Add mask image utilities

.github/CODEOWNERS

@@ -1 +0,0 @@
-* @tailwindlabs/engineering

.github/CONTRIBUTING.md

@@ -1,48 +1,12 @@
 # Contributing
 
-## Requirements
-
-Before getting started, ensure your system has access to the following tools:
-
-- [Node.js](https://nodejs.org/)
-- [Rustup](https://rustup.rs/)
-- [pnpm](https://pnpm.io/)
-
-## Getting started
-
-```sh
-# Install dependencies
-pnpm install
-
-# Install Rust toolchain and WASM targets
-rustup default stable
-rustup target add wasm32-wasip1-threads
-
-# Build the project
-pnpm build
-```
-
-## Development workflow
-
-During development, you can run tests in watch mode:
-
-```sh
-pnpm tdd
-```
-
-The `playgrounds` directory contains example projects you can use to test your changes. To start the Vite playground, use:
-
-```sh
-pnpm build && pnpm vite
-```
-
 ## Bug fixes
 
 If you've found a bug in Tailwind that you'd like to fix, [submit a pull request](https://github.com/tailwindlabs/tailwindcss/pulls) with your changes. Include a helpful description of the problem and how your changes address it, and provide tests so we can verify the fix works as expected.
 
 ## New features
 
-If there's a new feature you'd like to see added to Tailwind, [share your idea with us](https://github.com/tailwindlabs/tailwindcss/discussions/new?category=ideas) in our discussion forum to get it on our radar as something to consider for a future release before starting work on it.
+If there's a new feature you'd like to see added to Tailwind, [share your idea with us](https://github.com/tailwindlabs/tailwindcss/discussions/new?category=ideas) in our discussion forum to get it on our radar as something to consider for a future release.
 
 **Please note that we don't often accept pull requests for new features.** Adding a new feature to Tailwind requires us to think through the entire problem ourselves to make sure we agree with the proposed API, which means the feature needs to be high on our own priority list for us to be able to give it the attention it needs.
 
@@ -50,7 +14,7 @@ If you open a pull request for a new feature, we're likely to close it not becau
 
 ## Coding standards
 
-Our code formatting rules are defined in the `"prettier"` section of [package.json](https://github.com/tailwindlabs/tailwindcss/blob/main/package.json). You can check your code against these standards by running:
+Our code formatting rules are defined in the `"prettier"` section of [package.json](https://github.com/tailwindcss/tailwindcss/blob/next/package.json). You can check your code against these standards by running:
 
 ```sh
 pnpm run lint
@@ -64,40 +28,10 @@ pnpm run format
 
 ## Running tests
 
-You can run the TypeScript and Rust test suites using the following command:
+You can run the test suite using the following commands:
 
 ```sh
-pnpm test
+pnpm build && pnpm test
 ```
 
-To run the integration tests, use:
-
-```sh
-pnpm build && pnpm test:integrations
-```
-
-Additionally, some features require testing in browsers (i.e. to ensure CSS variable resolution works as expected). These can be run via:
-
-```sh
-pnpm build && pnpm test:ui
-```
-
-Please ensure that all tests are passing when submitting a pull request. If you're adding new features to Tailwind CSS, always include tests.
-
-After a successful build, you can also use the npm package tarballs created inside the `dist/` folder to install your build in other local projects.
-
-## Pull request process
-
-When submitting a pull request:
-
-- Ensure the pull request title and description explain the changes you made and why you made them.
-- Include a test plan section that outlines how you tested your contributions. We do not accept contributions without tests.
-- Ensure all tests pass. You can add the tag `[ci-all]` in your pull request description to run the test suites across all platforms.
-
-When a pull request is created, Tailwind CSS maintainers will be notified automatically.
-
-## Communication
-
-- **GitHub discussions**: For feature ideas and general questions
-- **GitHub issues**: For bug reports
-- **GitHub pull requests**: For code contributions
+Please ensure that the tests are passing when submitting a pull request. If you're adding new features to Tailwind, please include tests.

.github/FUNDING.yml

@@ -1 +0,0 @@
-custom: ['https://tailwindcss.com/sponsor']

.github/ISSUE_TEMPLATE/bug-report.md

@@ -1,39 +0,0 @@
----
-name: Bug report
-about: If you've already asked for help with a problem and confirmed something is broken with Tailwind CSS itself, create a bug report.
-title: ''
-labels: ''
-assignees: ''
----
-
-<!-- Please provide all of the information requested below. We're a small team and without all of this information it's not possible for us to help and your bug report will be closed. -->
-
-**What version of Tailwind CSS are you using?**
-
-For example: v4.0.6
-
-**What build tool (or framework if it abstracts the build tool) are you using?**
-
-For example: postcss-cli 11.0.0, Next.js 15.1.7, Vite 6.1.0
-
-**What version of Node.js are you using?**
-
-For example: v20.0.0
-
-**What browser are you using?**
-
-For example: Chrome, Safari, or N/A
-
-**What operating system are you using?**
-
-For example: macOS, Windows
-
-**Reproduction URL**
-
-A Tailwind Play link or public GitHub repo that includes a minimal reproduction of the bug. **Please do not link to your actual project**, what we need instead is a _minimal_ reproduction in a fresh project without any unnecessary code. This means it doesn't matter if your real project is private/confidential, since we want a link to a separate, isolated reproduction anyways.
-
-A reproduction is **required** when filing an issue — any issue opened without a reproduction will be closed and you'll be asked to create a new issue that includes a reproduction. We're a small team and we can't keep up with the volume of issues we receive if we need to reproduce each issue from scratch ourselves.
-
-**Describe your issue**
-
-Describe the problem you're seeing, any important steps to reproduce and what behavior you expect instead.

.github/ISSUE_TEMPLATE/config.yml

@@ -6,6 +6,9 @@ contact_links:
   - name: Feature Request
     url: https://github.com/tailwindlabs/tailwindcss/discussions/new?category=ideas
     about: 'Suggest any ideas you have using our discussion forums.'
+  - name: Bug Report
+    url: https://github.com/tailwindlabs/tailwindcss/issues/new?body=%3C%21--%20Please%20provide%20all%20of%20the%20information%20requested%20below.%20We%27re%20a%20small%20team%20and%20without%20all%20of%20this%20information%20it%27s%20not%20possible%20for%20us%20to%20help%20and%20your%20bug%20report%20will%20be%20closed.%20--%3E%0A%0A%2A%2AWhat%20version%20of%20Tailwind%20CSS%20are%20you%20using%3F%2A%2A%0A%0AFor%20example%3A%20v2.0.4%0A%0A%2A%2AWhat%20build%20tool%20%28or%20framework%20if%20it%20abstracts%20the%20build%20tool%29%20are%20you%20using%3F%2A%2A%0A%0AFor%20example%3A%20postcss-cli%208.3.1%2C%20Next.js%2010.0.9%2C%20webpack%205.28.0%0A%0A%2A%2AWhat%20version%20of%20Node.js%20are%20you%20using%3F%2A%2A%0A%0AFor%20example%3A%20v12.0.0%0A%0A%2A%2AWhat%20browser%20are%20you%20using%3F%2A%2A%0A%0AFor%20example%3A%20Chrome%2C%20Safari%2C%20or%20N%2FA%0A%0A%2A%2AWhat%20operating%20system%20are%20you%20using%3F%2A%2A%0A%0AFor%20example%3A%20macOS%2C%20Windows%0A%0A%2A%2AReproduction%20URL%2A%2A%0A%0AA%20Tailwind%20Play%20link%20or%20public%20GitHub%20repo%20that%20includes%20a%20minimal%20reproduction%20of%20the%20bug.%20%2A%2APlease%20do%20not%20link%20to%20your%20actual%20project%2A%2A%2C%20what%20we%20need%20instead%20is%20a%20_minimal_%20reproduction%20in%20a%20fresh%20project%20without%20any%20unnecessary%20code.%20This%20means%20it%20doesn%27t%20matter%20if%20your%20real%20project%20is%20private%2Fconfidential%2C%20since%20we%20want%20a%20link%20to%20a%20separate%2C%20isolated%20reproduction%20anyways.%0A%0AA%20reproduction%20is%20%2A%2Arequired%2A%2A%20when%20filing%20an%20issue%20%E2%80%94%20any%20issue%20opened%20without%20a%20reproduction%20will%20be%20closed%20and%20you%27ll%20be%20asked%20to%20create%20a%20new%20issue%20that%20includes%20a%20reproduction.%20We%27re%20a%20small%20team%20and%20we%20can%27t%20keep%20up%20with%20the%20volume%20of%20issues%20we%20receive%20if%20we%20need%20to%20reproduce%20each%20issue%20from%20scratch%20ourselves.%0A%0A%2A%2ADescribe%20your%20issue%2A%2A%0A%0ADescribe%20the%20problem%20you%27re%20seeing%2C%20any%20important%20steps%20to%20reproduce%20and%20what%20behavior%20you%20expect%20instead.
+    about: If you've already asked for help with a problem and confirmed something is broken with Tailwind CSS itself, create a bug report.
   - name: Documentation Issue
     url: https://github.com/tailwindlabs/tailwindcss.com
     about: 'For documentation issues, suggest changes on our documentation repository.'

.github/PULL_REQUEST_TEMPLATE.md

@@ -4,26 +4,8 @@
 
 **Please ask first before starting work on any significant new features.**
 
-It's never a fun experience to have your pull request declined after investing a lot of time and effort into a new feature. To avoid this from happening, we request that contributors create a discussion to first discuss any significant new features.
+It's never a fun experience to have your pull request declined after investing a lot of time and effort into a new feature. To avoid this from happening, we request that contributors create an issue to first discuss any significant new features. This includes things like adding new utilities, creating new at-rules, or adding new component examples to the documentation.
 
-For more info, check out the contributing guide:
-
-https://github.com/tailwindlabs/tailwindcss/blob/main/.github/CONTRIBUTING.md
-
--->
-
-## Summary
-
-<!--
-
-Provide a summary of the issue and the changes you're making. How does your change solve the problem?
-
--->
-
-## Test plan
-
-<!--
-
-Explain how you tested your changes. Include the exact commands that you used to verify the change works and include screenshots/screen recordings of the update behavior in the browser if applicable.
+https://github.com/tailwindcss/tailwindcss/blob/master/.github/CONTRIBUTING.md
 
 -->

.github/workflows/ci.yml

@@ -2,68 +2,40 @@ name: CI
 
 on:
   push:
-    branches: [main]
+    branches: [master, next]
   pull_request:
+    branches: [master, next]
 
 permissions:
   contents: read
 
-env:
-  NODE_VERSION: 24
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
 jobs:
-  tests:
+  build:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+
     strategy:
-      fail-fast: false
       matrix:
-        runner:
-          - name: Windows
-            os: windows-latest
-
-          - name: Linux
-            os: namespace-profile-default
-
-          # Playwright 1.62+ dropped WebKit support for macOS 14, and hangs
-          # instead of failing when launching WebKit on a macos-14 runner.
-          - name: macOS
-            os: macos-15
-
-        # Exclude windows and macos from being built on feature branches
-        run-all:
-          - ${{ github.ref == 'refs/heads/main' || contains(github.event.pull_request.body, '[ci-all]') || github.event.pull_request.user.login == 'depfu[bot]' }}
-        exclude:
-          - run-all: false
-            runner:
-              name: Windows
-          - run-all: false
-            runner:
-              name: macOS
-
-    runs-on: ${{ matrix.runner.os }}
-    timeout-minutes: 30
-
-    name: ${{ matrix.runner.name }}
+        node-version: [20]
 
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - uses: actions/checkout@v3
+      - uses: pnpm/action-setup@v3
         with:
-          persist-credentials: false
-      - uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
+          version: ^8.15.0
 
-      - name: Use Node.js ${{ env.NODE_VERSION }}
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
+      - name: Use Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v3
         with:
-          node-version: ${{ env.NODE_VERSION }}
+          node-version: ${{ matrix.node-version }}
+          cache: 'pnpm'
 
       # Cargo already skips downloading dependencies if they already exist
       - name: Cache cargo
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5
+        uses: actions/cache@v3
         with:
           path: |
+            ~/.cargo/bin/
             ~/.cargo/registry/index/
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
@@ -72,36 +44,23 @@ jobs:
 
       # Cache the `oxide` Rust build
       - name: Cache oxide build
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5
+        uses: actions/cache@v3
         with:
           path: |
+            ./target/
             ./crates/node/*.node
-            ./crates/node/*.wasm
-            ./crates/node/index.d.ts
             ./crates/node/index.js
-            ./crates/node/browser.js
-            ./crates/node/tailwindcss-oxide.wasi-browser.js
-            ./crates/node/tailwindcss-oxide.wasi.cjs
-            ./crates/node/wasi-worker-browser.mjs
-            ./crates/node/wasi-worker.mjs
+            ./crates/node/index.d.ts
           key: ${{ runner.os }}-oxide-${{ hashFiles('./crates/**/*') }}
 
-      - name: Setup WASM target
-        run: rustup target add wasm32-wasip1-threads
-
       - name: Install dependencies
-        run: pnpm install --frozen-lockfile
+        run: pnpm install
 
       - name: Build
         run: pnpm run build
-        env:
-          CARGO_PROFILE_RELEASE_LTO: 'off'
-          CARGO_TARGET_X86_64_PC_WINDOWS_MSVC_LINKER: 'lld-link'
 
       - name: Lint
         run: pnpm run lint
-        # Only lint on linux to avoid \r\n line ending errors
-        if: matrix.runner.os == 'ubuntu-latest'
 
       - name: Test
         run: pnpm run test
@@ -112,13 +71,12 @@ jobs:
       - name: Run Playwright tests
         run: npm run test:ui
 
-  notify:
-    if: ${{ always() && github.ref == 'refs/heads/main' && needs.tests.result == 'failure' }}
-    needs: tests
-    runs-on: ubuntu-latest
-    steps:
-      - name: Notify Discord
-        uses: discord-actions/message@5c7149c81a83146e5d01f142be1bf87a61831c4d # v2
+      - uses: actions/upload-artifact@v3
+        if: always()
         with:
-          webhookUrl: ${{ secrets.DISCORD_WEBHOOK_URL }}
-          message: 'The [most recent ${{ github.workflow }} workflow](<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}>) on the `main` branch has failed.'
+          name: playwright-report
+          path: packages/tailwindcss/playwright-report/
+          retention-days: 30
+
+      - name: Bench
+        run: pnpm run bench

.github/workflows/integration-tests.yml

@@ -1,125 +0,0 @@
-name: Integration Tests
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-
-permissions:
-  contents: read
-
-env:
-  NODE_VERSION: 24
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  tests:
-    strategy:
-      fail-fast: false
-      matrix:
-        runner:
-          - name: Windows
-            os: windows-latest
-
-          - name: Linux
-            os: namespace-profile-default
-
-          - name: macOS
-            os: macos-14
-
-        integration:
-          - upgrade
-          - vite
-          - cli
-          - postcss
-          - oxide
-          - webpack
-
-        # Exclude windows and macos from being built on feature branches
-        run-all:
-          - ${{ github.ref == 'refs/heads/main' || contains(github.event.pull_request.body, '[ci-all]') }}
-        exclude:
-          - run-all: false
-            runner:
-              name: Windows
-          - run-all: false
-            runner:
-              name: macOS
-
-    runs-on: ${{ matrix.runner.os }}
-    timeout-minutes: 30
-
-    name: ${{ matrix.runner.name }} /  ${{ matrix.integration }}
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          persist-credentials: false
-      - uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
-
-      - run: |
-          git config --global user.name "github-actions[bot]"
-          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
-
-      - name: Use Node.js ${{ env.NODE_VERSION }}
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-
-      # Cargo already skips downloading dependencies if they already exist
-      - name: Cache cargo
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5
-        with:
-          path: |
-            ~/.cargo/registry/index/
-            ~/.cargo/registry/cache/
-            ~/.cargo/git/db/
-            target/
-          key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
-
-      # Cache the `oxide` Rust build
-      - name: Cache oxide build
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5
-        with:
-          path: |
-            ./crates/node/*.node
-            ./crates/node/*.wasm
-            ./crates/node/index.d.ts
-            ./crates/node/index.js
-            ./crates/node/browser.js
-            ./crates/node/tailwindcss-oxide.wasi-browser.js
-            ./crates/node/tailwindcss-oxide.wasi.cjs
-            ./crates/node/wasi-worker-browser.mjs
-            ./crates/node/wasi-worker.mjs
-          key: ${{ runner.os }}-oxide-${{ hashFiles('./crates/**/*') }}
-
-      - name: Setup WASM target
-        run: rustup target add wasm32-wasip1-threads
-
-      - name: Install dependencies
-        run: pnpm install
-
-      - name: Build
-        run: pnpm run build
-        env:
-          CARGO_PROFILE_RELEASE_LTO: 'off'
-          CARGO_TARGET_X86_64_PC_WINDOWS_MSVC_LINKER: 'lld-link'
-
-      - name: Test ${{ matrix.integration }}
-        run: pnpm run test:integrations ./integrations/${{ matrix.integration }}
-        env:
-          GITHUB_WORKSPACE: ${{ github.workspace }}
-
-  notify:
-    if: ${{ always() && github.ref == 'refs/heads/main' && needs.tests.result == 'failure' }}
-    needs: tests
-    runs-on: ubuntu-latest
-    steps:
-      - name: Notify Discord
-        uses: discord-actions/message@5c7149c81a83146e5d01f142be1bf87a61831c4d # v2
-        with:
-          webhookUrl: ${{ secrets.DISCORD_WEBHOOK_URL }}
-          message: 'The [most recent ${{ github.workflow }} workflow](<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}>) on the `main` branch has failed.'

.github/workflows/prepare-release.yml

@@ -1,307 +0,0 @@
-name: Prepare Release
-
-on:
-  workflow_dispatch:
-    inputs:
-      dry_run:
-        description: Skip creating the draft GitHub release
-        required: false
-        default: true
-        type: boolean
-  push:
-    tags:
-      - 'v*'
-
-env:
-  APP_NAME: tailwindcss-oxide
-  NODE_VERSION: 24
-  PNPM_VERSION: '11.9.0'
-  OXIDE_LOCATION: ./crates/node
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    strategy:
-      matrix:
-        include:
-          # Windows
-          - os: windows-latest
-            target: x86_64-pc-windows-msvc
-          - os: windows-latest
-            target: aarch64-pc-windows-msvc
-          # macOS
-          - os: macos-latest
-            target: x86_64-apple-darwin
-            strip: strip -x # Must use -x on macOS. This produces larger results on linux.
-          - os: macos-latest
-            target: aarch64-apple-darwin
-            page-size: 14
-            strip: strip -x # Must use -x on macOS. This produces larger results on linux.
-          # Android
-          - os: ubuntu-latest
-            target: aarch64-linux-android
-            strip: ${ANDROID_NDK_LATEST_HOME}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip
-          - os: ubuntu-latest
-            target: armv7-linux-androideabi
-            strip: ${ANDROID_NDK_LATEST_HOME}/toolchains/llvm/prebuilt/linux-x86_64/bin/llvm-strip
-          # Linux
-          - os: ubuntu-latest
-            target: x86_64-unknown-linux-gnu
-            strip: strip
-            build-flags: --use-napi-cross
-          - os: ubuntu-latest
-            target: aarch64-unknown-linux-gnu
-            strip: aarch64-linux-gnu-strip
-            build-flags: --use-napi-cross
-          - os: ubuntu-latest
-            target: armv7-unknown-linux-gnueabihf
-            strip: arm-linux-gnueabihf-strip
-            build-flags: --use-napi-cross
-          - os: ubuntu-latest
-            target: aarch64-unknown-linux-musl
-            strip-zig: true
-            build-flags: -x
-          - os: ubuntu-latest
-            target: x86_64-unknown-linux-musl
-            strip: strip
-            build-flags: -x
-
-    name: Build ${{ matrix.target }} (oxide)
-    runs-on: ${{ matrix.os }}
-    timeout-minutes: 15
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          persist-credentials: false
-      - uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
-        with:
-          version: ${{ env.PNPM_VERSION }}
-
-      - name: Use Node.js ${{ env.NODE_VERSION }}
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-          package-manager-cache: false
-
-      - name: Install gcc-arm-linux-gnueabihf
-        if: ${{ matrix.target == 'armv7-unknown-linux-gnueabihf' }}
-        run: |
-          sudo apt-get update
-          sudo apt-get install gcc-arm-linux-gnueabihf g++-arm-linux-gnueabihf -y
-
-      - name: Install binutils-aarch64-linux-gnu
-        if: ${{ matrix.target == 'aarch64-unknown-linux-gnu' }}
-        run: |
-          sudo apt-get update
-          sudo apt-get install binutils-aarch64-linux-gnu -y
-
-      - uses: mlugg/setup-zig@d1434d08867e3ee9daa34448df10607b98908d29 # v2
-        if: ${{ contains(matrix.target, 'musl') }}
-        with:
-          version: 0.14.1
-          use-cache: false
-
-      - name: Install cargo-zigbuild
-        uses: taiki-e/install-action@65851e10cd6c377f11a60e600abc07cb08643468 # v2
-        if: ${{ contains(matrix.target, 'musl') }}
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
-        with:
-          tool: cargo-zigbuild
-
-      - name: Setup rust target
-        run: rustup target add ${{ matrix.target }}
-
-      - name: Install dependencies
-        run: pnpm install --ignore-scripts --frozen-lockfile --filter=!./playgrounds/*
-
-      - name: Build release
-        run: pnpm run --filter ${{ env.OXIDE_LOCATION }} build:platform --target=${{ matrix.target }} ${{ matrix.build-flags }}
-        env:
-          RUST_TARGET: ${{ matrix.target }}
-          JEMALLOC_SYS_WITH_LG_PAGE: ${{ matrix.page-size }}
-
-      - name: Strip debug symbols # https://github.com/rust-lang/rust/issues/46034
-        if: ${{ matrix.strip || matrix.strip-zig }}
-        env:
-          STRIP_COMMAND: ${{ matrix.strip }}
-          STRIP_ZIG: ${{ matrix.strip-zig }}
-        run: |
-          if [ "$STRIP_ZIG" = "true" ]; then
-            for file in ${{ env.OXIDE_LOCATION }}/*.node; do
-              zig objcopy --strip-all "$file" "$file.stripped"
-              mv "$file.stripped" "$file"
-            done
-            exit 0
-          fi
-
-          eval "$STRIP_COMMAND ${{ env.OXIDE_LOCATION }}/*.node"
-
-      - name: Upload artifacts
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
-        with:
-          name: bindings-${{ matrix.target }}
-          path: ${{ env.OXIDE_LOCATION }}/*.node
-
-  build-freebsd:
-    name: Build x86_64-unknown-freebsd (OXIDE)
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          persist-credentials: false
-      - name: Build FreeBSD
-        uses: cross-platform-actions/action@cdc9ee69ef84a5f2e59c9058335d9c57bcb4ac86 # v0.25.0
-        env:
-          DEBUG: napi:*
-          RUSTUP_HOME: /usr/local/rustup
-          CARGO_HOME: /usr/local/cargo
-          RUSTUP_IO_THREADS: 1
-          RUST_TARGET: x86_64-unknown-freebsd
-        with:
-          operating_system: freebsd
-          version: '14.0'
-          memory: 13G
-          cpu_count: 3
-          environment_variables: 'DEBUG RUSTUP_IO_THREADS'
-          shell: bash
-          run: |
-            sudo pkg install -y -f curl node libnghttp2 npm
-            sudo npm install -g pnpm@${{ env.PNPM_VERSION }} --unsafe-perm=true
-            curl -sSf https://static.rust-lang.org/rustup/archive/1.27.1/x86_64-unknown-freebsd/rustup-init --output rustup-init
-            chmod +x rustup-init
-            ./rustup-init -y --profile minimal
-            source "$HOME/.cargo/env"
-            pnpm install --ignore-scripts --frozen-lockfile --filter=!./playgrounds/* || true
-            echo "~~~~ rustc --version ~~~~"
-            rustc --version
-            echo "~~~~ node -v ~~~~"
-            node -v
-            echo "~~~~ pnpm --version ~~~~"
-            pnpm --version
-            pnpm run --filter ${{ env.OXIDE_LOCATION }} build:platform
-            strip -x ${{ env.OXIDE_LOCATION }}/*.node
-            ls -la ${{ env.OXIDE_LOCATION }}
-      - name: Upload artifacts
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
-        with:
-          name: bindings-x86_64-unknown-freebsd
-          path: ${{ env.OXIDE_LOCATION }}/*.node
-
-  prepare:
-    runs-on: macos-14
-    timeout-minutes: 15
-    name: Build and release Tailwind CSS
-
-    permissions:
-      contents: write # Required for creating releases
-
-    needs:
-      - build
-      - build-freebsd
-
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          fetch-depth: 20
-          persist-credentials: false
-
-      - run: git fetch --tags -f
-
-      - name: Resolve version
-        id: vars
-        run: |
-          echo "TAG_NAME=$(git describe --tags --abbrev=0)" >> $GITHUB_ENV
-
-      - uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
-        with:
-          version: ${{ env.PNPM_VERSION }}
-
-      - name: Use Node.js ${{ env.NODE_VERSION }}
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-          registry-url: 'https://registry.npmjs.org'
-          package-manager-cache: false
-
-      - name: Setup WASM target
-        run: rustup target add wasm32-wasip1-threads
-
-      - name: Install dependencies
-        run: pnpm --filter=!./playgrounds/* install --frozen-lockfile
-
-      - name: Download artifacts
-        uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131 # v7
-        with:
-          path: ${{ env.OXIDE_LOCATION }}
-
-      - name: Move artifacts
-        run: |
-          cd ${{ env.OXIDE_LOCATION }}
-          cp bindings-x86_64-pc-windows-msvc/* ./npm/win32-x64-msvc/
-          cp bindings-aarch64-pc-windows-msvc/* ./npm/win32-arm64-msvc/
-          cp bindings-x86_64-apple-darwin/* ./npm/darwin-x64/
-          cp bindings-aarch64-apple-darwin/* ./npm/darwin-arm64/
-          cp bindings-aarch64-linux-android/* ./npm/android-arm64/
-          cp bindings-armv7-linux-androideabi/* ./npm/android-arm-eabi/
-          cp bindings-aarch64-unknown-linux-gnu/* ./npm/linux-arm64-gnu/
-          cp bindings-aarch64-unknown-linux-musl/* ./npm/linux-arm64-musl/
-          cp bindings-armv7-unknown-linux-gnueabihf/* ./npm/linux-arm-gnueabihf/
-          cp bindings-x86_64-unknown-linux-gnu/* ./npm/linux-x64-gnu/
-          cp bindings-x86_64-unknown-linux-musl/* ./npm/linux-x64-musl/
-          cp bindings-x86_64-unknown-freebsd/* ./npm/freebsd-x64/
-
-      - name: Build Tailwind CSS
-        run: pnpm run build
-        env:
-          FEATURES_ENV: stable
-
-      - name: Run pre-publish optimizations scripts
-        run: node ./scripts/pre-publish-optimizations.mjs
-
-      - name: Lock pre-release versions
-        run: node ./scripts/lock-pre-release-versions.mjs
-
-      - name: Get release notes
-        run: |
-          RELEASE_NOTES=$(node ./scripts/release-notes.mjs)
-          echo "RELEASE_NOTES<<EOF" >> $GITHUB_ENV
-          echo "$RELEASE_NOTES" >> $GITHUB_ENV
-          echo "EOF" >> $GITHUB_ENV
-
-      - name: Upload standalone artifacts
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
-        with:
-          name: tailwindcss-standalone
-          path: packages/@tailwindcss-standalone/dist/
-
-      - name: Upload npm package tarballs
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
-        with:
-          name: npm-package-tarballs
-          path: dist/*.tgz
-
-      - name: Prepare GitHub Release
-        if: ${{ !inputs.dry_run }}
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          gh release create "${TAG_NAME}" \
-              --draft \
-              --title "${TAG_NAME}" \
-              --notes "${RELEASE_NOTES}" \
-              packages/@tailwindcss-standalone/dist/sha256sums.txt \
-              packages/@tailwindcss-standalone/dist/tailwindcss-linux-arm64 \
-              packages/@tailwindcss-standalone/dist/tailwindcss-linux-arm64-musl \
-              packages/@tailwindcss-standalone/dist/tailwindcss-linux-x64 \
-              packages/@tailwindcss-standalone/dist/tailwindcss-linux-x64-musl \
-              packages/@tailwindcss-standalone/dist/tailwindcss-macos-arm64 \
-              packages/@tailwindcss-standalone/dist/tailwindcss-macos-x64 \
-              packages/@tailwindcss-standalone/dist/tailwindcss-windows-x64.exe

.github/workflows/release.yml

@@ -1,34 +1,23 @@
 name: Release
 
 on:
-  push:
-    branches: [main]
-  release:
-    types: [published]
   workflow_dispatch:
     inputs:
-      channel:
-        description: Release channel to publish
-        required: true
-        default: insiders
-        type: choice
-        options:
-          - insiders
-          - release
+      release_channel:
+        description: 'Release channel'
+        required: false
+        default: 'next'
+        type: string
 
 permissions:
   contents: read
 
 env:
   APP_NAME: tailwindcss-oxide
-  NODE_VERSION: 24
-  PNPM_VERSION: '11.9.0'
+  NODE_VERSION: 20
+  PNPM_VERSION: ^8.15.0
   OXIDE_LOCATION: ./crates/node
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.ref }}
-  cancel-in-progress: true
-
 jobs:
   build:
     strategy:
@@ -37,8 +26,6 @@ jobs:
           # Windows
           - os: windows-latest
             target: x86_64-pc-windows-msvc
-          - os: windows-latest
-            target: aarch64-pc-windows-msvc
           # macOS
           - os: macos-latest
             target: x86_64-apple-darwin
@@ -58,151 +45,110 @@ jobs:
           - os: ubuntu-latest
             target: x86_64-unknown-linux-gnu
             strip: strip
-            build-flags: --use-napi-cross
+            container:
+              image: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-debian
           - os: ubuntu-latest
             target: aarch64-unknown-linux-gnu
-            strip: aarch64-linux-gnu-strip
-            build-flags: --use-napi-cross
+            strip: llvm-strip
+            container:
+              image: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-debian-aarch64
           - os: ubuntu-latest
             target: armv7-unknown-linux-gnueabihf
-            strip: arm-linux-gnueabihf-strip
-            build-flags: --use-napi-cross
+            strip: llvm-strip
+            container:
+              image: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-debian-zig
           - os: ubuntu-latest
             target: aarch64-unknown-linux-musl
-            strip-zig: true
-            build-flags: -x
+            strip: aarch64-linux-musl-strip
+            download: true
+            container:
+              image: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
           - os: ubuntu-latest
             target: x86_64-unknown-linux-musl
             strip: strip
-            build-flags: -x
+            download: true
+            container:
+              image: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
 
-    name: Build ${{ matrix.target }} (oxide)
+    name: Build ${{ matrix.target }} (OXIDE)
     runs-on: ${{ matrix.os }}
+    container: ${{ matrix.container }}
     timeout-minutes: 15
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          persist-credentials: false
-      - uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
+      - uses: actions/checkout@v3
+      - uses: pnpm/action-setup@v3
         with:
           version: ${{ env.PNPM_VERSION }}
 
       - name: Use Node.js ${{ env.NODE_VERSION }}
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
+        uses: actions/setup-node@v3
         with:
           node-version: ${{ env.NODE_VERSION }}
-          package-manager-cache: false
+          cache: 'pnpm'
 
-      - name: Install gcc-arm-linux-gnueabihf
-        if: ${{ matrix.target == 'armv7-unknown-linux-gnueabihf' }}
-        run: |
-          sudo apt-get update
-          sudo apt-get install gcc-arm-linux-gnueabihf g++-arm-linux-gnueabihf -y
-
-      - name: Install binutils-aarch64-linux-gnu
-        if: ${{ matrix.target == 'aarch64-unknown-linux-gnu' }}
-        run: |
-          sudo apt-get update
-          sudo apt-get install binutils-aarch64-linux-gnu -y
-
-      - uses: mlugg/setup-zig@d1434d08867e3ee9daa34448df10607b98908d29 # v2
-        if: ${{ contains(matrix.target, 'musl') }}
+      # Cargo already skips downloading dependencies if they already exist
+      - name: Cache cargo
+        uses: actions/cache@v3
         with:
-          version: 0.14.1
-          use-cache: false
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ matrix.target }}-cargo-${{ hashFiles('**/Cargo.lock') }}
 
-      - name: Install cargo-zigbuild
-        uses: taiki-e/install-action@65851e10cd6c377f11a60e600abc07cb08643468 # v2
-        if: ${{ contains(matrix.target, 'musl') }}
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
+      # Cache the `oxide` Rust build
+      - name: Cache oxide build
+        uses: actions/cache@v3
         with:
-          tool: cargo-zigbuild
+          path: |
+            ./oxide/target/
+            ./crates/node/*.node
+            ./crates/node/index.js
+            ./crates/node/index.d.ts
+          key: ${{ runner.os }}-${{ matrix.target }}-oxide-${{ hashFiles('./crates/**/*') }}
+
+      - name: Install Node.JS
+        uses: actions/setup-node@v3
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Setup cross compile toolchain
+        if: ${{ matrix.setup }}
+        run: ${{ matrix.setup }}
+
+      - name: Install Rust (Stable)
+        if: ${{ matrix.download }}
+        run: |
+          rustup default stable
 
       - name: Setup rust target
         run: rustup target add ${{ matrix.target }}
 
       - name: Install dependencies
-        run: pnpm install --ignore-scripts --frozen-lockfile --filter=!./playgrounds/*
+        run: pnpm install --ignore-scripts --filter=!./playgrounds/*
 
       - name: Build release
-        run: pnpm run --filter ${{ env.OXIDE_LOCATION }} build:platform --target=${{ matrix.target }} ${{ matrix.build-flags }}
+        run: pnpm run build --filter ${{ env.OXIDE_LOCATION }}
         env:
           RUST_TARGET: ${{ matrix.target }}
           JEMALLOC_SYS_WITH_LG_PAGE: ${{ matrix.page-size }}
 
       - name: Strip debug symbols # https://github.com/rust-lang/rust/issues/46034
-        if: ${{ matrix.strip || matrix.strip-zig }}
-        env:
-          STRIP_COMMAND: ${{ matrix.strip }}
-          STRIP_ZIG: ${{ matrix.strip-zig }}
-        run: |
-          if [ "$STRIP_ZIG" = "true" ]; then
-            for file in ${{ env.OXIDE_LOCATION }}/*.node; do
-              zig objcopy --strip-all "$file" "$file.stripped"
-              mv "$file.stripped" "$file"
-            done
-            exit 0
-          fi
-
-          eval "$STRIP_COMMAND ${{ env.OXIDE_LOCATION }}/*.node"
+        if: ${{ matrix.strip }}
+        run: ${{ matrix.strip }} ${{ env.OXIDE_LOCATION }}/*.node
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
+        uses: actions/upload-artifact@v3
         with:
           name: bindings-${{ matrix.target }}
           path: ${{ env.OXIDE_LOCATION }}/*.node
 
-  build-freebsd:
-    name: Build x86_64-unknown-freebsd (OXIDE)
+  release:
     runs-on: ubuntu-latest
     timeout-minutes: 15
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          persist-credentials: false
-      - name: Build FreeBSD
-        uses: cross-platform-actions/action@cdc9ee69ef84a5f2e59c9058335d9c57bcb4ac86 # v0.25.0
-        env:
-          DEBUG: napi:*
-          RUSTUP_HOME: /usr/local/rustup
-          CARGO_HOME: /usr/local/cargo
-          RUSTUP_IO_THREADS: 1
-          RUST_TARGET: x86_64-unknown-freebsd
-        with:
-          operating_system: freebsd
-          version: '14.0'
-          memory: 13G
-          cpu_count: 3
-          environment_variables: 'DEBUG RUSTUP_IO_THREADS'
-          shell: bash
-          run: |
-            sudo pkg install -y -f curl node libnghttp2 npm
-            sudo npm install -g pnpm@${{ env.PNPM_VERSION }} --unsafe-perm=true
-            curl -sSf https://static.rust-lang.org/rustup/archive/1.27.1/x86_64-unknown-freebsd/rustup-init --output rustup-init
-            chmod +x rustup-init
-            ./rustup-init -y --profile minimal
-            source "$HOME/.cargo/env"
-            echo "~~~~ rustc --version ~~~~"
-            rustc --version
-            echo "~~~~ node -v ~~~~"
-            node -v
-            echo "~~~~ pnpm --version ~~~~"
-            pnpm --version
-            pnpm install --ignore-scripts --frozen-lockfile --filter=!./playgrounds/* || true
-            pnpm run --filter ${{ env.OXIDE_LOCATION }} build:platform
-            strip -x ${{ env.OXIDE_LOCATION }}/*.node
-            ls -la ${{ env.OXIDE_LOCATION }}
-      - name: Upload artifacts
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
-        with:
-          name: bindings-x86_64-unknown-freebsd
-          path: ${{ env.OXIDE_LOCATION }}/*.node
-
-  release:
-    runs-on: macos-14
-    timeout-minutes: 15
-    name: Build and publish Tailwind CSS
+    name: Build and release Tailwind CSS
 
     permissions:
       contents: read
@@ -211,54 +157,51 @@ jobs:
 
     needs:
       - build
-      - build-freebsd
 
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          fetch-depth: 20
-          persist-credentials: false
-
-      - uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
+      - uses: actions/checkout@v3
+      - uses: pnpm/action-setup@v3
         with:
           version: ${{ env.PNPM_VERSION }}
 
       - name: Use Node.js ${{ env.NODE_VERSION }}
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
+        uses: actions/setup-node@v3
         with:
           node-version: ${{ env.NODE_VERSION }}
+          cache: 'pnpm'
           registry-url: 'https://registry.npmjs.org'
-          package-manager-cache: false
 
-      # npm trusted publishing validates the caller workflow filename, so all npm publishes live here.
-      # This workflow rebuilds the publish artifacts instead of depending on prepare-release.yml.
-      - name: Resolve release metadata
-        env:
-          INPUT_CHANNEL: ${{ github.event.inputs.channel || '' }}
-        run: |
-          if [[ "${{ github.event_name }}" == "release" || "$INPUT_CHANNEL" == "release" ]]; then
-            release_channel=$(node ./scripts/release-channel.js)
+      # Cargo already skips downloading dependencies if they already exist
+      - name: Cache cargo
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            target/
+          key: ${{ runner.os }}-${{ matrix.target }}-cargo-${{ hashFiles('**/Cargo.lock') }}
 
-            echo "RELEASE_KIND=release" >> $GITHUB_ENV
-            echo "RELEASE_CHANNEL=$release_channel" >> $GITHUB_ENV
-            echo "FEATURES_ENV=stable" >> $GITHUB_ENV
-          else
-            sha_short=$(git rev-parse --short HEAD)
-
-            echo "RELEASE_KIND=insiders" >> $GITHUB_ENV
-            echo "RELEASE_CHANNEL=insiders" >> $GITHUB_ENV
-            echo "SHA_SHORT=$sha_short" >> $GITHUB_ENV
-            echo "INSIDERS_VERSION=0.0.0-insiders.$sha_short" >> $GITHUB_ENV
-          fi
-
-      - name: Setup WASM target
-        run: rustup target add wasm32-wasip1-threads
+      # Cache the `oxide` Rust build
+      - name: Cache oxide build
+        uses: actions/cache@v3
+        with:
+          path: |
+            ./oxide/target/
+            ./crates/node/*.node
+            ./crates/node/index.js
+            ./crates/node/index.d.ts
+          key: ${{ runner.os }}-${{ matrix.target }}-oxide-${{ hashFiles('./crates/**/*') }}
 
       - name: Install dependencies
-        run: pnpm --filter=!./playgrounds/* install --frozen-lockfile
+        run: pnpm install --ignore-scripts --filter=!./playgrounds/*
+
+      - name: Build Tailwind CSS
+        run: pnpm run build
 
       - name: Download artifacts
-        uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131 # v7
+        uses: actions/download-artifact@v3
         with:
           path: ${{ env.OXIDE_LOCATION }}
 
@@ -266,7 +209,6 @@ jobs:
         run: |
           cd ${{ env.OXIDE_LOCATION }}
           cp bindings-x86_64-pc-windows-msvc/* ./npm/win32-x64-msvc/
-          cp bindings-aarch64-pc-windows-msvc/* ./npm/win32-arm64-msvc/
           cp bindings-x86_64-apple-darwin/* ./npm/darwin-x64/
           cp bindings-aarch64-apple-darwin/* ./npm/darwin-arm64/
           cp bindings-aarch64-linux-android/* ./npm/android-arm64/
@@ -276,21 +218,6 @@ jobs:
           cp bindings-armv7-unknown-linux-gnueabihf/* ./npm/linux-arm-gnueabihf/
           cp bindings-x86_64-unknown-linux-gnu/* ./npm/linux-x64-gnu/
           cp bindings-x86_64-unknown-linux-musl/* ./npm/linux-x64-musl/
-          cp bindings-x86_64-unknown-freebsd/* ./npm/freebsd-x64/
-
-      - name: 'Version based on commit: ${{ env.INSIDERS_VERSION }}'
-        if: env.RELEASE_KIND == 'insiders'
-        run: pnpm run version-packages ${INSIDERS_VERSION}
-
-      - name: Build Tailwind CSS
-        if: env.RELEASE_KIND == 'insiders'
-        run: pnpm run build
-
-      - name: Build Tailwind CSS
-        if: env.RELEASE_KIND == 'release'
-        run: pnpm run build
-        env:
-          FEATURES_ENV: ${{ env.FEATURES_ENV }}
 
       - name: Run pre-publish optimizations scripts
         run: node ./scripts/pre-publish-optimizations.mjs
@@ -298,61 +225,7 @@ jobs:
       - name: Lock pre-release versions
         run: node ./scripts/lock-pre-release-versions.mjs
 
-      - name: Upload npm package tarballs
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
-        with:
-          name: npm-package-tarballs
-          path: dist/*.tgz
-
       - name: Publish
-        run: |
-          pnpm --recursive --filter="!@tailwindcss/oxide-wasm32-wasi" publish --tag ${RELEASE_CHANNEL} --no-git-checks
-          # The wasm package needs a special npm config that isn't read when pnpm --recursive is used
-          pushd crates/node/npm/wasm32-wasi; pnpm publish --tag ${RELEASE_CHANNEL} --no-git-checks --config.node-linker=hoisted; popd;
-
-      - name: Trigger Tailwind Play update
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
-        with:
-          github-token: ${{ secrets.TAILWIND_PLAY_TOKEN }}
-          script: |
-            await github.rest.actions.createWorkflowDispatch({
-              owner: 'tailwindlabs',
-              repo: 'upgrades',
-              ref: 'main',
-              workflow_id: 'upgrade-tailwindcss.yml'
-            })
-
-  notify:
-    if: ${{ always() && (needs.build.result == 'failure' || needs.build-freebsd.result == 'failure' || needs.release.result == 'failure') }}
-    needs:
-      - build
-      - build-freebsd
-      - release
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          persist-credentials: false
-
-      - name: Resolve release label
-        id: release
+        run: pnpm --recursive publish --tag ${{ inputs.release_channel }} --no-git-checks
         env:
-          INPUT_CHANNEL: ${{ github.event.inputs.channel || '' }}
-          RELEASE_TAG: ${{ github.event.release.tag_name || '' }}
-        run: |
-          if [[ "${{ github.event_name }}" == "release" ]]; then
-            tag_name="${RELEASE_TAG:-${GITHUB_REF_NAME}}"
-            echo "label=release ${tag_name}" >> $GITHUB_OUTPUT
-          elif [[ "$INPUT_CHANNEL" == "release" ]]; then
-            version=$(node -p "require('./packages/tailwindcss/package.json').version")
-            echo "label=release v${version}" >> $GITHUB_OUTPUT
-          else
-            sha_short=$(git rev-parse --short HEAD)
-            echo "label=insiders release 0.0.0-insiders.${sha_short}" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Notify Discord
-        uses: discord-actions/message@5c7149c81a83146e5d01f142be1bf87a61831c4d # v2
-        with:
-          webhookUrl: ${{ secrets.DISCORD_WEBHOOK_URL }}
-          message: 'The [most recent ${{ github.workflow }} workflow](<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}>) for `${{ steps.release.outputs.label }}` has failed.'
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}

.gitignore

@@ -7,4 +7,3 @@ playwright-report/
 blob-report/
 playwright/.cache/
 target/
-.debug/

.npmrc

@@ -0,0 +1 @@
+auto-install-peers = true

.prettierignore

@@ -4,6 +4,5 @@ pnpm-lock.yaml
 target/
 crates/node/index.d.ts
 crates/node/index.js
-crates/ignore/
 .next
 .fingerprint

README.md

@@ -13,10 +13,10 @@
 </p>
 
 <p align="center">
-    <a href="https://github.com/tailwindlabs/tailwindcss/actions"><img src="https://img.shields.io/github/actions/workflow/status/tailwindlabs/tailwindcss/ci.yml?branch=main" alt="Build Status"></a>
+    <a href="https://github.com/tailwindlabs/tailwindcss/actions"><img src="https://img.shields.io/github/actions/workflow/status/tailwindlabs/tailwindcss/ci.yml?branch=next" alt="Build Status"></a>
     <a href="https://www.npmjs.com/package/tailwindcss"><img src="https://img.shields.io/npm/dt/tailwindcss.svg" alt="Total Downloads"></a>
-    <a href="https://github.com/tailwindlabs/tailwindcss/releases"><img src="https://img.shields.io/npm/v/tailwindcss.svg" alt="Latest Release"></a>
-    <a href="https://github.com/tailwindlabs/tailwindcss/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/tailwindcss.svg" alt="License"></a>
+    <a href="https://github.com/tailwindcss/tailwindcss/releases"><img src="https://img.shields.io/npm/v/tailwindcss.svg" alt="Latest Release"></a>
+    <a href="https://github.com/tailwindcss/tailwindcss/blob/master/LICENSE"><img src="https://img.shields.io/npm/l/tailwindcss.svg" alt="License"></a>
 </p>
 
 ---
@@ -27,10 +27,14 @@ For full documentation, visit [tailwindcss.com](https://tailwindcss.com).
 
 ## Community
 
-For help, discussion about best practices, or feature ideas:
+For help, discussion about best practices, or any other conversation that would benefit from being searchable:
 
-[Discuss Tailwind CSS on GitHub](https://github.com/tailwindlabs/tailwindcss/discussions)
+[Discuss Tailwind CSS on GitHub](https://github.com/tailwindcss/tailwindcss/discussions)
+
+For chatting with others using the framework:
+
+[Join the Tailwind CSS Discord Server](https://discord.gg/7NF8GNe)
 
 ## Contributing
 
-If you're interested in contributing to Tailwind CSS, please read our [contributing docs](https://github.com/tailwindlabs/tailwindcss/blob/main/.github/CONTRIBUTING.md) **before submitting a pull request**.
+If you're interested in contributing to Tailwind CSS, please read our [contributing docs](https://github.com/tailwindcss/tailwindcss/blob/next/.github/CONTRIBUTING.md) **before submitting a pull request**.

crates/classification-macros/Cargo.toml

@@ -1,12 +0,0 @@
-[package]
-name = "classification-macros"
-version = "0.1.0"
-edition = "2021"
-
-[lib]
-proc-macro = true
-
-[dependencies]
-syn = "2"
-quote = "1"
-proc-macro2 = "1"

crates/classification-macros/src/lib.rs

@@ -1,253 +0,0 @@
-use proc_macro::TokenStream;
-use quote::quote;
-use syn::{
-    parse_macro_input, punctuated::Punctuated, token::Comma, Attribute, Data, DataEnum,
-    DeriveInput, Expr, ExprLit, ExprRange, Ident, Lit, RangeLimits, Result, Variant,
-};
-
-/// A custom derive that supports:
-///
-/// - `#[bytes(…)]` for single byte literals
-/// - `#[bytes_range(…)]` for inclusive byte ranges (b'a'..=b'z')
-/// - `#[fallback]` for a variant that covers everything else
-///
-/// Example usage:
-///
-/// ```rust
-/// use classification_macros::ClassifyBytes;
-///
-/// #[derive(Clone, Copy, ClassifyBytes)]
-/// enum Class {
-///     #[bytes(b'a', b'b', b'c')]
-///     Letters,
-///
-///     #[bytes_range(b'0'..=b'9')]
-///     Digits,
-///
-///     #[fallback]
-///     Other,
-/// }
-/// ```
-/// Then call `b'a'.into()` to get `Example::SomeLetters`.
