Publish binary from main (#163)

Fixes https://github.com/uutils/diffutils/issues/172

.github/workflows/ci.yml

@@ -4,6 +4,7 @@ name: Basic CI
 
 env:
   CARGO_TERM_COLOR: always
+  CARGO_INCREMENTAL: 0
 
 jobs:
   check:
@@ -15,7 +16,6 @@ jobs:
         os: [ubuntu-latest, macOS-latest, windows-latest]
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@stable
       - run: cargo check
 
   test:
@@ -27,10 +27,11 @@ jobs:
         os: [ubuntu-latest, macOS-latest, windows-latest]
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@stable
       - name: install GNU patch on MacOS
         if: runner.os == 'macOS'
-        run: brew install gpatch
+        run: |
+          brew install gpatch
+          echo "/opt/homebrew/opt/gpatch/libexec/gnubin" >> "$GITHUB_PATH"
       - name: set up PATH on Windows
         # Needed to use GNU's patch.exe instead of Strawberry Perl patch
         if: runner.os == 'Windows'
@@ -42,8 +43,6 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@stable
-      - run: rustup component add rustfmt
       - run: cargo fmt --all -- --check
 
   clippy:
@@ -55,17 +54,18 @@ jobs:
         os: [ubuntu-latest, macOS-latest, windows-latest]
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@stable
-      - run: rustup component add clippy
       - run: cargo clippy -- -D warnings
 
   gnu-testsuite:
+    permissions:
+      contents: write # Publish diffutils instead of discarding
     name: GNU test suite
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@stable
-      - run: cargo build --release
+      - run: |
+          cargo build --config=profile.release.strip=true --profile=release #-fast
+          zstd -19 target/release/diffutils -o diffutils-x86_64-unknown-linux-gnu.zst
       # do not fail, the report is merely informative (at least until all tests pass reliably)
       - run: ./tests/run-upstream-testsuite.sh release || true
         env:
@@ -75,6 +75,17 @@ jobs:
           name: test-results.json
           path: tests/test-results.json
       - run: ./tests/print-test-results.sh tests/test-results.json
+      - name: Publish latest commit
+        uses: softprops/action-gh-release@v2
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        with:
+          tag_name: latest-commit
+          draft: false
+          prerelease: true
+          files: |
+            diffutils-x86_64-unknown-linux-gnu.zst
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
   coverage:
     name: Code Coverage
@@ -89,44 +100,42 @@ jobs:
     steps:
     - uses: actions/checkout@v4
     - name: Initialize workflow variables
+      env:
+        # Use -Z
+        RUSTC_BOOTSTRAP: 1
       id: vars
       shell: bash
       run: |
         ## VARs setup
         outputs() { step_id="vars"; for var in "$@" ; do echo steps.${step_id}.outputs.${var}="${!var}"; echo "${var}=${!var}" >> $GITHUB_OUTPUT; done; }
-        # toolchain
-        TOOLCHAIN="nightly" ## default to "nightly" toolchain (required for certain required unstable compiler flags) ## !maint: refactor when stable channel has needed support
-        # * specify gnu-type TOOLCHAIN for windows; `grcov` requires gnu-style code coverage data files
-        case ${{ matrix.job.os }} in windows-*) TOOLCHAIN="$TOOLCHAIN-x86_64-pc-windows-gnu" ;; esac;
-        # * use requested TOOLCHAIN if specified
-        if [ -n "${{ matrix.job.toolchain }}" ]; then TOOLCHAIN="${{ matrix.job.toolchain }}" ; fi
-        outputs TOOLCHAIN
         # target-specific options
-        # * CARGO_FEATURES_OPTION
-        CARGO_FEATURES_OPTION='--all -- --check' ;  ## default to '--all-features' for code coverage
         # * CODECOV_FLAGS
         CODECOV_FLAGS=$( echo "${{ matrix.job.os }}" | sed 's/[^[:alnum:]]/_/g' )
         outputs CODECOV_FLAGS
 
-    - name: rust toolchain ~ install
-      uses: dtolnay/rust-toolchain@nightly
-    - run: rustup component add llvm-tools-preview
     - name: install GNU patch on MacOS
       if: runner.os == 'macOS'
-      run: brew install gpatch
+      run: |
+        brew install gpatch
+        echo "/opt/homebrew/opt/gpatch/libexec/gnubin" >> "$GITHUB_PATH"
     - name: set up PATH on Windows
       # Needed to use GNU's patch.exe instead of Strawberry Perl patch
       if: runner.os == 'Windows'
       run: echo "C:\Program Files\Git\usr\bin" >> $env:GITHUB_PATH
     - name: Test
-      run: cargo test ${{ steps.vars.outputs.CARGO_FEATURES_OPTION }} --no-fail-fast
+      run: cargo test --all-features --no-fail-fast
       env:
         CARGO_INCREMENTAL: "0"
         RUSTC_WRAPPER: ""
         RUSTFLAGS: "-Cinstrument-coverage -Zcoverage-options=branch -Ccodegen-units=1 -Copt-level=0 -Coverflow-checks=off -Zpanic_abort_tests -Cpanic=abort"
         RUSTDOCFLAGS: "-Cpanic=abort"
         LLVM_PROFILE_FILE: "diffutils-%p-%m.profraw"
+        # Use -Z
+        RUSTC_BOOTSTRAP: 1
     - name: "`grcov` ~ install"
+      env:
+        # Use -Z
+        RUSTC_BOOTSTRAP: 1
       id: build_grcov
       shell: bash
       run: |
@@ -158,10 +167,10 @@ jobs:
         grcov . --output-type lcov --output-path "${COVERAGE_REPORT_FILE}" --binary-path "${COVERAGE_REPORT_DIR}" --branch
         echo "report=${COVERAGE_REPORT_FILE}" >> $GITHUB_OUTPUT
     - name: Upload coverage results (to Codecov.io)
-      uses: codecov/codecov-action@v4
+      uses: codecov/codecov-action@v5
       with:
         token: ${{ secrets.CODECOV_TOKEN }}
-        file: ${{ steps.coverage.outputs.report }}
+        files: ${{ steps.coverage.outputs.report }}
         ## flags: IntegrationTests, UnitTests, ${{ steps.vars.outputs.CODECOV_FLAGS }}
         flags: ${{ steps.vars.outputs.CODECOV_FLAGS }}
         name: codecov-umbrella

.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 -m simulation
+
+      - name: Run the benchmarks
+        uses: CodSpeedHQ/action@v4
+        with:
+          mode: simulation
+          run: cargo codspeed run

.github/workflows/fuzzing.yml

@@ -21,15 +21,17 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@nightly
       - name: Install `cargo-fuzz`
-        run: cargo install cargo-fuzz
+        run: |
+          echo "RUSTC_BOOTSTRAP=1" >> "${GITHUB_ENV}"
+          echo "CARGO_INCREMENTAL=0" >> "${GITHUB_ENV}"
+          cargo install cargo-fuzz --locked
       - uses: Swatinem/rust-cache@v2
         with:
           shared-key: "cargo-fuzz-cache-key"
           cache-directories: "fuzz/target"
       - name: Run `cargo-fuzz build`
-        run: cargo +nightly fuzz build
+        run: cargo fuzz build
 
   fuzz-run:
     needs: fuzz-build
@@ -46,17 +48,20 @@ jobs:
           - { name: fuzz_ed, should_pass: true }
           - { name: fuzz_normal, should_pass: true }
           - { name: fuzz_patch, should_pass: true }
+          - { name: fuzz_side, should_pass: true }
     steps:
       - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@nightly
       - name: Install `cargo-fuzz`
-        run: cargo install cargo-fuzz
+        run: |
+          echo "RUSTC_BOOTSTRAP=1" >> "${GITHUB_ENV}"
+          echo "CARGO_INCREMENTAL=0" >> "${GITHUB_ENV}"
+          cargo install cargo-fuzz --locked
       - uses: Swatinem/rust-cache@v2
         with:
           shared-key: "cargo-fuzz-cache-key"
           cache-directories: "fuzz/target"
       - name: Restore Cached Corpus
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@v5
         with:
           key: corpus-cache-${{ matrix.test-target.name }}
           path: |
@@ -65,9 +70,9 @@ jobs:
         shell: bash
         continue-on-error: ${{ !matrix.test-target.name.should_pass }}
         run: |
-          cargo +nightly fuzz run ${{ matrix.test-target.name }} -- -max_total_time=${{ env.RUN_FOR }} -detect_leaks=0
+          cargo fuzz run ${{ matrix.test-target.name }} -- -max_total_time=${{ env.RUN_FOR }} -detect_leaks=0
       - name: Save Corpus Cache
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@v5
         with:
           key: corpus-cache-${{ matrix.test-target.name }}
           path: |

.github/workflows/release.yml

@@ -1,10 +1,12 @@
+# This file was autogenerated by dist: https://axodotdev.github.io/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 cargo-dist (archives, installers, hashes)
+# * builds artifacts with dist (archives, installers, hashes)
 # * uploads those artifacts to temporary workflow zip
 # * on success, uploads the artifacts to a GitHub Release
 #
@@ -12,9 +14,8 @@
 # title/body based on your changelogs.
 
