version 0.4.1

Handle directory-file and file-directory comparisons in the diff

.github/workflows/ci.yml

@@ -0,0 +1,161 @@
+on: [push, pull_request]
+
+name: Basic CI
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  check:
+    name: cargo check
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macOS-latest, windows-latest]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+      - run: cargo check
+
+  test:
+    name: cargo test
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macOS-latest, windows-latest]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+      - 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
+      - run: cargo test
+
+  fmt:
+    name: cargo fmt --all -- --check
+    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:
+    name: cargo clippy -- -D warnings
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        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:
+    name: GNU test suite
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+      - run: cargo build --release
+      # do not fail, the report is merely informative (at least until all tests pass reliably)
+      - run: ./tests/run-upstream-testsuite.sh release || true
+        env:
+          TERM: xterm
+      - uses: actions/upload-artifact@v4
+        with:
+          name: test-results.json
+          path: tests/test-results.json
+      - run: ./tests/print-test-results.sh tests/test-results.json
+
+  coverage:
+    name: Code Coverage
+    runs-on: ${{ matrix.job.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        job:
+          - { os: ubuntu-latest  , features: unix }
+          - { os: macos-latest   , features: macos }
+          - { os: windows-latest , features: windows }
+    steps:
+    - uses: actions/checkout@v4
+    - name: Initialize workflow variables
+      id: vars
+      shell: bash
+      run: |
+        ## VARs setup
+        outputs() { step_id="vars"; for var in "$@" ; 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
+    - 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 ${{ steps.vars.outputs.CARGO_FEATURES_OPTION }} --no-fail-fast
+      env:
+        CARGO_INCREMENTAL: "0"
+        RUSTC_WRAPPER: ""
+        RUSTFLAGS: "-Zprofile -Ccodegen-units=1 -Copt-level=0 -Clink-dead-code -Coverflow-checks=off -Zpanic_abort_tests -Cpanic=abort"
+        RUSTDOCFLAGS: "-Cpanic=abort"
+    - name: "`grcov` ~ install"
+      id: build_grcov
+      shell: bash
+      run: |
+        git clone https://github.com/mozilla/grcov.git ~/grcov/
+        cd ~/grcov
+        # Hardcode the version of crossbeam-epoch. See
+        # https://github.com/uutils/coreutils/issues/3680
+        sed -i -e "s|tempfile =|crossbeam-epoch = \"=0.9.8\"\ntempfile =|" Cargo.toml
+        cargo install --path .
+        cd -
+# Uncomment when the upstream issue
+# https://github.com/mozilla/grcov/issues/849 is fixed
+#      uses: actions-rs/install@v0.1
+#      with:
+#        crate: grcov
+#        version: latest
+#        use-tool-cache: false
+    - name: Generate coverage data (via `grcov`)
+      id: coverage
+      shell: bash
+      run: |
+        ## Generate coverage data
+        COVERAGE_REPORT_DIR="target/debug"
+        COVERAGE_REPORT_FILE="${COVERAGE_REPORT_DIR}/lcov.info"
+        mkdir -p "${COVERAGE_REPORT_DIR}"
+        # display coverage files
+        grcov . --output-type files --ignore build.rs --ignore "vendor/*" --ignore "/*" --ignore "[a-zA-Z]:/*" --excl-br-line "^\s*((debug_)?assert(_eq|_ne)?!|#\[derive\()" | sort --unique
+        # generate coverage report
+        grcov . --output-type lcov --output-path "${COVERAGE_REPORT_FILE}" --branch --ignore build.rs --ignore "vendor/*" --ignore "/*" --ignore "[a-zA-Z]:/*" --excl-br-line "^\s*((debug_)?assert(_eq|_ne)?!|#\[derive\()"
+        echo "report=${COVERAGE_REPORT_FILE}" >> $GITHUB_OUTPUT
+    - name: Upload coverage results (to Codecov.io)
+      uses: codecov/codecov-action@v4
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}
+        file: ${{ steps.coverage.outputs.report }}
+        ## flags: IntegrationTests, UnitTests, ${{ steps.vars.outputs.CODECOV_FLAGS }}
+        flags: ${{ steps.vars.outputs.CODECOV_FLAGS }}
+        name: codecov-umbrella
+        fail_ci_if_error: false
+

.github/workflows/fuzzing.yml

@@ -0,0 +1,72 @@
+name: Fuzzing
+
+# spell-checker:ignore fuzzer
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+jobs:
+  fuzz-build:
+    name: Build the fuzzers
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@nightly
+      - name: Install `cargo-fuzz`
+        run: cargo install cargo-fuzz
+      - uses: Swatinem/rust-cache@v2
+        with:
+          shared-key: "cargo-fuzz-cache-key"
+          cache-directories: "fuzz/target"
+      - name: Run `cargo-fuzz build`
+        run: cargo +nightly fuzz build
+
+  fuzz-run:
+    needs: fuzz-build
+    name: Run the fuzzers
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    env:
+      RUN_FOR: 60
+    strategy:
+      matrix:
+        test-target:
+          - { name: fuzz_ed, should_pass: true }
+          - { name: fuzz_normal, should_pass: true }
+          - { name: fuzz_patch, should_pass: true }
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@nightly
+      - name: Install `cargo-fuzz`
+        run: cargo install cargo-fuzz
+      - uses: Swatinem/rust-cache@v2
+        with:
+          shared-key: "cargo-fuzz-cache-key"
+          cache-directories: "fuzz/target"
+      - name: Restore Cached Corpus
+        uses: actions/cache/restore@v4
+        with:
+          key: corpus-cache-${{ matrix.test-target.name }}
+          path: |
+            fuzz/corpus/${{ matrix.test-target.name }}
+      - name: Run ${{ matrix.test-target.name }} for XX seconds
+        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
+      - name: Save Corpus Cache
+        uses: actions/cache/save@v4
+        with:
+          key: corpus-cache-${{ matrix.test-target.name }}
+          path: |
+            fuzz/corpus/${{ matrix.test-target.name }}

