updatedb: clear error when the output database can't be created

Opening the output file with `?` surfaced a bare "No such file or
directory" with no indication of which file failed (easy to hit because the
default output path /usr/local/var/locatedb often doesn't exist).

Report it like GNU does, naming the path and the reason, e.g.
`cannot create '/usr/local/var/locatedb': No such file or directory`.
strip_errno() drops the trailing "(os error N)" noise.

.appveyor.yml

@@ -1,23 +0,0 @@
-os: Visual Studio 2015
-
-version: "{build}"
-
-environment:
-  matrix:
-    - channel: stable
-      target: x86_64-pc-windows-msvc
-    - channel: nightly
-      target: x86_64-pc-windows-msvc
-
-install:
-  - appveyor DownloadFile https://win.rustup.rs/ -FileName rustup-init.exe
-  - rustup-init -yv --default-toolchain %channel% --default-host %target%
-  - set PATH=%PATH%;%USERPROFILE%\.cargo\bin
-  - rustc -vV && cargo -vV
-
-build_script:
-  - cargo build --verbose
-
-test_script:
-  - cargo test --verbose
-

.github/workflows/audit.yml

@@ -0,0 +1,15 @@
+name: Security audit
+
+on:
+  schedule:
+    - cron: "0 0 * * *"
+jobs:
+  audit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+      - uses: rustsec/audit-check@v2
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/ci.yml

@@ -2,6 +2,9 @@ on: [push, pull_request]
 
 name: Basic CI
 
+env:
+  CARGO_INCREMENTAL: "0"
+
 jobs:
   check:
     name: cargo check
@@ -10,15 +13,9 @@ jobs:
       matrix:
         os: [ubuntu-latest, macOS-latest, windows-latest]
     steps:
-      - uses: actions/checkout@v3
-      - name: Install `rust` toolchain
-        run: |
-          ## Install `rust` toolchain
-          rustup toolchain install stable --no-self-update -c rustfmt --profile minimal
-          rustup default stable
-
+      - uses: actions/checkout@v6
       # For bindgen: https://github.com/rust-lang/rust-bindgen/issues/1797
-      - uses: KyleMayes/install-llvm-action@v1
+      - uses: KyleMayes/install-llvm-action@v2
         if: matrix.os == 'windows-latest'
         with:
           version: "11.0"
@@ -28,7 +25,7 @@ jobs:
 
       - name: Check
         run: |
-          cargo check
+          cargo check --all --all-features
 
   test:
     name: cargo test
@@ -37,15 +34,9 @@ jobs:
       matrix:
         os: [ubuntu-latest, macOS-latest, windows-latest]
     steps:
-      - uses: actions/checkout@v3
-      - name: Install `rust` toolchain
-        run: |
-          ## Install `rust` toolchain
-          rustup toolchain install stable --no-self-update -c rustfmt --profile minimal
-          rustup default stable
-
+      - uses: actions/checkout@v6
       # For bindgen: https://github.com/rust-lang/rust-bindgen/issues/1797
-      - uses: KyleMayes/install-llvm-action@v1
+      - uses: KyleMayes/install-llvm-action@v2
         if: matrix.os == 'windows-latest'
         with:
           version: "11.0"
@@ -53,22 +44,15 @@ jobs:
       - run: echo "LIBCLANG_PATH=$((gcm clang).source -replace "clang.exe")" >> $env:GITHUB_ENV
         if: matrix.os == 'windows-latest'
 
-      - name: Check
+      - name: Test
         run: |
-          cargo check
+          cargo test
 
   fmt:
     name: cargo fmt --all -- --check
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - name: Install `rust` toolchain
-        run: |
-          ## Install `rust` toolchain
-          rustup toolchain install stable --no-self-update -c rustfmt --profile minimal
-          rustup default stable
-
-      - run: rustup component add rustfmt
+      - uses: actions/checkout@v6
       - name: cargo fmt
         run: |
           cargo fmt --all -- --check
@@ -77,16 +61,9 @@ jobs:
     name: cargo clippy -- -D warnings
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - name: Install `rust` toolchain
-        run: |
-          ## Install `rust` toolchain
-          rustup toolchain install stable --no-self-update -c rustfmt --profile minimal
-          rustup default stable
-      - run: rustup component add clippy
-      - name: cargo clippy
-        run: |
-          cargo clippy -- -D warnings
+      - uses: actions/checkout@v6
+      - run: |
+          cargo clippy --all-targets -- -D warnings
 
   grcov:
     name: Code coverage
@@ -95,58 +72,29 @@ jobs:
       matrix:
         os:
           - ubuntu-latest
-        toolchain:
-          - nightly
         cargo_flags:
           - "--all-features"
     steps:
       - name: Checkout source code
-        uses: actions/checkout@v3
-
-      - name: Install `rust` toolchain
-        run: |
-          ## Install `rust` toolchain
-          rustup toolchain install nightly --no-self-update -c rustfmt --profile minimal
-          rustup default nightly
-
-      - name: "`grcov` ~ install"
-        run: cargo install grcov
-
-      - name: cargo test
-        run: |
-          cargo test --all --no-fail-fast ${{ matrix.cargo_flags }}
+        uses: actions/checkout@v6
+      - name: Install cargo-llvm-cov
+        uses: taiki-e/install-action@cargo-llvm-cov
+      - name: Generate code coverage
         env:
-          CARGO_INCREMENTAL: "0"
-          RUSTFLAGS: '-Zprofile -Ccodegen-units=1 -Copt-level=0 -Clink-dead-code -Coverflow-checks=off -Zpanic_abort_tests -Cpanic=abort -Cdebug-assertions=off'
-          RUSTDOCFLAGS: '-Zprofile -Ccodegen-units=1 -Copt-level=0 -Clink-dead-code -Coverflow-checks=off -Zpanic_abort_tests -Cpanic=abort -Cdebug-assertions=off'
-
-      - name: Generate coverage data
-        id: grcov
+          RUSTC_BOOTSTRAP: 1
         run: |
-          grcov target/debug/ \
-              --branch \
-              --llvm \
-              --source-dir . \
-              --output-path lcov.info \
-              --ignore-not-existing \
-              --excl-line "#\\[derive\\(" \
-              --excl-br-line "#\\[derive\\(" \
-              --excl-start "#\\[cfg\\(test\\)\\]" \
-              --excl-br-start "#\\[cfg\\(test\\)\\]" \
-              --commit-sha ${{ github.sha }} \
-              --service-job-id ${{ github.job }} \
-              --service-name "GitHub Actions" \
-              --service-number ${{ github.run_id }}
+          cargo llvm-cov --all-features --lcov --branch --output-path lcov.info
+
       - name: Upload coverage as artifact
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v7
         with:
           name: lcov.info
-          # path: ${{ steps.grcov.outputs.report }}
           path: lcov.info
 
       - name: Upload coverage to codecov.io
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v6
         with:
-          # file: ${{ steps.grcov.outputs.report }}
-          file: lcov.info
+          files: lcov.info
           fail_ci_if_error: true
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_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

.github/workflows/comment.yml

@@ -0,0 +1,76 @@
+on:
+  workflow_run:
+    workflows: [External-testsuites]
+    types: [completed]
+
+name: Comment Test results on the PR
+
+permissions: {}
+jobs:
+  upload-pr-comment:
+    if: ${{ github.event.workflow_run.event == 'pull_request' }}
+    
+    name: Upload PR comment
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      pull-requests: write
+
+    steps:
+      - name: List Annotations
+        uses: actions/github-script@v9
+        with:
+          script: |
+            let artifacts = await github.rest.actions.listWorkflowRunArtifacts({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              run_id: ${{ github.event.workflow_run.id }},
+            });
+
+            // List all artifacts
+            let matchArtifact = artifacts.data.artifacts.filter((artifact) => {
+              return artifact.name == "comment"
+            })[0];
+
+            // Download the artifact to github.workspace
+            let download = await github.rest.actions.downloadArtifact({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              artifact_id: matchArtifact.id,
+              archive_format: 'zip',
+            });
+
+            let fs = require('fs');
+            fs.writeFileSync('${{ github.workspace }}/comment.zip', Buffer.from(download.data));
+
+      - run: unzip comment.zip
+
+      - name: Comment on PR
+        uses: actions/github-script@v9
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            let fs = require('fs');
+            let annotations = JSON.parse(fs.readFileSync('./annotations.json', 'utf8'));
+
+            let annotationContent = annotations
+              .data
+              .map(annotation => `${annotation.run}: ${annotation.annotation.message}`)
+              .join('\n');
+
+            // check if no changes
+            let gnuTestReport = annotationContent.includes('Run GNU findutils tests: Gnu tests No changes');
+            let bfsTestReport = annotationContent.includes('Run BFS tests: BFS tests No changes');
+
+            if (gnuTestReport && bfsTestReport) {
+              console.log('No changes');
+              return;
+            }
+
+            // Comment on the PR
+            github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: annotations.pull_request_number,
+              body: 'Commit ${{ github.event.workflow_run.head_sha }} has GNU testsuite comparison:\n```\n' + annotationContent + '\n```\n'
+            });