 name: Release
-
 permissions:
-  contents: write
+  "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.
@@ -23,10 +24,10 @@ permissions:
 # 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 cargo-dist-able).
+# 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
-# (cargo-dist-able) packages in the workspace with that version (this mode is
+# (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).
 #
@@ -38,15 +39,15 @@ permissions:
 # 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]+*'
-  pull_request:
 
 jobs:
-  # Run 'cargo dist plan' (or host) to determine what tasks we need to do
+  # Run 'dist plan' (or host) to determine what tasks we need to do
   plan:
-    runs-on: ubuntu-latest
+    runs-on: "ubuntu-22.04"
     outputs:
       val: ${{ steps.plan.outputs.manifest }}
       tag: ${{ !github.event.pull_request && github.ref_name || '' }}
@@ -57,12 +58,18 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
+          persist-credentials: false
           submodules: recursive
-      - name: Install cargo-dist
+      - 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/v0.13.3/cargo-dist-installer.sh | sh"
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.30.3/cargo-dist-installer.sh | sh"
+      - name: Cache dist
+        uses: actions/upload-artifact@v4
+        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.
@@ -70,8 +77,8 @@ jobs:
       # but also really annoying to build CI around when it needs secrets to work right.)
       - id: plan
         run: |
-          cargo dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json
-          echo "cargo dist ran successfully"
+          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"
@@ -89,18 +96,19 @@ jobs:
     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 cargo-dist in create-release.
+      # 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 cargo dist
-      # - install-dist: expression to run to install cargo-dist on the 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
@@ -110,12 +118,17 @@ jobs:
           git config --global core.longpaths true
       - uses: actions/checkout@v4
         with:
+          persist-credentials: false
           submodules: recursive
-      - uses: swatinem/rust-cache@v2
-        with:
-          key: ${{ join(matrix.targets, '-') }}
-      - name: Install cargo-dist
-        run: ${{ matrix.install_dist }}
+      - 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@v4
@@ -129,8 +142,8 @@ jobs:
       - name: Build artifacts
         run: |
           # Actually do builds and make zips and whatnot
-          cargo dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
-          echo "cargo dist ran successfully"
+          dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
+          echo "dist ran successfully"
       - id: cargo-dist
         name: Post-build
         # We force bash here just because github makes it really hard to get values up
@@ -140,7 +153,7 @@ jobs:
         run: |
           # Parse out what we just built and upload it to scratch storage
           echo "paths<<EOF" >> "$GITHUB_OUTPUT"
-          jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
+          dist print-upload-files-from-manifest --manifest dist-manifest.json >> "$GITHUB_OUTPUT"
           echo "EOF" >> "$GITHUB_OUTPUT"
 
           cp dist-manifest.json "$BUILD_MANIFEST_NAME"
@@ -157,17 +170,21 @@ jobs:
     needs:
       - plan
       - build-local-artifacts
-    runs-on: "ubuntu-20.04"
+    runs-on: "ubuntu-22.04"
     env:
       GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       BUILD_MANIFEST_NAME: target/distrib/global-dist-manifest.json
     steps:
       - uses: actions/checkout@v4
         with:
+          persist-credentials: false
           submodules: recursive
-      - name: Install cargo-dist
-        shell: bash
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.13.3/cargo-dist-installer.sh | sh"
+      - name: Install cached dist
+        uses: actions/download-artifact@v4
+        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@v4
@@ -178,8 +195,8 @@ jobs:
       - id: cargo-dist
         shell: bash
         run: |
-          cargo dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json
-          echo "cargo dist ran successfully"
+          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"
@@ -200,19 +217,24 @@ jobs:
       - 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') }}
+    # Only run if we're "publishing", and only if plan, local and global didn't fail (skipped is fine)
+    if: ${{ always() && needs.plan.result == 'success' && 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-20.04"
+    runs-on: "ubuntu-22.04"
     outputs:
       val: ${{ steps.host.outputs.manifest }}
     steps:
       - uses: actions/checkout@v4
         with:
+          persist-credentials: false
           submodules: recursive
-      - name: Install cargo-dist
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.13.3/cargo-dist-installer.sh | sh"
+      - name: Install cached dist
+        uses: actions/download-artifact@v4
+        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@v4
@@ -220,11 +242,10 @@ jobs:
           pattern: artifacts-*
           path: target/distrib/
           merge-multiple: true
-      # This is a harmless no-op for GitHub Releases, hosting for that happens in "announce"
       - id: host
         shell: bash
         run: |
-          cargo dist host ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json
+          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"
@@ -234,23 +255,7 @@ jobs:
           # Overwrite the previous copy
           name: artifacts-dist-manifest
           path: dist-manifest.json
-
-  # Create a GitHub Release while uploading all files to it
-  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-20.04"
-    env:
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
+      # Create a GitHub Release while uploading all files to it
       - name: "Download GitHub Artifacts"
         uses: actions/download-artifact@v4
         with:
@@ -262,10 +267,30 @@ jobs:
           # Remove the granular manifests
           rm -f artifacts/*-dist-manifest.json
       - name: Create GitHub Release
-        uses: ncipollo/release-action@v1
+        env:
+          PRERELEASE_FLAG: "${{ 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 }}" --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-22.04"
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v4
         with:
-          tag: ${{ needs.plan.outputs.tag }}
-          name: ${{ fromJson(needs.host.outputs.val).announcement_title }}
-          body: ${{ fromJson(needs.host.outputs.val).announcement_github_body }}
-          prerelease: ${{ fromJson(needs.host.outputs.val).announcement_is_prerelease }}
-          artifacts: "artifacts/*"
+          persist-credentials: false
+          submodules: recursive

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "diffutils"
-version = "0.4.2"
+version = "0.5.0"
 edition = "2021"
 description = "A CLI app for generating diff files"
 license = "MIT OR Apache-2.0"
@@ -23,25 +23,34 @@ same-file = "1.0.6"
 unicode-width = "0.2.0"
 
 [dev-dependencies]
-pretty_assertions = "1.4.0"
 assert_cmd = "2.0.14"
+divan = { version = "4.3.0", package = "codspeed-divan-compat" }
+pretty_assertions = "1.4.0"
 predicates = "3.1.0"
-tempfile = "3.10.1"
+rand = "0.10.0"
+tempfile = "3.26.0"
 
-# The profile that 'cargo dist' will build with
+[profile.release]
+lto = "thin"
+codegen-units = 1
+
+[profile.release-fast]
+inherits = "release"
+panic = "abort"
+
+# The profile that 'dist' will build with
 [profile.dist]
 inherits = "release"
 lto = "thin"
 
-# Config for 'cargo dist'
-[workspace.metadata.dist]
-# The preferred cargo-dist version to use in CI (Cargo.toml SemVer syntax)
-cargo-dist-version = "0.13.3"
-# CI backends to support
-ci = ["github"]
-# The installers to generate for each app
-installers = []
-# Target platforms to build apps for (Rust target-triple syntax)
-targets = ["aarch64-apple-darwin", "x86_64-apple-darwin", "x86_64-unknown-linux-gnu", "x86_64-pc-windows-msvc"]
-# Publish jobs to run in CI
-pr-run-mode = "plan"
+[[bench]]
+name = "bench_diffutils"
+path = "benches/bench-diffutils.rs"
+harness = false
+
+[features]
+# default = ["feat_bench_not_diff"]
+# Turn bench for diffutils cmp off
+feat_bench_not_cmp = []
+# Turn bench for diffutils diff off
+feat_bench_not_diff = []

README.md

@@ -2,10 +2,11 @@
 [![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/diffutils/blob/main/LICENSE)
 [![dependency status](https://deps.rs/repo/github/uutils/diffutils/status.svg)](https://deps.rs/repo/github/uutils/diffutils)
+[![CodSpeed](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/uutils/diffutils?utm_source=badge)
 
 [![CodeCov](https://codecov.io/gh/uutils/diffutils/branch/main/graph/badge.svg)](https://codecov.io/gh/uutils/diffutils)
 
-The goal of this package is to be a drop-in replacement for the [diffutils commands](https://www.gnu.org/software/diffutils/) in Rust.
+The goal of this package is to be a drop-in replacement for the [diffutils commands](https://www.gnu.org/software/diffutils/) (diff, cmp, diff3, sdiff) in Rust.
 
 Based on the incomplete diff generator in https://github.com/rust-lang/rust/blob/master/src/tools/compiletest/src/runtest.rs, and made to be compatible with GNU's diff and patch tools.
 

