Add grep benchmarks and CodSpeed CI workflow

Add a divan-based benchmark suite (benches/grep_bench.rs) modeled on the
sed benchmarks, covering literal/fixed-string/regex search, case-insensitive
matching, counting, inversion, line numbers, word/whole-line matching, and
quiet mode. Wire up the dev-dependencies (codspeed-divan-compat, tempfile,
uucore benchmark feature) and a [[bench]] entry.

Add a Benchmarks GitHub Actions workflow running the suite through CodSpeed,
adapted from the sed setup.

.github/workflows/benchmarks.yml

@@ -0,0 +1,50 @@
+name: Benchmarks
+
+# spell-checker:ignore codspeed dtolnay Swatinem sccache
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+permissions:
+  contents: read # to fetch code (actions/checkout)
+
+# End the current execution if there is a new changeset in the PR.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+jobs:
+  benchmarks:
+    name: Run benchmarks (CodSpeed)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+
+      - name: Install Rust
+        uses: dtolnay/rust-toolchain@stable
+      - uses: Swatinem/rust-cache@v2
+
+      - name: Run sccache-cache
+        uses: mozilla-actions/sccache-action@v0.0.10
+
+      - name: Install cargo-codspeed
+        uses: taiki-e/install-action@v2
+        with:
+          tool: cargo-codspeed
+
+      - name: Build benchmarks
+        run: cargo codspeed build -p uu_grep
+
+      - name: Run benchmarks
+        uses: CodSpeedHQ/action@v4
+        env:
+          CODSPEED_LOG: debug
+        with:
+          mode: simulation
+          run: cargo codspeed run -p uu_grep > /dev/null
+          token: ${{ secrets.CODSPEED_TOKEN }}

.github/workflows/codspeed.yml

@@ -1,37 +0,0 @@
-name: CodSpeed
-
-on:
-  push:
-    branches:
-      - "main"
-  pull_request:
-  # `workflow_dispatch` allows CodSpeed to trigger backtest
-  # performance analysis in order to generate initial data.
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  id-token: write
-
-jobs:
-  codspeed:
-    name: Run benchmarks
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Setup Rust toolchain, cache and cargo-codspeed binary
-        uses: moonrepo/setup-rust@v0
-        with:
-          channel: stable
-          cache-target: release
-          bins: cargo-codspeed
-
-      - name: Build the benchmark target(s)
-        run: cargo codspeed build
-
-      - name: Run the benchmarks
-        uses: CodSpeedHQ/action@v4
-        with:
-          mode: simulation
-          run: cargo codspeed run

.pre-commit-config.yaml

@@ -1,55 +0,0 @@
-# See https://pre-commit.com for more information
-# See https://pre-commit.com/hooks.html for more hooks
-exclude: ^tests/fixtures/
-repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v6.0.0
-    hooks:
-      - id: check-added-large-files
-      - id: check-executables-have-shebangs
-      - id: check-json
-        exclude: '\.vscode/(cSpell|extensions)\.json' # cSpell.json and extensions.json use comments
-      - id: check-shebang-scripts-are-executable
-        exclude: '.+\.rs' # would be triggered by #![some_attribute]
-      - id: check-symlinks
-      - id: check-toml
-      - id: check-yaml
-        args: [ --allow-multiple-documents ]
-      - id: destroyed-symlinks
-      - id: end-of-file-fixer
-      - id: mixed-line-ending
-        args: [ --fix=lf ]
-      - id: trailing-whitespace
-
-  - repo: local
-    hooks:
-      - id: rust-linting
-        name: Rust linting
-        description: Run cargo fmt on files included in the commit.
-        entry: cargo +stable fmt --
-        pass_filenames: true
-        types: [file, rust]
-        language: system
-      - id: rust-clippy
-        name: Rust clippy
-        description: Run cargo clippy on files included in the commit.
-        entry: cargo +stable clippy --workspace --all-targets --all-features -- -D warnings
-        pass_filenames: false
-        types: [file, rust]
-        language: system
-      - id: cargo-lock-check
-        name: Cargo.lock sync check
-        description: Ensure Cargo.lock and fuzz/Cargo.lock are up-to-date.
-        entry: bash -c 'for dir in . fuzz; do if [ -d "$dir" ]; then ( cd "$dir" && cargo fetch --quiet ); fi; done'
-        pass_filenames: false
-        files: 'Cargo\.(toml|lock)$'
-        language: system
-      - id: cspell
-        name: Code spell checker (cspell)
-        description: Run cspell to check for spelling errors (if available).
-        entry: bash -c 'if command -v cspell >/dev/null 2>&1; then cspell --no-must-find-files -- "$@"; else echo "cspell not found, skipping spell check"; exit 0; fi' --
-        pass_filenames: true
-        language: system
-
-ci:
-  skip: [rust-linting, rust-clippy, cargo-lock-check, cspell]