-#[proc_macro_derive(ClassifyBytes, attributes(bytes, bytes_range, fallback))]
-pub fn classify_bytes_derive(input: TokenStream) -> TokenStream {
-    let ast = parse_macro_input!(input as DeriveInput);
-
-    // This derive only works on an enum
-    let Data::Enum(DataEnum { variants, .. }) = &ast.data else {
-        return syn::Error::new_spanned(
-            &ast.ident,
-            "ClassifyBytes can only be derived on an enum.",
-        )
-        .to_compile_error()
-        .into();
-    };
-
-    let enum_name = &ast.ident;
-
-    let mut byte_map: [Option<Ident>; 256] = [const { None }; 256];
-    let mut fallback_variant: Option<Ident> = None;
-
-    // Start parsing the variants
-    for variant in variants {
-        let variant_ident = &variant.ident;
-
-        // If this variant has #[fallback], record it
-        if has_fallback_attr(variant) {
-            if fallback_variant.is_some() {
-                let err = syn::Error::new_spanned(
-                    variant_ident,
-                    "Multiple variants have #[fallback]. Only one allowed.",
-                );
-                return err.to_compile_error().into();
-            }
-            fallback_variant = Some(variant_ident.clone());
-        }
-
-        // Get #[bytes(…)]
-        let single_bytes = get_bytes_attrs(&variant.attrs);
-
-        // Get #[bytes_range(…)]
-        let range_bytes = get_bytes_range_attrs(&variant.attrs);
-
-        // Combine them
-        let all_bytes = single_bytes
-            .into_iter()
-            .chain(range_bytes)
-            .collect::<Vec<_>>();
-
-        // Mark them in the table
-        for b in all_bytes {
-            byte_map[b as usize] = Some(variant_ident.clone());
-        }
-    }
-
-    // If no fallback variant is found, default to "Other"
-    let fallback_ident = fallback_variant.expect("A variant marked with #[fallback] is missing");
-
-    // For each of the 256 byte values, fill the table
-    let fill = byte_map
-        .clone()
-        .into_iter()
-        .map(|variant_opt| match variant_opt {
-            Some(ident) => quote!(#enum_name::#ident),
-            None => quote!(#enum_name::#fallback_ident),
-        });
-
-    // Generate the final expanded code
-    let expanded = quote! {
-        impl #enum_name {
-            pub const TABLE: [#enum_name; 256] = [
-                #(#fill),*
-            ];
-        }
-
-        impl From<u8> for #enum_name {
-            fn from(byte: u8) -> Self {
-                #enum_name::TABLE[byte as usize]
-            }
-        }
-
-        impl From<&u8> for #enum_name {
-            fn from(byte: &u8) -> Self {
-                #enum_name::TABLE[*byte as usize]
-            }
-        }
-    };
-
-    TokenStream::from(expanded)
-}
-
-/// Checks if a variant has `#[fallback]`
-fn has_fallback_attr(variant: &Variant) -> bool {
-    variant
-        .attrs
-        .iter()
-        .any(|attr| attr.path().is_ident("fallback"))
-}
-
-/// Get all single byte literals from `#[bytes(…)]`
-fn get_bytes_attrs(attrs: &[Attribute]) -> Vec<u8> {
-    let mut assigned = Vec::new();
-    for attr in attrs {
-        if attr.path().is_ident("bytes") {
-            match parse_bytes_attr(attr) {
-                Ok(list) => assigned.extend(list),
-                Err(e) => panic!("Error parsing #[bytes(...)]: {}", e),
-            }
-        }
-    }
-    assigned
-}
-
-/// Parse `#[bytes(...)]` as a comma-separated list of **byte literals**, e.g. `b'a'`, `b'\n'`.
-fn parse_bytes_attr(attr: &Attribute) -> Result<Vec<u8>> {
-    // We'll parse it as a list of syn::Lit separated by commas: e.g. (b'a', b'b')
-    let items: Punctuated<Lit, Comma> = attr.parse_args_with(Punctuated::parse_terminated)?;
-    let mut out = Vec::new();
-    for lit in items {
-        match lit {
-            Lit::Byte(lb) => out.push(lb.value()),
-            _ => {
-                return Err(syn::Error::new_spanned(
-                    lit,
-                    "Expected a byte literal like b'a'",
-                ))
-            }
-        }
-    }
-    Ok(out)
-}
-
-/// Get all byte ranges from `#[bytes_range(...)]`
-fn get_bytes_range_attrs(attrs: &[Attribute]) -> Vec<u8> {
-    let mut assigned = Vec::new();
-    for attr in attrs {
-        if attr.path().is_ident("bytes_range") {
-            match parse_bytes_range_attr(attr) {
-                Ok(list) => assigned.extend(list),
-                Err(e) => panic!("Error parsing #[bytes_range(...)]: {}", e),
-            }
-        }
-    }
-    assigned
-}
-
-/// Parse `#[bytes_range(...)]` as a comma-separated list of range expressions, e.g.:
-/// `b'a'..=b'z', b'0'..=b'9'`
-fn parse_bytes_range_attr(attr: &Attribute) -> Result<Vec<u8>> {
-    // We'll parse each element as a syn::Expr, then see if it's an Expr::Range
-    let exprs: Punctuated<Expr, Comma> = attr.parse_args_with(Punctuated::parse_terminated)?;
-    let mut out = Vec::new();
-
-    for expr in exprs {
-        if let Expr::Range(ExprRange {
-            start: Some(start),
-            end: Some(end),
-            limits,
-            ..
-        }) = expr
-        {
-            let from = extract_byte_literal(&start)?;
-            let to = extract_byte_literal(&end)?;
-
-            match limits {
-                RangeLimits::Closed(_) => {
-                    // b'a'..=b'z'
-                    if from <= to {
-                        out.extend(from..=to);
-                    }
-                }
-                RangeLimits::HalfOpen(_) => {
-                    // b'a'..b'z'  => from..(to-1)
-                    if from < to {
-                        out.extend(from..to);
-                    }
-                }
-            }
-        } else {
-            return Err(syn::Error::new_spanned(
-                expr,
-                "Expected a byte range like b'a'..=b'z'",
-            ));
-        }
-    }
-
-    Ok(out)
-}
-
-/// Extract a u8 from an expression that can be:
-///
-/// - `Expr::Lit(Lit::Byte(...))`, e.g. b'a'
-/// - `Expr::Lit(Lit::Int(...))`, e.g. 0x80 or 255
-fn extract_byte_literal(expr: &Expr) -> Result<u8> {
-    if let Expr::Lit(ExprLit { lit, .. }) = expr {
-        match lit {
-            // Existing case: b'a'
-            Lit::Byte(lb) => Ok(lb.value()),
-
-            // New case: 0x80, 255, etc.
-            Lit::Int(li) => {
-                let value = li.base10_parse::<u64>()?;
-                if value <= 255 {
-                    Ok(value as u8)
-                } else {
-                    Err(syn::Error::new_spanned(
-                        li,
-                        format!("Integer literal {} out of range for a byte (0..255)", value),
-                    ))
-                }
-            }
-
-            _ => Err(syn::Error::new_spanned(
-                lit,
-                "Expected b'...' or an integer literal in range 0..=255",
-            )),
-        }
-    } else {
-        Err(syn::Error::new_spanned(
-            expr,
-            "Expected a literal expression like b'a' or 0x80",
-        ))
-    }
-}

crates/ignore/COPYING

@@ -1,3 +0,0 @@
-This project is dual-licensed under the Unlicense and MIT licenses.
-
-You may use this code under the terms of either license.

crates/ignore/Cargo.toml

@@ -1,50 +0,0 @@
-[package]
-name = "ignore"
-version = "0.4.33"  #:version
-authors = ["Andrew Gallant <jamslam@gmail.com>"]
-description = """
-A fast library for efficiently matching ignore files such as `.gitignore`
-against file paths.
-"""
-documentation = "https://docs.rs/ignore"
-homepage = "https://github.com/BurntSushi/ripgrep/tree/master/crates/ignore"
-repository = "https://github.com/BurntSushi/ripgrep/tree/master/crates/ignore"
-readme = "README.md"
-keywords = ["glob", "ignore", "gitignore", "pattern", "file"]
-license = "Unlicense OR MIT"
-# CHANGED: Use an explicit edition instead of `edition.workspace = true` since this crate is
-# vendored into the Tailwind CSS workspace.
-edition = "2024"
-rust-version = "1.88"
-
-[lib]
-name = "ignore"
-bench = false
-
-[dependencies]
-crossbeam-deque = "0.8.3"
-# CHANGED: Use the published globset crate instead of a path dependency.
-globset = "0.4.20"
-log = "0.4.20"
-memchr = "2.6.3"
-same-file = "1.0.6"
-walkdir = "2.4.0"
-# CHANGED: Added `dunce` to canonicalize paths without UNC prefixes on Windows.
-dunce = "1.0.5"
-
-[dependencies.regex-automata]
-version = "0.4.18"
-default-features = false
-features = ["std", "perf", "syntax", "meta", "nfa", "hybrid", "dfa-onepass"]
-
-[target.'cfg(windows)'.dependencies.winapi-util]
-version = "0.1.2"
-
-[dev-dependencies]
-bstr = { version = "1.6.2", default-features = false, features = ["std"] }
-crossbeam-channel = "0.5.15"
-
-[features]
-# DEPRECATED. It is a no-op. SIMD is done automatically through runtime
-# dispatch.
-simd-accel = []

crates/ignore/LICENSE-MIT

@@ -1,21 +0,0 @@
-The MIT License (MIT)
-
-Copyright (c) 2015 Andrew Gallant
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.

crates/ignore/README.md

@@ -1,59 +0,0 @@
-ignore
-======
-The ignore crate provides a fast recursive directory iterator that respects
-various filters such as globs, file types and `.gitignore` files. This crate
-also provides lower level direct access to gitignore and file type matchers.
-
-[![Build status](https://github.com/BurntSushi/ripgrep/workflows/ci/badge.svg)](https://github.com/BurntSushi/ripgrep/actions)
-[![](https://img.shields.io/crates/v/ignore.svg)](https://crates.io/crates/ignore)
-
-Dual-licensed under MIT or the [UNLICENSE](https://unlicense.org/).
-
-### Documentation
-
-[https://docs.rs/ignore](https://docs.rs/ignore)
-
-### Usage
-
-Add this to your `Cargo.toml`:
-
-```toml
-[dependencies]
-ignore = "0.4"
-```
-
-### Example
-
-This example shows the most basic usage of this crate. This code will
-recursively traverse the current directory while automatically filtering out
-files and directories according to ignore globs found in files like
-`.ignore` and `.gitignore`:
-
-
-```rust,no_run
-use ignore::Walk;
-
-for result in Walk::new("./") {
-    // Each item yielded by the iterator is either a directory entry or an
-    // error, so either print the path or the error.
-    match result {
-        Ok(entry) => println!("{}", entry.path().display()),
-        Err(err) => println!("ERROR: {}", err),
-    }
-}
-```
-
-### Example: advanced
-
-By default, the recursive directory iterator will ignore hidden files and
-directories. This can be disabled by building the iterator with `WalkBuilder`:
-
-```rust,no_run
-use ignore::WalkBuilder;
-
-for result in WalkBuilder::new("./").hidden(false).build() {
-    println!("{:?}", result);
-}
-```
-
-See the documentation for `WalkBuilder` for many other options.

crates/ignore/UNLICENSE

@@ -1,24 +0,0 @@
-This is free and unencumbered software released into the public domain.
-
-Anyone is free to copy, modify, publish, use, compile, sell, or
-distribute this software, either in source code form or as a compiled
-binary, for any purpose, commercial or non-commercial, and by any
-means.
-
-In jurisdictions that recognize copyright laws, the author or authors
-of this software dedicate any and all copyright interest in the
-software to the public domain. We make this dedication for the benefit
-of the public at large and to the detriment of our heirs and
-successors. We intend this dedication to be an overt act of
-relinquishment in perpetuity of all present and future rights to this
-software under copyright law.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
-OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
-ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-OTHER DEALINGS IN THE SOFTWARE.
-
-For more information, please refer to <http://unlicense.org/>

crates/ignore/examples/walk.rs

@@ -1,64 +0,0 @@
-use std::{env, io::Write, path::Path};
-
-use {bstr::ByteVec, ignore::WalkBuilder, walkdir::WalkDir};
-
-fn main() {
-    let mut path = env::args().nth(1).unwrap();
-    let mut parallel = false;
-    let mut simple = false;
-    let (tx, rx) = crossbeam_channel::bounded::<DirEntry>(100);
-    if path == "parallel" {
-        path = env::args().nth(2).unwrap();
-        parallel = true;
-    } else if path == "walkdir" {
-        path = env::args().nth(2).unwrap();
-        simple = true;
-    }
-
-    let stdout_thread = std::thread::spawn(move || {
-        let mut stdout = std::io::BufWriter::new(std::io::stdout());
-        for dent in rx {
-            stdout.write_all(&Vec::from_path_lossy(dent.path())).unwrap();
-            stdout.write_all(b"\n").unwrap();
-        }
-    });
-
-    if parallel {
-        let walker = WalkBuilder::new(path).threads(6).build_parallel();
-        walker.run(|| {
-            let tx = tx.clone();
-            Box::new(move |result| {
-                use ignore::WalkState::*;
-
-                tx.send(DirEntry::Y(result.unwrap())).unwrap();
-                Continue
-            })
-        });
-    } else if simple {
-        let walker = WalkDir::new(path);
-        for result in walker {
-            tx.send(DirEntry::X(result.unwrap())).unwrap();
-        }
-    } else {
-        let walker = WalkBuilder::new(path).build();
-        for result in walker {
-            tx.send(DirEntry::Y(result.unwrap())).unwrap();
-        }
-    }
-    drop(tx);
-    stdout_thread.join().unwrap();
-}
-
-enum DirEntry {
-    X(walkdir::DirEntry),
-    Y(ignore::DirEntry),
-}
-
-impl DirEntry {
-    fn path(&self) -> &Path {
-        match *self {
-            DirEntry::X(ref x) => x.path(),
-            DirEntry::Y(ref y) => y.path(),
-        }
-    }
-}

crates/ignore/src/default_types.rs

@@ -1,378 +0,0 @@
-/// This list represents the default file types that ripgrep ships with. In
-/// general, any file format is fair game, although it should generally be
-/// limited to reasonably popular open formats. For other cases, you can add
-/// types to each invocation of ripgrep with the '--type-add' flag.
-///
-/// If you would like to add or improve this list, please file a PR:
-/// <https://github.com/BurntSushi/ripgrep>.
-///
-/// Please try to keep this list sorted lexicographically and wrapped to 79
-/// columns (inclusive).
-#[rustfmt::skip]
-pub(crate) const DEFAULT_TYPES: &[(&[&str], &[&str])] = &[
-    (&["ada"], &["*.adb", "*.ads"]),
-    (&["agda"], &["*.agda", "*.lagda"]),
-    (&["aidl"], &["*.aidl"]),
-    (&["alire"], &["alire.toml"]),
-    (&["amake"], &["*.mk", "*.bp"]),
-    (&["asciidoc"], &["*.adoc", "*.asc", "*.asciidoc"]),
-    (&["asm"], &["*.asm", "*.s", "*.S"]),
-    (&["asp"], &[
-        "*.aspx", "*.aspx.cs", "*.aspx.vb", "*.ascx", "*.ascx.cs",
-        "*.ascx.vb", "*.asp"
-    ]),
-    (&["ats"], &["*.ats", "*.dats", "*.sats", "*.hats"]),
-    (&["avro"], &["*.avdl", "*.avpr", "*.avsc"]),
-    (&["awk"], &["*.awk"]),
-    (&["bat", "batch"], &["*.bat"]),
-    (&["bazel"], &[
-        "*.bazel", "*.bzl", "*.BUILD", "*.bazelrc", "BUILD", "MODULE.bazel",
-        "WORKSPACE", "WORKSPACE.bazel", "WORKSPACE.bzlmod",
-    ]),
-    (&["bitbake"], &["*.bb", "*.bbappend", "*.bbclass", "*.conf", "*.inc"]),
-    (&["boxlang"], &["*.bx", "*.bxm", "*.bxs"]),
-    (&["brotli"], &["*.br"]),
-    (&["buildstream"], &["*.bst"]),
-    (&["bzip2"], &["*.bz2", "*.tbz2"]),
-    (&["c"], &["*.[chH]", "*.[chH].in", "*.cats"]),
-    (&["cabal"], &["*.cabal"]),
-    (&["candid"], &["*.did"]),
-    (&["carp"], &["*.carp"]),
-    (&["cbor"], &["*.cbor"]),
-    (&["ceylon"], &["*.ceylon"]),
-    (&["cfml"], &["*.cfc", "*.cfm"]),
-    (&["clojure"], &["*.clj", "*.cljc", "*.cljs", "*.cljx"]),
-    (&["cmake"], &["*.cmake", "CMakeLists.txt"]),
-    (&["cmd"], &["*.bat", "*.cmd"]),
-    (&["cml"], &["*.cml"]),
-    (&["coffeescript"], &["*.coffee"]),
-    (&["config"], &["*.cfg", "*.conf", "*.config", "*.ini"]),
-    (&["container"], &["*Containerfile*", "*Dockerfile*"]),
-    (&["coq"], &["*.v"]),
-    (&["cpp"], &[
-        "*.[ChH]", "*.cc", "*.[ch]pp", "*.[ch]xx", "*.hh",  "*.inl",
-        "*.[ChH].in", "*.cc.in", "*.[ch]pp.in", "*.[ch]xx.in", "*.hh.in",
-    ]),
-    (&["creole"], &["*.creole"]),
-    (&["crystal"], &["Projectfile", "*.cr", "*.ecr", "shard.yml"]),
-    (&["cs"], &["*.cs"]),
-    (&["csharp"], &["*.cs"]),
-    (&["cshtml"], &["*.cshtml"]),
-    (&["csproj"], &["*.csproj"]),
-    (&["css"], &["*.css", "*.scss"]),
-    (&["csv"], &["*.csv"]),
-    (&["cuda"], &["*.cu", "*.cuh"]),
-    (&["cython"], &["*.pyx", "*.pxi", "*.pxd"]),
-    (&["d"], &["*.d"]),
-    (&["dart"], &["*.dart"]),
-    (&["devicetree"], &["*.dts", "*.dtsi", "*.dtso"]),
-    (&["dhall"], &["*.dhall"]),
-    (&["diff"], &["*.patch", "*.diff"]),
-    (&["dita"], &["*.dita", "*.ditamap", "*.ditaval"]),
-    (&["docker"], &["*Dockerfile*"]),
-    (&["dockercompose"], &["docker-compose.yml", "docker-compose.*.yml"]),
-    (&["dts"], &["*.dts", "*.dtsi"]),
-    (&["dvc"], &["Dvcfile", "*.dvc"]),
-    (&["ebuild"], &["*.ebuild", "*.eclass"]),
-    (&["edn"], &["*.edn"]),
-    (&["elisp"], &["*.el"]),
-    (&["elixir"], &["*.ex", "*.eex", "*.exs", "*.heex", "*.leex", "*.livemd"]),
-    (&["elm"], &["*.elm"]),
-    (&["erb"], &["*.erb"]),
-    (&["erlang"], &["*.erl", "*.hrl"]),
-    (&["fennel"], &["*.fnl"]),
-    (&["fidl"], &["*.fidl"]),
-    (&["fish"], &["*.fish"]),
-    (&["flatbuffers"], &["*.fbs"]),
-    (&["fortran"], &[
-        "*.f", "*.F", "*.f77", "*.F77", "*.pfo",
-        "*.f90", "*.F90", "*.f95", "*.F95",
-    ]),
-    (&["fsharp"], &["*.fs", "*.fsx", "*.fsi"]),
-    (&["fut"], &["*.fut"]),
-    (&["gap"], &["*.g", "*.gap", "*.gi", "*.gd", "*.tst"]),
-    (&["gdscript"], &["*.gd"]),
-    (&["gleam"], &["*.gleam"]),
-    (&["gn"], &["*.gn", "*.gni"]),
-    (&["go"], &["*.go"]),
-    (&["gprbuild"], &["*.gpr"]),
-    (&["gradle"], &[
-        "*.gradle", "*.gradle.kts", "gradle.properties", "gradle-wrapper.*",
-        "gradlew", "gradlew.bat",
-    ]),
-    (&["graphql"], &["*.graphql", "*.graphqls"]),
-    (&["groovy"], &["*.groovy", "*.gradle"]),
-    (&["gzip"], &["*.gz", "*.tgz"]),
-    (&["h"], &["*.h", "*.hh", "*.hpp"]),
-    (&["haml"], &["*.haml"]),
-    (&["hare"], &["*.ha"]),
-    (&["haskell"], &["*.hs", "*.lhs", "*.cpphs", "*.c2hs", "*.hsc"]),
-    (&["hbs"], &["*.hbs"]),
-    (&["hs"], &["*.hs", "*.lhs"]),
-    (&["html"], &["*.htm", "*.html", "*.ejs"]),
-    (&["hurl"], &["*.hurl"]),
-    (&["hy"], &["*.hy"]),
-    (&["idris"], &["*.idr", "*.lidr"]),
-    (&["janet"], &["*.janet"]),
-    (&["java"], &["*.java", "*.jsp", "*.jspx", "*.properties"]),
-    (&["jinja"], &["*.j2", "*.jinja", "*.jinja2"]),
-    (&["jl"], &["*.jl"]),
-    (&["js"], &["*.js", "*.jsx", "*.vue", "*.cjs", "*.mjs"]),
-    (&["json"], &["*.json", "composer.lock", "*.sarif"]),
-    (&["jsonl"], &["*.jsonl"]),
-    (&["julia"], &["*.jl"]),
-    (&["jupyter"], &["*.ipynb", "*.jpynb"]),
-    (&["k"], &["*.k"]),
-    (&["kconfig"], &["Kconfig", "Kconfig.*"]),
-    (&["kotlin"], &["*.kt", "*.kts"]),
-    (&["lean"], &["*.lean"]),
-    (&["less"], &["*.less"]),
-    (&["license"], &[
-        // General
-        "COPYING", "COPYING[.-]*",
-        "COPYRIGHT", "COPYRIGHT[.-]*",
-        "EULA", "EULA[.-]*",
-        "licen[cs]e", "licen[cs]e.*",
-        "LICEN[CS]E", "LICEN[CS]E[.-]*", "*[.-]LICEN[CS]E*",
-        "NOTICE", "NOTICE[.-]*",
-        "PATENTS", "PATENTS[.-]*",
-        "UNLICEN[CS]E", "UNLICEN[CS]E[.-]*",
-        // GPL (gpl.txt, etc.)
-        "agpl[.-]*",
-        "gpl[.-]*",
-        "lgpl[.-]*",
-        // Other license-specific (APACHE-2.0.txt, etc.)
-        "AGPL-*[0-9]*",
-        "APACHE-*[0-9]*",
-        "BSD-*[0-9]*",
-        "CC-BY-*",
-        "GFDL-*[0-9]*",
-        "GNU-*[0-9]*",
-        "GPL-*[0-9]*",
-        "LGPL-*[0-9]*",
-        "MIT-*[0-9]*",
-        "MPL-*[0-9]*",
-        "OFL-*[0-9]*",
-    ]),
-    (&["lilypond"], &["*.ly", "*.ily"]),
-    (&["lisp"], &["*.el", "*.jl", "*.lisp", "*.lsp", "*.sc", "*.scm"]),
-    (&["llvm"], &["*.ll"]),
-    (&["lock"], &["*.lock", "package-lock.json"]),
-    (&["log"], &["*.log"]),
-    (&["lua"], &["*.lua"]),
-    (&["lz4"], &["*.lz4"]),
-    (&["lzma"], &["*.lzma"]),
-    (&["m4"], &["*.ac", "*.m4"]),
-    (&["make"], &[
-        "[Gg][Nn][Uu]makefile", "[Mm]akefile",
-        "[Gg][Nn][Uu]makefile.am", "[Mm]akefile.am",
-        "[Gg][Nn][Uu]makefile.in", "[Mm]akefile.in",
-        "Makefile.*",
-        "*.mk", "*.mak"
-    ]),
-    (&["mako"], &["*.mako", "*.mao"]),
-    (&["man"], &["*.[0-9lnpx]", "*.[0-9][cEFMmpSx]"]),
-    (&["markdown", "md"], &[
-        "*.markdown",
-        "*.md",
-        "*.mdown",
-        "*.mdwn",
-        "*.mkd",
-        "*.mkdn",
-        "*.mdx",
-    ]),
-    (&["matlab"], &["*.m"]),
-    (&["meson"], &["meson.build", "meson_options.txt", "meson.options"]),
-    (&["minified"], &["*.min.html", "*.min.css", "*.min.js"]),
-    (&["mint"], &["*.mint"]),
-    (&["mk"], &["mkfile"]),
-    (&["ml"], &["*.ml"]),
-    (&["mojo"], &["*.mojo"]),
-    (&["motoko"], &["*.mo"]),
-    (&["msbuild"], &[
-        "*.csproj", "*.fsproj", "*.vcxproj", "*.proj", "*.props", "*.targets",
-        "*.sln", "*.slnf"
-    ]),
-    (&["nim"], &["*.nim", "*.nimf", "*.nimble", "*.nims"]),
-    (&["nix"], &["*.nix"]),
-    (&["objc"], &["*.h", "*.m"]),
-    (&["objcpp"], &["*.h", "*.mm"]),
-    (&["ocaml"], &["*.ml", "*.mli", "*.mll", "*.mly"]),
-    (&["org"], &["*.org", "*.org_archive"]),
-    (&["pants"], &["BUILD"]),
-    (&["pascal"], &["*.pas", "*.dpr", "*.lpr", "*.pp", "*.inc"]),
-    (&["pdf"], &["*.pdf"]),
-    (&["perl"], &["*.perl", "*.pl", "*.PL", "*.plh", "*.plx", "*.pm", "*.t"]),
-    (&["php"], &[
-        // note that PHP 6 doesn't exist
-        // See: https://wiki.php.net/rfc/php6
-        "*.php", "*.php3", "*.php4", "*.php5", "*.php7", "*.php8",
-        "*.pht", "*.phtml"
-    ]),
-    (&["pkgbuild"], &["PKGBUILD"]),
-    (&["po"], &["*.po"]),
-    (&["pod"], &["*.pod"]),
-    (&["postscript"], &["*.eps", "*.ps"]),
-    (&["prolog"], &["*.pl", "*.pro", "*.prolog", "*.P"]),
-    (&["proto", "protobuf"], &["*.proto"]),
-    (&["ps"], &["*.cdxml", "*.ps1", "*.ps1xml", "*.psd1", "*.psm1"]),
-    (&["puppet"], &["*.epp", "*.erb", "*.pp", "*.rb"]),
-    (&["purs"], &["*.purs"]),
-    (&["py", "python"], &["*.py", "*.pyi"]),
-    (&["qmake"], &["*.pro", "*.pri", "*.prf"]),
-    (&["qml"], &["*.qml"]),
-    (&["qrc"], &["*.qrc"]),
-    (&["qui"], &["*.ui"]),
-    (&["r"], &["*.R", "*.r", "*.Rmd", "*.rmd", "*.Rnw", "*.rnw"]),
-    (&["racket"], &["*.rkt"]),
-    (&["raku"], &[
-        "*.raku", "*.rakumod", "*.rakudoc", "*.rakutest",
-        "*.p6", "*.pl6", "*.pm6"
-    ]),
-    (&["rdoc"], &["*.rdoc"]),
-    (&["readme"], &["README*", "*README"]),
-    (&["reasonml"], &["*.re", "*.rei"]),
-    (&["red"], &["*.r", "*.red", "*.reds"]),
-    (&["rescript"], &["*.res", "*.resi"]),
-    (&["robot"], &["*.robot"]),
-    (&["rocq"], &["*.v"]),
-    (&["rst"], &["*.rst"]),
-    (&["ruby"], &[
-        // Idiomatic files
-        "config.ru", "Gemfile", ".irbrc", "Rakefile",
-        // Extensions
-        "*.gemspec", "*.rb", "*.rbw", "*.rake"
-    ]),
-    (&["rust"], &["*.rs"]),
-    (&["sass"], &["*.sass", "*.scss"]),
-    (&["scala"], &["*.scala", "*.sbt"]),
-    (&["scdoc"], &["*.scd", "*.scdoc"]),
-    (&["seed7"], &["*.sd7", "*.s7i"]),
-    (&["sh"], &[
-        // Portable/misc. init files
-        ".env", ".login", ".logout", ".profile", "profile",
-        // bash-specific init files
-        ".bash_login", "bash_login",
-        ".bash_logout", "bash_logout",
-        ".bash_profile", "bash_profile",
-        ".bashrc", "bashrc", "*.bashrc",
-        // csh-specific init files
-        ".cshrc", "*.cshrc",
-        // ksh-specific init files
-        ".kshrc", "*.kshrc",
-        // tcsh-specific init files
-        ".tcshrc",
-        // zsh-specific init files
-        ".zshenv", "zshenv",
-        ".zlogin", "zlogin",
-        ".zlogout", "zlogout",
-        ".zprofile", "zprofile",
-        ".zshrc", "zshrc",
-        // Extensions
-        "*.bash", "*.csh", "*.env", "*.ksh", "*.sh", "*.tcsh", "*.zsh",
-    ]),
-    (&["slim"], &["*.skim", "*.slim", "*.slime"]),
-    (&["smarty"], &["*.tpl"]),
-    (&["sml"], &["*.sml", "*.sig"]),
-    (&["solidity"], &["*.sol"]),
-    (&["soy"], &["*.soy"]),
-    (&["spark"], &["*.spark"]),
-    (&["spec"], &["*.spec"]),
-    (&["sql"], &["*.sql", "*.psql"]),
-    (&["ssa"], &["*.ssa"]),
-    (&["stylus"], &["*.styl"]),
-    (&["sv"], &["*.v", "*.vg", "*.sv", "*.svh", "*.h"]),
-    (&["svelte"], &["*.svelte", "*.svelte.ts"]),
-    (&["svg"], &["*.svg"]),
-    (&["swift"], &["*.swift"]),
-    (&["swig"], &["*.def", "*.i"]),
-    (&["systemd"], &[
-        "*.automount", "*.conf", "*.device", "*.link", "*.mount", "*.path",
-        "*.scope", "*.service", "*.slice", "*.socket", "*.swap", "*.target",
-        "*.timer",
-    ]),
-    (&["taskpaper"], &["*.taskpaper"]),
-    (&["tcl"], &["*.tcl"]),
-    (&["tex"], &["*.tex", "*.ltx", "*.cls", "*.sty", "*.bib", "*.dtx", "*.ins"]),
-    (&["texinfo"], &["*.texi"]),
-    (&["textile"], &["*.textile"]),
-    (&["tf"], &[
-        "*.tf", "*.tf.json", "*.tfvars", "*.tfvars.json",
-        "*.terraformrc", "terraform.rc", "*.tfrc", "*.terraform.lock.hcl",
-    ]),
-    (&["thrift"], &["*.thrift"]),
-    (&["toml"], &["*.toml", "Cargo.lock"]),
-    (&["ts", "typescript"], &["*.ts", "*.tsx", "*.cts", "*.mts"]),
-    (&["twig"], &["*.twig"]),
-    (&["txt"], &["*.txt"]),
-    (&["typoscript"], &["*.typoscript", "*.ts"]),
-    (&["typst"], &["*.typ"]),
-    (&["usd"], &["*.usd", "*.usda", "*.usdc"]),
-    (&["v"], &["*.v", "*.vsh"]),
-    (&["vala"], &["*.vala"]),
-    (&["vb"], &["*.vb"]),
-    (&["vcl"], &["*.vcl"]),
-    (&["verilog"], &["*.v", "*.vh", "*.sv", "*.svh"]),
-    (&["vhdl"], &["*.vhd", "*.vhdl"]),
-    (&["vim"], &[
-        "*.vim", ".vimrc", ".gvimrc", "vimrc", "gvimrc", "_vimrc", "_gvimrc",
-    ]),
-    (&["vimscript"], &[
-        "*.vim", ".vimrc", ".gvimrc", "vimrc", "gvimrc", "_vimrc", "_gvimrc",
-    ]),
-    (&["vue"], &["*.vue"]),
-    (&["webidl"], &["*.idl", "*.webidl", "*.widl"]),
-    (&["wgsl"], &["*.wgsl"]),
-    (&["wiki"], &["*.mediawiki", "*.wiki"]),
-    (&["xml"], &[
-        "*.xml", "*.xml.dist", "*.dtd", "*.xsl", "*.xslt", "*.xsd", "*.xjb",
-        "*.rng", "*.sch", "*.xhtml",
-    ]),
-    (&["xz"], &["*.xz", "*.txz"]),
-    (&["yacc"], &["*.y"]),
-    (&["yaml"], &["*.yaml", "*.yml"]),
-    (&["yang"], &["*.yang"]),
-    (&["z"], &["*.Z"]),
-    (&["zig"], &["*.zig"]),
-    (&["zsh"], &[
-        ".zshenv", "zshenv",
-        ".zlogin", "zlogin",
-        ".zlogout", "zlogout",
-        ".zprofile", "zprofile",
-        ".zshrc", "zshrc",
-        "*.zsh",
-    ]),
-    (&["zstd"], &["*.zst", "*.zstd"]),
-];
-
-#[cfg(test)]
-mod tests {
-    use super::DEFAULT_TYPES;
-
-    #[test]
-    fn default_types_are_sorted() {
-        let mut names = DEFAULT_TYPES.iter().map(|(aliases, _)| aliases[0]);
-        let Some(mut previous_name) = names.next() else {
-            return;
-        };
-        for name in names {
-            assert!(
-                name > previous_name,
-                r#""{}" should be sorted before "{}" in `DEFAULT_TYPES`"#,
-                name,
-                previous_name
-            );
-            previous_name = name;
-        }
-    }
-
-    #[test]
-    fn default_types_aliases_are_sorted() {
-        for (aliases, _) in DEFAULT_TYPES.iter() {
-            assert!(
-                aliases.is_sorted(),
-                "this alias list is not sorted: {aliases:?}",
-            );
-        }
-    }
-}

crates/ignore/src/gitignore.rs

@@ -1,913 +0,0 @@
-/*!
-The gitignore module provides a way to match globs from a gitignore file
-against file paths.
-
-Note that this module implements the specification as described in the
-`gitignore` man page from scratch. That is, this module does *not* shell out to
-the `git` command line tool.
-*/
-
-use std::{
-    fs::File,
-    io::{BufRead, BufReader, Read},
-    path::{Path, PathBuf},
-    sync::Arc,
-};
-
-use {
-    globset::{Candidate, GlobBuilder, GlobSet, GlobSetBuilder},
-    regex_automata::util::pool::Pool,
-};
-
-use crate::{
-    Error, Match, PartialErrorBuilder,
-    pathutil::{is_file_name, strip_prefix},
-};
-
-/// Glob represents a single glob in a gitignore file.
-///
-/// This is used to report information about the highest precedent glob that
-/// matched in one or more gitignore files.
-#[derive(Clone, Debug)]
-pub struct Glob {
-    /// The file path that this glob was extracted from.
-    from: Option<PathBuf>,
-    /// The original glob string.
-    original: String,
-    /// The actual glob string used to convert to a regex.
-    actual: String,
-    /// Whether this is a whitelisted glob or not.
-    is_whitelist: bool,
-    /// Whether this glob should only match directories or not.
-    is_only_dir: bool,
-}
-
-impl Glob {
-    /// Returns the file path that defined this glob.
-    pub fn from(&self) -> Option<&Path> {
-        self.from.as_ref().map(|p| &**p)
-    }
-
-    /// The original glob as it was defined in a gitignore file.
-    pub fn original(&self) -> &str {
-        &self.original
-    }
-
-    /// The actual glob that was compiled to respect gitignore
-    /// semantics.
-    pub fn actual(&self) -> &str {
-        &self.actual
-    }
-
-    /// Whether this was a whitelisted glob or not.
-    pub fn is_whitelist(&self) -> bool {
-        self.is_whitelist
-    }
-
-    /// Whether this glob must match a directory or not.
-    pub fn is_only_dir(&self) -> bool {
-        self.is_only_dir
-    }
-
-    /// Returns true if and only if this glob has a `**/` prefix.
-    fn has_doublestar_prefix(&self) -> bool {
-        self.actual.starts_with("**/") || self.actual == "**"
-    }
-}
-
-/// Gitignore is a matcher for the globs in one or more gitignore files
-/// in the same directory.
-#[derive(Clone, Debug)]
-pub struct Gitignore {
-    set: GlobSet,
-    root: PathBuf,
-    globs: Vec<Glob>,
-    num_ignores: u64,
-    num_whitelists: u64,
-    matches: Option<Arc<Pool<Vec<usize>>>>,
-    // CHANGED: Add a flag to have Gitignore rules that apply only to files.
-    only_on_files: bool,
-}
-
-impl Gitignore {
-    /// Creates a new gitignore matcher from the gitignore file path given.
-    ///
-    /// If it's desirable to include multiple gitignore files in a single
-    /// matcher, or read gitignore globs from a different source, then
-    /// use `GitignoreBuilder`.
-    ///
-    /// This always returns a valid matcher, even if it's empty. In particular,
-    /// a Gitignore file can be partially valid, e.g., when one glob is invalid
-    /// but the rest aren't.
-    ///
-    /// Note that I/O errors are ignored. For more granular control over
-    /// errors, use `GitignoreBuilder`.
-    pub fn new<P: AsRef<Path>>(
-        gitignore_path: P,
-    ) -> (Gitignore, Option<Error>) {
-        let path = gitignore_path.as_ref();
-        let parent = path.parent().unwrap_or(Path::new("/"));
-        let mut builder = GitignoreBuilder::new(parent);
-        let mut errs = PartialErrorBuilder::default();
-        errs.maybe_push_ignore_io(builder.add(path));
-        match builder.build() {
-            Ok(gi) => (gi, errs.into_error_option()),
-            Err(err) => {
-                errs.push(err);
-                (Gitignore::empty(), errs.into_error_option())
-            }
-        }
-    }
-
-    /// Creates a new gitignore matcher from the global ignore file, if one
-    /// exists.
-    ///
-    /// The global config file path is specified by git's `core.excludesFile`
-    /// config option.
-    ///
-    /// # Behavior
-    ///
-    /// This routine does its best to discover any global git exclude files.
-    /// This will try to parse out the `excludesFile` config option in your
-    /// global git configuration, if necessary.
-    ///
-    /// The specific things this routine tries (which are subject to change
-    /// based on how git behaves) are:
-    ///
-    ///
-    ///
-    /// Git's config file location is `$HOME/.gitconfig`. If `$HOME/.gitconfig`
-    /// does not exist or does not specify `core.excludesFile`, then
-    /// `$XDG_CONFIG_HOME/git/ignore` is read. If `$XDG_CONFIG_HOME` is not
-    /// set or is empty, then `$HOME/.config/git/ignore` is used instead.
-    pub fn global() -> (Gitignore, Option<Error>) {
-        match std::env::current_dir() {
-            Ok(cwd) => GitignoreBuilder::new(cwd).build_global(),
-            Err(err) => (Gitignore::empty(), Some(err.into())),
-        }
-    }
-
-    /// Creates a new empty gitignore matcher that never matches anything.
-    ///
-    /// Its path is empty.
-    pub fn empty() -> Gitignore {
-        Gitignore {
-            set: GlobSet::empty(),
-            root: PathBuf::from(""),
-            globs: vec![],
-            num_ignores: 0,
-            num_whitelists: 0,
-            matches: None,
-            // CHANGED: Add a flag to have Gitignore rules that apply only to
-            // files.
-            only_on_files: false,
-        }
-    }
-
-    /// Returns the directory containing this gitignore matcher.
-    ///
-    /// All matches are done relative to this path.
-    pub fn path(&self) -> &Path {
-        &*self.root
-    }
-
-    /// Returns true if and only if this gitignore has zero globs, and
-    /// therefore never matches any file path.
-    pub fn is_empty(&self) -> bool {
-        self.set.is_empty()
-    }
-
-    /// Returns the total number of globs, which should be equivalent to
-    /// `num_ignores + num_whitelists`.
-    pub fn len(&self) -> usize {
-        self.set.len()
-    }
-
-    /// Returns the total number of ignore globs.
-    pub fn num_ignores(&self) -> u64 {
-        self.num_ignores
-    }
-
-    /// Returns the total number of whitelisted globs.
-    pub fn num_whitelists(&self) -> u64 {
-        self.num_whitelists
-    }
-
-    /// Returns whether the given path (file or directory) matched a pattern in
-    /// this gitignore matcher.
-    ///
-    /// `is_dir` should be true if the path refers to a directory and false
-    /// otherwise.
-    ///
-    /// The given path is matched relative to the path given when building
-    /// the matcher. Specifically, before matching `path`, its prefix (as
-    /// determined by a common suffix of the directory containing this
-    /// gitignore) is stripped. If there is no common suffix/prefix overlap,
-    /// then `path` is assumed to be relative to this matcher.
-    pub fn matched<P: AsRef<Path>>(
-        &self,
-        path: P,
-        is_dir: bool,
-    ) -> Match<&Glob> {
-        if self.is_empty() {
-            return Match::None;
-        }
-        self.matched_stripped(self.strip(path.as_ref()), is_dir)
-    }
-
-    /// Returns whether the given path (file or directory, and expected to be
-    /// under the root) or any of its parent directories (up to the root)
-    /// matched a pattern in this gitignore matcher.
-    ///
-    /// NOTE: This method is more expensive than walking the directory hierarchy
-    /// top-to-bottom and matching the entries. But, is easier to use in cases
-    /// when a list of paths are available without a hierarchy.
-    ///
-    /// `is_dir` should be true if the path refers to a directory and false
-    /// otherwise.
-    ///
-    /// The given path is matched relative to the path given when building
-    /// the matcher. Specifically, before matching `path`, its prefix (as
-    /// determined by a common suffix of the directory containing this
-    /// gitignore) is stripped. If there is no common suffix/prefix overlap,
-    /// then `path` is assumed to be relative to this matcher.
-    ///
-    /// # Panics
-    ///
-    /// This method panics if the given file path is not under the root path
-    /// of this matcher.
-    pub fn matched_path_or_any_parents<P: AsRef<Path>>(
-        &self,
-        path: P,
-        is_dir: bool,
-    ) -> Match<&Glob> {
-        if self.is_empty() {
-            return Match::None;
-        }
-        let mut path = self.strip(path.as_ref());
-        assert!(!path.has_root(), "path is expected to be under the root");
-
-        match self.matched_stripped(path, is_dir) {
-            Match::None => (), // walk up
-            a_match => return a_match,
-        }
-        while let Some(parent) = path.parent() {
-            match self.matched_stripped(parent, /* is_dir */ true) {
-                Match::None => path = parent, // walk up
-                a_match => return a_match,
-            }
-        }
-        Match::None
-    }
-
-    /// Like matched, but takes a path that has already been stripped.
-    fn matched_stripped<P: AsRef<Path>>(
-        &self,
-        path: P,
-        is_dir: bool,
-    ) -> Match<&Glob> {
-        if self.is_empty() {
-            return Match::None;
-        }
-        // CHANGED: Rules marked as only_on_files can not match against
-        // directories.
-        if self.only_on_files && is_dir {
-            return Match::None;
-        }
-        let path = path.as_ref();
-        let mut matches = self.matches.as_ref().unwrap().get();
-        let candidate = Candidate::new(path);
-        self.set.matches_candidate_into(&candidate, &mut *matches);
-        for &i in matches.iter().rev() {
-            let glob = &self.globs[i];
-            if !glob.is_only_dir() || is_dir {
-                return if glob.is_whitelist() {
-                    Match::Whitelist(glob)
-                } else {
-                    Match::Ignore(glob)
-                };
-            }
-        }
-        Match::None
-    }
-
-    /// Strips the given path such that it's suitable for matching with this
-    /// gitignore matcher.
-    fn strip<'a, P: 'a + AsRef<Path> + ?Sized>(
-        &'a self,
-        path: &'a P,
-    ) -> &'a Path {
-        let mut path = path.as_ref();
-        // A leading ./ is completely superfluous. We also strip it from
-        // our gitignore root path, so we need to strip it from our candidate
-        // path too.
-        if let Some(p) = strip_prefix("./", path) {
-            path = p;
-        }
-        // Strip any common prefix between the candidate path and the root
-        // of the gitignore, to make sure we get relative matching right.
-        // BUT, a file name might not have any directory components to it,
-        // in which case, we don't want to accidentally strip any part of the
-        // file name.
-        //
-        // As an additional special case, if the root is just `.`, then we
-        // shouldn't try to strip anything, e.g., when path begins with a `.`.
-        if self.root != Path::new(".") && !is_file_name(path) {
-            if let Some(p) = strip_prefix(&self.root, path) {
-                path = p;
-                // If we're left with a leading slash, get rid of it.
-                if let Some(p) = strip_prefix("/", path) {
-                    path = p;
-                }
-            }
-        }
-        path
-    }
-}
-
-/// Builds a matcher for a single set of globs from a .gitignore file.
-#[derive(Clone, Debug)]
-pub struct GitignoreBuilder {
-    builder: GlobSetBuilder,
-    root: PathBuf,
-    globs: Vec<Glob>,
-    case_insensitive: bool,
-    allow_unclosed_class: bool,
-    // CHANGED: Add a flag to have Gitignore rules that apply only to files.
-    only_on_files: bool,
-}
-
-impl GitignoreBuilder {
-    /// Create a new builder for a gitignore file.
-    ///
-    /// The path given should be the path at which the globs for this gitignore
-    /// file should be matched. Note that paths are always matched relative
-    /// to the root path given here. Generally, the root path should correspond
-    /// to the *directory* containing a `.gitignore` file.
-    pub fn new<P: AsRef<Path>>(root: P) -> GitignoreBuilder {
-        let root = root.as_ref();
-        GitignoreBuilder {
-            builder: GlobSetBuilder::new(),
-            root: strip_prefix("./", root).unwrap_or(root).to_path_buf(),
-            globs: vec![],
-            case_insensitive: false,
-            allow_unclosed_class: true,
-            // CHANGED: Add a flag to have Gitignore rules that apply only to
-            // files.
-            only_on_files: false,
-        }
-    }
-
-    /// Builds a new matcher from the globs added so far.
-    ///
-    /// Once a matcher is built, no new globs can be added to it.
-    pub fn build(&self) -> Result<Gitignore, Error> {
-        let nignore = self.globs.iter().filter(|g| !g.is_whitelist()).count();
-        let nwhite = self.globs.iter().filter(|g| g.is_whitelist()).count();
-        let set = self
-            .builder
-            .build()
-            .map_err(|err| Error::Glob { glob: None, err: err.to_string() })?;
-        Ok(Gitignore {
-            set,
-            root: self.root.clone(),
-            globs: self.globs.clone(),
-            num_ignores: nignore as u64,
-            num_whitelists: nwhite as u64,
-            matches: Some(Arc::new(
-                Pool::with_available_parallelism_capacity(|| vec![]),
-            )),
-            // CHANGED: Add a flag to have Gitignore rules that apply only to
-            // files.
-            only_on_files: self.only_on_files,
-        })
-    }
-
-    /// Build a global gitignore matcher using the configuration in this
-    /// builder.
-    ///
-    /// This consumes ownership of the builder unlike `build` because it
-    /// must mutate the builder to add the global gitignore globs.
-    ///
-    /// Note that this ignores the path given to this builder's constructor
-    /// and instead derives the path automatically from git's global
-    /// configuration.
-    pub fn build_global(mut self) -> (Gitignore, Option<Error>) {
-        match gitconfig_excludes_path() {
-            None => (Gitignore::empty(), None),
-            Some(path) => {
-                if !path.is_file() {
-                    (Gitignore::empty(), None)
-                } else {
-                    let mut errs = PartialErrorBuilder::default();
-                    errs.maybe_push_ignore_io(self.add(path));
-                    match self.build() {
-                        Ok(gi) => (gi, errs.into_error_option()),
-                        Err(err) => {
-                            errs.push(err);
-                            (Gitignore::empty(), errs.into_error_option())
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    /// Add each glob from the file path given.
-    ///
-    /// The file given should be formatted as a `gitignore` file.
-    ///
-    /// Note that partial errors can be returned. For example, if there was
-    /// a problem adding one glob, an error for that will be returned, but
-    /// all other valid globs will still be added.
-    pub fn add<P: AsRef<Path>>(&mut self, path: P) -> Option<Error> {
-        let path = path.as_ref();
-        let file = match File::open(path) {
-            Err(err) => return Some(Error::Io(err).with_path(path)),
-            Ok(file) => file,
-        };
-        log::debug!("opened gitignore file: {}", path.display());
-        let rdr = BufReader::new(file);
-        let mut errs = PartialErrorBuilder::default();
-        for (i, line) in rdr.lines().enumerate() {
-            let lineno = (i + 1) as u64;
-            let line = match line {
-                Ok(line) => line,
-                Err(err) => {
-                    errs.push(Error::Io(err).tagged(path, lineno));
-                    break;
-                }
-            };
-
-            // Match Git's handling of .gitignore files that begin with the Unicode BOM
-            const UTF8_BOM: &str = "\u{feff}";
-            let line =
-                if i == 0 { line.trim_start_matches(UTF8_BOM) } else { &line };
-
-            if let Err(err) = self.add_line(Some(path.to_path_buf()), &line) {
-                errs.push(err.tagged(path, lineno));
-            }
-        }
-        errs.into_error_option()
-    }
-
-    /// Add each glob line from the string given.
-    ///
-    /// If this string came from a particular `gitignore` file, then its path
-    /// should be provided here.
