Compare commits

..

1 Commits

Author SHA1 Message Date
Sylvestre Ledru c3b3f7dfa6 github action: try to build and release findutils 2024-04-03 23:41:58 +02:00
41 changed files with 853 additions and 7471 deletions
-100
View File
@@ -1,100 +0,0 @@
name: GnuComment
on:
workflow_run:
workflows: ["GnuTests"]
types:
- completed
permissions: {}
jobs:
post-comment:
permissions:
actions: read # to list workflow runs artifacts
pull-requests: write # to comment on pr
runs-on: ubuntu-latest
if: >
github.event.workflow_run.event == 'pull_request'
steps:
- name: 'Download artifact'
uses: actions/github-script@v9
with:
script: |
// List all artifacts from GnuTests
var artifacts = await github.rest.actions.listWorkflowRunArtifacts({
owner: context.repo.owner,
repo: context.repo.repo,
run_id: ${{ github.event.workflow_run.id }},
});
// Download the "comment" artifact, which contains a PR number (NR) and result.txt
var matchArtifact = artifacts.data.artifacts.filter((artifact) => {
return artifact.name == "comment"
})[0];
if (!matchArtifact) {
console.log('No comment artifact found');
return;
}
var download = await github.rest.actions.downloadArtifact({
owner: context.repo.owner,
repo: context.repo.repo,
artifact_id: matchArtifact.id,
archive_format: 'zip',
});
var fs = require('fs');
fs.writeFileSync('${{ github.workspace }}/comment.zip', Buffer.from(download.data));
- run: unzip comment.zip || echo "Failed to unzip comment artifact"
- name: 'Comment on PR'
uses: actions/github-script@v9
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
script: |
var fs = require('fs');
// Check if files exist
if (!fs.existsSync('./NR')) {
console.log('No NR file found, skipping comment');
return;
}
if (!fs.existsSync('./result.txt')) {
console.log('No result.txt file found, skipping comment');
return;
}
var issue_number = Number(fs.readFileSync('./NR'));
var content = fs.readFileSync('./result.txt');
if (content.toString().trim().length > 7) { // 7 because we have backquote + \n
// Update existing comment if present, otherwise create a new one
var marker = '<!-- gnu-tests-bot -->';
var body = marker + '\nGNU diffutils testsuite comparison:\n```\n' + content + '```';
var comments = await github.rest.issues.listComments({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue_number,
});
var existing = comments.data.filter(c => c.body.includes(marker))[0];
if (existing) {
await github.rest.issues.updateComment({
owner: context.repo.owner,
repo: context.repo.repo,
comment_id: existing.id,
body: body,
});
} else {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue_number,
body: body,
});
}
} else {
console.log('Comment content too short, skipping');
}
-231
View File
@@ -1,231 +0,0 @@
name: GnuTests
# Run GNU diffutils testsuite against the Rust diffutils implementation
# and compare results against the main branch to catch regressions
on:
pull_request:
push:
branches:
- '*'
permissions:
contents: write # Publish diffutils instead of discarding
# End the current execution if there is a new changeset in the PR
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
env:
DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
TEST_FULL_SUMMARY_FILE: 'diffutils-gnu-full-result.json'
jobs:
native:
name: Run GNU diffutils testsuite
runs-on: ubuntu-24.04
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
persist-credentials: false
- uses: dtolnay/rust-toolchain@master
with:
toolchain: stable
- uses: Swatinem/rust-cache@v2
### Build
- name: Build Rust diffutils binary
shell: bash
run: |
## Build Rust diffutils binary
cargo build --config=profile.release.strip=true --profile=release
zstd -19 target/release/diffutils -o diffutils-x86_64-unknown-linux-gnu.zst
- name: Publish latest commit
uses: softprops/action-gh-release@v3
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
with:
tag_name: latest-commit
body: |
commit: ${{ github.sha }}
draft: false
prerelease: true
files: |
diffutils-x86_64-unknown-linux-gnu.zst
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
### Run tests
- name: Run GNU diffutils testsuite
shell: bash
run: |
## Run GNU diffutils testsuite
./tests/run-upstream-testsuite.sh release || true
env:
TERM: xterm
- name: Upload full json results
uses: actions/upload-artifact@v7
with:
name: diffutils-gnu-full-result
path: tests/test-results.json
if-no-files-found: warn
aggregate:
needs: [native]
permissions:
actions: read
contents: read
pull-requests: read
name: Aggregate GNU test results
runs-on: ubuntu-24.04
steps:
- name: Initialize workflow variables
id: vars
shell: bash
run: |
## VARs setup
outputs() { step_id="${{ github.action }}"; for var in "$@" ; do echo steps.${step_id}.outputs.${var}="${!var}"; echo "${var}=${!var}" >> $GITHUB_OUTPUT; done; }
TEST_SUMMARY_FILE='diffutils-gnu-result.json'
outputs TEST_SUMMARY_FILE
- name: Checkout code
uses: actions/checkout@v4
with:
persist-credentials: false
- name: Retrieve reference artifacts
uses: dawidd6/action-download-artifact@v21
continue-on-error: true
with:
workflow: GnuTests.yml
branch: "${{ env.DEFAULT_BRANCH }}"
workflow_conclusion: completed
path: "reference"
if_no_artifact_found: warn
- name: Download full json results
uses: actions/download-artifact@v8
with:
name: diffutils-gnu-full-result
path: results
- name: Extract/summarize testing info
id: summary
shell: bash
run: |
## Extract/summarize testing info
outputs() { step_id="${{ github.action }}"; for var in "$@" ; do echo steps.${step_id}.outputs.${var}="${!var}"; echo "${var}=${!var}" >> $GITHUB_OUTPUT; done; }
RESULT_FILE="results/test-results.json"
if [[ ! -f "$RESULT_FILE" ]]; then
echo "::error ::Missing test results at $RESULT_FILE"
exit 1
fi
TOTAL=$(jq '[.tests[]] | length' "$RESULT_FILE")
PASS=$(jq '[.tests[] | select(.result=="PASS")] | length' "$RESULT_FILE")
FAIL=$(jq '[.tests[] | select(.result=="FAIL")] | length' "$RESULT_FILE")
SKIP=$(jq '[.tests[] | select(.result=="SKIP")] | length' "$RESULT_FILE")
ERROR=0
output="GNU diffutils tests summary = TOTAL: $TOTAL / PASS: $PASS / FAIL: $FAIL / SKIP: $SKIP"
echo "${output}"
if [[ "$FAIL" -gt 0 ]]; then
echo "::warning ::${output}"
fi
jq -n \
--arg date "$(date --rfc-email)" \
--arg sha "$GITHUB_SHA" \
--arg total "$TOTAL" \
--arg pass "$PASS" \
--arg skip "$SKIP" \
--arg fail "$FAIL" \
--arg error "$ERROR" \
'{($date): { sha: $sha, total: $total, pass: $pass, skip: $skip, fail: $fail, error: $error }}' > '${{ steps.vars.outputs.TEST_SUMMARY_FILE }}'
HASH=$(sha1sum '${{ steps.vars.outputs.TEST_SUMMARY_FILE }}' | cut --delim=" " -f 1)
outputs HASH TOTAL PASS FAIL SKIP
- name: Upload SHA1/ID of 'test-summary'
uses: actions/upload-artifact@v7
with:
name: "${{ steps.summary.outputs.HASH }}"
path: "${{ steps.vars.outputs.TEST_SUMMARY_FILE }}"
- name: Upload test results summary
uses: actions/upload-artifact@v7
with:
name: test-summary
path: "${{ steps.vars.outputs.TEST_SUMMARY_FILE }}"
- name: Compare test failures VS reference
shell: bash
run: |
## Compare test failures VS reference
REF_SUMMARY_FILE='reference/diffutils-gnu-full-result/test-results.json'
CURRENT_SUMMARY_FILE="results/test-results.json"
IGNORE_INTERMITTENT=".github/workflows/ignore-intermittent.txt"
COMMENT_DIR="reference/comment"
mkdir -p ${COMMENT_DIR}
echo ${{ github.event.number }} > ${COMMENT_DIR}/NR
COMMENT_LOG="${COMMENT_DIR}/result.txt"
COMPARISON_RESULT=0
if test -f "${CURRENT_SUMMARY_FILE}"; then
if test -f "${REF_SUMMARY_FILE}"; then
echo "Reference summary SHA1/ID: $(sha1sum -- "${REF_SUMMARY_FILE}")"
echo "Current summary SHA1/ID: $(sha1sum -- "${CURRENT_SUMMARY_FILE}")"
python3 util/compare_test_results.py \
--ignore-file "${IGNORE_INTERMITTENT}" \
--output "${COMMENT_LOG}" \
"${CURRENT_SUMMARY_FILE}" "${REF_SUMMARY_FILE}"
COMPARISON_RESULT=$?
else
echo "::warning ::Skipping test comparison; no prior reference summary is available at '${REF_SUMMARY_FILE}'."
fi
else
echo "::error ::Failed to find summary of test results (missing '${CURRENT_SUMMARY_FILE}'); failing early"
exit 1
fi
if [ ${COMPARISON_RESULT} -eq 1 ]; then
echo "::error ::Found new non-intermittent test failures"
exit 1
else
echo "::notice ::No new test failures detected"
fi
- name: Upload comparison log (for GnuComment workflow)
if: success() || failure()
uses: actions/upload-artifact@v7
with:
name: comment
path: reference/comment/
- name: Report test results
if: success() || failure()
shell: bash
run: |
## Report final results
echo "::notice ::GNU diffutils testsuite results:"
echo "::notice :: Total tests: ${{ steps.summary.outputs.TOTAL }}"
echo "::notice :: Passed: ${{ steps.summary.outputs.PASS }}"
echo "::notice :: Failed: ${{ steps.summary.outputs.FAIL }}"
echo "::notice :: Skipped: ${{ steps.summary.outputs.SKIP }}"
if [[ "${{ steps.summary.outputs.FAIL }}" -gt 0 ]]; then
PASS_RATE=$(( ${{ steps.summary.outputs.PASS }} * 100 / (${{ steps.summary.outputs.PASS }} + ${{ steps.summary.outputs.FAIL }}) ))
echo "::notice :: Pass rate: ${PASS_RATE}%"
fi
-15
View File
@@ -1,15 +0,0 @@
name: Security audit
on:
schedule:
- cron: "0 0 * * *"
jobs:
audit:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
with:
persist-credentials: false
- uses: rustsec/audit-check@v2
with:
token: ${{ secrets.GITHUB_TOKEN }}
+175 -27
View File
@@ -4,7 +4,6 @@ name: Basic CI
env:
CARGO_TERM_COLOR: always
CARGO_INCREMENTAL: 0
jobs:
check:
@@ -16,6 +15,7 @@ jobs:
os: [ubuntu-latest, macOS-latest, windows-latest]
steps:
- uses: actions/checkout@v4
- uses: dtolnay/rust-toolchain@stable
- run: cargo check
test:
@@ -27,14 +27,7 @@ jobs:
os: [ubuntu-latest, macOS-latest, windows-latest]
steps:
- uses: actions/checkout@v4
- name: install GNU patch on MacOS
if: runner.os == 'macOS'
run: |
brew install gpatch
- 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
- uses: dtolnay/rust-toolchain@stable
- run: cargo test
fmt:
@@ -42,6 +35,8 @@ 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:
@@ -53,12 +48,111 @@ 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:
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
build:
name: build ${{ matrix.binary || 'findutils' }} ${{ matrix.target }}
runs-on: ${{ matrix.os }}
container: ${{ fromJson(matrix.container || '{"image":null}') }}
timeout-minutes: 30
strategy:
fail-fast: false
matrix:
include:
- os: ubuntu-20.04
target: x86_64-unknown-linux-musl
- os: ubuntu-20.04
target: aarch64-unknown-linux-musl
- os: ubuntu-20.04
target: armv7-unknown-linux-musleabi
container: '{"image": "messense/rust-musl-cross:armv7-musleabi"}'
- os: ubuntu-20.04
target: i686-unknown-linux-musl
container: '{"image": "messense/rust-musl-cross:i686-musl"}'
- os: macOS-11
target: x86_64-apple-darwin
macosx_deployment_target: 10.13
developer_dir: /Applications/Xcode_11.7.app
sdkroot: /Applications/Xcode_11.7.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.15.sdk
- os: macos-14
target: aarch64-apple-darwin
macosx_deployment_target: 11.0
- os: windows-2019
target: x86_64-pc-windows-msvc
rustflags: -Ctarget-feature=+crt-static
steps:
- name: Clone repository
uses: actions/checkout@v4
- name: Install rust
uses: ./.github/actions/rust-toolchain
with:
toolchain: ${{ matrix.target == 'aarch64-apple-darwin' && 'beta' || 'stable' }}
target: ${{ matrix.target }}
if: ${{ !matrix.container }}
- name: Install musl-tools (x86_64)
run: sudo apt-get install musl-tools
if: ${{ matrix.target == 'x86_64-unknown-linux-musl' }}
- name: Install musl-tools (arm64)
run: |
set -x
sed 's/mirror+file:\/etc\/apt\/apt-mirrors\.txt/[arch=arm64] http:\/\/ports.ubuntu.com\/ubuntu-ports\//g' /etc/apt/sources.list | sudo tee /etc/apt/sources.list.d/ports.list
sudo dpkg --add-architecture arm64
sudo apt-get update || true
sudo apt-get install musl-dev:arm64 binutils-multiarch gcc-10-aarch64-linux-gnu libc6-dev-arm64-cross
apt-get download musl-tools:arm64
sudo dpkg-deb -x musl-tools_*_arm64.deb /
sed 2iREALGCC=aarch64-linux-gnu-gcc-10 /usr/bin/musl-gcc | sudo tee /usr/bin/aarch64-linux-musl-gcc > /dev/null
sudo chmod +x /usr/bin/aarch64-linux-musl-gcc
if: ${{ matrix.target == 'aarch64-unknown-linux-musl' }}
- name: Build
run: cargo build --locked --release --bin ${{ matrix.binary || 'findutils' }} --target ${{ matrix.target }} --features=openssl/vendored ${{ matrix.extra_args }}
env:
CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER: aarch64-linux-musl-gcc
MACOSX_DEPLOYMENT_TARGET: ${{ matrix.macosx_deployment_target }}
DEVELOPER_DIR: ${{ matrix.developer_dir }}
SDKROOT: ${{ matrix.sdkroot }}
RUSTFLAGS: ${{ matrix.rustflags }}
# Workaround for the lack of substring() function in github actions expressions.
- name: Id
id: id
shell: bash
run: echo "id=${ID#refs/tags/}" >> $GITHUB_OUTPUT
env:
ID: ${{ startsWith(github.ref, 'refs/tags/') && github.ref || github.sha }}
- name: Upload artifacts
uses: actions/upload-artifact@v4
with:
name: ${{ matrix.binary || 'findutils' }}-${{ steps.id.outputs.id }}-${{ matrix.target }}
path: target/${{ matrix.target }}/release/${{ matrix.binary || 'findutils' }}${{ endsWith(matrix.target, '-msvc') && '.exe' || '' }}
if-no-files-found: error
coverage:
name: Code Coverage
env:
RUSTC_BOOTSTRAP: 1
runs-on: ${{ matrix.job.os }}
strategy:
fail-fast: false
@@ -75,26 +169,29 @@ jobs:
run: |
## VARs setup
outputs() { step_id="vars"; for var in "$@" ; 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: install GNU patch on MacOS
if: runner.os == 'macOS'
run: |
brew install gpatch
- 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: rust toolchain ~ install
uses: dtolnay/rust-toolchain@nightly
- name: Test
run: cargo test --all-features --no-fail-fast
run: cargo test ${{ steps.vars.outputs.CARGO_FEATURES_OPTION }} --no-fail-fast
env:
CARGO_INCREMENTAL: "0"
RUSTC_WRAPPER: ""
RUSTFLAGS: "-Cinstrument-coverage -Zcoverage-options=branch -Ccodegen-units=1 -Copt-level=0 -Coverflow-checks=off -Zpanic_abort_tests -Cpanic=abort"
RUSTFLAGS: "-Zprofile -Ccodegen-units=1 -Copt-level=0 -Clink-dead-code -Coverflow-checks=off -Zpanic_abort_tests -Cpanic=abort"
RUSTDOCFLAGS: "-Cpanic=abort"
LLVM_PROFILE_FILE: "diffutils-%p-%m.profraw"
- name: "`grcov` ~ install"
id: build_grcov
shell: bash
@@ -122,16 +219,67 @@ jobs:
COVERAGE_REPORT_FILE="${COVERAGE_REPORT_DIR}/lcov.info"
mkdir -p "${COVERAGE_REPORT_DIR}"
# display coverage files
grcov . --output-type files --binary-path "${COVERAGE_REPORT_DIR}" | sort --unique
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 "${COVERAGE_REPORT_FILE}" --binary-path "${COVERAGE_REPORT_DIR}" --branch
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@v7
uses: codecov/codecov-action@v3
# if: steps.vars.outputs.HAS_CODECOV_TOKEN
with:
token: ${{ secrets.CODECOV_TOKEN }}
files: ${{ steps.coverage.outputs.report }}
# 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
release:
name: release
runs-on: ubuntu-latest
needs: [build, clippy, check, test]
if: ${{ startsWith(github.ref, 'refs/tags/') }}
steps:
- name: Clone repository
uses: actions/checkout@v4
- name: Check versions
run: |
tag_name=${GITHUB_REF#refs/tags/}
v=$(grep -m 1 "^version" Cargo.toml|sed -e "s|version = \"\(.*\)\"|\1|")
if ! echo $tag_name|grep -q $v; then
echo "Mistmatch of the version:"
echo "Cargo.toml says $v while the tag is $tag_name"
exit 2
fi
- name: Get artifacts
uses: actions/download-artifact@v4
- name: Create release assets
run: |
for d in findutils-*; do
chmod +x "$d/findutils"*
cp README.md LICENSE "$d/"
tar -zcvf "$d.tar.gz" "$d"
echo -n "$(shasum -ba 256 "$d.tar.gz" | cut -d " " -f 1)" > "$d.tar.gz.sha256"
if [[ $d =~ (findutils-)(.*)?(x86_64-pc-windows)(.*)? ]]; then
zip -r "$d.zip" "$d"
echo -n "$(shasum -ba 256 "$d.zip" | cut -d " " -f 1)" > "$d.zip.sha256"
fi
done
- name: Create release
run: |
sudo apt-get update && sudo apt-get install -y hub
tag_name=${GITHUB_REF#refs/tags/}
for f in findutils-*.tar.gz* findutils-*.zip*; do
if [[ -f "$f" ]]; then
files="$files -a $f";
fi
done
hub release create -m $tag_name $tag_name $files
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-37
View File
@@ -1,37 +0,0 @@
name: CodSpeed
on:
push:
branches:
- "main"
pull_request:
# `workflow_dispatch` allows CodSpeed to trigger backtest
# performance analysis in order to generate initial data.
workflow_dispatch:
permissions:
contents: read
id-token: write
jobs:
codspeed:
name: Run benchmarks
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Setup rust toolchain, cache and cargo-codspeed binary
uses: moonrepo/setup-rust@v1
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
+9 -16
View File
@@ -2,10 +2,6 @@ name: Fuzzing
# spell-checker:ignore fuzzer
env:
CARGO_INCREMENTAL: 0
RUSTC_BOOTSTRAP: 1
on:
pull_request:
push:
@@ -25,15 +21,15 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: dtolnay/rust-toolchain@nightly
- name: Install `cargo-fuzz`
run: |
cargo install cargo-fuzz --locked
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 fuzz build
run: cargo +nightly fuzz build
fuzz-run:
needs: fuzz-build
@@ -45,34 +41,31 @@ jobs:
strategy:
matrix:
test-target:
- { name: fuzz_cmp, should_pass: true }
- { name: fuzz_cmp_args, should_pass: true }
- { 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 --locked
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@v5
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.should_pass }}
continue-on-error: ${{ !matrix.test-target.name.should_pass }}
run: |
cargo fuzz run ${{ matrix.test-target.name }} -- -max_total_time=${{ env.RUN_FOR }} -detect_leaks=0
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@v5
uses: actions/cache/save@v4
with:
key: corpus-cache-${{ matrix.test-target.name }}
path: |
-296
View File
@@ -1,296 +0,0 @@
# 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 dist (archives, installers, hashes)
# * uploads those artifacts to temporary workflow zip
# * on success, uploads the artifacts to a GitHub Release
#
# Note that the GitHub Release will be created with a generated
# title/body based on your changelogs.
name: Release
permissions:
"contents": "write"
# This task will run whenever you push a git tag that looks like a version
# like "1.0.0", "v0.1.0-prerelease.1", "my-app/0.1.0", "releases/v1.0.0", etc.
# Various formats will be parsed into a VERSION and an optional PACKAGE_NAME, where
# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION
# must be a Cargo-style SemVer Version (must have at least major.minor.patch).
#
# If PACKAGE_NAME is specified, then the announcement will be for that
# package (erroring out if it doesn't have the given version or isn't dist-able).
#
# If PACKAGE_NAME isn't specified, then the announcement will be for all
# (dist-able) packages in the workspace with that version (this mode is
# intended for workspaces with only one dist-able package, or with all dist-able
# packages versioned/released in lockstep).
#
# If you push multiple tags at once, separate instances of this workflow will
# spin up, creating an independent announcement for each one. However, GitHub
# will hard limit this to 3 tags per commit, as it will assume more tags is a
# mistake.
#
# If there's a prerelease-style suffix to the version, then the release(s)
# will be marked as a prerelease.
on:
pull_request:
push:
tags:
- '**[0-9]+.[0-9]+.[0-9]+*'
jobs:
# Run 'dist plan' (or host) to determine what tasks we need to do
plan:
runs-on: "ubuntu-22.04"
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:
persist-credentials: false
submodules: recursive
- name: Install dist
# we specify bash to get pipefail; it guards against the `curl` command
# failing. otherwise `sh` won't catch that `curl` returned non-0
shell: bash
run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.30.3/cargo-dist-installer.sh | sh"
- name: Cache dist
uses: actions/upload-artifact@v7
with:
name: cargo-dist-cache
path: ~/.cargo/bin/dist
# sure would be cool if github gave us proper conditionals...
# so here's a doubly-nested ternary-via-truthiness to try to provide the best possible
# functionality based on whether this is a pull_request, and whether it's from a fork.
# (PRs run on the *source* but secrets are usually on the *target* -- that's *good*
# but also really annoying to build CI around when it needs secrets to work right.)
- id: plan
run: |
dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json
echo "dist ran successfully"
cat plan-dist-manifest.json
echo "manifest=$(jq -c "." plan-dist-manifest.json)" >> "$GITHUB_OUTPUT"
- name: "Upload dist-manifest.json"
uses: actions/upload-artifact@v7
with:
name: artifacts-plan-dist-manifest
path: plan-dist-manifest.json
# Build and packages all the platform-specific things
build-local-artifacts:
name: build-local-artifacts (${{ join(matrix.targets, ', ') }})
# Let the initial task tell us to not run (currently very blunt)
needs:
- plan
if: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix.include != null && (needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload') }}
strategy:
fail-fast: false
# Target platforms/runners are computed by dist in create-release.
# Each member of the matrix has the following arguments:
#
# - runner: the github runner
# - dist-args: cli flags to pass to dist
# - install-dist: expression to run to install dist on the runner
#
# Typically there will be:
# - 1 "global" task that builds universal installers
# - N "local" tasks that build each platform's binaries and platform-specific installers
matrix: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix }}
runs-on: ${{ matrix.runner }}
container: ${{ matrix.container && matrix.container.image || null }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
BUILD_MANIFEST_NAME: target/distrib/${{ join(matrix.targets, '-') }}-dist-manifest.json
steps:
- name: enable windows longpaths
run: |
git config --global core.longpaths true
- uses: actions/checkout@v4
with:
persist-credentials: false
submodules: recursive
- name: Install Rust non-interactively if not already installed
if: ${{ matrix.container }}
run: |
if ! command -v cargo > /dev/null 2>&1; then
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
echo "$HOME/.cargo/bin" >> $GITHUB_PATH
fi
- name: Install dist
run: ${{ matrix.install_dist.run }}
# Get the dist-manifest
- name: Fetch local artifacts
uses: actions/download-artifact@v8
with:
pattern: artifacts-*
path: target/distrib/
merge-multiple: true
- name: Install dependencies
run: |
${{ matrix.packages_install }}
- name: Build artifacts
run: |
# Actually do builds and make zips and whatnot
dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
echo "dist ran successfully"