.github/workflows/compat.yml

@@ -1,145 +1,261 @@
 on: [push, pull_request]
 
-name: External testsuites
-
+name: External-testsuites
+env:
+  CARGO_INCREMENTAL: "0"
 jobs:
   gnu-tests:
+    permissions:
+      actions: read
+      contents: write # Publish binaries instead of discarding
+
     name: Run GNU findutils tests
     runs-on: ubuntu-latest
     steps:
-    - name: Checkout findutils
-      uses: actions/checkout@v3
-      with:
-        path: findutils
-    - name: Checkout GNU findutils
-      uses: actions/checkout@v3
-      with:
-        repository: gnu-mirror-unofficial/findutils
-        path: findutils.gnu
-        ref: 5768a03ddfb5e18b1682e339d6cdd24ff721c510
-        submodules: true
-    - name: Install `rust` toolchain
-      run: |
-        ## Install `rust` toolchain
-        rustup toolchain install stable --no-self-update -c rustfmt --profile minimal
-        rustup default stable
-    - name: Install dependencies
-      shell: bash
-      run: |
-        # Enable sources & install dependencies
-        sudo find /etc/apt/sources.list* -type f -exec sed -i 'p; s/^deb /deb-src /' '{}' +
-        sudo apt-get update
-        sudo apt-get build-dep findutils
-    - name: Run GNU tests
-      shell: bash
-      run: |
-        cd findutils
-        bash util/build-gnu.sh ||:
-    - name: Extract testing info
-      shell: bash
-      run: |
-    - uses: actions/upload-artifact@v3
-      with:
-        name: gnu-test-report
-        path: |
-          findutils.gnu/find/testsuite/*.log
-          findutils.gnu/xargs/testsuite/*.log
-          findutils.gnu/tests/**/*.log
-    - uses: actions/upload-artifact@v3
-      with:
-        name: gnu-result
-        path: gnu-result.json
-    - name: Download the result
-      uses: dawidd6/action-download-artifact@v2
-      with:
-        workflow: compat.yml
-        workflow_conclusion: completed
-        name: gnu-result
-        repo: uutils/findutils
-        branch: main
-        path: dl
-    - name: Download the log
-      uses: dawidd6/action-download-artifact@v2
-      with:
-        workflow: compat.yml
-        workflow_conclusion: completed
-        name: gnu-test-report
-        repo: uutils/findutils
-        branch: main
-        path: dl
-    - name: Compare failing tests against master
-      shell: bash
-      run: |
-        ./findutils/util/diff-gnu.sh ./dl ./findutils.gnu
-    - name: Compare against main results
-      shell: bash
-      run: |
-        mv dl/gnu-result.json latest-gnu-result.json
-        python findutils/util/compare_gnu_result.py
+      - name: Checkout findutils
+        uses: actions/checkout@v6
+        with:
+          path: findutils
+      - name: Checkout GNU findutils
+        uses: actions/checkout@v6
+        with:
+          repository: gnu-mirror-unofficial/findutils
+          path: findutils.gnu
+          ref: 5768a03ddfb5e18b1682e339d6cdd24ff721c510
+          submodules: false
+
+      - name: Override submodule URL and initialize submodules
+        # Use github instead of upstream git server
+        run: |
+          git submodule sync --recursive
+          git config submodule.gnulib.url https://github.com/coreutils/gnulib.git
+          git submodule update --init --recursive --depth 1
+        working-directory: findutils.gnu
+      - name: Install dependencies
+        shell: bash
+        run: |
+          # Enable sources & install dependencies
+          sudo sed -i 's/^Types: deb$/Types: deb deb-src/' /etc/apt/sources.list.d/ubuntu.sources
+          sudo apt-get update
+          sudo apt-get build-dep findutils
+      - name: Run GNU tests
+        shell: bash
+        run: |
+          cd findutils
+          bash util/build-gnu.sh ||:
+          install --strip -Dm755 target/release/{find,xargs} -t findutils-x86_64-unknown-linux-gnu
+          ZSTD_CLEVEL=19 tar --zstd -caf ../findutils-x86_64-unknown-linux-gnu.tar.zst findutils-x86_64-unknown-linux-gnu
+      - name: Publish latest commit
+        uses: softprops/action-gh-release@v3
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        with:
+          tag_name: latest-commit
+          body: |
+            commit: ${{ github.sha }}
+          draft: false
+          prerelease: true
+          files: |
+            findutils-x86_64-unknown-linux-gnu.tar.zst
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Extract testing info
+        shell: bash
+        run: |
+
+      - name: Upload gnu-test-report
+        uses: actions/upload-artifact@v7
+        with:
+          name: gnu-test-report
+          path: |
+            findutils.gnu/find/testsuite/*.log
+            findutils.gnu/xargs/testsuite/*.log
+            findutils.gnu/tests/**/*.log
+      - name: Upload gnu-result
+        uses: actions/upload-artifact@v7
+        with:
+          name: gnu-result
+          path: gnu-result.json
+      - name: Download artifacts (gnu-result and gnu-test-report)
+        uses: actions/github-script@v9
+        with:
+          script: |
+            let fs = require('fs');
+            fs.mkdirSync('${{ github.workspace }}/dl', { recursive: true });
+
+            async function downloadArtifact(artifactName) {
+              // List all artifacts from the workflow run
+              let artifacts = await github.rest.actions.listWorkflowRunArtifacts({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                run_id: ${{ github.run_id }},
+              });
+
+              // Find the specified artifact
+              let matchArtifact = artifacts.data.artifacts.find((artifact) => artifact.name === artifactName);
+              if (!matchArtifact) {
+                throw new Error(`Artifact "${artifactName}" not found.`);
+              }
+
+              // Download the artifact
+              let download = await github.rest.actions.downloadArtifact({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                artifact_id: matchArtifact.id,
+                archive_format: 'zip',
+              });
+
+              // Save the artifact to a file
+              fs.writeFileSync(`${{ github.workspace }}/dl/${artifactName}.zip`, Buffer.from(download.data));
+            }
+
+            // Download the required artifacts
+            await downloadArtifact("gnu-result");
+            await downloadArtifact("gnu-test-report");
+
+      - name: Compare failing tests against master
+        shell: bash
+        run: |
+          ./findutils/util/diff-gnu.sh ./dl ./findutils.gnu
+      - name: Compare against main results
+        shell: bash
+        run: |
+          unzip dl/gnu-result.zip -d dl/
+          unzip dl/gnu-test-report.zip -d dl/
+          mv dl/gnu-result.json latest-gnu-result.json
+          python findutils/util/compare_gnu_result.py
 