.github/workflows/release.yml

@@ -0,0 +1,266 @@
+# Copyright 2022-2023, 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)
+# * uploads those artifacts to temporary workflow zip
+# * on success, uploads the artifacts to a Github Release
+#
+# Note that the Github Release will be created with a generated
+# title/body based on your changelogs.
+
+name: Release
+
+permissions:
+  contents: write
+
+# This task will run whenever you push a git tag that looks like a version
+# like "1.0.0", "v0.1.0-prerelease.1", "my-app/0.1.0", "releases/v1.0.0", etc.
+# Various formats will be parsed into a VERSION and an optional PACKAGE_NAME, where
+# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION
+# must be a Cargo-style SemVer Version (must have at least major.minor.patch).
+#
+# If PACKAGE_NAME is specified, then the announcement will be for that
+# package (erroring out if it doesn't have the given version or isn't cargo-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
+# intended for workspaces with only one dist-able package, or with all dist-able
+# packages versioned/released in lockstep).
+#
+# If you push multiple tags at once, separate instances of this workflow will
+# spin up, creating an independent announcement for each one. However Github
+# will hard limit this to 3 tags per commit, as it will assume more tags is a
+# mistake.
+#
+# If there's a prerelease-style suffix to the version, then the release(s)
+# will be marked as a prerelease.
+on:
+  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
+  plan:
+    runs-on: ubuntu-latest
+    outputs:
+      val: ${{ steps.plan.outputs.manifest }}
+      tag: ${{ !github.event.pull_request && github.ref_name || '' }}
+      tag-flag: ${{ !github.event.pull_request && format('--tag={0}', github.ref_name) || '' }}
+      publishing: ${{ !github.event.pull_request }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+      - name: Install cargo-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/v0.12.0/cargo-dist-installer.sh | sh"
+      # sure would be cool if github gave us proper conditionals...
+      # so here's a doubly-nested ternary-via-truthiness to try to provide the best possible
+      # functionality based on whether this is a pull_request, and whether it's from a fork.
+      # (PRs run on the *source* but secrets are usually on the *target* -- that's *good*
+      # but also really annoying to build CI around when it needs secrets to work right.)
+      - id: plan
+        run: |
+          cargo dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json
+          echo "cargo dist ran successfully"
+          cat plan-dist-manifest.json
+          echo "manifest=$(jq -c "." plan-dist-manifest.json)" >> "$GITHUB_OUTPUT"
+      - name: "Upload dist-manifest.json"
+        uses: actions/upload-artifact@v4
+        with:
+          name: artifacts-plan-dist-manifest
+          path: plan-dist-manifest.json
+
+  # Build and packages all the platform-specific things
+  build-local-artifacts:
+    name: build-local-artifacts (${{ join(matrix.targets, ', ') }})
+    # Let the initial task tell us to not run (currently very blunt)
+    needs:
+      - plan
+    if: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix.include != null && (needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload') }}
+    strategy:
+      fail-fast: false
+      # Target platforms/runners are computed by cargo-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
+      #
+      # 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 }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      BUILD_MANIFEST_NAME: target/distrib/${{ join(matrix.targets, '-') }}-dist-manifest.json
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+      - uses: swatinem/rust-cache@v2
+      - name: Install cargo-dist
+        run: ${{ matrix.install_dist }}
+      # Get the dist-manifest
+      - name: Fetch local artifacts
+        uses: actions/download-artifact@v4
+        with:
+          pattern: artifacts-*
+          path: target/distrib/
+          merge-multiple: true
+      - name: Install dependencies
+        run: |
+          ${{ matrix.packages_install }}
+      - name: Build artifacts
+        run: |
+          # Actually do builds and make zips and whatnot
+          cargo dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
+          echo "cargo dist ran successfully"
+      - id: cargo-dist
+        name: Post-build
+        # We force bash here just because github makes it really hard to get values up
+        # to "real" actions without writing to env-vars, and writing to env-vars has
+        # inconsistent syntax between shell and powershell.
+        shell: bash
+        run: |
+          # Parse out what we just built and upload it to scratch storage
+          echo "paths<<EOF" >> "$GITHUB_OUTPUT"
+          jq --raw-output ".artifacts[]?.path | select( . != null )" dist-manifest.json >> "$GITHUB_OUTPUT"
+          echo "EOF" >> "$GITHUB_OUTPUT"
+
+          cp dist-manifest.json "$BUILD_MANIFEST_NAME"
+      - name: "Upload artifacts"
+        uses: actions/upload-artifact@v4
+        with:
+          name: artifacts-build-local-${{ join(matrix.targets, '_') }}
+          path: |
+            ${{ steps.cargo-dist.outputs.paths }}
+            ${{ env.BUILD_MANIFEST_NAME }}
+
+  # Build and package all the platform-agnostic(ish) things
+  build-global-artifacts:
+    needs:
+      - plan
+      - build-local-artifacts
+    runs-on: "ubuntu-20.04"
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      BUILD_MANIFEST_NAME: target/distrib/global-dist-manifest.json
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+      - name: Install cargo-dist
+        shell: bash
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.12.0/cargo-dist-installer.sh | sh"
+      # Get all the local artifacts for the global tasks to use (for e.g. checksums)
+      - name: Fetch local artifacts
+        uses: actions/download-artifact@v4
+        with:
+          pattern: artifacts-*
+          path: target/distrib/
+          merge-multiple: true
+      - id: cargo-dist
+        shell: bash
+        run: |
+          cargo dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json
+          echo "cargo dist ran successfully"
+
+          # Parse out what we just built and upload it to scratch storage
+          echo "paths<<EOF" >> "$GITHUB_OUTPUT"
+          jq --raw-output ".artifacts[]?.path | select( . != null )" dist-manifest.json >> "$GITHUB_OUTPUT"
+          echo "EOF" >> "$GITHUB_OUTPUT"
+
+          cp dist-manifest.json "$BUILD_MANIFEST_NAME"
+      - name: "Upload artifacts"
+        uses: actions/upload-artifact@v4
+        with:
+          name: artifacts-build-global
+          path: |
+            ${{ steps.cargo-dist.outputs.paths }}
+            ${{ env.BUILD_MANIFEST_NAME }}
+  # Determines if we should publish/announce
+  host:
+    needs:
+      - plan
+      - build-local-artifacts
+      - build-global-artifacts
+    # Only run if we're "publishing", and only if local and global didn't fail (skipped is fine)
+    if: ${{ always() && needs.plan.outputs.publishing == 'true' && (needs.build-global-artifacts.result == 'skipped' || needs.build-global-artifacts.result == 'success') && (needs.build-local-artifacts.result == 'skipped' || needs.build-local-artifacts.result == 'success') }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    runs-on: "ubuntu-20.04"
+    outputs:
+      val: ${{ steps.host.outputs.manifest }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+      - name: Install cargo-dist
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.12.0/cargo-dist-installer.sh | sh"
+      # Fetch artifacts from scratch-storage
+      - name: Fetch artifacts
+        uses: actions/download-artifact@v4
+        with:
+          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 ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json
+          echo "artifacts uploaded and released successfully"
+          cat dist-manifest.json
+          echo "manifest=$(jq -c "." dist-manifest.json)" >> "$GITHUB_OUTPUT"
+      - name: "Upload dist-manifest.json"
+        uses: actions/upload-artifact@v4
+        with:
+          # 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
+      - name: "Download Github Artifacts"
+        uses: actions/download-artifact@v4
+        with:
+          pattern: artifacts-*
+          path: artifacts
+          merge-multiple: true
+      - name: Cleanup
+        run: |
+          # Remove the granular manifests
+          rm -f artifacts/*-dist-manifest.json
+      - name: Create Github Release
+        uses: ncipollo/release-action@v1
+        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/*"