- id: cargo-dist
name: Post-build
# We force bash here just because github makes it really hard to get values up
# to "real" actions without writing to env-vars, and writing to env-vars has
# inconsistent syntax between shell and powershell.
shell: bash
run: |
# Parse out what we just built and upload it to scratch storage
echo "paths<<EOF" >> "$GITHUB_OUTPUT"
dist print-upload-files-from-manifest --manifest dist-manifest.json >> "$GITHUB_OUTPUT"
echo "EOF" >> "$GITHUB_OUTPUT"
cp dist-manifest.json "$BUILD_MANIFEST_NAME"
- name: "Upload artifacts"
uses: actions/upload-artifact@v7
with:
name: artifacts-build-local-${{ join(matrix.targets, '_') }}
path: |
${{ steps.cargo-dist.outputs.paths }}
${{ env.BUILD_MANIFEST_NAME }}
# Build and package all the platform-agnostic(ish) things
build-global-artifacts:
needs:
- plan
- build-local-artifacts
runs-on: "ubuntu-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 cached dist
uses: actions/download-artifact@v8
with:
name: cargo-dist-cache
path: ~/.cargo/bin/
- run: chmod +x ~/.cargo/bin/dist
# Get all the local artifacts for the global tasks to use (for e.g. checksums)
- name: Fetch local artifacts
uses: actions/download-artifact@v8
with:
pattern: artifacts-*
path: target/distrib/
merge-multiple: true
- id: cargo-dist
shell: bash
run: |
dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json
echo "dist ran successfully"
# Parse out what we just built and upload it to scratch storage
echo "paths<<EOF" >> "$GITHUB_OUTPUT"
jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
echo "EOF" >> "$GITHUB_OUTPUT"
cp dist-manifest.json "$BUILD_MANIFEST_NAME"
- name: "Upload artifacts"
uses: actions/upload-artifact@v7
with:
name: artifacts-build-global
path: |
${{ steps.cargo-dist.outputs.paths }}
${{ env.BUILD_MANIFEST_NAME }}
# Determines if we should publish/announce
host:
needs:
- plan
- build-local-artifacts
- build-global-artifacts
# Only run if we're "publishing", and only if 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-22.04"
outputs:
val: ${{ steps.host.outputs.manifest }}
steps:
- uses: actions/checkout@v4
with:
persist-credentials: false
submodules: recursive
- name: Install cached dist
uses: actions/download-artifact@v8
with:
name: cargo-dist-cache
path: ~/.cargo/bin/
- run: chmod +x ~/.cargo/bin/dist
# Fetch artifacts from scratch-storage
- name: Fetch artifacts
uses: actions/download-artifact@v8
with:
pattern: artifacts-*
path: target/distrib/
merge-multiple: true
- id: host
shell: bash
run: |
dist host ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json
echo "artifacts uploaded and released successfully"
cat dist-manifest.json
echo "manifest=$(jq -c "." dist-manifest.json)" >> "$GITHUB_OUTPUT"
- name: "Upload dist-manifest.json"
uses: actions/upload-artifact@v7
with:
# Overwrite the previous copy
name: artifacts-dist-manifest
path: dist-manifest.json
# Create a GitHub Release while uploading all files to it
- name: "Download GitHub Artifacts"
uses: actions/download-artifact@v8
with:
pattern: artifacts-*
path: artifacts
merge-multiple: true
- name: Cleanup
run: |
# Remove the granular manifests
rm -f artifacts/*-dist-manifest.json
- name: Create GitHub Release
env:
PRERELEASE_FLAG: "${{ fromJson(steps.host.outputs.manifest).announcement_is_prerelease && '--prerelease' || '' }}"
ANNOUNCEMENT_TITLE: "${{ fromJson(steps.host.outputs.manifest).announcement_title }}"
ANNOUNCEMENT_BODY: "${{ fromJson(steps.host.outputs.manifest).announcement_github_body }}"
RELEASE_COMMIT: "${{ github.sha }}"
run: |
# Write and read notes from a file to avoid quoting breaking things
echo "$ANNOUNCEMENT_BODY" > $RUNNER_TEMP/notes.txt
gh release create "${{ needs.plan.outputs.tag }}" --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:
persist-credentials: false
submodules: recursive
-28
View File
@@ -1,28 +0,0 @@
# spell-checker:ignore wasip
name: WASI
on:
pull_request:
push:
branches:
- main
permissions:
contents: read
# End the current execution if there is a new changeset in the PR.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
jobs:
test_wasi:
name: Tests
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- uses: dtolnay/rust-toolchain@stable
with:
targets: wasm32-wasip1
- name: check
run: cargo check --target wasm32-wasip1
-48
View File
@@ -1,48 +0,0 @@
# See https://pre-commit.com for more information
# See https://pre-commit.com/hooks.html for more hooks
exclude: ^tests/fixtures/
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v6.0.0
hooks:
- id: check-added-large-files
- id: check-executables-have-shebangs
- id: check-json
exclude: '\.vscode/(cSpell|extensions)\.json' # cSpell.json and extensions.json use comments
- id: check-shebang-scripts-are-executable
exclude: '.+\.rs' # would be triggered by #![some_attribute]
- id: check-symlinks
- id: check-toml
- id: check-yaml
args: [ --allow-multiple-documents ]
- id: destroyed-symlinks
- id: end-of-file-fixer
- id: mixed-line-ending
args: [ --fix=lf ]
- id: trailing-whitespace
- repo: local
hooks:
- id: rust-linting
name: Rust linting
description: Run cargo fmt on files included in the commit.
entry: cargo +stable fmt --
pass_filenames: true
types: [file, rust]
language: system
- id: rust-clippy
name: Rust clippy
description: Run cargo clippy on files included in the commit.
entry: cargo +stable clippy --workspace --all-targets --all-features -- -D warnings
pass_filenames: false
types: [file, rust]
language: system
- id: cspell
name: Code spell checker (cspell)
description: Run cspell to check for spelling errors (if available).
entry: bash -c 'if command -v cspell >/dev/null 2>&1; then cspell --no-must-find-files -- "$@"; else echo "cspell not found, skipping spell check"; exit 0; fi' --
pass_filenames: true
language: system
ci:
skip: [rust-linting, rust-clippy, cspell]
-32
View File
@@ -1,32 +0,0 @@
# Contributing to diffutils
Hi! Welcome to uutils/diffutils, and thanks for wanting to contribute!
This project follows the shared conventions of the [uutils](https://github.com/uutils)
organization. Before opening a pull request, please read:
- Our **[Review Guidelines](https://uutils.github.io/reviews/)** — what we expect
from a pull request and how reviews are carried out.
- Our community's [CODE_OF_CONDUCT.md](./CODE_OF_CONDUCT.md), if present.
Finally, feel free to join our [Discord](https://discord.gg/wQVJbvJ)!
> [!WARNING]
> uutils is original code and cannot contain any code from GNU or other
> strongly-licensed (GPL/LGPL) implementations. We **cannot** accept changes
> based on the GNU source code, and you **must not link** to it either. You may
> look at permissively-licensed implementations (MIT/BSD) and read the GNU
> *manuals* — never the GNU *source*.
## In short
- Discuss non-trivial changes in an issue **before** writing the code.
- Keep pull requests **small, self-contained, and descriptively titled**
(e.g. `diffutils: fix ...`).
- Make sure CI passes: tests are green, `rustfmt` is satisfied, and there are
no `clippy` warnings.
- Add tests for new behavior; don't let coverage regress.
- Write small, atomic commits annotated with the component you touched.
See the [Review Guidelines](https://uutils.github.io/reviews/) for the full
details.
-8
View File
@@ -1,8 +0,0 @@
Copyright (c) Michael Howell
Copyright (c) uutils developers
Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
<LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
option. All files in the project carrying such notice may not be
copied, modified, or distributed except according to those terms.
Generated
+108 -888
View File
File diff suppressed because it is too large Load Diff
+6 -31
View File
@@ -1,6 +1,6 @@
[package]
name = "diffutils"
version = "0.5.0"
version = "0.3.0"
edition = "2021"
description = "A CLI app for generating diff files"
license = "MIT OR Apache-2.0"
@@ -15,38 +15,13 @@ name = "diffutils"
path = "src/main.rs"
[dependencies]
chrono = "0.4.38"
diff = "0.1.13"
itoa = "1.0.11"
regex = "1.10.4"
diff = "0.1.10"
regex = "1.10.3"
same-file = "1.0.6"
unicode-width = "0.2.0"
unicode-width = "0.1.11"
[dev-dependencies]
pretty_assertions = "1"
assert_cmd = "2.0.14"
divan = { version = "4.3.0", package = "codspeed-divan-compat" }
pretty_assertions = "1.4.0"
predicates = "3.1.0"
rand = "0.10.0"
tempfile = "3.26.0"
[profile.release]
lto = "thin"
codegen-units = 1
panic = "abort"
# alias profile for 'dist'
[profile.dist]
inherits = "release"
[[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 = []
tempfile = "3.10.0"
+2 -7
View File
@@ -2,11 +2,10 @@
[![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/) (diff, cmp, diff3, sdiff) in Rust.
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.
@@ -54,8 +53,4 @@ $ cargo run -- -u fruits_old.txt fruits_new.txt
## License
This project is distributed under the terms of both the MIT license and the
Apache License (Version 2.0).
See [LICENSE-APACHE](LICENSE-APACHE), [LICENSE-MIT](LICENSE-MIT), and
[COPYRIGHT](COPYRIGHT) for details.
diffutils is licensed under the MIT and Apache Licenses - see the `LICENSE-MIT` or `LICENSE-APACHE` files for details
-44
View File
@@ -1,44 +0,0 @@
# Security Policy
## Supported Versions
We provide security updates only for the latest released version of `uutils/diffutils`.
Older versions may not receive patches.
If you are using a version packaged by your Linux distribution, please check with your distribution maintainers for their update policy.
---
## Reporting a Vulnerability
**Do not open public GitHub issues for security vulnerabilities.**
This prevents accidental disclosure before a fix is available.
Instead, please use the following method:
- **Email:** [sylvestre@debian.org](mailto:Sylvestre@debian.org)
- **Encryption (optional):** You may encrypt your report using our PGP key:
Fingerprint: B60D B599 4D39 BEC4 D1A9 5CCF 7E65 28DA 752F 1BE1
---
### What to Include in Your Report
To help us investigate and resolve the issue quickly, please include as much detail as possible:
- **Type of issue:** e.g. privilege escalation, information disclosure.
- **Location in the source:** file path, commit hash, branch, or tag.
- **Steps to reproduce:** exact commands, test cases, or scripts.
- **Special configuration:** any flags, environment variables, or system setup required.
- **Affected systems:** OS/distribution and version(s) where the issue occurs.
- **Impact:** your assessment of the potential severity (DoS, RCE, data leak, etc.).
---
## Disclosure Policy
We follow a **Coordinated Vulnerability Disclosure (CVD)** process:
1. We will acknowledge receipt of your report within **10 days**.
2. We will investigate, reproduce, and assess the issue.
3. We will provide a timeline for developing and releasing a fix.
4. Once a fix is available, we will publish a GitHub Security Advisory.
5. You will be credited in the advisory unless you request anonymity.
-377
View File
@@ -1,377 +0,0 @@
// 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();
}
-13
View File
@@ -1,13 +0,0 @@
[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"]
-447
View File
@@ -1,447 +0,0 @@
# 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 = "3.20.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d20789868f4b01b2f2caec9f5c4e0213b41e3e5702a50157d699ae31ced2fcb"
[[package]]
name = "cc"
version = "1.2.60"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43c5703da9466b66a946814e1adf53ea2c90f10063b86290cc9eb67ce3478a20"
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 = "0.4.44"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c673075a2e0e5f4a1dde27ce9dee1ea4558c7ffe648f576438a20ca1d2acc4b0"
dependencies = [
"iana-time-zone",
"js-sys",
"num-traits",
"wasm-bindgen",
"windows-link",
]
[[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",
"diff",
"itoa",
"regex",
"same-file",
"unicode-width",
]
[[package]]
name = "find-msvc-tools"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
[[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 = "0.1.65"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e31bc9ad994ba00e440a8aa5c9ef0ec67d5cb5e5cb0cc7f8b744a35b389cc470"
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 = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
[[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 = "0.3.94"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2e04e2ef80ce82e13552136fabeef8a5ed1f985a96805761cbb9a2c34e7664d9"
dependencies = [
"once_cell",
"wasm-bindgen",
]
[[package]]
name = "libc"
version = "0.2.184"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "48f5d2a454e16a5ea0f4ced81bd44e4cfc7bd3a507b61887c99fd3538b28e4af"
[[package]]
name = "libfuzzer-sys"
version = "0.4.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a9fd2f41a1cba099f79a0b6b6c35656cf7c03351a7bae8ff0f28f25270f929d2"
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 = "2.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
[[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 = "1.21.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
[[package]]
name = "proc-macro2"
version = "1.0.106"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.45"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
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 = "1.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e10754a14b9137dd7b1e3e5b0493cc9171fdd105e0ab477f51b72e7f3ac0e276"
dependencies = [
"aho-corasick",
"memchr",
"regex-automata",
"regex-syntax",
]
[[package]]
name = "regex-automata"
version = "0.4.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6e1dd4122fc1595e8162618945476892eefca7b88c52820e74af6262213cae8f"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
[[package]]
name = "regex-syntax"
version = "0.8.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
[[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 = "2.0.117"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "unicode-ident"
version = "1.0.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
[[package]]
name = "unicode-width"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
[[package]]
name = "unified-diff-fuzz"
version = "0.0.0"
dependencies = [
"diffutils",
"libfuzzer-sys",
]
[[package]]
name = "wasip2"
version = "1.0.2+wasi-0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9517f9239f02c069db75e65f174b3da828fe5f5b945c4dd26bd25d89c03ebcf5"
dependencies = [
"wit-bindgen",
]
[[package]]
name = "wasm-bindgen"
version = "0.2.117"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0551fc1bb415591e3372d0bc4780db7e587d84e2a7e79da121051c5c4b89d0b0"
dependencies = [
"cfg-if",
"once_cell",
"rustversion",
"wasm-bindgen-macro",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.117"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7fbdf9a35adf44786aecd5ff89b4563a90325f9da0923236f6104e603c7e86be"
dependencies = [
"quote",
"wasm-bindgen-macro-support",
]
[[package]]
name = "wasm-bindgen-macro-support"
version = "0.2.117"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dca9693ef2bab6d4e6707234500350d8dad079eb508dca05530c85dc3a529ff2"
dependencies = [
"bumpalo",
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-shared"
version = "0.2.117"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39129a682a6d2d841b6c429d0c51e5cb0ed1a03829d8b3d1e69a011e62cb3d3b"
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 = "0.51.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d7249219f66ced02969388cf2bb044a09756a083d0fab1e566056b04d9fbcaa5"
+2 -18
View File
@@ -9,25 +9,13 @@ edition = "2018"
cargo-fuzz = true
[dependencies]
libfuzzer-sys = "0.4.7"
libfuzzer-sys = "0.4"
diffutils = { path = "../" }
# Prevent this from interfering with workspaces
[workspace]
members = ["."]
