Add Default impl for GlobSet to satisfy clippy

Add CodSpeed performance benchmarks

.github/workflows/benchmarks.yml

@@ -1,50 +0,0 @@
-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

@@ -0,0 +1,37 @@
+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

@@ -0,0 +1,55 @@
+# 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

@@ -27,12 +27,10 @@ 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

@@ -4,6 +4,7 @@
 [![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
 
@@ -29,6 +30,10 @@ 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

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