.gitignore

@@ -1,3 +1,2 @@
 /target
-Cargo.lock
 *.swp

Cargo.toml

@@ -1,18 +1,46 @@
 [package]
-name = "unified-diff"
-version = "0.2.1"
-authors = [
-    "Michael Howell <michael@notriddle.com>",
-    "The Rust Project Developers"
-]
-edition = "2018"
-description = "An implementation of the GNU unified diff format"
+name = "diffutils"
+version = "0.4.1"
+edition = "2021"
+description = "A CLI app for generating diff files"
 license = "MIT OR Apache-2.0"
-repository = "https://github.com/notriddle/rust-unified-diff"
-exclude = [ "fuzz" ]
+repository = "https://github.com/uutils/diffutils"
+
+[lib]
+name = "diffutilslib"
+path = "src/lib.rs"
 
 [[bin]]
-name = "unified-diff"
+name = "diffutils"
+path = "src/main.rs"
 
 [dependencies]
-diff = "0.1.10"
+chrono = "0.4.38"
+diff = "0.1.13"
+regex = "1.10.4"
+same-file = "1.0.6"
+unicode-width = "0.1.11"
+
+[dev-dependencies]
+pretty_assertions = "1"
+assert_cmd = "2.0.14"
+predicates = "3.1.0"
+tempfile = "3.10.1"
+
+# The profile that 'cargo 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 = "0.12.0"
+# 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"

LICENSE-APACHE

@@ -1,3 +1,6 @@
+Copyright (c) Michael Howell
+Copyright (c) uutils developers
+
                               Apache License
                         Version 2.0, January 2004
                      http://www.apache.org/licenses/

LICENSE-MIT

@@ -1,3 +1,6 @@
+Copyright (c) Michael Howell
+Copyright (c) uutils developers
+
 Permission is hereby granted, free of charge, to any
 person obtaining a copy of this software and associated
 documentation files (the "Software"), to deal in the

README.md

@@ -1,41 +1,56 @@
-A GNU unified diff generator. Oracle tested against GNU patch 2.7.6
+[![Crates.io](https://img.shields.io/crates/v/diffutils.svg)](https://crates.io/crates/diffutils)
+[![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)
 
-Based on the incomplete diff generator in https://github.com/rust-lang/rust/blob/master/src/tools/compiletest/src/runtest.rs,
-but it implements a different format.
+[![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.
+
+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.
+
+
+## Installation
+
+Ensure you have Rust installed on your system. You can install Rust through [rustup](https://rustup.rs/).
+
+Clone the repository and build the project using Cargo:
+
+```bash
+git clone https://github.com/uutils/diffutils.git
+cd diffutils
+cargo build --release
 ```
-~/unified-diff$ cargo run Cargo.lock Cargo.toml 
+
+## Example
+
+```bash
+
+cat <<EOF >fruits_old.txt
+Apple
+Banana
+Cherry
+EOF
+
+cat <<EOF >fruits_new.txt
+Apple
+Fig
+Cherry
+EOF
+
+$ cargo run -- -u fruits_old.txt fruits_new.txt
     Finished dev [unoptimized + debuginfo] target(s) in 0.00s
-     Running `target/debug/unified-diff Cargo.lock Cargo.toml`
---- Cargo.lock	
-+++ Cargo.toml	
-@@ -1,14 +1,14 @@
--# This file is automatically @generated by Cargo.
--# It is not intended for manual editing.
--[[package]]
--name = "diff"
--version = "0.1.12"
--source = "registry+https://github.com/rust-lang/crates.io-index"
--checksum = "0e25ea47919b1560c4e3b7fe0aaab9becf5b84a10325ddf7db0f0ba5e1026499"
--
--[[package]]
-+[package]
- name = "unified-diff"
- version = "0.1.0"
--dependencies = [
-- "diff",
-+authors = [
-+    "Michael Howell <michael@notriddle.com>",
-+    "The Rust Project Developers"
- ]
-+edition = "2018"
-+
-+[[bin]]
-+name = "unified-diff"
-+
-+[dependencies]
-+diff = "0.1.10"
-~/unified-diff$ rustup override set nightly
-~/unified-diff$ cargo fuzz run fuzz_patch
+     Running `target/debug/diffutils -u fruits_old.txt fruits_new.txt`
+--- fruits_old.txt
++++ fruits_new.txt
+@@ -1,3 +1,3 @@
+ Apple
+-Banana
++Fig
+ Cherry
+
 ```
 