[[bin]]
name = "fuzz_cmp"
path = "fuzz_targets/fuzz_cmp.rs"
test = false
doc = false
[[bin]]
name = "fuzz_cmp_args"
path = "fuzz_targets/fuzz_cmp_args.rs"
test = false
doc = false
[[bin]]
name = "fuzz_patch"
path = "fuzz_targets/fuzz_patch.rs"
@@ -47,8 +35,4 @@ path = "fuzz_targets/fuzz_ed.rs"
test = false
doc = false
[[bin]]
name = "fuzz_side"
path = "fuzz_targets/fuzz_side.rs"
test = false
doc = false
-36
View File
@@ -1,36 +0,0 @@
"-l"
"--verbose"
"-b"
"--print-bytes"
"-lb"
"-bl"
"-n"
"--bytes"
"--bytes="
"--bytes=1024"
"--bytes=99999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999"
"-i"
"--ignore-initial"
"--ignore-initial="
"--ignore-initial=1024"
"--ignore-initial=99999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999:9999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999"
"-s"
"-q"
"--quiet"
"--silent"
"-"
"--"
"1kB"
"1G"
"1GB"
"1T"
"1TB"
"1P"
"1PB"
"1Z"
"1ZB"
"1Y"
"1YB"
"1Y"
"0"
"1:2"
-51
View File
@@ -1,51 +0,0 @@
#![no_main]
#[macro_use]
extern crate libfuzzer_sys;
use diffutilslib::cmp::{self, Cmp};
use std::ffi::OsString;
use std::fs::{self, File};
use std::io::Write;
fn os(s: &str) -> OsString {
OsString::from(s)
}
fuzz_target!(|x: (Vec<u8>, Vec<u8>)| {
let args = vec!["cmp", "-l", "-b", "target/fuzz.cmp.a", "target/fuzz.cmp.b"]
.into_iter()
.map(|s| os(s))
.peekable();
let (from, to) = x;
fs::create_dir_all("target").unwrap();
File::create("target/fuzz.cmp.a")
.unwrap()
.write_all(&from)
.unwrap();
File::create("target/fuzz.cmp.b")
.unwrap()
.write_all(&to)
.unwrap();
let params =
cmp::parse_params(args).unwrap_or_else(|e| panic!("Failed to parse params: {}", e));
let ret = cmp::cmp(&params);
if from == to && !matches!(ret, Ok(Cmp::Equal)) {
panic!(
"target/fuzz.cmp.a and target/fuzz.cmp.b are equal, but cmp returned {:?}.",
ret
);
} else if from != to && !matches!(ret, Ok(Cmp::Different)) {
panic!(
"target/fuzz.cmp.a and target/fuzz.cmp.b are different, but cmp returned {:?}.",
ret
);
} else if ret.is_err() {
panic!(
"target/fuzz.cmp.a and target/fuzz.cmp.b caused cmp to error ({:?}).",
ret
);
}
});
-26
View File
@@ -1,26 +0,0 @@
#![no_main]
#[macro_use]
extern crate libfuzzer_sys;
use diffutilslib::cmp;
use libfuzzer_sys::Corpus;
use std::ffi::OsString;
fn os(s: &str) -> OsString {
OsString::from(s)
}
fuzz_target!(|x: Vec<OsString>| -> Corpus {
if x.iter().any(|a| a == "--help") {
return Corpus::Reject;
}
if x.len() > 6 {
// Make sure we try to parse an option when we get longer args. x[0] will be
// the executable name.
if ![os("-l"), os("-b"), os("-s"), os("-n"), os("-i")].contains(&x[1]) {
return Corpus::Reject;
}
}
let _ = cmp::parse_params(x.into_iter().peekable());
Corpus::Keep
});
-1
View File
@@ -38,7 +38,6 @@ fuzz_target!(|x: (Vec<u8>, Vec<u8>)| {
} else {
return;
}
fs::create_dir_all("target").unwrap();
let diff = diff_w(&from, &to, "target/fuzz.file").unwrap();
File::create("target/fuzz.file.original")
.unwrap()
-1
View File
@@ -23,7 +23,6 @@ fuzz_target!(|x: (Vec<u8>, Vec<u8>)| {
return
}*/
let diff = normal_diff::diff(&from, &to, &Params::default());
fs::create_dir_all("target").unwrap();
File::create("target/fuzz.file.original")
.unwrap()
.write_all(&from)
+3 -5
View File
@@ -21,17 +21,15 @@ fuzz_target!(|x: (Vec<u8>, Vec<u8>, u8)| {
} else {
return
}*/
fs::create_dir_all("target").unwrap();
let patched = "target/fuzz.file";
let diff = unified_diff::diff(
&from,
&to,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/fuzz.file".into(),
to: "target/fuzz.file".into(),
context_count: context as usize,
..Default::default()
},
}
);
File::create("target/fuzz.file.original")
.unwrap()
-43
View File
@@ -1,43 +0,0 @@
#![no_main]
#[macro_use]
extern crate libfuzzer_sys;
use diffutilslib::side_diff;
use diffutilslib::params::Params;
use std::fs::{self, File};
use std::io::Write;
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()
};
fs::create_dir_all("target").unwrap();
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();
});
-1203
View File
File diff suppressed because it is too large Load Diff
+43 -59
View File
@@ -8,7 +8,6 @@ use std::io::Write;
use crate::params::Params;
use crate::utils::do_write_line;
use crate::utils::get_modification_time;
#[derive(Debug, PartialEq)]
pub enum DiffLine {
@@ -268,14 +267,10 @@ fn make_diff(
#[must_use]
pub fn diff(expected: &[u8], actual: &[u8], params: &Params) -> Vec<u8> {
let from_modified_time = get_modification_time(&params.from.to_string_lossy());
let to_modified_time = get_modification_time(&params.to.to_string_lossy());
let mut output = format!(
"*** {0}\t{1}\n--- {2}\t{3}\n",
"*** {0}\t\n--- {1}\t\n",
params.from.to_string_lossy(),
from_modified_time,
params.to.to_string_lossy(),
to_modified_time
params.to.to_string_lossy()
)
.into_bytes();
let diff_results = make_diff(expected, actual, params.context_count, params.brief);
@@ -381,9 +376,6 @@ pub fn diff(expected: &[u8], actual: &[u8], params: &Params) -> Vec<u8> {
mod tests {
use super::*;
use pretty_assertions::assert_eq;
use crate::utils::testcmds::PATCH_CMD;
#[test]
fn test_permutations() {
// test all possible six-line files.
@@ -397,6 +389,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"b\n" })
@@ -431,38 +424,36 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alef");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alef".into(),
to: (&format!("{target}/alef")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/ab.diff"))
File::create(&format!("{target}/ab.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef")).unwrap();
let mut fa = File::create(&format!("{target}/alef")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet")).unwrap();
let mut fb = File::create(&format!("{target}/bet")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg("--context")
.stdin(File::open(format!("{target}/ab.diff")).unwrap())
.stdin(File::open(&format!("{target}/ab.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alef")).unwrap();
let alef = fs::read(&format!("{target}/alef")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -485,6 +476,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"\n" } else { b"b\n" }).unwrap();
@@ -513,38 +505,36 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alef_");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alef_".into(),
to: (&format!("{target}/alef_")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/ab_.diff"))
File::create(&format!("{target}/ab_.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef_")).unwrap();
let mut fa = File::create(&format!("{target}/alef_")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet_")).unwrap();
let mut fb = File::create(&format!("{target}/bet_")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg("--context")
.stdin(File::open(format!("{target}/ab_.diff")).unwrap())
.stdin(File::open(&format!("{target}/ab_.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alef_")).unwrap();
let alef = fs::read(&format!("{target}/alef_")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -567,6 +557,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"" }).unwrap();
@@ -598,38 +589,36 @@ mod tests {
};
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alefx");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alefx".into(),
to: (&format!("{target}/alefx")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/abx.diff"))
File::create(&format!("{target}/abx.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefx")).unwrap();
let mut fa = File::create(&format!("{target}/alefx")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betx")).unwrap();
let mut fb = File::create(&format!("{target}/betx")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg("--context")
.stdin(File::open(format!("{target}/abx.diff")).unwrap())
.stdin(File::open(&format!("{target}/abx.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alefx")).unwrap();
let alef = fs::read(&format!("{target}/alefx")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -652,6 +641,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"f\n" })
@@ -686,38 +676,36 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let alefr_path = &format!("{target}/alefr");
let diff = diff(
&alef,
&bet,
&Params {
from: alefr_path.into(),
to: alefr_path.into(),
from: "a/alefr".into(),
to: (&format!("{target}/alefr")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/abr.diff"))
File::create(&format!("{target}/abr.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefr")).unwrap();
let mut fa = File::create(&format!("{target}/alefr")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betr")).unwrap();
let mut fb = File::create(&format!("{target}/betr")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg("--context")
.stdin(File::open(format!("{target}/abr.diff")).unwrap())
.stdin(File::open(&format!("{target}/abr.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alefr")).unwrap();
let alef = fs::read(&format!("{target}/alefr")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -729,8 +717,6 @@ mod tests {
#[test]
fn test_stop_early() {
use crate::assert_diff_eq;
let from_filename = "foo";
let from = ["a", "b", "c", ""].join("\n");
let to_filename = "bar";
@@ -745,10 +731,9 @@ mod tests {
..Default::default()
},
);
let expected_full = [
"*** foo\tTIMESTAMP",
"--- bar\tTIMESTAMP",
"*** foo\t",
"--- bar\t",
"***************",
"*** 1,3 ****",
" a",
@@ -761,7 +746,7 @@ mod tests {
"",
]
.join("\n");
assert_diff_eq!(diff_full, expected_full);
assert_eq!(diff_full, expected_full.as_bytes());
let diff_brief = diff(
from.as_bytes(),
@@ -773,9 +758,8 @@ mod tests {
..Default::default()
},
);
let expected_brief = ["*** foo\tTIMESTAMP", "--- bar\tTIMESTAMP", ""].join("\n");
assert_diff_eq!(diff_brief, expected_brief);
let expected_brief = ["*** foo\t", "--- bar\t", ""].join("\n");
assert_eq!(diff_brief, expected_brief.as_bytes());
let nodiff_full = diff(
from.as_bytes(),
-102
View File
@@ -1,102 +0,0 @@
// 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 crate::utils::report_failure_to_read_input_file;
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, stdout, Read, Write};
use std::iter::Peekable;
use std::process::{exit, ExitCode};
// 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.