   bfs-tests:
     name: Run BFS tests
     runs-on: ubuntu-latest
     steps:
-    - name: Checkout findutils
-      uses: actions/checkout@v3
-      with:
-        path: findutils
-    - name: Checkout BFS
-      uses: actions/checkout@v3
-      with:
-        repository: tavianator/bfs
-        path: bfs
-        ref: '2.6.2'
-    - name: Install `rust` toolchain
-      run: |
-        ## Install `rust` toolchain
-        rustup toolchain install stable --no-self-update -c rustfmt --profile minimal
-        rustup default stable
-    - name: Install dependencies
-      shell: bash
-      run: |
-        # Enable sources & install dependencies
-        sudo find /etc/apt/sources.list* -type f -exec sed -i 'p; s/^deb /deb-src /' '{}' +
-        sudo apt-get update
-        sudo apt-get build-dep bfs
-    - name: Run BFS tests
-      shell: bash
-      run: |
-        cd findutils
-        bash util/build-bfs.sh ||:
-    - uses: actions/upload-artifact@v3
-      with:
-        name: bfs-test-report
-        path: bfs/tests.log
-    - uses: actions/upload-artifact@v3
-      with:
-        name: bfs-result
-        path: bfs-result.json
-    - name: Download the result
-      uses: dawidd6/action-download-artifact@v2
-      with:
-        workflow: compat.yml
-        workflow_conclusion: completed
-        name: bfs-result
-        repo: uutils/findutils
-        branch: main
-        path: dl
-    - name: Download the log
-      uses: dawidd6/action-download-artifact@v2
-      with:
-        workflow: compat.yml
-        workflow_conclusion: completed
-        name: bfs-test-report
-        repo: uutils/findutils
-        branch: main
-        path: dl
-    - name: Compare failing tests against main
-      shell: bash
-      run: |
-        ./findutils/util/diff-bfs.sh dl/tests.log bfs/tests.log
-    - name: Compare against main results
-      shell: bash
-      run: |
-        mv dl/bfs-result.json latest-bfs-result.json
-        python findutils/util/compare_bfs_result.py
+      - name: Checkout findutils
+        uses: actions/checkout@v6
+        with:
+          path: findutils
+      - name: Checkout BFS
+        uses: actions/checkout@v6
+        with:
+          repository: tavianator/bfs
+          path: bfs
+          ref: "4.0"
+      - name: Install dependencies
+        shell: bash
+        run: |
+          # Enable sources & install dependencies
+          sudo sed -i 's/^Types: deb$/Types: deb deb-src/' /etc/apt/sources.list.d/ubuntu.sources
+          sudo apt-get update
+          sudo apt-get build-dep bfs
+      - name: Run BFS tests
+        shell: bash
+        run: |
+          cd findutils
+          export CARGO_INCREMENTAL=0
+          bash util/build-bfs.sh ||:
+      - name: Upload bfs-test-report
+        uses: actions/upload-artifact@v7
+        with:
+          name: bfs-test-report
+          path: bfs/tests.log
+      - name: Upload bfs-result
+        uses: actions/upload-artifact@v7
+        with:
+          name: bfs-result
+          path: bfs-result.json
+      - name: Download artifacts (gnu-result and bfs-test-report)
+        uses: actions/github-script@v9
+        with:
+          script: |
+            let fs = require('fs');
+            fs.mkdirSync('${{ github.workspace }}/dl', { recursive: true });
+
+            async function downloadArtifact(artifactName) {
+              // List all artifacts from the workflow run
+              let artifacts = await github.rest.actions.listWorkflowRunArtifacts({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                run_id: ${{ github.run_id }},
+              });
+
+              // Find the specified artifact
+              let matchArtifact = artifacts.data.artifacts.find((artifact) => artifact.name === artifactName);
+              if (!matchArtifact) {
+                throw new Error(`Artifact "${artifactName}" not found.`);
+              }
+
+              // Download the artifact
+              let download = await github.rest.actions.downloadArtifact({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                artifact_id: matchArtifact.id,
+                archive_format: 'zip',
+              });
+
+              // Save the artifact to a file
+              fs.writeFileSync(`${{ github.workspace }}/dl/${artifactName}.zip`, Buffer.from(download.data));
+            }
+
+            // Download the required artifacts
+            await downloadArtifact("bfs-result");
+            await downloadArtifact("bfs-test-report");
+      - name: Compare failing tests against main
+        shell: bash
+        run: |
+          ./findutils/util/diff-bfs.sh dl/tests.log bfs/tests.log
+      - name: Compare against main results
+        shell: bash
+        run: |
+          unzip dl/bfs-result.zip -d dl/
+          unzip dl/bfs-test-report.zip -d dl/
+          mv dl/bfs-result.json latest-bfs-result.json
+          python findutils/util/compare_bfs_result.py
+
+  upload-annotations:
+    name: Upload annotations
+    runs-on: ubuntu-latest
+    needs: [gnu-tests, bfs-tests]
+    if: ${{ github.event_name == 'pull_request' }}
+
+    steps:
+      - name: List Annotations
+        uses: actions/github-script@v9
+
+        with:
+          script: |
+            let runs = await github.rest.checks.listForRef({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              ref: '${{ github.event.pull_request.head.sha }}'
+            });
+
+            let names = ['Run GNU findutils tests', 'Run BFS tests'];
+            let results = [];
+            runs.data.check_runs.filter(check => names.includes(check.name)).forEach(run => results.push(run));
+
+            let annotations = { data: [], pull_request_number: '${{ github.event.number }}' };
+            for (let result of results) {
+              let run = await github.rest.checks.listAnnotations({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                check_run_id: result.id
+              });
+
+              run.data.forEach(data => {
+                annotations.data.push({
+                  run: result.name,
+                  annotation: data
+                });
+              });
+            }
+
+            // Remove duplicate items.
+            annotations.data = annotations.data.filter((value, index, self) =>
+              self.findIndex(v => v.annotation.message === value.annotation.message) === index);
+
+            let fs = require('fs');
+            fs.writeFileSync('${{ github.workspace }}/annotations.json', JSON.stringify(annotations));
+
+      - name: Upload annotations
+        uses: actions/upload-artifact@v7
+        with:
+          name: comment
+          path: annotations.json