-    ///
-    /// The string given should be formatted as a `gitignore` file.
-    #[cfg(test)]
-    fn add_str(
-        &mut self,
-        from: Option<PathBuf>,
-        gitignore: &str,
-    ) -> Result<&mut GitignoreBuilder, Error> {
-        for line in gitignore.lines() {
-            self.add_line(from.clone(), line)?;
-        }
-        Ok(self)
-    }
-
-    /// Add a line from a gitignore file to this builder.
-    ///
-    /// If this line came from a particular `gitignore` file, then its path
-    /// should be provided here.
-    ///
-    /// If the line could not be parsed as a glob, then an error is returned.
-    pub fn add_line(
-        &mut self,
-        from: Option<PathBuf>,
-        mut line: &str,
-    ) -> Result<&mut GitignoreBuilder, Error> {
-        #![allow(deprecated)]
-
-        if line.starts_with("#") {
-            return Ok(self);
-        }
-        if !line.ends_with("\\ ") {
-            line = line.trim_right();
-        }
-        if line.is_empty() {
-            return Ok(self);
-        }
-        let mut glob = Glob {
-            from,
-            original: line.to_string(),
-            actual: String::new(),
-            is_whitelist: false,
-            is_only_dir: false,
-        };
-        let mut is_absolute = false;
-        if line.starts_with("\\!") || line.starts_with("\\#") {
-            line = &line[1..];
-            is_absolute = line.chars().nth(0) == Some('/');
-        } else {
-            if line.starts_with("!") {
-                glob.is_whitelist = true;
-                line = &line[1..];
-            }
-            if line.starts_with("/") {
-                // `man gitignore` says that if a glob starts with a slash,
-                // then the glob can only match the beginning of a path
-                // (relative to the location of gitignore). We achieve this by
-                // simply banning wildcards from matching /.
-                line = &line[1..];
-                is_absolute = true;
-            }
-        }
-        // If it ends with a slash, then this should only match directories,
-        // but the slash should otherwise not be used while globbing.
-        if line.as_bytes().last() == Some(&b'/') {
-            glob.is_only_dir = true;
-            line = &line[..line.len() - 1];
-            // If the slash was escaped, then remove the escape.
-            // See: https://github.com/BurntSushi/ripgrep/issues/2236
-            if line.as_bytes().last() == Some(&b'\\') {
-                line = &line[..line.len() - 1];
-            }
-        }
-        glob.actual = line.to_string();
-        // If there is a literal slash, then this is a glob that must match the
-        // entire path name. Otherwise, we should let it match anywhere, so use
-        // a **/ prefix.
-        if !is_absolute && !line.chars().any(|c| c == '/') {
-            // ... but only if we don't already have a **/ prefix.
-            if !glob.has_doublestar_prefix() {
-                glob.actual = format!("**/{}", glob.actual);
-            }
-        }
-        // If the glob ends with `/**`, then we should only match everything
-        // inside a directory, but not the directory itself. Standard globs
-        // will match the directory. So we add `/*` to force the issue.
-        if glob.actual.ends_with("/**") {
-            glob.actual = format!("{}/*", glob.actual);
-        }
-        let parsed = GlobBuilder::new(&glob.actual)
-            .literal_separator(true)
-            .case_insensitive(self.case_insensitive)
-            .backslash_escape(true)
-            .allow_unclosed_class(self.allow_unclosed_class)
-            .build()
-            .map_err(|err| Error::Glob {
-                glob: Some(glob.original.clone()),
-                err: err.kind().to_string(),
-            })?;
-        self.builder.add(parsed);
-        self.globs.push(glob);
-        Ok(self)
-    }
-
-    /// Toggle whether the globs should be matched case insensitively or not.
-    ///
-    /// When this option is changed, only globs added after the change will be
-    /// affected.
-    ///
-    /// This is disabled by default.
-    pub fn case_insensitive(
-        &mut self,
-        yes: bool,
-    ) -> Result<&mut GitignoreBuilder, Error> {
-        // TODO: This should not return a `Result`. Fix this in the next semver
-        // release.
-        self.case_insensitive = yes;
-        Ok(self)
-    }
-
-    /// Toggle whether unclosed character classes are allowed. When allowed,
-    /// a `[` without a matching `]` is treated literally instead of resulting
-    /// in a parse error.
-    ///
-    /// For example, if this is set then the glob `[abc` will be treated as the
-    /// literal string `[abc` instead of returning an error.
-    ///
-    /// By default, this is true in order to match established `gitignore`
-    /// semantics. Generally speaking, enabling this leads to worse failure
-    /// modes since the glob parser becomes more permissive. You might want to
-    /// enable this when compatibility (e.g., with POSIX glob implementations)
-    /// is more important than good error messages.
-    pub fn allow_unclosed_class(
-        &mut self,
-        yes: bool,
-    ) -> &mut GitignoreBuilder {
-        self.allow_unclosed_class = yes;
-        self
-    }
-
-    /// CHANGED: Add a flag to have Gitignore rules that apply only to files.
-    ///
-    /// If this is set, then the globs will only be matched against file paths.
-    /// This will ensure that ignore rules like `*.pages` will _only_ ignore
-    /// files ending in `.pages` and not folders ending in `.pages`.
-    pub fn only_on_files(&mut self, yes: bool) -> &mut GitignoreBuilder {
-        self.only_on_files = yes;
-        self
-    }
-}
-
-/// Return the file path of the current environment's global gitignore file.
-///
-/// Note that the file path returned may not exist.
-pub fn gitconfig_excludes_path() -> Option<PathBuf> {
-    // When GIT_CONFIG_GLOBAL is set, it replaces both $HOME/.gitconfig and
-    // $XDG_CONFIG_HOME/git/config (per git 2.32+). Otherwise, git supports
-    // $HOME/.gitconfig and $XDG_CONFIG_HOME/git/config simultaneously, where
-    // $HOME/.gitconfig takes precedent.
-    gitconfig_global_env_contents()
-        .and_then(|x| parse_excludes_file(&x))
-        .or_else(|| {
-            gitconfig_home_contents().and_then(|x| parse_excludes_file(&x))
-        })
-        .or_else(|| {
-            gitconfig_xdg_contents().and_then(|x| parse_excludes_file(&x))
-        })
-        // System-level config has the lowest priority for core.excludesFile.
-        // GIT_CONFIG_SYSTEM overrides the default /etc/gitconfig path.
-        .or_else(|| {
-            gitconfig_system_contents().and_then(|x| parse_excludes_file(&x))
-        })
-        .or_else(excludes_file_default)
-}
-
-/// Returns the file contents of git's global config file from the path
-/// specified by the `GIT_CONFIG_GLOBAL` environment variable.
-fn gitconfig_global_env_contents() -> Option<Vec<u8>> {
-    let path = std::env::var_os("GIT_CONFIG_GLOBAL").map(PathBuf::from)?;
-    if path.as_os_str().is_empty() {
-        return None;
-    }
-    let mut file = BufReader::new(File::open(path).ok()?);
-    let mut contents = vec![];
-    file.read_to_end(&mut contents).ok().map(|_| contents)
-}
-
-/// Returns the file contents of git's system-level config file.
-///
-/// Checks `GIT_CONFIG_SYSTEM` first, then falls back to `/etc/gitconfig`.
-fn gitconfig_system_contents() -> Option<Vec<u8>> {
-    let path = std::env::var_os("GIT_CONFIG_SYSTEM")
-        .map(PathBuf::from)
-        .filter(|x| !x.as_os_str().is_empty())
-        .unwrap_or_else(|| PathBuf::from("/etc/gitconfig"));
-    let mut file = BufReader::new(File::open(path).ok()?);
-    let mut contents = vec![];
-    file.read_to_end(&mut contents).ok().map(|_| contents)
-}
-
-/// Returns the file contents of git's global config file, if one exists, in
-/// the user's home directory.
-fn gitconfig_home_contents() -> Option<Vec<u8>> {
-    let home = home_dir()?;
-    let mut file = BufReader::new(File::open(home.join(".gitconfig")).ok()?);
-    let mut contents = vec![];
-    file.read_to_end(&mut contents).ok().map(|_| contents)
-}
-
-/// Returns the file contents of git's global config file, if one exists, in
-/// the user's XDG_CONFIG_HOME directory.
-fn gitconfig_xdg_contents() -> Option<Vec<u8>> {
-    let path = std::env::var_os("XDG_CONFIG_HOME")
-        .map(PathBuf::from)
-        .filter(|x| !x.as_os_str().is_empty())
-        .or_else(|| home_dir().map(|p| p.join(".config")))
-        .map(|x| x.join("git/config"))?;
-    let mut file = BufReader::new(File::open(path).ok()?);
-    let mut contents = vec![];
-    file.read_to_end(&mut contents).ok().map(|_| contents)
-}
-
-/// Returns the default file path for a global .gitignore file.
-///
-/// Specifically, this respects XDG_CONFIG_HOME.
-fn excludes_file_default() -> Option<PathBuf> {
-    std::env::var_os("XDG_CONFIG_HOME")
-        .map(PathBuf::from)
-        .filter(|x| !x.as_os_str().is_empty())
-        .or_else(|| home_dir().map(|p| p.join(".config")))
-        .map(|x| x.join("git/ignore"))
-}
-
-/// Extract git's `core.excludesfile` config setting from the raw file contents
-/// given.
-fn parse_excludes_file(data: &[u8]) -> Option<PathBuf> {
-    use std::sync::OnceLock;
-
-    use regex_automata::{meta::Regex, util::syntax};
-
-    // N.B. This is the lazy approach, and isn't technically correct, but
-    // probably works in more circumstances. I guess we would ideally have
-    // a full INI parser. Yuck.
-    static RE: OnceLock<Regex> = OnceLock::new();
-    let re = RE.get_or_init(|| {
-        Regex::builder()
-            .configure(Regex::config().utf8_empty(false))
-            .syntax(syntax::Config::new().utf8(false))
-            .build(r#"(?im-u)^\s*excludesfile\s*=\s*"?\s*(\S+?)\s*"?\s*$"#)
-            .unwrap()
-    });
-    // We don't care about amortizing allocs here I think. This should only
-    // be called ~once per traversal or so? (Although it's not guaranteed...)
-    let mut caps = re.create_captures();
-    re.captures(data, &mut caps);
-    let span = caps.get_group(1)?;
-    let candidate = &data[span];
-    std::str::from_utf8(candidate).ok().map(|s| PathBuf::from(expand_tilde(s)))
-}
-
-/// Expands ~ in file paths to the value of $HOME.
-fn expand_tilde(path: &str) -> String {
-    let home = match home_dir() {
-        None => return path.to_string(),
-        Some(home) => home.to_string_lossy().into_owned(),
-    };
-    path.replace("~", &home)
-}
-
-/// Returns the location of the user's home directory.
-fn home_dir() -> Option<PathBuf> {
-    // We're fine with using std::env::home_dir for now. Its bugs are, IMO,
-    // pretty minor corner cases.
-    #![allow(deprecated)]
-    std::env::home_dir()
-}
-
-#[cfg(test)]
-mod tests {
-    use std::path::Path;
-
-    use super::{Gitignore, GitignoreBuilder};
-
-    fn gi_from_str<P: AsRef<Path>>(root: P, s: &str) -> Gitignore {
-        let mut builder = GitignoreBuilder::new(root);
-        builder.add_str(None, s).unwrap();
-        builder.build().unwrap()
-    }
-
-    macro_rules! ignored {
-        ($name:ident, $root:expr, $gi:expr, $path:expr) => {
-            ignored!($name, $root, $gi, $path, false);
-        };
-        ($name:ident, $root:expr, $gi:expr, $path:expr, $is_dir:expr) => {
-            #[test]
-            fn $name() {
-                let gi = gi_from_str($root, $gi);
-                assert!(gi.matched($path, $is_dir).is_ignore());
-            }
-        };
-    }
-
-    macro_rules! not_ignored {
-        ($name:ident, $root:expr, $gi:expr, $path:expr) => {
-            not_ignored!($name, $root, $gi, $path, false);
-        };
-        ($name:ident, $root:expr, $gi:expr, $path:expr, $is_dir:expr) => {
-            #[test]
-            fn $name() {
-                let gi = gi_from_str($root, $gi);
-                assert!(!gi.matched($path, $is_dir).is_ignore());
-            }
-        };
-    }
-
-    const ROOT: &'static str = "/home/foobar/rust/rg";
-
-    ignored!(ig1, ROOT, "months", "months");
-    ignored!(ig2, ROOT, "*.lock", "Cargo.lock");
-    ignored!(ig3, ROOT, "*.rs", "src/main.rs");
-    ignored!(ig4, ROOT, "src/*.rs", "src/main.rs");
-    ignored!(ig5, ROOT, "/*.c", "cat-file.c");
-    ignored!(ig6, ROOT, "/src/*.rs", "src/main.rs");
-    ignored!(ig7, ROOT, "!src/main.rs\n*.rs", "src/main.rs");
-    ignored!(ig8, ROOT, "foo/", "foo", true);
-    ignored!(ig9, ROOT, "**/foo", "foo");
-    ignored!(ig10, ROOT, "**/foo", "src/foo");
-    ignored!(ig11, ROOT, "**/foo/**", "src/foo/bar");
-    ignored!(ig12, ROOT, "**/foo/**", "wat/src/foo/bar/baz");
-    ignored!(ig13, ROOT, "**/foo/bar", "foo/bar");
-    ignored!(ig14, ROOT, "**/foo/bar", "src/foo/bar");
-    ignored!(ig15, ROOT, "abc/**", "abc/x");
-    ignored!(ig16, ROOT, "abc/**", "abc/x/y");
-    ignored!(ig17, ROOT, "abc/**", "abc/x/y/z");
-    ignored!(ig18, ROOT, "a/**/b", "a/b");
-    ignored!(ig19, ROOT, "a/**/b", "a/x/b");
-    ignored!(ig20, ROOT, "a/**/b", "a/x/y/b");
-    ignored!(ig21, ROOT, r"\!xy", "!xy");
-    ignored!(ig22, ROOT, r"\#foo", "#foo");
-    ignored!(ig23, ROOT, "foo", "./foo");
-    ignored!(ig24, ROOT, "target", "grep/target");
-    ignored!(ig25, ROOT, "Cargo.lock", "./tabwriter-bin/Cargo.lock");
-    ignored!(ig26, ROOT, "/foo/bar/baz", "./foo/bar/baz");
-    ignored!(ig27, ROOT, "foo/", "xyz/foo", true);
-    ignored!(ig28, "./src", "/llvm/", "./src/llvm", true);
-    ignored!(ig29, ROOT, "node_modules/ ", "node_modules", true);
-    ignored!(ig30, ROOT, "**/", "foo/bar", true);
-    ignored!(ig31, ROOT, "path1/*", "path1/foo");
-    ignored!(ig32, ROOT, ".a/b", ".a/b");
-    ignored!(ig33, "./", ".a/b", ".a/b");
-    ignored!(ig34, ".", ".a/b", ".a/b");
-    ignored!(ig35, "./.", ".a/b", ".a/b");
-    ignored!(ig36, "././", ".a/b", ".a/b");
-    ignored!(ig37, "././.", ".a/b", ".a/b");
-    ignored!(ig38, ROOT, "\\[", "[");
-    ignored!(ig39, ROOT, "\\?", "?");
-    ignored!(ig40, ROOT, "\\*", "*");
-    ignored!(ig41, ROOT, "\\a", "a");
-    ignored!(ig42, ROOT, "s*.rs", "sfoo.rs");
-    ignored!(ig43, ROOT, "**", "foo.rs");
-    ignored!(ig44, ROOT, "**/**/*", "a/foo.rs");
-
-    not_ignored!(ignot1, ROOT, "amonths", "months");
-    not_ignored!(ignot2, ROOT, "monthsa", "months");
-    not_ignored!(ignot3, ROOT, "/src/*.rs", "src/grep/src/main.rs");
-    not_ignored!(ignot4, ROOT, "/*.c", "mozilla-sha1/sha1.c");
-    not_ignored!(ignot5, ROOT, "/src/*.rs", "src/grep/src/main.rs");
-    not_ignored!(ignot6, ROOT, "*.rs\n!src/main.rs", "src/main.rs");
-    not_ignored!(ignot7, ROOT, "foo/", "foo", false);
-    not_ignored!(ignot8, ROOT, "**/foo/**", "wat/src/afoo/bar/baz");
-    not_ignored!(ignot9, ROOT, "**/foo/**", "wat/src/fooa/bar/baz");
-    not_ignored!(ignot10, ROOT, "**/foo/bar", "foo/src/bar");
-    not_ignored!(ignot11, ROOT, "#foo", "#foo");
-    not_ignored!(ignot12, ROOT, "\n\n\n", "foo");
-    not_ignored!(ignot13, ROOT, "foo/**", "foo", true);
-    not_ignored!(
-        ignot14,
-        "./third_party/protobuf",
-        "m4/ltoptions.m4",
-        "./third_party/protobuf/csharp/src/packages/repositories.config"
-    );
-    not_ignored!(ignot15, ROOT, "!/bar", "foo/bar");
-    not_ignored!(ignot16, ROOT, "*\n!**/", "foo", true);
-    not_ignored!(ignot17, ROOT, "src/*.rs", "src/grep/src/main.rs");
-    not_ignored!(ignot18, ROOT, "path1/*", "path2/path1/foo");
-    not_ignored!(ignot19, ROOT, "s*.rs", "src/foo.rs");
-
-    fn bytes(s: &str) -> Vec<u8> {
-        s.to_string().into_bytes()
-    }
-
-    fn path_string<P: AsRef<Path>>(path: P) -> String {
-        path.as_ref().to_str().unwrap().to_string()
-    }
-
-    #[test]
-    fn parse_excludes_file1() {
-        let data = bytes("[core]\nexcludesFile = /foo/bar");
-        let got = super::parse_excludes_file(&data).unwrap();
-        assert_eq!(path_string(got), "/foo/bar");
-    }
-
-    #[test]
-    fn parse_excludes_file2() {
-        let data = bytes("[core]\nexcludesFile = ~/foo/bar");
-        let got = super::parse_excludes_file(&data).unwrap();
-        assert_eq!(path_string(got), super::expand_tilde("~/foo/bar"));
-    }
-
-    #[test]
-    fn parse_excludes_file3() {
-        let data = bytes("[core]\nexcludeFile = /foo/bar");
-        assert!(super::parse_excludes_file(&data).is_none());
-    }
-
-    #[test]
-    fn parse_excludes_file4() {
-        let data = bytes("[core]\nexcludesFile = \"~/foo/bar\"");
-        let got = super::parse_excludes_file(&data);
-        assert_eq!(
-            path_string(got.unwrap()),
-            super::expand_tilde("~/foo/bar")
-        );
-    }
-
-    #[test]
-    fn parse_excludes_file5() {
-        let data = bytes("[core]\nexcludesFile = \" \"~/foo/bar \" \"");
-        assert!(super::parse_excludes_file(&data).is_none());
-    }
-
-    // See: https://github.com/BurntSushi/ripgrep/issues/106
-    #[test]
-    fn regression_106() {
-        gi_from_str("/", " ");
-    }
-
-    #[test]
-    fn case_insensitive() {
-        let gi = GitignoreBuilder::new(ROOT)
-            .case_insensitive(true)
-            .unwrap()
-            .add_str(None, "*.html")
-            .unwrap()
-            .build()
-            .unwrap();
-        assert!(gi.matched("foo.html", false).is_ignore());
-        assert!(gi.matched("foo.HTML", false).is_ignore());
-        assert!(!gi.matched("foo.htm", false).is_ignore());
-        assert!(!gi.matched("foo.HTM", false).is_ignore());
-    }
-
-    ignored!(cs1, ROOT, "*.html", "foo.html");
-    not_ignored!(cs2, ROOT, "*.html", "foo.HTML");
-    not_ignored!(cs3, ROOT, "*.html", "foo.htm");
-    not_ignored!(cs4, ROOT, "*.html", "foo.HTM");
-}

crates/ignore/src/lib.rs

@@ -1,549 +0,0 @@
-/*!
-The ignore crate provides a fast recursive directory iterator that respects
-various filters such as globs, file types and `.gitignore` files. The precise
-matching rules and precedence is explained in the documentation for
-`WalkBuilder`.
-
-Secondarily, this crate exposes gitignore and file type matchers for use cases
-that demand more fine-grained control.
-
-# Example
-
-This example shows the most basic usage of this crate. This code will
-recursively traverse the current directory while automatically filtering out
-files and directories according to ignore globs found in files like
-`.ignore` and `.gitignore`:
-
-
-```rust,no_run
-use ignore::Walk;
-
-for result in Walk::new("./") {
-    // Each item yielded by the iterator is either a directory entry or an
-    // error, so either print the path or the error.
-    match result {
-        Ok(entry) => println!("{}", entry.path().display()),
-        Err(err) => println!("ERROR: {}", err),
-    }
-}
-```
-
-# Example: advanced
-
-By default, the recursive directory iterator will ignore hidden files and
-directories. This can be disabled by building the iterator with `WalkBuilder`:
-
-```rust,no_run
-use ignore::WalkBuilder;
-
-for result in WalkBuilder::new("./").hidden(false).build() {
-    println!("{:?}", result);
-}
-```
-
-See the documentation for `WalkBuilder` for many other options.
-*/
-
-#![deny(missing_docs)]
-
-use std::path::{Path, PathBuf};
-
-pub use crate::incremental::{IncrementalIgnore, IncrementalMatch};
-pub use crate::walk::{
-    DirEntry, ParallelVisitor, ParallelVisitorBuilder, Walk, WalkBuilder,
-    WalkParallel, WalkState,
-};
-
-mod default_types;
-mod dir;
-pub mod gitignore;
-mod incremental;
-pub mod overrides;
-mod pathutil;
-pub mod types;
-mod walk;
-
-/// Represents an error that can occur when parsing a gitignore file.
-#[derive(Debug)]
-pub enum Error {
-    /// A collection of "soft" errors. These occur when adding an ignore
-    /// file partially succeeded.
-    Partial(Vec<Error>),
-    /// An error associated with a specific line number.
-    WithLineNumber {
-        /// The line number.
-        line: u64,
-        /// The underlying error.
-        err: Box<Error>,
-    },
-    /// An error associated with a particular file path.
-    WithPath {
-        /// The file path.
-        path: PathBuf,
-        /// The underlying error.
-        err: Box<Error>,
-    },
-    /// An error associated with a particular directory depth when recursively
-    /// walking a directory.
-    WithDepth {
-        /// The directory depth.
-        depth: usize,
-        /// The underlying error.
-        err: Box<Error>,
-    },
-    /// An error that occurs when a file loop is detected when traversing
-    /// symbolic links.
-    Loop {
-        /// The ancestor file path in the loop.
-        ancestor: PathBuf,
-        /// The child file path in the loop.
-        child: PathBuf,
-    },
-    /// An error that occurs when doing I/O, such as reading an ignore file.
-    Io(std::io::Error),
-    /// An error that occurs when trying to parse a glob.
-    Glob {
-        /// The original glob that caused this error. This glob, when
-        /// available, always corresponds to the glob provided by an end user.
-        /// e.g., It is the glob as written in a `.gitignore` file.
-        ///
-        /// (This glob may be distinct from the glob that is actually
-        /// compiled, after accounting for `gitignore` semantics.)
-        glob: Option<String>,
-        /// The underlying glob error as a string.
-        err: String,
-    },
-    /// A type selection for a file type that is not defined.
-    UnrecognizedFileType(String),
-    /// A user specified file type definition could not be parsed.
-    InvalidDefinition,
-}
-
-impl Clone for Error {
-    fn clone(&self) -> Error {
-        match *self {
-            Error::Partial(ref errs) => Error::Partial(errs.clone()),
-            Error::WithLineNumber { line, ref err } => {
-                Error::WithLineNumber { line, err: err.clone() }
-            }
-            Error::WithPath { ref path, ref err } => {
-                Error::WithPath { path: path.clone(), err: err.clone() }
-            }
-            Error::WithDepth { depth, ref err } => {
-                Error::WithDepth { depth, err: err.clone() }
-            }
-            Error::Loop { ref ancestor, ref child } => Error::Loop {
-                ancestor: ancestor.clone(),
-                child: child.clone(),
-            },
-            Error::Io(ref err) => match err.raw_os_error() {
-                Some(e) => Error::Io(std::io::Error::from_raw_os_error(e)),
-                None => {
-                    Error::Io(std::io::Error::new(err.kind(), err.to_string()))
-                }
-            },
-            Error::Glob { ref glob, ref err } => {
-                Error::Glob { glob: glob.clone(), err: err.clone() }
-            }
-            Error::UnrecognizedFileType(ref err) => {
-                Error::UnrecognizedFileType(err.clone())
-            }
-            Error::InvalidDefinition => Error::InvalidDefinition,
-        }
-    }
-}
-
-impl Error {
-    /// Returns true if this is a partial error.
-    ///
-    /// A partial error occurs when only some operations failed while others
-    /// may have succeeded. For example, an ignore file may contain an invalid
-    /// glob among otherwise valid globs.
-    pub fn is_partial(&self) -> bool {
-        match *self {
-            Error::Partial(_) => true,
-            Error::WithLineNumber { ref err, .. } => err.is_partial(),
-            Error::WithPath { ref err, .. } => err.is_partial(),
-            Error::WithDepth { ref err, .. } => err.is_partial(),
-            _ => false,
-        }
-    }
-
-    /// Returns true if this error is exclusively an I/O error.
-    pub fn is_io(&self) -> bool {
-        match *self {
-            Error::Partial(ref errs) => errs.len() == 1 && errs[0].is_io(),
-            Error::WithLineNumber { ref err, .. } => err.is_io(),
-            Error::WithPath { ref err, .. } => err.is_io(),
-            Error::WithDepth { ref err, .. } => err.is_io(),
-            Error::Loop { .. } => false,
-            Error::Io(_) => true,
-            Error::Glob { .. } => false,
-            Error::UnrecognizedFileType(_) => false,
-            Error::InvalidDefinition => false,
-        }
-    }
-
-    /// Inspect the original [`std::io::Error`] if there is one.
-    ///
-    /// [`None`] is returned if the [`Error`] doesn't correspond to an
-    /// [`std::io::Error`]. This might happen, for example, when the error was
-    /// produced because a cycle was found in the directory tree while
-    /// following symbolic links.
-    ///
-    /// This method returns a borrowed value that is bound to the lifetime of the [`Error`]. To
-    /// obtain an owned value, the [`into_io_error`] can be used instead.
-    ///
-    /// > This is the original [`std::io::Error`] and is _not_ the same as
-    /// > [`impl From<Error> for std::io::Error`][impl] which contains
-    /// > additional context about the error.
-    ///
-    /// [`None`]: https://doc.rust-lang.org/stable/std/option/enum.Option.html#variant.None
-    /// [`std::io::Error`]: https://doc.rust-lang.org/stable/std/io/struct.Error.html
-    /// [`From`]: https://doc.rust-lang.org/stable/std/convert/trait.From.html
-    /// [`Error`]: struct.Error.html
-    /// [`into_io_error`]: struct.Error.html#method.into_io_error
-    /// [impl]: struct.Error.html#impl-From%3CError%3E
-    pub fn io_error(&self) -> Option<&std::io::Error> {
-        match *self {
-            Error::Partial(ref errs) => {
-                if errs.len() == 1 {
-                    errs[0].io_error()
-                } else {
-                    None
-                }
-            }
-            Error::WithLineNumber { ref err, .. } => err.io_error(),
-            Error::WithPath { ref err, .. } => err.io_error(),
-            Error::WithDepth { ref err, .. } => err.io_error(),
-            Error::Loop { .. } => None,
-            Error::Io(ref err) => Some(err),
-            Error::Glob { .. } => None,
-            Error::UnrecognizedFileType(_) => None,
-            Error::InvalidDefinition => None,
-        }
-    }
-
-    /// Similar to [`io_error`] except consumes self to convert to the original
-    /// [`std::io::Error`] if one exists.
-    ///
-    /// [`io_error`]: struct.Error.html#method.io_error
-    /// [`std::io::Error`]: https://doc.rust-lang.org/stable/std/io/struct.Error.html
-    pub fn into_io_error(self) -> Option<std::io::Error> {
-        match self {
-            Error::Partial(mut errs) => {
-                if errs.len() == 1 {
-                    errs.remove(0).into_io_error()
-                } else {
-                    None
-                }
-            }
-            Error::WithLineNumber { err, .. } => err.into_io_error(),
-            Error::WithPath { err, .. } => err.into_io_error(),
-            Error::WithDepth { err, .. } => err.into_io_error(),
-            Error::Loop { .. } => None,
-            Error::Io(err) => Some(err),
-            Error::Glob { .. } => None,
-            Error::UnrecognizedFileType(_) => None,
-            Error::InvalidDefinition => None,
-        }
-    }
-
-    /// Returns a depth associated with recursively walking a directory (if
-    /// this error was generated from a recursive directory iterator).
-    pub fn depth(&self) -> Option<usize> {
-        match *self {
-            Error::WithPath { ref err, .. } => err.depth(),
-            Error::WithDepth { depth, .. } => Some(depth),
-            _ => None,
-        }
-    }
-
-    /// Turn an error into a tagged error with the given file path.
-    fn with_path<P: AsRef<Path>>(self, path: P) -> Error {
-        Error::WithPath {
-            path: path.as_ref().to_path_buf(),
-            err: Box::new(self),
-        }
-    }
-
-    /// Turn an error into a tagged error with the given depth.
-    fn with_depth(self, depth: usize) -> Error {
-        Error::WithDepth { depth, err: Box::new(self) }
-    }
-
-    /// Turn an error into a tagged error with the given file path and line
-    /// number. If path is empty, then it is omitted from the error.
-    fn tagged<P: AsRef<Path>>(self, path: P, lineno: u64) -> Error {
-        let errline =
-            Error::WithLineNumber { line: lineno, err: Box::new(self) };
-        if path.as_ref().as_os_str().is_empty() {
-            return errline;
-        }
-        errline.with_path(path)
-    }
-
-    /// Build an error from a walkdir error.
-    fn from_walkdir(err: walkdir::Error) -> Error {
-        let depth = err.depth();
-        if let (Some(anc), Some(child)) = (err.loop_ancestor(), err.path()) {
-            return Error::WithDepth {
-                depth,
-                err: Box::new(Error::Loop {
-                    ancestor: anc.to_path_buf(),
-                    child: child.to_path_buf(),
-                }),
-            };
-        }
-        let path = err.path().map(|p| p.to_path_buf());
-        let mut ig_err = Error::WithDepth {
-            depth,
-            err: Box::new(Error::Io(std::io::Error::from(err))),
-        };
-        if let Some(path) = path {
-            ig_err = Error::WithPath { path, err: Box::new(ig_err) };
-        }
-        ig_err
-    }
-}
-
-impl std::error::Error for Error {
-    #[allow(deprecated)]
-    fn description(&self) -> &str {
-        match *self {
-            Error::Partial(_) => "partial error",
-            Error::WithLineNumber { ref err, .. } => err.description(),
-            Error::WithPath { ref err, .. } => err.description(),
-            Error::WithDepth { ref err, .. } => err.description(),
-            Error::Loop { .. } => "file system loop found",
-            Error::Io(ref err) => err.description(),
-            Error::Glob { ref err, .. } => err,
-            Error::UnrecognizedFileType(_) => "unrecognized file type",
-            Error::InvalidDefinition => "invalid definition",
-        }
-    }
-}
-
-impl std::fmt::Display for Error {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        match *self {
-            Error::Partial(ref errs) => {
-                let msgs: Vec<String> =
-                    errs.iter().map(|err| err.to_string()).collect();
-                write!(f, "{}", msgs.join("\n"))
-            }
-            Error::WithLineNumber { line, ref err } => {
-                write!(f, "line {}: {}", line, err)
-            }
-            Error::WithPath { ref path, ref err } => {
-                write!(f, "{}: {}", path.display(), err)
-            }
-            Error::WithDepth { ref err, .. } => err.fmt(f),
-            Error::Loop { ref ancestor, ref child } => write!(
-                f,
-                "File system loop found: \
-                           {} points to an ancestor {}",
-                child.display(),
-                ancestor.display()
-            ),
-            Error::Io(ref err) => err.fmt(f),
-            Error::Glob { glob: None, ref err } => write!(f, "{}", err),
-            Error::Glob { glob: Some(ref glob), ref err } => {
-                write!(f, "error parsing glob '{}': {}", glob, err)
-            }
-            Error::UnrecognizedFileType(ref ty) => {
-                write!(f, "unrecognized file type: {}", ty)
-            }
-            Error::InvalidDefinition => write!(
-                f,
-                "invalid definition (format is type:glob, e.g., \
-                           html:*.html)"
-            ),
-        }
-    }
-}
-
-impl From<std::io::Error> for Error {
-    fn from(err: std::io::Error) -> Error {
-        Error::Io(err)
-    }
-}
-
-#[derive(Debug, Default)]
-struct PartialErrorBuilder(Vec<Error>);
-
-impl PartialErrorBuilder {
-    fn push(&mut self, err: Error) {
-        self.0.push(err);
-    }
-
-    fn push_ignore_io(&mut self, err: Error) {
-        if !err.is_io() {
-            self.push(err);
-        }
-    }
-
-    fn maybe_push(&mut self, err: Option<Error>) {
-        if let Some(err) = err {
-            self.push(err);
-        }
-    }
-
-    fn maybe_push_ignore_io(&mut self, err: Option<Error>) {
-        if let Some(err) = err {
-            self.push_ignore_io(err);
-        }
-    }
-
-    fn into_error_option(mut self) -> Option<Error> {
-        if self.0.is_empty() {
-            None
-        } else if self.0.len() == 1 {
-            Some(self.0.pop().unwrap())
-        } else {
-            Some(Error::Partial(self.0))
-        }
-    }
-}
-
-/// The result of a glob match.
-///
-/// The type parameter `T` typically refers to a type that provides more
-/// information about a particular match. For example, it might identify
-/// the specific gitignore file and the specific glob pattern that caused
-/// the match.
-#[derive(Clone, Debug)]
-pub enum Match<T> {
-    /// The path didn't match any glob.
-    None,
-    /// The highest precedent glob matched indicates the path should be
-    /// ignored.
-    Ignore(T),
-    /// The highest precedent glob matched indicates the path should be
-    /// whitelisted.
-    Whitelist(T),
-}
-
-impl<T> Match<T> {
-    /// Returns true if the match result didn't match any globs.
-    pub fn is_none(&self) -> bool {
-        match *self {
-            Match::None => true,
-            Match::Ignore(_) | Match::Whitelist(_) => false,
-        }
-    }
-
-    /// Returns true if the match result implies the path should be ignored.
-    pub fn is_ignore(&self) -> bool {
-        match *self {
-            Match::Ignore(_) => true,
-            Match::None | Match::Whitelist(_) => false,
-        }
-    }
-
-    /// Returns true if the match result implies the path should be
-    /// whitelisted.
-    pub fn is_whitelist(&self) -> bool {
-        match *self {
-            Match::Whitelist(_) => true,
-            Match::None | Match::Ignore(_) => false,
-        }
-    }
-
-    /// Inverts the match so that `Ignore` becomes `Whitelist` and
-    /// `Whitelist` becomes `Ignore`. A non-match remains the same.
-    pub fn invert(self) -> Match<T> {
-        match self {
-            Match::None => Match::None,
-            Match::Ignore(t) => Match::Whitelist(t),
-            Match::Whitelist(t) => Match::Ignore(t),
-        }
-    }
-
-    /// Return the value inside this match if it exists.
-    pub fn inner(&self) -> Option<&T> {
-        match *self {
-            Match::None => None,
-            Match::Ignore(ref t) => Some(t),
-            Match::Whitelist(ref t) => Some(t),
-        }
-    }
-
-    /// Apply the given function to the value inside this match.
-    ///
-    /// If the match has no value, then return the match unchanged.
-    pub fn map<U, F: FnOnce(T) -> U>(self, f: F) -> Match<U> {
-        match self {
-            Match::None => Match::None,
-            Match::Ignore(t) => Match::Ignore(f(t)),
-            Match::Whitelist(t) => Match::Whitelist(f(t)),
-        }
-    }
-
-    /// Return the match if it is not none. Otherwise, return other.
-    pub fn or(self, other: Self) -> Self {
-        if self.is_none() { other } else { self }
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use std::{
-        env, fs,
-        path::{Path, PathBuf},
-    };
-
-    /// A convenient result type alias.
-    pub(crate) type Result<T> =
-        std::result::Result<T, Box<dyn std::error::Error + Send + Sync>>;
-
-    macro_rules! err {
-        ($($tt:tt)*) => {
-            Box::<dyn std::error::Error + Send + Sync>::from(format!($($tt)*))
-        }
-    }
-
-    /// A simple wrapper for creating a temporary directory that is
-    /// automatically deleted when it's dropped.
-    ///
-    /// We use this in lieu of tempfile because tempfile brings in too many
-    /// dependencies.
-    #[derive(Debug)]
-    pub struct TempDir(PathBuf);
-
-    impl Drop for TempDir {
-        fn drop(&mut self) {
-            fs::remove_dir_all(&self.0).unwrap();
-        }
-    }
-
-    impl TempDir {
-        /// Create a new empty temporary directory under the system's configured
-        /// temporary directory.
-        pub fn new() -> Result<TempDir> {
-            use std::sync::atomic::{AtomicUsize, Ordering};
-
-            static TRIES: usize = 100;
-            static COUNTER: AtomicUsize = AtomicUsize::new(0);
-
-            let tmpdir = env::temp_dir();
-            for _ in 0..TRIES {
-                let count = COUNTER.fetch_add(1, Ordering::Relaxed);
-                let path = tmpdir.join("rust-ignore").join(count.to_string());
-                if path.is_dir() {
-                    continue;
-                }
-                fs::create_dir_all(&path).map_err(|e| {
-                    err!("failed to create {}: {}", path.display(), e)
-                })?;
-                return Ok(TempDir(path));
-            }
-            Err(err!("failed to create temp dir after {} tries", TRIES))
-        }
-
-        /// Return the underlying path to this temporary directory.
-        pub fn path(&self) -> &Path {
-            &self.0
-        }
-    }
-}

crates/ignore/src/overrides.rs

@@ -1,293 +0,0 @@
-/*!
-The overrides module provides a way to specify a set of override globs.
-
-This provides functionality similar to `--include` or `--exclude` in command
-line tools.
-*/
-
-use std::path::Path;
-
-use crate::{
-    Error, Match,
-    gitignore::{self, Gitignore, GitignoreBuilder},
-};
-
-/// Glob represents a single glob in an override matcher.
-///
-/// This is used to report information about the highest precedent glob
-/// that matched.
-///
-/// Note that not all matches necessarily correspond to a specific glob. For
-/// example, if there are one or more whitelist globs and a file path doesn't
-/// match any glob in the set, then the file path is considered to be ignored.
-///
-/// The lifetime `'a` refers to the lifetime of the matcher that produced
-/// this glob.
-#[derive(Clone, Debug)]
-#[allow(dead_code)]
-pub struct Glob<'a>(GlobInner<'a>);
-
-#[derive(Clone, Debug)]
-#[allow(dead_code)]
-enum GlobInner<'a> {
-    /// No glob matched, but the file path should still be ignored.
-    UnmatchedIgnore,
-    /// A glob matched.
-    Matched(&'a gitignore::Glob),
-}
-
-impl<'a> Glob<'a> {
-    fn unmatched() -> Glob<'a> {
-        Glob(GlobInner::UnmatchedIgnore)
-    }
-}
-
-/// Manages a set of overrides provided explicitly by the end user.
-#[derive(Clone, Debug)]
-pub struct Override(Gitignore);
-
-impl Override {
-    /// Returns an empty matcher that never matches any file path.
-    pub fn empty() -> Override {
-        Override(Gitignore::empty())
-    }
-
-    /// Returns the directory of this override set.
-    ///
-    /// All matches are done relative to this path.
-    pub fn path(&self) -> &Path {
-        self.0.path()
-    }
-
-    /// Returns true if and only if this matcher is empty.
-    ///
-    /// When a matcher is empty, it will never match any file path.
-    pub fn is_empty(&self) -> bool {
-        self.0.is_empty()
-    }
-
-    /// Returns the total number of ignore globs.
-    pub fn num_ignores(&self) -> u64 {
-        self.0.num_whitelists()
-    }
-
-    /// Returns the total number of whitelisted globs.
-    pub fn num_whitelists(&self) -> u64 {
-        self.0.num_ignores()
-    }
-
-    /// Returns whether the given file path matched a pattern in this override
-    /// matcher.
-    ///
-    /// `is_dir` should be true if the path refers to a directory and false
-    /// otherwise.
-    ///
-    /// If there are no overrides, then this always returns `Match::None`.
-    ///
-    /// If there is at least one whitelist override and `is_dir` is false, then
-    /// this never returns `Match::None`, since non-matches are interpreted as
-    /// ignored.
-    ///
-    /// The given path is matched to the globs relative to the path given
-    /// when building the override matcher. Specifically, before matching
-    /// `path`, its prefix (as determined by a common suffix of the directory
-    /// given) is stripped. If there is no common suffix/prefix overlap, then
-    /// `path` is assumed to reside in the same directory as the root path for
-    /// this set of overrides.
-    pub fn matched<'a, P: AsRef<Path>>(
-        &'a self,
-        path: P,
-        is_dir: bool,
-    ) -> Match<Glob<'a>> {
-        if self.is_empty() {
-            return Match::None;
-        }
-        let mat = self.0.matched(path, is_dir).invert();
-        if mat.is_none() && self.num_whitelists() > 0 && !is_dir {
-            return Match::Ignore(Glob::unmatched());
-        }
-        mat.map(move |giglob| Glob(GlobInner::Matched(giglob)))
-    }
-}
-
-/// Builds a matcher for a set of glob overrides.
-#[derive(Clone, Debug)]
-pub struct OverrideBuilder {
-    builder: GitignoreBuilder,
-}
-
-impl OverrideBuilder {
-    /// Create a new override builder.
-    ///
-    /// Matching is done relative to the directory path provided.
-    pub fn new<P: AsRef<Path>>(path: P) -> OverrideBuilder {
-        let mut builder = GitignoreBuilder::new(path);
-        builder.allow_unclosed_class(false);
-        OverrideBuilder { builder }
-    }
-
-    /// Builds a new override matcher from the globs added so far.
-    ///
-    /// Once a matcher is built, no new globs can be added to it.
-    pub fn build(&self) -> Result<Override, Error> {
-        Ok(Override(self.builder.build()?))
-    }
-
-    /// Add a glob to the set of overrides.
-    ///
-    /// Globs provided here have precisely the same semantics as a single
-    /// line in a `gitignore` file, where the meaning of `!` is inverted:
-    /// namely, `!` at the beginning of a glob will ignore a file. Without `!`,
-    /// all matches of the glob provided are treated as whitelist matches.
-    pub fn add(&mut self, glob: &str) -> Result<&mut OverrideBuilder, Error> {
-        self.builder.add_line(None, glob)?;
-        Ok(self)
-    }
-
-    /// Toggle whether the globs should be matched case insensitively or not.
-    ///
-    /// When this option is changed, only globs added after the change will be
-    /// affected.
-    ///
-    /// This is disabled by default.
-    pub fn case_insensitive(
-        &mut self,
-        yes: bool,
-    ) -> Result<&mut OverrideBuilder, Error> {
-        // TODO: This should not return a `Result`. Fix this in the next semver
-        // release.
-        self.builder.case_insensitive(yes)?;
-        Ok(self)
-    }
-
-    /// Toggle whether unclosed character classes are allowed. When allowed,
-    /// a `[` without a matching `]` is treated literally instead of resulting
-    /// in a parse error.
-    ///
-    /// For example, if this is set then the glob `[abc` will be treated as the
-    /// literal string `[abc` instead of returning an error.
-    ///
-    /// By default, this is false. Generally speaking, enabling this leads to
-    /// worse failure modes since the glob parser becomes more permissive. You
-    /// might want to enable this when compatibility (e.g., with POSIX glob
-    /// implementations) is more important than good error messages.
-    ///
-    /// This default is different from the default for [`Gitignore`]. Namely,
-    /// [`Gitignore`] is intended to match git's behavior as-is. But this
-    /// abstraction for "override" globs does not necessarily conform to any
-    /// other known specification and instead prioritizes better error
-    /// messages.
-    pub fn allow_unclosed_class(&mut self, yes: bool) -> &mut OverrideBuilder {
-        self.builder.allow_unclosed_class(yes);
-        self
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::{Override, OverrideBuilder};
-
-    const ROOT: &'static str = "/home/andrew/foo";
-
-    fn ov(globs: &[&str]) -> Override {
-        let mut builder = OverrideBuilder::new(ROOT);
-        for glob in globs {
-            builder.add(glob).unwrap();
-        }
-        builder.build().unwrap()
-    }
-
-    #[test]
-    fn empty() {
-        let ov = ov(&[]);
-        assert!(ov.matched("a.foo", false).is_none());
-        assert!(ov.matched("a", false).is_none());
-        assert!(ov.matched("", false).is_none());
-    }
-
-    #[test]
-    fn simple() {
-        let ov = ov(&["*.foo", "!*.bar"]);
-        assert!(ov.matched("a.foo", false).is_whitelist());
-        assert!(ov.matched("a.foo", true).is_whitelist());
-        assert!(ov.matched("a.rs", false).is_ignore());
-        assert!(ov.matched("a.rs", true).is_none());
-        assert!(ov.matched("a.bar", false).is_ignore());
-        assert!(ov.matched("a.bar", true).is_ignore());
-    }
-
-    #[test]
-    fn only_ignores() {
-        let ov = ov(&["!*.bar"]);
-        assert!(ov.matched("a.rs", false).is_none());
-        assert!(ov.matched("a.rs", true).is_none());
-        assert!(ov.matched("a.bar", false).is_ignore());
-        assert!(ov.matched("a.bar", true).is_ignore());
-    }
-
-    #[test]
-    fn precedence() {
-        let ov = ov(&["*.foo", "!*.bar.foo"]);
-        assert!(ov.matched("a.foo", false).is_whitelist());
-        assert!(ov.matched("a.baz", false).is_ignore());
-        assert!(ov.matched("a.bar.foo", false).is_ignore());
-    }
-
-    #[test]
-    fn gitignore() {
-        let ov = ov(&["/foo", "bar/*.rs", "baz/**"]);
-        assert!(ov.matched("bar/lib.rs", false).is_whitelist());
-        assert!(ov.matched("bar/wat/lib.rs", false).is_ignore());
-        assert!(ov.matched("wat/bar/lib.rs", false).is_ignore());
-        assert!(ov.matched("foo", false).is_whitelist());
-        assert!(ov.matched("wat/foo", false).is_ignore());
-        assert!(ov.matched("baz", false).is_ignore());
-        assert!(ov.matched("baz/a", false).is_whitelist());
-        assert!(ov.matched("baz/a/b", false).is_whitelist());
-    }
-
-    #[test]
-    fn allow_directories() {
-        // This tests that directories are NOT ignored when they are unmatched.
-        let ov = ov(&["*.rs"]);
-        assert!(ov.matched("foo.rs", false).is_whitelist());
-        assert!(ov.matched("foo.c", false).is_ignore());
-        assert!(ov.matched("foo", false).is_ignore());
-        assert!(ov.matched("foo", true).is_none());
-        assert!(ov.matched("src/foo.rs", false).is_whitelist());
-        assert!(ov.matched("src/foo.c", false).is_ignore());
-        assert!(ov.matched("src/foo", false).is_ignore());
-        assert!(ov.matched("src/foo", true).is_none());
-    }
-
-    #[test]
-    fn absolute_path() {
-        let ov = ov(&["!/bar"]);
-        assert!(ov.matched("./foo/bar", false).is_none());
-    }
-
-    #[test]
-    fn case_insensitive() {
-        let ov = OverrideBuilder::new(ROOT)
-            .case_insensitive(true)
-            .unwrap()
-            .add("*.html")
-            .unwrap()
-            .build()
-            .unwrap();
-        assert!(ov.matched("foo.html", false).is_whitelist());
-        assert!(ov.matched("foo.HTML", false).is_whitelist());
-        assert!(ov.matched("foo.htm", false).is_ignore());
-        assert!(ov.matched("foo.HTM", false).is_ignore());
-    }
-
-    #[test]
-    fn default_case_sensitive() {
-        let ov =
-            OverrideBuilder::new(ROOT).add("*.html").unwrap().build().unwrap();
-        assert!(ov.matched("foo.html", false).is_whitelist());
-        assert!(ov.matched("foo.HTML", false).is_ignore());
-        assert!(ov.matched("foo.htm", false).is_ignore());
-        assert!(ov.matched("foo.HTM", false).is_ignore());
-    }
-}

crates/ignore/src/pathutil.rs

@@ -1,171 +0,0 @@
-use std::{ffi::OsStr, path::Path};
-
-use crate::walk::DirEntry;
-
-/// Returns true if and only if this path is considered to be hidden.
-///
-/// # Platform behavior
-///
-/// ## Windows
-///
-/// This returns true if one of the following is true:
-///
-/// * The base name of the path starts with a `.`.