pub fn main(opts: Peekable<ArgsOs>) -> ExitCode {
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
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 mut io_error = false;
let from_content = match read_file_contents(&params.from) {
Ok(from_content) => from_content,
Err(e) => {
report_failure_to_read_input_file(&params.executable, &params.from, &e);
io_error = true;
vec![]
}
};
let to_content = match read_file_contents(&params.to) {
Ok(to_content) => to_content,
Err(e) => {
report_failure_to_read_input_file(&params.executable, &params.to, &e);
io_error = true;
vec![]
}
};
if io_error {
return ExitCode::from(2);
}
// run diff
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);
}),
Format::SideBySide => {
let mut output = stdout().lock();
side_diff::diff(&from_content, &to_content, &mut output, &params)
}
};
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)
}
}
+46 -58
View File
@@ -162,9 +162,6 @@ pub fn diff(expected: &[u8], actual: &[u8], params: &Params) -> Result<Vec<u8>,
mod tests {
use super::*;
use pretty_assertions::assert_eq;
use crate::utils::testcmds::ED_CMD;
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();
@@ -191,8 +188,9 @@ mod tests {
for &d in &[0, 1, 2] {
for &e in &[0, 1, 2] {
for &f in &[0, 1, 2] {
use std::fs::File;
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"b\n" })
@@ -228,30 +226,26 @@ mod tests {
// 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"))
File::create("target/ab.ed")
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef")).unwrap();
let mut fa = File::create(&format!("{target}/alef")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet")).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
{
let output = ED_CMD
.new()
.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);
}
let output = Command::new("ed")
.arg(&format!("{target}/alef"))
.stdin(File::open("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 = fs::read(&format!("{target}/alef")).unwrap();
assert_eq!(alef, bet);
}
}
}
@@ -271,8 +265,9 @@ mod tests {
for &d in &[0, 1, 2] {
for &e in &[0, 1, 2] {
for &f in &[0, 1, 2] {
use std::fs::File;
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"\n" } else { b"b\n" }).unwrap();
@@ -301,31 +296,27 @@ mod tests {
}
// 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"))
let diff = diff_w(&alef, &bet, "target/alef_").unwrap();
File::create("target/ab_.ed")
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef_")).unwrap();
let mut fa = File::create("target/alef_").unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet_")).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
{
let output = ED_CMD
.new()
.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);
}
let output = Command::new("ed")
.arg("target/alef_")
.stdin(File::open("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 = fs::read("target/alef_").unwrap();
assert_eq!(alef, bet);
}
}
}
@@ -345,8 +336,9 @@ mod tests {
for &d in &[0, 1, 2] {
for &e in &[0, 1, 2] {
for &f in &[0, 1, 2] {
use std::fs::File;
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"f\n" })
@@ -382,30 +374,26 @@ mod tests {
// 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"))
File::create("target/abr.ed")
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefr")).unwrap();
let mut fa = File::create(&format!("{target}/alefr")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betr")).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
{
let output = ED_CMD
.new()
.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);
}
let output = Command::new("ed")
.arg(&format!("{target}/alefr"))
.stdin(File::open("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 = fs::read(&format!("{target}/alefr")).unwrap();
assert_eq!(alef, bet);
}
}
}
-4
View File
@@ -1,10 +1,7 @@
pub mod cmp;
pub mod context_diff;
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;
@@ -12,5 +9,4 @@ 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;
-25
View File
@@ -1,25 +0,0 @@
// 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);
}};
}
+67 -67
View File
@@ -3,83 +3,83 @@
// For the full copyright and license information, please view the LICENSE-*
// files that was distributed with this source code.
use std::{
env::ArgsOs,
ffi::{OsStr, OsString},
iter::Peekable,
path::{Path, PathBuf},
process::ExitCode,
};
use crate::params::{parse_params, Format};
use std::env;
use std::fs;
use std::io::{self, Write};
use std::process::{exit, ExitCode};
mod cmp;
mod context_diff;
mod diff;
mod ed_diff;
mod macros;
mod normal_diff;
mod params;
mod side_diff;
mod unified_diff;
mod utils;
/// # Panics
/// Panics if the binary path cannot be determined
fn binary_path(args: &mut Peekable<ArgsOs>) -> PathBuf {
match args.peek() {
Some(ref s) if !s.is_empty() => PathBuf::from(s),
_ => std::env::current_exe().unwrap(),
}
}
/// #Panics
/// Panics if path has no UTF-8 valid name
fn name(binary_path: &Path) -> &OsStr {
binary_path.file_stem().unwrap()
}
const VERSION: &str = env!("CARGO_PKG_VERSION");
fn usage(name: &str) {
println!("{name} {VERSION} (multi-call binary)\n");
println!("Usage: {name} [function [arguments...]]\n");
println!("Currently defined functions:\n");
println!(" cmp, diff\n");
}
fn second_arg_error(name: &OsStr) -> ! {
eprintln!("Expected utility name as second argument, got nothing.");
usage(&name.to_string_lossy());
std::process::exit(0);
}
// 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 mut args = std::env::args_os().peekable();
let exe_path = binary_path(&mut args);
let exe_name = name(&exe_path);
let util_name = if exe_name.as_encoded_bytes().ends_with(b"diffutils") {
// Discard the item we peeked.
let _ = args.next();
args.peek()
.cloned()
.unwrap_or_else(|| second_arg_error(exe_name))
} else {
OsString::from(exe_name)
};
match util_name.as_encoded_bytes() {
name if name.ends_with(b"diff") => diff::main(args),
name if name.ends_with(b"cmp") => cmp::main(args),
name => {
use std::io::{stderr, Write as _};
let _ = writeln!(
stderr(),
"{}: utility not supported",
String::from_utf8_lossy(name)
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(),
);
ExitCode::from(2)
}
};
if 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(&params.from) {
Ok(from_content) => from_content,
Err(e) => {
eprintln!("Failed to read from-file: {e}");
return ExitCode::from(2);
}
};
let to_content = match fs::read(&params.to) {
Ok(to_content) => to_content,
Err(e) => {
eprintln!("Failed to read to-file: {e}");
return ExitCode::from(2);
}
};
// run diff
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)
}
}
+32 -34
View File
@@ -215,8 +215,6 @@ mod tests {
use super::*;
use pretty_assertions::assert_eq;
use crate::utils::testcmds::PATCH_CMD;
#[test]
fn test_basic() {
let mut a = Vec::new();
@@ -241,6 +239,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"b\n" })
@@ -276,27 +275,26 @@ mod tests {
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let diff = diff(&alef, &bet, &Params::default());
File::create(format!("{target}/ab.diff"))
File::create(&format!("{target}/ab.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef")).unwrap();
let mut fa = File::create(&format!("{target}/alef")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet")).unwrap();
let mut fb = File::create(&format!("{target}/bet")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg(format!("{target}/alef"))
.stdin(File::open(format!("{target}/ab.diff")).unwrap())
.arg(&format!("{target}/alef"))
.stdin(File::open(&format!("{target}/ab.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alef")).unwrap();
let alef = fs::read(&format!("{target}/alef")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -320,6 +318,7 @@ mod tests {
for &g in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"b\n" })
@@ -368,28 +367,27 @@ mod tests {
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let diff = diff(&alef, &bet, &Params::default());
File::create(format!("{target}/abn.diff"))
File::create(&format!("{target}/abn.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefn")).unwrap();
let mut fa = File::create(&format!("{target}/alefn")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betn")).unwrap();
let mut fb = File::create(&format!("{target}/betn")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg("--normal")
.arg(format!("{target}/alefn"))
.stdin(File::open(format!("{target}/abn.diff")).unwrap())
.arg(&format!("{target}/alefn"))
.stdin(File::open(&format!("{target}/abn.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alefn")).unwrap();
let alef = fs::read(&format!("{target}/alefn")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -413,6 +411,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"\n" } else { b"b\n" }).unwrap();
@@ -442,27 +441,26 @@ mod tests {
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let diff = diff(&alef, &bet, &Params::default());
File::create(format!("{target}/ab_.diff"))
File::create(&format!("{target}/ab_.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef_")).unwrap();
let mut fa = File::create(&format!("{target}/alef_")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet_")).unwrap();
let mut fb = File::create(&format!("{target}/bet_")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg(format!("{target}/alef_"))
.stdin(File::open(format!("{target}/ab_.diff")).unwrap())
.arg(&format!("{target}/alef_"))
.stdin(File::open(&format!("{target}/ab_.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alef_")).unwrap();
let alef = fs::read(&format!("{target}/alef_")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -485,6 +483,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"f\n" })
@@ -520,27 +519,26 @@ mod tests {
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let diff = diff(&alef, &bet, &Params::default());
File::create(format!("{target}/abr.diff"))
File::create(&format!("{target}/abr.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefr")).unwrap();
let mut fa = File::create(&format!("{target}/alefr")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betr")).unwrap();
let mut fb = File::create(&format!("{target}/betr")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.arg(format!("{target}/alefr"))
.stdin(File::open(format!("{target}/abr.diff")).unwrap())
.arg(&format!("{target}/alefr"))
.stdin(File::open(&format!("{target}/abr.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alefr")).unwrap();
let alef = fs::read(&format!("{target}/alefr")).unwrap();
assert_eq!(alef, bet);
}
}
+107 -521
View File
@@ -1,6 +1,4 @@
use std::ffi::OsString;
use std::iter::Peekable;
use std::path::PathBuf;
use std::ffi::{OsStr, OsString};
use regex::Regex;
@@ -11,12 +9,21 @@ pub enum Format {
Unified,
Context,
Ed,
SideBySide,
}
#[cfg(unix)]
fn osstr_bytes(osstr: &OsStr) -> &[u8] {
use std::os::unix::ffi::OsStrExt;
osstr.as_bytes()
}
#[cfg(not(unix))]
fn osstr_bytes(osstr: &OsStr) -> Vec<u8> {
osstr.to_string_lossy().bytes().collect()
}
#[derive(Clone, Debug, Eq, PartialEq)]
pub struct Params {
pub executable: OsString,
pub from: OsString,
pub to: OsString,
pub format: Format,
@@ -25,13 +32,11 @@ pub struct Params {
pub brief: bool,
pub expand_tabs: bool,
pub tabsize: usize,
pub width: usize,
}
impl Default for Params {
fn default() -> Self {
Self {
executable: OsString::default(),
from: OsString::default(),
to: OsString::default(),
format: Format::default(),
@@ -40,42 +45,33 @@ impl Default for Params {
brief: false,
expand_tabs: false,
tabsize: 8,
width: 130,
}
}
}
pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Result<Params, String> {
pub fn parse_params<I: IntoIterator<Item = OsString>>(opts: I) -> Result<Params, String> {
let mut opts = opts.into_iter();
// parse CLI
let Some(executable) = opts.next() else {
let Some(exe) = opts.next() else {
return Err("Usage: <exe> <from> <to>".to_string());
};
let mut params = Params {
executable,
..Default::default()
};
let mut params = Params::default();
let mut from = None;
let mut to = None;
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 == "--" {
break;
}
if param == "-" {
if from.is_none() {
from = Some(param);
from = Some(OsString::from("/dev/stdin"));
} else if to.is_none() {
to = Some(param);
to = Some(OsString::from("/dev/stdin"));
} else {
return Err(format!(
"Usage: {} <from> <to>",
params.executable.to_string_lossy()
));
return Err(format!("Usage: {} <from> <to>", exe.to_string_lossy()));
}
continue;
}
@@ -91,48 +87,6 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
params.expand_tabs = true;
continue;
}
if param == "--normal" {
if format.is_some() && format != Some(Format::Normal) {
return Err("Conflicting output style options".to_string());
}
format = Some(Format::Normal);
continue;
}
if param == "-e" || param == "--ed" {
if format.is_some() && format != Some(Format::Ed) {
return Err("Conflicting output style options".to_string());
}
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.