+## License
+
+diffutils is licensed under the MIT and Apache Licenses - see the `LICENSE-MIT` or `LICENSE-APACHE` files for details

fuzz/Cargo.toml

@@ -2,7 +2,6 @@
 [package]
 name = "unified-diff-fuzz"
 version = "0.0.0"
-authors = ["Automatically generated"]
 publish = false
 edition = "2018"
 
@@ -10,10 +9,8 @@ edition = "2018"
 cargo-fuzz = true
 
 [dependencies]
-libfuzzer-sys = "0.3"
-
-[dependencies.unified-diff]
-path = ".."
+libfuzzer-sys = "0.4"
+diffutils = { path = "../" }
 
 # Prevent this from interfering with workspaces
 [workspace]
@@ -25,3 +22,17 @@ path = "fuzz_targets/fuzz_patch.rs"
 test = false
 doc = false
 
+[[bin]]
+name = "fuzz_normal"
+path = "fuzz_targets/fuzz_normal.rs"
+test = false
+doc = false
+
+
+[[bin]]
+name = "fuzz_ed"
+path = "fuzz_targets/fuzz_ed.rs"
+test = false
+doc = false
+
+

fuzz/fuzz_targets/fuzz_ed.rs

@@ -0,0 +1,78 @@
+#![no_main]
+#[macro_use]
+extern crate libfuzzer_sys;
+use diffutilslib::ed_diff;
+use diffutilslib::ed_diff::DiffError;
+use diffutilslib::params::Params;
+use std::fs::{self, File};
+use std::io::Write;
+use std::process::Command;
+
+fn diff_w(expected: &[u8], actual: &[u8], filename: &str) -> Result<Vec<u8>, DiffError> {
+    let mut output = ed_diff::diff(expected, actual, &Params::default())?;
+    writeln!(&mut output, "w {filename}").unwrap();
+    Ok(output)
+}
+
+fuzz_target!(|x: (Vec<u8>, Vec<u8>)| {
+    let (mut from, mut to) = x;
+    from.push(b'\n');
+    to.push(b'\n');
+    if let Ok(s) = String::from_utf8(from.clone()) {
+        if !s.is_ascii() {
+            return;
+        }
+        if s.find(|x| x < ' ' && x != '\n').is_some() {
+            return;
+        }
+    } else {
+        return;
+    }
+    if let Ok(s) = String::from_utf8(to.clone()) {
+        if !s.is_ascii() {
+            return;
+        }
+        if s.find(|x| x < ' ' && x != '\n').is_some() {
+            return;
+        }
+    } else {
+        return;
+    }
+    let diff = diff_w(&from, &to, "target/fuzz.file").unwrap();
+    File::create("target/fuzz.file.original")
+        .unwrap()
+        .write_all(&from)
+        .unwrap();
+    File::create("target/fuzz.file.expected")
+        .unwrap()
+        .write_all(&to)
+        .unwrap();
+    File::create("target/fuzz.file")
+        .unwrap()
+        .write_all(&from)
+        .unwrap();
+    File::create("target/fuzz.ed")
+        .unwrap()
+        .write_all(&diff)
+        .unwrap();
+    let output = Command::new("ed")
+        .arg("target/fuzz.file")
+        .stdin(File::open("target/fuzz.ed").unwrap())
+        .output()
+        .unwrap();
+    if !output.status.success() {
+        panic!(
+            "STDOUT:\n{}\nSTDERR:\n{}",
+            String::from_utf8_lossy(&output.stdout),
+            String::from_utf8_lossy(&output.stderr)
+        );
+    }
+    let result = fs::read("target/fuzz.file").unwrap();
+    if result != to {
+        panic!(
+            "STDOUT:\n{}\nSTDERR:\n{}",
+            String::from_utf8_lossy(&output.stdout),
+            String::from_utf8_lossy(&output.stderr)
+        );
+    }
+});

fuzz/fuzz_targets/fuzz_normal.rs

@@ -0,0 +1,66 @@
+#![no_main]
+#[macro_use]
+extern crate libfuzzer_sys;
+use diffutilslib::normal_diff;
+use diffutilslib::params::Params;
+
+use std::fs::{self, File};
+use std::io::Write;
+use std::process::Command;
+
+fuzz_target!(|x: (Vec<u8>, Vec<u8>)| {
+    let (from, to) = x;
+    /*if let Ok(s) = String::from_utf8(from.clone()) {
+        if !s.is_ascii() { return }
+        if s.find(|x| x < ' ' && x != '\n').is_some() { return }
+    } else {
+        return
+    }
+    if let Ok(s) = String::from_utf8(to.clone()) {
+        if !s.is_ascii() { return }
+        if s.find(|x| x < ' ' && x != '\n').is_some() { return }
+    } else {
+        return
+    }*/
+    let diff = normal_diff::diff(&from, &to, &Params::default());
+    File::create("target/fuzz.file.original")
+        .unwrap()
+        .write_all(&from)
+        .unwrap();
+    File::create("target/fuzz.file.expected")
+        .unwrap()
+        .write_all(&to)
+        .unwrap();
+    File::create("target/fuzz.file")
+        .unwrap()
+        .write_all(&from)
+        .unwrap();
+    File::create("target/fuzz.diff")
+        .unwrap()
+        .write_all(&diff)
+        .unwrap();
+    let output = Command::new("patch")
+        .arg("-p0")
+        .arg("--binary")
+        .arg("--fuzz=0")
+        .arg("--normal")
+        .arg("target/fuzz.file")
+        .stdin(File::open("target/fuzz.diff").unwrap())
+        .output()
+        .unwrap();
+    if !output.status.success() {
+        panic!(
+            "STDOUT:\n{}\nSTDERR:\n{}",
+            String::from_utf8_lossy(&output.stdout),
+            String::from_utf8_lossy(&output.stderr)
+        );
+    }
+    let result = fs::read("target/fuzz.file").unwrap();
+    if result != to {
+        panic!(
+            "STDOUT:\n{}\nSTDERR:\n{}",
+            String::from_utf8_lossy(&output.stdout),
+            String::from_utf8_lossy(&output.stderr)
+        );
+    }
+});