benches/bench-diffutils.rs

@@ -0,0 +1,377 @@
+// This file is part of the uutils diffutils package.
+//
+// For the full copyright and license information, please view the LICENSE-*
+// files that was distributed with this source code.
+
+//! Benches for all utils in diffutils.
+//!
+//! There is a file generator included to create files of different sizes for comparison. \
+//! Set the TEMP_DIR const to keep the files. df_to_ files have small changes in them, search for '#'. \
+//! File generation up to 1 GB is really fast, Benchmarking above 100 MB takes very long.
+
+/// Generate test files with these sizes in KB.
+const FILE_SIZE_KILO_BYTES: [u64; 4] = [100, 1 * MB, 10 * MB, 25 * MB];
+// const FILE_SIZE_KILO_BYTES: [u64; 3] = [100, 1 * MB, 5 * MB];
+// Empty String to use TempDir (files will be removed after test) or specify dir to keep generated files
+const TEMP_DIR: &str = "";
+const NUM_DIFF: u64 = 4;
+// just for FILE_SIZE_KILO_BYTES
+const MB: u64 = 1_000;
+const CHANGE_CHAR: u8 = b'#';
+
+#[cfg(not(feature = "feat_bench_not_cmp"))]
+mod diffutils_cmp {
+    use std::hint::black_box;
+
+    use diffutilslib::cmp;
+    use divan::Bencher;
+
+    use crate::{binary, prepare::*, FILE_SIZE_KILO_BYTES};
+
+    #[divan::bench(args = FILE_SIZE_KILO_BYTES)]
+    fn cmp_compare_files_equal(bencher: Bencher, kb: u64) {
+        let (from, to) = get_context().get_test_files_equal(kb);
+        let cmd = format!("cmp {from} {to}");
+        let opts = str_to_options(&cmd).into_iter().peekable();
+        let params = cmp::parse_params(opts).unwrap();
+
+        bencher
+            // .with_inputs(|| prepare::cmp_params_identical_testfiles(lines))
+            .with_inputs(|| params.clone())
+            .bench_refs(|params| black_box(cmp::cmp(&params).unwrap()));
+    }
+
+    // bench the actual compare; cmp exits on first difference
+    #[divan::bench(args = FILE_SIZE_KILO_BYTES)]
+    fn cmp_compare_files_different(bencher: Bencher, bytes: u64) {
+        let (from, to) = get_context().get_test_files_different(bytes);
+        let cmd = format!("cmp {from} {to} -s");
+        let opts = str_to_options(&cmd).into_iter().peekable();
+        let params = cmp::parse_params(opts).unwrap();
+
+        bencher
+            // .with_inputs(|| prepare::cmp_params_identical_testfiles(lines))
+            .with_inputs(|| params.clone())
+            .bench_refs(|params| black_box(cmp::cmp(&params).unwrap()));
+    }
+
+    // bench original GNU cmp
+    #[divan::bench(args = FILE_SIZE_KILO_BYTES)]
+    fn cmd_cmp_gnu_equal(bencher: Bencher, bytes: u64) {
+        let (from, to) = get_context().get_test_files_equal(bytes);
+        let args_str = format!("{from} {to}");
+        bencher
+            // .with_inputs(|| prepare::cmp_params_identical_testfiles(lines))
+            .with_inputs(|| args_str.clone())
+            .bench_refs(|cmd_args| binary::bench_binary("cmp", cmd_args));
+    }
+
+    // bench the compiled release version
+    #[divan::bench(args = FILE_SIZE_KILO_BYTES)]
+    fn cmd_cmp_release_equal(bencher: Bencher, bytes: u64) {
+        let (from, to) = get_context().get_test_files_equal(bytes);
+        let args_str = format!("cmp {from} {to}");
+
+        bencher
+            // .with_inputs(|| prepare::cmp_params_identical_testfiles(lines))
+            .with_inputs(|| args_str.clone())
+            .bench_refs(|cmd_args| binary::bench_binary("target/release/diffutils", cmd_args));
+    }
+}
+
+#[cfg(not(feature = "feat_bench_not_diff"))]
+mod diffutils_diff {
+    // use std::hint::black_box;
+
+    use crate::{binary, prepare::*, FILE_SIZE_KILO_BYTES};
+    // use diffutilslib::params;
+    use divan::Bencher;
+
+    // bench the actual compare
+    // TODO diff does not have a diff function
+    //     #[divan::bench(args = [100_000,10_000])]
+    //     fn diff_compare_files(bencher: Bencher, bytes: u64) {
+    //         let (from, to) = gen_testfiles(lines, 0, "id");
+    //         let cmd = format!("cmp {from} {to}");
+    //         let opts = str_to_options(&cmd).into_iter().peekable();
+    //         let params = params::parse_params(opts).unwrap();
+    //
+    //         bencher
+    //             // .with_inputs(|| prepare::cmp_params_identical_testfiles(lines))
+    //             .with_inputs(|| params.clone())
+    //             .bench_refs(|params| diff::diff(&params).unwrap());
+    //     }
+
+    // bench original GNU diff
+    #[divan::bench(args = FILE_SIZE_KILO_BYTES)]
+    fn cmd_diff_gnu_equal(bencher: Bencher, bytes: u64) {
+        let (from, to) = get_context().get_test_files_equal(bytes);
+        let args_str = format!("{from} {to}");
+        bencher
+            // .with_inputs(|| prepare::cmp_params_identical_testfiles(lines))
+            .with_inputs(|| args_str.clone())
+            .bench_refs(|cmd_args| binary::bench_binary("diff", cmd_args));
+    }
+
+    // bench the compiled release version
+    #[divan::bench(args = FILE_SIZE_KILO_BYTES)]
+    fn cmd_diff_release_equal(bencher: Bencher, bytes: u64) {
+        let (from, to) = get_context().get_test_files_equal(bytes);
+        let args_str = format!("diff {from} {to}");
+
+        bencher
+            // .with_inputs(|| prepare::cmp_params_identical_testfiles(lines))
+            .with_inputs(|| args_str.clone())
+            .bench_refs(|cmd_args| binary::bench_binary("target/release/diffutils", cmd_args));
+    }
+}
+
+mod parser {
+    use std::hint::black_box;
+
+    use diffutilslib::{cmp, params};
+    use divan::Bencher;
+
+    use crate::prepare::str_to_options;
+
+    // bench the time it takes to parse the command line arguments
+    #[divan::bench]
+    fn cmp_parser(bencher: Bencher) {
+        let cmd = "cmd file_1.txt file_2.txt -bl n10M --ignore-initial=100KiB:1MiB";
+        let args = str_to_options(&cmd).into_iter().peekable();
+        bencher
+            .with_inputs(|| args.clone())
+            .bench_values(|data| black_box(cmp::parse_params(data)));
+    }
+
+    // // test the impact on the benchmark if not converting the cmd to Vec<OsString> (doubles for parse)
+    // #[divan::bench]
+    // fn cmp_parser_no_prepare() {
+    //     let cmd = "cmd file_1.txt file_2.txt -bl n10M --ignore-initial=100KiB:1MiB";
+    //     let args = str_to_options(&cmd).into_iter().peekable();
+    //     let _ = cmp::parse_params(args);
+    // }
+
+    // bench the time it takes to parse the command line arguments
+    #[divan::bench]
+    fn diff_parser(bencher: Bencher) {
+        let cmd = "diff file_1.txt file_2.txt -s --brief --expand-tabs --width=100";
+        let args = str_to_options(&cmd).into_iter().peekable();
+        bencher
+            .with_inputs(|| args.clone())
+            .bench_values(|data| black_box(params::parse_params(data)));
+    }
+}
+
+mod prepare {
+    use std::{
+        ffi::OsString,
+        fs::{self, File},
+        io::{BufWriter, Write},
+        path::Path,
+        sync::OnceLock,
+    };
+
+    use rand::RngExt;
+    use tempfile::TempDir;
+
+    use crate::{CHANGE_CHAR, FILE_SIZE_KILO_BYTES, NUM_DIFF, TEMP_DIR};
+
+    // file lines and .txt will be added
+    const FROM_FILE: &str = "from_file";
+    const TO_FILE: &str = "to_file";
+    const LINE_LENGTH: usize = 60;
+
+    /// Contains test data (file names) which only needs to be created once.
+    #[derive(Debug, Default)]
+    pub struct BenchContext {
+        pub tmp_dir: Option<TempDir>,
+        pub dir: String,
+        pub files_equal: Vec<(String, String)>,
+        pub files_different: Vec<(String, String)>,
+    }
+
+    impl BenchContext {
+        pub fn get_path(&self) -> &Path {
+            match &self.tmp_dir {
+                Some(tmp) => tmp.path(),
+                None => Path::new(&self.dir),
+            }
+        }
+
+        pub fn get_test_files_equal(&self, kb: u64) -> &(String, String) {
+            let p = FILE_SIZE_KILO_BYTES.iter().position(|f| *f == kb).unwrap();
+            &self.files_equal[p]
+        }
+
+        #[allow(unused)]
+        pub fn get_test_files_different(&self, kb: u64) -> &(String, String) {
+            let p = FILE_SIZE_KILO_BYTES.iter().position(|f| *f == kb).unwrap();
+            &self.files_different[p]
+        }
+    }
+
+    // Since each bench function is separate in Divan it is more difficult to dynamically create test data.
+    // This keeps the TempDir alive until the program exits and generates the files only once.
+    static SHARED_CONTEXT: OnceLock<BenchContext> = OnceLock::new();
+    /// Creates the test files once and provides them to all tests.
+    pub fn get_context() -> &'static BenchContext {
+        SHARED_CONTEXT.get_or_init(|| {
+            let mut ctx = BenchContext::default();
+            if TEMP_DIR.is_empty() {
+                let tmp_dir = TempDir::new().expect("Failed to create temp dir");
+                ctx.tmp_dir = Some(tmp_dir);
+            } else {
+                // uses current directory, the generated files are kept
+                let path = Path::new(TEMP_DIR);
+                if !path.exists() {
+                    fs::create_dir_all(path).expect("Path {path} could not be created");
+                }
+                ctx.dir = TEMP_DIR.to_string();
+            };
+
+            // generate test bytes
+            for kb in FILE_SIZE_KILO_BYTES {
+                let f = generate_test_files_bytes(ctx.get_path(), kb * 1000, 0, "eq")
+                    .expect("generate_test_files failed");
+                ctx.files_equal.push(f);
+                let f = generate_test_files_bytes(ctx.get_path(), kb * 1000, NUM_DIFF, "df")
+                    .expect("generate_test_files failed");
+                ctx.files_different.push(f);
+            }
+
+            ctx
+        })
+    }
+
+    pub fn str_to_options(opt: &str) -> Vec<OsString> {
+        let s: Vec<OsString> = opt
+            .split(" ")
+            .into_iter()
+            .filter(|s| !s.is_empty())
+            .map(|s| OsString::from(s))
+            .collect();
+
+        s
+    }
+
+    /// Generates two test files for comparison with <bytes> size.
+    ///
+    /// Each line consists of 10 words with 5 letters, giving a line length of 60 bytes.
+    /// If num_differences is set, '#' will be inserted between the first two words of a line,
+    /// evenly spaced in the file. 1 will add the change in the last line, so the comparison takes longest.
+    fn generate_test_files_bytes(
+        dir: &Path,
+        bytes: u64,
+        num_differences: u64,
+        id: &str,
+    ) -> std::io::Result<(String, String)> {
+        let id = if id.is_empty() {
+            "".to_string()
+        } else {
+            format!("{id}_")
+        };
+        let f1 = format!("{id}{FROM_FILE}_{bytes}.txt");
+        let f2 = format!("{id}{TO_FILE}_{bytes}.txt");
+        let from_path = dir.join(f1);
+        let to_path = dir.join(f2);
+
+        generate_file_bytes(&from_path, &to_path, bytes, num_differences)?;
+
+        Ok((
+            from_path.to_string_lossy().to_string(),
+            to_path.to_string_lossy().to_string(),
+        ))
+    }
+
+    fn generate_file_bytes(
+        from_name: &Path,
+        to_name: &Path,
+        bytes: u64,
+        num_differences: u64,
+    ) -> std::io::Result<()> {
+        let file_from = File::create(from_name)?;
+        let file_to = File::create(to_name)?;
+        // for int division, lines will be smaller than requested bytes
+        let n_lines = bytes / LINE_LENGTH as u64;
+        let change_every_n_lines = if num_differences == 0 {
+            0
+        } else {
+            let c = n_lines / num_differences;
+            if c == 0 {
+                1
+            } else {
+                c
+            }
+        };
+        // Use a larger 128KB buffer for massive files
+        let mut writer_from = BufWriter::with_capacity(128 * 1024, file_from);
+        let mut writer_to = BufWriter::with_capacity(128 * 1024, file_to);
+        let mut rng = rand::rng();
+
+        // Each line: (5 chars * 10 words) + 9 spaces + 1 newline = 60 bytes
+        let mut line_buffer = [b' '; 60];
+        line_buffer[59] = b'\n'; // Set the newline once at the end
+
+        for i in (0..n_lines).rev() {
+            // Fill only the letter positions, skipping spaces and the newline
+            for word_idx in 0..10 {
+                let start = word_idx * 6; // Each word + space block is 6 bytes
+                for i in 0..5 {
+                    line_buffer[start + i] = rng.random_range(b'a'..b'z' + 1);
+                }
+            }
+
+            // Write the raw bytes directly to both files
+            writer_from.write_all(&line_buffer)?;
+            // make changes in the file
+            if num_differences == 0 {
+                writer_to.write_all(&line_buffer)?;
+            } else {
+                if i % change_every_n_lines == 0 && n_lines - i > 2 {
+                    line_buffer[5] = CHANGE_CHAR;
+                }
+                writer_to.write_all(&line_buffer)?;
+                line_buffer[5] = b' ';
+            }
+        }
+
+        // create last line
+        let missing = (bytes - n_lines as u64 * LINE_LENGTH as u64) as usize;
+        if missing > 0 {
+            for word_idx in 0..10 {
+                let start = word_idx * 6; // Each word + space block is 6 bytes
+                for i in 0..5 {
+                    line_buffer[start + i] = rng.random_range(b'a'..b'z' + 1);
+                }
+            }
+            line_buffer[missing - 1] = b'\n';
+            writer_from.write_all(&line_buffer[0..missing])?;
+            writer_to.write_all(&line_buffer[0..missing])?;
+        }
+
+        writer_from.flush()?;
+        writer_to.flush()?;
+
+        Ok(())
+    }
+}
+
+mod binary {
+    use std::process::Command;
+
+    use crate::prepare::str_to_options;
+
+    pub fn bench_binary(program: &str, cmd_args: &str) -> std::process::ExitStatus {
+        let args = str_to_options(cmd_args);
+        Command::new(program)
+            .args(args)
+            .status()
+            .expect("Failed to execute binary")
+    }
+}
+
+fn main() {
+    // Run registered benchmarks.
+    divan::main();
+}