-/// * The file attributes have the `HIDDEN` property set.
-///
-/// ## All other platforms
-///
-/// This only returns true if the base name of the path starts with a `.`.
-pub(crate) fn is_hidden_path(dent: &Path) -> bool {
-    #[cfg(not(windows))]
-    fn imp(path: &Path) -> bool {
-        is_hidden_path_only(path)
-    }
-
-    #[cfg(windows)]
-    fn imp(path: &Path) -> bool {
-        use std::os::windows::fs::MetadataExt;
-        use winapi_util::file;
-
-        if let Ok(md) = path.metadata() {
-            if file::is_hidden(md.file_attributes() as u64) {
-                return true;
-            }
-        }
-        is_hidden_path_only(path)
-    }
-
-    imp(dent)
-}
-
-/// Returns true if and only if this directory entry is considered to be
-/// hidden.
-///
-/// # Platform behavior
-///
-/// ## Windows
-///
-/// This returns true if one of the following is true:
-///
-/// * The base name of the path starts with a `.`.
-/// * The file attributes have the `HIDDEN` property set.
-///
-/// ## All other platforms
-///
-/// This only returns true if the base name of the path starts with a `.`.
-pub(crate) fn is_hidden_entry(dent: &DirEntry) -> bool {
-    #[cfg(not(windows))]
-    fn imp(dent: &DirEntry) -> bool {
-        is_hidden_path_only(dent.path())
-    }
-
-    #[cfg(windows)]
-    fn imp(dent: &DirEntry) -> bool {
-        use std::os::windows::fs::MetadataExt;
-        use winapi_util::file;
-
-        // This looks like we're doing an extra stat call, but on Windows, the
-        // directory traverser reuses the metadata retrieved from each directory
-        // entry and stores it on the DirEntry itself. So this is "free."
-        if let Ok(md) = dent.metadata() {
-            if file::is_hidden(md.file_attributes() as u64) {
-                return true;
-            }
-        }
-        is_hidden_path_only(dent.path())
-    }
-
-    imp(dent)
-}
-
-/// Returns true if and only if this path is considered to be hidden from only
-/// the path itself.
-///
-/// This has the same behavior on all platforms.
-fn is_hidden_path_only(path: &Path) -> bool {
-    if let Some(name) = file_name(path) {
-        name.as_encoded_bytes().starts_with(b".")
-    } else {
-        false
-    }
-}
-
-/// Strip `prefix` from the `path` and return the remainder.
-///
-/// If `path` doesn't have a prefix `prefix`, then return `None`.
-pub(crate) fn strip_prefix<'a, P: AsRef<Path> + ?Sized>(
-    prefix: &'a P,
-    path: &'a Path,
-) -> Option<&'a Path> {
-    #[cfg(unix)]
-    fn imp<'a>(prefix: &'a Path, path: &'a Path) -> Option<&'a Path> {
-        use std::os::unix::ffi::OsStrExt;
-
-        let prefix = prefix.as_os_str().as_bytes();
-        let path = path.as_os_str().as_bytes();
-        if prefix.len() > path.len() || prefix != &path[0..prefix.len()] {
-            None
-        } else {
-            Some(&Path::new(OsStr::from_bytes(&path[prefix.len()..])))
-        }
-    }
-
-    #[cfg(not(unix))]
-    fn imp<'a>(prefix: &'a Path, path: &'a Path) -> Option<&'a Path> {
-        path.strip_prefix(prefix).ok()
-    }
-
-    imp(prefix.as_ref(), path)
-}
-
-/// Returns true if this file path is just a file name. i.e., Its parent is
-/// the empty string.
-pub(crate) fn is_file_name<P: AsRef<Path>>(path: P) -> bool {
-    #[cfg(unix)]
-    {
-        memchr::memchr(b'/', path.as_ref().as_os_str().as_encoded_bytes())
-            .is_none()
-    }
-    #[cfg(not(unix))]
-    {
-        path.as_ref()
-            .parent()
-            .map(|p| p.as_os_str().is_empty())
-            .unwrap_or(false)
-    }
-}
-
-/// The final component of the path, if it is a normal file.
-///
-/// If the path terminates in `.`, `..`, or consists solely of a root of
-/// prefix, this will return `None`.
-pub(crate) fn file_name<'a, P: AsRef<Path> + ?Sized>(
-    path: &'a P,
-) -> Option<&'a OsStr> {
-    #[cfg(unix)]
-    fn imp(path: &Path) -> Option<&OsStr> {
-        use std::os::unix::ffi::OsStrExt;
-
-        use memchr::memrchr;
-
-        let path = path.as_os_str().as_bytes();
-        if path.is_empty() {
-            return None;
-        } else if path.len() == 1 && path[0] == b'.' {
-            return None;
-        } else if path.last() == Some(&b'.') {
-            return None;
-        } else if path.len() >= 2 && &path[path.len() - 2..] == &b".."[..] {
-            return None;
-        }
-        let last_slash = memrchr(b'/', path).map(|i| i + 1).unwrap_or(0);
-        Some(OsStr::from_bytes(&path[last_slash..]))
-    }
-
-    #[cfg(not(unix))]
-    fn imp(path: &Path) -> Option<&OsStr> {
-        path.file_name()
-    }
-
-    imp(path.as_ref())
-}

crates/ignore/src/types.rs

@@ -1,588 +0,0 @@
-/*!
-The types module provides a way of associating globs on file names to file
-types.
-
-This can be used to match specific types of files. For example, among
-the default file types provided, the Rust file type is defined to be `*.rs`
-with name `rust`. Similarly, the C file type is defined to be `*.{c,h}` with
-name `c`.
-
-Note that the set of default types may change over time.
-
-# Example
-
-This shows how to create and use a simple file type matcher using the default
-file types defined in this crate.
-
-```
-use ignore::types::TypesBuilder;
-
-let mut builder = TypesBuilder::new();
-builder.add_defaults();
-builder.select("rust");
-let matcher = builder.build().unwrap();
-
-assert!(matcher.matched("foo.rs", false).is_whitelist());
-assert!(matcher.matched("foo.c", false).is_ignore());
-```
-
-# Example: negation
-
-This is like the previous example, but shows how negating a file type works.
-That is, this will let us match file paths that *don't* correspond to a
-particular file type.
-
-```
-use ignore::types::TypesBuilder;
-
-let mut builder = TypesBuilder::new();
-builder.add_defaults();
-builder.negate("c");
-let matcher = builder.build().unwrap();
-
-assert!(matcher.matched("foo.rs", false).is_none());
-assert!(matcher.matched("foo.c", false).is_ignore());
-```
-
-# Example: custom file type definitions
-
-This shows how to extend this library default file type definitions with
-your own.
-
-```
-use ignore::types::TypesBuilder;
-
-let mut builder = TypesBuilder::new();
-builder.add_defaults();
-builder.add("foo", "*.foo");
-// Another way of adding a file type definition.
-// This is useful when accepting input from an end user.
-builder.add_def("bar:*.bar");
-// Note: we only select `foo`, not `bar`.
-builder.select("foo");
-let matcher = builder.build().unwrap();
-
-assert!(matcher.matched("x.foo", false).is_whitelist());
-// This is ignored because we only selected the `foo` file type.
-assert!(matcher.matched("x.bar", false).is_ignore());
-```
-
-We can also add file type definitions based on other definitions.
-
-```
-use ignore::types::TypesBuilder;
-
-let mut builder = TypesBuilder::new();
-builder.add_defaults();
-builder.add("foo", "*.foo");
-builder.add_def("bar:include:foo,cpp");
-builder.select("bar");
-let matcher = builder.build().unwrap();
-
-assert!(matcher.matched("x.foo", false).is_whitelist());
-assert!(matcher.matched("y.cpp", false).is_whitelist());
-```
-*/
-
-use std::{collections::HashMap, path::Path, sync::Arc};
-
-use {
-    globset::{GlobBuilder, GlobSet, GlobSetBuilder},
-    regex_automata::util::pool::Pool,
-};
-
-use crate::{Error, Match, default_types::DEFAULT_TYPES, pathutil::file_name};
-
-/// Glob represents a single glob in a set of file type definitions.
-///
-/// There may be more than one glob for a particular file type.
-///
-/// This is used to report information about the highest precedent glob
-/// that matched.
-///
-/// Note that not all matches necessarily correspond to a specific glob.
-/// For example, if there are one or more selections and a file path doesn't
-/// match any of those selections, then the file path is considered to be
-/// ignored.
-///
-/// The lifetime `'a` refers to the lifetime of the underlying file type
-/// definition, which corresponds to the lifetime of the file type matcher.
-#[derive(Clone, Debug)]
-pub struct Glob<'a>(GlobInner<'a>);
-
-#[derive(Clone, Debug)]
-enum GlobInner<'a> {
-    /// No glob matched, but the file path should still be ignored.
-    UnmatchedIgnore,
-    /// A glob matched.
-    Matched {
-        /// The file type definition which provided the glob.
-        def: &'a FileTypeDef,
-    },
-}
-
-impl<'a> Glob<'a> {
-    fn unmatched() -> Glob<'a> {
-        Glob(GlobInner::UnmatchedIgnore)
-    }
-
-    /// Return the file type definition that matched, if one exists. A file type
-    /// definition always exists when a specific definition matches a file
-    /// path.
-    pub fn file_type_def(&self) -> Option<&FileTypeDef> {
-        match self {
-            Glob(GlobInner::UnmatchedIgnore) => None,
-            Glob(GlobInner::Matched { def, .. }) => Some(def),
-        }
-    }
-}
-
-/// A single file type definition.
-///
-/// File type definitions can be retrieved in aggregate from a file type
-/// matcher. File type definitions are also reported when its responsible
-/// for a match.
-#[derive(Clone, Debug, Eq, PartialEq)]
-pub struct FileTypeDef {
-    name: String,
-    globs: Vec<String>,
-}
-
-impl FileTypeDef {
-    /// Return the name of this file type.
-    pub fn name(&self) -> &str {
-        &self.name
-    }
-
-    /// Return the globs used to recognize this file type.
-    pub fn globs(&self) -> &[String] {
-        &self.globs
-    }
-}
-
-/// Types is a file type matcher.
-#[derive(Clone, Debug)]
-pub struct Types {
-    /// All of the file type definitions, sorted lexicographically by name.
-    defs: Vec<FileTypeDef>,
-    /// All of the selections made by the user.
-    selections: Vec<Selection<FileTypeDef>>,
-    /// Whether there is at least one Selection::Select in our selections.
-    /// When this is true, a Match::None is converted to Match::Ignore.
-    has_selected: bool,
-    /// A mapping from glob index in the set to two indices. The first is an
-    /// index into `selections` and the second is an index into the
-    /// corresponding file type definition's list of globs.
-    glob_to_selection: Vec<(usize, usize)>,
-    /// The set of all glob selections, used for actual matching.
-    set: GlobSet,
-    /// Temporary storage for globs that match.
-    matches: Arc<Pool<Vec<usize>>>,
-}
-
-/// Indicates the type of a selection for a particular file type.
-#[derive(Clone, Debug)]
-enum Selection<T> {
-    Select(String, T),
-    Negate(String, T),
-}
-
-impl<T> Selection<T> {
-    fn is_negated(&self) -> bool {
-        match *self {
-            Selection::Select(..) => false,
-            Selection::Negate(..) => true,
-        }
-    }
-
-    fn name(&self) -> &str {
-        match *self {
-            Selection::Select(ref name, _) => name,
-            Selection::Negate(ref name, _) => name,
-        }
-    }
-
-    fn map<U, F: FnOnce(T) -> U>(self, f: F) -> Selection<U> {
-        match self {
-            Selection::Select(name, inner) => {
-                Selection::Select(name, f(inner))
-            }
-            Selection::Negate(name, inner) => {
-                Selection::Negate(name, f(inner))
-            }
-        }
-    }
-
-    fn inner(&self) -> &T {
-        match *self {
-            Selection::Select(_, ref inner) => inner,
-            Selection::Negate(_, ref inner) => inner,
-        }
-    }
-}
-
-impl Types {
-    /// Creates a new file type matcher that never matches any path and
-    /// contains no file type definitions.
-    pub fn empty() -> Types {
-        Types {
-            defs: vec![],
-            selections: vec![],
-            has_selected: false,
-            glob_to_selection: vec![],
-            set: GlobSetBuilder::new().build().unwrap(),
-            matches: Arc::new(Pool::with_available_parallelism_capacity(
-                || vec![],
-            )),
-        }
-    }
-
-    /// Returns true if and only if this matcher has zero selections.
-    pub fn is_empty(&self) -> bool {
-        self.selections.is_empty()
-    }
-
-    /// Returns the number of selections used in this matcher.
-    pub fn len(&self) -> usize {
-        self.selections.len()
-    }
-
-    /// Return the set of current file type definitions.
-    ///
-    /// Definitions and globs are sorted.
-    pub fn definitions(&self) -> &[FileTypeDef] {
-        &self.defs
-    }
-
-    /// Returns a match for the given path against this file type matcher.
-    ///
-    /// The path is considered whitelisted if it matches a selected file type.
-    /// The path is considered ignored if it matches a negated file type.
-    /// If at least one file type is selected and `path` doesn't match, then
-    /// the path is also considered ignored.
-    pub fn matched<'a, P: AsRef<Path>>(
-        &'a self,
-        path: P,
-        is_dir: bool,
-    ) -> Match<Glob<'a>> {
-        // File types don't apply to directories, and we can't do anything
-        // if our glob set is empty.
-        if is_dir || self.set.is_empty() {
-            return Match::None;
-        }
-        // We only want to match against the file name, so extract it.
-        // If one doesn't exist, then we can't match it.
-        let name = match file_name(path.as_ref()) {
-            Some(name) => name,
-            None if self.has_selected => {
-                return Match::Ignore(Glob::unmatched());
-            }
-            None => {
-                return Match::None;
-            }
-        };
-        let mut matches = self.matches.get();
-        self.set.matches_into(name, &mut *matches);
-        // The highest precedent match is the last one.
-        if let Some(&i) = matches.last() {
-            let (isel, _) = self.glob_to_selection[i];
-            let sel = &self.selections[isel];
-            let glob = Glob(GlobInner::Matched { def: sel.inner() });
-            return if sel.is_negated() {
-                Match::Ignore(glob)
-            } else {
-                Match::Whitelist(glob)
-            };
-        }
-        if self.has_selected {
-            Match::Ignore(Glob::unmatched())
-        } else {
-            Match::None
-        }
-    }
-}
-
-/// TypesBuilder builds a type matcher from a set of file type definitions and
-/// a set of file type selections.
-pub struct TypesBuilder {
-    types: HashMap<String, FileTypeDef>,
-    selections: Vec<Selection<()>>,
-}
-
-impl TypesBuilder {
-    /// Create a new builder for a file type matcher.
-    ///
-    /// The builder contains *no* type definitions to start with. A set
-    /// of default type definitions can be added with `add_defaults`, and
-    /// additional type definitions can be added with `select` and `negate`.
-    pub fn new() -> TypesBuilder {
-        TypesBuilder { types: HashMap::new(), selections: vec![] }
-    }
-
-    /// Build the current set of file type definitions *and* selections into
-    /// a file type matcher.
-    pub fn build(&self) -> Result<Types, Error> {
-        let defs = self.definitions();
-        let has_selected = self.selections.iter().any(|s| !s.is_negated());
-
-        let mut selections = vec![];
-        let mut glob_to_selection = vec![];
-        let mut build_set = GlobSetBuilder::new();
-        for (isel, selection) in self.selections.iter().enumerate() {
-            let def = match self.types.get(selection.name()) {
-                Some(def) => def.clone(),
-                None => {
-                    let name = selection.name().to_string();
-                    return Err(Error::UnrecognizedFileType(name));
-                }
-            };
-            for (iglob, glob) in def.globs.iter().enumerate() {
-                build_set.add(
-                    GlobBuilder::new(glob)
-                        .literal_separator(true)
-                        .build()
-                        .map_err(|err| Error::Glob {
-                            glob: Some(glob.to_string()),
-                            err: err.kind().to_string(),
-                        })?,
-                );
-                glob_to_selection.push((isel, iglob));
-            }
-            selections.push(selection.clone().map(move |_| def));
-        }
-        let set = build_set
-            .build()
-            .map_err(|err| Error::Glob { glob: None, err: err.to_string() })?;
-        Ok(Types {
-            defs,
-            selections,
-            has_selected,
-            glob_to_selection,
-            set,
-            matches: Arc::new(Pool::with_available_parallelism_capacity(
-                || vec![],
-            )),
-        })
-    }
-
-    /// Return the set of current file type definitions.
-    ///
-    /// Definitions and globs are sorted.
-    pub fn definitions(&self) -> Vec<FileTypeDef> {
-        let mut defs = vec![];
-        for def in self.types.values() {
-            let mut def = def.clone();
-            def.globs.sort();
-            defs.push(def);
-        }
-        defs.sort_by(|def1, def2| def1.name().cmp(def2.name()));
-        defs
-    }
-
-    /// Select the file type given by `name`.
-    ///
-    /// If `name` is `all`, then all file types currently defined are selected.
-    pub fn select(&mut self, name: &str) -> &mut TypesBuilder {
-        if name == "all" {
-            for name in self.types.keys() {
-                self.selections.push(Selection::Select(name.to_string(), ()));
-            }
-        } else {
-            self.selections.push(Selection::Select(name.to_string(), ()));
-        }
-        self
-    }
-
-    /// Ignore the file type given by `name`.
-    ///
-    /// If `name` is `all`, then all file types currently defined are negated.
-    pub fn negate(&mut self, name: &str) -> &mut TypesBuilder {
-        if name == "all" {
-            for name in self.types.keys() {
-                self.selections.push(Selection::Negate(name.to_string(), ()));
-            }
-        } else {
-            self.selections.push(Selection::Negate(name.to_string(), ()));
-        }
-        self
-    }
-
-    /// Clear any file type definitions for the type name given.
-    pub fn clear(&mut self, name: &str) -> &mut TypesBuilder {
-        self.types.remove(name);
-        self
-    }
-
-    /// Add a new file type definition. `name` can be arbitrary and `pat`
-    /// should be a glob recognizing file paths belonging to the `name` type.
-    ///
-    /// If `name` is `all` or otherwise contains any character that is not a
-    /// Unicode letter or number, then an error is returned.
-    pub fn add(&mut self, name: &str, glob: &str) -> Result<(), Error> {
-        if name == "all" || !name.chars().all(|c| c.is_alphanumeric()) {
-            return Err(Error::InvalidDefinition);
-        }
-        let (key, glob) = (name.to_string(), glob.to_string());
-        self.types
-            .entry(key)
-            .or_insert_with(|| FileTypeDef {
-                name: name.to_string(),
-                globs: vec![],
-            })
-            .globs
-            .push(glob);
-        Ok(())
-    }
-
-    /// Add a new file type definition specified in string form. There are two
-    /// valid formats:
-    /// 1. `{name}:{glob}`.  This defines a 'root' definition that associates the
-    ///     given name with the given glob.
-    /// 2. `{name}:include:{comma-separated list of already defined names}.
-    ///     This defines an 'include' definition that associates the given name
-    ///     with the definitions of the given existing types.
-    /// Names may not include any characters that are not
-    /// Unicode letters or numbers.
-    pub fn add_def(&mut self, def: &str) -> Result<(), Error> {
-        let parts: Vec<&str> = def.split(':').collect();
-        match parts.len() {
-            2 => {
-                let name = parts[0];
-                let glob = parts[1];
-                if name.is_empty() || glob.is_empty() {
-                    return Err(Error::InvalidDefinition);
-                }
-                self.add(name, glob)
-            }
-            3 => {
-                let name = parts[0];
-                let types_string = parts[2];
-                if name.is_empty()
-                    || parts[1] != "include"
-                    || types_string.is_empty()
-                {
-                    return Err(Error::InvalidDefinition);
-                }
-                let types = types_string.split(',');
-                // Check ahead of time to ensure that all types specified are
-                // present and fail fast if not.
-                if types.clone().any(|t| !self.types.contains_key(t)) {
-                    return Err(Error::InvalidDefinition);
-                }
-                for type_name in types {
-                    let globs =
-                        self.types.get(type_name).unwrap().globs.clone();
-                    for glob in globs {
-                        self.add(name, &glob)?;
-                    }
-                }
-                Ok(())
-            }
-            _ => Err(Error::InvalidDefinition),
-        }
-    }
-
-    /// Add a set of default file type definitions.
-    pub fn add_defaults(&mut self) -> &mut TypesBuilder {
-        static MSG: &'static str = "adding a default type should never fail";
-        for &(names, exts) in DEFAULT_TYPES {
-            for name in names {
-                for ext in exts {
-                    self.add(name, ext).expect(MSG);
-                }
-            }
-        }
-        self
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::TypesBuilder;
-
-    macro_rules! matched {
-        ($name:ident, $types:expr, $sel:expr, $selnot:expr,
-         $path:expr) => {
-            matched!($name, $types, $sel, $selnot, $path, true);
-        };
-        (not, $name:ident, $types:expr, $sel:expr, $selnot:expr,
-         $path:expr) => {
-            matched!($name, $types, $sel, $selnot, $path, false);
-        };
-        ($name:ident, $types:expr, $sel:expr, $selnot:expr,
-         $path:expr, $matched:expr) => {
-            #[test]
-            fn $name() {
-                let mut btypes = TypesBuilder::new();
-                for tydef in $types {
-                    btypes.add_def(tydef).unwrap();
-                }
-                for sel in $sel {
-                    btypes.select(sel);
-                }
-                for selnot in $selnot {
-                    btypes.negate(selnot);
-                }
-                let types = btypes.build().unwrap();
-                let mat = types.matched($path, false);
-                assert_eq!($matched, !mat.is_ignore());
-            }
-        };
-    }
-
-    fn types() -> Vec<&'static str> {
-        vec![
-            "html:*.html",
-            "html:*.htm",
-            "rust:*.rs",
-            "js:*.js",
-            "py:*.py",
-            "python:*.py",
-            "foo:*.{rs,foo}",
-            "combo:include:html,rust",
-        ]
-    }
-
-    matched!(match1, types(), vec!["rust"], vec![], "lib.rs");
-    matched!(match2, types(), vec!["html"], vec![], "index.html");
-    matched!(match3, types(), vec!["html"], vec![], "index.htm");
-    matched!(match4, types(), vec!["html", "rust"], vec![], "main.rs");
-    matched!(match5, types(), vec![], vec![], "index.html");
-    matched!(match6, types(), vec![], vec!["rust"], "index.html");
-    matched!(match7, types(), vec!["foo"], vec!["rust"], "main.foo");
-    matched!(match8, types(), vec!["combo"], vec![], "index.html");
-    matched!(match9, types(), vec!["combo"], vec![], "lib.rs");
-    matched!(match10, types(), vec!["py"], vec![], "main.py");
-    matched!(match11, types(), vec!["python"], vec![], "main.py");
-
-    matched!(not, matchnot1, types(), vec!["rust"], vec![], "index.html");
-    matched!(not, matchnot2, types(), vec![], vec!["rust"], "main.rs");
-    matched!(not, matchnot3, types(), vec!["foo"], vec!["rust"], "main.rs");
-    matched!(not, matchnot4, types(), vec!["rust"], vec!["foo"], "main.rs");
-    matched!(not, matchnot5, types(), vec!["rust"], vec!["foo"], "main.foo");
-    matched!(not, matchnot6, types(), vec!["combo"], vec![], "leftpad.js");
-    matched!(not, matchnot7, types(), vec!["py"], vec![], "index.html");
-    matched!(not, matchnot8, types(), vec!["python"], vec![], "doc.md");
-
-    #[test]
-    fn test_invalid_defs() {
-        let mut btypes = TypesBuilder::new();
-        for tydef in types() {
-            btypes.add_def(tydef).unwrap();
-        }
-        // Preserve the original definitions for later comparison.
-        let original_defs = btypes.definitions();
-        let bad_defs = vec![
-            // Reference to type that does not exist
-            "combo:include:html,qwerty",
-            // Bad format
-            "combo:foobar:html,rust",
-            "",
-        ];
-        for def in bad_defs {
-            assert!(btypes.add_def(def).is_err());
-            // Ensure that nothing changed, even if some of the includes were valid.
-            assert_eq!(btypes.definitions(), original_defs);
-        }
-    }
-}

crates/ignore/tests/gitignore_matched_path_or_any_parents_tests.gitignore

@@ -1,216 +0,0 @@
-# Based on https://github.com/behnam/gitignore-test/blob/master/.gitignore
-
-### file in root
-
-# MATCH /file_root_1
-file_root_00
-
-# NO_MATCH
-file_root_01/
-
-# NO_MATCH
-file_root_02/*
-
-# NO_MATCH
-file_root_03/**
-
-
-# MATCH /file_root_10
-/file_root_10
-
-# NO_MATCH
-/file_root_11/
-
-# NO_MATCH
-/file_root_12/*
-
-# NO_MATCH
-/file_root_13/**
-
-
-# NO_MATCH
-*/file_root_20
-
-# NO_MATCH
-*/file_root_21/
-
-# NO_MATCH
-*/file_root_22/*
-
-# NO_MATCH
-*/file_root_23/**
-
-
-# MATCH /file_root_30
-**/file_root_30
-
-# NO_MATCH
-**/file_root_31/
-
-# NO_MATCH
-**/file_root_32/*
-
-# NO_MATCH
-**/file_root_33/**
-
-
-### file in sub-dir
-
-# MATCH /parent_dir/file_deep_1
-file_deep_00
-
-# NO_MATCH
-file_deep_01/
-
-# NO_MATCH
-file_deep_02/*
-
-# NO_MATCH
-file_deep_03/**
-
-
-# NO_MATCH
-/file_deep_10
-
-# NO_MATCH
-/file_deep_11/
-
-# NO_MATCH
-/file_deep_12/*
-
-# NO_MATCH
-/file_deep_13/**
-
-
-# MATCH /parent_dir/file_deep_20
-*/file_deep_20
-
-# NO_MATCH
-*/file_deep_21/
-
-# NO_MATCH
-*/file_deep_22/*
-
-# NO_MATCH
-*/file_deep_23/**
-
-
-# MATCH /parent_dir/file_deep_30
-**/file_deep_30
-
-# NO_MATCH
-**/file_deep_31/
-
-# NO_MATCH
-**/file_deep_32/*
-
-# NO_MATCH
-**/file_deep_33/**
-
-
-### dir in root
-
-# MATCH /dir_root_00
-dir_root_00
-
-# MATCH /dir_root_01
-dir_root_01/
-
-# MATCH /dir_root_02
-dir_root_02/*
-
-# MATCH /dir_root_03
-dir_root_03/**
-
-
-# MATCH /dir_root_10
-/dir_root_10
-
-# MATCH /dir_root_11
-/dir_root_11/
-
-# MATCH /dir_root_12
-/dir_root_12/*
-
-# MATCH /dir_root_13
-/dir_root_13/**
-
-
-# NO_MATCH
-*/dir_root_20
-
-# NO_MATCH
-*/dir_root_21/
-
-# NO_MATCH
-*/dir_root_22/*
-
-# NO_MATCH
-*/dir_root_23/**
-
-
-# MATCH /dir_root_30
-**/dir_root_30
-
-# MATCH /dir_root_31
-**/dir_root_31/
-
-# MATCH /dir_root_32
-**/dir_root_32/*
-
-# MATCH /dir_root_33
-**/dir_root_33/**
-
-
-### dir in sub-dir
-
-# MATCH /parent_dir/dir_deep_00
-dir_deep_00
-
-# MATCH /parent_dir/dir_deep_01
-dir_deep_01/
-
-# NO_MATCH
-dir_deep_02/*
-
-# NO_MATCH
-dir_deep_03/**
-
-
-# NO_MATCH
-/dir_deep_10
-
-# NO_MATCH
-/dir_deep_11/
-
-# NO_MATCH
-/dir_deep_12/*
-
-# NO_MATCH
-/dir_deep_13/**
-
-
-# MATCH /parent_dir/dir_deep_20
-*/dir_deep_20
-
-# MATCH /parent_dir/dir_deep_21
-*/dir_deep_21/
-
-# MATCH /parent_dir/dir_deep_22
-*/dir_deep_22/*
-
-# MATCH /parent_dir/dir_deep_23
-*/dir_deep_23/**
-
-
-# MATCH /parent_dir/dir_deep_30
-**/dir_deep_30
-
-# MATCH /parent_dir/dir_deep_31
-**/dir_deep_31/
-
-# MATCH /parent_dir/dir_deep_32
-**/dir_deep_32/*
-
-# MATCH /parent_dir/dir_deep_33
-**/dir_deep_33/**

crates/ignore/tests/gitignore_matched_path_or_any_parents_tests.rs

@@ -1,318 +0,0 @@
-use std::path::Path;
-
-use ignore::gitignore::{Gitignore, GitignoreBuilder};
-
-const IGNORE_FILE: &'static str =
-    "tests/gitignore_matched_path_or_any_parents_tests.gitignore";
-
-fn get_gitignore() -> Gitignore {
-    let mut builder = GitignoreBuilder::new("ROOT");
-    let error = builder.add(IGNORE_FILE);
-    assert!(error.is_none(), "failed to open gitignore file");
-    builder.build().unwrap()
-}
-
-#[test]
-#[should_panic(expected = "path is expected to be under the root")]
-fn test_path_should_be_under_root() {
-    let gitignore = get_gitignore();
-    let path = "/tmp/some_file";
-    gitignore.matched_path_or_any_parents(Path::new(path), false);
-    assert!(false);
-}
-
-#[test]
-fn test_files_in_root() {
-    let gitignore = get_gitignore();
-    let m = |path: &str| {
-        gitignore.matched_path_or_any_parents(Path::new(path), false)
-    };
-
-    // 0x
-    assert!(m("ROOT/file_root_00").is_ignore());
-    assert!(m("ROOT/file_root_01").is_none());
-    assert!(m("ROOT/file_root_02").is_none());
-    assert!(m("ROOT/file_root_03").is_none());
-
-    // 1x
-    assert!(m("ROOT/file_root_10").is_ignore());
-    assert!(m("ROOT/file_root_11").is_none());
-    assert!(m("ROOT/file_root_12").is_none());
-    assert!(m("ROOT/file_root_13").is_none());
-
-    // 2x
-    assert!(m("ROOT/file_root_20").is_none());
-    assert!(m("ROOT/file_root_21").is_none());
-    assert!(m("ROOT/file_root_22").is_none());
-    assert!(m("ROOT/file_root_23").is_none());
-
-    // 3x
-    assert!(m("ROOT/file_root_30").is_ignore());
-    assert!(m("ROOT/file_root_31").is_none());
-    assert!(m("ROOT/file_root_32").is_none());
-    assert!(m("ROOT/file_root_33").is_none());
-}
-
-#[test]
-fn test_files_in_deep() {
-    let gitignore = get_gitignore();
-    let m = |path: &str| {
-        gitignore.matched_path_or_any_parents(Path::new(path), false)
-    };
-
-    // 0x
-    assert!(m("ROOT/parent_dir/file_deep_00").is_ignore());
-    assert!(m("ROOT/parent_dir/file_deep_01").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_02").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_03").is_none());
-
-    // 1x
-    assert!(m("ROOT/parent_dir/file_deep_10").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_11").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_12").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_13").is_none());
-
-    // 2x
-    assert!(m("ROOT/parent_dir/file_deep_20").is_ignore());
-    assert!(m("ROOT/parent_dir/file_deep_21").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_22").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_23").is_none());
-
-    // 3x
-    assert!(m("ROOT/parent_dir/file_deep_30").is_ignore());
-    assert!(m("ROOT/parent_dir/file_deep_31").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_32").is_none());
-    assert!(m("ROOT/parent_dir/file_deep_33").is_none());
-}
-
-#[test]
-fn test_dirs_in_root() {
-    let gitignore = get_gitignore();
-    let m = |path: &str, is_dir: bool| {
-        gitignore.matched_path_or_any_parents(Path::new(path), is_dir)
-    };
-
-    // 00
-    assert!(m("ROOT/dir_root_00", true).is_ignore());
-    assert!(m("ROOT/dir_root_00/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_00/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_00/child_dir/file", false).is_ignore());
-
-    // 01
-    assert!(m("ROOT/dir_root_01", true).is_ignore());
-    assert!(m("ROOT/dir_root_01/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_01/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_01/child_dir/file", false).is_ignore());
-
-    // 02
-    assert!(m("ROOT/dir_root_02", true).is_none()); // dir itself doesn't match
-    assert!(m("ROOT/dir_root_02/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_02/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_02/child_dir/file", false).is_ignore());
-
-    // 03
-    assert!(m("ROOT/dir_root_03", true).is_none()); // dir itself doesn't match
-    assert!(m("ROOT/dir_root_03/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_03/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_03/child_dir/file", false).is_ignore());
-
-    // 10
-    assert!(m("ROOT/dir_root_10", true).is_ignore());
-    assert!(m("ROOT/dir_root_10/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_10/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_10/child_dir/file", false).is_ignore());
-
-    // 11
-    assert!(m("ROOT/dir_root_11", true).is_ignore());
-    assert!(m("ROOT/dir_root_11/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_11/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_11/child_dir/file", false).is_ignore());
-
-    // 12
-    assert!(m("ROOT/dir_root_12", true).is_none()); // dir itself doesn't match
-    assert!(m("ROOT/dir_root_12/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_12/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_12/child_dir/file", false).is_ignore());
-
-    // 13
-    assert!(m("ROOT/dir_root_13", true).is_none());
-    assert!(m("ROOT/dir_root_13/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_13/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_13/child_dir/file", false).is_ignore());
-
-    // 20
-    assert!(m("ROOT/dir_root_20", true).is_none());
-    assert!(m("ROOT/dir_root_20/file", false).is_none());
-    assert!(m("ROOT/dir_root_20/child_dir", true).is_none());
-    assert!(m("ROOT/dir_root_20/child_dir/file", false).is_none());
-
-    // 21
-    assert!(m("ROOT/dir_root_21", true).is_none());
-    assert!(m("ROOT/dir_root_21/file", false).is_none());
-    assert!(m("ROOT/dir_root_21/child_dir", true).is_none());
-    assert!(m("ROOT/dir_root_21/child_dir/file", false).is_none());
-
-    // 22
-    assert!(m("ROOT/dir_root_22", true).is_none());
-    assert!(m("ROOT/dir_root_22/file", false).is_none());
-    assert!(m("ROOT/dir_root_22/child_dir", true).is_none());
-    assert!(m("ROOT/dir_root_22/child_dir/file", false).is_none());
-
-    // 23
-    assert!(m("ROOT/dir_root_23", true).is_none());
-    assert!(m("ROOT/dir_root_23/file", false).is_none());
-    assert!(m("ROOT/dir_root_23/child_dir", true).is_none());
-    assert!(m("ROOT/dir_root_23/child_dir/file", false).is_none());
-
-    // 30
-    assert!(m("ROOT/dir_root_30", true).is_ignore());
-    assert!(m("ROOT/dir_root_30/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_30/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_30/child_dir/file", false).is_ignore());
-
-    // 31
-    assert!(m("ROOT/dir_root_31", true).is_ignore());
-    assert!(m("ROOT/dir_root_31/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_31/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_31/child_dir/file", false).is_ignore());
-
-    // 32
-    assert!(m("ROOT/dir_root_32", true).is_none()); // dir itself doesn't match
-    assert!(m("ROOT/dir_root_32/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_32/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_32/child_dir/file", false).is_ignore());
-
-    // 33
-    assert!(m("ROOT/dir_root_33", true).is_none()); // dir itself doesn't match
-    assert!(m("ROOT/dir_root_33/file", false).is_ignore());
-    assert!(m("ROOT/dir_root_33/child_dir", true).is_ignore());
-    assert!(m("ROOT/dir_root_33/child_dir/file", false).is_ignore());
-}
-
-#[test]
-fn test_dirs_in_deep() {
-    let gitignore = get_gitignore();
-    let m = |path: &str, is_dir: bool| {
-        gitignore.matched_path_or_any_parents(Path::new(path), is_dir)
-    };
-
-    // 00
-    assert!(m("ROOT/parent_dir/dir_deep_00", true).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_00/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_00/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_00/child_dir/file", false).is_ignore()
-    );
-
-    // 01
-    assert!(m("ROOT/parent_dir/dir_deep_01", true).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_01/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_01/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_01/child_dir/file", false).is_ignore()
-    );
-
-    // 02
-    assert!(m("ROOT/parent_dir/dir_deep_02", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_02/file", false).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_02/child_dir", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_02/child_dir/file", false).is_none());
-
-    // 03
-    assert!(m("ROOT/parent_dir/dir_deep_03", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_03/file", false).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_03/child_dir", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_03/child_dir/file", false).is_none());
-
-    // 10
-    assert!(m("ROOT/parent_dir/dir_deep_10", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_10/file", false).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_10/child_dir", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_10/child_dir/file", false).is_none());
-
-    // 11
-    assert!(m("ROOT/parent_dir/dir_deep_11", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_11/file", false).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_11/child_dir", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_11/child_dir/file", false).is_none());
-
-    // 12
-    assert!(m("ROOT/parent_dir/dir_deep_12", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_12/file", false).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_12/child_dir", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_12/child_dir/file", false).is_none());
-
-    // 13
-    assert!(m("ROOT/parent_dir/dir_deep_13", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_13/file", false).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_13/child_dir", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_13/child_dir/file", false).is_none());
-
-    // 20
-    assert!(m("ROOT/parent_dir/dir_deep_20", true).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_20/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_20/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_20/child_dir/file", false).is_ignore()
-    );
-
-    // 21
-    assert!(m("ROOT/parent_dir/dir_deep_21", true).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_21/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_21/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_21/child_dir/file", false).is_ignore()
-    );
-
-    // 22
-    // dir itself doesn't match
-    assert!(m("ROOT/parent_dir/dir_deep_22", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_22/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_22/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_22/child_dir/file", false).is_ignore()
-    );
-
-    // 23
-    // dir itself doesn't match
-    assert!(m("ROOT/parent_dir/dir_deep_23", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_23/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_23/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_23/child_dir/file", false).is_ignore()
-    );
-
-    // 30
-    assert!(m("ROOT/parent_dir/dir_deep_30", true).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_30/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_30/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_30/child_dir/file", false).is_ignore()
-    );
-
-    // 31
-    assert!(m("ROOT/parent_dir/dir_deep_31", true).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_31/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_31/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_31/child_dir/file", false).is_ignore()
-    );
-
-    // 32
-    // dir itself doesn't match
-    assert!(m("ROOT/parent_dir/dir_deep_32", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_32/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_32/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_32/child_dir/file", false).is_ignore()
-    );
-
-    // 33
-    // dir itself doesn't match
-    assert!(m("ROOT/parent_dir/dir_deep_33", true).is_none());
-    assert!(m("ROOT/parent_dir/dir_deep_33/file", false).is_ignore());
-    assert!(m("ROOT/parent_dir/dir_deep_33/child_dir", true).is_ignore());
-    assert!(
-        m("ROOT/parent_dir/dir_deep_33/child_dir/file", false).is_ignore()
-    );
-}

crates/ignore/tests/gitignore_skip_bom.gitignore

@@ -1,2 +0,0 @@
-ignore/this/path
-# This file begins with a BOM (U+FEFF)

crates/ignore/tests/gitignore_skip_bom.rs

@@ -1,17 +0,0 @@
-use ignore::gitignore::GitignoreBuilder;
-
-const IGNORE_FILE: &'static str = "tests/gitignore_skip_bom.gitignore";
-
-/// Skip a Byte-Order Mark (BOM) at the beginning of the file, matching Git's
-/// behavior.
-///
-/// Ref: <https://github.com/BurntSushi/ripgrep/issues/2177>
-#[test]
-fn gitignore_skip_bom() {
-    let mut builder = GitignoreBuilder::new("ROOT");
-    let error = builder.add(IGNORE_FILE);
-    assert!(error.is_none(), "failed to open gitignore file");
-    let g = builder.build().unwrap();
-
-    assert!(g.matched("ignore/this/path", false).is_ignore());
-}

crates/node/.cargo/config.toml

@@ -4,11 +4,4 @@ linker = "aarch64-linux-gnu-gcc"
 linker = "aarch64-linux-musl-gcc"
 rustflags = ["-C", "target-feature=-crt-static"]
 [target.armv7-unknown-linux-gnueabihf]
-linker = "arm-linux-gnueabihf-gcc"
-# Statically link Visual Studio redistributables on Windows builds
-[target.x86_64-pc-windows-msvc]
-rustflags = ["-C", "target-feature=+crt-static"]
-[target.aarch64-pc-windows-msvc]
-rustflags = ["-C", "target-feature=+crt-static"]
-[target.'cfg(target_env = "gnu")']
-rustflags = ["-C", "link-args=-Wl,-z,nodelete"]
+linker = "arm-linux-gnueabihf-gcc"

crates/node/.gitignore

@@ -121,7 +121,7 @@ dist
 .AppleDouble
 .LSOverride
 
-# Icon must end with two
+# Icon must end with two 
 Icon
 
 
@@ -194,14 +194,8 @@ Cargo.lock
 !.yarn/sdks
 !.yarn/versions
 
-# Generated
 *.node
-*.wasm
+
+# Generated
 index.d.ts
 index.js
-browser.js
-tailwindcss-oxide.wasi-browser.js
-tailwindcss-oxide.wasi.cjs
-tailwindcss-oxide.wasi.d.cts
-wasi-worker-browser.mjs
-wasi-worker.mjs

crates/node/Cargo.toml

@@ -8,10 +8,11 @@ crate-type = ["cdylib"]
 
 [dependencies]
 # Default enable napi4 feature, see https://nodejs.org/api/n-api.html#node-api-version-matrix
-napi = { version = "3.11.0", default-features = false, features = ["napi4"] }
-napi-derive = "3.6.0"
+napi = { version = "2.13.1", default-features = false, features = ["napi4"] }
+napi-derive = "2.13.0"
 tailwindcss-oxide = { path = "../oxide" }
-rayon = "1.12.0"
+rayon = "1.5.3"
 
 [build-dependencies]
-napi-build = "2.3.2"
+napi-build = "2.0.1"
+

crates/node/npm/android-arm-eabi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-android-arm-eabi",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,6 +22,6 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   }
 }

crates/node/npm/android-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-android-arm64",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,6 +22,6 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   }
 }

crates/node/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-darwin-arm64",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,6 +22,6 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   }
 }

crates/node/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-darwin-x64",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,6 +22,6 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   }
 }

crates/node/npm/freebsd-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-freebsd-x64",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,6 +22,6 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   }
 }

crates/node/npm/linux-arm-gnueabihf/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-linux-arm-gnueabihf",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,6 +22,6 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   }
 }

crates/node/npm/linux-arm64-gnu/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-linux-arm64-gnu",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,7 +22,7 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   },
   "libc": [
     "glibc"

crates/node/npm/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-linux-arm64-musl",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,7 +22,7 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   },
   "libc": [
     "musl"

crates/node/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-linux-x64-gnu",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,7 +22,7 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   },
   "libc": [
     "glibc"

crates/node/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-linux-x64-musl",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,7 +22,7 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   },
   "libc": [
     "musl"

crates/node/npm/wasm32-wasi/.gitignore

@@ -1 +0,0 @@
-node_modules/

crates/node/npm/wasm32-wasi/README.md

@@ -1,3 +0,0 @@
-# `@tailwindcss/oxide-wasm32-wasi`
-
-This is the **wasm32-wasip1-threads** build of `@tailwindcss/oxide`

crates/node/npm/wasm32-wasi/package.json

@@ -1,42 +0,0 @@
-{
-  "name": "@tailwindcss/oxide-wasm32-wasi",
-  "version": "4.3.3",
-  "main": "tailwindcss-oxide.wasi.cjs",
-  "files": [
-    "tailwindcss-oxide.wasm32-wasi.wasm",
-    "tailwindcss-oxide.wasi.cjs",
-    "tailwindcss-oxide.wasi-browser.js",
-    "wasi-worker.mjs",
-    "wasi-worker-browser.mjs"
-  ],
-  "license": "MIT",
-  "engines": {
-    "node": "^20.19.0 || ^22.13.0 || >=23.5.0"
-  },
-  "publishConfig": {
-    "provenance": true,
-    "access": "public"
-  },
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
-    "directory": "crates/node"
-  },
-  "browser": "tailwindcss-oxide.wasi-browser.js",
-  "dependencies": {
-    "@napi-rs/wasm-runtime": "^1.2.2",
-    "@emnapi/core": "^1.11.3",
-    "@emnapi/runtime": "^1.11.3",
-    "@tybys/wasm-util": "^0.10.3",
-    "@emnapi/wasi-threads": "^1.2.3",
-    "tslib": "^2.8.1"
-  },
-  "bundledDependencies": [
-    "@napi-rs/wasm-runtime",
-    "@emnapi/core",
-    "@emnapi/runtime",
-    "@tybys/wasm-util",
-    "@emnapi/wasi-threads",
-    "tslib"
-  ]
-}

crates/node/npm/win32-arm64-msvc/README.md

@@ -1,3 +0,0 @@
-# `@tailwindcss/oxide-win32-arm64-msvc`
-
-This is the **arm64-pc-windows-msvc** binary for `@tailwindcss/oxide`

crates/node/npm/win32-arm64-msvc/package.json

@@ -1,27 +0,0 @@
-{
-  "name": "@tailwindcss/oxide-win32-arm64-msvc",
-  "version": "4.3.3",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
-    "directory": "crates/node/npm/win32-arm64-msvc"
-  },
-  "os": [
-    "win32"
-  ],
-  "cpu": [
-    "arm64"
-  ],
-  "main": "tailwindcss-oxide.win32-arm64-msvc.node",
-  "files": [
-    "tailwindcss-oxide.win32-arm64-msvc.node"
-  ],
-  "publishConfig": {
-    "provenance": true,
-    "access": "public"
-  },
-  "license": "MIT",
-  "engines": {
-    "node": ">= 20"
-  }
-}

crates/node/npm/win32-x64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide-win32-x64-msvc",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -22,6 +22,6 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   }
 }

crates/node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tailwindcss/oxide",
-  "version": "4.3.3",
+  "version": "4.0.0-alpha.15",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/tailwindlabs/tailwindcss.git",
@@ -9,38 +9,27 @@
   "main": "index.js",
   "types": "index.d.ts",
   "napi": {
-    "binaryName": "tailwindcss-oxide",
-    "packageName": "@tailwindcss/oxide",
-    "targets": [
-      "armv7-linux-androideabi",
-      "aarch64-linux-android",
-      "aarch64-apple-darwin",
-      "aarch64-unknown-linux-gnu",
-      "aarch64-unknown-linux-musl",
-      "armv7-unknown-linux-gnueabihf",
-      "x86_64-unknown-linux-musl",
-      "x86_64-unknown-freebsd",
-      "i686-pc-windows-msvc",
-      "aarch64-pc-windows-msvc",
-      "wasm32-wasip1-threads"
-    ],
-    "wasm": {
-      "initialMemory": 16384,
-      "browser": {
-        "fs": true
-      }
+    "name": "tailwindcss-oxide",
+    "triples": {
+      "additional": [
+        "armv7-linux-androideabi",
+        "aarch64-linux-android",
+        "aarch64-apple-darwin",
+        "aarch64-unknown-linux-gnu",
+        "aarch64-unknown-linux-musl",
+        "armv7-unknown-linux-gnueabihf",
+        "x86_64-unknown-linux-musl",
+        "x86_64-unknown-freebsd",
+        "i686-pc-windows-msvc"
+      ]
     }
   },
   "license": "MIT",
   "devDependencies": {
-    "@emnapi/core": "1.11.3",
-    "@emnapi/runtime": "1.11.3",
-    "@napi-rs/cli": "3.7.4",
-    "@napi-rs/wasm-runtime": "^1.2.2",
-    "emnapi": "1.11.3"
+    "@napi-rs/cli": "^2.18.3"
   },
   "engines": {
-    "node": ">= 20"
+    "node": ">= 10"
   },
   "files": [
     "index.js",
@@ -51,14 +40,11 @@
     "access": "public"
   },
   "scripts": {
-    "build": "pnpm run build:platform && pnpm run build:wasm",
-    "build:platform": "napi build --platform --release",
-    "postbuild:platform": "node ./scripts/move-artifacts.mjs",
-    "build:wasm": "napi build --release --target wasm32-wasip1-threads",
-    "postbuild:wasm": "node ./scripts/move-artifacts.mjs",
+    "artifacts": "npx napi artifacts",
+    "build": "npx napi build --platform --release --no-const-enum",
     "dev": "cargo watch --quiet --shell 'npm run build'",
-    "build:debug": "napi build --platform",
-    "version": "napi version"
+    "build:debug": "npx napi build --platform --no-const-enum",
+    "version": "npx napi version"
   },
   "optionalDependencies": {
     "@tailwindcss/oxide-android-arm64": "workspace:*",
@@ -70,8 +56,6 @@
     "@tailwindcss/oxide-linux-arm64-musl": "workspace:*",
     "@tailwindcss/oxide-linux-x64-gnu": "workspace:*",
     "@tailwindcss/oxide-linux-x64-musl": "workspace:*",
-    "@tailwindcss/oxide-wasm32-wasi": "workspace:*",
-    "@tailwindcss/oxide-win32-arm64-msvc": "workspace:*",
     "@tailwindcss/oxide-win32-x64-msvc": "workspace:*"
   }
 }

crates/node/scripts/move-artifacts.mjs

@@ -1,37 +0,0 @@
-import fs from 'node:fs/promises'
-import path from 'node:path'
-import url from 'node:url'
-
-const __dirname = path.dirname(url.fileURLToPath(import.meta.url))
-let root = path.resolve(__dirname, '..')