fuzz/fuzz_targets/fuzz_patch.rs

@@ -1,7 +1,8 @@
 #![no_main]
-#[macro_use] extern crate libfuzzer_sys;
-extern crate unified_diff;
-
+#[macro_use]
+extern crate libfuzzer_sys;
+use diffutilslib::params::Params;
+use diffutilslib::unified_diff;
 use std::fs::{self, File};
 use std::io::Write;
 use std::process::Command;
@@ -20,7 +21,16 @@ fuzz_target!(|x: (Vec<u8>, Vec<u8>, u8)| {
     } else {
         return
     }*/
-    let diff = unified_diff::diff(&from, "a/fuzz.file", &to, "target/fuzz.file", context as usize);
+    let diff = unified_diff::diff(
+        &from,
+        &to,
+        &Params {
+            from: "a/fuzz.file".into(),
+            to: "target/fuzz.file".into(),
+            context_count: context as usize,
+            ..Default::default()
+        }
+    );
     File::create("target/fuzz.file.original")
         .unwrap()
         .write_all(&from)
@@ -45,11 +55,18 @@ fuzz_target!(|x: (Vec<u8>, Vec<u8>, u8)| {
         .output()
         .unwrap();
     if !output.status.success() {
-        panic!("STDOUT:\n{}\nSTDERR:\n{}", String::from_utf8_lossy(&output.stdout), String::from_utf8_lossy(&output.stderr));
+        panic!(
+            "STDOUT:\n{}\nSTDERR:\n{}",
+            String::from_utf8_lossy(&output.stdout),
+            String::from_utf8_lossy(&output.stderr)
+        );
     }
     let result = fs::read("target/fuzz.file").unwrap();
     if result != to {
-        panic!("STDOUT:\n{}\nSTDERR:\n{}", String::from_utf8_lossy(&output.stdout), String::from_utf8_lossy(&output.stderr));
+        panic!(
+            "STDOUT:\n{}\nSTDERR:\n{}",
+            String::from_utf8_lossy(&output.stdout),
+            String::from_utf8_lossy(&output.stderr)
+        );
     }
 });
-

renovate.json

@@ -0,0 +1,6 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
+  "extends": [
+    "config:recommended"
+  ]
+}