dist-workspace.toml

@@ -0,0 +1,13 @@
+[workspace]
+members = ["cargo:."]
+
+# Config for 'dist'
+[dist]
+# The preferred dist version to use in CI (Cargo.toml SemVer syntax)
+cargo-dist-version = "0.30.3"
+# CI backends to support
+ci = "github"
+# The installers to generate for each app
+installers = []
+# Target platforms to build apps for (Rust target-triple syntax)
+targets = ["aarch64-apple-darwin", "aarch64-unknown-linux-gnu", "x86_64-apple-darwin", "x86_64-unknown-linux-gnu", "x86_64-pc-windows-msvc"]

fuzz/Cargo.lock

@@ -0,0 +1,474 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "android_system_properties"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "arbitrary"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3d036a3c4ab069c7b410a2ce876bd74808d2d0888a82667669f8e783a898bf1"
+
+[[package]]
+name = "autocfg"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
+[[package]]
+name = "bumpalo"
+version = "3.19.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5dd9dc738b7a8311c7ade152424974d8115f2cdad61e8dab8dac9f2362298510"
+
+[[package]]
+name = "cc"
+version = "1.2.51"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a0aeaff4ff1a90589618835a598e545176939b97874f7abc7851caa0618f203"
+dependencies = [
+ "find-msvc-tools",
+ "jobserver",
+ "libc",
+ "shlex",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "chrono"
+version = "0.4.42"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "145052bdd345b87320e369255277e3fb5152762ad123a901ef5c262dd38fe8d2"
+dependencies = [
+ "iana-time-zone",
+ "js-sys",
+ "num-traits",
+ "wasm-bindgen",
+ "windows-link",
+]
+
+[[package]]
+name = "const_format"
+version = "0.2.35"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7faa7469a93a566e9ccc1c73fe783b4a65c274c5ace346038dca9c39fe0030ad"
+dependencies = [
+ "const_format_proc_macros",
+]
+
+[[package]]
+name = "const_format_proc_macros"
+version = "0.2.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d57c2eccfb16dbac1f4e61e206105db5820c9d26c3c472bc17c774259ef7744"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-xid",
+]
+
+[[package]]
+name = "core-foundation-sys"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
+
+[[package]]
+name = "diff"
+version = "0.1.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "56254986775e3233ffa9c4d7d3faaf6d36a2c09d30b20687e9f88bc8bafc16c8"
+
+[[package]]
+name = "diffutils"
+version = "0.5.0"
+dependencies = [
+ "chrono",
+ "const_format",
+ "diff",
+ "itoa",
+ "regex",
+ "same-file",
+ "unicode-width",
+]
+
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "645cbb3a84e60b7531617d5ae4e57f7e27308f6445f5abf653209ea76dec8dff"
+
+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasip2",
+]
+
+[[package]]
+name = "iana-time-zone"
+version = "0.1.64"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33e57f83510bb73707521ebaffa789ec8caf86f9657cad665b092b581d40e9fb"
+dependencies = [
+ "android_system_properties",
+ "core-foundation-sys",
+ "iana-time-zone-haiku",
+ "js-sys",
+ "log",
+ "wasm-bindgen",
+ "windows-core",
+]
+
+[[package]]
+name = "iana-time-zone-haiku"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92ecc6618181def0457392ccd0ee51198e065e016d1d527a7ac1b6dc7c1f09d2"
+
+[[package]]
+name = "jobserver"
+version = "0.1.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33"
+dependencies = [
+ "getrandom",
+ "libc",
+]
+
+[[package]]
+name = "js-sys"
+version = "0.3.83"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "464a3709c7f55f1f721e5389aa6ea4e3bc6aba669353300af094b29ffbdde1d8"
+dependencies = [
+ "once_cell",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.178"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37c93d8daa9d8a012fd8ab92f088405fb202ea0b6ab73ee2482ae66af4f42091"
+
+[[package]]
+name = "libfuzzer-sys"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f12a681b7dd8ce12bff52488013ba614b869148d54dd79836ab85aafdd53f08d"
+dependencies = [
+ "arbitrary",
+ "cc",
+]
+
+[[package]]
+name = "log"
+version = "0.4.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
+
+[[package]]
+name = "memchr"
+version = "2.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273"
+
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.104"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9695f8df41bb4f3d222c95a67532365f569318332d03d5f3f67f37b20e6ebdf0"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.42"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a338cc41d27e6cc6dce6cefc13a0729dfbb81c262b1f519331575dd80ef3067f"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
+[[package]]
+name = "regex"
+version = "1.12.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843bc0191f75f3e22651ae5f1e72939ab2f72a4bc30fa80a066bd66edefc24d4"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5276caf25ac86c8d810222b3dbb938e512c55c6831a10f3e6ed1c93b84041f1c"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a2d987857b319362043e95f5353c0535c1f58eec5336fdfcf626430af7def58"
+
+[[package]]
+name = "rustversion"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
+
+[[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "syn"
+version = "2.0.112"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "21f182278bf2d2bcb3c88b1b08a37df029d71ce3d3ae26168e3c653b213b99d4"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
+
+[[package]]
+name = "unicode-width"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
+
+[[package]]
+name = "unicode-xid"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
+
+[[package]]
+name = "unified-diff-fuzz"
+version = "0.0.0"
+dependencies = [
+ "diffutils",
+ "libfuzzer-sys",
+]
+
+[[package]]
+name = "wasip2"
+version = "1.0.1+wasi-0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0562428422c63773dad2c345a1882263bbf4d65cf3f42e90921f787ef5ad58e7"
+dependencies = [
+ "wit-bindgen",
+]
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d759f433fa64a2d763d1340820e46e111a7a5ab75f993d1852d70b03dbb80fd"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "rustversion",
+ "wasm-bindgen-macro",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48cb0d2638f8baedbc542ed444afc0644a29166f1595371af4fecf8ce1e7eeb3"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cefb59d5cd5f92d9dcf80e4683949f15ca4b511f4ac0a6e14d4e1ac60c6ecd40"
+dependencies = [
+ "bumpalo",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cbc538057e648b67f72a982e708d485b2efa771e1ac05fec311f9f63e5800db4"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "winapi-util"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "windows-core"
+version = "0.62.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
+dependencies = [
+ "windows-implement",
+ "windows-interface",
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-implement"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "windows-interface"
+version = "0.59.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+
+[[package]]
+name = "windows-result"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "wit-bindgen"
+version = "0.46.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f17a85883d4e6d00e8a97c586de764dabcc06133f7f1d55dce5cdc070ad7fe59"

fuzz/Cargo.toml

@@ -47,4 +47,8 @@ path = "fuzz_targets/fuzz_ed.rs"
 test = false
 doc = false
 
-
+[[bin]]
+name = "fuzz_side"
+path = "fuzz_targets/fuzz_side.rs"
+test = false
+doc = false