.github/workflows/release.yml

@@ -0,0 +1,291 @@
+# This file was autogenerated by dist: https://opensource.axo.dev/cargo-dist/
+#
+# Copyright 2022-2024, axodotdev
+# SPDX-License-Identifier: MIT or Apache-2.0
+#
+# CI that:
+#
+# * checks for a Git Tag that looks like a release
+# * builds artifacts with dist (archives, installers, hashes)
+# * uploads those artifacts to temporary workflow zip
+# * on success, uploads the artifacts to a GitHub Release
+#
+# Note that the GitHub Release will be created with a generated
+# title/body based on your changelogs.
+
+name: Release
+permissions:
+  "contents": "write"
+
+# This task will run whenever you push a git tag that looks like a version
+# like "1.0.0", "v0.1.0-prerelease.1", "my-app/0.1.0", "releases/v1.0.0", etc.
+# Various formats will be parsed into a VERSION and an optional PACKAGE_NAME, where
+# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION
+# must be a Cargo-style SemVer Version (must have at least major.minor.patch).
+#
+# If PACKAGE_NAME is specified, then the announcement will be for that
+# package (erroring out if it doesn't have the given version or isn't dist-able).
+#
+# If PACKAGE_NAME isn't specified, then the announcement will be for all
+# (dist-able) packages in the workspace with that version (this mode is
+# intended for workspaces with only one dist-able package, or with all dist-able
+# packages versioned/released in lockstep).
+#
+# If you push multiple tags at once, separate instances of this workflow will
+# spin up, creating an independent announcement for each one. However, GitHub
+# will hard limit this to 3 tags per commit, as it will assume more tags is a
+# mistake.
+#
+# If there's a prerelease-style suffix to the version, then the release(s)
+# will be marked as a prerelease.
+on:
+  pull_request:
+  push:
+    tags:
+      - '**[0-9]+.[0-9]+.[0-9]+*'
+
+jobs:
+  # Run 'dist plan' (or host) to determine what tasks we need to do
+  plan:
+    runs-on: "ubuntu-latest"
+    outputs:
+      val: ${{ steps.plan.outputs.manifest }}
+      tag: ${{ !github.event.pull_request && github.ref_name || '' }}
+      tag-flag: ${{ !github.event.pull_request && format('--tag={0}', github.ref_name) || '' }}
+      publishing: ${{ !github.event.pull_request }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+      - name: Install dist
+        # we specify bash to get pipefail; it guards against the `curl` command
+        # failing. otherwise `sh` won't catch that `curl` returned non-0
+        shell: bash
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.28.0/cargo-dist-installer.sh | sh"
+      - name: Cache dist
+        uses: actions/upload-artifact@v7
+        with:
+          name: cargo-dist-cache
+          path: ~/.cargo/bin/dist
+      # sure would be cool if github gave us proper conditionals...
+      # so here's a doubly-nested ternary-via-truthiness to try to provide the best possible
+      # functionality based on whether this is a pull_request, and whether it's from a fork.
+      # (PRs run on the *source* but secrets are usually on the *target* -- that's *good*
+      # but also really annoying to build CI around when it needs secrets to work right.)
+      - id: plan
+        run: |
+          dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json
+          echo "dist ran successfully"
+          cat plan-dist-manifest.json
+          echo "manifest=$(jq -c "." plan-dist-manifest.json)" >> "$GITHUB_OUTPUT"
+      - name: "Upload dist-manifest.json"
+        uses: actions/upload-artifact@v7
+        with:
+          name: artifacts-plan-dist-manifest
+          path: plan-dist-manifest.json
+
+  # Build and packages all the platform-specific things
+  build-local-artifacts:
+    name: build-local-artifacts (${{ join(matrix.targets, ', ') }})
+    # Let the initial task tell us to not run (currently very blunt)
+    needs:
+      - plan
+    if: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix.include != null && (needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload') }}
+    strategy:
+      fail-fast: false
+      # Target platforms/runners are computed by dist in create-release.
+      # Each member of the matrix has the following arguments:
+      #
+      # - runner: the github runner
+      # - dist-args: cli flags to pass to dist
+      # - install-dist: expression to run to install dist on the runner
+      #
+      # Typically there will be:
+      # - 1 "global" task that builds universal installers
+      # - N "local" tasks that build each platform's binaries and platform-specific installers
+      matrix: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix }}
+    runs-on: ${{ matrix.runner }}
+    container: ${{ matrix.container && matrix.container.image || null }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      BUILD_MANIFEST_NAME: target/distrib/${{ join(matrix.targets, '-') }}-dist-manifest.json
+    steps:
+      - name: enable windows longpaths
+        run: |
+          git config --global core.longpaths true
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+      - name: Install Rust non-interactively if not already installed
+        if: ${{ matrix.container }}
+        run: |
+          if ! command -v cargo > /dev/null 2>&1; then
+            curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
+            echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+          fi
+      - name: Install dist
+        run: ${{ matrix.install_dist.run }}
+      # Get the dist-manifest
+      - name: Fetch local artifacts
+        uses: actions/download-artifact@v8
+        with:
+          pattern: artifacts-*
+          path: target/distrib/
+          merge-multiple: true
+      - name: Install dependencies
+        run: |
+          ${{ matrix.packages_install }}
+      - name: Build artifacts
+        run: |
+          # Actually do builds and make zips and whatnot
+          dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
+          echo "dist ran successfully"
+      - id: cargo-dist
+        name: Post-build
+        # We force bash here just because github makes it really hard to get values up
+        # to "real" actions without writing to env-vars, and writing to env-vars has
+        # inconsistent syntax between shell and powershell.
+        shell: bash
+        run: |
+          # Parse out what we just built and upload it to scratch storage
+          echo "paths<<EOF" >> "$GITHUB_OUTPUT"
+          dist print-upload-files-from-manifest --manifest dist-manifest.json >> "$GITHUB_OUTPUT"
+          echo "EOF" >> "$GITHUB_OUTPUT"
+
+          cp dist-manifest.json "$BUILD_MANIFEST_NAME"
+      - name: "Upload artifacts"
+        uses: actions/upload-artifact@v7
+        with:
+          name: artifacts-build-local-${{ join(matrix.targets, '_') }}
+          path: |
+            ${{ steps.cargo-dist.outputs.paths }}
+            ${{ env.BUILD_MANIFEST_NAME }}
+
+  # Build and package all the platform-agnostic(ish) things
+  build-global-artifacts:
+    needs:
+      - plan
+      - build-local-artifacts
+    runs-on: "ubuntu-latest"
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      BUILD_MANIFEST_NAME: target/distrib/global-dist-manifest.json
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+      - name: Install cached dist
+        uses: actions/download-artifact@v8
+        with:
+          name: cargo-dist-cache
+          path: ~/.cargo/bin/
+      - run: chmod +x ~/.cargo/bin/dist
+      # Get all the local artifacts for the global tasks to use (for e.g. checksums)
+      - name: Fetch local artifacts
+        uses: actions/download-artifact@v8
+        with:
+          pattern: artifacts-*
+          path: target/distrib/
+          merge-multiple: true
+      - id: cargo-dist
+        shell: bash
+        run: |
+          dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json
+          echo "dist ran successfully"
+
+          # Parse out what we just built and upload it to scratch storage
+          echo "paths<<EOF" >> "$GITHUB_OUTPUT"
+          jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
+          echo "EOF" >> "$GITHUB_OUTPUT"
+
+          cp dist-manifest.json "$BUILD_MANIFEST_NAME"
+      - name: "Upload artifacts"
+        uses: actions/upload-artifact@v7
+        with:
+          name: artifacts-build-global
+          path: |
+            ${{ steps.cargo-dist.outputs.paths }}
+            ${{ env.BUILD_MANIFEST_NAME }}
+  # Determines if we should publish/announce
+  host:
+    needs:
+      - plan
+      - build-local-artifacts
+      - build-global-artifacts
+    # Only run if we're "publishing", and only if local and global didn't fail (skipped is fine)
+    if: ${{ always() && needs.plan.outputs.publishing == 'true' && (needs.build-global-artifacts.result == 'skipped' || needs.build-global-artifacts.result == 'success') && (needs.build-local-artifacts.result == 'skipped' || needs.build-local-artifacts.result == 'success') }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    runs-on: "ubuntu-latest"
+    outputs:
+      val: ${{ steps.host.outputs.manifest }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive
+      - name: Install cached dist
+        uses: actions/download-artifact@v8
+        with:
+          name: cargo-dist-cache
+          path: ~/.cargo/bin/
+      - run: chmod +x ~/.cargo/bin/dist
+      # Fetch artifacts from scratch-storage
+      - name: Fetch artifacts
+        uses: actions/download-artifact@v8
+        with:
+          pattern: artifacts-*
+          path: target/distrib/
+          merge-multiple: true
+      - id: host
+        shell: bash
+        run: |
+          dist host ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json
+          echo "artifacts uploaded and released successfully"
+          cat dist-manifest.json
+          echo "manifest=$(jq -c "." dist-manifest.json)" >> "$GITHUB_OUTPUT"
+      - name: "Upload dist-manifest.json"
+        uses: actions/upload-artifact@v7
+        with:
+          # Overwrite the previous copy
+          name: artifacts-dist-manifest
+          path: dist-manifest.json
+      # Create a GitHub Release while uploading all files to it
+      - name: "Download GitHub Artifacts"
+        uses: actions/download-artifact@v8
+        with:
+          pattern: artifacts-*
+          path: artifacts
+          merge-multiple: true
+      - name: Cleanup
+        run: |
+          # Remove the granular manifests
+          rm -f artifacts/*-dist-manifest.json
+      - name: Create GitHub Release
+        env:
+          PRERELEASE_FLAG: "${{ fromJson(steps.host.outputs.manifest).announcement_is_prerelease && '--prerelease' || '' }}"
+          ANNOUNCEMENT_TITLE: "${{ fromJson(steps.host.outputs.manifest).announcement_title }}"
+          ANNOUNCEMENT_BODY: "${{ fromJson(steps.host.outputs.manifest).announcement_github_body }}"
+          RELEASE_COMMIT: "${{ github.sha }}"
+        run: |
+          # Write and read notes from a file to avoid quoting breaking things
+          echo "$ANNOUNCEMENT_BODY" > $RUNNER_TEMP/notes.txt
+
+          gh release create "${{ needs.plan.outputs.tag }}" --draft --target "$RELEASE_COMMIT" $PRERELEASE_FLAG --title "$ANNOUNCEMENT_TITLE" --notes-file "$RUNNER_TEMP/notes.txt" artifacts/*
+
+  announce:
+    needs:
+      - plan
+      - host
+    # use "always() && ..." to allow us to wait for all publish jobs while
+    # still allowing individual publish jobs to skip themselves (for prereleases).
+    # "host" however must run to completion, no skipping allowed!
+    if: ${{ always() && needs.host.result == 'success' }}
+    runs-on: "ubuntu-latest"
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          submodules: recursive

.gitignore

@@ -4,3 +4,4 @@ target
 .cargo
 .settings
 test_data/links/link-*
+/public/

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+repos:
+-   repo: local
+    hooks:
+    -   id: rust-linting
+        name: Rust linting
+        description: Run cargo fmt on files included in the commit.
+        entry: cargo +nightly 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 +nightly clippy --workspace --all-targets --all-features --
+        pass_filenames: false
+        types: [file, rust]
+        language: system
+ci:
+  skip: [rust-linting, rust-clippy]

.travis.yml

@@ -1,33 +0,0 @@
-language: rust
-
-sudo: false
-os:
-  - linux
-  - osx
-rust:
-  - stable
-  - nightly
-
-matrix:
-  fast_finish: true
-
-branches:
-  only:
-    - master
-
-cache: cargo
-
-before_cache: |
-  if [[ "$TRAVIS_RUST_VERSION" = nightly ]]; then
-    RUSTFLAGS="--cfg procmacro2_semver_exempt" cargo install cargo-tarpaulin -f
-  fi
-
-script:
-  - cargo build --verbose
-  - cargo test --verbose
-
-after_script: |
-  if [[ "$TRAVIS_OS_NAME" = linux && "$TRAVIS_RUST_VERSION" = nightly ]]; then
-    cargo tarpaulin --out Xml
-    bash <(curl -s https://codecov.io/bash)
-  fi

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socioeconomic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+sylvestre@debian.org.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+<https://www.contributor-covenant.org/version/2/0/code_of_conduct.html>.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+<https://www.contributor-covenant.org/faq>. Translations are available at
+<https://www.contributor-covenant.org/translations>.