src/ed_diff.rs

@@ -0,0 +1,449 @@
+// 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.
+
+use std::io::Write;
+
+use crate::params::Params;
+use crate::utils::do_write_line;
+
+#[derive(Debug, PartialEq)]
+struct Mismatch {
+    pub line_number_expected: usize,
+    pub line_number_actual: usize,
+    pub expected: Vec<Vec<u8>>,
+    pub actual: Vec<Vec<u8>>,
+}
+
+#[derive(Debug, PartialEq, Eq)]
+pub enum DiffError {
+    MissingNL,
+}
+
+impl std::fmt::Display for DiffError {
+    fn fmt(&self, f: &mut std::fmt::Formatter) -> Result<(), std::fmt::Error> {
+        std::fmt::Display::fmt("No newline at end of file", f)
+    }
+}
+
+impl From<DiffError> for String {
+    fn from(_: DiffError) -> String {
+        "No newline at end of file".into()
+    }
+}
+
+impl Mismatch {
+    fn new(line_number_expected: usize, line_number_actual: usize) -> Mismatch {
+        Mismatch {
+            line_number_expected,
+            line_number_actual,
+            expected: Vec::new(),
+            actual: Vec::new(),
+        }
+    }
+}
+
+// Produces a diff between the expected output and actual output.
+fn make_diff(expected: &[u8], actual: &[u8], stop_early: bool) -> Result<Vec<Mismatch>, DiffError> {
+    let mut line_number_expected = 1;
+    let mut line_number_actual = 1;
+    let mut results = Vec::new();
+    let mut mismatch = Mismatch::new(line_number_expected, line_number_actual);
+
+    let mut expected_lines: Vec<&[u8]> = expected.split(|&c| c == b'\n').collect();
+    let mut actual_lines: Vec<&[u8]> = actual.split(|&c| c == b'\n').collect();
+
+    debug_assert_eq!(b"".split(|&c| c == b'\n').count(), 1);
+    // ^ means that underflow here is impossible
+    let _expected_lines_count = expected_lines.len() - 1;
+    let _actual_lines_count = actual_lines.len() - 1;
+
+    if expected_lines.last() == Some(&&b""[..]) {
+        expected_lines.pop();
+    } else {
+        return Err(DiffError::MissingNL);
+    }
+
+    if actual_lines.last() == Some(&&b""[..]) {
+        actual_lines.pop();
+    } else {
+        return Err(DiffError::MissingNL);
+    }
+
+    for result in diff::slice(&expected_lines, &actual_lines) {
+        match result {
+            diff::Result::Left(str) => {
+                if !mismatch.actual.is_empty() {
+                    results.push(mismatch);
+                    mismatch = Mismatch::new(line_number_expected, line_number_actual);
+                }
+                mismatch.expected.push(str.to_vec());
+                line_number_expected += 1;
+            }
+            diff::Result::Right(str) => {
+                mismatch.actual.push(str.to_vec());
+                line_number_actual += 1;
+            }
+            diff::Result::Both(_str, _) => {
+                line_number_expected += 1;
+                line_number_actual += 1;
+                if !mismatch.actual.is_empty() || !mismatch.expected.is_empty() {
+                    results.push(mismatch);
+                    mismatch = Mismatch::new(line_number_expected, line_number_actual);
+                } else {
+                    mismatch.line_number_expected = line_number_expected;
+                    mismatch.line_number_actual = line_number_actual;
+                }
+            }
+        }
+        if stop_early && !results.is_empty() {
+            // Optimization: stop analyzing the files as soon as there are any differences
+            return Ok(results);
+        }
+    }
+
+    if !mismatch.actual.is_empty() || !mismatch.expected.is_empty() {
+        results.push(mismatch);
+    }
+
+    Ok(results)
+}
+
+pub fn diff(expected: &[u8], actual: &[u8], params: &Params) -> Result<Vec<u8>, DiffError> {
+    let mut output = Vec::new();
+    let diff_results = make_diff(expected, actual, params.brief)?;
+    if params.brief && !diff_results.is_empty() {
+        write!(&mut output, "\0").unwrap();
+        return Ok(output);
+    }
+    let mut lines_offset = 0;
+    for result in diff_results {
+        let line_number_expected: isize = result.line_number_expected as isize + lines_offset;
+        let _line_number_actual: isize = result.line_number_actual as isize + lines_offset;
+        let expected_count: isize = result.expected.len() as isize;
+        let actual_count: isize = result.actual.len() as isize;
+        match (expected_count, actual_count) {
+            (0, 0) => unreachable!(),
+            (0, _) => writeln!(&mut output, "{}a", line_number_expected - 1).unwrap(),
+            (_, 0) => writeln!(
+                &mut output,
+                "{},{}d",
+                line_number_expected,
+                expected_count + line_number_expected - 1
+            )
+            .unwrap(),
+            (1, _) => writeln!(&mut output, "{line_number_expected}c").unwrap(),
+            _ => writeln!(
+                &mut output,
+                "{},{}c",
+                line_number_expected,
+                expected_count + line_number_expected - 1
+            )
+            .unwrap(),
+        }
+        lines_offset += actual_count - expected_count;
+        if actual_count != 0 {
+            for actual in &result.actual {
+                if actual == b"." {
+                    writeln!(&mut output, "..\n.\ns/.//\na").unwrap();
+                } else {
+                    do_write_line(&mut output, actual, params.expand_tabs, params.tabsize).unwrap();
+                    writeln!(&mut output).unwrap();
+                }
+            }
+            writeln!(&mut output, ".").unwrap();
+        }
+    }
+    Ok(output)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use pretty_assertions::assert_eq;
+    pub fn diff_w(expected: &[u8], actual: &[u8], filename: &str) -> Result<Vec<u8>, DiffError> {
+        let mut output = diff(expected, actual, &Params::default())?;
+        writeln!(&mut output, "w {filename}").unwrap();
+        Ok(output)
+    }
+
+    #[test]
+    fn test_basic() {
+        let from = b"a\n";
+        let to = b"b\n";
+        let diff = diff(from, to, &Params::default()).unwrap();
+        let expected = ["1c", "b", ".", ""].join("\n");
+        assert_eq!(diff, expected.as_bytes());
+    }
+
+    #[test]
+    fn test_permutations() {
+        let target = "target/ed-diff/";
+        // test all possible six-line files.
+        let _ = std::fs::create_dir(target);
+        for &a in &[0, 1, 2] {
+            for &b in &[0, 1, 2] {
+                for &c in &[0, 1, 2] {
+                    for &d in &[0, 1, 2] {
+                        for &e in &[0, 1, 2] {
+                            for &f in &[0, 1, 2] {
+                                use std::fs::File;
+                                use std::io::Write;
+                                let mut alef = Vec::new();
+                                let mut bet = Vec::new();
+                                alef.write_all(if a == 0 { b"a\n" } else { b"b\n" })
+                                    .unwrap();
+                                if a != 2 {
+                                    bet.write_all(b"b\n").unwrap();
+                                }
+                                alef.write_all(if b == 0 { b"c\n" } else { b"d\n" })
+                                    .unwrap();
+                                if b != 2 {
+                                    bet.write_all(b"d\n").unwrap();
+                                }
+                                alef.write_all(if c == 0 { b"e\n" } else { b"f\n" })
+                                    .unwrap();
+                                if c != 2 {
+                                    bet.write_all(b"f\n").unwrap();
+                                }
+                                alef.write_all(if d == 0 { b"g\n" } else { b"h\n" })
+                                    .unwrap();
+                                if d != 2 {
+                                    bet.write_all(b"h\n").unwrap();
+                                }
+                                alef.write_all(if e == 0 { b"i\n" } else { b"j\n" })
+                                    .unwrap();
+                                if e != 2 {
+                                    bet.write_all(b"j\n").unwrap();
+                                }
+                                alef.write_all(if f == 0 { b"k\n" } else { b"l\n" })
+                                    .unwrap();
+                                if f != 2 {
+                                    bet.write_all(b"l\n").unwrap();
+                                }
+                                // This test diff is intentionally reversed.
+                                // We want it to turn the alef into bet.
+                                let diff = diff_w(&alef, &bet, &format!("{target}/alef")).unwrap();
+                                File::create(&format!("{target}/ab.ed"))
+                                    .unwrap()
+                                    .write_all(&diff)
+                                    .unwrap();
+                                let mut fa = File::create(&format!("{target}/alef")).unwrap();
+                                fa.write_all(&alef[..]).unwrap();
+                                let mut fb = File::create(&format!("{target}/bet")).unwrap();
+                                fb.write_all(&bet[..]).unwrap();
+                                let _ = fa;
+                                let _ = fb;
+                                #[cfg(not(windows))] // there's no ed on windows
+                                {
+                                    use std::process::Command;
+                                    let output = Command::new("ed")
+                                        .arg(&format!("{target}/alef"))
+                                        .stdin(File::open(&format!("{target}/ab.ed")).unwrap())
+                                        .output()
+                                        .unwrap();