-const tailwindcssOxideRoot = path.join(root)
-
-// Move napi artifacts into sub packages
-for (let file of await fs.readdir(tailwindcssOxideRoot)) {
-  if (file.startsWith('tailwindcss-oxide.') && file.endsWith('.node')) {
-    let target = file.split('.')[1]
-    await fs.cp(
-      path.join(tailwindcssOxideRoot, file),
-      path.join(tailwindcssOxideRoot, 'npm', target, file),
-    )
-    console.log(`Moved ${file} to npm/${target}`)
-  }
-}
-
-// Move napi wasm artifacts into sub package
-let wasmArtifacts = {
-  'tailwindcss-oxide.debug.wasm': 'tailwindcss-oxide.wasm32-wasi.debug.wasm',
-  'tailwindcss-oxide.wasm': 'tailwindcss-oxide.wasm32-wasi.wasm',
-  'tailwindcss-oxide.wasi-browser.js': 'tailwindcss-oxide.wasi-browser.js',
-  'tailwindcss-oxide.wasi.cjs': 'tailwindcss-oxide.wasi.cjs',
-  'wasi-worker-browser.mjs': 'wasi-worker-browser.mjs',
-  'wasi-worker.mjs': 'wasi-worker.mjs',
-}
-for (let file of await fs.readdir(tailwindcssOxideRoot)) {
-  if (!wasmArtifacts[file]) continue
-  await fs.cp(
-    path.join(tailwindcssOxideRoot, file),
-    path.join(tailwindcssOxideRoot, 'npm', 'wasm32-wasi', wasmArtifacts[file]),
-  )
-  console.log(`Moved ${file} to npm/wasm32-wasi`)
-}

crates/node/src/lib.rs

@@ -1,192 +1,89 @@
-use utf16::IndexConverter;
+use napi::bindgen_prelude::{FromNapiValue, ToNapiValue};
+use std::path::PathBuf;
 
 #[macro_use]
 extern crate napi_derive;
 
-mod utf16;
-
 #[derive(Debug, Clone)]
 #[napi(object)]
 pub struct ChangedContent {
-  /// File path to the changed file
   pub file: Option<String>,
-
-  /// Contents of the changed file
   pub content: Option<String>,
-
-  /// File extension
   pub extension: String,
 }
 
+impl From<ChangedContent> for tailwindcss_oxide::ChangedContent {
+  fn from(changed_content: ChangedContent) -> Self {
+    tailwindcss_oxide::ChangedContent {
+      file: changed_content.file.map(PathBuf::from),
+      content: changed_content.content,
+    }
+  }
+}
+
+#[derive(Debug, Clone)]
+#[napi(object)]
+pub struct ScanResult {
+  pub globs: Vec<GlobEntry>,
+  pub files: Vec<String>,
+  pub candidates: Vec<String>,
+}
+
 #[derive(Debug, Clone)]
 #[napi(object)]
 pub struct GlobEntry {
-  /// Base path of the glob
   pub base: String,
-
-  /// Glob pattern
-  pub pattern: String,
+  pub glob: String,
 }
 
 #[derive(Debug, Clone)]
 #[napi(object)]
-pub struct SourceEntry {
-  /// Base path of the glob
+pub struct ScanOptions {
   pub base: String,
-
-  /// Glob pattern
-  pub pattern: String,
-
-  /// Negated flag
-  pub negated: bool,
-}
-
-impl From<ChangedContent> for tailwindcss_oxide::ChangedContent {
-  fn from(changed_content: ChangedContent) -> Self {
-    if let Some(file) = changed_content.file {
-      return tailwindcss_oxide::ChangedContent::File(file.into(), changed_content.extension);
-    }
-
-    if let Some(contents) = changed_content.content {
-      return tailwindcss_oxide::ChangedContent::Content(contents, changed_content.extension);
-    }
-
-    unreachable!()
-  }
-}
-
-impl From<GlobEntry> for tailwindcss_oxide::GlobEntry {
-  fn from(glob: GlobEntry) -> Self {
-    Self {
-      base: glob.base,
-      pattern: glob.pattern,
-    }
-  }
-}
-
-impl From<tailwindcss_oxide::GlobEntry> for GlobEntry {
-  fn from(glob: tailwindcss_oxide::GlobEntry) -> Self {
-    Self {
-      base: glob.base,
-      pattern: glob.pattern,
-    }
-  }
-}
-
-impl From<SourceEntry> for tailwindcss_oxide::PublicSourceEntry {
-  fn from(source: SourceEntry) -> Self {
-    Self {
-      base: source.base,
-      pattern: source.pattern,
-      negated: source.negated,
-    }
-  }
-}
-
-// ---
-
-#[derive(Debug, Clone)]
-#[napi(object)]
-pub struct ScannerOptions {
-  /// Glob sources
-  pub sources: Option<Vec<SourceEntry>>,
-}
-
-#[derive(Debug, Clone)]
-#[napi]
-pub struct Scanner {
-  scanner: tailwindcss_oxide::Scanner,
-}
-
-#[derive(Debug, Clone)]
-#[napi(object)]
-pub struct CandidateWithPosition {
-  /// The candidate string
-  pub candidate: String,
-
-  /// The position of the candidate inside the content file
-  pub position: i64,
+  pub globs: Option<bool>,
 }
 
 #[napi]
-impl Scanner {
-  #[napi(constructor)]
-  pub fn new(opts: ScannerOptions) -> Self {
-    Self {
-      scanner: tailwindcss_oxide::Scanner::new(match opts.sources {
-        Some(sources) => sources.into_iter().map(Into::into).collect(),
-        None => vec![],
-      }),
-    }
-  }
+pub fn clear_cache() {
+    tailwindcss_oxide::clear_cache();
+}
 
-  #[napi]
-  pub fn scan(&mut self) -> Vec<String> {
-    self.scanner.scan()
-  }
+#[napi]
+pub fn scan_dir(args: ScanOptions) -> ScanResult {
+  let result = tailwindcss_oxide::scan_dir(tailwindcss_oxide::ScanOptions {
+    base: args.base,
+    globs: args.globs.unwrap_or(false),
+  });
 
-  #[napi]
-  pub fn scan_files(&mut self, input: Vec<ChangedContent>) -> Vec<String> {
-    self
-      .scanner
-      .scan_content(input.into_iter().map(Into::into).collect())
-  }
-
-  #[napi]
-  pub fn get_candidates_with_positions(
-    &mut self,
-    input: ChangedContent,
-  ) -> Vec<CandidateWithPosition> {
-    let content = input.content.unwrap_or_else(|| {
-      std::fs::read_to_string(input.file.unwrap()).expect("Failed to read file")
-    });
-
-    let input = ChangedContent {
-      file: None,
-      content: Some(content.clone()),
-      extension: input.extension,
-    };
-
-    let mut utf16_idx = IndexConverter::new(&content[..]);
-
-    self
-      .scanner
-      .get_candidates_with_positions(input.into())
+  ScanResult {
+    files: result.files,
+    candidates: result.candidates,
+    globs: result
+      .globs
       .into_iter()
-      .map(|(candidate, position)| CandidateWithPosition {
-        candidate,
-        position: utf16_idx.get(position),
+      .map(|g| GlobEntry {
+        base: g.base,
+        glob: g.glob,
       })
-      .collect()
-  }
-
-  #[napi(getter)]
-  pub fn files(&mut self) -> Vec<String> {
-    self.scanner.get_files()
-  }
-
-  #[napi(getter)]
-  pub fn scanned_files(&self) -> Vec<String> {
-    self.scanner.get_scanned_files()
-  }
-
-  #[napi(getter)]
-  pub fn globs(&mut self) -> Vec<GlobEntry> {
-    self
-      .scanner
-      .get_globs()
-      .into_iter()
-      .map(Into::into)
-      .collect()
-  }
-
-  #[napi(getter)]
-  pub fn normalized_sources(&mut self) -> Vec<GlobEntry> {
-    self
-      .scanner
-      .get_normalized_sources()
-      .into_iter()
-      .map(Into::into)
-      .collect()
+      .collect(),
   }
 }
+
+#[derive(Debug)]
+#[napi]
+pub enum IO {
+  Sequential = 0b0001,
+  Parallel = 0b0010,
+}
+
+#[derive(Debug)]
+#[napi]
+pub enum Parsing {
+  Sequential = 0b0100,
+  Parallel = 0b1000,
+}
+
+#[napi]
+pub fn scan_files(input: Vec<ChangedContent>, strategy: u8) -> Vec<String> {
+  tailwindcss_oxide::scan_files(input.into_iter().map(Into::into).collect(), strategy)
+}

crates/node/src/utf16.rs

@@ -1,94 +0,0 @@
-/// The `IndexConverter` is used to convert UTF-8 *BYTE* indexes to UTF-16
-/// *character* indexes
-#[derive(Clone)]
-pub struct IndexConverter<'a> {
-  input: &'a str,
-  curr_utf8: usize,
-  curr_utf16: usize,
-}
-
-impl<'a> IndexConverter<'a> {
-  pub fn new(input: &'a str) -> Self {
-    Self {
-      input,
-      curr_utf8: 0,
-      curr_utf16: 0,
-    }
-  }
-
-  pub fn get(&mut self, pos: usize) -> i64 {
-    #[cfg(debug_assertions)]
-    if self.curr_utf8 > self.input.len() {
-      panic!("curr_utf8 points past the end of the input string");
-    }
-
-    if pos < self.curr_utf8 {
-      self.curr_utf8 = 0;
-      self.curr_utf16 = 0;
-    }
-
-    // SAFETY: No matter what `pos` is passed into this function `curr_utf8`
-    // will only ever be incremented up to the length of the input string.
-    //
-    // This eliminates a "potential" panic that cannot actually happen
-    let slice = unsafe { self.input.get_unchecked(self.curr_utf8..) };
-
-    for c in slice.chars() {
-      if self.curr_utf8 >= pos {
-        break;
-      }
-
-      self.curr_utf8 += c.len_utf8();
-      self.curr_utf16 += c.len_utf16();
-    }
-
-    self.curr_utf16 as i64
-  }
-}
-
-#[cfg(test)]
-mod test {
-  use super::*;
-  use std::collections::HashMap;
-
-  #[test]
-  fn test_index_converter() {
-    let mut converter = IndexConverter::new("Hello 🔥🥳 world!");
-
-    let map = HashMap::from([
-      // hello<space>
-      (0, 0),
-      (1, 1),
-      (2, 2),
-      (3, 3),
-      (4, 4),
-      (5, 5),
-      (6, 6),
-      // inside the 🔥
-      (7, 8),
-      (8, 8),
-      (9, 8),
-      (10, 8),
-      // inside the 🥳
-      (11, 10),
-      (12, 10),
-      (13, 10),
-      (14, 10),
-      // <space>world!
-      (15, 11),
-      (16, 12),
-      (17, 13),
-      (18, 14),
-      (19, 15),
-      (20, 16),
-      (21, 17),
-      // Past the end should return the last utf-16 character index
-      (22, 17),
-      (100, 17),
-    ]);
-
-    for (idx_utf8, idx_utf16) in map {
-      assert_eq!(converter.get(idx_utf8), idx_utf16);
-    }
-  }
-}

crates/oxide/Cargo.toml

@@ -4,23 +4,18 @@ version = "0.1.0"
 edition = "2021"
 
 [dependencies]
-bstr = "1.11.3"
-globwalk = "0.9.1"
-log = "0.4.22"
-rayon = "1.10.0"
-fxhash = { package = "rustc-hash", version = "2.1.1" }
-tracing = { version = "0.1.40", features = [] }
-tracing-subscriber = { version = "0.3.18", features = ["env-filter"] }
-walkdir = "2.5.0"
-dunce = "1.0.5"
-bexpand = "1.2.0"
-fast-glob = "0.4.3"
-classification-macros = { path = "../classification-macros" }
-ignore = { path = "../ignore" }
-regex = "1.11.1"
+bstr = "1.0.1"
+globwalk = "0.8.1"
+log = "0.4"
+rayon = "1.5.3"
+fxhash = "0.2.1"
+crossbeam = "0.8.2"
+tracing = { version = "0.1.37", features = [] }
+tracing-subscriber = { version = "0.3.16", features = ["env-filter"] }
+walkdir = "2.3.3"
+ignore = "0.4.20"
+lazy_static = "1.4.0"
 
 [dev-dependencies]
-insta = "1.48.0"
-tempfile = "3.13.0"
-pretty_assertions = "1.4.1"
-unicode-width = "0.2.0"
+tempfile = "3.5.0"
+

crates/oxide/src/cache.rs

@@ -0,0 +1,57 @@
+use std::{path::PathBuf, time::SystemTime};
+use std::fs::{self};
+use fxhash::{FxHashMap, FxHashSet};
+
+/// A cache to manage the list of candidates and the last modified time of files
+/// in the project. This is used to avoid recompiling files that haven't changed.
+#[derive(Default)]
+pub struct Cache {
+    mtimes: FxHashMap<PathBuf, SystemTime>,
+    candidates: FxHashSet<String>,
+}
+
+impl Cache {
+    pub fn clear(&mut self) {
+        self.mtimes.clear();
+        self.candidates.clear();
+    }
+
+    pub fn add_candidates(&mut self, additional_candidates: Vec<String>) {
+        self.candidates.extend(additional_candidates);
+    }
+
+    pub fn get_candidates(&self) -> Vec<String> {
+        let mut result = vec![];
+        result.extend(self.candidates.iter().cloned());
+        result.sort();
+        result
+    }
+
+    pub fn find_modified_files<'a>(&mut self, paths: &'a Vec<PathBuf>) -> Vec<&'a PathBuf> {
+        // Get a list of the files that have been modified since the last time we checked
+        let mut modified: Vec<&PathBuf> = vec![];
+
+        for path in paths {
+            let curr = fs::metadata(path)
+                .and_then(|m| m.modified())
+                .unwrap_or(SystemTime::now());
+
+            let prev = self.mtimes.insert(path.clone(), curr);
+
+            match prev {
+                // Only add the file to the modified list if the mod time has changed
+                Some(prev) if prev != curr => {
+                    modified.push(path);
+                },
+
+                // If the file was already in the cache then we don't need to do anything
+                Some(_) => (),
+
+                // If the file didn't exist before then it's been modified
+                None => modified.push(path),
+            }
+        }
+
+        modified
+    }
+}

crates/oxide/src/cursor.rs

@@ -1,80 +1,82 @@
 use std::{ascii::escape_default, fmt::Display};
 
-#[derive(Debug, Clone, Copy)]
+#[derive(Debug, Clone)]
 pub struct Cursor<'a> {
     // The input we're scanning
     pub input: &'a [u8],
 
     // The location of the cursor in the input
     pub pos: usize,
+
+    /// Is the cursor at the start of the input
+    pub at_start: bool,
+
+    /// Is the cursor at the end of the input
+    pub at_end: bool,
+
+    /// The previously consumed character
+    /// If `at_start` is true, this will be NUL
+    pub prev: u8,
+
+    /// The current character
+    pub curr: u8,
+
+    /// The upcoming character (if any)
+    /// If `at_end` is true, this will be NUL
+    pub next: u8,
 }
 
 impl<'a> Cursor<'a> {
-    #[inline(always)]
     pub fn new(input: &'a [u8]) -> Self {
-        Self { input, pos: 0 }
+        let mut cursor = Self {
+            input,
+            pos: 0,
+            at_start: true,
+            at_end: false,
+            prev: 0x00,
+            curr: 0x00,
+            next: 0x00,
+        };
+        cursor.move_to(0);
+        cursor
     }
 
-    /// The current byte at `pos`, or 0x00 if past the end.
-    #[inline(always)]
-    pub fn curr(&self) -> u8 {
-        if self.pos < self.input.len() {
-            unsafe { *self.input.get_unchecked(self.pos) }
-        } else {
-            0x00
-        }
-    }
-
-    /// The next byte at `pos + 1`, or 0x00 if past the end.
-    #[inline(always)]
-    pub fn next(&self) -> u8 {
-        let next_pos = self.pos + 1;
-        if next_pos < self.input.len() {
-            unsafe { *self.input.get_unchecked(next_pos) }
-        } else {
-            0x00
-        }
-    }
-
-    /// The previous byte at `pos - 1`, or 0x00 if at the start.
-    #[inline(always)]
-    pub fn prev(&self) -> u8 {
-        if self.pos > 0 {
-            unsafe { *self.input.get_unchecked(self.pos - 1) }
-        } else {
-            0x00
-        }
+    pub fn rewind_by(&mut self, amount: usize) {
+        self.move_to(self.pos.saturating_sub(amount));
     }
 
     pub fn advance_by(&mut self, amount: usize) {
         self.move_to(self.pos.saturating_add(amount));
     }
 
-    #[inline(always)]
-    pub fn advance(&mut self) {
-        self.pos += 1;
-    }
-
-    #[inline(always)]
-    pub fn advance_twice(&mut self) {
-        self.pos += 2;
-    }
-
     pub fn move_to(&mut self, pos: usize) {
-        self.pos = pos.min(self.input.len());
+        let len = self.input.len();
+        let pos = pos.clamp(0, len);
+
+        self.pos = pos;
+        self.at_start = pos == 0;
+        self.at_end = pos + 1 >= len;
+
+        self.prev = if pos > 0 { self.input[pos - 1] } else { 0x00 };
+        self.curr = if pos < len { self.input[pos] } else { 0x00 };
+        self.next = if pos + 1 < len {
+            self.input[pos + 1]
+        } else {
+            0x00
+        };
     }
 }
 
-impl Display for Cursor<'_> {
+impl<'a> Display for Cursor<'a> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let len = self.input.len().to_string();
 
         let pos = format!("{: >len_count$}", self.pos, len_count = len.len());
         write!(f, "{}/{} ", pos, len)?;
 
-        if self.pos == 0 {
+        if self.at_start {
             write!(f, "S ")?;
-        } else if self.pos + 1 >= self.input.len() {
+        } else if self.at_end {
             write!(f, "E ")?;
         } else {
             write!(f, "M ")?;
@@ -91,9 +93,9 @@ impl Display for Cursor<'_> {
         write!(
             f,
             "[{} {} {}]",
-            to_str(self.prev()),
-            to_str(self.curr()),
-            to_str(self.next())
+            to_str(self.prev),
+            to_str(self.curr),
+            to_str(self.next)
         )
     }
 }
@@ -101,34 +103,57 @@ impl Display for Cursor<'_> {
 #[cfg(test)]
 mod test {
     use super::*;
-    use pretty_assertions::assert_eq;
 
     #[test]
     fn test_cursor() {
         let mut cursor = Cursor::new(b"hello world");
         assert_eq!(cursor.pos, 0);
-        assert_eq!(cursor.prev(), 0x00);
-        assert_eq!(cursor.curr(), b'h');
-        assert_eq!(cursor.next(), b'e');
+        assert!(cursor.at_start);
+        assert!(!cursor.at_end);
+        assert_eq!(cursor.prev, 0x00);
+        assert_eq!(cursor.curr, b'h');
+        assert_eq!(cursor.next, b'e');
 
         cursor.advance_by(1);
         assert_eq!(cursor.pos, 1);
-        assert_eq!(cursor.prev(), b'h');
-        assert_eq!(cursor.curr(), b'e');
-        assert_eq!(cursor.next(), b'l');
+        assert!(!cursor.at_start);
+        assert!(!cursor.at_end);
+        assert_eq!(cursor.prev, b'h');
+        assert_eq!(cursor.curr, b'e');
+        assert_eq!(cursor.next, b'l');
 
         // Advancing too far should stop at the end
         cursor.advance_by(10);
         assert_eq!(cursor.pos, 11);
-        assert_eq!(cursor.prev(), b'd');
-        assert_eq!(cursor.curr(), 0x00);
-        assert_eq!(cursor.next(), 0x00);
+        assert!(!cursor.at_start);
+        assert!(cursor.at_end);
+        assert_eq!(cursor.prev, b'd');
+        assert_eq!(cursor.curr, 0x00);
+        assert_eq!(cursor.next, 0x00);
 
         // Can't advance past the end
         cursor.advance_by(1);
         assert_eq!(cursor.pos, 11);
-        assert_eq!(cursor.prev(), b'd');
-        assert_eq!(cursor.curr(), 0x00);
-        assert_eq!(cursor.next(), 0x00);
+        assert!(!cursor.at_start);
+        assert!(cursor.at_end);
+        assert_eq!(cursor.prev, b'd');
+        assert_eq!(cursor.curr, 0x00);
+        assert_eq!(cursor.next, 0x00);
+
+        cursor.rewind_by(1);
+        assert_eq!(cursor.pos, 10);
+        assert!(!cursor.at_start);
+        assert!(cursor.at_end);
+        assert_eq!(cursor.prev, b'l');
+        assert_eq!(cursor.curr, b'd');
+        assert_eq!(cursor.next, 0x00);
+
+        cursor.rewind_by(10);
+        assert_eq!(cursor.pos, 0);
+        assert!(cursor.at_start);
+        assert!(!cursor.at_end);
+        assert_eq!(cursor.prev, 0x00);
+        assert_eq!(cursor.curr, b'h');
+        assert_eq!(cursor.next, b'e');
     }
 }

crates/oxide/src/extractor/arbitrary_property_machine.rs

@@ -1,457 +0,0 @@
-use crate::cursor;
-use crate::extractor::bracket_stack::BracketStack;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::string_machine::StringMachine;
-use crate::extractor::CssVariableMachine;
-use classification_macros::ClassifyBytes;
-use std::marker::PhantomData;
-
-#[derive(Debug, Default)]
-pub struct IdleState;
-
-/// Parsing the property, e.g.:
-///
-/// ```text
-/// [color:red]
-///  ^^^^^
-///
-/// [--my-color:red]
-///  ^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ParsingPropertyState;
-
-/// Parsing the value, e.g.:
-///
-/// ```text
-/// [color:red]
-///        ^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ParsingValueState;
-
-/// Extracts arbitrary properties from the input, including the brackets.
-///
-/// E.g.:
-///
-/// ```text
-/// [color:red]
-/// ^^^^^^^^^^^
-///
-/// [--my-color:red]
-/// ^^^^^^^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ArbitraryPropertyMachine<State = IdleState> {
-    /// Start position of the arbitrary value
-    start_pos: usize,
-
-    /// Track brackets to ensure they are balanced
-    bracket_stack: BracketStack,
-
-    css_variable_machine: CssVariableMachine,
-    string_machine: StringMachine,
-
-    _state: PhantomData<State>,
-}
-
-impl<State> ArbitraryPropertyMachine<State> {
-    #[inline(always)]
-    fn transition<NextState>(&self) -> ArbitraryPropertyMachine<NextState> {
-        ArbitraryPropertyMachine {
-            start_pos: self.start_pos,
-            bracket_stack: Default::default(),
-            css_variable_machine: Default::default(),
-            string_machine: Default::default(),
-            _state: PhantomData,
-        }
-    }
-}
-
-impl Machine for ArbitraryPropertyMachine<IdleState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.curr().into() {
-            // Start of an arbitrary property
-            Class::OpenBracket => {
-                self.start_pos = cursor.pos;
-                cursor.advance();
-                self.transition::<ParsingPropertyState>().next(cursor)
-            }
-
-            // Anything else is not a valid start of an arbitrary value
-            _ => MachineState::Idle,
-        }
-    }
-}
-
-impl Machine for ArbitraryPropertyMachine<ParsingPropertyState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        let len = cursor.input.len();
-
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                Class::Dash => match cursor.next().into() {
-                    // Start of a CSS variable
-                    //
-                    // E.g.: `[--my-color:red]`
-                    //         ^^
-                    Class::Dash => return self.parse_property_variable(cursor),
-
-                    // Dashes are allowed in the property name
-                    //
-                    // E.g.: `[background-color:red]`
-                    //                   ^
-                    _ => cursor.advance(),
-                },
-
-                // Alpha characters are allowed in the property name
-                //
-                // E.g.: `[color:red]`
-                //         ^^^^^
-                Class::AlphaLower => cursor.advance(),
-
-                // End of the property name, but there must be at least a single character
-                Class::Colon if cursor.pos > self.start_pos + 1 => {
-                    cursor.advance();
-                    return self.transition::<ParsingValueState>().next(cursor);
-                }
-
-                // Anything else is not a valid property character
-                _ => return self.restart(),
-            }
-        }
-
-        self.restart()
-    }
-}
-
-impl ArbitraryPropertyMachine<ParsingPropertyState> {
-    fn parse_property_variable(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match self.css_variable_machine.next(cursor) {
-            MachineState::Idle => self.restart(),
-            MachineState::Done(_) => match cursor.next().into() {
-                // End of the CSS variable, must be followed by a `:`
-                //
-                // E.g.: `[--my-color:red]`
-                //                   ^
-                Class::Colon => {
-                    cursor.advance_twice();
-                    self.transition::<ParsingValueState>().next(cursor)
-                }
-
-                // Invalid arbitrary property
-                _ => self.restart(),
-            },
-        }
-    }
-}
-
-impl Machine for ArbitraryPropertyMachine<ParsingValueState> {
-    #[inline(always)]
-    fn reset(&mut self) {
-        self.bracket_stack.reset();
-    }
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        let len = cursor.input.len();
-        let start_of_value_pos = cursor.pos;
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                Class::Escape => match cursor.next().into() {
-                    // An escaped whitespace character is not allowed
-                    //
-                    // E.g.: `[color:var(--my-\ color)]`
-                    //                         ^
-                    Class::Whitespace => return self.restart(),
-
-                    // An escaped character, skip the next character, resume after
-                    //
-                    // E.g.: `[color:var(--my-\#color)]`
-                    //                        ^
-                    _ => cursor.advance_twice(),
-                },
-
-                Class::OpenParen | Class::OpenBracket | Class::OpenCurly => {
-                    if !self.bracket_stack.push(cursor.curr()) {
-                        return self.restart();
-                    }
-                    cursor.advance();
-                }
-
-                Class::CloseParen | Class::CloseBracket | Class::CloseCurly
-                    if !self.bracket_stack.is_empty() =>
-                {
-                    if !self.bracket_stack.pop(cursor.curr()) {
-                        return self.restart();
-                    }
-                    cursor.advance();
-                }
-
-                // End of an arbitrary value
-                //
-                // 1. All brackets must be balanced
-                // 2. There must be at least a single character inside the brackets
-                Class::CloseBracket
-                    if self.start_pos + 1 != cursor.pos && self.bracket_stack.is_empty() =>
-                {
-                    return self.done(self.start_pos, cursor)
-                }
-
-                // Start of a string
-                Class::Quote => return self.parse_string(cursor),
-
-                // Another `:` inside of an arbitrary property is only valid inside of a string or
-                // inside of brackets. Everywhere else, it's invalid.
-                //
-                // E.g.: `[color:red:blue]`
-                //                  ^ Not valid
-                // E.g.: `[background:url(https://example.com)]`
-                //                             ^ Valid
-                // E.g.: `[content:'a:b:c:']`
-                //                   ^ ^ ^ Valid
-                Class::Colon if self.bracket_stack.is_empty() => return self.restart(),
-
-                // Any kind of whitespace is not allowed
-                Class::Whitespace => return self.restart(),
-
-                // URLs are not allowed
-                Class::Slash if start_of_value_pos == cursor.pos => return self.restart(),
-
-                // String interpolation-like syntax is not allowed. E.g.: `[${x}]`
-                Class::Dollar if matches!(cursor.next().into(), Class::OpenCurly) => {
-                    return self.restart()
-                }
-
-                // An `!` at the top-level is invalid. We don't allow things to end with
-                // `!important` either as we have dedicated syntax for this.
-                Class::Exclamation if self.bracket_stack.is_empty() => {
-                    return self.restart();
-                }
-
-                // Everything else is valid
-                _ => cursor.advance(),
-            };
-        }
-
-        self.restart()
-    }
-}
-
-impl ArbitraryPropertyMachine<ParsingValueState> {
-    fn parse_string(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match self.string_machine.next(cursor) {
-            MachineState::Idle => self.restart(),
-            MachineState::Done(_) => {
-                cursor.advance();
-                self.next(cursor)
-            }
-        }
-    }
-}
-
-#[derive(Clone, Copy, ClassifyBytes)]
-enum Class {
-    #[bytes(b'(')]
-    OpenParen,
-
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b'{')]
-    OpenCurly,
-
-    #[bytes(b')')]
-    CloseParen,
-
-    #[bytes(b']')]
-    CloseBracket,
-
-    #[bytes(b'}')]
-    CloseCurly,
-
-    #[bytes(b'\\')]
-    Escape,
-
-    #[bytes(b'"', b'\'', b'`')]
-    Quote,
-
-    #[bytes(b'-')]
-    Dash,
-
-    #[bytes(b'$')]
-    Dollar,
-
-    #[bytes_range(b'a'..=b'z')]
-    AlphaLower,
-
-    #[bytes(b':')]
-    Colon,
-
-    #[bytes(b'/')]
-    Slash,
-
-    #[bytes(b'!')]
-    Exclamation,
-
-    #[bytes(b' ', b'\t', b'\n', b'\r', b'\x0C')]
-    Whitespace,
-
-    #[bytes(b'\0')]
-    End,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::{ArbitraryPropertyMachine, IdleState};
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_arbitrary_property_machine_performance() {
-        let input = r#"<button class="[color:red] [background-color:red] [--my-color:red] [background:url('https://example.com')]">"#.repeat(10);
-
-        ArbitraryPropertyMachine::<IdleState>::test_throughput(1_000_000, &input);
-        ArbitraryPropertyMachine::<IdleState>::test_duration_once(&input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_arbitrary_property_machine_extraction() {
-        for (input, expected) in [
-            // Simple arbitrary property
-            ("[color:red]", vec!["[color:red]"]),
-            // Name with dashes
-            ("[background-color:red]", vec!["[background-color:red]"]),
-            // Name with leading `-` is valid
-            ("[-webkit-value:red]", vec!["[-webkit-value:red]"]),
-            // Setting a CSS Variable
-            ("[--my-color:red]", vec!["[--my-color:red]"]),
-            // Value with nested brackets
-            (
-                "[background:url(https://example.com)]",
-                vec!["[background:url(https://example.com)]"],
-            ),
-            // Value containing strings
-            (
-                "[background:url('https://example.com')]",
-                vec!["[background:url('https://example.com')]"],
-            ),
-            // --------------------------------------------------------
-
-            // Invalid CSS Variable
-            ("[--my#color:red]", vec![]),
-            // Spaces are not allowed
-            ("[color: red]", vec![]),
-            // Multiple colons are not allowed
-            ("[color:red:blue]", vec![]),
-            // Only alphanumeric characters are allowed in the property name
-            ("[background_color:red]", vec![]),
-            // A color is required
-            ("[red]", vec![]),
-            // The property cannot be empty
-            ("[:red]", vec![]),
-            // Empty brackets are not allowed
-            ("[]", vec![]),
-            // URLs
-            ("[http://example.com]", vec![]),
-            ("[https://example.com]", vec![]),
-            // Missing colon in more complex example
-            (r#"[CssClass("gap-y-4")]"#, vec![]),
-            // Brackets must be balanced
-            ("[background:url(https://example.com]", vec![]),
-            // Many brackets (>= 8) must be balanced
-            (
-                "[background:url(https://example.com?q={[{[([{[[2]]}])]}]})]",
-                vec!["[background:url(https://example.com?q={[{[([{[[2]]}])]}]})]"],
-            ),
-            // A property containing `!` at the top-level is invalid
-            ("[color:red!]", vec![]),
-            ("[color:red!important]", vec![]),
-        ] {
-            for wrapper in [
-                // No wrapper
-                "{}",
-                // With leading spaces
-                " {}",
-                // With trailing spaces
-                "{} ",
-                // Surrounded by spaces
-                " {} ",
-                // Inside a string
-                "'{}'",
-                // Inside a function call
-                "fn({})",
-                // Inside nested function calls
-                "fn1(fn2({}))",
-                // --------------------------
-                //
-                // HTML
-                // Inside a class (on its own)
-                r#"<div class="{}"></div>"#,
-                // Inside a class (first)
-                r#"<div class="{} foo"></div>"#,
-                // Inside a class (second)
-                r#"<div class="foo {}"></div>"#,
-                // Inside a class (surrounded)
-                r#"<div class="foo {} bar"></div>"#,
-                // --------------------------
-                //
-                // JavaScript
-                // Inside a variable
-                r#"let classes = '{}';"#,
-                // Inside an object (key)
-                r#"let classes = { '{}': true };"#,
-                // Inside an object (no spaces, key)
-                r#"let classes = {'{}':true};"#,
-                // Inside an object (value)
-                r#"let classes = { primary: '{}' };"#,
-                // Inside an object (no spaces, value)
-                r#"let classes = {primary:'{}'};"#,
-            ] {
-                let input = wrapper.replace("{}", input);
-                let actual = ArbitraryPropertyMachine::<IdleState>::test_extract_all(&input);
-
-                if actual != expected {
-                    dbg!(&input);
-                }
-                assert_eq!(actual, expected);
-            }
-        }
-    }
-
-    #[test]
-    fn test_exceptions() {
-        for (input, expected) in [
-            // JS string interpolation
-            // In key
-            ("[${x}:value]", vec![]),
-            // As part of the key
-            ("[background-${property}:value]", vec![]),
-            // In value
-            ("[key:${x}]", vec![]),
-            // As part of the value
-            ("[key:value-${x}]", vec![]),
-            // Allowed in strings
-            ("[--img:url('${x}')]", vec!["[--img:url('${x}')]"]),
-        ] {
-            assert_eq!(
-                ArbitraryPropertyMachine::<IdleState>::test_extract_all(input),
-                expected
-            );
-        }
-    }
-}

crates/oxide/src/extractor/arbitrary_value_machine.rs

@@ -1,213 +0,0 @@
-use crate::cursor;
-use crate::extractor::bracket_stack::BracketStack;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::string_machine::StringMachine;
-use classification_macros::ClassifyBytes;
-
-/// Extracts arbitrary values including the brackets.
-///
-/// E.g.:
-///
-/// ```text
-/// bg-[#0088cc]
-///    ^^^^^^^^^
-///
-/// bg-red-500/[20%]
-///            ^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ArbitraryValueMachine {
-    /// Track brackets to ensure they are balanced
-    bracket_stack: BracketStack,
-
-    string_machine: StringMachine,
-}
-
-impl Machine for ArbitraryValueMachine {
-    #[inline(always)]
-    fn reset(&mut self) {
-        self.bracket_stack.reset();
-    }
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        // An arbitrary value must start with an open bracket
-        if Class::OpenBracket != cursor.curr().into() {
-            return MachineState::Idle;
-        }
-
-        let start_pos = cursor.pos;
-        cursor.advance();
-
-        let len = cursor.input.len();
-
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                Class::Escape => match cursor.next().into() {
-                    // An escaped whitespace character is not allowed
-                    //
-                    // E.g.: `[color:var(--my-\ color)]`
-                    //                         ^
-                    Class::Whitespace => {
-                        cursor.advance_twice();
-                        return self.restart();
-                    }
-
-                    // An escaped character, skip the next character, resume after
-                    //
-                    // E.g.: `[color:var(--my-\#color)]`
-                    //                        ^
-                    _ => cursor.advance_twice(),
-                },
-
-                Class::OpenParen | Class::OpenBracket | Class::OpenCurly => {
-                    if !self.bracket_stack.push(cursor.curr()) {
-                        return self.restart();
-                    }
-                    cursor.advance();
-                }
-
-                Class::CloseParen | Class::CloseBracket | Class::CloseCurly
-                    if !self.bracket_stack.is_empty() =>
-                {
-                    if !self.bracket_stack.pop(cursor.curr()) {
-                        return self.restart();
-                    }
-                    cursor.advance();
-                }
-
-                // End of an arbitrary value
-                //
-                // 1. All brackets must be balanced
-                // 2. There must be at least a single character inside the brackets
-                Class::CloseBracket
-                    if start_pos + 1 != cursor.pos && self.bracket_stack.is_empty() =>
-                {
-                    return self.done(start_pos, cursor);
-                }
-
-                // Start of a string
-                Class::Quote => match self.string_machine.next(cursor) {
-                    MachineState::Idle => return self.restart(),
-                    MachineState::Done(_) => cursor.advance(),
-                },
-
-                // Any kind of whitespace is not allowed
-                Class::Whitespace => return self.restart(),
-
-                // String interpolation-like syntax is not allowed. E.g.: `[${x}]`
-                Class::Dollar if matches!(cursor.next().into(), Class::OpenCurly) => {
-                    return self.restart()
-                }
-
-                // Everything else is valid
-                _ => cursor.advance(),
-            };
-        }
-
-        self.restart()
-    }
-}
-
-#[derive(Clone, Copy, PartialEq, ClassifyBytes)]
-enum Class {
-    #[bytes(b'\\')]
-    Escape,
-
-    #[bytes(b'(')]
-    OpenParen,
-
-    #[bytes(b')')]
-    CloseParen,
-
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b']')]
-    CloseBracket,
-
-    #[bytes(b'{')]
-    OpenCurly,
-
-    #[bytes(b'}')]
-    CloseCurly,
-
-    #[bytes(b'"', b'\'', b'`')]
-    Quote,
-
-    #[bytes(b' ', b'\t', b'\n', b'\r', b'\x0C')]
-    Whitespace,
-
-    #[bytes(b'$')]
-    Dollar,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::ArbitraryValueMachine;
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_arbitrary_value_machine_performance() {
-        let input = r#"<div class="[color:red] [[data-foo]] [url('https://tailwindcss.com')] [url(https://tailwindcss.com)]"></div>"#.repeat(100);
-
-        ArbitraryValueMachine::test_throughput(100_000, &input);
-        ArbitraryValueMachine::test_duration_once(&input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_arbitrary_value_machine_extraction() {
-        for (input, expected) in [
-            // Simple variable
-            ("[#0088cc]", vec!["[#0088cc]"]),
-            // With parentheses
-            (
-                "[url(https://tailwindcss.com)]",
-                vec!["[url(https://tailwindcss.com)]"],
-            ),
-            // With strings, where bracket balancing doesn't matter
-            ("['[({])}']", vec!["['[({])}']"]),
-            // With strings later in the input
-            (
-                "[url('https://tailwindcss.com?[{]}')]",
-                vec!["[url('https://tailwindcss.com?[{]}')]"],
-            ),
-            // With nested brackets
-            ("[[data-foo]]", vec!["[[data-foo]]"]),
-            (
-                "[&>[data-slot=icon]:last-child]",
-                vec!["[&>[data-slot=icon]:last-child]"],
-            ),
-            // With data types
-            ("[length:32rem]", vec!["[length:32rem]"]),
-            // Spaces are not allowed
-            ("[ #0088cc ]", vec![]),
-            // Unbalanced brackets are not allowed
-            ("[foo[bar]", vec![]),
-            // Empty brackets are not allowed
-            ("[]", vec![]),
-        ] {
-            assert_eq!(ArbitraryValueMachine::test_extract_all(input), expected);
-        }
-    }
-
-    #[test]
-    fn test_exceptions() {
-        for (input, expected) in [
-            // JS string interpolation
-            ("[${x}]", vec![]),
-            ("[url(${x})]", vec![]),
-            // Allowed in strings
-            ("[url('${x}')]", vec!["[url('${x}')]"]),
-        ] {
-            assert_eq!(ArbitraryValueMachine::test_extract_all(input), expected);
-        }
-    }
-}

crates/oxide/src/extractor/arbitrary_variable_machine.rs

@@ -1,413 +0,0 @@
-use crate::cursor;
-use crate::extractor::bracket_stack::BracketStack;
-use crate::extractor::css_variable_machine::CssVariableMachine;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::string_machine::StringMachine;
-use classification_macros::ClassifyBytes;
-use std::marker::PhantomData;
-
-#[derive(Debug, Default)]
-pub struct IdleState;
-
-/// Currently parsing the inside of the arbitrary variable
-///
-/// ```text
-/// (--my-opacity)
-///  ^^^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ParsingState;
-
-/// Currently parsing the data type of the arbitrary variable
-///
-/// ```text
-/// (length:--my-opacity)
-///  ^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ParsingDataTypeState;
-
-/// Currently parsing the fallback of the arbitrary variable
-///
-/// ```text
-/// (--my-opacity,50%)
-///              ^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ParsingFallbackState;
-
-/// Extracts arbitrary variables including the parens.
-///
-/// E.g.:
-///
-/// ```text
-/// (--my-value)
-/// ^^^^^^^^^^^^
-///
-/// bg-red-500/(--my-opacity)
-///            ^^^^^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ArbitraryVariableMachine<State = IdleState> {
-    /// Start position of the arbitrary variable
-    start_pos: usize,
-
-    /// Track brackets to ensure they are balanced
-    bracket_stack: BracketStack,
-
-    string_machine: StringMachine,
-    css_variable_machine: CssVariableMachine,
-
-    _state: PhantomData<State>,
-}
-
-impl<State> ArbitraryVariableMachine<State> {
-    #[inline(always)]
-    fn transition<NextState>(&self) -> ArbitraryVariableMachine<NextState> {
-        ArbitraryVariableMachine {
-            start_pos: self.start_pos,
-            bracket_stack: Default::default(),
-            string_machine: Default::default(),
-            css_variable_machine: Default::default(),
-            _state: PhantomData,
-        }
-    }
-}
-
-impl Machine for ArbitraryVariableMachine<IdleState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.curr().into() {
-            // Arbitrary variables start with `(` followed by a CSS variable
-            //
-            // E.g.: `(--my-variable)`
-            //        ^^
-            //
-            Class::OpenParen => match cursor.next().into() {
-                Class::Dash => {
-                    self.start_pos = cursor.pos;
-                    cursor.advance();
-                    self.transition::<ParsingState>().next(cursor)
-                }
-
-                Class::AlphaLower => {
-                    self.start_pos = cursor.pos;
-                    cursor.advance();
-                    self.transition::<ParsingDataTypeState>().next(cursor)
-                }
-
-                _ => MachineState::Idle,
-            },
-
-            // Everything else, is not a valid start of the arbitrary variable. But the next
-            // character might be a valid start for a new utility.
-            _ => MachineState::Idle,
-        }
-    }
-}
-
-impl Machine for ArbitraryVariableMachine<ParsingState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match self.css_variable_machine.next(cursor) {
-            MachineState::Idle => self.restart(),
-            MachineState::Done(_) => match cursor.next().into() {
-                // A CSS variable followed by a `,` means that there is a fallback
-                //
-                // E.g.: `(--my-color,red)`
-                //                   ^
-                Class::Comma => {
-                    cursor.advance_twice(); // Skip the `,`
-                    self.transition::<ParsingFallbackState>().next(cursor)
-                }
-
-                // End of the CSS variable
-                //
-                // E.g.: `(--my-color)`
-                //                  ^
-                _ => {
-                    cursor.advance();
-
-                    match cursor.curr().into() {
-                        // End of an arbitrary variable, must be followed by `)`
-                        Class::CloseParen => self.done(self.start_pos, cursor),
-
-                        // Invalid arbitrary variable, not ending at `)`
-                        _ => self.restart(),
-                    }
-                }
-            },
-        }
-    }
-}
-
-impl Machine for ArbitraryVariableMachine<ParsingDataTypeState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        let len = cursor.input.len();
-
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                // Valid data type characters
-                //
-                // E.g.: `(length:--my-length)`
-                //         ^
-                Class::AlphaLower | Class::Dash => {
-                    cursor.advance();
-                }
-
-                // End of the data type
-                //
-                // E.g.: `(length:--my-length)`
-                //               ^
-                Class::Colon => match cursor.next().into() {
-                    Class::Dash => {
-                        cursor.advance();
-                        return self.transition::<ParsingState>().next(cursor);
-                    }
-
-                    _ => return self.restart(),
-                },
-
-                // Anything else is not a valid character
-                _ => return self.restart(),
-            };
-        }
-        self.restart()
-    }
-}
-
-impl Machine for ArbitraryVariableMachine<ParsingFallbackState> {
-    #[inline(always)]
-    fn reset(&mut self) {
-        self.bracket_stack.reset();
-    }
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        let len = cursor.input.len();
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                Class::Escape => match cursor.next().into() {
-                    // An escaped whitespace character is not allowed
-                    //
-                    // E.g.: `(--my-\ color)`
-                    //              ^^
-                    Class::Whitespace => return self.restart(),
-
-                    // An escaped character, skip the next character, resume after
-                    //
-                    // E.g.: `(--my-\#color)`
-                    //              ^^
-                    _ => cursor.advance_twice(),
-                },
-
-                Class::OpenParen | Class::OpenBracket | Class::OpenCurly => {
-                    if !self.bracket_stack.push(cursor.curr()) {
-                        return self.restart();
-                    }
-                    cursor.advance();
-                }
-
-                Class::CloseParen | Class::CloseBracket | Class::CloseCurly
-                    if !self.bracket_stack.is_empty() =>
-                {
-                    if !self.bracket_stack.pop(cursor.curr()) {
-                        return self.restart();
-                    }
-                    cursor.advance();
-                }
-
-                // End of an arbitrary variable
-                Class::CloseParen => return self.done(self.start_pos, cursor),
-
-                // Start of a string
-                Class::Quote => match self.string_machine.next(cursor) {
-                    MachineState::Idle => return self.restart(),
-                    MachineState::Done(_) => cursor.advance(),
-                },
-
-                // A `:` inside of a fallback value is only valid inside of brackets or inside of a
-                // string. Everywhere else, it's invalid.
-                //
-                // E.g.: `(--foo,bar:baz)`
-                //                  ^ Not valid
-                //
-                // E.g.: `(--url,url(https://example.com))`
-                //                        ^ Valid
-                //
-                // E.g.: `(--my-content:'a:b:c:')`
-                //                        ^ ^ ^ Valid
-                Class::Colon if self.bracket_stack.is_empty() => return self.restart(),
-
-                // Any kind of whitespace is not allowed
-                Class::Whitespace => return self.restart(),
-
-                // String interpolation-like syntax is not allowed. E.g.: `[${x}]`
-                Class::Dollar if matches!(cursor.next().into(), Class::OpenCurly) => {
-                    return self.restart()
-                }
-
-                // Everything else is valid
-                _ => cursor.advance(),
-            };
-        }
-
-        self.restart()
-    }
-}
-
-#[derive(Clone, Copy, PartialEq, ClassifyBytes)]
-enum Class {
-    #[bytes_range(b'a'..=b'z')]
-    AlphaLower,
-
-    #[bytes_range(b'A'..=b'Z')]
-    AlphaUpper,
-
-    #[bytes(b'@')]
-    At,
-
-    #[bytes(b':')]
-    Colon,
-
-    #[bytes(b',')]
-    Comma,
-
-    #[bytes(b'-')]
-    Dash,
-
-    #[bytes(b'.')]