CONTRIBUTING.md

@@ -0,0 +1,262 @@
+<!-- spell-checker:ignore reimplementing toybox RUNTEST CARGOFLAGS nextest embeddable Rustonomicon rustdoc's -->
+
+# Contributing to findutils
+
+Hi! Welcome to uutils/findutils!
+
+Thanks for wanting to contribute to this project! This document explains
+everything you need to know to contribute. Before you start make sure to also
+check out these documents:
+
+- Our community's [CODE_OF_CONDUCT.md](./CODE_OF_CONDUCT.md).
+- [DEVELOPMENT.md](./DEVELOPMENT.md) for setting up your development
+  environment.
+- Our [Review Guidelines](https://uutils.github.io/reviews/) for what we expect
+  from a pull request and how reviews are done.
+
+Now follows a very important warning:
+
+> [!WARNING]
+> uutils is original code and cannot contain any code from GNU or
+> other implementations. This means that **we cannot accept any changes based on
+> the GNU source code**. To make sure that cannot happen, **you cannot link to
+> the GNU source code** either. It is however possible to look at other implementations
+> under a BSD or MIT license like [Apple's implementation](https://opensource.apple.com/source/file_cmds/)
+> or [OpenBSD](https://github.com/openbsd/src/tree/master/bin).
+
+Finally, feel free to join our [Discord](https://discord.gg/wQVJbvJ)!
+
+<!-- TODO: Getting Oriented -->
+
+## Design Goals
+
+We have the following goals with our development:
+
+- **Compatible**: The utilities should be a drop-in replacement for the GNU
+  coreutils.
+- **Cross-platform**: All utilities should run on as many of the supported
+  platforms as possible.
+- **Reliable**: The utilities should never unexpectedly fail.
+- **Performant**: Our utilities should be written in fast idiomatic Rust. We aim
+  to match or exceed the performance of the GNU utilities.
+- **Well-tested**: We should have a lot of tests to be able to guarantee
+  reliability and compatibility.
+
+## How to Help
+
+There are several ways to help and writing code is just one of them. Reporting
+issues and writing documentation are just as important as writing code.
+
+### Reporting Issues
+
+We can't fix bugs we don't know about, so good issues are super helpful! Here
+are some tips for writing good issues:
+
+- If you find a bug, make sure it's still a problem on the `main` branch.
+- Search through the existing issues to see whether it has already been
+  reported.
+- Make sure to include all relevant information, such as:
+  - Which version of uutils did you check?
+  - Which version of GNU coreutils are you comparing with?
+  - What platform are you on?
+- Provide a way to reliably reproduce the issue.
+- Be as specific as possible!
+
+### Writing Documentation
+
+There's never enough documentation. If you come across any documentation that
+could be improved, feel free to submit a PR for it!
+
+### Writing Code
+
+If you want to submit a PR, make sure that you've discussed the solution with
+the maintainers beforehand. We want to avoid situations where you put a lot of
+work into a fix that we can't merge! If there's no issue for what you're trying
+to fix yet, make one _before_ you start working on the PR.
+
+Generally, we try to follow what GNU is doing in terms of options and behavior.
+It is recommended to look at the GNU findtils manual
+([on the web](https://www.gnu.org/software/findutils/manual/html_node/index.html),
+or locally using `info <utility>`). It is more in depth than the man pages and
+provides a good description of available features and their implementation
+details. But remember, you cannot look at the GNU source code!
+
+Also remember that we can only merge PRs which pass our test suite, follow
+rustfmt, and do not have any warnings from clippy. See
+[DEVELOPMENT.md](./DEVELOPMENT.md) for more information. Be sure to also read
+about our [Rust style](#our-rust-style).
+
+## Our Rust Style
+
+We want uutils to be written in idiomatic Rust, so here are some guidelines to
+follow. Some of these are aspirational, meaning that we don't do them correctly
+everywhere in the code. If you find violations of the advice below, feel free to
+submit a patch!
+
+### Don't `panic!`
+
+The coreutils should be very reliable. This means that we should never `panic!`.
+Therefore, you should avoid using `.unwrap()` and `panic!`. Sometimes the use of
+`unreachable!` can be justified with a comment explaining why that code is
+unreachable.
+
+### Don't `exit`
+
+We want uutils to be embeddable in other programs. This means that no function
+in uutils should exit the program. Doing so would also lead to code with more
+confusing control flow. Avoid therefore `std::process::exit` and similar
+functions which exit the program early.
+
+### `unsafe`
+
+uutils cannot be entirely safe, because we have to call out to `libc` and do
+syscalls. However, we still want to limit our use of `unsafe`. We generally only
+accept `unsafe` for FFI, with very few exceptions. Note that performance is very
+rarely a valid argument for using `unsafe`.
+
+If you still need to write code with `unsafe`, make sure to read the
+[Rustonomicon](https://doc.rust-lang.org/nomicon/intro.html) and annotate the
+calls with `// SAFETY:` comments explaining why the use of `unsafe` is sound.
+
+### Macros
+
+Macros can be a great tool, but they are also usually hard to understand. They
+should be used sparingly. Make sure to explore simpler options before you reach
+for a solution involving macros.
+
+### `str`, `OsStr` & `Path`
+
+Rust has many string-like types, and sometimes it's hard to choose the right
+one. It's tempting to use `str` (and `String`) for everything, but that is not
+always the right choice for uutils, because we need to support invalid UTF-8,
+just like the GNU coreutils. For example, paths on Linux might not be valid
+UTF-8! Whenever we are dealing with paths, we should therefore stick with
+`OsStr` and `Path`. Make sure that you only convert to `str`/`String` if you
+know that something is always valid UTF-8. If you need more operations on
+`OsStr`, you can use the [`bstr`](https://docs.rs/bstr/latest/bstr/) crate.
+
+### Doc-comments
+
+We use rustdoc for our documentation, so it's best to follow
+[rustdoc's guidelines](https://doc.rust-lang.org/rustdoc/how-to-write-documentation.html#documenting-components).
+Make sure that your documentation is not just repeating the name of the
+function, but actually giving more useful information. Rustdoc recommends the
+following structure:
+
+```
+[short sentence explaining what it is]
+
+[more detailed explanation]
+
+[at least one code example that users can copy/paste to try it]
+
+[even more advanced explanations if necessary]
+```
+
+### Other comments
+
+Comments should be written to _explain_ the code, not to _describe_ the code.
+Try to focus on explaining _why_ the code is the way it is. If you feel like you
+have to describe the code, that's usually a sign that you could improve the
+naming of variables and functions.
+
+If you edit a piece of code, make sure to update any comments that need to
+change as a result. The only thing worse than having no comments is having
+outdated comments!
+
+## Git Etiquette
+
+To ensure easy collaboration, we have guidelines for using Git and GitHub.
+
+### Commits
+
+- Make small and atomic commits.
+- Keep a clean history of commits.
+- Write informative commit messages.
+- Annotate your commit message with the component you're editing. For example:
+  `cp: do not overwrite on with -i` or `uucore: add support for FreeBSD`.
+- Do not unnecessarily move items around in the code. This makes the changes
+  much harder to review. If you do need to move things around, do that in a
+  separate commit.
+
+### Commit messages
+
+You can read this section in the Git book to learn how to write good commit
+messages: https://git-scm.com/book/en/v2/Distributed-Git-Contributing-to-a-Project.
+
+In addition, here are a few examples for a summary line when committing to
+uutils:
+
+- commit for a single utility
+
+```
+nohup: cleanup and refactor
+```
+
+- commit for a utility's tests
+
+```
+tests/rm: test new feature
+```
+
+Beyond changes to an individual utility or its tests, other summary lines for
+non-utility modules include:
+
+```
+README: add help
+uucore: add new modules
+uutils: add new utility
+gitignore: add temporary files
+```
+
+### PRs
+
+- Make the titles of PRs descriptive.
+  - This means describing the problem you solve. For example, do not write
+    `Fix #1234`, but `ls: fix version sort order`.
+  - You can prefix the title with the utility the PR concerns.
+- Keep PRs small and self-contained. A set of small PRs is much more likely to
+  get merged quickly than one large PR.
+- Make sure the CI passes (up to intermittently failing tests).
+- You know your code best, that's why it's best if you can solve merge conflicts
+  on your branch yourself.
+  - It's up to you whether you want to use `git merge main` or
+    `git rebase main`.
+  - Feel free to ask for help with merge conflicts.
+- You do not need to ping maintainers to request a review, but it's fine to do
+  so if you don't get a response within a few days.
+
+## Platforms
+
+We take pride in supporting many operating systems and architectures. Any code
+you contribute must at least compile without warnings for all platforms in the
+CI. However, you can use `#[cfg(...)]` attributes to create platform dependent
+features.
+
+## Licensing
+
+uutils is distributed under the terms of the MIT License; see the `LICENSE` file
+for details. This is a permissive license, which allows the software to be used
+with few restrictions.
+
+Copyrights in the uutils project are retained by their contributors, and no
+copyright assignment is required to contribute.
+
+If you wish to add or change dependencies as part of a contribution to the
+project, a tool like `cargo-license` can be used to show their license details.
+The following types of license are acceptable:
+
+- MIT License
+- Dual- or tri-license with an MIT License option ("Apache-2.0 or MIT" is a
+  popular combination)
+- "MIT equivalent" license (2-clause BSD, 3-clause BSD, ISC)
+- License less restrictive than the MIT License (CC0 1.0 Universal)
+- Apache License version 2.0
+
+Licenses we will not use:
+
+- An ambiguous license, or no license
+- Strongly reciprocal licenses (GNU GPL, GNU LGPL)
+
+If you wish to add a reference but it doesn't meet these requirements, please
+raise an issue to describe the dependency.