Cargo.toml

@@ -27,10 +27,12 @@ onig_sys = { version = "*", default-features = false }
 uucore = "0.8.0"
 walkdir = "2.5"
 
+[dev-dependencies]
+divan = { package = "codspeed-divan-compat", version = "4.0.5" }
+tempfile = "3.10.1"
+uucore = { version = "0.8.0", features = ["benchmark"] }
+uutests = "0.8.0"
+
 [[bench]]
 name = "grep_bench"
 harness = false
-
-[dev-dependencies]
-criterion = { version = "4.7.0", package = "codspeed-criterion-compat" }
-uutests = "0.8.0"

README.md

@@ -4,7 +4,6 @@
 [![dependency status](https://deps.rs/repo/github/uutils/grep/status.svg)](https://deps.rs/repo/github/uutils/grep)
 
 [![CodeCov](https://codecov.io/gh/uutils/grep/branch/main/graph/badge.svg)](https://codecov.io/gh/uutils/grep)
-[![CodSpeed](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/uutils/grep?utm_source=badge)
 
 # Grep, now in Rust
 
@@ -30,10 +29,6 @@ cargo build --release
 cargo test
 ```
 
-## Pre-commit hooks
-
-This project uses [pre-commit](https://pre-commit.com); run `pre-commit install` to enable the git hooks.
-
 ## Known Issues
 
 * Does not take `LANG`, etc., into account for handling file encodings (non-UTF8 matches are treated as binary)

src/lib.rs

@@ -3,12 +3,9 @@
 // For the full copyright and license information, please view the LICENSE
 // file that was distributed with this source code.
 
-#[doc(hidden)]
+mod context_buffer;
-pub mod context_buffer;
+mod line_buffer;
-#[doc(hidden)]
+mod matcher;
-pub mod line_buffer;
-#[doc(hidden)]
-pub mod matcher;
 mod output;
 mod searcher;
 
@@ -23,8 +20,7 @@ use std::path::Path;
 use uucore::error::{FromIo, UResult, USimpleError};
 
 #[derive(Clone, Copy, PartialEq, Eq)]
-#[doc(hidden)]
+enum RegexMode {
-pub enum RegexMode {
     Fixed,
     Basic,
     Extended,
@@ -32,8 +28,7 @@ pub enum RegexMode {
 }
 
 #[derive(Clone, Copy, PartialEq, Eq)]
-#[doc(hidden)]
+enum BinaryMode {
-pub enum BinaryMode {
     Binary,
     Text,
     WithoutMatch,
@@ -47,84 +42,79 @@ enum ColorMode {
 }
 
 #[derive(Clone, Copy, PartialEq, Eq)]
-#[doc(hidden)]
+enum DirectoryMode {
-pub enum DirectoryMode {
     Read,
     Skip,
     Recurse,
 }
 
 #[derive(Clone, Copy, PartialEq, Eq)]
-#[doc(hidden)]
+enum DeviceMode {
-pub enum DeviceMode {
     Default,
     Read,
     Skip,
 }
 
-#[doc(hidden)]
+struct ColorConfig<'a> {
-pub struct ColorConfig<'a> {
+    matched_selected: &'a str,
-    pub matched_selected: &'a str,
+    matched_context: &'a str,
-    pub matched_context: &'a str,
+    filename: &'a str,
-    pub filename: &'a str,
+    line_number: &'a str,
-    pub line_number: &'a str,
+    byte_offset: &'a str,
-    pub byte_offset: &'a str,
+    separator: &'a str,
-    pub separator: &'a str,
+    selected_line: &'a str,
-    pub selected_line: &'a str,
+    context_line: &'a str,
-    pub context_line: &'a str,
 
-    pub reverse_video: bool,
+    reverse_video: bool,