fuzz/fuzz_targets/fuzz_side.rs

@@ -0,0 +1,42 @@
+#![no_main]
+#[macro_use]
+extern crate libfuzzer_sys;
+
+use diffutilslib::side_diff;
+
+use std::fs::File;
+use std::io::Write;
+use diffutilslib::params::Params;
+
+fuzz_target!(|x: (Vec<u8>, Vec<u8>, /* usize, usize */ bool)| {
+    let (original, new, /* width, tabsize, */ expand) = x;
+
+    // if width == 0 || tabsize == 0 {
+    //     return;
+    // }
+
+    let params = Params {
+        // width,
+        // tabsize,
+        expand_tabs: expand,
+        ..Default::default()
+    };
+    let mut output_buf = vec![];
+    side_diff::diff(&original, &new, &mut output_buf, &params);
+    File::create("target/fuzz.file.original")
+        .unwrap()
+        .write_all(&original)
+        .unwrap();
+    File::create("target/fuzz.file.new")
+        .unwrap()
+        .write_all(&new)
+        .unwrap();
+    File::create("target/fuzz.file")
+        .unwrap()
+        .write_all(&original)
+        .unwrap();
+    File::create("target/fuzz.diff")
+        .unwrap()
+        .write_all(&output_buf)
+        .unwrap();
+});

src/cmp.rs

@@ -9,7 +9,7 @@ use std::ffi::OsString;
 use std::io::{BufRead, BufReader, BufWriter, Read, Write};
 use std::iter::Peekable;
 use std::process::ExitCode;
-use std::{fs, io};
+use std::{cmp, fs, io};
 
 #[cfg(not(target_os = "windows"))]
 use std::os::fd::{AsRawFd, FromRawFd};
@@ -35,7 +35,7 @@ pub struct Params {
 
 #[inline]
 fn usage_string(executable: &str) -> String {
-    format!("Usage: {} <from> <to>", executable)
+    format!("Usage: {executable} <from> <to>")
 }
 
 #[cfg(not(target_os = "windows"))]
@@ -75,8 +75,7 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
             Err(e) if *e.kind() == std::num::IntErrorKind::PosOverflow => usize::MAX,
             Err(_) => {
                 return Err(format!(
-                    "{}: invalid --ignore-initial value '{}'",
-                    executable_str, skip_desc
+                    "{executable_str}: invalid --ignore-initial value '{skip_desc}'"
                 ))
             }
         };
@@ -91,20 +90,29 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
                 "M" => 1_048_576,
                 "GB" => 1_000_000_000,
                 "G" => 1_073_741_824,
-                "TB" => 1_000_000_000_000,
-                "T" => 1_099_511_627_776,
-                "PB" => 1_000_000_000_000_000,
-                "P" => 1_125_899_906_842_624,
-                "EB" => 1_000_000_000_000_000_000,
-                "E" => 1_152_921_504_606_846_976,
+                // This only generates a warning when compiling for target_pointer_width < 64
+                #[allow(unused_variables)]
+                suffix @ ("TB" | "T" | "PB" | "P" | "EB" | "E") => {
+                    #[cfg(target_pointer_width = "64")]
+                    match suffix {
+                        "TB" => 1_000_000_000_000,
+                        "T" => 1_099_511_627_776,
+                        "PB" => 1_000_000_000_000_000,
+                        "P" => 1_125_899_906_842_624,
+                        "EB" => 1_000_000_000_000_000_000,
+                        "E" => 1_152_921_504_606_846_976,
+                        _ => unreachable!(),
+                    }
+                    #[cfg(not(target_pointer_width = "64"))]
+                    usize::MAX
+                }
                 "ZB" => usize::MAX, // 1_000_000_000_000_000_000_000,
                 "Z" => usize::MAX,  // 1_180_591_620_717_411_303_424,
                 "YB" => usize::MAX, // 1_000_000_000_000_000_000_000_000,
                 "Y" => usize::MAX,  // 1_208_925_819_614_629_174_706_176,
                 _ => {
                     return Err(format!(
-                        "{}: invalid --ignore-initial value '{}'",
-                        executable_str, skip_desc
+                        "{executable_str}: invalid --ignore-initial value '{skip_desc}'"
                     ));
                 }
             };
@@ -170,8 +178,7 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
                 Err(e) if *e.kind() == std::num::IntErrorKind::PosOverflow => usize::MAX,
                 Err(_) => {
                     return Err(format!(
-                        "{}: invalid --bytes value '{}'",
-                        executable_str, max_bytes
+                        "{executable_str}: invalid --bytes value '{max_bytes}'"
                     ))
                 }
             };
@@ -210,7 +217,7 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
             std::process::exit(0);
         }
         if param_str.starts_with('-') {
-            return Err(format!("Unknown option: {:?}", param));
+            return Err(format!("unrecognized option: {param:?}"));
         }
         if from.is_none() {
             from = Some(param);
@@ -236,8 +243,7 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
 
     if params.quiet && params.verbose {
         return Err(format!(
-            "{}: options -l and -s are incompatible",
-            executable_str
+            "{executable_str}: options -l and -s are incompatible"
         ));
     }
 
@@ -320,10 +326,35 @@ pub fn cmp(params: &Params) -> Result<Cmp, String> {
     let mut from = prepare_reader(&params.from, &params.skip_a, params)?;
     let mut to = prepare_reader(&params.to, &params.skip_b, params)?;
 
+    let mut offset_width = params.max_bytes.unwrap_or(usize::MAX);
+
+    if let (Ok(a_meta), Ok(b_meta)) = (fs::metadata(&params.from), fs::metadata(&params.to)) {
+        #[cfg(not(target_os = "windows"))]
+        let (a_size, b_size) = (a_meta.size(), b_meta.size());
+
+        #[cfg(target_os = "windows")]
+        let (a_size, b_size) = (a_meta.file_size(), b_meta.file_size());
+
+        // If the files have different sizes, we already know they are not identical. If we have not
+        // been asked to show even the first difference, we can quit early.
+        if params.quiet && a_size != b_size {
+            return Ok(Cmp::Different);
+        }
+
+        let smaller = cmp::min(a_size, b_size) as usize;
+        offset_width = cmp::min(smaller, offset_width);
+    }
+
+    let offset_width = 1 + offset_width.checked_ilog10().unwrap_or(1) as usize;
+
+    // Capacity calc: at_byte width + 2 x 3-byte octal numbers + 2 x 4-byte value + 4 spaces
+    let mut output = Vec::<u8>::with_capacity(offset_width + 3 * 2 + 4 * 2 + 4);
+
     let mut at_byte = 1;
     let mut at_line = 1;
     let mut start_of_line = true;
-    let mut verbose_diffs = vec![];
+    let mut stdout = BufWriter::new(io::stdout().lock());
+    let mut compare = Cmp::Equal;
     loop {
         // Fill up our buffers.
         let from_buf = match from.fill_buf() {
@@ -360,10 +391,6 @@ pub fn cmp(params: &Params) -> Result<Cmp, String> {
                 &params.to.to_string_lossy()
             };
 
-            if params.verbose {
-                report_verbose_diffs(verbose_diffs, params)?;
-            }
-
             report_eof(at_byte, at_line, start_of_line, eof_on, params);
             return Ok(Cmp::Different);
         }
@@ -395,8 +422,24 @@ pub fn cmp(params: &Params) -> Result<Cmp, String> {
         // first one runs out.
         for (&from_byte, &to_byte) in from_buf.iter().zip(to_buf.iter()) {
             if from_byte != to_byte {
+                compare = Cmp::Different;
+
                 if params.verbose {
-                    verbose_diffs.push((at_byte, from_byte, to_byte));
+                    format_verbose_difference(
+                        from_byte,
+                        to_byte,
+                        at_byte,
+                        offset_width,
+                        &mut output,
+                        params,
+                    )?;
+                    stdout.write_all(output.as_slice()).map_err(|e| {
+                        format!(
+                            "{}: error printing output: {e}",
+                            params.executable.to_string_lossy()
+                        )
+                    })?;
+                    output.clear();
                 } else {
                     report_difference(from_byte, to_byte, at_byte, at_line, params);
                     return Ok(Cmp::Different);
@@ -422,12 +465,7 @@ pub fn cmp(params: &Params) -> Result<Cmp, String> {
         to.consume(consumed);
     }
 
-    if params.verbose && !verbose_diffs.is_empty() {
-        report_verbose_diffs(verbose_diffs, params)?;
-        return Ok(Cmp::Different);
-    }
-
-    Ok(Cmp::Equal)
+    Ok(compare)
 }
 
 // Exit codes are documented at
@@ -450,21 +488,6 @@ pub fn main(opts: Peekable<ArgsOs>) -> ExitCode {
         return ExitCode::SUCCESS;
     }
 
-    // If the files have different sizes, we already know they are not identical. If we have not
-    // been asked to show even the first difference, we can quit early.
-    if params.quiet {
-        if let (Ok(a_meta), Ok(b_meta)) = (fs::metadata(&params.from), fs::metadata(&params.to)) {
-            #[cfg(not(target_os = "windows"))]
-            if a_meta.size() != b_meta.size() {
-                return ExitCode::from(1);
-            }
-            #[cfg(target_os = "windows")]
-            if a_meta.file_size() != b_meta.file_size() {
-                return ExitCode::from(1);
-            }
-        }
-    }
-
     match cmp(&params) {
         Ok(Cmp::Equal) => ExitCode::SUCCESS,
         Ok(Cmp::Different) => ExitCode::from(1),
@@ -477,12 +500,6 @@ pub fn main(opts: Peekable<ArgsOs>) -> ExitCode {
     }
 }
 
-#[inline]
-fn is_ascii_printable(byte: u8) -> bool {
-    let c = byte as char;
-    c.is_ascii() && !c.is_ascii_control()
-}
-
 #[inline]
 fn format_octal(byte: u8, buf: &mut [u8; 3]) -> &str {
     *buf = [b' ', b' ', b'0'];
@@ -502,130 +519,136 @@ fn format_octal(byte: u8, buf: &mut [u8; 3]) -> &str {
 }
 