Cargo.toml

@@ -1,36 +1,65 @@
 [package]
 name = "findutils"
-version = "0.3.0"
+version = "0.9.0"
 homepage = "https://github.com/uutils/findutils"
 repository = "https://github.com/uutils/findutils"
-edition = "2018"
+edition = "2021"
 license = "MIT"
 readme = "README.md"
 description = "Rust implementation of GNU findutils"
 authors = ["uutils developers"]
 
 [dependencies]
-chrono = "0.4"
-clap = "2.34"
+argmax = "0.4.0"
+chrono = "0.4.45"
+clap = { version = "4.6", features = ["env"] }
 faccess = "0.2.4"
-walkdir = "2.3"
-regex = "1.7"
-once_cell = "1.17"
-onig = "6.4"
-uucore = { version = "0.0.12", features = ["entries", "fs", "fsext", "mode"] }
+nix = { version = "0.31", features = ["fs", "user"] }
+onig = { version = "6.5", default-features = false }
+regex = "1.12"
+uucore = { version = "0.9.0", features = ["entries", "fs", "fsext", "mode"] }
+walkdir = "2.5"
+itertools = "0.14.0"
+thiserror = "2.0.12"
 
 [dev-dependencies]
+criterion = { version = "4.7.0", package = "codspeed-criterion-compat" }
 assert_cmd = "2"
+ctor = "1.0"
 filetime = "0.2"
-nix = "0.26"
-predicates = "2"
-serial_test = "1.0"
+nix = { version = "0.31", features = ["fs"] }
+rstest = "0.26.1"
 tempfile = "3"
+uutests = "0.9.0"
+
+[[bench]]
+name = "find_bench"
+harness = false
+
+[[bench]]
+name = "xargs_bench"
+harness = false
+
+[[bench]]
+name = "updatedb_bench"
+harness = false
+
+[[bench]]
+name = "locate_bench"
+harness = false
 
 [[bin]]
 name = "find"
 path = "src/find/main.rs"
 
+[[bin]]
+name = "locate"
+path = "src/locate/main.rs"
+
+[[bin]]
+name = "updatedb"
+path = "src/updatedb/main.rs"
+
 [[bin]]
 name = "xargs"
 path = "src/xargs/main.rs"
@@ -38,3 +67,53 @@ path = "src/xargs/main.rs"
 [[bin]]
 name = "testing-commandline"
 path = "src/testing/commandline/main.rs"
+
+[profile.release]
+lto = "thin"
+codegen-units = 1
+
+[profile.release-fast]
+inherits = "release"
+panic = "abort"
+
+[lints.clippy]
+all = { level = "warn", priority = -1 }
+cargo = { level = "warn", priority = -1 }
+pedantic = { level = "warn", priority = -1 }
+use_self = "warn" # nursery lint
+
+# Group-level allows for lints that are too noisy or not worth enforcing for now.
+multiple_crate_versions = "allow"
+cargo_common_metadata = "allow"
+uninlined_format_args = "allow"
+missing_errors_doc = "allow"
+missing_panics_doc = "allow"
+must_use_candidate = "allow"
+match_same_arms = "allow"
+cast_possible_truncation = "allow"
+too_many_lines = "allow"
+cast_possible_wrap = "allow"
+cast_sign_loss = "allow"
+struct_excessive_bools = "allow"
+cast_precision_loss = "allow"
+cast_lossless = "allow"
+ignored_unit_patterns = "allow"
+similar_names = "allow"
+float_cmp = "allow"
+return_self_not_must_use = "allow"
+inline_always = "allow"
+fn_params_excessive_bools = "allow"
+used_underscore_items = "allow"
+should_panic_without_expect = "allow"
+doc_markdown = "allow"
+unused_self = "allow"
+enum_glob_use = "allow"
+unnested_or_patterns = "allow"
+implicit_hasher = "allow"
+doc_link_with_quotes = "allow"
+format_push_string = "allow"
+flat_map_option = "allow"
+from_iter_instead_of_collect = "allow"
+large_types_passed_by_value = "allow"
+# Disable for now, we have a few occurrences
+# panic = "warn"

DEVELOPMENT.md

@@ -0,0 +1,156 @@
+<!-- spell-checker:ignore (flags) Ccodegen Coverflow Cpanic Zinstrument Zpanic reimplementing toybox RUNTEST CARGOFLAGS nextest prereq autopoint gettext texinfo automake findutils shellenv libexec gnubin toolchains gsed -->
+
+# Setting up your local development environment
+
+For contributing rules and best practices please refer to [CONTRIBUTING.md](CONTRIBUTING.md)
+
+## Before you start
+
+For this guide we assume that you already have a GitHub account and have `git` and your favorite code editor or IDE installed and configured.
+Before you start working on findutils, please follow these steps:
+
+1. Fork the [findutils repository](https://github.com/uutils/findutils) to your GitHub account.
+***Tip:*** See [this GitHub guide](https://docs.github.com/en/get-started/quickstart/fork-a-repo) for more information on this step.
+2. Clone that fork to your local development environment:
+
+```shell
+git clone https://github.com/YOUR-GITHUB-ACCOUNT/findutils
+cd findutils
+```
+
+## Tools
+
+You will need the tools mentioned in this section to build and test your code changes locally.
+This section will explain how to install and configure these tools.
+We also have an extensive CI that uses these tools and will check your code before it can be merged.
+The next section [Testing](#testing) will explain how to run those checks locally to avoid waiting for the CI.
+
+### Rust toolchain
+
+[Install Rust](https://www.rust-lang.org/tools/install)
+
+If you're using rustup to install and manage your Rust toolchains, `clippy` and `rustfmt` are usually already installed. If you are using one of the alternative methods, please make sure to install them manually. See following sub-sections for their usage: [clippy](#clippy) [rustfmt](#rustfmt).
+
+***Tip*** You might also need to add 'llvm-tools' component if you are going to [generate code coverage reports locally](#code-coverage-report):
+
+```shell
+rustup component add llvm-tools-preview
+```
+
+### pre-commit hooks
+
+A configuration for `pre-commit` is provided in the repository. It allows
+automatically checking every git commit you make to ensure it compiles, and
+passes `clippy` and `rustfmt` without warnings.
+
+To use the provided hook:
+
+1. [Install `pre-commit`](https://pre-commit.com/#install)
+1. Run `pre-commit install` while in the repository directory
+
+Your git commits will then automatically be checked. If a check fails, an error
+message will explain why, and your commit will be canceled. You can then make
+the suggested changes, and run `git commit ...` again.
+
+**NOTE: On MacOS** the pre-commit hooks are currently broken. There are workarounds involving switching to unstable nightly Rust and components.
+
+### clippy
+
+```shell
+cargo clippy --all-targets --all-features
+```
+
+The `msrv` key in the clippy configuration file `clippy.toml` is used to disable
+lints pertaining to newer features by specifying the minimum supported Rust
+version (MSRV).
+
+### rustfmt
+
+```shell
+cargo fmt --all
+```
+
+### cargo-deny
+
+This project uses [cargo-deny](https://github.com/EmbarkStudios/cargo-deny/) to
+detect duplicate dependencies, checks licenses, etc. To run it locally, first
+install it and then run with:
+
+```shell
+cargo deny --all-features check all
+```
+
+### Markdown linter
+
+We use [markdownlint](https://github.com/DavidAnson/markdownlint) to lint the
+Markdown files in the repository.
+
+### Spell checker
+
+We use `cspell` as spell checker for all files in the project. If you are using
+VS Code, you can install the
+[code spell checker](https://marketplace.visualstudio.com/items?itemName=streetsidesoftware.code-spell-checker)
+extension to enable spell checking within your editor. Otherwise, you can
+install [cspell](https://cspell.org/) separately.
+
+If you want to make the spell checker ignore a word, you can add
+
+```rust
+// spell-checker:ignore word_to_ignore
+```
+
+at the top of the file.
+
+## Testing
+
+Just like with building, we follow the standard procedure for testing using
+Cargo:
+
+```shell
+cargo test
+```
+
+## Code coverage report
+
+Code coverage report can be generated using [grcov](https://github.com/mozilla/grcov).
+
+### Using Nightly Rust
+
+To generate [gcov-based](https://github.com/mozilla/grcov#example-how-to-generate-gcda-files-for-a-rust-project) coverage report
+
+```shell
+export CARGO_INCREMENTAL=0
+export RUSTFLAGS="-Zprofile -Ccodegen-units=1 -Copt-level=0 -Clink-dead-code -Coverflow-checks=off -Zpanic_abort_tests -Cpanic=abort"
+export RUSTDOCFLAGS="-Cpanic=abort"
+cargo build <options...>
+cargo test <options...>
+grcov . -s . --binary-path ./target/debug/ -t html --branch --ignore-not-existing --ignore build.rs --excl-br-line "^\s*((debug_)?assert(_eq|_ne)?\#\[derive\()" -o ./target/debug/coverage/
+# open target/debug/coverage/index.html in browser
+```
+
+if changes are not reflected in the report then run `cargo clean` and run the above commands.
+
+### Using Stable Rust
+
+If you are using stable version of Rust that doesn't enable code coverage instrumentation by default
+then add `-Z-Zinstrument-coverage` flag to `RUSTFLAGS` env variable specified above.
+
+## Tips for setting up on Mac
+
+### C Compiler and linker
+
+On MacOS you'll need to install C compiler & linker:
+
+```shell
+xcode-select --install
+```
+
+## Tips for setting up on Windows
+
+### MSVC build tools
+
+On Windows you'll need the MSVC build tools for Visual Studio 2013 or later.
+
+If you are using `rustup-init.exe` to install Rust toolchain, it will guide you through the process of downloading and installing these prerequisites.
+
+Otherwise please follow [this guide](https://learn.microsoft.com/en-us/windows/dev-environment/rust/setup).