-    Dot,
-
-    #[bytes(b'$')]
-    Dollar,
-
-    #[bytes(b'\\')]
-    Escape,
-
-    #[bytes(b'\0')]
-    End,
-
-    #[bytes_range(b'0'..=b'9')]
-    Number,
-
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b']')]
-    CloseBracket,
-
-    #[bytes(b'(')]
-    OpenParen,
-
-    #[bytes(b')')]
-    CloseParen,
-
-    #[bytes(b'{')]
-    OpenCurly,
-
-    #[bytes(b'}')]
-    CloseCurly,
-
-    #[bytes(b'"', b'\'', b'`')]
-    Quote,
-
-    #[bytes(b'_')]
-    Underscore,
-
-    #[bytes(b' ', b'\t', b'\n', b'\r', b'\x0C')]
-    Whitespace,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::ArbitraryVariableMachine;
-    use crate::extractor::{arbitrary_variable_machine::IdleState, machine::Machine};
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_arbitrary_variable_machine_performance() {
-        let input = r#"<div class="(--foo) (--my-color,red,blue) (--my-img,url('https://example.com?q=(][)'))"></div>"#.repeat(100);
-
-        ArbitraryVariableMachine::<IdleState>::test_throughput(100_000, &input);
-        ArbitraryVariableMachine::<IdleState>::test_duration_once(&input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_arbitrary_variable_extraction() {
-        for (input, expected) in [
-            // Simple utility
-            ("(--foo)", vec!["(--foo)"]),
-            // With dashes
-            ("(--my-color)", vec!["(--my-color)"]),
-            // With a fallback
-            ("(--my-color,red,blue)", vec!["(--my-color,red,blue)"]),
-            // With a fallback containing a string with unbalanced brackets
-            (
-                "(--my-img,url('https://example.com?q=(][)'))",
-                vec!["(--my-img,url('https://example.com?q=(][)'))"],
-            ),
-            // With a type hint
-            ("(length:--my-length)", vec!["(length:--my-length)"]),
-            // --------------------------------------------------------
-
-            // Exceptions:
-            // Arbitrary variable must start with a CSS variable
-            (r"(bar)", vec![]),
-            // Arbitrary variables must be valid CSS variables
-            (r"(--my-\ color)", vec![]),
-            (r"(--my#color)", vec![]),
-            // Fallbacks cannot have spaces
-            (r"(--my-color, red)", vec![]),
-            // Fallbacks cannot have escaped spaces
-            (r"(--my-color,\ red)", vec![]),
-            // Variables must have at least one character after the `--`
-            (r"(--)", vec![]),
-            (r"(--,red)", vec![]),
-            (r"(-)", vec![]),
-            (r"(-my-color)", vec![]),
-        ] {
-            assert_eq!(
-                ArbitraryVariableMachine::<IdleState>::test_extract_all(input),
-                expected
-            );
-        }
-    }
-
-    #[test]
-    fn test_exceptions() {
-        for (input, expected) in [
-            // JS string interpolation
-            // As part of the variable
-            ("(--my-${var})", vec![]),
-            // As the fallback
-            ("(--my-variable,${var})", vec![]),
-            // As the fallback in strings
-            (
-                "(--my-variable,url('${var}'))",
-                vec!["(--my-variable,url('${var}'))"],
-            ),
-        ] {
-            assert_eq!(
-                ArbitraryVariableMachine::<IdleState>::test_extract_all(input),
-                expected
-            );
-        }
-    }
-}

crates/oxide/src/extractor/boundary.rs

@@ -1,128 +0,0 @@
-use classification_macros::ClassifyBytes;
-
-use crate::extractor::Span;
-
-#[inline(always)]
-pub fn is_valid_before_boundary(c: &u8) -> bool {
-    matches!(c.into(), Class::Common | Class::Before)
-}
-
-#[inline(always)]
-pub fn is_valid_after_boundary(c: &u8) -> bool {
-    matches!(c.into(), Class::Common | Class::After)
-}
-
-#[inline(always)]
-pub fn has_valid_boundaries(span: &Span, input: &[u8]) -> bool {
-    let before = {
-        if span.start == 0 {
-            b'\0'
-        } else {
-            input[span.start - 1]
-        }
-    };
-
-    let after = {
-        if span.end >= input.len() - 1 {
-            b'\0'
-        } else {
-            input[span.end + 1]
-        }
-    };
-
-    // Ensure the span has valid boundary characters before and after
-    is_valid_before_boundary(&before) && is_valid_after_boundary(&after)
-}
-
-#[derive(Debug, Clone, Copy, ClassifyBytes)]
-enum Class {
-    // Whitespace, e.g.:
-    //
-    // ```
-    // <div class="flex flex-col items-center"></div>
-    //                 ^        ^
-    // ```
-    #[bytes(b'\t', b'\n', b'\x0C', b'\r', b' ')]
-    // Quotes, e.g.:
-    //
-    // ```
-    // <div class="flex">
-    //            ^    ^
-    // ```
-    #[bytes(b'"', b'\'', b'`')]
-    // End of the input, e.g.:
-    //
-    // ```
-    // flex
-    //     ^
-    // ```
-    #[bytes(b'\0')]
-    Common,
-
-    // Angular like attributes, e.g.:
-    //
-    // ````
-    // [class.foo]
-    //       ^
-    // ```
-    #[bytes(b'.')]
-    // Twig-like templating languages, e.g.:
-    //
-    // ```
-    // <div class="{% if true %}flex{% else %}block{% endif %}">
-    //                         ^
-    // ```
-    #[bytes(b'}')]
-    // XML-like languages where classes are inside the tag, e.g.:
-    // ```
-    // <f:case value="0">from-blue-900 to-cyan-200</f:case>
-    //                  ^
-    // ```
-    #[bytes(b'>')]
-    Before,
-
-    // Clojure and Angular like languages, e.g.:
-    // ```
-    // [:div.p-2]
-    //          ^
-    // [class.foo]
-    //           ^
-    // ```
-    #[bytes(b']')]
-    // Twig like templating languages, e.g.:
-    //
-    // ```
-    // <div class="{% if true %}flex{% else %}block{% endif %}">
-    //                              ^
-    // ```
-    #[bytes(b'{')]
-    // Svelte like attributes, e.g.:
-    //
-    // ```
-    // <div class:flex="bool"></div>
-    //                ^
-    // ```
-    #[bytes(b'=')]
-    // Escaped character when embedding one language in another via strings, e.g.:
-    //
-    // ```
-    // $attributes->merge([
-    //   'x-init' => '$el.classList.add(\'-translate-x-full\'); $el.classList.add(\'transition-transform\')',
-    //                                                     ^                                            ^
-    // ]);
-    // ```
-    //
-    // In this case there is some JavaScript embedded in an string in PHP and some of the quotes
-    // need to be escaped.
-    #[bytes(b'\\')]
-    // XML-like languages where classes are inside the tag, e.g.:
-    // ```
-    // <f:case value="0">from-blue-900 to-cyan-200</f:case>
-    //                                            ^
-    // ```
-    #[bytes(b'<')]
-    After,
-
-    #[fallback]
-    Other,
-}

crates/oxide/src/extractor/bracket_stack.rs

@@ -1,57 +0,0 @@
-const SIZE: usize = 32;
-
-#[repr(C)]
-#[derive(Debug, Default)]
-pub struct BracketStack {
-    /// Bracket stack to ensure properly balanced brackets.
-    bracket_stack: [u8; SIZE],
-    bracket_stack_len: usize,
-}
-
-impl BracketStack {
-    #[inline(always)]
-    pub fn is_empty(&self) -> bool {
-        self.bracket_stack_len == 0
-    }
-
-    #[inline(always)]
-    pub fn push(&mut self, bracket: u8) -> bool {
-        if self.bracket_stack_len >= SIZE {
-            return false;
-        }
-
-        unsafe {
-            *self.bracket_stack.get_unchecked_mut(self.bracket_stack_len) = match bracket {
-                b'(' => b')',
-                b'[' => b']',
-                b'{' => b'}',
-                b'<' => b'>',
-                _ => std::hint::unreachable_unchecked(),
-            };
-        }
-
-        self.bracket_stack_len += 1;
-        true
-    }
-
-    #[inline(always)]
-    pub fn pop(&mut self, bracket: u8) -> bool {
-        if self.bracket_stack_len == 0 {
-            return false;
-        }
-
-        self.bracket_stack_len -= 1;
-        unsafe {
-            if *self.bracket_stack.get_unchecked(self.bracket_stack_len) != bracket {
-                return false;
-            }
-        }
-
-        true
-    }
-
-    #[inline(always)]
-    pub fn reset(&mut self) {
-        self.bracket_stack_len = 0;
-    }
-}

crates/oxide/src/extractor/candidate_machine.rs

@@ -1,361 +0,0 @@
-use crate::cursor;
-use crate::extractor::boundary::{has_valid_boundaries, is_valid_before_boundary};
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::utility_machine::UtilityMachine;
-use crate::extractor::variant_machine::VariantMachine;
-use crate::extractor::Span;
-
-/// Extract full candidates including variants and utilities.
-#[derive(Debug, Default)]
-pub struct CandidateMachine {
-    /// Start position of the candidate
-    start_pos: usize,
-
-    /// End position of the last variant (if any)
-    last_variant_end_pos: Option<usize>,
-
-    utility_machine: UtilityMachine,
-    variant_machine: VariantMachine,
-}
-
-impl Machine for CandidateMachine {
-    #[inline(always)]
-    fn reset(&mut self) {
-        self.start_pos = 0;
-        self.last_variant_end_pos = None;
-    }
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        let len = cursor.input.len();
-
-        while cursor.pos < len {
-            // Skip ahead for known characters that will never be part of a candidate. No need to
-            // run any sub-machines.
-            if cursor.curr().is_ascii_whitespace() {
-                self.reset();
-                cursor.advance();
-                continue;
-            }
-
-            // Candidates don't start with these characters, so we can skip ahead.
-            if matches!(cursor.curr(), b':' | b'"' | b'\'' | b'`') {
-                self.reset();
-                cursor.advance();
-                continue;
-            }
-
-            // Jump ahead if the character is known to be an invalid boundary and we should start
-            // at the next boundary even though "valid" candidates can exist.
-            //
-            // E.g.: `<div class="">`
-            //         ^^^            Valid candidate
-            //        ^               But this character makes it invalid
-            //             ^          Therefore we jump here
-            //
-            // E.g.: `Some Class`
-            //        ^    ^       Invalid, we can jump ahead to the next boundary
-            //
-            if matches!(cursor.curr(), b'<' | b'A'..=b'Z') {
-                if let Some(offset) = cursor.input[cursor.pos..]
-                    .iter()
-                    .position(|&c| is_valid_before_boundary(&c))
-                {
-                    self.reset();
-                    cursor.advance_by(offset + 1);
-                } else {
-                    return self.restart();
-                }
-
-                continue;
-            }
-
-            let mut variant_cursor = cursor.clone();
-            let variant_machine_state = self.variant_machine.next(&mut variant_cursor);
-
-            let mut utility_cursor = cursor.clone();
-            let utility_machine_state = self.utility_machine.next(&mut utility_cursor);
-
-            match (variant_machine_state, utility_machine_state) {
-                // No variant, but the utility machine completed
-                (MachineState::Idle, MachineState::Done(utility_span)) => {
-                    cursor.move_to(utility_cursor.pos + 1);
-
-                    let span = match self.last_variant_end_pos {
-                        Some(end_pos) => {
-                            // Verify that the utility is touching the last variant
-                            if end_pos + 1 != utility_span.start {
-                                return self.restart();
-                            }
-
-                            Span::new(self.start_pos, utility_span.end)
-                        }
-                        None => utility_span,
-                    };
-
-                    // Ensure the span has valid boundary characters before and after
-                    if !has_valid_boundaries(&span, cursor.input) {
-                        return self.restart();
-                    }
-
-                    return self.done_span(span);
-                }
-
-                // Both variant and utility machines are done
-                // E.g.: `hover:flex`
-                //        ^^^^^^      Variant
-                //        ^^^^^       Utility
-                //
-                (MachineState::Done(variant_span), MachineState::Done(utility_span)) => {
-                    cursor.move_to(variant_cursor.pos + 1);
-
-                    if let Some(end_pos) = self.last_variant_end_pos {
-                        // Verify variant is touching the last variant
-                        if end_pos + 1 != variant_span.start {
-                            return self.restart();
-                        }
-                    } else {
-                        // We know that there is no variant before this one.
-                        //
-                        // Edge case: JavaScript keys should be considered utilities if they are
-                        // not preceded by another variant, and followed by any kind of whitespace
-                        // or the end of the line.
-                        //
-                        // E.g.: `{ underline: true }`
-                        //          ^^^^^^^^^^        Variant
-                        //          ^^^^^^^^^         Utility (followed by `: `)
-                        let after = cursor.input.get(utility_span.end + 2).unwrap_or(&b'\0');
-                        if after.is_ascii_whitespace() || *after == b'\0' {
-                            cursor.move_to(utility_cursor.pos + 2);
-                            return self.done_span(utility_span);
-                        }
-
-                        self.start_pos = variant_span.start;
-                    }
-
-                    self.last_variant_end_pos = Some(variant_cursor.pos);
-                }
-
-                // Variant is done, utility is invalid
-                (MachineState::Done(variant_span), MachineState::Idle) => {
-                    cursor.move_to(variant_cursor.pos + 1);
-
-                    if let Some(end_pos) = self.last_variant_end_pos {
-                        if end_pos + 1 > variant_span.start {
-                            self.reset();
-                            return MachineState::Idle;
-                        }
-                    } else {
-                        self.start_pos = variant_span.start;
-                    }
-
-                    self.last_variant_end_pos = Some(variant_cursor.pos);
-                }
-
-                (MachineState::Idle, MachineState::Idle) => {
-                    // Skip main cursor to the next character after both machines. We already know
-                    // there is no candidate here.
-                    if variant_cursor.pos > cursor.pos || utility_cursor.pos > cursor.pos {
-                        cursor.move_to(variant_cursor.pos.max(utility_cursor.pos));
-                    }
-
-                    self.reset();
-                    cursor.advance();
-                }
-            }
-        }
-
-        MachineState::Idle
-    }
-}
-
-impl CandidateMachine {
-    #[inline(always)]
-    fn done_span(&mut self, span: Span) -> MachineState {
-        self.reset();
-        MachineState::Done(span)
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::CandidateMachine;
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_candidate_machine_performance() {
-        let n = 10_000;
-        let input = include_str!("../fixtures/example.html");
-        // let input = &r#"<button type="button" class="absolute -top-1 -left-1.5 flex items-center justify-center p-1.5 text-gray-400 hover:text-gray-500">"#.repeat(100);
-
-        CandidateMachine::test_throughput(n, input);
-        CandidateMachine::test_duration_once(input);
-        CandidateMachine::test_duration_n(n, input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_candidate_extraction() {
-        for (input, expected) in [
-            // Simple utility
-            ("flex", vec!["flex"]),
-            // Simple utility with special character(s)
-            ("@container", vec!["@container"]),
-            // Single character utility
-            ("a", vec!["a"]),
-            // Simple utility with dashes
-            ("items-center", vec!["items-center"]),
-            // Simple utility with numbers
-            ("px-2.5", vec!["px-2.5"]),
-            // Simple variant with simple utility
-            ("hover:flex", vec!["hover:flex"]),
-            // Arbitrary properties
-            ("[color:red]", vec!["[color:red]"]),
-            ("![color:red]", vec!["![color:red]"]),
-            ("[color:red]!", vec!["[color:red]!"]),
-            ("[color:red]/20", vec!["[color:red]/20"]),
-            ("![color:red]/20", vec!["![color:red]/20"]),
-            ("[color:red]/20!", vec!["[color:red]/20!"]),
-            // With multiple variants
-            ("hover:focus:flex", vec!["hover:focus:flex"]),
-            // Exceptions:
-            //
-            // Keys inside of a JS object could be a variant-less candidate. Vue example.
-            ("{ underline: true }", vec!["underline", "true"]),
-            // With complex variants
-            (
-                "[&>[data-slot=icon]:last-child]:right-2.5",
-                vec!["[&>[data-slot=icon]:last-child]:right-2.5"],
-            ),
-            // With multiple (complex) variants
-            (
-                "[&>[data-slot=icon]:last-child]:sm:right-2.5",
-                vec!["[&>[data-slot=icon]:last-child]:sm:right-2.5"],
-            ),
-            (
-                "sm:[&>[data-slot=icon]:last-child]:right-2.5",
-                vec!["sm:[&>[data-slot=icon]:last-child]:right-2.5"],
-            ),
-            // Exceptions regarding boundaries
-            //
-            // `flex!` is valid, but since it's followed by a non-boundary character it's invalid.
-            // `block` is therefore also invalid because it didn't start after a boundary.
-            ("flex!block", vec![]),
-        ] {
-            for (wrapper, additional) in [
-                // No wrapper
-                ("{}", vec![]),
-                // With leading spaces
-                (" {}", vec![]),
-                ("  {}", vec![]),
-                ("   {}", vec![]),
-                // With trailing spaces
-                ("{} ", vec![]),
-                ("{}  ", vec![]),
-                ("{}   ", vec![]),
-                // Surrounded by spaces
-                (" {} ", vec![]),
-                // Inside a string
-                ("'{}'", vec![]),
-                // Inside a function call
-                ("fn('{}')", vec![]),
-                // Inside nested function calls
-                ("fn1(fn2('{}'))", vec![]),
-                // --------------------------
-                //
-                // HTML
-                // Inside a class (on its own)
-                (r#"<div class="{}"></div>"#, vec!["class"]),
-                // Inside a class (first)
-                (r#"<div class="{} foo"></div>"#, vec!["class", "foo"]),
-                // Inside a class (second)
-                (r#"<div class="foo {}"></div>"#, vec!["class", "foo"]),
-                // Inside a class (surrounded)
-                (
-                    r#"<div class="foo {} bar"></div>"#,
-                    vec!["class", "foo", "bar"],
-                ),
-                // --------------------------
-                //
-                // JavaScript
-                // Inside a variable
-                (r#"let classes = '{}';"#, vec!["let", "classes"]),
-                // Inside an object (key)
-                (
-                    r#"let classes = { '{}': true };"#,
-                    vec!["let", "classes", "true"],
-                ),
-                // Inside an object (no spaces, key)
-                (r#"let classes = {'{}':true};"#, vec!["let", "classes"]),
-                // Inside an object (value)
-                (
-                    r#"let classes = { primary: '{}' };"#,
-                    vec!["let", "classes", "primary"],
-                ),
-                // Inside an object (no spaces, value)
-                (r#"let classes = {primary:'{}'};"#, vec!["let", "classes"]),
-            ] {
-                let input = wrapper.replace("{}", input);
-
-                let mut expected = expected.clone();
-                expected.extend(additional);
-                expected.sort();
-
-                let mut actual = CandidateMachine::test_extract_all(&input);
-                actual.sort();
-
-                if actual != expected {
-                    dbg!(&input);
-                }
-
-                assert_eq!(actual, expected);
-            }
-        }
-    }
-
-    #[test]
-    fn do_not_consider_svg_path_commands() {
-        for input in [
-            r#"<path d="M19 21V5a2 2 0 00-2-2H7a2 2 0 00-2 2v16m14 0h2m-2 0h-5m-9 0H3m2 0h5M9 7h1m-1 4h1m4-4h1m-1 4h1m-5 10v-5a1 1 0 011-1h2a1 1 0 011 1v5m-4 0h4"/>"#,
-            r#"<path d="0h2m-2"/>"#,
-        ] {
-            assert_eq!(
-                CandidateMachine::test_extract_all(input),
-                Vec::<&str>::new()
-            );
-        }
-    }
-
-    #[test]
-    fn test_js_interpolation() {
-        for (input, expected) in [
-            // Utilities
-            // Arbitrary value
-            ("bg-[${color}]", vec![]),
-            // Arbitrary property
-            ("[color:${value}]", vec![]),
-            ("[${key}:value]", vec![]),
-            ("[${key}:${value}]", vec![]),
-            // Arbitrary property for CSS variables
-            ("[--color:${value}]", vec![]),
-            ("[--color-${name}:value]", vec![]),
-            // Arbitrary variable
-            ("bg-(--my-${name})", vec![]),
-            ("bg-(--my-variable,${fallback})", vec![]),
-            (
-                "bg-(--my-image,url('https://example.com?q=${value}'))",
-                vec!["bg-(--my-image,url('https://example.com?q=${value}'))"],
-            ),
-            // Variants
-            ("data-[state=${state}]:flex", vec![]),
-            ("support-(--my-${value}):flex", vec![]),
-            ("support-(--my-variable,${fallback}):flex", vec![]),
-            ("[@media(width>=${value})]:flex", vec![]),
-        ] {
-            assert_eq!(CandidateMachine::test_extract_all(input), expected);
-        }
-    }
-}

crates/oxide/src/extractor/css_variable_machine.rs

@@ -1,214 +0,0 @@
-use crate::cursor;
-use crate::extractor::machine::{Machine, MachineState};
-use classification_macros::ClassifyBytes;
-
-/// Extract CSS variables from an input.
-///
-/// E.g.:
-///
-/// ```text
-/// var(--my-variable)
-///     ^^^^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct CssVariableMachine;
-
-impl Machine for CssVariableMachine {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        // CSS Variables must start with `--`
-        if Class::Dash != cursor.curr().into() || Class::Dash != cursor.next().into() {
-            return MachineState::Idle;
-        }
-
-        let start_pos = cursor.pos;
-        let len = cursor.input.len();
-
-        cursor.advance_twice();
-
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                // https://drafts.csswg.org/css-syntax-3/#ident-token-diagram
-                //
-                Class::AllowedCharacter | Class::Dash => {
-                    match cursor.next().into() {
-                        // Valid character followed by a valid character or an escape character
-                        //
-                        // E.g.: `--my-variable`
-                        //                ^^
-                        // E.g.: `--my-\#variable`
-                        //            ^^
-                        Class::AllowedCharacter | Class::Dash | Class::Escape => cursor.advance(),
-
-                        // Valid character followed by anything else means the variable is done
-                        //
-                        // E.g.: `'--my-variable'`
-                        //                      ^
-                        _ => {
-                            // There must be at least 1 character after the `--`
-                            if cursor.pos - start_pos < 2 {
-                                return self.restart();
-                            } else {
-                                return self.done(start_pos, cursor);
-                            }
-                        }
-                    }
-                }
-
-                Class::Escape => match cursor.next().into() {
-                    // An escaped whitespace character is not allowed
-                    //
-                    // In CSS it is allowed, but in the context of a class it's not because then we
-                    // would have spaces in the class.
-                    //
-                    // E.g.: `bg-(--my-\ color)`
-                    //                  ^
-                    Class::Whitespace => return self.restart(),
-
-                    // An escape at the end of the class is not allowed
-                    Class::End => return self.restart(),
-
-                    // An escaped character, skip the next character, resume after
-                    //
-                    // E.g.: `--my-\#variable`
-                    //             ^           We are here
-                    //               ^         Resume here
-                    _ => cursor.advance_twice(),
-                },
-
-                // Character is not valid anymore
-                _ => return self.restart(),
-            }
-        }
-
-        MachineState::Idle
-    }
-}
-
-#[derive(Clone, Copy, PartialEq, ClassifyBytes)]
-enum Class {
-    #[bytes(b'-')]
-    Dash,
-
-    #[bytes(b'_')]
-    #[bytes_range(b'a'..=b'z', b'A'..=b'Z', b'0'..=b'9')]
-    // non-ASCII (such as Emoji): https://drafts.csswg.org/css-syntax-3/#non-ascii-ident-code-point
-    #[bytes_range(0x80..=0xff)]
-    AllowedCharacter,
-
-    #[bytes(b'\\')]
-    Escape,
-
-    #[bytes(b' ', b'\t', b'\n', b'\r', b'\x0C')]
-    Whitespace,
-
-    #[bytes(b'\0')]
-    End,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::CssVariableMachine;
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_css_variable_machine_performance() {
-        let input = r#"This sentence will contain a few variables here and there var(--my-variable) --other-variable-1\/2 var(--more-variables-here)"#.repeat(100);
-
-        CssVariableMachine::test_throughput(100_000, &input);
-        CssVariableMachine::test_duration_once(&input);
-
-        todo!();
-    }
-
-    #[test]
-    fn test_css_variable_machine_extraction() {
-        for (input, expected) in [
-            // Simple variable
-            ("--foo", vec!["--foo"]),
-            ("--my-variable", vec!["--my-variable"]),
-            // Multiple variables
-            (
-                "calc(var(--first) + var(--second))",
-                vec!["--first", "--second"],
-            ),
-            // Variables with... emojis
-            ("--😀", vec!["--😀"]),
-            ("--😀-😁", vec!["--😀-😁"]),
-            // Escaped character in the middle, skips the next character
-            (r#"--spacing-1\/2"#, vec![r#"--spacing-1\/2"#]),
-            // Escaped whitespace is not allowed
-            (r#"--my-\ variable"#, vec![]),
-            // --------------------------
-            //
-            // Exceptions
-            // Not a valid variable
-            ("", vec![]),
-            ("-", vec![]),
-            ("--", vec![]),
-        ] {
-            for wrapper in [
-                // No wrapper
-                "{}",
-                // With leading spaces
-                " {}",
-                // With trailing spaces
-                "{} ",
-                // Surrounded by spaces
-                " {} ",
-                // Inside a string
-                "'{}'",
-                // Inside a function call
-                "fn({})",
-                // Inside nested function calls
-                "fn1(fn2({}))",
-                // --------------------------
-                //
-                // HTML
-                // Inside a class (on its own)
-                r#"<div class="{}"></div>"#,
-                // Inside a class (first)
-                r#"<div class="{} foo"></div>"#,
-                // Inside a class (second)
-                r#"<div class="foo {}"></div>"#,
-                // Inside a class (surrounded)
-                r#"<div class="foo {} bar"></div>"#,
-                // Inside an arbitrary property
-                r#"<div class="[{}:red]"></div>"#,
-                // --------------------------
-                //
-                // JavaScript
-                // Inside a variable
-                r#"let classes = '{}';"#,
-                // Inside an object (key)
-                r#"let classes = { '{}': true };"#,
-                // Inside an object (no spaces, key)
-                r#"let classes = {'{}':true};"#,
-                // Inside an object (value)
-                r#"let classes = { primary: '{}' };"#,
-                // Inside an object (no spaces, value)
-                r#"let classes = {primary:'{}'};"#,
-                // Inside an array
-                r#"let classes = ['{}'];"#,
-            ] {
-                let input = wrapper.replace("{}", input);
-
-                let actual = CssVariableMachine::test_extract_all(&input);
-
-                if actual != expected {
-                    dbg!(&input);
-                }
-
-                assert_eq!(actual, expected);
-            }
-        }
-    }
-}

crates/oxide/src/extractor/machine.rs

@@ -1,161 +0,0 @@
-use crate::cursor;
-
-#[derive(Debug, Clone, Copy)]
-pub struct Span {
-    /// Inclusive start position of the span
-    pub start: usize,
-
-    /// Inclusive end position of the span
-    pub end: usize,
-}
-
-impl Span {
-    pub fn new(start: usize, end: usize) -> Self {
-        Self { start, end }
-    }
-
-    #[inline(always)]
-    pub fn slice<'a>(&self, input: &'a [u8]) -> &'a [u8] {
-        &input[self.start..=self.end]
-    }
-}
-
-#[derive(Debug, Default)]
-pub enum MachineState {
-    /// Machine is not doing anything at the moment
-    #[default]
-    Idle,
-
-    /// Machine is done parsing and has extracted a span
-    Done(Span),
-}
-
-pub trait Machine: Sized + Default {
-    fn reset(&mut self);
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState;
-
-    /// Reset the state machine, and mark the machine as [MachineState::Idle].
-    #[inline(always)]
-    fn restart(&mut self) -> MachineState {
-        self.reset();
-        MachineState::Idle
-    }
-
-    /// Reset the state machine, and mark the machine as [MachineState::Done(…)].
-    #[inline(always)]
-    fn done(&mut self, start: usize, cursor: &cursor::Cursor<'_>) -> MachineState {
-        self.reset();
-        MachineState::Done(Span::new(start, cursor.pos))
-    }
-
-    #[cfg(test)]
-    fn test_throughput(iterations: usize, input: &str) {
-        use crate::throughput::Throughput;
-        use std::hint::black_box;
-
-        let input = input.as_bytes();
-        let len = input.len();
-
-        let throughput = Throughput::compute(iterations, len, || {
-            let mut machine = Self::default();
-            let mut cursor = cursor::Cursor::new(input);
-
-            while cursor.pos < len {
-                _ = black_box(machine.next(&mut cursor));
-
-                cursor.advance();
-            }
-        });
-        eprintln!(
-            "{}: Throughput: {}",
-            std::any::type_name::<Self>(),
-            throughput
-        );
-    }
-
-    #[cfg(test)]
-    fn test_duration_once(input: &str) {
-        use std::hint::black_box;
-
-        let input = input.as_bytes();
-        let len = input.len();
-
-        let duration = {
-            let start = std::time::Instant::now();
-            let mut machine = Self::default();
-            let mut cursor = cursor::Cursor::new(input);
-
-            while cursor.pos < len {
-                _ = black_box(machine.next(&mut cursor));
-
-                cursor.advance();
-            }
-
-            start.elapsed()
-        };
-        eprintln!(
-            "{}:   Duration: {:?}",
-            std::any::type_name::<Self>(),
-            duration
-        );
-    }
-
-    #[cfg(test)]
-    fn test_duration_n(n: usize, input: &str) {
-        use std::hint::black_box;
-
-        let input = input.as_bytes();
-        let len = input.len();
-
-        let duration = {
-            let start = std::time::Instant::now();
-
-            for _ in 0..n {
-                let mut machine = Self::default();
-                let mut cursor = cursor::Cursor::new(input);
-
-                while cursor.pos < len {
-                    _ = black_box(machine.next(&mut cursor));
-
-                    cursor.advance();
-                }
-            }
-
-            start.elapsed()
-        };
-        eprintln!(
-            "{}:   Duration: {:?} ({} iterations, ~{:?} per iteration)",
-            std::any::type_name::<Self>(),
-            duration,
-            n,
-            duration / n as u32
-        );
-    }
-
-    #[cfg(test)]
-    fn test_extract_all(input: &str) -> Vec<&str> {
-        input
-            // Mimicking the behavior of how we parse lines individually
-            .split_terminator("\n")
-            .flat_map(|input| {
-                let mut machine = Self::default();
-                let mut cursor = cursor::Cursor::new(input.as_bytes());
-
-                let mut actual: Vec<&str> = vec![];
-                let len = cursor.input.len();
-
-                while cursor.pos < len {
-                    if let MachineState::Done(span) = machine.next(&mut cursor) {
-                        actual.push(unsafe {
-                            std::str::from_utf8_unchecked(span.slice(cursor.input))
-                        });
-                    }
-
-                    cursor.advance();
-                }
-
-                actual
-            })
-            .collect()
-    }
-}

crates/oxide/src/extractor/modifier_machine.rs

@@ -1,167 +0,0 @@
-use crate::cursor;
-use crate::extractor::arbitrary_value_machine::ArbitraryValueMachine;
-use crate::extractor::arbitrary_variable_machine::ArbitraryVariableMachine;
-use crate::extractor::machine::{Machine, MachineState};
-use classification_macros::ClassifyBytes;
-
-/// Extract modifiers from an input including the `/`.
-///
-/// E.g.:
-///
-/// ```text
-/// bg-red-500/20
-///           ^^^
-///
-/// bg-red-500/[20%]
-///           ^^^^^^
-///
-/// bg-red-500/(--my-opacity)
-///           ^^^^^^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct ModifierMachine {
-    arbitrary_value_machine: ArbitraryValueMachine,
-    arbitrary_variable_machine: ArbitraryVariableMachine,
-}
-
-impl Machine for ModifierMachine {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        // A modifier must start with a `/`, everything else is not a valid start of a modifier
-        if Class::Slash != cursor.curr().into() {
-            return MachineState::Idle;
-        }
-
-        let start_pos = cursor.pos;
-        cursor.advance();
-
-        match cursor.curr().into() {
-            // Start of an arbitrary value:
-            //
-            // ```
-            // bg-red-500/[20%]
-            //            ^^^^^
-            // ```
-            Class::OpenBracket => match self.arbitrary_value_machine.next(cursor) {
-                MachineState::Idle => self.restart(),
-                MachineState::Done(_) => self.done(start_pos, cursor),
-            },
-
-            // Start of an arbitrary variable:
-            //
-            // ```
-            // bg-red-500/(--my-opacity)
-            //            ^^^^^^^^^^^^^^
-            // ```
-            Class::OpenParen => match self.arbitrary_variable_machine.next(cursor) {
-                MachineState::Idle => self.restart(),
-                MachineState::Done(_) => self.done(start_pos, cursor),
-            },
-
-            // Start of a named modifier:
-            //
-            // ```
-            // bg-red-500/20
-            //            ^^
-            // ```
-            Class::ValidStart => {
-                let len = cursor.input.len();
-                while cursor.pos < len {
-                    match cursor.curr().into() {
-                        Class::ValidStart | Class::ValidInside => {
-                            match cursor.next().into() {
-                                // Only valid characters are allowed, if followed by another valid character
-                                Class::ValidStart | Class::ValidInside => cursor.advance(),
-
-                                // Valid character, but at the end of the modifier, this ends the
-                                // modifier
-                                _ => return self.done(start_pos, cursor),
-                            }
-                        }
-
-                        // Anything else is invalid, end of the modifier
-                        _ => return self.restart(),
-                    }
-                }
-
-                MachineState::Idle
-            }
-
-            // Anything else is not a valid start of a modifier
-            _ => MachineState::Idle,
-        }
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, ClassifyBytes)]
-enum Class {
-    #[bytes_range(b'a'..=b'z', b'A'..=b'Z', b'0'..=b'9')]
-    ValidStart,
-
-    #[bytes(b'-', b'_', b'.')]
-    ValidInside,
-
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b'(')]
-    OpenParen,
-
-    #[bytes(b'/')]
-    Slash,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::ModifierMachine;
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_modifier_machine_performance() {
-        let input = r#"<button class="group-hover/name:flex bg-red-500/20 text-black/[20%] border-white/(--my-opacity)">"#;
-
-        ModifierMachine::test_throughput(1_000_000, input);
-        ModifierMachine::test_duration_once(input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_modifier_extraction() {
-        for (input, expected) in [
-            // Simple modifier
-            ("foo/bar", vec!["/bar"]),
-            ("foo/bar-baz", vec!["/bar-baz"]),
-            // Simple modifier with numbers
-            ("foo/20", vec!["/20"]),
-            // Simple modifier with numbers
-            ("foo/20", vec!["/20"]),
-            // Arbitrary value
-            ("foo/[20]", vec!["/[20]"]),
-            // Arbitrary value with CSS variable shorthand
-            ("foo/(--x)", vec!["/(--x)"]),
-            ("foo/(--foo-bar)", vec!["/(--foo-bar)"]),
-            // --------------------------------------------------------
-
-            // Empty arbitrary value is not allowed
-            ("foo/[]", vec![]),
-            // Empty arbitrary value shorthand is not allowed
-            ("foo/()", vec![]),
-            // A CSS variable must start with `--` and must have at least a single character
-            ("foo/(-)", vec![]),
-            ("foo/(--)", vec![]),
-            // Arbitrary value shorthand should be a valid CSS variable
-            ("foo/(--my#color)", vec![]),
-        ] {
-            assert_eq!(ModifierMachine::test_extract_all(input), expected);
-        }
-    }
-}

crates/oxide/src/extractor/named_utility_machine.rs

@@ -1,535 +0,0 @@
-use crate::cursor;
-use crate::extractor::arbitrary_value_machine::ArbitraryValueMachine;
-use crate::extractor::arbitrary_variable_machine::ArbitraryVariableMachine;
-use crate::extractor::boundary::is_valid_after_boundary;
-use crate::extractor::machine::{Machine, MachineState};
-use classification_macros::ClassifyBytes;
-use std::marker::PhantomData;
-
-#[derive(Debug, Default)]
-pub struct IdleState;
-
-#[derive(Debug, Default)]
-pub struct ParsingState;
-
-/// Extracts named utilities from an input.
-///
-/// E.g.:
-///
-/// ```text
-/// flex
-/// ^^^^
-///
-/// bg-red-500
-/// ^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct NamedUtilityMachine<State = IdleState> {
-    /// Start position of the utility
-    start_pos: usize,
-
-    arbitrary_variable_machine: ArbitraryVariableMachine,
-    arbitrary_value_machine: ArbitraryValueMachine,
-
-    _state: PhantomData<State>,
-}
-
-impl<State> NamedUtilityMachine<State> {
-    #[inline(always)]
-    fn transition<NextState>(&self) -> NamedUtilityMachine<NextState> {
-        NamedUtilityMachine {
-            start_pos: self.start_pos,
-            arbitrary_variable_machine: Default::default(),
-            arbitrary_value_machine: Default::default(),
-            _state: PhantomData,
-        }
-    }
-}
-
-impl Machine for NamedUtilityMachine<IdleState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.curr().into() {
-            Class::AlphaLower => match cursor.next().into() {
-                // Valid single character utility in between quotes
-                //
-                // E.g.: `<div class="a"></div>`
-                //                    ^
-                // E.g.: `<div class="a "></div>`
-                //                    ^
-                // E.g.: `<div class=" a"></div>`
-                //                     ^
-                Class::Whitespace | Class::Quote | Class::End => self.done(cursor.pos, cursor),
-
-                // Valid start characters
-                //
-                // E.g.: `flex`
-                //        ^
-                _ => {
-                    self.start_pos = cursor.pos;
-                    cursor.advance();
-                    self.transition::<ParsingState>().next(cursor)
-                }
-            },
-
-            // Valid start characters
-            //
-            // E.g.: `@container`
-            //        ^
-            Class::At => {
-                self.start_pos = cursor.pos;
-                cursor.advance();
-                self.transition::<ParsingState>().next(cursor)
-            }
-
-            // Valid start of a negative utility, if followed by another set of valid
-            // characters. `@` as a second character is invalid.
-            //
-            // E.g.: `-mx-2.5`
-            //        ^^
-            Class::Dash => match cursor.next().into() {
-                Class::AlphaLower => {
-                    self.start_pos = cursor.pos;
-                    cursor.advance();
-                    self.transition::<ParsingState>().next(cursor)
-                }
-
-                // A dash should not be followed by anything else
-                _ => MachineState::Idle,
-            },
-
-            // Everything else, is not a valid start of the utility.
-            _ => MachineState::Idle,
-        }
-    }
-}
-
-impl Machine for NamedUtilityMachine<ParsingState> {
-    #[inline(always)]
-    fn reset(&mut self) {
-        self.start_pos = 0;
-    }
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        let len = cursor.input.len();
-
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                // Followed by a boundary character, we are at the end of the utility.
-                //
-                // E.g.: `'flex'`
-                //             ^
-                // E.g.: `<div class="flex items-center">`
-                //                        ^
-                // E.g.: `[flex]` (Angular syntax)
-                //             ^
-                // E.g.: `[class.flex.items-center]` (Angular syntax)
-                //                   ^
-                // E.g.: `:div="{ flex: true }"` (JavaScript object syntax)
-                //                    ^
-                Class::AlphaLower | Class::AlphaUpper => {
-                    if is_valid_after_boundary(&cursor.next()) || {
-                        // Or any of these characters
-                        //
-                        // - `:`, because of JS object keys
-                        // - `/`, because of modifiers
-                        // - `!`, because of important
-                        matches!(
-                            cursor.next().into(),
-                            Class::Colon | Class::Slash | Class::Exclamation
-                        )
-                    } {
-                        return self.done(self.start_pos, cursor);
-                    }
-
-                    // Still valid characters
-                    cursor.advance()
-                }
-
-                Class::Dash => match cursor.next().into() {
-                    // Start of an arbitrary value
-                    //
-                    // E.g.: `bg-[#0088cc]`
-                    //          ^^
-                    Class::OpenBracket => {
-                        cursor.advance();
-                        return match self.arbitrary_value_machine.next(cursor) {
-                            MachineState::Idle => self.restart(),
-                            MachineState::Done(_) => self.done(self.start_pos, cursor),
-                        };
-                    }
-
-                    // Start of an arbitrary variable
-                    //
-                    // E.g.: `bg-(--my-color)`
-                    //          ^^
-                    Class::OpenParen => {
-                        cursor.advance();
-                        return match self.arbitrary_variable_machine.next(cursor) {
-                            MachineState::Idle => self.restart(),
-                            MachineState::Done(_) => self.done(self.start_pos, cursor),
-                        };
-                    }
-
-                    // A dash is a valid character if it is followed by another valid
-                    // character.
-                    //
-                    // E.g.: `flex-`
-                    //            ^    Invalid
-                    // E.g.: `flex-!`
-                    //            ^    Invalid
-                    // E.g.: `flex-/`
-                    //            ^    Invalid
-                    // E.g.: `flex-2`
-                    //            ^    Valid
-                    // E.g.: `foo--bar`
-                    //            ^    Valid
-                    Class::AlphaLower | Class::AlphaUpper | Class::Number | Class::Dash => {
-                        cursor.advance();
-                    }
-
-                    // Everything else is invalid
-                    _ => return self.restart(),
-                },
-
-                Class::Underscore => match cursor.next().into() {
-                    // Valid characters _if_ followed by another valid character. These characters are
-                    // only valid inside of the utility but not at the end of the utility.
-                    //
-                    // E.g.: `custom_`
-                    //              ^    Invalid
-                    // E.g.: `custom_!`
-                    //              ^    Invalid
-                    // E.g.: `custom_/`
-                    //              ^    Invalid
-                    // E.g.: `custom_2`
-                    //              ^    Valid
-                    //
-                    Class::AlphaLower | Class::AlphaUpper | Class::Number | Class::Underscore => {
-                        cursor.advance();
-                    }
-
-                    // Followed by a boundary character, we are at the end of the utility.
-                    //
-                    // E.g.: `'flex'`
-                    //             ^
-                    // E.g.: `<div class="flex items-center">`
-                    //                        ^
-                    // E.g.: `[flex]` (Angular syntax)
-                    //             ^
-                    // E.g.: `[class.flex.items-center]` (Angular syntax)
-                    //                   ^
-                    // E.g.: `:div="{ flex: true }"` (JavaScript object syntax)
-                    //                    ^
-                    _ if is_valid_after_boundary(&cursor.next()) || {
-                        // Or any of these characters
-                        //
-                        // - `:`, because of JS object keys
-                        // - `/`, because of modifiers
-                        // - `!`, because of important
-                        matches!(
-                            cursor.next().into(),
-                            Class::Colon | Class::Slash | Class::Exclamation
-                        )
-                    } =>
-                    {
-                        return self.done(self.start_pos, cursor)
-                    }
-
-                    // Everything else is invalid
-                    _ => return self.restart(),
-                },
-
-                // A dot must be surrounded by numbers
-                //
-                // E.g.: `px-2.5`
-                //           ^^^
-                Class::Dot => {
-                    if !matches!(cursor.prev().into(), Class::Number) {
-                        return self.restart();
-                    }
-
-                    if !matches!(cursor.next().into(), Class::Number) {
-                        return self.restart();
-                    }
-
-                    cursor.advance();
-                }
-
-                // A number must be preceded by a `-`, `.` or another alphanumeric
-                // character, and can be followed by a `.` or an alphanumeric character or
-                // dash or underscore.
-                //
-                // E.g.: `text-2xs`
-                //            ^^
-                //       `p-2.5`
-                //           ^^
-                //       `bg-red-500`
-                //                ^^
-                // It can also be followed by a %, but that will be considered the end of
-                // the candidate.
-                //
-                // E.g.: `from-15%`
-                //               ^
-                //
-                Class::Number => {
-                    if !matches!(
-                        cursor.prev().into(),
-                        Class::Dash
-                            | Class::Underscore
-                            | Class::Dot
-                            | Class::Number
-                            | Class::AlphaLower
-                            | Class::AlphaUpper
-                    ) {
-                        return self.restart();
-                    }
-
-                    if !matches!(
-                        cursor.next().into(),
-                        Class::Dot
-                            | Class::Number
-                            | Class::AlphaLower
-                            | Class::AlphaUpper
-                            | Class::Percent
-                            | Class::Underscore
-                            | Class::Dash
-                    ) {
-                        return self.done(self.start_pos, cursor);
-                    }
-
-                    cursor.advance();
-                }
-
-                // A percent sign must be preceded by a number.
-                //
-                // E.g.:
-                //
-                // ```
-                // from-15%
-                //       ^^
-                // ```
-                Class::Percent => {
-                    if !matches!(cursor.prev().into(), Class::Number) {
-                        return self.restart();
-                    }
-
-                    return self.done(self.start_pos, cursor);
-                }
-
-                // Everything else is invalid
-                _ => return self.restart(),
-            };
-        }
-
-        self.restart()
-    }
-}
-
-#[derive(Clone, Copy, ClassifyBytes)]
-enum Class {
-    #[bytes_range(b'a'..=b'z')]
-    AlphaLower,
-
-    #[bytes_range(b'A'..=b'Z')]
-    AlphaUpper,
-
-    #[bytes(b'@')]
-    At,
-
-    #[bytes(b':')]
-    Colon,
-
-    #[bytes(b'-')]
-    Dash,
-
-    #[bytes(b'.')]
-    Dot,
-
-    #[bytes(b'\0')]
-    End,
-
-    #[bytes(b'!')]
-    Exclamation,
-
-    #[bytes_range(b'0'..=b'9')]
-    Number,
-
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b']')]
-    CloseBracket,
-
-    #[bytes(b'(')]
-    OpenParen,
-
-    #[bytes(b'%')]
-    Percent,
-
-    #[bytes(b'"', b'\'', b'`')]
-    Quote,
-
-    #[bytes(b'/')]
-    Slash,
-
-    #[bytes(b'_')]
-    Underscore,
-
-    #[bytes(b' ', b'\t', b'\n', b'\r', b'\x0C')]
-    Whitespace,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::{IdleState, NamedUtilityMachine};
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_named_utility_machine_performance() {
-        let input = r#"<button class="flex items-center px-2.5 -inset-x-2 bg-[#0088cc] text-(--my-color)">"#;
-
-        NamedUtilityMachine::<IdleState>::test_throughput(1_000_000, input);
-        NamedUtilityMachine::<IdleState>::test_duration_once(input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_named_utility_extraction() {
-        for (input, expected) in [
-            // Simple utility
-            ("flex", vec!["flex"]),
-            // Simple utility with special character(s)
-            ("@container", vec!["@container"]),
-            // Simple single-character utility
-            ("a", vec!["a"]),
-            // With dashes
-            ("items-center", vec!["items-center"]),
-            // With double dashes
-            ("items--center", vec!["items--center"]),
-            // With numbers
-            ("px-5", vec!["px-5"]),
-            ("px-2.5", vec!["px-2.5"]),
-            // Underscores followed by numbers
-            ("header_1", vec!["header_1"]),
-            ("header_1_2", vec!["header_1_2"]),
-            // With number followed by dash or underscore
-            ("text-title1-strong", vec!["text-title1-strong"]),
-            ("text-title1_strong", vec!["text-title1_strong"]),
-            // With capital letter followed by number
-            ("text-titleV1-strong", vec!["text-titleV1-strong"]),
-            // With trailing % sign
-            ("from-15%", vec!["from-15%"]),
-            // Arbitrary value with bracket notation
-            ("bg-[#0088cc]", vec!["bg-[#0088cc]"]),
-            // Arbitrary variable
-            ("bg-(--my-color)", vec!["bg-(--my-color)"]),
-            // Arbitrary variable with fallback
-            ("bg-(--my-color,red,blue)", vec!["bg-(--my-color,red,blue)"]),
-            // --------------------------------------------------------
-
-            // Exceptions:
-            // Arbitrary variable must be valid
-            (r"bg-(--my-color\)", vec![]),
-            (r"bg-(--my#color)", vec![]),
-            // Single letter utility with uppercase letter is invalid
-            ("A", vec![]),
-            // A dot must be in-between numbers
-            ("opacity-0.5", vec!["opacity-0.5"]),
-            ("opacity-.5", vec![]),
-            ("opacity-5.", vec![]),
-            // A number must be preceded by a `-`, `.` or another number
-            ("text-2xs", vec!["text-2xs"]),
-            // Random invalid utilities
-            ("-$", vec![]),
-            ("-_", vec![]),
-            ("-foo-", vec![]),
-            ("foo-=", vec![]),
-            ("foo-#", vec![]),
-            ("foo-!", vec![]),
-            ("foo-/20", vec![]),
-            ("-", vec![]),
-            ("--", vec![]),
-            ("---", vec![]),
-        ] {
-            for (wrapper, additional) in [
-                // No wrapper
-                ("{}", vec![]),
-                // With leading spaces
-                (" {}", vec![]),
-                // With trailing spaces
-                ("{} ", vec![]),
-                // Surrounded by spaces
-                (" {} ", vec![]),
-                // Inside a string
-                ("'{}'", vec![]),
-                // Inside a function call
-                ("fn('{}')", vec![]),
-                // Inside nested function calls
-                ("fn1(fn2('{}'))", vec!["fn1", "fn2"]),
-                // --------------------------
-                //
-                // HTML
-                // Inside a class (on its own)
-                (r#"<div class="{}"></div>"#, vec!["div", "class"]),
-                // Inside a class (first)
-                (r#"<div class="{} foo"></div>"#, vec!["div", "class", "foo"]),
-                // Inside a class (second)
-                (r#"<div class="foo {}"></div>"#, vec!["div", "class", "foo"]),
-                // Inside a class (surrounded)
-                (
-                    r#"<div class="foo {} bar"></div>"#,
-                    vec!["div", "class", "foo", "bar"],
-                ),
-                // --------------------------
-                //
-                // JavaScript
-                // Inside a variable
-                (r#"let classes = '{}';"#, vec!["let", "classes"]),
-                // Inside an object (key)
-                (
-                    r#"let classes = { '{}': true };"#,
-                    vec!["let", "classes", "true"],
-                ),
-                // Inside an object (no spaces, key)
-                (r#"let classes = {'{}':true};"#, vec!["let", "classes"]),
-                // Inside an object (value)
-                (
-                    r#"let classes = { primary: '{}' };"#,
-                    vec!["let", "classes", "primary"],
-                ),
-                // Inside an object (no spaces, value)
-                (
-                    r#"let classes = {primary:'{}'};"#,
-                    vec!["let", "classes", "primary"],
-                ),
-                // Inside an array
-                (r#"let classes = ['{}'];"#, vec!["let", "classes"]),
-            ] {
-                let input = wrapper.replace("{}", input);
-
-                let mut expected = expected.clone();
-                expected.extend(additional);
-                expected.sort();
-
-                let mut actual = NamedUtilityMachine::<IdleState>::test_extract_all(&input);
-                actual.sort();
-
-                if actual != expected {
-                    dbg!(&input);
-                }
-                assert_eq!(actual, expected);
-            }
-        }
-    }
-}

crates/oxide/src/extractor/named_variant_machine.rs

@@ -1,422 +0,0 @@
-use crate::cursor;
-use crate::extractor::arbitrary_value_machine::ArbitraryValueMachine;
-use crate::extractor::arbitrary_variable_machine::ArbitraryVariableMachine;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::modifier_machine::ModifierMachine;
-use classification_macros::ClassifyBytes;
-use std::marker::PhantomData;
-
-#[derive(Debug, Default)]
-pub struct IdleState;
-
-/// Parsing a variant
-#[derive(Debug, Default)]
-pub struct ParsingState;
-
-/// Parsing a modifier
-///
-/// E.g.:
-///
-/// ```text
-/// group-hover/name:
-///            ^^^^^
-/// ```
-///
-#[derive(Debug, Default)]
-pub struct ParsingModifierState;
-
-/// Parsing the end of a variant
-///
-/// E.g.:
-///
-/// ```text
-/// hover:
-///      ^
-/// ```
-#[derive(Debug, Default)]
-pub struct ParsingEndState;
-
-/// Extract named variants from an input including the `:`.