 #[inline]
-fn format_byte(byte: u8) -> String {
-    let mut byte = byte;
-    let mut quoted = vec![];
-
-    if !is_ascii_printable(byte) {
-        if byte >= 128 {
-            quoted.push(b'M');
-            quoted.push(b'-');
-            byte -= 128;
+fn write_visible_byte(output: &mut Vec<u8>, byte: u8) -> usize {
+    match byte {
+        // Control characters: ^@, ^A, ..., ^_
+        0..=31 => {
+            output.push(b'^');
+            output.push(byte + 64);
+            2
         }
-
-        if byte < 32 {
-            quoted.push(b'^');
-            byte += 64;
-        } else if byte == 127 {
-            quoted.push(b'^');
-            byte = b'?';
+        // Printable ASCII (space through ~)
+        32..=126 => {
+            output.push(byte);
+            1
+        }
+        // DEL: ^?
+        127 => {
+            output.extend_from_slice(b"^?");
+            2
+        }
+        // High bytes with control equivalents: M-^@, M-^A, ..., M-^_
+        128..=159 => {
+            output.push(b'M');
+            output.push(b'-');
+            output.push(b'^');
+            output.push(byte - 64);
+            4
+        }
+        // High bytes: M-<space>, M-!, ..., M-~
+        160..=254 => {
+            output.push(b'M');
+            output.push(b'-');
+            output.push(byte - 128);
+            3
+        }
+        // Byte 255: M-^?
+        255 => {
+            output.extend_from_slice(b"M-^?");
+            4
         }
-        assert!((byte as char).is_ascii());
     }
+}
 
-    quoted.push(byte);
+/// Writes a byte in visible form with right-padding to 4 spaces.
+#[inline]
+fn write_visible_byte_padded(output: &mut Vec<u8>, byte: u8) {
+    const SPACES: &[u8] = b"    ";
+    const WIDTH: usize = SPACES.len();
 
-    // SAFETY: the checks and shifts we do above match what cat and GNU
+    let display_width = write_visible_byte(output, byte);
+
+    // Add right-padding spaces
+    let padding = WIDTH.saturating_sub(display_width);
+    output.extend_from_slice(&SPACES[..padding]);
+}
+
+/// Formats a byte as a visible string (for non-performance-critical path)
+#[inline]
+fn format_visible_byte(byte: u8) -> String {
+    let mut result = Vec::with_capacity(4);
+    write_visible_byte(&mut result, byte);
+    // SAFETY: the checks and shifts in write_visible_byte match what cat and GNU
     // cmp do to ensure characters fall inside the ascii range.
-    unsafe { String::from_utf8_unchecked(quoted) }
+    unsafe { String::from_utf8_unchecked(result) }
 }
 
 // This function has been optimized to not use the Rust fmt system, which
 // leads to a massive speed up when processing large files: cuts the time
 // for comparing 2 ~36MB completely different files in half on an M1 Max.
-fn report_verbose_diffs(diffs: Vec<(usize, u8, u8)>, params: &Params) -> Result<(), String> {
+#[inline]
+fn format_verbose_difference(
+    from_byte: u8,
+    to_byte: u8,
+    at_byte: usize,
+    offset_width: usize,
+    output: &mut Vec<u8>,
+    params: &Params,
+) -> Result<(), String> {
     assert!(!params.quiet);
 
-    let mut stdout = BufWriter::new(io::stdout().lock());
-    if let Some((offset, _, _)) = diffs.last() {
-        // Obtain the width of the first column from the last byte offset.
-        let width = format!("{}", offset).len();
+    let mut at_byte_buf = itoa::Buffer::new();
+    let mut from_oct = [0u8; 3]; // for octal conversions
+    let mut to_oct = [0u8; 3];
 
-        let mut at_byte_buf = itoa::Buffer::new();
-        let mut from_oct = [0u8; 3]; // for octal conversions
-        let mut to_oct = [0u8; 3];
+    if params.print_bytes {
+        // "{:>width$} {:>3o} {:4} {:>3o} {}",
+        let at_byte_str = at_byte_buf.format(at_byte);
+        let at_byte_padding = offset_width.saturating_sub(at_byte_str.len());
 
-        // Capacity calc: at_byte width + 2 x 3-byte octal numbers + 4-byte value + up to 2 byte value + 4 spaces
-        let mut output = Vec::<u8>::with_capacity(width + 3 * 2 + 4 + 2 + 4);
-
-        if params.print_bytes {
-            for (at_byte, from_byte, to_byte) in diffs {
-                output.clear();
-
-                // "{:>width$} {:>3o} {:4} {:>3o} {}",
-                let at_byte_str = at_byte_buf.format(at_byte);
-                let at_byte_padding = width - at_byte_str.len();
-
-                for _ in 0..at_byte_padding {
-                    output.push(b' ')
-                }
-
-                output.extend_from_slice(at_byte_str.as_bytes());
-
-                output.push(b' ');
-
-                output.extend_from_slice(format_octal(from_byte, &mut from_oct).as_bytes());
-
-                output.push(b' ');
-
-                let from_byte_str = format_byte(from_byte);
-                let from_byte_padding = 4 - from_byte_str.len();
-
-                output.extend_from_slice(from_byte_str.as_bytes());
-
-                for _ in 0..from_byte_padding {
-                    output.push(b' ')
-                }
-
-                output.push(b' ');
-
-                output.extend_from_slice(format_octal(to_byte, &mut to_oct).as_bytes());
-
-                output.push(b' ');
-
-                output.extend_from_slice(format_byte(to_byte).as_bytes());
-
-                output.push(b'\n');
-
-                stdout.write_all(output.as_slice()).map_err(|e| {
-                    format!(
-                        "{}: error printing output: {e}",
-                        params.executable.to_string_lossy()
-                    )
-                })?;
-            }
-        } else {
-            for (at_byte, from_byte, to_byte) in diffs {
-                output.clear();
-
-                // "{:>width$} {:>3o} {:>3o}"
-                let at_byte_str = at_byte_buf.format(at_byte);
-                let at_byte_padding = width - at_byte_str.len();
-
-                for _ in 0..at_byte_padding {
-                    output.push(b' ')
-                }
-
-                output.extend_from_slice(at_byte_str.as_bytes());
-
-                output.push(b' ');
-
-                output.extend_from_slice(format_octal(from_byte, &mut from_oct).as_bytes());
-
-                output.push(b' ');
-
-                output.extend_from_slice(format_octal(to_byte, &mut to_oct).as_bytes());
-
-                output.push(b'\n');
-
-                stdout.write_all(output.as_slice()).map_err(|e| {
-                    format!(
-                        "{}: error printing output: {e}",
-                        params.executable.to_string_lossy()
-                    )
-                })?;
-            }
+        for _ in 0..at_byte_padding {
+            output.push(b' ')
         }
+
+        output.extend_from_slice(at_byte_str.as_bytes());
+
+        output.push(b' ');
+
+        output.extend_from_slice(format_octal(from_byte, &mut from_oct).as_bytes());
+
+        output.push(b' ');
+
+        write_visible_byte_padded(output, from_byte);
+
+        output.push(b' ');
+
+        output.extend_from_slice(format_octal(to_byte, &mut to_oct).as_bytes());
+
+        output.push(b' ');
+
+        write_visible_byte(output, to_byte);
+
+        output.push(b'\n');
+    } else {
+        // "{:>width$} {:>3o} {:>3o}"
+        let at_byte_str = at_byte_buf.format(at_byte);
+        let at_byte_padding = offset_width - at_byte_str.len();
+
+        for _ in 0..at_byte_padding {
+            output.push(b' ')
+        }
+
+        output.extend_from_slice(at_byte_str.as_bytes());
+
+        output.push(b' ');
+
+        output.extend_from_slice(format_octal(from_byte, &mut from_oct).as_bytes());
+
+        output.push(b' ');
+
+        output.extend_from_slice(format_octal(to_byte, &mut to_oct).as_bytes());
+
+        output.push(b'\n');
     }
 
     Ok(())
@@ -706,9 +729,9 @@ fn report_difference(from_byte: u8, to_byte: u8, at_byte: usize, at_line: usize,
         print!(
             " is {:>3o} {:char_width$} {:>3o} {:char_width$}",
             from_byte,
-            format_byte(from_byte),
+            format_visible_byte(from_byte),
             to_byte,
-            format_byte(to_byte)
+            format_visible_byte(to_byte)
         );
     }
     println!();
@@ -1062,6 +1085,9 @@ mod tests {
                 from: os("foo"),
                 to: os("bar"),
                 skip_a: Some(1_000_000_000),
+                #[cfg(target_pointer_width = "32")]
+                skip_b: Some((2_147_483_647.5 * 2.0) as usize),
+                #[cfg(target_pointer_width = "64")]
                 skip_b: Some(1_152_921_504_606_846_976 * 2),
                 ..Default::default()
             }),

src/diff.rs

@@ -5,11 +5,11 @@
 
 use crate::params::{parse_params, Format};
 use crate::utils::report_failure_to_read_input_file;
-use crate::{context_diff, ed_diff, normal_diff, unified_diff};
+use crate::{context_diff, ed_diff, normal_diff, side_diff, unified_diff};
 use std::env::ArgsOs;
 use std::ffi::OsString;
 use std::fs;
-use std::io::{self, Read, Write};
+use std::io::{self, stdout, Read, Write};
 use std::iter::Peekable;
 use std::process::{exit, ExitCode};
 