README.md

@@ -1,10 +1,13 @@
 # findutils
 
 [![Crates.io](https://img.shields.io/crates/v/findutils.svg)](https://crates.io/crates/findutils)
+[![Discord](https://img.shields.io/badge/discord-join-7289DA.svg?logo=discord&longCache=true&style=flat)](https://discord.gg/wQVJbvJ)
+[![License](http://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/uutils/findutils/blob/main/LICENSE)
 [![dependency status](https://deps.rs/repo/github/uutils/findutils/status.svg)](https://deps.rs/repo/github/uutils/findutils)
 [![codecov](https://codecov.io/gh/uutils/findutils/branch/master/graph/badge.svg)](https://codecov.io/gh/uutils/findutils)
 
-Rust implementation of [GNU findutils](https://www.gnu.org/software/findutils/).
+Rust implementation of [GNU findutils](https://www.gnu.org/software/findutils/): `xargs`, `find`, `locate` and `updatedb`.
+The goal is to be a full drop-in replacement of the original commands.
 
 ## Run the GNU testsuite on rust/findutils:
 
@@ -17,7 +20,18 @@ bash util/build-gnu.sh tests/misc/help-version.sh
 
 ## Comparing with GNU
 
-![Evolution over time - GNU testsuite](https://github.com/uutils/findutils-tracking/blob/main/gnu-results.png?raw=true)
-![Evolution over time - BFS testsuite](https://github.com/uutils/findutils-tracking/blob/main/bfs-results.png?raw=true)
+![Evolution over time - GNU testsuite](https://github.com/uutils/findutils-tracking/blob/main/gnu-results.svg?raw=true)
+![Evolution over time - BFS testsuite](https://github.com/uutils/findutils-tracking/blob/main/bfs-results.svg?raw=true)
+
+## Build/run with BFS
+
+[bfs](https://github.com/tavianator/bfs) is a variant of the UNIX find command that operates breadth-first rather than depth-first.
+
+```
+bash util/build-bfs.sh
+
+# To run a specific test:
+bash util/build-bfs.sh posix/basic
+```
 
 For more details, see https://github.com/uutils/findutils-tracking/

SECURITY.md

@@ -0,0 +1,44 @@
+# Security Policy
+
+## Supported Versions
+
+We provide security updates only for the latest released version of `uutils/findutils`.
+Older versions may not receive patches.
+If you are using a version packaged by your Linux distribution, please check with your distribution maintainers for their update policy.
+
+---
+
+## Reporting a Vulnerability
+
+**Do not open public GitHub issues for security vulnerabilities.**
+This prevents accidental disclosure before a fix is available.
+
+Instead, please use the following method:
+
+- **Email:** [sylvestre@debian.org](mailto:Sylvestre@debian.org)
+- **Encryption (optional):** You may encrypt your report using our PGP key:
+Fingerprint: B60D B599 4D39 BEC4 D1A9 5CCF 7E65 28DA 752F 1BE1
+---
+
+### What to Include in Your Report
+
+To help us investigate and resolve the issue quickly, please include as much detail as possible:
+
+- **Type of issue:** e.g. privilege escalation, information disclosure.
+- **Location in the source:** file path, commit hash, branch, or tag.
+- **Steps to reproduce:** exact commands, test cases, or scripts.
+- **Special configuration:** any flags, environment variables, or system setup required.
+- **Affected systems:** OS/distribution and version(s) where the issue occurs.
+- **Impact:** your assessment of the potential severity (DoS, RCE, data leak, etc.).
+
+---
+
+## Disclosure Policy
+
+We follow a **Coordinated Vulnerability Disclosure (CVD)** process:
+
+1. We will acknowledge receipt of your report within **10 days**.
+2. We will investigate, reproduce, and assess the issue.
+3. We will provide a timeline for developing and releasing a fix.
+4. Once a fix is available, we will publish a GitHub Security Advisory.
+5. You will be credited in the advisory unless you request anonymity.

benches/find_bench.rs

@@ -0,0 +1,166 @@
+// Copyright 2024 the uutils developers
+//
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file or at
+// https://opensource.org/licenses/MIT.
+
+//! End-to-end benchmarks for `find`, run through the real `find_main` entry
+//! point so they exercise argument parsing, the matcher tree and the directory
+//! walk together. Output is sent to a sink so the benchmarks measure the work
+//! `find` does rather than terminal I/O.
+
+use std::cell::RefCell;
+use std::io::{self, Write};
+use std::path::{Path, PathBuf};
+use std::time::SystemTime;
+
+use criterion::{black_box, criterion_group, criterion_main, Criterion};
+use findutils::find::{find_main, Dependencies};
+
+/// `Dependencies` implementation that throws output away. A fixed `now` keeps
+/// time-based matchers (`-newer`, `-mtime`, …) deterministic across runs.
+struct SinkDependencies {
+    output: RefCell<io::Sink>,
+    now: SystemTime,
+}
+
+impl SinkDependencies {
+    fn new() -> Self {
+        Self {
+            output: RefCell::new(io::sink()),
+            now: SystemTime::now(),
+        }
+    }
+}
+
+impl Dependencies for SinkDependencies {
+    fn get_output(&self) -> &RefCell<dyn Write> {
+        &self.output
+    }
+
+    fn now(&self) -> SystemTime {
+        self.now
+    }
+
+    fn confirm(&self, _prompt: &str) -> bool {
+        false
+    }
+}
+
+/// Run `find` end-to-end. `args` are the arguments after the program name
+/// (flags, paths, expression). The exit status is ignored — we only care about
+/// the work performed.
+fn run(args: &[&str]) {
+    let mut argv: Vec<&str> = Vec::with_capacity(args.len() + 1);
+    argv.push("find");
+    argv.extend_from_slice(args);
+    let deps = SinkDependencies::new();
+    let _ = find_main(&argv, &deps);
+}
+
+/// Build a moderately deep directory tree to walk. `depth` levels, each holding
+/// `dirs` sub-directories and `files` files. File names vary so name/regex
+/// matchers have something to discriminate on, and sizes vary so `-size` does
+/// real work. Returns the root directory.
+fn build_tree(depth: u32, dirs: u32, files: u32) -> PathBuf {
+    let root = std::env::temp_dir().join(format!("uu_find_bench_{}", std::process::id()));
+    let _ = std::fs::remove_dir_all(&root);
+    std::fs::create_dir_all(&root).unwrap();
+    populate(&root, depth, dirs, files, 0);
+    root
+}
+
+fn populate(dir: &Path, depth: u32, dirs: u32, files: u32, seed: u32) {
+    for f in 0..files {
+        let n = seed.wrapping_add(f);
+        // A mix of extensions and a sprinkling of a rare marker name.
+        let name = match n % 5 {
+            0 => format!("module_{n}.rs"),
+            1 => format!("data_{n}.txt"),
+            2 => format!("image_{n}.png"),
+            3 => format!("README_{n}.md"),
+            _ if n % 500 == 0 => format!("RAREHIT_{n}.log"),
+            _ => format!("file_{n}.log"),
+        };
+        // Sizes from a few bytes up to ~8 KiB so -size buckets differ.
+        let size = (n as usize % 8192) + 1;
+        let path = dir.join(name);
+        std::fs::write(&path, vec![b'x'; size]).unwrap();
+    }
+
+    if depth == 0 {
+        return;
+    }
+
+    for d in 0..dirs {
+        let sub = dir.join(format!("dir_{d}"));
+        std::fs::create_dir_all(&sub).unwrap();
+        populate(
+            &sub,
+            depth - 1,
+            dirs,
+            files,
+            seed.wrapping_add((d + 1) * 31),
+        );
+    }
+}
+
+fn bench_e2e(c: &mut Criterion) {
+    // depth 4, 4 dirs/level, 25 files/dir → a few thousand entries.
+    let root = build_tree(4, 4, 25);
+    let dir = root.to_str().unwrap();
+
+    let mut group = c.benchmark_group("find");
+
+    // Plain full walk with the implicit -print.
+    group.bench_function("walk_all", |b| {
+        b.iter(|| run(black_box(&[dir])));
+    });
+    // Filter by file type only.
+    group.bench_function("type_f", |b| {
+        b.iter(|| run(black_box(&[dir, "-type", "f"])));
+    });
+    // Glob name match — a common invocation.
+    group.bench_function("name_glob", |b| {
+        b.iter(|| run(black_box(&[dir, "-name", "*.rs"])));
+    });
+    // Case-insensitive name match.
+    group.bench_function("iname_glob", |b| {
+        b.iter(|| run(black_box(&[dir, "-iname", "*.RS"])));
+    });
+    // Regex over the whole path.
+    group.bench_function("regex_path", |b| {
+        b.iter(|| run(black_box(&[dir, "-regex", r".*/module_[0-9]+\.rs"])));
+    });
+    // Size predicate forces a stat per entry.
+    group.bench_function("size_gt", |b| {
+        b.iter(|| run(black_box(&[dir, "-type", "f", "-size", "+4k"])));
+    });
+    // Combined predicate with AND/OR and grouping.
+    group.bench_function("combined_expr", |b| {
+        b.iter(|| {
+            run(black_box(&[
+                dir, "-type", "f", "(", "-name", "*.rs", "-o", "-name", "*.md", ")",
+            ]));
+        });
+    });
+    // Prune whole subtrees, then print the rest.
+    group.bench_function("prune", |b| {
+        b.iter(|| {
+            run(black_box(&[
+                dir, "-name", "dir_0", "-prune", "-o", "-type", "f", "-print",
+            ]));
+        });
+    });
+    // -printf with several directives exercises the formatter.
+    group.bench_function("printf", |b| {
+        b.iter(|| run(black_box(&[dir, "-type", "f", "-printf", "%p %s %y\\n"])));
+    });
+
+    group.finish();
+
+    let _ = std::fs::remove_dir_all(&root);
+}
+
+criterion_group!(benches, bench_e2e);
+criterion_main!(benches);