+                                    assert!(output.status.success(), "{output:?}");
+                                    //println!("{}", String::from_utf8_lossy(&output.stdout));
+                                    //println!("{}", String::from_utf8_lossy(&output.stderr));
+                                    let alef = std::fs::read(&format!("{target}/alef")).unwrap();
+                                    assert_eq!(alef, bet);
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    #[test]
+    fn test_permutations_empty_lines() {
+        let target = "target/ed-diff/";
+        // test all possible six-line files with missing newlines.
+        let _ = std::fs::create_dir(target);
+        for &a in &[0, 1, 2] {
+            for &b in &[0, 1, 2] {
+                for &c in &[0, 1, 2] {
+                    for &d in &[0, 1, 2] {
+                        for &e in &[0, 1, 2] {
+                            for &f in &[0, 1, 2] {
+                                use std::fs::File;
+                                use std::io::Write;
+                                let mut alef = Vec::new();
+                                let mut bet = Vec::new();
+                                alef.write_all(if a == 0 { b"\n" } else { b"b\n" }).unwrap();
+                                if a != 2 {
+                                    bet.write_all(b"b\n").unwrap();
+                                }
+                                alef.write_all(if b == 0 { b"\n" } else { b"d\n" }).unwrap();
+                                if b != 2 {
+                                    bet.write_all(b"d\n").unwrap();
+                                }
+                                alef.write_all(if c == 0 { b"\n" } else { b"f\n" }).unwrap();
+                                if c != 2 {
+                                    bet.write_all(b"f\n").unwrap();
+                                }
+                                alef.write_all(if d == 0 { b"\n" } else { b"h\n" }).unwrap();
+                                if d != 2 {
+                                    bet.write_all(b"h\n").unwrap();
+                                }
+                                alef.write_all(if e == 0 { b"\n" } else { b"j\n" }).unwrap();
+                                if e != 2 {
+                                    bet.write_all(b"j\n").unwrap();
+                                }
+                                alef.write_all(if f == 0 { b"\n" } else { b"l\n" }).unwrap();
+                                if f != 2 {
+                                    bet.write_all(b"l\n").unwrap();
+                                }
+                                // This test diff is intentionally reversed.
+                                // We want it to turn the alef into bet.
+                                let diff = diff_w(&alef, &bet, &format!("{target}/alef_")).unwrap();
+                                File::create(&format!("{target}/ab_.ed"))
+                                    .unwrap()
+                                    .write_all(&diff)
+                                    .unwrap();
+                                let mut fa = File::create(&format!("{target}/alef_")).unwrap();
+                                fa.write_all(&alef[..]).unwrap();
+                                let mut fb = File::create(&format!("{target}/bet_")).unwrap();
+                                fb.write_all(&bet[..]).unwrap();
+                                let _ = fa;
+                                let _ = fb;
+                                #[cfg(not(windows))] // there's no ed on windows
+                                {
+                                    use std::process::Command;
+                                    let output = Command::new("ed")
+                                        .arg(&format!("{target}/alef_"))
+                                        .stdin(File::open(&format!("{target}/ab_.ed")).unwrap())
+                                        .output()
+                                        .unwrap();
+                                    assert!(output.status.success(), "{output:?}");
+                                    //println!("{}", String::from_utf8_lossy(&output.stdout));
+                                    //println!("{}", String::from_utf8_lossy(&output.stderr));
+                                    let alef = std::fs::read(&format!("{target}/alef_")).unwrap();
+                                    assert_eq!(alef, bet);
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    #[test]
+    fn test_permutations_reverse() {
+        let target = "target/ed-diff/";
+        // test all possible six-line files.
+        let _ = std::fs::create_dir(target);
+        for &a in &[0, 1, 2] {
+            for &b in &[0, 1, 2] {
+                for &c in &[0, 1, 2] {
+                    for &d in &[0, 1, 2] {
+                        for &e in &[0, 1, 2] {
+                            for &f in &[0, 1, 2] {
+                                use std::fs::File;
+                                use std::io::Write;
+                                let mut alef = Vec::new();
+                                let mut bet = Vec::new();
+                                alef.write_all(if a == 0 { b"a\n" } else { b"f\n" })
+                                    .unwrap();
+                                if a != 2 {
+                                    bet.write_all(b"a\n").unwrap();
+                                }
+                                alef.write_all(if b == 0 { b"b\n" } else { b"e\n" })
+                                    .unwrap();
+                                if b != 2 {
+                                    bet.write_all(b"b\n").unwrap();
+                                }
+                                alef.write_all(if c == 0 { b"c\n" } else { b"d\n" })
+                                    .unwrap();
+                                if c != 2 {
+                                    bet.write_all(b"c\n").unwrap();
+                                }
+                                alef.write_all(if d == 0 { b"d\n" } else { b"c\n" })
+                                    .unwrap();
+                                if d != 2 {
+                                    bet.write_all(b"d\n").unwrap();
+                                }
+                                alef.write_all(if e == 0 { b"e\n" } else { b"b\n" })
+                                    .unwrap();
+                                if e != 2 {
+                                    bet.write_all(b"e\n").unwrap();
+                                }
+                                alef.write_all(if f == 0 { b"f\n" } else { b"a\n" })
+                                    .unwrap();
+                                if f != 2 {
+                                    bet.write_all(b"f\n").unwrap();
+                                }
+                                // This test diff is intentionally reversed.
+                                // We want it to turn the alef into bet.
+                                let diff = diff_w(&alef, &bet, &format!("{target}/alefr")).unwrap();
+                                File::create(&format!("{target}/abr.ed"))
+                                    .unwrap()
+                                    .write_all(&diff)
+                                    .unwrap();
+                                let mut fa = File::create(&format!("{target}/alefr")).unwrap();
+                                fa.write_all(&alef[..]).unwrap();
+                                let mut fb = File::create(&format!("{target}/betr")).unwrap();
+                                fb.write_all(&bet[..]).unwrap();
+                                let _ = fa;
+                                let _ = fb;
+                                #[cfg(not(windows))] // there's no ed on windows
+                                {
+                                    use std::process::Command;
+                                    let output = Command::new("ed")
+                                        .arg(&format!("{target}/alefr"))
+                                        .stdin(File::open(&format!("{target}/abr.ed")).unwrap())
+                                        .output()
+                                        .unwrap();
+                                    assert!(output.status.success(), "{output:?}");
+                                    //println!("{}", String::from_utf8_lossy(&output.stdout));
+                                    //println!("{}", String::from_utf8_lossy(&output.stderr));
+                                    let alef = std::fs::read(&format!("{target}/alefr")).unwrap();
+                                    assert_eq!(alef, bet);
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    #[test]
+    fn test_stop_early() {
+        let from = ["a", "b", "c", ""].join("\n");
+        let to = ["a", "d", "c", ""].join("\n");
+
+        let diff_full = diff(from.as_bytes(), to.as_bytes(), &Params::default()).unwrap();
+        let expected_full = ["2c", "d", ".", ""].join("\n");
+        assert_eq!(diff_full, expected_full.as_bytes());
+
+        let diff_brief = diff(
+            from.as_bytes(),
+            to.as_bytes(),
+            &Params {
+                brief: true,
+                ..Default::default()
+            },
+        )
+        .unwrap();
+        let expected_brief = "\0".as_bytes();
+        assert_eq!(diff_brief, expected_brief);
+
+        let nodiff_full = diff(from.as_bytes(), from.as_bytes(), &Params::default()).unwrap();
+        assert!(nodiff_full.is_empty());
+
+        let nodiff_brief = diff(
+            from.as_bytes(),
+            from.as_bytes(),
+            &Params {
+                brief: true,
+                ..Default::default()
+            },
+        )
+        .unwrap();
+        assert!(nodiff_brief.is_empty());
+    }
+}