-///
-/// E.g.:
-///
-/// ```text
-/// hover:flex
-/// ^^^^^^
-///
-/// data-[state=pending]:flex
-/// ^^^^^^^^^^^^^^^^^^^^^
-///
-/// supports-(--my-variable):flex
-/// ^^^^^^^^^^^^^^^^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct NamedVariantMachine<State = IdleState> {
-    /// Start position of the variant
-    start_pos: usize,
-
-    arbitrary_variable_machine: ArbitraryVariableMachine,
-    arbitrary_value_machine: ArbitraryValueMachine,
-    modifier_machine: ModifierMachine,
-
-    _state: PhantomData<State>,
-}
-
-impl<State> NamedVariantMachine<State> {
-    #[inline(always)]
-    fn transition<NextState>(&self) -> NamedVariantMachine<NextState> {
-        NamedVariantMachine {
-            start_pos: self.start_pos,
-            arbitrary_variable_machine: Default::default(),
-            arbitrary_value_machine: Default::default(),
-            modifier_machine: Default::default(),
-            _state: PhantomData,
-        }
-    }
-}
-
-impl Machine for NamedVariantMachine<IdleState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.curr().into() {
-            Class::AlphaLower | Class::Star => match cursor.next().into() {
-                // Valid single character variant, must be followed by a `:`
-                //
-                // E.g.: `<div class="x:flex"></div>`
-                //                    ^^
-                // E.g.: `*:`
-                //        ^^
-                Class::Colon => {
-                    cursor.advance();
-                    self.transition::<ParsingEndState>().next(cursor)
-                }
-
-                // Valid start characters
-                //
-                // E.g.: `hover:`
-                //        ^
-                // E.g.: `**:`
-                //        ^
-                _ => {
-                    self.start_pos = cursor.pos;
-                    cursor.advance();
-                    self.transition::<ParsingState>().next(cursor)
-                }
-            },
-
-            // Valid start characters
-            //
-            // E.g.: `2xl:`
-            //        ^
-            // E.g.: `@md:`
-            //        ^
-            Class::Number | Class::At => {
-                self.start_pos = cursor.pos;
-                cursor.advance();
-                self.transition::<ParsingState>().next(cursor)
-            }
-
-            // Everything else, is not a valid start of the variant.
-            _ => MachineState::Idle,
-        }
-    }
-}
-
-impl Machine for NamedVariantMachine<ParsingState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        let len = cursor.input.len();
-
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                Class::Dash => match cursor.next().into() {
-                    // Start of an arbitrary value
-                    //
-                    // E.g.: `data-[state=pending]:`.
-                    //            ^^
-                    Class::OpenBracket => {
-                        cursor.advance();
-                        return match self.arbitrary_value_machine.next(cursor) {
-                            MachineState::Idle => self.restart(),
-                            MachineState::Done(_) => self.parse_arbitrary_end(cursor),
-                        };
-                    }
-
-                    // Start of an arbitrary variable
-                    //
-                    // E.g.: `supports-(--my-color):`.
-                    //                ^^
-                    Class::OpenParen => {
-                        cursor.advance();
-                        return match self.arbitrary_variable_machine.next(cursor) {
-                            MachineState::Idle => self.restart(),
-                            MachineState::Done(_) => self.parse_arbitrary_end(cursor),
-                        };
-                    }
-
-                    // Valid characters _if_ followed by another valid character. These characters are
-                    // only valid inside of the variant but not at the end of the variant.
-                    //
-                    // E.g.: `hover-`
-                    //             ^   Invalid
-                    // E.g.: `hover-!`
-                    //             ^   Invalid
-                    // E.g.: `hover-/`
-                    //             ^   Invalid
-                    // E.g.: `flex-1`
-                    //            ^    Valid
-                    Class::Dash
-                    | Class::Underscore
-                    | Class::AlphaLower
-                    | Class::AlphaUpper
-                    | Class::Number => cursor.advance(),
-
-                    // Everything else is invalid
-                    _ => return self.restart(),
-                },
-
-                // Start of an arbitrary value
-                //
-                // E.g.: `@[state=pending]:`.
-                //         ^
-                Class::OpenBracket => {
-                    return match self.arbitrary_value_machine.next(cursor) {
-                        MachineState::Idle => self.restart(),
-                        MachineState::Done(_) => self.parse_arbitrary_end(cursor),
-                    };
-                }
-
-                Class::Underscore => match cursor.next().into() {
-                    // Valid characters _if_ followed by another valid character. These characters are
-                    // only valid inside of the variant but not at the end of the variant.
-                    //
-                    // E.g.: `hover_`
-                    //             ^     Invalid
-                    // E.g.: `hover_!`
-                    //             ^     Invalid
-                    // E.g.: `hover_/`
-                    //             ^     Invalid
-                    // E.g.: `custom_1`
-                    //              ^    Valid
-                    Class::Dash
-                    | Class::Underscore
-                    | Class::AlphaLower
-                    | Class::AlphaUpper
-                    | Class::Number => cursor.advance(),
-
-                    // Everything else is invalid
-                    _ => return self.restart(),
-                },
-
-                // Still valid characters
-                Class::AlphaLower | Class::AlphaUpper | Class::Number | Class::Star => {
-                    cursor.advance()
-                }
-
-                // A `/` means we are at the end of the variant, but there might be a modifier
-                //
-                // E.g.:
-                //
-                // ```
-                // group-hover/name:
-                //            ^
-                // ```
-                Class::Slash => return self.transition::<ParsingModifierState>().next(cursor),
-
-                // A `:` means we are at the end of the variant
-                //
-                // E.g.: `hover:`
-                //             ^
-                Class::Colon => return self.done(self.start_pos, cursor),
-
-                // A dot must be surrounded by numbers
-                //
-                // E.g.: `2.5xl:flex`
-                //        ^^^
-                Class::Dot => {
-                    if !matches!(cursor.prev().into(), Class::Number) {
-                        return self.restart();
-                    }
-
-                    if !matches!(cursor.next().into(), Class::Number) {
-                        return self.restart();
-                    }
-
-                    cursor.advance();
-                }
-
-                // Everything else is invalid
-                _ => return self.restart(),
-            };
-        }
-
-        self.restart()
-    }
-}
-
-impl NamedVariantMachine<ParsingState> {
-    #[inline(always)]
-    fn parse_arbitrary_end(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.next().into() {
-            Class::Slash => {
-                cursor.advance();
-                self.transition::<ParsingModifierState>().next(cursor)
-            }
-            Class::Colon => {
-                cursor.advance();
-                self.transition::<ParsingEndState>().next(cursor)
-            }
-            _ => self.restart(),
-        }
-    }
-}
-
-impl Machine for NamedVariantMachine<ParsingModifierState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match self.modifier_machine.next(cursor) {
-            MachineState::Idle => self.restart(),
-            MachineState::Done(_) => match cursor.next().into() {
-                // Modifier must be followed by a `:`
-                //
-                // E.g.: `group-hover/name:`
-                //                        ^
-                Class::Colon => {
-                    cursor.advance();
-                    self.transition::<ParsingEndState>().next(cursor)
-                }
-
-                // Everything else is invalid
-                _ => self.restart(),
-            },
-        }
-    }
-}
-
-impl Machine for NamedVariantMachine<ParsingEndState> {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline(always)]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.curr().into() {
-            // The end of a variant must be the `:`
-            //
-            // E.g.: `hover:`
-            //             ^
-            Class::Colon => self.done(self.start_pos, cursor),
-
-            // Everything else is invalid
-            _ => self.restart(),
-        }
-    }
-}
-
-#[derive(Clone, Copy, ClassifyBytes)]
-enum Class {
-    #[bytes_range(b'a'..=b'z')]
-    AlphaLower,
-
-    #[bytes_range(b'A'..=b'Z')]
-    AlphaUpper,
-
-    #[bytes(b'@')]
-    At,
-
-    #[bytes(b':')]
-    Colon,
-
-    #[bytes(b'-')]
-    Dash,
-
-    #[bytes(b'.')]
-    Dot,
-
-    #[bytes_range(b'0'..=b'9')]
-    Number,
-
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b'(')]
-    OpenParen,
-
-    #[bytes(b'*')]
-    Star,
-
-    #[bytes(b'/')]
-    Slash,
-
-    #[bytes(b'_')]
-    Underscore,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::{IdleState, NamedVariantMachine};
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_named_variant_machine_performance() {
-        let input = r#"<button class="hover:focus:flex data-[state=pending]:flex supports-(--my-variable):flex group-hover/named:not-has-peer-data-disabled:flex">"#;
-
-        NamedVariantMachine::<IdleState>::test_throughput(1_000_000, input);
-        NamedVariantMachine::<IdleState>::test_duration_once(input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_named_variant_extraction() {
-        for (input, expected) in [
-            // Simple variant
-            ("hover:", vec!["hover:"]),
-            // Simple single-character variant
-            ("a:", vec!["a:"]),
-            ("a/foo:", vec!["a/foo:"]),
-            //
-            ("group-hover:flex", vec!["group-hover:"]),
-            ("group-hover/name:flex", vec!["group-hover/name:"]),
-            (
-                "group-[data-state=pending]/name:flex",
-                vec!["group-[data-state=pending]/name:"],
-            ),
-            ("supports-(--foo)/name:flex", vec!["supports-(--foo)/name:"]),
-            // Odd media queries
-            ("1.5xl:flex", vec!["1.5xl:"]),
-            // Container queries
-            ("@md:flex", vec!["@md:"]),
-            ("@max-md:flex", vec!["@max-md:"]),
-            ("@-[36rem]:flex", vec!["@-[36rem]:"]),
-            ("@[36rem]:flex", vec!["@[36rem]:"]),
-            // --------------------------------------------------------
-
-            // Exceptions:
-            // Arbitrary variable must be valid
-            (r"supports-(--my-color\):", vec![]),
-            (r"supports-(--my#color)", vec![]),
-            // Single letter variant with uppercase letter is invalid
-            ("A:", vec![]),
-        ] {
-            let actual = NamedVariantMachine::<IdleState>::test_extract_all(input);
-            if actual != expected {
-                dbg!(&input);
-            }
-            assert_eq!(actual, expected);
-        }
-    }
-}

crates/oxide/src/extractor/pre_processors/clojure.rs

@@ -1,436 +0,0 @@
-use crate::cursor;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use bstr::ByteSlice;
-
-#[derive(Debug, Default)]
-pub struct Clojure;
-
-/// This is meant to be a rough estimate of a valid ClojureScript keyword
-///
-/// This can be approximated by the following regex:
-/// /::?[a-zA-Z0-9!#$%&*+./:<=>?_|-]+/
-///
-/// However, keywords are intended to be detected as utilities. Since the set
-/// of valid characters in a utility (outside of arbitrary values) is smaller,
-/// along with the fact that neither `[]` nor `()` are allowed in keywords we
-/// can simplify this list quite a bit.
-#[inline]
-fn is_keyword_character(byte: u8) -> bool {
-    (matches!(
-        byte,
-        b'!' | b'#' | b'%' | b'*' | b'+' | b'-' | b'.' | b'/' | b':' | b'_'
-    ) | byte.is_ascii_alphanumeric())
-}
-
-impl PreProcessor for Clojure {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let content = content
-            .replace(":class", "      ")
-            .replace(":className", "          ");
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(&content);
-
-        while cursor.pos < len {
-            match cursor.curr() {
-                // Consume strings as-is
-                b'"' => {
-                    result[cursor.pos] = b' ';
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // Escaped character, skip ahead to the next character
-                            b'\\' => cursor.advance_twice(),
-
-                            // End of the string
-                            b'"' => {
-                                result[cursor.pos] = b' ';
-                                break;
-                            }
-
-                            // Everything else is valid
-                            _ => cursor.advance(),
-                        };
-                    }
-                }
-
-                // Discard line comments until the end of the line.
-                // Comments start with `;;`
-                b';' if matches!(cursor.next(), b';') => {
-                    while cursor.pos < len && cursor.curr() != b'\n' {
-                        result[cursor.pos] = b' ';
-                        cursor.advance();
-                    }
-                }
-
-                // Consume keyword until a terminating character is reached.
-                b':' => {
-                    result[cursor.pos] = b' ';
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // A `.` surrounded by digits is a decimal number, so we don't want to replace it.
-                            //
-                            // E.g.:
-                            // ```
-                            // gap-1.5
-                            //      ^
-                            // ```
-                            b'.' if cursor.prev().is_ascii_digit()
-                                && cursor.next().is_ascii_digit() =>
-                            {
-                                // Keep the `.` as-is
-                            }
-                            // A `.` not surrounded by digits denotes the start of a new class name in a
-                            // dot-delimited keyword.
-                            //
-                            // E.g.:
-                            // ```
-                            // flex.gap-1.5
-                            //     ^
-                            // ```
-                            b'.' => {
-                                result[cursor.pos] = b' ';
-                            }
-                            // End of keyword.
-                            _ if !is_keyword_character(cursor.curr()) => {
-                                result[cursor.pos] = b' ';
-                                break;
-                            }
-
-                            // Consume everything else.
-                            _ => {}
-                        };
-
-                        cursor.advance();
-                    }
-                }
-
-                // Handle quote with a list, e.g.: `'(…)`
-                // and with a vector, e.g.: `'[…]`
-                b'\'' if matches!(cursor.next(), b'[' | b'(') => {
-                    result[cursor.pos] = b' ';
-                    cursor.advance();
-                    result[cursor.pos] = b' ';
-                    let end = match cursor.curr() {
-                        b'[' => b']',
-                        b'(' => b')',
-                        _ => unreachable!(),
-                    };
-
-                    // Consume until the closing `]`
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            x if x == end => {
-                                result[cursor.pos] = b' ';
-                                break;
-                            }
-
-                            // Consume strings as-is
-                            b'"' => {
-                                result[cursor.pos] = b' ';
-                                cursor.advance();
-
-                                while cursor.pos < len {
-                                    match cursor.curr() {
-                                        // Escaped character, skip ahead to the next character
-                                        b'\\' => cursor.advance_twice(),
-
-                                        // End of the string
-                                        b'"' => {
-                                            result[cursor.pos] = b' ';
-                                            break;
-                                        }
-
-                                        // Everything else is valid
-                                        _ => cursor.advance(),
-                                    };
-                                }
-                            }
-                            _ => {}
-                        };
-
-                        cursor.advance();
-                    }
-                }
-
-                // Handle quote with a keyword, e.g.: `'bg-white`
-                b'\'' if !cursor.next().is_ascii_whitespace() => {
-                    result[cursor.pos] = b' ';
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // End of keyword.
-                            _ if !is_keyword_character(cursor.curr()) => {
-                                result[cursor.pos] = b' ';
-                                break;
-                            }
-
-                            // Consume everything else.
-                            _ => {}
-                        };
-
-                        cursor.advance();
-                    }
-                }
-
-                // Aggressively discard everything else, reducing false positives and preventing
-                // characters surrounding keywords from producing false negatives.
-                // E.g.:
-                // ```
-                // (when condition :bg-white)
-                //                          ^
-                // ```
-                // A ')' is never a valid part of a keyword, but will nonetheless prevent 'bg-white'
-                // from being extracted if not discarded.
-                _ => {
-                    result[cursor.pos] = b' ';
-                }
-            };
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Clojure;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_clojure_pre_processor() {
-        for (input, expected) in [
-            (":div.flex-1.flex-2", " div flex-1 flex-2"),
-            (
-                ":.flex-3.flex-4 ;defaults to div",
-                "  flex-3 flex-4                 ",
-            ),
-            ("{:class :flex-5.flex-6", "         flex-5 flex-6"),
-            (r#"{:class "flex-7 flex-8"}"#, r#"         flex-7 flex-8  "#),
-            (
-                r#"{:class  ["flex-9" :flex-10]}"#,
-                r#"           flex-9   flex-10  "#,
-            ),
-            (
-                r#"(dom/div {:class "flex-11 flex-12"})"#,
-                r#"                  flex-11 flex-12   "#,
-            ),
-            ("(dom/div :.flex-13.flex-14", "           flex-13 flex-14"),
-            (
-                r#"[:div#hello.bg-white.pr-1.5 {:class ["grid grid-cols-[auto,1fr] grid-rows-2"]}]"#,
-                r#"  div#hello bg-white pr-1.5           grid grid-cols-[auto,1fr] grid-rows-2    "#,
-            ),
-        ] {
-            Clojure::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_extract_candidates() {
-        // https://github.com/luckasRanarison/tailwind-tools.nvim/issues/68#issuecomment-2660951258
-        let input = r#"
-            :div.c1.c2
-            :.c3.c4 ;defaults to div
-            {:class :c5.c6
-            {:class "c7 c8"}
-            {:class  ["c9" :c10]}
-            (dom/div {:class "c11 c12"})
-            (dom/div :.c13.c14
-            {:className :c15.c16
-            {:className "c17 c18"}
-            {:className  ["c19" :c20]}
-            (dom/div {:className "c21 c22"})
-        "#;
-
-        Clojure::test_extract_contains(
-            input,
-            vec![
-                "c1", "c2", "c3", "c4", "c5", "c6", "c7", "c8", "c9", "c10", "c11", "c12", "c13",
-                "c14", "c15", "c16", "c17", "c18", "c19", "c20", "c21", "c22",
-            ],
-        );
-
-        // Similar structure but using real classes
-        let input = r#"
-            :div.flex-1.flex-2
-            :.flex-3.flex-4 ;defaults to div
-            {:class :flex-5.flex-6
-            {:class "flex-7 flex-8"}
-            {:class  ["flex-9" :flex-10]}
-            (dom/div {:class "flex-11 flex-12"})
-            (dom/div :.flex-13.flex-14
-            {:className :flex-15.flex-16
-            {:className "flex-17 flex-18"}
-            {:className  ["flex-19" :flex-20]}
-            (dom/div {:className "flex-21 flex-22"})
-        "#;
-
-        Clojure::test_extract_contains(
-            input,
-            vec![
-                "flex-1", "flex-2", "flex-3", "flex-4", "flex-5", "flex-6", "flex-7", "flex-8",
-                "flex-9", "flex-10", "flex-11", "flex-12", "flex-13", "flex-14", "flex-15",
-                "flex-16", "flex-17", "flex-18", "flex-19", "flex-20", "flex-21", "flex-22",
-            ],
-        );
-    }
-
-    #[test]
-    fn test_special_characters_are_valid_in_strings() {
-        // In this case the `:` and `.` should not be replaced by ` ` because they are inside a
-        // string.
-        let input = r#"
-            (dom/div {:class "hover:flex px-1.5"})
-        "#;
-
-        Clojure::test_extract_contains(input, vec!["hover:flex", "px-1.5"]);
-    }
-
-    #[test]
-    fn test_ignore_comments_with_invalid_strings() {
-        let input = r#"
-            ;; This is an unclosed string: "
-            (dom/div {:class "hover:flex px-1.5"})
-        "#;
-
-        Clojure::test_extract_contains(input, vec!["hover:flex", "px-1.5"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17760
-    #[test]
-    fn test_extraction_of_classes_with_dots() {
-        let input = r#"
-            ($ :div {:class [:flex :gap-1.5 :p-1]} …)
-        "#;
-
-        Clojure::test_extract_contains(input, vec!["flex", "gap-1.5", "p-1"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/18336
-    #[test]
-    fn test_extraction_of_pseudoclasses_from_keywords() {
-        let input = r#"
-            ($ :div {:class [:flex :first:lg:pr-6 :first:2xl:pl-6 :group-hover/2:2xs:pt-6]} …)
-
-            :.hover:bg-white
-
-            [:div#hello.bg-white.pr-1.5]
-        "#;
-
-        Clojure::test_extract_contains(
-            input,
-            vec![
-                "flex",
-                "first:lg:pr-6",
-                "first:2xl:pl-6",
-                "group-hover/2:2xs:pt-6",
-                "hover:bg-white",
-                "bg-white",
-                "pr-1.5",
-            ],
-        );
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/18344
-    #[test]
-    fn test_noninterference_of_parens_on_keywords() {
-        let input = r#"
-            (get props :y-padding :py-5)
-            ($ :div {:class [:flex.pr-1.5 (if condition :bg-white :bg-black)]})
-        "#;
-
-        Clojure::test_extract_contains(
-            input,
-            vec!["py-5", "flex", "pr-1.5", "bg-white", "bg-black"],
-        );
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/18882
-    #[test]
-    fn test_extract_from_symbol_list() {
-        let input = r#"
-            [:div {:class '[z-1 z-2
-                            z-3 z-4]}]
-        "#;
-        Clojure::test_extract_contains(input, vec!["z-1", "z-2", "z-3", "z-4"]);
-
-        // https://github.com/tailwindlabs/tailwindcss/pull/18345#issuecomment-3253403847
-        let input = r#"
-            (def hl-class-names '[ring ring-blue-500])
-
-            [:div
-             {:class (cond-> '[input w-full]
-                       textarea? (conj 'textarea)
-                       (seq errors) (concat '[border-red-500 bg-red-100])
-                       highlight? (concat hl-class-names))}]
-        "#;
-        Clojure::test_extract_contains(
-            input,
-            vec![
-                "ring",
-                "ring-blue-500",
-                "input",
-                "w-full",
-                "textarea",
-                "border-red-500",
-                "bg-red-100",
-            ],
-        );
-
-        let input = r#"
-          [:div
-            {:class '[h-100 lg:h-200 max-w-32 mx-auto py-60
-                      flex flex-col justify-end items-center
-                      lg:flex-row lg:justify-between
-                      bg-cover bg-center bg-no-repeat rounded-3xl overflow-hidden
-                      font-semibold text-gray-900]}]
-        "#;
-        Clojure::test_extract_contains(
-            input,
-            vec![
-                "h-100",
-                "lg:h-200",
-                "max-w-32",
-                "mx-auto",
-                "py-60",
-                "flex",
-                "flex-col",
-                "justify-end",
-                "items-center",
-                "lg:flex-row",
-                "lg:justify-between",
-                "bg-cover",
-                "bg-center",
-                "bg-no-repeat",
-                "rounded-3xl",
-                "overflow-hidden",
-                "font-semibold",
-                "text-gray-900",
-            ],
-        );
-
-        // `/` is invalid and requires explicit quoting
-        let input = r#"
-            '[p-32 "text-black/50"]
-        "#;
-        Clojure::test_extract_contains(input, vec!["p-32", "text-black/50"]);
-
-        // `[…]` is invalid and requires explicit quoting
-        let input = r#"
-            (print '[ring ring-blue-500 "bg-[#0088cc]"])
-        "#;
-        Clojure::test_extract_contains(input, vec!["ring", "ring-blue-500", "bg-[#0088cc]"]);
-
-        // `'(…)` looks similar to `[…]` but uses parentheses instead of brackets
-        let input = r#"
-            (print '(ring ring-blue-500 "bg-[#0088cc]"))
-        "#;
-        Clojure::test_extract_contains(input, vec!["ring", "ring-blue-500", "bg-[#0088cc]"]);
-    }
-}

crates/oxide/src/extractor/pre_processors/elixir.rs

@@ -1,154 +0,0 @@
-use crate::cursor;
-use crate::extractor::bracket_stack::BracketStack;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-#[derive(Debug, Default)]
-pub struct Elixir;
-
-impl PreProcessor for Elixir {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let mut cursor = cursor::Cursor::new(content);
-        let mut result = content.to_vec();
-        let mut bracket_stack = BracketStack::default();
-
-        while cursor.pos < content.len() {
-            // Look for a sigil marker
-            if cursor.curr() != b'~' {
-                cursor.advance();
-                continue;
-            }
-
-            // Scan charlists, strings, and wordlists
-            if !matches!(cursor.next(), b'c' | b'C' | b's' | b'S' | b'w' | b'W') {
-                cursor.advance();
-                continue;
-            }
-
-            cursor.advance_twice();
-
-            // Match the opening for a sigil
-            if !matches!(cursor.curr(), b'(' | b'[' | b'{') {
-                continue;
-            }
-
-            // Replace the opening bracket with a space
-            result[cursor.pos] = b' ';
-
-            // Scan until we find a balanced closing one and replace it too
-            bracket_stack.push(cursor.curr());
-
-            while cursor.pos < content.len() {
-                cursor.advance();
-
-                match cursor.curr() {
-                    // Escaped character, skip ahead to the next character
-                    b'\\' => cursor.advance_twice(),
-                    b'(' | b'[' | b'{' => {
-                        bracket_stack.push(cursor.curr());
-                    }
-                    b')' | b']' | b'}' if !bracket_stack.is_empty() => {
-                        bracket_stack.pop(cursor.curr());
-
-                        if bracket_stack.is_empty() {
-                            // Replace the closing bracket with a space
-                            result[cursor.pos] = b' ';
-                            break;
-                        }
-                    }
-                    _ => {}
-                }
-            }
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Elixir;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_elixir_pre_processor() {
-        for (input, expected) in [
-            // Simple sigils
-            ("~W(flex underline)", "~W flex underline "),
-            ("~W[flex underline]", "~W flex underline "),
-            ("~W{flex underline}", "~W flex underline "),
-            // Sigils with nested brackets
-            (
-                "~W(text-(--my-color) bg-(--my-color))",
-                "~W text-(--my-color) bg-(--my-color) ",
-            ),
-            ("~W[text-[red] bg-[red]]", "~W text-[red] bg-[red] "),
-            // Word sigils with modifiers
-            ("~W(flex underline)a", "~W flex underline a"),
-            ("~W(flex underline)c", "~W flex underline c"),
-            ("~W(flex underline)s", "~W flex underline s"),
-            // Other sigil types
-            ("~w(flex underline)", "~w flex underline "),
-            ("~c(flex underline)", "~c flex underline "),
-            ("~C(flex underline)", "~C flex underline "),
-            ("~s(flex underline)", "~s flex underline "),
-            ("~S(flex underline)", "~S flex underline "),
-        ] {
-            Elixir::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_extract_candidates() {
-        let input = r#"
-          ~W(c1 c2)
-          ~W[c3 c4]
-          ~W{c5 c6}
-          ~W(text-(--c7) bg-(--c8))
-          ~W[text-[c9] bg-[c10]]
-          ~W(c13 c14)a
-          ~W(c15 c16)c
-          ~W(c17 c18)s
-          ~w(c19 c20)
-          ~c(c21 c22)
-          ~C(c23 c24)
-          ~s(c25 c26)
-          ~S(c27 c28)
-          ~W"c29 c30"
-          ~W'c31 c32'
-        "#;
-
-        Elixir::test_extract_contains(
-            input,
-            vec![
-                "c1",
-                "c2",
-                "c3",
-                "c4",
-                "c5",
-                "c6",
-                "text-(--c7)",
-                "bg-(--c8)",
-                "c13",
-                "c14",
-                "c15",
-                "c16",
-                "c17",
-                "c18",
-                "c19",
-                "c20",
-                "c21",
-                "c22",
-                "c23",
-                "c24",
-                "c25",
-                "c26",
-                "c27",
-                "c28",
-                "c29",
-                "c30",
-                "c31",
-                "c32",
-            ],
-        );
-    }
-}

crates/oxide/src/extractor/pre_processors/haml.rs

@@ -1,616 +0,0 @@
-use crate::cursor;
-use crate::extractor::bracket_stack::BracketStack;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use crate::extractor::variant_machine::VariantMachine;
-use crate::scanner::pre_process_input;
-use bstr::ByteVec;
-
-#[derive(Debug, Default)]
-pub struct Haml;
-
-impl PreProcessor for Haml {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-        let mut bracket_stack = BracketStack::default();
-
-        // Haml Comments: -#
-        // https://haml.info/docs/yardoc/file.REFERENCE.html#ruby-evaluation
-        //
-        // > The hyphen followed immediately by the pound sign signifies a silent comment. Any text
-        // > following this isn’t rendered in the resulting document at all.
-        //
-        // ```haml
-        // %p foo
-        // -# This is a comment
-        // %p bar
-        // ```
-        //
-        // > You can also nest text beneath a silent comment. None of this text will be rendered.
-        //
-        // ```haml
-        // %p foo
-        // -#
-        //   This won't be displayed
-        //     Nor will this
-        //                    Nor will this.
-        // %p bar
-        // ```
-        //
-        // Ruby Evaluation
-        // https://haml.info/docs/yardoc/file.REFERENCE.html#ruby-evaluation
-        //
-        // When any of the following characters are the first non-whitespace character on the line,
-        // then the line is treated as Ruby code:
-        //
-        // - Inserting Ruby: =
-        //   https://haml.info/docs/yardoc/file.REFERENCE.html#inserting_ruby
-        //
-        //   ```haml
-        //   %p
-        //     = ['hi', 'there', 'reader!'].join " "
-        //     = "yo"
-        //   ```
-        //
-        // - Running Ruby: -
-        //   https://haml.info/docs/yardoc/file.REFERENCE.html#running-ruby--
-        //
-        //   ```haml
-        //   - foo = "hello"
-        //   - foo << " there"
-        //   - foo << " you!"
-        //   %p= foo
-        //   ```
-        //
-        // - Whitespace Preservation: ~
-        //   https://haml.info/docs/yardoc/file.REFERENCE.html#tilde
-        //
-        //   > ~ works just like =, except that it runs Haml::Helpers.preserve on its input.
-        //
-        //   ```haml
-        //   ~ "Foo\n<pre>Bar\nBaz</pre>"
-        //   ```
-        //
-        // Important note:
-        //
-        // > A line of Ruby code can be stretched over multiple lines as long as each line but the
-        // > last ends with a comma.
-        //
-        // ```haml
-        // - links = {:home => "/",
-        //   :docs => "/docs",
-        //   :about => "/about"}
-        // ```
-        //
-        // Ruby Blocks:
-        // https://haml.info/docs/yardoc/file.REFERENCE.html#ruby-blocks
-        //
-        // > Ruby blocks, like XHTML tags, don’t need to be explicitly closed in Haml. Rather,
-        // > they’re automatically closed, based on indentation. A block begins whenever the
-        // > indentation is increased after a Ruby evaluation command. It ends when the indentation
-        // > decreases (as long as it’s not an else clause or something similar).
-        //
-        // ```haml
-        // - (42...47).each do |i|
-        //   %p= i
-        // %p See, I can count!
-        // ```
-        //
-        let mut last_newline_position = 0;
-
-        while cursor.pos < len {
-            match cursor.curr() {
-                // Escape the next character
-                b'\\' => {
-                    cursor.advance_twice();
-                    continue;
-                }
-
-                // Track the last newline position
-                b'\n' => {
-                    last_newline_position = cursor.pos;
-                    cursor.advance();
-                    continue;
-                }
-
-                // Skip HAML comments. `-#`
-                b'-' if cursor.input[last_newline_position..cursor.pos]
-                    .iter()
-                    .all(u8::is_ascii_whitespace)
-                    && matches!(cursor.next(), b'#') =>
-                {
-                    // Just consume the comment
-                    let updated_last_newline_position =
-                        self.skip_indented_block(&mut cursor, last_newline_position);
-
-                    // Override the last known newline position
-                    last_newline_position = updated_last_newline_position;
-                }
-
-                // Skip HTML comments. `/`
-                b'/' if cursor.input[last_newline_position..cursor.pos]
-                    .iter()
-                    .all(u8::is_ascii_whitespace) =>
-                {
-                    // Just consume the comment
-                    let updated_last_newline_position =
-                        self.skip_indented_block(&mut cursor, last_newline_position);
-
-                    // Override the last known newline position
-                    last_newline_position = updated_last_newline_position;
-                }
-
-                // Ruby evaluation
-                b'-' | b'=' | b'~'
-                    if cursor.input[last_newline_position..cursor.pos]
-                        .iter()
-                        .all(u8::is_ascii_whitespace) =>
-                {
-                    let mut start = cursor.pos;
-                    let end = self.skip_indented_block(&mut cursor, last_newline_position);
-
-                    // Increment start with 1 character to skip the `=` or `-` character
-                    start += 1;
-
-                    let ruby_code = &cursor.input[start..end];
-
-                    // Override the last known newline position
-                    last_newline_position = end;
-
-                    let replaced = pre_process_input(ruby_code.to_vec(), "rb");
-                    result.replace_range(start..end, replaced);
-                }
-
-                // Only replace `.` with a space if it's not surrounded by numbers. E.g.:
-                //
-                // ```diff
-                // - .flex.items-center
-                // +  flex items-center
-                // ```
-                //
-                // But with numbers, it's allowed:
-                //
-                // ```diff
-                // - px-2.5
-                // + px-2.5
-                // ```
-                b'.' => {
-                    // Don't replace dots with spaces when inside of any type of brackets, because
-                    // this could be part of arbitrary values. E.g.: `bg-[url(https://example.com)]`
-                    //                                                                       ^
-                    if !bracket_stack.is_empty() {
-                        cursor.advance();
-                        continue;
-                    }
-
-                    // If the dot is surrounded by digits, we want to keep it. E.g.: `px-2.5`
-                    // EXCEPT if it's followed by a valid variant that happens to start with a
-                    // digit.
-                    // E.g.: `bg-red-500.2xl:flex`
-                    //                 ^^^
-                    if cursor.prev().is_ascii_digit() && cursor.next().is_ascii_digit() {
-                        let mut next_cursor = cursor.clone();
-                        next_cursor.advance();
-
-                        let mut variant_machine = VariantMachine::default();
-                        if let MachineState::Done(_) = variant_machine.next(&mut next_cursor) {
-                            result[cursor.pos] = b' ';
-                        }
-                    } else {
-                        result[cursor.pos] = b' ';
-                    }
-                }
-
-                // Handle Ruby syntax with `%w[]` arrays embedded in Haml attribute hashes. E.g.:
-                //
-                // ```haml
-                // %div{class: %w[bg-blue-500 w-10 h-10]}
-                // ```
-                //
-                // A `%` that follows a value is not a percent literal. E.g.: the `50%w` in
-                // `hit rate 50%w.`
-                b'%' if matches!(cursor.next(), b'w' | b'W')
-                    && !cursor.prev().is_ascii_alphanumeric()
-                    && !matches!(cursor.prev(), b'_' | b')' | b']' | b'}') =>
-                {
-                    // Boundary characters
-                    let (open, close) = match cursor.input.get(cursor.pos + 2) {
-                        Some(b'[') => (b'[', b']'),
-                        Some(b'(') => (b'(', b')'),
-                        Some(b'{') => (b'{', b'}'),
-                        Some(b'<') => (b'<', b'>'),
-
-                        // Any other ASCII punctuation can be used as a custom delimiter
-                        Some(&c) if c.is_ascii_punctuation() => (c, c),
-
-                        // Everything else is not a valid delimiter
-                        _ => {
-                            cursor.advance();
-                            continue;
-                        }
-                    };
-
-                    result[cursor.pos] = b' '; // Replace `%`
-                    cursor.advance();
-                    result[cursor.pos] = b' '; // Replace `w`
-                    cursor.advance();
-                    result[cursor.pos] = b' '; // Replace the opening delimiter
-                    cursor.advance();
-
-                    // Paired delimiters can be nested as long as they are balanced. E.g.:
-                    // `%w[foo[bar]baz]` produces a flat array.
-                    let mut depth = 1_usize;
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // Skip escaped characters, unless the backslash is the delimiter
-                            // itself
-                            b'\\' if close != b'\\' => {
-                                // Use backslash to embed spaces in the strings.
-                                if cursor.next() == b' ' {
-                                    result[cursor.pos] = b' ';
-                                }
-
-                                cursor.advance();
-                            }
-
-                            // Start of a nested delimiter pair
-                            c if c == open && open != close => depth += 1,
-
-                            // Closing delimiter
-                            c if c == close => {
-                                depth -= 1;
-
-                                // End of the literal, replace the closing delimiter with a space
-                                if depth == 0 {
-                                    result[cursor.pos] = b' ';
-                                    break;
-                                }
-                            }
-
-                            // Everything else is valid content
-                            _ => {}
-                        }
-
-                        cursor.advance();
-                    }
-                }
-
-                // Replace following characters with spaces if they are not inside of brackets
-                b'#' | b'=' if bracket_stack.is_empty() => {
-                    result[cursor.pos] = b' ';
-                }
-
-                b'(' | b'[' | b'{' => {
-                    // Replace first bracket with a space
-                    if bracket_stack.is_empty() {
-                        result[cursor.pos] = b' ';
-                    }
-                    bracket_stack.push(cursor.curr());
-                }
-
-                b')' | b']' | b'}' if !bracket_stack.is_empty() => {
-                    bracket_stack.pop(cursor.curr());
-
-                    // Replace closing bracket with a space
-                    if bracket_stack.is_empty() {
-                        result[cursor.pos] = b' ';
-                    }
-                }
-
-                // Consume everything else
-                _ => {}
-            };
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-impl Haml {
-    fn skip_indented_block(
-        &self,
-        cursor: &mut cursor::Cursor,
-        last_known_newline_position: usize,
-    ) -> usize {
-        let len = cursor.input.len();
-
-        // Special case: if the first character of the block is `=`, then newlines are only allowed
-        // _if_ the last character of the previous line is a comma `,`.
-        //
-        // https://haml.info/docs/yardoc/file.REFERENCE.html#inserting_ruby
-        //
-        // > A line of Ruby code can be stretched over multiple lines as long as each line but the
-        // > last ends with a comma. For example:
-        //
-        // ```haml
-        // = link_to_remote "Add to cart",
-        //     :url => { :action => "add", :id => product.id },
-        //     :update => { :success => "cart", :failure => "error" }
-        // ```
-        let evaluation_type = cursor.curr();
-
-        let block_indentation_level = cursor
-            .pos
-            .saturating_sub(last_known_newline_position)
-            .saturating_sub(1); /* The newline itself */
-
-        let mut last_newline_position = last_known_newline_position;
-
-        // Consume until the end of the line first
-        while cursor.pos < len && cursor.curr() != b'\n' {
-            cursor.advance();
-        }
-
-        // Block is already done, aka just a line
-        if evaluation_type == b'=' && cursor.prev() != b',' {
-            return cursor.pos;
-        }
-
-        'outer: while cursor.pos < len {
-            match cursor.curr() {
-                // Escape the next character
-                b'\\' => {
-                    cursor.advance_twice();
-                    continue;
-                }
-
-                // Track the last newline position
-                b'\n' => {
-                    last_newline_position = cursor.pos;
-
-                    // We are done with this block
-                    if evaluation_type == b'=' && cursor.prev() != b',' {
-                        break;
-                    }
-
-                    cursor.advance();
-                    continue;
-                }
-
-                // Skip whitespace and compute the indentation level
-                x if x.is_ascii_whitespace() => {
-                    // Find first non-whitespace character
-                    while cursor.pos < len && cursor.curr().is_ascii_whitespace() {
-                        if cursor.curr() == b'\n' {
-                            last_newline_position = cursor.pos;
-
-                            if evaluation_type == b'=' && cursor.prev() != b',' {
-                                // We are done with this block
-                                break 'outer;
-                            }
-                        }
-
-                        cursor.advance();
-                    }
-
-                    let indentation = cursor
-                        .pos
-                        .saturating_sub(last_newline_position)
-                        .saturating_sub(1); /* The newline itself */
-                    if indentation < block_indentation_level {
-                        // We are done with this block
-                        break;
-                    }
-                }
-
-                // Not whitespace, end of block
-                _ => break,
-            };
-
-            cursor.advance();
-        }
-
-        // We didn't find a newline, we reached the end of the input
-        if last_known_newline_position == last_newline_position {
-            return cursor.pos;
-        }
-
-        // Move the cursor to the last newline position
-        cursor.move_to(last_newline_position);
-
-        last_newline_position
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Haml;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    fn test_haml_pre_processor() {
-        for (input, expected) in [
-            // Element with classes
-            (
-                "%body.flex.flex-col.items-center.justify-center",
-                "%body flex flex-col items-center justify-center",
-            ),
-            // Plain element
-            (
-                ".text-slate-500.xl:text-gray-500",
-                " text-slate-500 xl:text-gray-500",
-            ),
-            // Element with hash attributes
-            (
-                ".text-black.xl:text-red-500{ data: { tailwind: 'css' } }",
-                " text-black xl:text-red-500  data: { tailwind: 'css' }  ",
-            ),
-            // Element with a boolean attribute
-            (
-                ".text-green-500.xl:text-blue-500(data-sidebar)",
-                " text-green-500 xl:text-blue-500 data-sidebar ",
-            ),
-            // Element with interpreted content
-            (
-                ".text-yellow-500.xl:text-purple-500= 'Element with interpreted content'",
-                " text-yellow-500 xl:text-purple-500  'Element with interpreted content'",
-            ),
-            // Element with a hash at the end and an extra class.
-            (
-                ".text-orange-500.xl:text-pink-500{ class: 'bg-slate-100' }",
-                " text-orange-500 xl:text-pink-500  class: 'bg-slate-100'  ",
-            ),
-            // Object reference
-            (
-                ".text-teal-500.xl:text-indigo-500[@user, :greeting]",
-                " text-teal-500 xl:text-indigo-500 @user, :greeting ",
-            ),
-            // Element with an ID
-            (
-                ".text-lime-500.xl:text-emerald-500#root",
-                " text-lime-500 xl:text-emerald-500 root",
-            ),
-            // Dots in strings in HTML attributes stay as-is
-            (r#"<div id="px-2.5"></div>"#, r#"<div id "px-2.5"></div>"#),
-        ] {
-            Haml::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_strings_only_occur_when_nested() {
-        let input = r#"
-            %p.mt-2.text-xl
-              The quote in the next word, can't be the start of a string
-
-            %h3.mt-24.text-center.text-4xl.font-bold.italic
-              The classes above should be extracted
-        "#;
-
-        Haml::test_extract_contains(
-            input,
-            vec![
-                // First paragraph
-                "mt-2",
-                "text-xl",
-                // second paragraph
-                "mt-24",
-                "text-center",
-                "text-4xl",
-                "font-bold",
-                "italic",
-            ],
-        );
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/20386
-    #[test]
-    fn test_embedded_ruby_percent_w_delimiters() {
-        for (input, expected) in [
-            // %w[…] in an attribute hash
-            (
-                "%div{class: %w[flex px-2.5]}",
-                "%div class:    flex px-2.5  ",
-            ),
-            // %w<…>
-            (
-                "%div{class: %w<flex px-2.5>}",
-                "%div class:    flex px-2.5  ",
-            ),
-            // Nested `<…>` does not end the literal
-            (
-                "%div{class: %w<flex <nested> px-2.5>}",
-                "%div class:    flex <nested> px-2.5  ",
-            ),
-            // Custom delimiters
-            (
-                "%div{class: %w|flex px-2.5|}",
-                "%div class:    flex px-2.5  ",
-            ),
-            (
-                "%div{class: %W!flex px-2.5!}",
-                "%div class:    flex px-2.5  ",
-            ),
-            (
-                "%div{class: %w#text-sm leading-6#}",
-                "%div class:    text-sm leading-6  ",
-            ),
-            (
-                "%div{class: %w=italic tracking-wide=}",
-                "%div class:    italic tracking-wide  ",
-            ),
-            // Nested paired delimiters stay balanced inside the literal
-            (
-                "%div{class: %w[content-['[hello]'] p-4]}",
-                "%div class:    content-['[hello]'] p-4  ",
-            ),
-            // Escaped spaces embed a space in a single array element
-            (
-                r#"%div{class: %w[foo\ bar baz-1]}"#,
-                r#"%div class:    foo  bar baz-1  "#,
-            ),
-            // A `%` that follows a value is not a percent literal
-            ("%p hit rate 50%w.", "%p hit rate 50%w "),
-        ] {
-            Haml::test(input, expected);
-        }
-
-        let input = r#"
-            %div{class: %w[bg-blue-500 w-10 h-10]}
-            %div{class: %w<flex px-2.5>}
-            %div{class: %w|underline font-bold|}
-            - classes = %w<mt-4 grid>
-        "#;
-
-        Haml::test_extract_contains(
-            input,
-            vec![
-                "bg-blue-500",
-                "w-10",
-                "h-10",
-                "flex",
-                "px-2.5",
-                "underline",
-                "font-bold",
-                "mt-4",
-                "grid",
-            ],
-        );
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/pull/17051#issuecomment-2711181352
-    #[test]
-    fn test_haml_full_file_17051() {
-        let actual = Haml::extract_annotated(include_bytes!("./test-fixtures/haml/src-17051.haml"));
-        let expected = include_str!("./test-fixtures/haml/dst-17051.haml");
-
-        assert_eq!(actual.replace("\r\n", "\n"), expected.replace("\r\n", "\n"));
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17813
-    #[test]
-    fn test_haml_full_file_17813() {
-        let actual = Haml::extract_annotated(include_bytes!("./test-fixtures/haml/src-17813.haml"));
-        let expected = include_str!("./test-fixtures/haml/dst-17813.haml");
-
-        assert_eq!(actual.replace("\r\n", "\n"), expected.replace("\r\n", "\n"));
-    }
-
-    #[test]
-    fn test_arbitrary_code_followed_by_classes() {
-        let input = r#"
-            %p
-              = i < 3
-              .flex.items-center
-        "#;
-        Haml::test_extract_contains(input, vec!["flex", "items-center"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17379#issuecomment-2910108646
-    #[test]
-    fn test_crash_missing_newline() {
-        // The empty `""` will introduce a newline
-        let good = ["- index = 0", "- index += 1", ""].join("\n");
-        Haml::test_extract_contains(&good, vec!["index"]);
-
-        // This used to crash before the fix
-        let bad = ["- index = 0", "- index += 1"].join("\n");
-        Haml::test_extract_contains(&bad, vec!["index"]);
-    }
-}

crates/oxide/src/extractor/pre_processors/json.rs

@@ -1,63 +0,0 @@
-use crate::cursor;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-#[derive(Debug, Default)]
-pub struct Json;
-
-impl PreProcessor for Json {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-
-        while cursor.pos < len {
-            match cursor.curr() {
-                // Consume strings as-is
-                b'"' => {
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // Escaped character, skip ahead to the next character
-                            b'\\' => cursor.advance_twice(),
-
-                            // End of the string
-                            b'"' => break,
-
-                            // Everything else is valid
-                            _ => cursor.advance(),
-                        };
-                    }
-                }
-
-                // Replace brackets and curlies with spaces
-                b'[' | b'{' | b']' | b'}' => {
-                    result[cursor.pos] = b' ';
-                }
-
-                // Consume everything else
-                _ => {}
-            };
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Json;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_json_pre_processor() {
-        let (input, expected) = (
-            r#"[1,[2,[3,4,["flex flex-1 content-['hello_world']"]]], {"flex": true}]"#,
-            r#" 1, 2, 3,4, "flex flex-1 content-['hello_world']"   ,  "flex": true  "#,
-        );
-
-        Json::test(input, expected);
-    }
-}

crates/oxide/src/extractor/pre_processors/markdown.rs

@@ -1,83 +0,0 @@
-use crate::cursor;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-#[derive(Debug, Default)]
-pub struct Markdown;
-
-impl PreProcessor for Markdown {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-        let mut bracket_stack = vec![];
-
-        let mut in_directive = false;
-
-        while cursor.pos < len {
-            match (in_directive, cursor.curr()) {
-                (false, b'{') => {
-                    result[cursor.pos] = b' ';
-                    in_directive = true;
-                }
-                (true, b'(' | b'[' | b'{' | b'<') => {
-                    bracket_stack.push(cursor.curr());
-                }
-                (true, b')' | b']' | b'}' | b'>') if !bracket_stack.is_empty() => {
-                    bracket_stack.pop();
-                }
-                (true, b'}') => {
-                    result[cursor.pos] = b' ';
-                    in_directive = false;
-                }
-                (true, b'.') if bracket_stack.is_empty() => {
-                    result[cursor.pos] = b' ';
-                }
-                _ => {}
-            }
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Markdown;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_markdown_pre_processor() {
-        for (input, expected) in [
-            // Convert dots to spaces inside markdown inline directives
-            (
-                ":span[Some Text]{.text-gray-500}",
-                ":span[Some Text]  text-gray-500 ",
-            ),
-            (
-                ":span[Some Text]{.text-gray-500.bg-red-500}",
-                ":span[Some Text]  text-gray-500 bg-red-500 ",
-            ),
-            (
-                ":span[Some Text]{#myId .my-class key=val key2='val 2'}",
-                ":span[Some Text] #myId  my-class key=val key2='val 2' ",
-            ),
-        ] {
-            Markdown::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_nested_classes_keep_the_dots() {
-        for (input, expected) in [
-            (
-                r#"{<div class="px-2.5"></div>}"#,
-                r#" <div class="px-2.5"></div> "#,
-            ),
-            (r#"{content-['example.js']}"#, r#" content-['example.js'] "#),
-        ] {
-            Markdown::test(input, expected);
-        }
-    }
-}

crates/oxide/src/extractor/pre_processors/mod.rs

@@ -1,31 +0,0 @@
-pub mod clojure;
-pub mod elixir;
-pub mod haml;
-pub mod json;
-pub mod markdown;
-pub mod pre_processor;
-pub mod pug;
-pub mod razor;
-pub mod ruby;
-pub mod rust;
-pub mod slim;
-pub mod svelte;
-pub mod template_toolkit;
-pub mod twig;
-pub mod vue;
-
-pub use clojure::*;
-pub use elixir::*;
-pub use haml::*;
-pub use json::*;
-pub use markdown::*;
-pub use pre_processor::*;
-pub use pug::*;
-pub use razor::*;
-pub use ruby::*;
-pub use rust::*;
-pub use slim::*;
-pub use svelte::*;
-pub use template_toolkit::*;
-pub use twig::*;
-pub use vue::*;

crates/oxide/src/extractor/pre_processors/pre_processor.rs

@@ -1,186 +0,0 @@
-pub trait PreProcessor: Sized + Default {
-    fn process(&self, content: &[u8]) -> Vec<u8>;
-
-    #[cfg(test)]
-    fn test(input: &str, expected: &str) {
-        use pretty_assertions::assert_eq;
-
-        let input = input.as_bytes();
-        let expected = expected.as_bytes();
-
-        let processor = Self::default();
-
-        let actual = processor.process(input);
-
-        // Convert to strings for better error messages.