benches/locate_bench.rs

@@ -0,0 +1,127 @@
+// Copyright 2024 the uutils developers
+//
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file or at
+// https://opensource.org/licenses/MIT.
+
+//! End-to-end benchmarks for `locate`, run through the real `locate_main` entry
+//! point. A LOCATE02 database is built once (via `updatedb`) from a generated
+//! tree, then each case scans it in `-c`/count mode so the database decoding
+//! and pattern matching dominate rather than terminal output.
+//!
+//! `locate` is Unix-only (it relies on `OsStr`/`CStr` byte APIs), so the
+//! benchmark body is compiled only there.
+
+#[cfg(unix)]
+mod bench {
+    use std::path::{Path, PathBuf};
+
+    use criterion::{black_box, criterion_group, Criterion};
+    use findutils::locate::locate_main;
+    use findutils::updatedb::updatedb_main;
+
+    /// Run `locate` end-to-end. `args` are the arguments after the program name.
+    fn run(args: &[&str]) {
+        let mut argv: Vec<&str> = Vec::with_capacity(args.len() + 1);
+        argv.push("locate");
+        argv.extend_from_slice(args);
+        let _ = locate_main(&argv);
+    }
+
+    fn build_tree(depth: u32, dirs: u32, files: u32) -> PathBuf {
+        let root = std::env::temp_dir().join(format!("uu_locate_bench_{}", std::process::id()));
+        let _ = std::fs::remove_dir_all(&root);
+        std::fs::create_dir_all(&root).unwrap();
+        populate(&root, depth, dirs, files, 0);
+        root
+    }
+
+    fn populate(dir: &Path, depth: u32, dirs: u32, files: u32, seed: u32) {
+        for f in 0..files {
+            let n = seed.wrapping_add(f);
+            let name = match n % 4 {
+                0 => format!("module_{n}.rs"),
+                1 => format!("data_{n}.txt"),
+                2 => format!("image_{n}.png"),
+                _ => format!("file_{n}.log"),
+            };
+            std::fs::write(dir.join(name), b"x").unwrap();
+        }
+
+        if depth == 0 {
+            return;
+        }
+
+        for d in 0..dirs {
+            let sub = dir.join(format!("dir_{d}"));
+            std::fs::create_dir_all(&sub).unwrap();
+            populate(
+                &sub,
+                depth - 1,
+                dirs,
+                files,
+                seed.wrapping_add((d + 1) * 31),
+            );
+        }
+    }
+
+    pub fn bench_e2e(c: &mut Criterion) {
+        // ~8.5k paths, then front-coded into a LOCATE02 database once.
+        let root = build_tree(4, 4, 25);
+        let dir = root.to_str().unwrap();
+        let db = std::env::temp_dir().join(format!("uu_locate_bench_{}.db", std::process::id()));
+        let db_path = db.to_str().unwrap();
+
+        let _ = updatedb_main(&[
+            "updatedb",
+            &format!("--localpaths={dir}"),
+            &format!("--output={db_path}"),
+            "--prunepaths=",
+            "--prunefs=",
+        ]);
+
+        let mut group = c.benchmark_group("locate");
+
+        // Pattern matching nothing: forces a full decode + match of every entry.
+        group.bench_function("count_no_match", |b| {
+            b.iter(|| run(black_box(&["-d", db_path, "-c", "NONEXISTENT_TOKEN_XYZ"])));
+        });
+        // Substring matching many entries (count mode → no per-match output).
+        group.bench_function("count_many", |b| {
+            b.iter(|| run(black_box(&["-d", db_path, "-c", ".log"])));
+        });
+        // Basename matching (-b) restricts the comparison to the file name.
+        group.bench_function("basename", |b| {
+            b.iter(|| run(black_box(&["-d", db_path, "-c", "-b", "module"])));
+        });
+        // Case-insensitive matching (-i).
+        group.bench_function("ignore_case", |b| {
+            b.iter(|| run(black_box(&["-d", db_path, "-c", "-i", "MODULE"])));
+        });
+        // Regex matching (-r) over the whole path.
+        group.bench_function("regex", |b| {
+            b.iter(|| {
+                run(black_box(&[
+                    "-d",
+                    db_path,
+                    "-c",
+                    "-r",
+                    r"module_[0-9]+\.rs",
+                ]));
+            });
+        });
+
+        group.finish();
+
+        let _ = std::fs::remove_dir_all(&root);
+        let _ = std::fs::remove_file(&db);
+    }
+
+    criterion_group!(benches, bench_e2e);
+}
+
+#[cfg(unix)]
+criterion::criterion_main!(bench::benches);
+
+#[cfg(not(unix))]
+fn main() {}

benches/updatedb_bench.rs

@@ -0,0 +1,110 @@
+// Copyright 2024 the uutils developers
+//
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file or at
+// https://opensource.org/licenses/MIT.
+
+//! End-to-end benchmarks for `updatedb`, run through the real `updatedb_main`
+//! entry point. Each case walks a generated directory tree (via the internal
+//! `find`), encodes it into the LOCATE02 database format and writes the result
+//! to a temp file, so the walk + front-coding + write dominate the measurement.
+
+use std::path::{Path, PathBuf};
+
+use criterion::{black_box, criterion_group, criterion_main, Criterion};
+use findutils::updatedb::updatedb_main;
+
+/// Run `updatedb` end-to-end. `args` are the arguments after the program name.
+fn run(args: &[&str]) {
+    let mut argv: Vec<&str> = Vec::with_capacity(args.len() + 1);
+    argv.push("updatedb");
+    argv.extend_from_slice(args);
+    let _ = updatedb_main(&argv);
+}
+
+/// Build a directory tree to index. `depth` levels, each holding `dirs`
+/// sub-directories and `files` files with varied names. Returns the root.
+fn build_tree(depth: u32, dirs: u32, files: u32) -> PathBuf {
+    let root = std::env::temp_dir().join(format!("uu_updatedb_bench_{}", std::process::id()));
+    let _ = std::fs::remove_dir_all(&root);
+    std::fs::create_dir_all(&root).unwrap();
+    populate(&root, depth, dirs, files, 0);
+    root
+}
+
+fn populate(dir: &Path, depth: u32, dirs: u32, files: u32, seed: u32) {
+    for f in 0..files {
+        let n = seed.wrapping_add(f);
+        let name = match n % 4 {
+            0 => format!("module_{n}.rs"),
+            1 => format!("data_{n}.txt"),
+            2 => format!("image_{n}.png"),
+            _ => format!("file_{n}.log"),
+        };
+        // Tiny files: updatedb only records names, so content size is irrelevant.
+        std::fs::write(dir.join(name), b"x").unwrap();
+    }
+
+    if depth == 0 {
+        return;
+    }
+
+    for d in 0..dirs {
+        let sub = dir.join(format!("dir_{d}"));
+        std::fs::create_dir_all(&sub).unwrap();
+        populate(
+            &sub,
+            depth - 1,
+            dirs,
+            files,
+            seed.wrapping_add((d + 1) * 31),
+        );
+    }
+}
+
+fn bench_e2e(c: &mut Criterion) {
+    // depth 4, 4 dirs/level, 25 files/dir → ~8.5k indexed paths.
+    let root = build_tree(4, 4, 25);
+    let dir = root.to_str().unwrap();
+    let db = std::env::temp_dir().join(format!("uu_updatedb_bench_{}.db", std::process::id()));
+    let db_path = db.to_str().unwrap();
+
+    let localpaths = format!("--localpaths={dir}");
+    let output = format!("--output={db_path}");
+
+    let mut group = c.benchmark_group("updatedb");
+
+    // Full build: walk, front-code and write the whole tree. Empty prune
+    // options keep the run deterministic regardless of where temp_dir lives.
+    group.bench_function("build_full", |b| {
+        b.iter(|| {
+            run(black_box(&[
+                &localpaths,
+                &output,
+                "--prunepaths=",
+                "--prunefs=",
+            ]));
+        });
+    });
+
+    // Build with a prune clause that drops every `dir_0` subtree, exercising the
+    // -regex/-prune path updatedb hands to find.
+    group.bench_function("build_pruned", |b| {
+        b.iter(|| {
+            run(black_box(&[
+                &localpaths,
+                &output,
+                "--prunepaths=.*/dir_0",
+                "--prunefs=",
+            ]));
+        });
+    });
+
+    group.finish();
+
+    let _ = std::fs::remove_dir_all(&root);
+    let _ = std::fs::remove_file(&db);
+}
+
+criterion_group!(benches, bench_e2e);
+criterion_main!(benches);