@@ -144,68 +98,70 @@ 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) => {
if num == 0 {
return Err("invalid tabsize «0»".to_string());
}
num
}
Ok(num) => num,
Err(_) => return Err(format!("invalid tabsize «{tabsize_str}»")),
};
continue;
}
match match_context_diff_params(&param, next_param, format) {
Ok(DiffStyleMatch {
is_match,
context_count,
next_param_consumed,
}) => {
if is_match {
format = Some(Format::Context);
if context_count.is_some() {
context = context_count;
let p = osstr_bytes(&param);
if p.first() == Some(&b'-') && p.get(1) != Some(&b'-') {
let mut bit = p[1..].iter().copied().peekable();
// Can't use a for loop because `diff -30u` is supposed to make a diff
// with 30 lines of context.
while let Some(b) = bit.next() {
match b {
b'0'..=b'9' => {
params.context_count = (b - b'0') as usize;
while let Some(b'0'..=b'9') = bit.peek() {
params.context_count *= 10;
params.context_count += (bit.next().unwrap() - b'0') as usize;
}
}
if next_param_consumed {
opts.next();
b'c' => {
if format.is_some() && format != Some(Format::Context) {
return Err("Conflicting output style options".to_string());
}
format = Some(Format::Context);
}
continue;
b'e' => {
if format.is_some() && format != Some(Format::Ed) {
return Err("Conflicting output style options".to_string());
}
format = Some(Format::Ed);
}
b'u' => {
if format.is_some() && format != Some(Format::Unified) {
return Err("Conflicting output style options".to_string());
}
format = Some(Format::Unified);
}
b'U' => {
if format.is_some() && format != Some(Format::Unified) {
return Err("Conflicting output style options".to_string());
}
format = Some(Format::Unified);
let context_count_maybe = if bit.peek().is_some() {
String::from_utf8(bit.collect::<Vec<u8>>()).ok()
} else {
opts.next().map(|x| x.to_string_lossy().into_owned())
};
if let Some(context_count_maybe) =
context_count_maybe.and_then(|x| x.parse().ok())
{
params.context_count = context_count_maybe;
break;
}
return Err("Invalid context count".to_string());
}
_ => return Err(format!("Unknown option: {}", String::from_utf8_lossy(&[b]))),
}
}
Err(error) => return Err(error),
}
match match_unified_diff_params(&param, next_param, format) {
Ok(DiffStyleMatch {
is_match,
context_count,
next_param_consumed,
}) => {
if is_match {
format = Some(Format::Unified);
if context_count.is_some() {
context = context_count;
}
if next_param_consumed {
opts.next();
}
continue;
}
}
Err(error) => return Err(error),
}
if param.to_string_lossy().starts_with('-') {
return Err(format!("unrecognized option '{}'", param.to_string_lossy()));
}
if from.is_none() {
} else if from.is_none() {
from = Some(param);
} else if to.is_none() {
to = Some(param);
} else {
return Err(format!(
"Usage: {} <from> <to>",
params.executable.to_string_lossy()
));
return Err(format!("Usage: {} <from> <to>", exe.to_string_lossy()));
}
}
params.from = if let Some(from) = from {
@@ -213,136 +169,19 @@ pub fn parse_params<I: Iterator<Item = OsString>>(mut opts: Peekable<I>) -> Resu
} else if let Some(param) = opts.next() {
param
} else {
return Err(format!(
"Usage: {} <from> <to>",
params.executable.to_string_lossy()
));
return Err(format!("Usage: {} <from> <to>", exe.to_string_lossy()));
};
params.to = if let Some(to) = to {
to
} else if let Some(param) = opts.next() {
param
} else {
return Err(format!(
"Usage: {} <from> <to>",
params.executable.to_string_lossy()
));
return Err(format!("Usage: {} <from> <to>", exe.to_string_lossy()));
};
// diff DIRECTORY FILE => diff DIRECTORY/FILE FILE
// diff FILE DIRECTORY => diff FILE DIRECTORY/FILE
let mut from_path: PathBuf = PathBuf::from(&params.from);
let mut to_path: PathBuf = PathBuf::from(&params.to);
if from_path.is_dir() && to_path.is_file() {
from_path.push(to_path.file_name().unwrap());
params.from = from_path.into_os_string();
} else if from_path.is_file() && to_path.is_dir() {
to_path.push(from_path.file_name().unwrap());
params.to = to_path.into_os_string();
}
params.format = format.unwrap_or(Format::default());
if let Some(context_count) = context {
params.context_count = context_count;
}
Ok(params)
}
struct DiffStyleMatch {
is_match: bool,
context_count: Option<usize>,
next_param_consumed: bool,
}
fn match_context_diff_params(
param: &OsString,
next_param: Option<&OsString>,
format: Option<Format>,
) -> Result<DiffStyleMatch, String> {
const CONTEXT_RE: &str = r"^(-[cC](?<num1>\d*)|--context(=(?<num2>\d*))?|-(?<num3>\d+)c)$";
let regex = Regex::new(CONTEXT_RE).unwrap();
let is_match = regex.is_match(param.to_string_lossy().as_ref());
let mut context_count = None;
let mut next_param_consumed = false;
if is_match {
if format.is_some() && format != Some(Format::Context) {
return Err("Conflicting output style options".to_string());
}
let captures = regex.captures(param.to_str().unwrap()).unwrap();
let num = captures
.name("num1")
.or(captures.name("num2"))
.or(captures.name("num3"));
if let Some(numvalue) = num {
if !numvalue.as_str().is_empty() {
context_count = Some(numvalue.as_str().parse::<usize>().unwrap());
}
}
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}'")),
}
}
}
}
Ok(DiffStyleMatch {
is_match,
context_count,
next_param_consumed,
})
}
fn match_unified_diff_params(
param: &OsString,
next_param: Option<&OsString>,
format: Option<Format>,
) -> Result<DiffStyleMatch, String> {
const UNIFIED_RE: &str = r"^(-[uU](?<num1>\d*)|--unified(=(?<num2>\d*))?|-(?<num3>\d+)u)$";
let regex = Regex::new(UNIFIED_RE).unwrap();
let is_match = regex.is_match(param.to_string_lossy().as_ref());
let mut context_count = None;
let mut next_param_consumed = false;
if is_match {
if format.is_some() && format != Some(Format::Unified) {
return Err("Conflicting output style options".to_string());
}
let captures = regex.captures(param.to_str().unwrap()).unwrap();
let num = captures
.name("num1")
.or(captures.name("num2"))
.or(captures.name("num3"));
if let Some(numvalue) = num {
if !numvalue.as_str().is_empty() {
context_count = Some(numvalue.as_str().parse::<usize>().unwrap());
}
}
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}'")),
}
}
}
}
Ok(DiffStyleMatch {
is_match,
context_count,
next_param_consumed,
})
}
#[cfg(test)]
mod tests {
use super::*;
@@ -353,176 +192,29 @@ mod tests {
fn basics() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
..Default::default()
}),
parse_params(
[os("diff"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
..Default::default()
}),
parse_params(
[os("diff"), os("--normal"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("foo"), os("bar")].iter().cloned())
);
}
#[test]
fn basics_ed() {
for arg in ["-e", "--ed"] {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Ed,
..Default::default()
}),
parse_params(
[os("diff"), os(arg), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
}
}
#[test]
fn context_valid() {
for args in [vec!["-c"], vec!["--context"], vec!["--context="]] {
let mut params = vec!["diff"];
params.extend(args);
params.extend(["foo", "bar"]);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Context,
..Default::default()
}),
parse_params(params.iter().map(|x| os(x)).peekable())
);
}
for args in [
vec!["-c42"],
vec!["-C42"],
vec!["-C", "42"],
vec!["--context=42"],
vec!["-42c"],
] {
let mut params = vec!["diff"];
params.extend(args);
params.extend(["foo", "bar"]);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Context,
context_count: 42,
..Default::default()
}),
parse_params(params.iter().map(|x| os(x)).peekable())
);
}
}
#[test]
fn context_invalid() {
for args in [
vec!["-c", "42"],
vec!["-c=42"],
vec!["-c="],
vec!["-C"],
vec!["-C=42"],
vec!["-C="],
vec!["--context42"],
vec!["--context", "42"],
vec!["-42C"],
] {
let mut params = vec!["diff"];
params.extend(args);
params.extend(["foo", "bar"]);
assert!(parse_params(params.iter().map(|x| os(x)).peekable()).is_err());
}
}
#[test]
fn unified_valid() {
for args in [vec!["-u"], vec!["--unified"], vec!["--unified="]] {
let mut params = vec!["diff"];
params.extend(args);
params.extend(["foo", "bar"]);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Unified,
..Default::default()
}),
parse_params(params.iter().map(|x| os(x)).peekable())
);
}
for args in [
vec!["-u42"],
vec!["-U42"],
vec!["-U", "42"],
vec!["--unified=42"],
vec!["-42u"],
] {
let mut params = vec!["diff"];
params.extend(args);
params.extend(["foo", "bar"]);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Unified,
context_count: 42,
..Default::default()
}),
parse_params(params.iter().map(|x| os(x)).peekable())
);
}
}
#[test]
fn unified_invalid() {
for args in [
vec!["-u", "42"],
vec!["-u=42"],
vec!["-u="],
vec!["-U"],
vec!["-U=42"],
vec!["-U="],
vec!["--unified42"],
vec!["--unified", "42"],
vec!["-42U"],
] {
let mut params = vec!["diff"];
params.extend(args);
params.extend(["foo", "bar"]);
assert!(parse_params(params.iter().map(|x| os(x)).peekable()).is_err());
}
assert_eq!(
Ok(Params {
from: os("foo"),
to: os("bar"),
format: Format::Ed,
..Default::default()
}),
parse_params([os("diff"), os("-e"), os("foo"), os("bar")].iter().cloned())
);
}
#[test]
fn context_count() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Unified,
@@ -533,12 +225,10 @@ mod tests {
[os("diff"), os("-u54"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Unified,
@@ -549,12 +239,10 @@ mod tests {
[os("diff"), os("-U54"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Unified,
@@ -565,12 +253,10 @@ mod tests {
[os("diff"), os("-U"), os("54"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
format: Format::Context,
@@ -581,7 +267,6 @@ mod tests {
[os("diff"), os("-c54"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
}
@@ -589,36 +274,23 @@ mod tests {
fn report_identical_files() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
..Default::default()
}),
parse_params(
[os("diff"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("foo"), os("bar")].iter().cloned())
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
report_identical_files: true,
..Default::default()
}),
parse_params(
[os("diff"), os("-s"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("-s"), os("foo"), os("bar")].iter().cloned())
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
report_identical_files: true,
@@ -633,7 +305,6 @@ mod tests {
]
.iter()
.cloned()
.peekable()
)
);
}
@@ -641,36 +312,23 @@ mod tests {
fn brief() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
..Default::default()
}),
parse_params(
[os("diff"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("foo"), os("bar")].iter().cloned())
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
brief: true,
..Default::default()
}),
parse_params(
[os("diff"), os("-q"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("-q"), os("foo"), os("bar")].iter().cloned())
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
brief: true,
@@ -680,7 +338,6 @@ mod tests {
[os("diff"), os("--brief"), os("foo"), os("bar"),]
.iter()
.cloned()
.peekable()
)
);
}
@@ -688,22 +345,15 @@ mod tests {
fn expand_tabs() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
..Default::default()
}),
parse_params(
[os("diff"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("foo"), os("bar")].iter().cloned())
);
for option in ["-t", "--expand-tabs"] {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
expand_tabs: true,
@@ -713,7 +363,6 @@ mod tests {
[os("diff"), os(option), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
}
@@ -722,36 +371,27 @@ mod tests {
fn tabsize() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
..Default::default()
}),
parse_params(
[os("diff"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("foo"), os("bar")].iter().cloned())
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
tabsize: 1,
tabsize: 0,
..Default::default()
}),
parse_params(
[os("diff"), os("--tabsize=1"), os("foo"), os("bar")]
[os("diff"), os("--tabsize=0"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("bar"),
tabsize: 42,
@@ -761,42 +401,36 @@ mod tests {
[os("diff"), os("--tabsize=42"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
);
assert!(parse_params(
[os("diff"), os("--tabsize"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(parse_params(
[os("diff"), os("--tabsize="), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(parse_params(
[os("diff"), os("--tabsize=r2"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(parse_params(
[os("diff"), os("--tabsize=-1"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(parse_params(
[os("diff"), os("--tabsize=r2"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(parse_params(
@@ -808,7 +442,6 @@ mod tests {
]
.iter()
.cloned()
.peekable()
)
.is_err());
}
@@ -816,104 +449,57 @@ mod tests {
fn double_dash() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("-g"),
to: os("-h"),
..Default::default()
}),
parse_params(
[os("diff"), os("--"), os("-g"), os("-h")]
.iter()
.cloned()
.peekable()
)
parse_params([os("diff"), os("--"), os("-g"), os("-h")].iter().cloned())
);
}
#[test]
fn default_to_stdin() {
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("foo"),
to: os("-"),
to: os("/dev/stdin"),
..Default::default()
}),
parse_params([os("diff"), os("foo"), os("-")].iter().cloned().peekable())
parse_params([os("diff"), os("foo"), os("-")].iter().cloned())
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("-"),
from: os("/dev/stdin"),
to: os("bar"),
..Default::default()
}),
parse_params([os("diff"), os("-"), os("bar")].iter().cloned().peekable())
parse_params([os("diff"), os("-"), os("bar")].iter().cloned())
);
assert_eq!(
Ok(Params {
executable: os("diff"),
from: os("-"),
to: os("-"),
from: os("/dev/stdin"),
to: os("/dev/stdin"),
..Default::default()
}),
parse_params([os("diff"), os("-"), os("-")].iter().cloned().peekable())
parse_params([os("diff"), os("-"), os("-")].iter().cloned())
);
assert!(parse_params(
