew Gallant <jamslam@gmail.com>"]
description = """
Fast line oriented regex searching as a library.
@@ -14,16 +14,16 @@ license = "Unlicense OR MIT"
edition = "2018"
[dependencies]
bstr = { version = "1.6.0", default-features = false, features = ["std"] }
bstr = { version = "0.2.0", default-features = false, features = ["std"] }
bytecount = "0.6"
encoding_rs = "0.8.14"
encoding_rs_io = "0.1.6"
grep-matcher = { version = "0.1.6", path = "../matcher" }
grep-matcher = { version = "0.1.5", path = "../matcher" }
log = "0.4.5"
memmap = { package = "memmap2", version = "0.5.3" }
[dev-dependencies]
grep-regex = { version = "0.1.11", path = "../regex" }
grep-regex = { version = "0.1.10", path = "../regex" }
regex = "1.1"
[features]

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

@@ -481,7 +481,7 @@ impl LineBuffer {
}
let roll_len = self.end - self.pos;
self.buf.copy_within(self.pos..self.end, 0);
self.buf.copy_within_str(self.pos..self.end, 0);
self.pos = 0;
self.last_lineterm = roll_len;
self.end = roll_len;

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

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

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

@@ -71,6 +71,16 @@ impl MmapChoice {
if !self.is_enabled() {
return None;
}
if !cfg!(target_pointer_width = "64") {
// For 32-bit systems, it looks like mmap will succeed even if it
// can't address the entire file. This seems to happen at least on
// Windows, even though it uses to work prior to ripgrep 13. The
// only Windows-related change in ripgrep 13, AFAIK, was statically
// linking vcruntime. So maybe that's related? But I'm not sure.
//
// See: https://github.com/BurntSushi/ripgrep/issues/1911
return None;
}
if cfg!(target_os = "macos") {
// I guess memory maps on macOS aren't great. Should re-evaluate.
return None;

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

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

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

@@ -232,16 +232,6 @@ would behave identically to the following command
rg --glob '!.git' foo
The bottom line is that every shell argument needs to be on its own line. So
for example, a config file containing
-j 4
is probably not doing what you intend. Instead, you want
-j
4
ripgrep also provides a flag, *--no-config*, that when present will suppress
any and all support for configuration. This includes any future support
for auto-loading configuration files from pre-determined paths.

28
pkg/windows/Manifest.xml
View File

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

15
pkg/windows/README.md
View File

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

46
tests/feature.rs
View File

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

45
tests/misc.rs
View File

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

47
tests/regression.rs
View File

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