src/macros.rs

@@ -0,0 +1,25 @@
+// asserts equality of the actual diff and expected diff
+// considering datetime varitations
+//
+// It replaces the modification time in the actual diff
+// with placeholder "TIMESTAMP" and then asserts the equality
+//
+// For eg.
+// let brief = "*** fruits_old.txt\t2024-03-24 23:43:05.189597645 +0530\n
+//              --- fruits_new.txt\t2024-03-24 23:35:08.922581904 +0530\n";
+//
+// replaced = "*** fruits_old.txt\tTIMESTAMP\n
+//             --- fruits_new.txt\tTIMESTAMP\n";
+#[macro_export]
+macro_rules! assert_diff_eq {
+    ($actual:expr, $expected:expr) => {{
+        use regex::Regex;
+        use std::str;
+
+        let diff = str::from_utf8(&$actual).unwrap();
+        let re = Regex::new(r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d+ [+-]\d{4}").unwrap();
+        let actual = re.replacen(diff, 2, "TIMESTAMP");
+
+        assert_eq!(actual, $expected);
+    }};
+}

src/main.rs

@@ -1,55 +1,96 @@
-// Sample program. Do not use.
+// 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.
+
+use crate::params::{parse_params, Format};
 use std::env;
+use std::ffi::OsString;
 use std::fs;
-use std::io::{self, Write};
-use std::process;
-fn main() {
-    let mut o = env::args_os();
-    // parse CLI
-    let exe = match o.next() {
-        Some(from) => from,
-        None => {
-            eprintln!("Usage: [exe] [from] [to]");
-            process::exit(1);
-        }
-    };
-    let from = match o.next() {
-        Some(from) => from,
-        None => {
-            eprintln!("Usage: {} [from] [to]", exe.to_string_lossy());
-            process::exit(1);
-        }
-    };
-    let to = match o.next() {
-        Some(from) => from,
-        None => {
-            eprintln!("Usage: {} [from] [to]", exe.to_string_lossy());
-            process::exit(1);
+use std::io::{self, Read, Write};
+use std::process::{exit, ExitCode};
+
+mod context_diff;
+mod ed_diff;
+mod macros;
+mod normal_diff;
+mod params;
+mod unified_diff;
+mod utils;
+
+// Exit codes are documented at
+// https://www.gnu.org/software/diffutils/manual/html_node/Invoking-diff.html.
+//     An exit status of 0 means no differences were found,
+//     1 means some differences were found,
+//     and 2 means trouble.
+fn main() -> ExitCode {
+    let opts = env::args_os();
+    let params = parse_params(opts).unwrap_or_else(|error| {
+        eprintln!("{error}");
+        exit(2);
+    });
+    // if from and to are the same file, no need to perform any comparison
+    let maybe_report_identical_files = || {
+        if params.report_identical_files {
+            println!(
+                "Files {} and {} are identical",
+                params.from.to_string_lossy(),
+                params.to.to_string_lossy(),
+            );
         }
     };
+    if params.from == "-" && params.to == "-"
+        || same_file::is_same_file(&params.from, &params.to).unwrap_or(false)
+    {
+        maybe_report_identical_files();
+        return ExitCode::SUCCESS;
+    }
     // read files
-    let from_content = match fs::read(&from) {
+    fn read_file_contents(filepath: &OsString) -> io::Result<Vec<u8>> {
+        if filepath == "-" {
+            let mut content = Vec::new();
+            io::stdin().read_to_end(&mut content).and(Ok(content))
+        } else {
+            fs::read(filepath)
+        }
+    }
+    let from_content = match read_file_contents(&params.from) {
         Ok(from_content) => from_content,
         Err(e) => {
-            eprintln!("Failed to read from-file: {}", e);
-            process::exit(2);
+            eprintln!("Failed to read from-file: {e}");
+            return ExitCode::from(2);
         }
     };
-    let to_content = match fs::read(&to) {
+    let to_content = match read_file_contents(&params.to) {
         Ok(to_content) => to_content,
         Err(e) => {
-            eprintln!("Failed to read to-file: {}", e);
-            process::exit(2);
+            eprintln!("Failed to read to-file: {e}");
+            return ExitCode::from(2);
         }
     };
     // run diff
-    io::stdout()
-        .write_all(&unified_diff::diff(
-            &from_content,
-            &from.to_string_lossy(),
-            &to_content,
-            &to.to_string_lossy(),
-            1,
-        ))
-        .unwrap();
+    let result: Vec<u8> = match params.format {
+        Format::Normal => normal_diff::diff(&from_content, &to_content, &params),
+        Format::Unified => unified_diff::diff(&from_content, &to_content, &params),
+        Format::Context => context_diff::diff(&from_content, &to_content, &params),
+        Format::Ed => ed_diff::diff(&from_content, &to_content, &params).unwrap_or_else(|error| {
+            eprintln!("{error}");
+            exit(2);
+        }),
+    };
+    if params.brief && !result.is_empty() {
+        println!(
+            "Files {} and {} differ",
+            params.from.to_string_lossy(),
+            params.to.to_string_lossy()
+        );
+    } else {
+        io::stdout().write_all(&result).unwrap();
+    }
+    if result.is_empty() {
+        maybe_report_identical_files();
+        ExitCode::SUCCESS
+    } else {
+        ExitCode::from(1)
+    }
 }