@@ -79,6 +79,10 @@ pub fn main(opts: Peekable<ArgsOs>) -> ExitCode {
             eprintln!("{error}");
             exit(2);
         }),
+        Format::SideBySide => {
+            let mut output = stdout().lock();
+            side_diff::diff(&from_content, &to_content, &mut output, &params)
+        }
     };
     if params.brief && !result.is_empty() {
         println!(

src/lib.rs

@@ -4,6 +4,7 @@ pub mod ed_diff;
 pub mod macros;
 pub mod normal_diff;
 pub mod params;
+pub mod side_diff;
 pub mod unified_diff;
 pub mod utils;
 
@@ -11,4 +12,5 @@ pub mod utils;
 pub use context_diff::diff as context_diff;
 pub use ed_diff::diff as ed_diff;
 pub use normal_diff::diff as normal_diff;
+pub use side_diff::diff as side_by_side_diff;
 pub use unified_diff::diff as unified_diff;

src/main.rs

@@ -18,6 +18,7 @@ mod ed_diff;
 mod macros;
 mod normal_diff;
 mod params;
+mod side_diff;
 mod unified_diff;
 mod utils;
 
@@ -72,7 +73,7 @@ fn main() -> ExitCode {
         Some("diff") => diff::main(args),
         Some("cmp") => cmp::main(args),
         Some(name) => {
-            eprintln!("{}: utility not supported", name);
+            eprintln!("{name}: utility not supported");
             ExitCode::from(2)
         }
         None => second_arg_error(exe_name),

src/params.rs

@@ -11,6 +11,7 @@ pub enum Format {
     Unified,
     Context,
     Ed,
+    SideBySide,
 }
 
 #[derive(Clone, Debug, Eq, PartialEq)]
@@ -24,6 +25,7 @@ pub struct Params {
     pub brief: bool,
     pub expand_tabs: bool,
     pub tabsize: usize,
+    pub width: usize,
 }
 
 impl Default for Params {
@@ -38,6 +40,7 @@ impl Default for Params {
             brief: false,
             expand_tabs: false,
             tabsize: 8,
+            width: 130,
         }
     }
 }
@@ -57,6 +60,7 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
     let mut format = None;
     let mut context = None;
     let tabsize_re = Regex::new(r"^--tabsize=(?<num>\d+)$").unwrap();
+    let width_re = Regex::new(r"--width=(?P<long>\d+)$").unwrap();
     while let Some(param) = opts.next() {
         let next_param = opts.peek();
         if param == "--" {
@@ -101,6 +105,34 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
             format = Some(Format::Ed);
             continue;
         }
+        if param == "-y" || param == "--side-by-side" {
+            if format.is_some() && format != Some(Format::SideBySide) {
+                return Err("Conflicting output style option".to_string());
+            }
+            format = Some(Format::SideBySide);
+            continue;
+        }
+        if width_re.is_match(param.to_string_lossy().as_ref()) {
+            let param = param.into_string().unwrap();
+            let width_str: &str = width_re
+                .captures(param.as_str())
+                .unwrap()
+                .name("long")
+                .unwrap()
+                .as_str();
+
+            params.width = match width_str.parse::<usize>() {
+                Ok(num) => {
+                    if num == 0 {
+                        return Err("invalid width «0»".to_string());
+                    }
+
+                    num
+                }
+                Err(_) => return Err(format!("invalid width «{width_str}»")),
+            };
+            continue;
+        }
         if tabsize_re.is_match(param.to_string_lossy().as_ref()) {
             // Because param matches the regular expression,
             // it is safe to assume it is valid UTF-8.
@@ -112,9 +144,16 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
                 .unwrap()
                 .as_str();
             params.tabsize = match tabsize_str.parse::<usize>() {
-                Ok(num) => num,
+                Ok(num) => {
+                    if num == 0 {
+                        return Err("invalid tabsize «0»".to_string());
+                    }
+
+                    num
+                }
                 Err(_) => return Err(format!("invalid tabsize «{tabsize_str}»")),
             };
+
             continue;
         }
         match match_context_diff_params(&param, next_param, format) {
@@ -156,7 +195,7 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
             Err(error) => return Err(error),
         }
         if param.to_string_lossy().starts_with('-') {
-            return Err(format!("Unknown option: {:?}", param));
+            return Err(format!("unrecognized option: {param:?}"));
         }
         if from.is_none() {
             from = Some(param);
@@ -240,17 +279,15 @@ fn match_context_diff_params(
                 context_count = Some(numvalue.as_str().parse::<usize>().unwrap());
             }
         }
-        if param == "-C" && next_param.is_some() {
-            match next_param.unwrap().to_string_lossy().parse::<usize>() {
-                Ok(context_size) => {
-                    context_count = Some(context_size);
-                    next_param_consumed = true;
-                }
-                Err(_) => {
-                    return Err(format!(
-                        "invalid context length '{}'",
-                        next_param.unwrap().to_string_lossy()
-                    ))
+        if param == "-C" {
+            if let Some(p) = next_param {
+                let size_str = p.to_string_lossy();
+                match size_str.parse::<usize>() {
+                    Ok(context_size) => {
+                        context_count = Some(context_size);
+                        next_param_consumed = true;
+                    }
+                    Err(_) => return Err(format!("invalid context length '{size_str}'")),
                 }
             }
         }
@@ -286,17 +323,15 @@ fn match_unified_diff_params(
                 context_count = Some(numvalue.as_str().parse::<usize>().unwrap());
             }
         }
-        if param == "-U" && next_param.is_some() {
-            match next_param.unwrap().to_string_lossy().parse::<usize>() {
-                Ok(context_size) => {
-                    context_count = Some(context_size);
-                    next_param_consumed = true;
-                }
-                Err(_) => {
-                    return Err(format!(
-                        "invalid context length '{}'",
-                        next_param.unwrap().to_string_lossy()
-                    ))
+        if param == "-U" {
+            if let Some(p) = next_param {
+                let size_str = p.to_string_lossy();
+                match size_str.parse::<usize>() {
+                    Ok(context_size) => {
+                        context_count = Some(context_size);
+                        next_param_consumed = true;
+                    }
+                    Err(_) => return Err(format!("invalid context length '{size_str}'")),
                 }
             }
         }
@@ -704,11 +739,11 @@ mod tests {
                 executable: os("diff"),
                 from: os("foo"),
                 to: os("bar"),
-                tabsize: 0,
+                tabsize: 1,
                 ..Default::default()
             }),
             parse_params(
-                [os("diff"), os("--tabsize=0"), os("foo"), os("bar")]
+                [os("diff"), os("--tabsize=1"), os("foo"), os("bar")]
                     .iter()
                     .cloned()
                     .peekable()

src/utils.rs

@@ -3,9 +3,8 @@
 // For the full copyright and license information, please view the LICENSE-*
 // files that was distributed with this source code.
 
-use std::{ffi::OsString, io::Write};
-
 use regex::Regex;
+use std::{ffi::OsString, io::Write};
 use unicode_width::UnicodeWidthStr;
 
 /// Replace tabs by spaces in the input line.

tests/integration.rs

@@ -3,9 +3,11 @@
 // For the full copyright and license information, please view the LICENSE-*
 // files that was distributed with this source code.
 
-use assert_cmd::cmd::Command;
+use assert_cmd::cargo::cargo_bin_cmd;
 use predicates::prelude::*;
-use std::fs::{File, OpenOptions};
+use std::fs::File;
+#[cfg(not(windows))]
+use std::fs::OpenOptions;
 use std::io::Write;
 use tempfile::{tempdir, NamedTempFile};
 
@@ -15,14 +17,14 @@ mod common {
 
     #[test]
     fn unknown_param() -> Result<(), Box<dyn std::error::Error>> {
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("patch");
         cmd.assert()
             .code(predicate::eq(2))
             .failure()
             .stderr(predicate::eq("patch: utility not supported\n"));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.assert()
             .code(predicate::eq(0))
             .success()
@@ -31,13 +33,15 @@ mod common {
             ));
 
         for subcmd in ["diff", "cmp"] {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg(subcmd);
             cmd.arg("--foobar");
             cmd.assert()
                 .code(predicate::eq(2))
                 .failure()
-                .stderr(predicate::str::starts_with("Unknown option: \"--foobar\""));
+                .stderr(predicate::str::starts_with(
+                    "unrecognized option: \"--foobar\"",
+                ));
         }
         Ok(())
     }
@@ -56,7 +60,7 @@ mod common {
         let error_message = "The system cannot find the file specified.";
 
         for subcmd in ["diff", "cmp"] {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg(subcmd);
             cmd.arg(&nopath).arg(file.path());
             cmd.assert()
@@ -67,7 +71,7 @@ mod common {
                     &nopath.as_os_str().to_string_lossy()
                 )));
 
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg(subcmd);
             cmd.arg(file.path()).arg(&nopath);
             cmd.assert()
@@ -79,7 +83,7 @@ mod common {
                 )));
         }
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("diff");
         cmd.arg(&nopath).arg(&nopath);
         cmd.assert().code(predicate::eq(2)).failure().stderr(
@@ -103,7 +107,7 @@ mod diff {
     fn no_differences() -> Result<(), Box<dyn std::error::Error>> {
         let file = NamedTempFile::new()?;
         for option in ["", "-u", "-c", "-e"] {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg("diff");
             if !option.is_empty() {
                 cmd.arg(option);
@@ -123,7 +127,7 @@ mod diff {
         let mut file1 = NamedTempFile::new()?;
         file1.write_all("foo\n".as_bytes())?;
         for option in ["", "-u", "-c", "-e"] {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg("diff");
             if !option.is_empty() {
                 cmd.arg(option);
@@ -142,7 +146,7 @@ mod diff {
         let mut file2 = NamedTempFile::new()?;
         file2.write_all("foo\n".as_bytes())?;
         for option in ["", "-u", "-c", "-e"] {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg("diff");
             if !option.is_empty() {
                 cmd.arg(option);
@@ -167,7 +171,7 @@ mod diff {
         let mut file2 = NamedTempFile::new()?;
         file2.write_all("bar\n".as_bytes())?;
         for option in ["", "-u", "-c", "-e"] {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg("diff");
             if !option.is_empty() {
                 cmd.arg(option);
@@ -188,7 +192,7 @@ mod diff {
         let mut file2 = NamedTempFile::new()?;
         file2.write_all("bar\n".as_bytes())?;
         for option in ["", "-u", "-c", "-e"] {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg("diff");
             if !option.is_empty() {
                 cmd.arg(option);
@@ -212,7 +216,7 @@ mod diff {
         file1.write_all("foo".as_bytes())?;
         let mut file2 = NamedTempFile::new()?;
         file2.write_all("bar".as_bytes())?;
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("diff");
         cmd.arg("-e").arg(file1.path()).arg(file2.path());
         cmd.assert()
@@ -229,7 +233,7 @@ mod diff {
         let mut file2 = NamedTempFile::new()?;
         file2.write_all("bar\n".as_bytes())?;
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("diff");
         cmd.arg("-u")
             .arg(file1.path())
@@ -246,7 +250,7 @@ mod diff {
             )
         );
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("diff");
         cmd.arg("-u")
             .arg("-")
@@ -263,7 +267,7 @@ mod diff {
             )
         );
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("diff");
         cmd.arg("-u").arg("-").arg("-");
         cmd.assert()
@@ -273,7 +277,7 @@ mod diff {
 