[os("diff"), os("foo"), os("bar"), os("-")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(parse_params(
[os("diff"), os("-"), os("-"), os("-")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(parse_params([os("diff"), os("foo"), os("bar"), os("-")].iter().cloned()).is_err());
assert!(parse_params([os("diff"), os("-"), os("-"), os("-")].iter().cloned()).is_err());
}
#[test]
fn missing_arguments() {
assert!(parse_params([os("diff")].iter().cloned().peekable()).is_err());
assert!(parse_params([os("diff"), os("foo")].iter().cloned().peekable()).is_err());
assert!(parse_params([os("diff")].iter().cloned()).is_err());
assert!(parse_params([os("diff"), os("foo")].iter().cloned()).is_err());
}
#[test]
fn unknown_argument() {
assert!(parse_params(
[os("diff"), os("-g"), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
.is_err());
assert!(
parse_params([os("diff"), os("-g"), os("bar")].iter().cloned().peekable()).is_err()
parse_params([os("diff"), os("-g"), os("foo"), os("bar")].iter().cloned()).is_err()
);
assert!(parse_params([os("diff"), os("-g")].iter().cloned().peekable()).is_err());
assert!(parse_params([os("diff"), os("-g"), os("bar")].iter().cloned()).is_err());
assert!(parse_params([os("diff"), os("-g")].iter().cloned()).is_err());
}
#[test]
fn empty() {
assert!(parse_params([].iter().cloned().peekable()).is_err());
}
#[test]
fn conflicting_output_styles() {
for (arg1, arg2) in [
("-u", "-c"),
("-u", "-e"),
("-c", "-u"),
("-c", "-U42"),
("-u", "--normal"),
("--normal", "-e"),
("--context", "--normal"),
] {
assert!(parse_params(
[os("diff"), os(arg1), os(arg2), os("foo"), os("bar")]
.iter()
.cloned()
.peekable()
)
.is_err());
}
assert!(parse_params([].iter().cloned()).is_err());
}
}
-1263
View File
File diff suppressed because it is too large Load Diff
+52 -70
View File
@@ -8,7 +8,6 @@ use std::io::Write;
use crate::params::Params;
use crate::utils::do_write_line;
use crate::utils::get_modification_time;
#[derive(Debug, PartialEq)]
pub enum DiffLine {
@@ -239,14 +238,10 @@ fn make_diff(
#[must_use]
pub fn diff(expected: &[u8], actual: &[u8], params: &Params) -> Vec<u8> {
let from_modified_time = get_modification_time(&params.from.to_string_lossy());
let to_modified_time = get_modification_time(&params.to.to_string_lossy());
let mut output = format!(
"--- {0}\t{1}\n+++ {2}\t{3}\n",
"--- {0}\t\n+++ {1}\t\n",
params.from.to_string_lossy(),
from_modified_time,
params.to.to_string_lossy(),
to_modified_time
params.to.to_string_lossy()
)
.into_bytes();
let diff_results = make_diff(expected, actual, params.context_count, params.brief);
@@ -408,8 +403,6 @@ mod tests {
use super::*;
use pretty_assertions::assert_eq;
use crate::utils::testcmds::PATCH_CMD;
#[test]
fn test_permutations() {
let target = "target/unified-diff/";
@@ -423,6 +416,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"b\n" })
@@ -457,24 +451,23 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alef");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alef".into(),
to: (&format!("{target}/alef")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/ab.diff"))
File::create(&format!("{target}/ab.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef")).unwrap();
let mut fa = File::create(&format!("{target}/alef")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet")).unwrap();
let mut fb = File::create(&format!("{target}/bet")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
@@ -494,18 +487,15 @@ mod tests {
.unwrap_or_else(|_| String::from("[Invalid UTF-8]"))
);
use crate::utils::testcmds::PATCH_CMD;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.stdin(File::open(format!("{target}/ab.diff")).unwrap())
.stdin(File::open(&format!("{target}/ab.diff")).unwrap())
.output()
.unwrap();
println!("{}", String::from_utf8_lossy(&output.stdout));
println!("{}", String::from_utf8_lossy(&output.stderr));
assert!(output.status.success(), "{output:?}");
let alef = fs::read(format!("{target}/alef")).unwrap();
let alef = fs::read(&format!("{target}/alef")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -529,6 +519,7 @@ mod tests {
for &g in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"b\n" })
@@ -576,37 +567,35 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alefn");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alefn".into(),
to: (&format!("{target}/alefn")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/abn.diff"))
File::create(&format!("{target}/abn.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefn")).unwrap();
let mut fa = File::create(&format!("{target}/alefn")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betn")).unwrap();
let mut fb = File::create(&format!("{target}/betn")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.stdin(File::open(format!("{target}/abn.diff")).unwrap())
.stdin(File::open(&format!("{target}/abn.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alefn")).unwrap();
let alef = fs::read(&format!("{target}/alefn")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -631,6 +620,7 @@ mod tests {
for &g in &[0, 1, 2, 3] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"\n" } else { b"b\n" }).unwrap();
@@ -673,37 +663,35 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alef_");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alef_".into(),
to: (&format!("{target}/alef_")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/ab_.diff"))
File::create(&format!("{target}/ab_.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alef_")).unwrap();
let mut fa = File::create(&format!("{target}/alef_")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/bet_")).unwrap();
let mut fb = File::create(&format!("{target}/bet_")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.stdin(File::open(format!("{target}/ab_.diff")).unwrap())
.stdin(File::open(&format!("{target}/ab_.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alef_")).unwrap();
let alef = fs::read(&format!("{target}/alef_")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -727,6 +715,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"" }).unwrap();
@@ -755,37 +744,35 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alefx");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alefx".into(),
to: (&format!("{target}/alefx")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/abx.diff"))
File::create(&format!("{target}/abx.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefx")).unwrap();
let mut fa = File::create(&format!("{target}/alefx")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betx")).unwrap();
let mut fb = File::create(&format!("{target}/betx")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.stdin(File::open(format!("{target}/abx.diff")).unwrap())
.stdin(File::open(&format!("{target}/abx.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alefx")).unwrap();
let alef = fs::read(&format!("{target}/alefx")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -808,6 +795,7 @@ mod tests {
for &f in &[0, 1, 2] {
use std::fs::{self, File};
use std::io::Write;
use std::process::Command;
let mut alef = Vec::new();
let mut bet = Vec::new();
alef.write_all(if a == 0 { b"a\n" } else { b"f\n" })
@@ -842,37 +830,35 @@ mod tests {
}
// This test diff is intentionally reversed.
// We want it to turn the alef into bet.
let patched = &format!("{target}/alefr");
let diff = diff(
&alef,
&bet,
&Params {
from: patched.into(),
to: patched.into(),
from: "a/alefr".into(),
to: (&format!("{target}/alefr")).into(),
context_count: 2,
..Default::default()
},
);
File::create(format!("{target}/abr.diff"))
File::create(&format!("{target}/abr.diff"))
.unwrap()
.write_all(&diff)
.unwrap();
let mut fa = File::create(format!("{target}/alefr")).unwrap();
let mut fa = File::create(&format!("{target}/alefr")).unwrap();
fa.write_all(&alef[..]).unwrap();
let mut fb = File::create(format!("{target}/betr")).unwrap();
let mut fb = File::create(&format!("{target}/betr")).unwrap();
fb.write_all(&bet[..]).unwrap();
let _ = fa;
let _ = fb;
let output = PATCH_CMD
.new()
let output = Command::new("patch")
.arg("-p0")
.stdin(File::open(format!("{target}/abr.diff")).unwrap())
.stdin(File::open(&format!("{target}/abr.diff")).unwrap())
.output()
.unwrap();
assert!(output.status.success(), "{output:?}");
//println!("{}", String::from_utf8_lossy(&output.stdout));
//println!("{}", String::from_utf8_lossy(&output.stderr));
let alef = fs::read(format!("{target}/alefr")).unwrap();
let alef = fs::read(&format!("{target}/alefr")).unwrap();
assert_eq!(alef, bet);
}
}
@@ -884,8 +870,6 @@ mod tests {
#[test]
fn test_stop_early() {
use crate::assert_diff_eq;
let from_filename = "foo";
let from = ["a", "b", "c", ""].join("\n");
let to_filename = "bar";
@@ -900,10 +884,9 @@ mod tests {
..Default::default()
},
);
let expected_full = [
"--- foo\tTIMESTAMP",
"+++ bar\tTIMESTAMP",
"--- foo\t",
"+++ bar\t",
"@@ -1,3 +1,3 @@",
" a",
"-b",
@@ -912,7 +895,7 @@ mod tests {
"",
]
.join("\n");
assert_diff_eq!(diff_full, expected_full);
assert_eq!(diff_full, expected_full.as_bytes());
let diff_brief = diff(
from.as_bytes(),
@@ -924,9 +907,8 @@ mod tests {
..Default::default()
},
);
let expected_brief = ["--- foo\tTIMESTAMP", "+++ bar\tTIMESTAMP", ""].join("\n");
assert_diff_eq!(diff_brief, expected_brief);
let expected_brief = ["--- foo\t", "+++ bar\t", ""].join("\n");
assert_eq!(diff_brief, expected_brief.as_bytes());
let nodiff_full = diff(
from.as_bytes(),
+6 -188
View File
@@ -3,8 +3,8 @@
// For the full copyright and license information, please view the LICENSE-*
// files that was distributed with this source code.
use regex::Regex;
use std::{ffi::OsString, io::Write};
use std::io::Write;
use unicode_width::UnicodeWidthStr;
/// Replace tabs by spaces in the input line.
@@ -52,145 +52,6 @@ pub fn do_write_line(
}
}
/// Retrieves the modification time of the input file specified by file path
/// If an error occurs, it returns the current system time
pub fn get_modification_time(file_path: &str) -> String {
use chrono::{DateTime, Local};
use std::fs;
use std::time::SystemTime;
let modification_time: SystemTime = fs::metadata(file_path)
.and_then(|m| m.modified())
.unwrap_or(SystemTime::now());
let modification_time: DateTime<Local> = modification_time.into();
let modification_time: String = modification_time
.format("%Y-%m-%d %H:%M:%S%.9f %z")
.to_string();
modification_time
}
pub fn format_failure_to_read_input_file(
executable: &OsString,
filepath: &OsString,
error: &std::io::Error,
) -> String {
// std::io::Error's display trait outputs "{detail} (os error {code})"
// but we want only the {detail} (error string) part
let error_code_re = Regex::new(r"\ \(os\ error\ \d+\)$").unwrap();
format!(
"{}: {}: {}",
executable.to_string_lossy(),
filepath.to_string_lossy(),
error_code_re.replace(error.to_string().as_str(), ""),
)
}
pub fn report_failure_to_read_input_file(
executable: &OsString,
filepath: &OsString,
error: &std::io::Error,
) {
eprintln!(
"{}",
format_failure_to_read_input_file(executable, filepath, error)
);
}
#[cfg(test)]
pub mod testcmds {
// Command construction wrapper that provides some validation and non-obscure, "fail fast"
// feedback and error messages.
use std::any::Any;
use std::io::Write;
use std::panic::catch_unwind;
use std::process::{Command, Stdio};
use std::sync::LazyLock;
pub struct CmdFactory {
cmd: &'static str,
validated_once: LazyLock<Result<(), String>>,
validate: fn(&CmdFactory) -> (),
}
impl CmdFactory {
pub fn new(&self) -> Command {
match &*self.validated_once {
Ok(()) => Command::new(self.cmd),
Err(errmsg) => panic!(
"'{}' validation failed in earlier thread/test: {}",
self.cmd, errmsg
),
}
}
// "self" is not compatible with static initialization
fn try_catch_validate(cmd: &CmdFactory) -> Result<(), String> {
// Note catch_unwind() does _not_ hide error messages, stack traces, etc.
catch_unwind(|| {
let _ = (cmd.validate)(cmd);
})
.map_err(find_panic_message)
}
}
fn find_panic_message(payload: Box<dyn Any + Send>) -> String {
// https://github.com/rust-lang/rust/blob/1.95.0/library/std/src/panicking.rs#L771
if let Some(&s) = payload.downcast_ref::<&'static str>() {
String::from(s)
} else if let Some(s) = payload.downcast_ref::<String>() {
s.clone()
} else {
format!(
"Unusual panic payload type {:?}, look for the first thread/test that failed",
payload.type_id(),
)
}
}
pub static PATCH_CMD: CmdFactory = CmdFactory {
cmd: if cfg!(target_os = "macos") {
"gpatch" // brew install gpatch
} else {
"patch"
},
validated_once: LazyLock::new(|| CmdFactory::try_catch_validate(&PATCH_CMD)),
validate: (|myself| {
let output = Command::new(myself.cmd)
.arg("--version")
.output()
.expect(format!("`{} --version` failed", myself.cmd).as_str());
// Non-GNU versions have subtle differences. When some newlines are missing in some test
// patches, the macOS version can even stall the whole test run.
assert!(output.stdout.starts_with(b"GNU patch"));
assert!(output.status.success());
}),
};
pub static ED_CMD: CmdFactory = CmdFactory {
cmd: "ed",
validated_once: LazyLock::new(|| CmdFactory::try_catch_validate(&ED_CMD)),
validate: (|myself| {
let mut child = Command::new(myself.cmd)
.arg("!echo hello_ed")
.stdin(Stdio::piped())
.stdout(Stdio::piped())
.spawn()
.expect("Failed to start 'ed' command");
let mut stdin = child.stdin.take().unwrap();
writeln!(stdin, "1p\nq").expect("Failed to send command to 'ed'");
let output = child
.wait_with_output()
.expect("Failed to read 'ed' stdout");
assert_eq!(String::from_utf8_lossy(&output.stdout), "9\nhello_ed\n");
}),
};
}
#[cfg(test)]
mod tests {
use super::*;
@@ -221,11 +82,10 @@ mod tests {
// Note: The Woman Scientist emoji (👩‍🔬) is a ZWJ sequence combining
// the Woman emoji (👩) and the Microscope emoji (🔬). On supported platforms
// it is displayed as a single emoji and has a print size of 2 columns.