-    pub no_erase: bool,
+    no_erase: bool,
 }
 
-#[doc(hidden)]
+struct GlobSet {
-pub struct GlobSet {
     patterns: Vec<glob::Pattern>,
 }
 
-#[doc(hidden)]
+struct Config<'a> {
-pub struct Config<'a> {
     // Searcher
-    pub directory_mode: DirectoryMode,
+    directory_mode: DirectoryMode,
-    pub device_mode: DeviceMode,
+    device_mode: DeviceMode,
-    pub follow_symlinks: bool,
+    follow_symlinks: bool,
-    pub include_globs: GlobSet,
+    include_globs: GlobSet,
-    pub exclude_globs: GlobSet,
+    exclude_globs: GlobSet,
-    pub exclude_dir_globs: GlobSet,
+    exclude_dir_globs: GlobSet,
-    pub label: &'a str,
+    label: &'a str,
     #[cfg(windows)]
-    pub strip_cr: bool,
+    strip_cr: bool,
-    pub binary_mode: BinaryMode,
+    binary_mode: BinaryMode,
-    pub max_count: Option<u64>,
+    max_count: Option<u64>,
-    pub before_context: usize,
+    before_context: usize,
-    pub after_context: usize,
+    after_context: usize,
-    pub has_context: bool,
+    has_context: bool,
 
     // Matcher
-    pub patterns: &'a [&'a str],
+    patterns: &'a [&'a str],
-    pub regex_mode: RegexMode,
+    regex_mode: RegexMode,
-    pub ignore_case: bool,
+    ignore_case: bool,
-    pub invert_match: bool,
+    invert_match: bool,
-    pub word_regexp: bool,
+    word_regexp: bool,
-    pub line_regexp: bool,
+    line_regexp: bool,
 
     // Output
-    pub quiet: bool,
+    quiet: bool,
-    pub count: bool,
+    count: bool,
-    pub show_filename: bool,
+    show_filename: bool,
-    pub files_with_matches: bool,
+    files_with_matches: bool,
-    pub files_without_match: bool,
+    files_without_match: bool,
-    pub only_matching: bool,
+    only_matching: bool,
-    pub byte_offset: bool,
+    byte_offset: bool,
-    pub line_number: bool,
+    line_number: bool,
-    pub initial_tab: bool,
+    initial_tab: bool,
-    pub null_separator: bool,
+    null_separator: bool,
-    pub null_data: bool,
+    null_data: bool,
-    pub line_buffered: bool,
+    line_buffered: bool,
-    pub no_messages: bool,
+    no_messages: bool,
-    pub group_separator: Option<&'a str>,
+    group_separator: Option<&'a str>,
-    pub use_color: bool,
+    use_color: bool,
-    pub color_config: ColorConfig<'a>,
+    color_config: ColorConfig<'a>,
 }
 
 #[uucore::main(no_signals)]
@@ -864,21 +854,8 @@ fn expand_num_shorthand(args: impl Iterator<Item = OsString>) -> Vec<OsString> {
     out
 }
 
-impl Default for GlobSet {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
 impl GlobSet {
-    /// Create an empty GlobSet.
+    fn with_capacity(capacity: usize) -> Self {
-    pub fn new() -> Self {
-        Self {
-            patterns: Vec::new(),
-        }
-    }
-
-    pub fn with_capacity(capacity: usize) -> Self {
         Self {
             patterns: Vec::with_capacity(capacity),
         }