         #[cfg(unix)]
         {
-            let mut cmd = Command::cargo_bin("diffutils")?;
+            let mut cmd = cargo_bin_cmd!("diffutils");
             cmd.arg("diff");
             cmd.arg("-u")
                 .arg(file1.path())
@@ -309,7 +313,7 @@ mod diff {
         let mut da = File::create(&da_path).unwrap();
         da.write_all(b"da\n").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("diff");
         cmd.arg("-u").arg(&directory).arg(&a_path);
         cmd.assert().code(predicate::eq(1)).failure();
@@ -324,7 +328,7 @@ mod diff {
             )
         );
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("diff");
         cmd.arg("-u").arg(&a_path).arg(&directory);
         cmd.assert().code(predicate::eq(1)).failure();
@@ -348,7 +352,7 @@ mod cmp {
 
     #[test]
     fn cmp_incompatible_params() -> Result<(), Box<dyn std::error::Error>> {
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-l");
         cmd.arg("-s");
@@ -371,7 +375,7 @@ mod cmp {
         let mut a = File::create(&a_path).unwrap();
         a.write_all(b"a\n").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg(&a_path);
         cmd.write_stdin("a\n");
@@ -381,7 +385,7 @@ mod cmp {
             .stderr(predicate::str::is_empty())
             .stdout(predicate::str::is_empty());
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg(&a_path);
@@ -407,7 +411,7 @@ mod cmp {
         let mut b = File::create(&b_path).unwrap();
         b.write_all(b"a\n").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg(&a_path).arg(&b_path);
         cmd.assert()
@@ -430,7 +434,7 @@ mod cmp {
         let b_path = tmp_dir.path().join("b");
         let _ = File::create(&b_path).unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg(&a_path).arg(&b_path);
         cmd.assert()
@@ -454,7 +458,7 @@ mod cmp {
         let mut b = File::create(&b_path).unwrap();
         b.write_all(b"bcd\n").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg(&a_path).arg(&b_path);
@@ -463,7 +467,7 @@ mod cmp {
             .failure()
             .stdout(predicate::str::ends_with(" differ: char 1, line 1\n"));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-b");
@@ -476,7 +480,7 @@ mod cmp {
                 " differ: byte 1, line 1 is 141 a 142 b\n",
             ));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-l");
@@ -487,7 +491,7 @@ mod cmp {
             .stderr(predicate::str::is_empty())
             .stdout(predicate::eq("1 141 142\n2 142 143\n3 143 144\n"));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-l");
@@ -516,7 +520,7 @@ mod cmp {
         let mut b = File::create(&b_path).unwrap();
         b.write_all(b"abc\ndef\ng").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg(&a_path).arg(&b_path);
@@ -526,7 +530,7 @@ mod cmp {
             .stderr(predicate::str::is_empty())
             .stdout(predicate::str::ends_with(" differ: char 8, line 2\n"));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-b");
@@ -539,7 +543,7 @@ mod cmp {
                 " differ: byte 8, line 2 is 147 g  12 ^J\n",
             ));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-l");
@@ -551,7 +555,7 @@ mod cmp {
             .stderr(predicate::str::contains(" EOF on"))
             .stderr(predicate::str::ends_with(" after byte 8\n"));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-b");
@@ -579,7 +583,7 @@ mod cmp {
         let mut b = File::create(&b_path).unwrap();
         b.write_all(b"abcdefghijkl\n").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-l");
         cmd.arg("-b");
@@ -592,7 +596,7 @@ mod cmp {
             .stderr(predicate::str::is_empty())
             .stdout(predicate::str::is_empty());
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-l");
         cmd.arg("-b");
@@ -605,7 +609,7 @@ mod cmp {
             .stderr(predicate::str::is_empty())
             .stdout(predicate::eq("4  40      144 d\n"));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-l");
         cmd.arg("-b");
@@ -616,7 +620,7 @@ mod cmp {
             .code(predicate::eq(1))
             .failure()
             .stderr(predicate::str::is_empty())
-            .stdout(predicate::eq("4  40      144 d\n8  40      150 h\n"));
+            .stdout(predicate::eq(" 4  40      144 d\n 8  40      150 h\n"));
         Ok(())
     }
 
@@ -632,7 +636,7 @@ mod cmp {
         let mut b = File::create(&b_path).unwrap();
         b.write_all(b"###abc\n").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-i");
@@ -645,7 +649,7 @@ mod cmp {
             .stdout(predicate::str::is_empty());
 
         // Positional skips should be ignored
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg("-i");
@@ -659,7 +663,7 @@ mod cmp {
             .stdout(predicate::str::is_empty());
 
         // Single positional argument should only affect first file.
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg(&a_path).arg(&b_path);
@@ -670,7 +674,7 @@ mod cmp {
             .stderr(predicate::str::is_empty())
             .stdout(predicate::str::ends_with(" differ: char 1, line 1\n"));
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.env("LC_ALL", "C");
         cmd.arg("cmp");
         cmd.arg(&a_path).arg(&b_path);
@@ -691,15 +695,15 @@ mod cmp {
 
         let a_path = tmp_dir.path().join("a");
         let mut a = File::create(&a_path).unwrap();
-        write!(a, "{}c\n", "a".repeat(1024)).unwrap();
+        writeln!(a, "{}c", "a".repeat(1024)).unwrap();
         a.flush().unwrap();
 
         let b_path = tmp_dir.path().join("b");
         let mut b = File::create(&b_path).unwrap();
-        write!(b, "{}c\n", "b".repeat(1024)).unwrap();
+        writeln!(b, "{}c", "b".repeat(1024)).unwrap();
         b.flush().unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("--ignore-initial=1K");
         cmd.arg(&a_path).arg(&b_path);
@@ -724,7 +728,7 @@ mod cmp {
         let mut b = File::create(&b_path).unwrap();
         b.write_all(b"abcdefghijkl\n").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-l");
         cmd.arg("-b");
@@ -737,7 +741,7 @@ mod cmp {
             .stderr(predicate::str::is_empty())
             .stdout(predicate::str::is_empty());
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-b");
         cmd.arg("-i");
@@ -770,7 +774,7 @@ mod cmp {
         let mut b = File::create(&b_path).unwrap();
         b.write_all(&bytes).unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-l");
         cmd.arg("-b");
@@ -815,7 +819,7 @@ mod cmp {
 
         let dev_null = OpenOptions::new().write(true).open("/dev/null").unwrap();
 
-        let mut child = std::process::Command::new(assert_cmd::cargo::cargo_bin("diffutils"))
+        let mut child = std::process::Command::new(assert_cmd::cargo::cargo_bin!("diffutils"))
             .arg("cmp")
             .arg(&a_path)
             .arg(&b_path)
@@ -823,12 +827,27 @@ mod cmp {
             .spawn()
             .unwrap();
 
-        std::thread::sleep(std::time::Duration::from_millis(100));
-
-        assert_eq!(child.try_wait().unwrap().unwrap().code(), Some(1));
+        // Bound the runtime to a very short time that still allows for some resource
+        // constraint to slow it down while also allowing very fast systems to exit as
+        // early as possible.
+        const MAX_TRIES: u8 = 50;
+        for tries in 0..=MAX_TRIES {
+            if tries == MAX_TRIES {
+                panic!("cmp took too long to run, /dev/null optimization probably not working")
+            }
+            match child.try_wait() {
+                Ok(Some(status)) => {
+                    assert_eq!(status.code(), Some(1));
+                    break;
+                }
+                Ok(None) => (),
+                Err(e) => panic!("{e:#?}"),
+            }
+            std::thread::sleep(std::time::Duration::from_millis(10));
+        }
 
         // Two stdins should be equal
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg("-");
         cmd.arg("-");
@@ -851,17 +870,18 @@ mod cmp {
 
         let a_path = tmp_dir.path().join("a");
         let mut a = File::create(&a_path).unwrap();
-        a.write_all(&bytes).unwrap();
+        a.write_all(bytes).unwrap();
         a.write_all(b"A").unwrap();
 
         let b_path = tmp_dir.path().join("b");
         let mut b = File::create(&b_path).unwrap();
-        b.write_all(&bytes).unwrap();
+        b.write_all(bytes).unwrap();
         b.write_all(b"B").unwrap();
 
-        let mut cmd = Command::cargo_bin("diffutils")?;
+        let mut cmd = cargo_bin_cmd!("diffutils");
         cmd.arg("cmp");
         cmd.arg(&a_path).arg(&b_path);
+        cmd.env("LC_ALL", "en_US");
         cmd.assert()
             .code(predicate::eq(1))
             .failure()