// Terminal emulators tend to not support this, and display the two emojis
// side by side, thus accounting for a print size of 4 columns, but the
// unicode_width crate reports a correct size of 2.
assert_tab_expansion("foo\t👩‍🔬\tbaz", 6, "foo 👩‍🔬 baz");
// it is displayed as a single emoji and should have a print size of 2 columns,
// but terminal emulators tend to not support this, and display the two emojis
// side by side, thus accounting for a print size of 4 columns.
assert_tab_expansion("foo\t👩‍🔬\tbaz", 6, "foo 👩‍🔬 baz");
}
#[test]
@@ -255,46 +115,4 @@ mod tests {
assert_line_written("foo bar\tbaz", true, 8, "foo bar baz");
}
}
mod modification_time {
use super::*;
#[test]
fn set_time() {
use chrono::{DateTime, Local};
use std::time::SystemTime;
use tempfile::NamedTempFile;
let temp = NamedTempFile::new().unwrap();
// set file modification time equal to current time
let current = SystemTime::now();
let _ = temp.as_file().set_modified(current);
// format current time
let current: DateTime<Local> = current.into();
let current: String = current.format("%Y-%m-%d %H:%M:%S%.9f %z").to_string();
// verify
assert_eq!(
current,
get_modification_time(&temp.path().to_string_lossy())
);
}
#[test]
fn invalid_file() {
use chrono::{DateTime, Local};
use std::time::SystemTime;
let invalid_file = "target/utils/invalid-file";
// store current time before calling `get_modification_time`
// Because the file is invalid, it will return SystemTime::now()
// which will be greater than previously saved time
let current_time: DateTime<Local> = SystemTime::now().into();
let m_time: DateTime<Local> = get_modification_time(invalid_file).parse().unwrap();
assert!(m_time > current_time);
}
}
}
+169 -854
View File
File diff suppressed because it is too large Load Diff
+26 -39
View File
@@ -19,9 +19,9 @@
# By default it expects a release build of the diffutils binary, but a
# different build profile can be specified as an argument
# (e.g. 'dev' or 'test').
# Unless overridden by the $TESTS environment variable, all tests in the test
# Unless overriden by the $TESTS environment variable, all tests in the test
# suite will be run. Tests targeting a command that is not yet implemented
# (e.g. diff3 or sdiff) are skipped.
# (e.g. cmp, diff3 or sdiff) are skipped.
scriptpath=$(dirname "$(readlink -f "$0")")
rev=$(git rev-parse HEAD)
@@ -57,13 +57,8 @@ upstreamrev=$(git rev-parse HEAD)
mkdir src
cd src
ln -s "$binary" diff
ln -s "$binary" cmp
cd ../tests
# Fetch tests/init.sh from the gnulib repository (needed since
# https://git.savannah.gnu.org/cgit/diffutils.git/commit/tests?id=1d2456f539)
curl -sL "$gitserver/gitweb/?p=gnulib.git;a=blob_plain;f=tests/init.sh;hb=HEAD" -o init.sh
if [[ -n "$TESTS" ]]
then
tests="$TESTS"
@@ -76,6 +71,7 @@ total=$(echo "$tests" | wc -w)
echo "Running $total tests"
export LC_ALL=C
export KEEP=yes
exitcode=0
timestamp=$(date -Iseconds)
urlroot="$gitserver/cgit/diffutils.git/tree/tests/"
passed=0
@@ -86,43 +82,35 @@ for test in $tests
do
result="FAIL"
url="$urlroot$test?id=$upstreamrev"
# Run only the tests that invoke `diff` or `cmp`,
# Run only the tests that invoke `diff`,
# because other binaries aren't implemented yet
if ! grep -E -s -q "(diff3|sdiff)" "$test"
if ! grep -E -s -q "(cmp|diff3|sdiff)" "$test"
then
sh "$test" 1> stdout.txt 2> stderr.txt && result="PASS"
if [[ $? = 77 ]]
then
result="SKIP"
else
json+="{\"test\":\"$test\",\"result\":\"$result\","
json+="\"url\":\"$url\","
json+="\"stdout\":\"$(base64 -w0 < stdout.txt)\","
json+="\"stderr\":\"$(base64 -w0 < stderr.txt)\","
json+="\"files\":{"
cd gt-$test.*
# Note: this doesn't include the contents of subdirectories,
# but there isn't much value added in doing so
for file in *
do
[[ -f "$file" ]] && json+="\"$file\":\"$(base64 -w0 < "$file")\","
done
json="${json%,}}},"
cd - > /dev/null
[[ "$result" = "PASS" ]] && (( passed++ ))
[[ "$result" = "FAIL" ]] && (( failed++ ))
fi
sh "$test" 1> stdout.txt 2> stderr.txt && result="PASS" || exitcode=1
json+="{\"test\":\"$test\",\"result\":\"$result\","
json+="\"url\":\"$url\","
json+="\"stdout\":\"$(base64 -w0 < stdout.txt)\","
json+="\"stderr\":\"$(base64 -w0 < stderr.txt)\","
json+="\"files\":{"
cd gt-$test.*
# Note: this doesn't include the contents of subdirectories,
# but there isn't much value added in doing so
for file in *
do
[[ -f "$file" ]] && json+="\"$file\":\"$(base64 -w0 < "$file")\","
done
json="${json%,}}},"
cd - > /dev/null
[[ "$result" = "PASS" ]] && (( passed++ ))
[[ "$result" = "FAIL" ]] && (( failed++ ))
else
result="SKIP"
(( skipped++ ))
json+="{\"test\":\"$test\",\"url\":\"$url\",\"result\":\"$result\"},"
fi
color=2 # green
[[ "$result" = "FAIL" ]] && color=1 # red
if [[ $result = "SKIP" ]]
then
(( skipped++ ))
json+="{\"test\":\"$test\",\"url\":\"$url\",\"result\":\"$result\"},"
color=3 # yellow
fi
[[ "$result" = "SKIP" ]] && color=3 # yellow
printf " %-40s $(tput setaf $color)$result$(tput sgr0)\n" "$test"
done
echo ""
@@ -150,5 +138,4 @@ resultsfile="test-results.json"
echo "$json" | jq > "$resultsfile"
echo "Results written to $scriptpath/$resultsfile"
(( failed > 0 )) && exit 1
exit 0
exit $exitcode
-158
View File
@@ -1,158 +0,0 @@
#!/usr/bin/env python3
"""
Compare the current GNU test results to the last results gathered from the main branch to
highlight if a PR is making the results better/worse.
Don't exit with error code if all failing tests are in the ignore-intermittent.txt list.
"""
import json
import sys
import argparse
from pathlib import Path
def load_ignore_list(ignore_file):
"""Load list of intermittent test names to ignore from file."""
ignore_set = set()
if ignore_file and Path(ignore_file).exists():
with open(ignore_file, "r") as f:
for line in f:
line = line.strip()
if line and not line.startswith("#"):
ignore_set.add(line)
return ignore_set
def extract_test_results(json_data):
"""Extract test results from a diffutils test-results.json.
Note: unlike sed, diffutils JSON has no 'summary' object results are
computed from the 'tests' array using the 'result' and 'test' fields.
"""
tests = json_data.get("tests", [])
passed = sum(1 for t in tests if t.get("result") == "PASS")
failed = sum(1 for t in tests if t.get("result") == "FAIL")
skipped = sum(1 for t in tests if t.get("result") == "SKIP")
summary = {"total": len(tests), "passed": passed, "failed": failed, "skipped": skipped}
failed_tests = [t["test"] for t in tests if t.get("result") == "FAIL"]
return summary, failed_tests
def compare_results(current_file, reference_file, ignore_file=None, output_file=None):
"""Compare current results with reference results."""
ignore_set = load_ignore_list(ignore_file)
try:
with open(current_file, "r") as f:
current_data = json.load(f)
current_summary, current_failed = extract_test_results(current_data)
except Exception as e:
print(f"Error loading current results: {e}")
return 1
try:
with open(reference_file, "r") as f:
reference_data = json.load(f)
reference_summary, reference_failed = extract_test_results(reference_data)
except Exception as e:
print(f"Error loading reference results: {e}")
return 1
# Calculate differences
pass_diff = int(current_summary.get("passed", 0)) - int(reference_summary.get("passed", 0))
fail_diff = int(current_summary.get("failed", 0)) - int(reference_summary.get("failed", 0))
total_diff = int(current_summary.get("total", 0)) - int(reference_summary.get("total", 0))
# Find new failures and improvements
current_failed_set = set(current_failed)
reference_failed_set = set(reference_failed)
new_failures = current_failed_set - reference_failed_set
improvements = reference_failed_set - current_failed_set
# Filter out intermittent failures
non_intermittent_new_failures = new_failures - ignore_set
# Check if results are identical (no changes)
no_changes = (
pass_diff == 0
and fail_diff == 0
and total_diff == 0
and not new_failures
and not improvements
)
# If no changes, write empty output to prevent comment posting
if no_changes:
if output_file:
with open(output_file, "w") as f:
f.write("")
return 0
# Prepare output message
output_lines = []
output_lines.append("Test results comparison:")
output_lines.append(
f" Current: TOTAL: {current_summary.get('total', 0)} / PASSED: {current_summary.get('passed', 0)} / FAILED: {current_summary.get('failed', 0)} / SKIPPED: {current_summary.get('skipped', 0)}"
)
output_lines.append(
f" Reference: TOTAL: {reference_summary.get('total', 0)} / PASSED: {reference_summary.get('passed', 0)} / FAILED: {reference_summary.get('failed', 0)} / SKIPPED: {reference_summary.get('skipped', 0)}"
)
output_lines.append("")
if pass_diff != 0 or fail_diff != 0 or total_diff != 0:
output_lines.append("Changes from main branch:")
output_lines.append(f" TOTAL: {total_diff:+d}")
output_lines.append(f" PASSED: {pass_diff:+d}")
output_lines.append(f" FAILED: {fail_diff:+d}")
output_lines.append("")
if new_failures:
output_lines.append(f"New test failures ({len(new_failures)}):")
for test in sorted(new_failures):
if test in ignore_set:
output_lines.append(f" - {test} (intermittent)")
else:
output_lines.append(f" - {test}")
output_lines.append("")
if improvements:
output_lines.append(f"Test improvements ({len(improvements)}):")
for test in sorted(improvements):
output_lines.append(f" + {test}")
output_lines.append("")
output_text = "\n".join(output_lines)
if output_file:
with open(output_file, "w") as f:
f.write(output_text)
else:
print(output_text)
if non_intermittent_new_failures:
print(
f"ERROR: Found {len(non_intermittent_new_failures)} new non-intermittent test failures"
)
return 1
return 0
def main():
parser = argparse.ArgumentParser(description="Compare GNU diffutils test results")
parser.add_argument("current", help="Current test results JSON file")
parser.add_argument("reference", help="Reference test results JSON file")
parser.add_argument(
"--ignore-file", help="File containing intermittent test names to ignore"
)
parser.add_argument("--output", help="Output file for comparison results")
args = parser.parse_args()
return compare_results(args.current, args.reference, args.ignore_file, args.output)
if __name__ == "__main__":
sys.exit(main())