-        let input = String::from_utf8_lossy(input);
-        let actual = String::from_utf8_lossy(&actual);
-        let expected = String::from_utf8_lossy(expected);
-
-        // The input and output should have the exact same length.
-        assert_eq!(input.len(), actual.len());
-        assert_eq!(actual.len(), expected.len());
-
-        assert_eq!(actual, expected);
-    }
-
-    #[cfg(test)]
-    fn test_extract_exact(input: &str, expected: Vec<&str>) {
-        use crate::extractor::{Extracted, Extractor};
-
-        let input = input.as_bytes();
-
-        let processor = Self::default();
-        let transformed = processor.process(input);
-
-        let extracted = Extractor::new(&transformed).extract();
-
-        // Extract all candidates and css variables.
-        let candidates = extracted
-            .iter()
-            .filter_map(|x| match x {
-                Extracted::Candidate(bytes) => std::str::from_utf8(bytes).ok(),
-                Extracted::CssVariable(bytes) => std::str::from_utf8(bytes).ok(),
-            })
-            .collect::<Vec<_>>();
-
-        if candidates != expected {
-            dbg!(&candidates, &expected);
-            panic!("Extracted candidates do not match expected candidates");
-        }
-    }
-
-    #[cfg(test)]
-    fn test_extract_contains(input: &str, expected: Vec<&str>) {
-        use crate::extractor::{Extracted, Extractor};
-
-        let input = input.as_bytes();
-
-        let processor = Self::default();
-        let transformed = processor.process(input);
-
-        let extracted = Extractor::new(&transformed).extract();
-
-        // Extract all candidates and css variables.
-        let candidates = extracted
-            .iter()
-            .filter_map(|x| match x {
-                Extracted::Candidate(bytes) => std::str::from_utf8(bytes).ok(),
-                Extracted::CssVariable(bytes) => std::str::from_utf8(bytes).ok(),
-            })
-            .collect::<Vec<_>>();
-
-        // Ensure all items are present in the candidates.
-        let mut missing = vec![];
-        for item in &expected {
-            if !candidates.contains(item) {
-                missing.push(item);
-            }
-        }
-
-        if !missing.is_empty() {
-            dbg!(&candidates, &missing);
-            panic!("Missing some items");
-        }
-    }
-
-    #[cfg(test)]
-    fn extract_annotated(input: &[u8]) -> String {
-        use crate::extractor::{Extracted, Extractor};
-        use std::collections::BTreeMap;
-        use unicode_width::UnicodeWidthStr;
-
-        let processor = Self::default();
-        let transformed = processor.process(input);
-
-        let extracted = Extractor::new(&transformed).extract();
-
-        // Extract only candidate positions
-        let byte_ranges = extracted
-            .iter()
-            .filter_map(|x| match x {
-                Extracted::Candidate(bytes) => {
-                    let start = bytes.as_ptr() as usize - transformed.as_ptr() as usize;
-                    let end = start + bytes.len();
-                    Some((start, end))
-                }
-                _ => None,
-            })
-            .collect::<Vec<_>>();
-
-        // Convert byte ranges to (line, start_col, end_col)
-        let mut annotations = byte_ranges
-            .into_iter()
-            .map(|(start, end)| {
-                let (line, start_col) = byte_offset_to_line_and_column(input, start);
-                let (_, end_col) = byte_offset_to_line_and_column(input, end);
-                (line, start_col, end_col)
-            })
-            .collect::<Vec<_>>();
-
-        // Sort for safe insertion
-        annotations.sort_by(|a, b| b.0.cmp(&a.0).then(b.1.cmp(&a.1)));
-
-        // Convert input to lines
-        let mut lines = std::str::from_utf8(input)
-            .expect("Input must be valid UTF-8")
-            .lines()
-            .map(|line| line.to_string())
-            .collect::<Vec<_>>();
-
-        // Group annotations per line
-        let mut grouped = BTreeMap::<usize, Vec<(usize, usize)>>::new();
-        for (line, start_char, end_char) in annotations {
-            grouped
-                .entry(line)
-                .or_default()
-                .push((start_char, end_char));
-        }
-
-        // Inject annotation lines
-        for (line_idx, spans) in grouped.into_iter().rev() {
-            let display_line = &lines[line_idx];
-            let width = UnicodeWidthStr::width(display_line.as_str());
-            let mut annotation = vec![' '; width];
-
-            for (start, end) in spans {
-                for i in start..end.min(annotation.len()) {
-                    annotation[i] = '^';
-                }
-            }
-
-            let annotation_line: String = annotation
-                .into_iter()
-                .collect::<String>()
-                .trim_end()
-                .to_owned();
-            lines.insert(line_idx + 1, annotation_line);
-        }
-
-        lines.join("\n").trim_end().to_string() + "\n"
-    }
-}
-
-#[cfg(test)]
-fn byte_offset_to_line_and_column(input: &[u8], offset: usize) -> (usize, usize) {
-    use unicode_width::UnicodeWidthStr;
-
-    let mut line_start = 0;
-    let mut line = 0;
-
-    for (i, &b) in input.iter().enumerate() {
-        if i >= offset {
-            break;
-        }
-        if b == b'\n' {
-            line += 1;
-            line_start = i + 1;
-        }
-    }
-
-    let slice = &input[line_start..offset];
-    let column = std::str::from_utf8(slice).expect("Valid UTF-8");
-    let column = UnicodeWidthStr::width(column);
-
-    (line, column)
-}

crates/oxide/src/extractor/pre_processors/pug.rs

@@ -1,181 +0,0 @@
-use crate::cursor;
-use crate::extractor::bracket_stack::BracketStack;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use crate::extractor::variant_machine::VariantMachine;
-
-#[derive(Debug, Default)]
-pub struct Pug;
-
-impl PreProcessor for Pug {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-        let mut bracket_stack = BracketStack::default();
-
-        while cursor.pos < len {
-            match cursor.curr() {
-                // Only replace `.` with a space if it's not surrounded by numbers. E.g.:
-                //
-                // ```diff
-                // - .flex.items-center
-                // +  flex items-center
-                // ```
-                //
-                // But with numbers, it's allowed:
-                //
-                // ```diff
-                // - px-2.5
-                // + px-2.5
-                // ```
-                b'.' => {
-                    // Don't replace dots with spaces when inside of any type of brackets, because
-                    // this could be part of arbitrary values. E.g.: `bg-[url(https://example.com)]`
-                    //                                                                       ^
-                    if !bracket_stack.is_empty() {
-                        cursor.advance();
-                        continue;
-                    }
-
-                    // If the dot is surrounded by digits, we want to keep it. E.g.: `px-2.5`
-                    // EXCEPT if it's followed by a valid variant that happens to start with a
-                    // digit.
-                    // E.g.: `bg-red-500.2xl:flex`
-                    //                 ^^^
-                    if cursor.prev().is_ascii_digit() && cursor.next().is_ascii_digit() {
-                        let mut next_cursor = cursor.clone();
-                        next_cursor.advance();
-
-                        let mut variant_machine = VariantMachine::default();
-                        if let MachineState::Done(_) = variant_machine.next(&mut next_cursor) {
-                            result[cursor.pos] = b' ';
-                        }
-                    } else {
-                        result[cursor.pos] = b' ';
-                    }
-                }
-
-                // In Pug the class name shorthand can be followed by a parenthesis. E.g.:
-                //
-                // ```pug
-                // body.border-t-4.p-8(attr=value)
-                //                    ^ Not part of the p-8 class
-                // ```
-                //
-                // This means that we need to replace all these `(` and `)` with spaces to make
-                // sure that we can extract the `p-8`.
-                //
-                // However, we also need to make sure that we keep the parens that are part of the
-                // utility class. E.g.: `bg-(--my-color)`.
-                b'(' if bracket_stack.is_empty() && !matches!(cursor.prev(), b'-' | b'/') => {
-                    result[cursor.pos] = b' ';
-                    bracket_stack.push(cursor.curr());
-                }
-
-                b'(' | b'[' | b'{' => {
-                    bracket_stack.push(cursor.curr());
-                }
-
-                b')' | b']' | b'}' if !bracket_stack.is_empty() => {
-                    bracket_stack.pop(cursor.curr());
-                }
-
-                // Consume everything else
-                _ => {}
-            };
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Pug;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_pug_pre_processor() {
-        for (input, expected) in [
-            // Convert dots to spaces
-            ("div.flex.bg-red-500", "div flex bg-red-500"),
-            (".flex.bg-red-500", " flex bg-red-500"),
-            // Keep dots in strings
-            (r#"div(class="px-2.5")"#, r#"div class="px-2.5")"#),
-            // Nested brackets
-            (
-                "bg-[url(https://example.com/?q=[1,2])]",
-                "bg-[url(https://example.com/?q=[1,2])]",
-            ),
-            // Classes in HTML attributes
-            (r#"<div id="px-2.5"></div>"#, r#"<div id="px-2.5"></div>"#),
-        ] {
-            Pug::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_strings_only_occur_when_nested() {
-        let input = r#"
-            p.mt-2.text-xl
-              div The quote in the next word, can't be the start of a string
-
-            h3.mt-24.text-center.text-4xl.font-bold.italic
-              div The classes above should be extracted
-        "#;
-
-        Pug::test_extract_contains(
-            input,
-            vec![
-                // First paragraph
-                "mt-2",
-                "text-xl",
-                // second paragraph
-                "mt-24",
-                "text-center",
-                "text-4xl",
-                "font-bold",
-                "italic",
-            ],
-        );
-    }
-
-    #[test]
-    fn test_arbitrary_code_followed_by_classes() {
-        let input = r#"
-            - i < 3
-              .flex.items-center
-        "#;
-        Pug::test_extract_contains(input, vec!["flex", "items-center"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17313
-    #[test]
-    fn test_class_shorthand_followed_by_parens() {
-        let input = r#"
-            .text-sky-600.bg-neutral-900(title="A tooltip") This div has an HTML attribute.
-        "#;
-        Pug::test_extract_contains(input, vec!["text-sky-600", "bg-neutral-900"]);
-
-        // Additional test with CSS Variable shorthand syntax in the attribute itself because `(`
-        // and `)` are not valid in the class shorthand version.
-        //
-        // Also included an arbitrary value including `(` and `)` to make sure that we don't
-        // accidentally remove those either.
-        let input = r#"
-            .p-8(class="bg-(--my-color) bg-(--my-color)/(--my-opacity) bg-[url(https://example.com)]")
-        "#;
-        Pug::test_extract_contains(
-            input,
-            vec![
-                "p-8",
-                "bg-(--my-color)",
-                "bg-(--my-color)/(--my-opacity)",
-                "bg-[url(https://example.com)]",
-            ],
-        );
-    }
-}

crates/oxide/src/extractor/pre_processors/razor.rs

@@ -1,42 +0,0 @@
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use bstr::ByteSlice;
-
-#[derive(Debug, Default)]
-pub struct Razor;
-
-impl PreProcessor for Razor {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        content.replace("@@", " @").replace(r#"@("@")"#, "     @")
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Razor;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_razor_pre_processor() {
-        let (input, expected) = (
-            r#"<div class="@@sm:text-red-500">"#,
-            r#"<div class=" @sm:text-red-500">"#,
-        );
-        Razor::test(input, expected);
-        Razor::test_extract_contains(input, vec!["@sm:text-red-500"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17424
-    #[test]
-    fn test_razor_syntax_with() {
-        let (input, expected) = (
-            r#"<p class="@("@")md:bg-red-500 @@md:border-green-500 border-8">With 2 elements</p>"#,
-            r#"<p class="     @md:bg-red-500  @md:border-green-500 border-8">With 2 elements</p>"#,
-        );
-
-        Razor::test(input, expected);
-        Razor::test_extract_contains(
-            input,
-            vec!["@md:bg-red-500", "@md:border-green-500", "border-8"],
-        );
-    }
-}

crates/oxide/src/extractor/pre_processors/ruby.rs

@@ -1,528 +0,0 @@
-// See: - https://docs.ruby-lang.org/en/3.4/syntax/literals_rdoc.html#label-Percent+Literals
-//      - https://docs.ruby-lang.org/en/3.4/syntax/literals_rdoc.html#label-25w+and+-25W-3A+String-Array+Literals
-use crate::cursor;
-use crate::extractor::bracket_stack;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use crate::scanner::pre_process_input;
-use bstr::ByteVec;
-use regex::{Regex, RegexBuilder};
-use std::sync;
-
-static TEMPLATE_START_REGEX: sync::LazyLock<Regex> = sync::LazyLock::new(|| {
-    RegexBuilder::new(r#"\s*([a-z0-9_-]+)_template\s*<<[-~]?([A-Z]+)$"#)
-        .multi_line(true)
-        .build()
-        .unwrap()
-});
-
-static TEMPLATE_END_REGEX: sync::LazyLock<Regex> = sync::LazyLock::new(|| {
-    RegexBuilder::new(r#"^\s*([A-Z]+)"#)
-        .multi_line(true)
-        .build()
-        .unwrap()
-});
-
-#[derive(Debug, Default)]
-pub struct Ruby;
-
-impl PreProcessor for Ruby {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-        let mut bracket_stack = bracket_stack::BracketStack::default();
-
-        // Extract embedded template languages
-        // https://viewcomponent.org/guide/templates.html#interpolations
-        // Only process if content is valid UTF-8, otherwise skip HEREDOC extraction
-        // but still perform the byte-level Ruby processing below
-        if let Ok(content_as_str) = std::str::from_utf8(content) {
-            let starts = TEMPLATE_START_REGEX
-                .captures_iter(content_as_str)
-                .collect::<Vec<_>>();
-            let ends = TEMPLATE_END_REGEX
-                .captures_iter(content_as_str)
-                .collect::<Vec<_>>();
-
-            for start in starts.iter() {
-                // The language for this block
-                let lang = start.get(1).unwrap().as_str();
-
-                // The HEREDOC delimiter
-                let delimiter_start = start.get(2).unwrap().as_str();
-
-                // Where the "body" starts for the HEREDOC block
-                let body_start = start.get(0).unwrap().end();
-
-                // Look through all of the ends to find a matching language
-                for end in ends.iter() {
-                    // 1. This must appear after the start
-                    let body_end = end.get(0).unwrap().start();
-                    if body_end < body_start {
-                        continue;
-                    }
-
-                    // The languages must match otherwise we haven't found the end
-                    let delimiter_end = end.get(1).unwrap().as_str();
-                    if delimiter_end != delimiter_start {
-                        continue;
-                    }
-
-                    let body = &content_as_str[body_start..body_end];
-                    let replaced =
-                        pre_process_input(body.as_bytes().to_vec(), &lang.to_ascii_lowercase());
-
-                    result.replace_range(body_start..body_end, replaced);
-                    break;
-                }
-            }
-        }
-
-        // Ruby extraction
-        while cursor.pos < len {
-            match cursor.curr() {
-                b'"' => {
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // Escaped character, skip ahead to the next character
-                            b'\\' => cursor.advance_twice(),
-
-                            // End of the string
-                            b'"' => break,
-
-                            // Everything else is valid
-                            _ => cursor.advance(),
-                        };
-                    }
-
-                    cursor.advance();
-                    continue;
-                }
-
-                b'\'' => {
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // Escaped character, skip ahead to the next character
-                            b'\\' => cursor.advance_twice(),
-
-                            // End of the string
-                            b'\'' => break,
-
-                            // Everything else is valid
-                            _ => cursor.advance(),
-                        };
-                    }
-
-                    cursor.advance();
-                    continue;
-                }
-
-                // Replace comments in Ruby files
-                //
-                // Except for strict locals, these are defined in a `<%# locals: … %>`. Checking if
-                // the comment is preceded by a `%` should be enough without having to perform more
-                // parsing logic. Worst case we _do_ scan a few comments.
-                //
-                // We also want to skip interpolation syntax, which look like `#{…}`.
-                b'#' if !matches!(cursor.prev(), b'%') && !matches!(cursor.next(), b'{') => {
-                    result[cursor.pos] = b' ';
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // End of the comment
-                            b'\n' => break,
-
-                            // Everything else is part of the comment and replaced
-                            _ => {
-                                result[cursor.pos] = b' ';
-                                cursor.advance();
-                            }
-                        };
-                    }
-
-                    cursor.advance();
-                    continue;
-                }
-
-                _ => {}
-            }
-
-            // Looking for `%w`, `%W`, or `%p`
-            if cursor.curr() != b'%' || !matches!(cursor.next(), b'w' | b'W' | b'p') {
-                cursor.advance();
-                continue;
-            }
-
-            // A `%` that follows a value is a modulo operation, not a percent literal. E.g.: the
-            // `50%w` in `hit rate 50%w.`
-            if cursor.prev().is_ascii_alphanumeric()
-                || matches!(cursor.prev(), b'_' | b')' | b']' | b'}')
-            {
-                cursor.advance();
-                continue;
-            }
-
-            cursor.advance_twice();
-
-            // Boundary character
-            let boundary = match cursor.curr() {
-                b'[' => b']',
-                b'(' => b')',
-                b'{' => b'}',
-                b'<' => b'>',
-                b' ' => b'\n',
-
-                // Any other ASCII punctuation can be used as a custom delimiter
-                c if c.is_ascii_punctuation() => c,
-
-                // Everything else is not a valid delimiter
-                _ => {
-                    cursor.advance();
-                    continue;
-                }
-            };
-
-            bracket_stack.reset();
-
-            // Replace the current character with a space
-            result[cursor.pos] = b' ';
-
-            // Skip the boundary character
-            cursor.advance();
-
-            while cursor.pos < len {
-                match cursor.curr() {
-                    // Skip escaped characters, unless the backslash is the delimiter itself
-                    b'\\' if boundary != b'\\' => {
-                        // Use backslash to embed spaces in the strings.
-                        if cursor.next() == b' ' {
-                            result[cursor.pos] = b' ';
-                        }
-
-                        cursor.advance();
-                    }
-
-                    // Start of a nested bracket
-                    b'[' | b'(' | b'{' => {
-                        bracket_stack.push(cursor.curr());
-                    }
-
-                    // Start of a nested `<…>`, which Ruby allows inside a `%w<…>` literal
-                    b'<' if boundary == b'>' => {
-                        bracket_stack.push(cursor.curr());
-                    }
-
-                    // End of a nested bracket
-                    b']' | b')' | b'}' if !bracket_stack.is_empty() => {
-                        if !bracket_stack.pop(cursor.curr()) {
-                            // Unbalanced
-                            cursor.advance();
-                        }
-                    }
-
-                    // End of a nested `<…>`
-                    b'>' if boundary == b'>' && !bracket_stack.is_empty() => {
-                        if !bracket_stack.pop(cursor.curr()) {
-                            // Unbalanced
-                            cursor.advance();
-                        }
-                    }
-
-                    // End of the pattern, replace the boundary character with a space
-                    _ if cursor.curr() == boundary => {
-                        if boundary != b'\n' {
-                            result[cursor.pos] = b' ';
-                        }
-
-                        break;
-                    }
-
-                    // Everything else is valid
-                    _ => {}
-                }
-
-                cursor.advance();
-            }
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Ruby;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_ruby_pre_processor() {
-        for (input, expected) in [
-            // %w[…]
-            ("%w[flex px-2.5]", "%w flex px-2.5 "),
-            (
-                "%w[flex data-[state=pending]:bg-[#0088cc] flex-col]",
-                "%w flex data-[state=pending]:bg-[#0088cc] flex-col ",
-            ),
-            // %w{…}
-            ("%w{flex px-2.5}", "%w flex px-2.5 "),
-            (
-                "%w{flex data-[state=pending]:bg-(--my-color) flex-col}",
-                "%w flex data-[state=pending]:bg-(--my-color) flex-col ",
-            ),
-            // %w(…)
-            ("%w(flex px-2.5)", "%w flex px-2.5 "),
-            (
-                "%w(flex data-[state=pending]:bg-(--my-color) flex-col)",
-                "%w flex data-[state=pending]:bg-(--my-color) flex-col ",
-            ),
-            // %w<…>
-            ("%w<flex px-2.5>", "%w flex px-2.5 "),
-            (
-                "%w<flex data-[state=pending]:bg-(--my-color) flex-col>",
-                "%w flex data-[state=pending]:bg-(--my-color) flex-col ",
-            ),
-            // Nested `<…>` does not end the literal
-            ("%w<flex <nested> px-2.5>", "%w flex <nested> px-2.5 "),
-            // %w|…|, %w:…:, %w!…!
-            ("%w|flex px-2.5|", "%w flex px-2.5 "),
-            ("%w:flex px-2.5:", "%w flex px-2.5 "),
-            ("%w!flex px-2.5!", "%w flex px-2.5 "),
-            (r#"%w\flex px-2.5\"#, r#"%w flex px-2.5 "#),
-            // A `%` that follows a value is a modulo operation, not a percent literal
-            (
-                "hit rate 50%w.\n%w[flex px-2.5]",
-                "hit rate 50%w.\n%w flex px-2.5 ",
-            ),
-
-            // %w …\n
-            ("%w flex px-2.5\n", "%w flex px-2.5\n"),
-
-            // Use backslash to embed spaces in the strings.
-            (r#"%w[foo\ bar baz\ bat]"#, r#"%w foo  bar baz  bat "#),
-            (r#"%W[foo\ bar baz\ bat]"#, r#"%W foo  bar baz  bat "#),
-
-            // The nested delimiters evaluated to a flat array of strings
-            // (not nested array).
-            (r#"%w[foo[bar baz]qux]"#, r#"%w foo[bar baz]qux "#),
-
-            (
-              "# test\n# test\n# {ActiveRecord::Base#save!}[rdoc-ref:Persistence#save!]\n%w[flex px-2.5]",
-              "      \n      \n                                                        \n%w flex px-2.5 "
-            ),
-
-            (r#""foo # bar""#, r#""foo # bar""#),
-            (r#"'foo # bar'"#, r#"'foo # bar'"#),
-            (
-              r#"def call = tag.span "Foo", class: %w[rounded-full h-0.75 w-0.75]"#,
-              r#"def call = tag.span "Foo", class: %w rounded-full h-0.75 w-0.75 "#
-            ),
-
-            (r#"%w[foo ' bar]"#, r#"%w foo ' bar "#),
-            (r#"%w[foo " bar]"#, r#"%w foo " bar "#),
-            (r#"%W[foo ' bar]"#, r#"%W foo ' bar "#),
-            (r#"%W[foo " bar]"#, r#"%W foo " bar "#),
-
-            (r#"%p foo ' bar "#, r#"%p foo ' bar "#),
-            (r#"%p foo " bar "#, r#"%p foo " bar "#),
-
-            (
-              "%p has a ' quote\n# this should be removed\n%p has a ' quote",
-              "%p has a ' quote\n                        \n%p has a ' quote"
-            ),
-            (
-              "%p has a \" quote\n# this should be removed\n%p has a \" quote",
-              "%p has a \" quote\n                        \n%p has a \" quote"
-            ),
-
-            (
-              "%w#this text is kept# # this text is not",
-              "%w this text is kept                    ",
-            ),
-        ] {
-            Ruby::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_ruby_extraction() {
-        for (input, expected) in [
-            // %w[…]
-            ("%w[flex px-2.5]", vec!["flex", "px-2.5"]),
-            ("%w[px-2.5 flex]", vec!["flex", "px-2.5"]),
-            ("%w[2xl:flex]", vec!["2xl:flex"]),
-            (
-                "%w[flex data-[state=pending]:bg-[#0088cc] flex-col]",
-                vec!["flex", "data-[state=pending]:bg-[#0088cc]", "flex-col"],
-            ),
-            // %w{…}
-            ("%w{flex px-2.5}", vec!["flex", "px-2.5"]),
-            ("%w{px-2.5 flex}", vec!["flex", "px-2.5"]),
-            ("%w{2xl:flex}", vec!["2xl:flex"]),
-            (
-                "%w{flex data-[state=pending]:bg-(--my-color) flex-col}",
-                vec!["flex", "data-[state=pending]:bg-(--my-color)", "flex-col"],
-            ),
-            // %w(…)
-            ("%w(flex px-2.5)", vec!["flex", "px-2.5"]),
-            ("%w(px-2.5 flex)", vec!["flex", "px-2.5"]),
-            ("%w(2xl:flex)", vec!["2xl:flex"]),
-            (
-                "%w(flex data-[state=pending]:bg-(--my-color) flex-col)",
-                vec!["flex", "data-[state=pending]:bg-(--my-color)", "flex-col"],
-            ),
-            // %w<…>
-            ("%w<flex px-2.5>", vec!["flex", "px-2.5"]),
-            ("%w<px-2.5 flex>", vec!["flex", "px-2.5"]),
-            ("%w<2xl:flex>", vec!["2xl:flex"]),
-            (
-                "%w<flex data-[state=pending]:bg-(--my-color) flex-col>",
-                vec!["flex", "data-[state=pending]:bg-(--my-color)", "flex-col"],
-            ),
-            // Nested `<…>` does not end the literal
-            ("%w<flex <nested> px-2.5>", vec!["flex", "px-2.5"]),
-            // %w|…|, %w:…:, %w!…!
-            ("%w|flex px-2.5|", vec!["flex", "px-2.5"]),
-            ("%w:flex px-2.5:", vec!["flex", "px-2.5"]),
-            ("%w!flex px-2.5!", vec!["flex", "px-2.5"]),
-
-            (
-              "# test\n# test\n# {ActiveRecord::Base#save!}[rdoc-ref:Persistence#save!]\n%w[flex px-2.5]",
-              vec!["flex", "px-2.5"],
-            ),
-
-            (r#""foo # bar""#, vec!["foo", "bar"]),
-            (r#"'foo # bar'"#, vec!["foo", "bar"]),
-
-            (r#"%w[foo ' bar]"#, vec!["foo", "bar"]),
-        ] {
-            Ruby::test_extract_contains(input, expected);
-        }
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17334
-    #[test]
-    fn test_embedded_slim_extraction() {
-        let input = r#"
-            class QweComponent < ApplicationComponent
-              slim_template <<~SLIM
-                button.rounded-full.bg-red-500
-                  | Some text
-                button.rounded-full(
-                  class="flex"
-                )
-                  | Some text
-              SLIM
-            end
-        "#;
-
-        Ruby::test_extract_contains(input, vec!["rounded-full", "bg-red-500", "flex"]);
-
-        // Embedded Svelte just to verify that we properly pick up the `{x}_template`
-        let input = r#"
-            class QweComponent < ApplicationComponent
-              svelte_template <<~HTML
-                  <div class:flex="true"></div>
-              HTML
-            end
-        "#;
-
-        Ruby::test_extract_contains(input, vec!["flex"]);
-
-        // Together in the same file
-        let input = r#"
-            class QweComponent < ApplicationComponent
-              slim_template <<~SLIM
-                button.z-1.z-2
-                  | Some text
-              SLIM
-            end
-
-            class QweComponent < ApplicationComponent
-              svelte_template <<~HTML
-                <div class:z-3="true"></div>
-              HTML
-            end
-        "#;
-        Ruby::test_extract_contains(input, vec!["z-1", "z-2", "z-3"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/19728
-    #[test]
-    fn test_interpolated_expressions() {
-        let input = r#"
-            def width_class(width = nil)
-              <<~STYLE_CLASS
-                #{width || 'w-100'}
-              STYLE_CLASS
-            end
-        "#;
-
-        Ruby::test_extract_contains(input, vec!["w-100"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/19239
-    #[test]
-    fn test_skip_comments() {
-        let input = r#"
-          # From activerecord-8.1.1/lib/active_record/errors.rb:147
-          # Rails uses RDoc cross-reference syntax in inline documentation:
-          # {ActiveRecord::Base#save!}[rdoc-ref:Persistence#save!]
-        "#;
-
-        // Nothing should be extracted from comments, so expect an empty array.
-        Ruby::test_extract_exact(input, vec![]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/19481
-    #[test]
-    fn test_strict_locals() {
-        // Strict locals are defined in a `<%# locals: … %>`, but the `#` looks like a comment
-        // which we should not ignore in this case.
-        let input = r#"
-          <%# locals: (css: "text-amber-600") %>
-          <% more_css = "text-sky-500" %>
-
-          <p class="text-green-500">
-            In a partial
-          </p>
-
-          <p class="<%= css %>">
-            In a partial using explicit local variables
-          </p>
-
-          <p class="<%= more_css %>">
-            In a partial using explicit local variables
-          </p>
-        "#;
-
-        Ruby::test_extract_contains(
-            input,
-            vec!["text-amber-600", "text-sky-500", "text-green-500"],
-        );
-    }
-
-    #[test]
-    fn test_invalid_utf8_does_not_panic() {
-        // Invalid UTF-8 sequence: 0x80 is a continuation byte without a leading byte
-        let invalid_utf8: &[u8] = &[0x80, 0x81, 0x82];
-
-        let processor = Ruby::default();
-
-        // Should not panic, just return the input unchanged
-        let result = processor.process(invalid_utf8);
-        assert_eq!(result, invalid_utf8);
-    }
-
-    #[test]
-    fn test_valid_utf8_with_multibyte_chars() {
-        // Test that valid UTF-8 with multi-byte characters (like em-dashes) works
-        let input = "# Comment with em—dash\n%w[flex px-2.5]";
-
-        Ruby::test_extract_contains(input, vec!["flex", "px-2.5"]);
-    }
-}

crates/oxide/src/extractor/pre_processors/rust.rs

@@ -1,238 +0,0 @@
-use crate::extractor::bracket_stack;
-use crate::extractor::cursor;
-use crate::extractor::machine::Machine;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use crate::extractor::variant_machine::VariantMachine;
-use crate::extractor::MachineState;
-use bstr::ByteSlice;
-
-#[derive(Debug, Default)]
-pub struct Rust;
-
-impl PreProcessor for Rust {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        // Leptos support: https://github.com/tailwindlabs/tailwindcss/pull/18093
-        let replaced_content = content
-            .replace(" class:", " class ")
-            .replace("\tclass:", " class ")
-            .replace("\nclass:", " class ");
-
-        if replaced_content.contains_str(b"html!") {
-            self.process_maud_templates(&replaced_content)
-        } else {
-            replaced_content
-        }
-    }
-}
-
-impl Rust {
-    fn process_maud_templates(&self, replaced_content: &[u8]) -> Vec<u8> {
-        let len = replaced_content.len();
-        let mut result = replaced_content.to_vec();
-        let mut cursor = cursor::Cursor::new(replaced_content);
-        let mut bracket_stack = bracket_stack::BracketStack::default();
-
-        while cursor.pos < len {
-            match cursor.curr() {
-                // Escaped character, skip ahead to the next character
-                b'\\' => {
-                    cursor.advance_twice();
-                    continue;
-                }
-
-                // Consume strings as-is
-                b'"' => {
-                    result[cursor.pos] = b' ';
-                    cursor.advance();
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // Escaped character, skip ahead to the next character
-                            b'\\' => cursor.advance_twice(),
-
-                            // End of the string
-                            b'"' => {
-                                result[cursor.pos] = b' ';
-                                break;
-                            }
-
-                            // Everything else is valid
-                            _ => cursor.advance(),
-                        };
-                    }
-                }
-
-                // Only replace `.` with a space if it's not surrounded by numbers. E.g.:
-                //
-                // ```diff
-                // - .flex.items-center
-                // +  flex items-center
-                // ```
-                //
-                // But with numbers, it's allowed:
-                //
-                // ```diff
-                // - px-2.5
-                // + px-2.5
-                // ```
-                b'.' => {
-                    // Don't replace dots with spaces when inside of any type of brackets, because
-                    // this could be part of arbitrary values. E.g.: `bg-[url(https://example.com)]`
-                    //                                                                       ^
-                    if !bracket_stack.is_empty() {
-                        cursor.advance();
-                        continue;
-                    }
-
-                    // If the dot is surrounded by digits, we want to keep it. E.g.: `px-2.5`
-                    // EXCEPT if it's followed by a valid variant that happens to start with a
-                    // digit.
-                    // E.g.: `bg-red-500.2xl:flex`
-                    //                 ^^^
-                    if cursor.prev().is_ascii_digit() && cursor.next().is_ascii_digit() {
-                        let mut next_cursor = cursor.clone();
-                        next_cursor.advance();
-
-                        let mut variant_machine = VariantMachine::default();
-                        if let MachineState::Done(_) = variant_machine.next(&mut next_cursor) {
-                            result[cursor.pos] = b' ';
-                        }
-                    } else {
-                        result[cursor.pos] = b' ';
-                    }
-                }
-
-                b'[' => {
-                    bracket_stack.push(cursor.curr());
-
-                    // Handle `p.flex[condition]`. If there is a `-` before it, it will likely be an
-                    // arbitrary value e.g. `text-[red]`
-                    if !matches!(cursor.prev(), b'-') {
-                        result[cursor.pos] = b' ';
-                    }
-                }
-
-                b']' if !bracket_stack.is_empty() => {
-                    bracket_stack.pop(cursor.curr());
-                }
-
-                // Consume everything else
-                _ => {}
-            };
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Rust;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_leptos_extraction() {
-        for (input, expected) in [
-            // Spaces
-            (
-                "<div class:flex class:px-2.5={condition()}>",
-                "<div class flex class px-2.5={condition()}>",
-            ),
-            // Tabs
-            (
-                "<div\tclass:flex class:px-2.5={condition()}>",
-                "<div class flex class px-2.5={condition()}>",
-            ),
-            // Newlines
-            (
-                "<div\nclass:flex class:px-2.5={condition()}>",
-                "<div class flex class px-2.5={condition()}>",
-            ),
-        ] {
-            Rust::test(input, expected);
-        }
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/18984
-    #[test]
-    fn test_maud_template_extraction() {
-        let input = r#"
-            use maud::{html, Markup};
-
-            pub fn main() -> Markup {
-                html! {
-                    header.px-8.py-4.text-black {
-                        "Hello, world!"
-                    }
-                }
-            }
-        "#;
-
-        Rust::test_extract_contains(input, vec!["px-8", "py-4", "text-black"]);
-
-        // https://maud.lambda.xyz/elements-attributes.html#classes-and-ids-foo-bar
-        let input = r#"
-            html! {
-                input #cannon .big.scary.bright-red type="button" value="Launch Party Cannon";
-            }
-        "#;
-        Rust::test_extract_contains(input, vec!["big", "scary", "bright-red"]);
-
-        let input = r#"
-            html! {
-                div."bg-[#0088cc]" { "Quotes for backticks" }
-            }
-        "#;
-        Rust::test_extract_contains(input, vec!["bg-[#0088cc]"]);
-
-        let input = r#"
-            html! {
-                #main {
-                    "Main content!"
-                    .tip { "Storing food in a refrigerator can make it 20% cooler." }
-                }
-            }
-        "#;
-        Rust::test_extract_contains(input, vec!["tip"]);
-
-        let input = r#"
-            html! {
-                div."bg-[url(https://example.com)]" { "Arbitrary values" }
-            }
-        "#;
-        Rust::test_extract_contains(input, vec!["bg-[url(https://example.com)]"]);
-
-        let input = r#"
-            html! {
-                div.px-4.text-black {
-                    "Some text, with unbalanced brackets ]["
-                }
-                div.px-8.text-white {
-                    "Some more text, with unbalanced brackets ]["
-                }
-            }
-        "#;
-        Rust::test_extract_contains(input, vec!["px-4", "text-black", "px-8", "text-white"]);
-
-        let input = r#"html! { \x.px-4.text-black {  } }"#;
-        Rust::test(input, r#"html! { \x px-4 text-black {  } }"#);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/20233
-    #[test]
-    fn test_maud_template_extraction_with_conditional_classes() {
-        let input = r#"
-            use maud::{html, Markup};
-
-            pub fn main() -> Markup {
-                html! {
-                    p.text-black[cuteness > 50] { "Squee!" }
-                }
-            }
-        "#;
-
-        Rust::test_extract_contains(input, vec!["text-black"]);
-    }
-}

crates/oxide/src/extractor/pre_processors/slim.rs

@@ -1,449 +0,0 @@
-use crate::cursor;
-use crate::extractor::bracket_stack::BracketStack;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use crate::extractor::variant_machine::VariantMachine;
-
-#[derive(Debug, Default)]
-pub struct Slim;
-
-impl PreProcessor for Slim {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-        let mut bracket_stack = BracketStack::default();
-
-        while cursor.pos < len {
-            match cursor.curr() {
-                // Only replace `.` with a space if it's not surrounded by numbers. E.g.:
-                //
-                // ```diff
-                // - .flex.items-center
-                // +  flex items-center
-                // ```
-                //
-                // But with numbers, it's allowed:
-                //
-                // ```diff
-                // - px-2.5
-                // + px-2.5
-                // ```
-                b'.' => {
-                    // Don't replace dots with spaces when inside of any type of brackets, because
-                    // this could be part of arbitrary values. E.g.: `bg-[url(https://example.com)]`
-                    //                                                                       ^
-                    if !bracket_stack.is_empty() {
-                        cursor.advance();
-                        continue;
-                    }
-
-                    // If the dot is surrounded by digits, we want to keep it. E.g.: `px-2.5`
-                    // EXCEPT if it's followed by a valid variant that happens to start with a
-                    // digit.
-                    // E.g.: `bg-red-500.2xl:flex`
-                    //                 ^^^
-                    if cursor.prev().is_ascii_digit() && cursor.next().is_ascii_digit() {
-                        let mut next_cursor = cursor.clone();
-                        next_cursor.advance();
-
-                        let mut variant_machine = VariantMachine::default();
-                        if let MachineState::Done(_) = variant_machine.next(&mut next_cursor) {
-                            result[cursor.pos] = b' ';
-                        }
-                    } else {
-                        result[cursor.pos] = b' ';
-                    }
-                }
-
-                // Handle Ruby syntax with `%w[]` arrays embedded in Slim directly.
-                //
-                // E.g.:
-                //
-                // ```
-                // div [
-                //   class=%w[bg-blue-500 w-10 h-10]
-                // ]
-                // ```
-                //
-                // A `%` that follows a value is not a percent literal. E.g.: the `50%w` in
-                // `hit rate 50%w.`
-                b'%' if matches!(cursor.next(), b'w' | b'W')
-                    && !cursor.prev().is_ascii_alphanumeric()
-                    && !matches!(cursor.prev(), b'_' | b')' | b']' | b'}') =>
-                {
-                    // Boundary characters
-                    let (open, close) = match cursor.input.get(cursor.pos + 2) {
-                        Some(b'[') => (b'[', b']'),
-                        Some(b'(') => (b'(', b')'),
-                        Some(b'{') => (b'{', b'}'),
-                        Some(b'<') => (b'<', b'>'),
-
-                        // Any other ASCII punctuation can be used as a custom delimiter
-                        Some(&c) if c.is_ascii_punctuation() => (c, c),
-
-                        // Everything else is not a valid delimiter
-                        _ => {
-                            cursor.advance();
-                            continue;
-                        }
-                    };
-
-                    result[cursor.pos] = b' '; // Replace `%`
-                    cursor.advance();
-                    result[cursor.pos] = b' '; // Replace `w`
-                    cursor.advance();
-                    result[cursor.pos] = b' '; // Replace the opening delimiter
-                    cursor.advance();
-
-                    // Paired delimiters can be nested as long as they are balanced. E.g.:
-                    // `%w[foo[bar]baz]` produces a flat array.
-                    let mut depth = 1_usize;
-
-                    while cursor.pos < len {
-                        match cursor.curr() {
-                            // Skip escaped characters, unless the backslash is the delimiter
-                            // itself
-                            b'\\' if close != b'\\' => {
-                                // Use backslash to embed spaces in the strings.
-                                if cursor.next() == b' ' {
-                                    result[cursor.pos] = b' ';
-                                }
-
-                                cursor.advance();
-                            }
-
-                            // Start of a nested delimiter pair
-                            c if c == open && open != close => depth += 1,
-
-                            // Closing delimiter
-                            c if c == close => {
-                                depth -= 1;
-
-                                // End of the literal, replace the closing delimiter with a space
-                                if depth == 0 {
-                                    result[cursor.pos] = b' ';
-                                    break;
-                                }
-                            }
-
-                            // Everything else is valid content
-                            _ => {}
-                        }
-
-                        cursor.advance();
-                    }
-                }
-
-                // Any `[` preceded by an alphanumeric value will not be part of a candidate.
-                //
-                // E.g.:
-                //
-                // ```
-                //  .text-xl.text-red-600[
-                //                       ^ not part of the `text-red-600` candidate
-                //    data-foo="bar"
-                //  ]
-                //    | This line should be red
-                // ```
-                //
-                // We know that `-[` is valid for an arbitrary value and that `:[` is valid as a
-                // variant. However `[color:red]` is also valid, in this case `[` will be preceded
-                // by nothing or a boundary character.
-                // Instead of listing all boundary characters, let's list the characters we know
-                // will be invalid instead.
-                b'[' if bracket_stack.is_empty()
-                    && matches!(cursor.prev(), b'a'..=b'z' | b'A'..=b'Z' | b'0'..=b'9') =>
-                {
-                    result[cursor.pos] = b' ';
-                    bracket_stack.push(cursor.curr());
-                }
-
-                // In Slim the class name shorthand can be followed by a parenthesis. E.g.:
-                //
-                // ```slim
-                // body.border-t-4.p-8(attr=value)
-                //                    ^ Not part of the p-8 class
-                // ```
-                //
-                // This means that we need to replace all these `(` and `)` with spaces to make
-                // sure that we can extract the `p-8`.
-                //
-                // However, we also need to make sure that we keep the parens that are part of the
-                // utility class. E.g.: `bg-(--my-color)`.
-                b'(' if bracket_stack.is_empty() && !matches!(cursor.prev(), b'-' | b'/') => {
-                    result[cursor.pos] = b' ';
-                    bracket_stack.push(cursor.curr());
-                }
-
-                b'(' | b'[' | b'{' => {
-                    bracket_stack.push(cursor.curr());
-                }
-
-                b')' | b']' | b'}' if !bracket_stack.is_empty() => {
-                    bracket_stack.pop(cursor.curr());
-                }
-
-                // Consume everything else
-                _ => {}
-            };
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Slim;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_slim_pre_processor() {
-        for (input, expected) in [
-            // Convert dots to spaces
-            ("div.flex.bg-red-500", "div flex bg-red-500"),
-            (".flex.bg-red-500", " flex bg-red-500"),
-            (".bg-red-500.2xl:flex", " bg-red-500 2xl:flex"),
-            (
-                ".bg-red-500.2xl:flex.bg-green-200.3xl:flex",
-                " bg-red-500 2xl:flex bg-green-200 3xl:flex",
-            ),
-            // Keep dots in strings
-            (r#"div(class="px-2.5")"#, r#"div class="px-2.5")"#),
-            // Replace top-level `(a-z0-9)[` with `$1 `. E.g.: `.flex[x]` -> `.flex x]`
-            (".text-xl.text-red-600[", " text-xl text-red-600 "),
-            // But keep important brackets:
-            (".text-[#0088cc]", " text-[#0088cc]"),
-            // Arbitrary value and arbitrary modifier
-            (
-                ".text-[#0088cc].bg-[#0088cc]/[20%]",
-                " text-[#0088cc] bg-[#0088cc]/[20%]",
-            ),
-            // Start of arbitrary property
-            ("[color:red]", "[color:red]"),
-            // Arbitrary container query
-            ("@[320px]:flex", "@[320px]:flex"),
-            // Nested brackets
-            (
-                "bg-[url(https://example.com/?q=[1,2])]",
-                "bg-[url(https://example.com/?q=[1,2])]",
-            ),
-            // Nested brackets, with "invalid" syntax but valid due to nesting
-            ("content-['50[]']", "content-['50[]']"),
-            // Escaped string
-            ("content-['a\'b\'c\'']", "content-['a\'b\'c\'']"),
-            // Classes in HTML attributes
-            ("<div id=\"px-2.5\"></div>", "<div id=\"px-2.5\"></div>"),
-            (
-                "<div id=\"px-2.5 bg-red-500 2xl:flex bg-green-200 3xl:flex\"></div>",
-                "<div id=\"px-2.5 bg-red-500 2xl:flex bg-green-200 3xl:flex\"></div>",
-            ),
-        ] {
-            Slim::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_nested_slim_syntax() {
-        let input = r#"
-            .text-black[
-              data-controller= ['foo', ('bar' if rand.positive?)].join(' ')
-            ]
-              .bg-green-300
-                | BLACK on GREEN - OK
-
-              .bg-red-300[
-                data-foo= 42
-              ]
-                | Should be BLACK on RED - FAIL
-        "#;
-
-        Slim::test_extract_contains(input, vec!["text-black", "bg-green-300", "bg-red-300"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17081
-    // https://github.com/slim-template/slim?tab=readme-ov-file#verbatim-text-with-trailing-white-space-
-    #[test]
-    fn test_single_quotes_to_enforce_trailing_whitespace() {
-        let input = r#"
-            div
-              'A single quote enforces trailing white space
-              = 1234
-
-            .text-red-500.text-3xl
-              | This text should be red
-        "#;
-
-        let expected = r#"
-            div
-              'A single quote enforces trailing white space
-              = 1234
-
-             text-red-500 text-3xl
-              | This text should be red
-        "#;
-
-        Slim::test(input, expected);
-        Slim::test_extract_contains(input, vec!["text-red-500", "text-3xl"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17277
-    #[test]
-    fn test_class_shorthand_followed_by_parens() {
-        let input = r#"
-              body.border-t-4.p-8(class="\#{body_classes}" data-hotwire-native="\#{hotwire_native_app?}" data-controller="update-time-zone")
-        "#;
-        Slim::test_extract_contains(input, vec!["border-t-4", "p-8"]);
-
-        // Additional test with CSS Variable shorthand syntax in the attribute itself because `(`
-        // and `)` are not valid in the class shorthand version.
-        //
-        // Also included an arbitrary value including `(` and `)` to make sure that we don't
-        // accidentally remove those either.
-        let input = r#"
-              body.p-8(class="bg-(--my-color) bg-(--my-color)/(--my-opacity) bg-[url(https://example.com)]")
-        "#;
-        Slim::test_extract_contains(
-            input,
-            vec![
-                "p-8",
-                "bg-(--my-color)",
-                "bg-(--my-color)/(--my-opacity)",
-                "bg-[url(https://example.com)]",
-            ],
-        );
-
-        // Top-level class shorthand with parens
-        let input = r#"
-            div class="bg-(--my-color) bg-(--my-color)/(--my-opacity)"
-        "#;
-        Slim::test_extract_contains(
-            input,
-            vec!["bg-(--my-color)", "bg-(--my-color)/(--my-opacity)"],
-        );
-    }
-
-    #[test]
-    fn test_strings_only_occur_when_nested() {
-        let input = r#"
-            p.mt-2.text-xl
-              | The quote in the next word, can't be the start of a string
-
-            h3.mt-24.text-center.text-4xl.font-bold.italic
-              | The classes above should be extracted
-        "#;
-
-        Slim::test_extract_contains(
-            input,
-            vec![
-                // First paragraph
-                "mt-2",
-                "text-xl",
-                // second paragraph
-                "mt-24",
-                "text-center",
-                "text-4xl",
-                "font-bold",
-                "italic",
-            ],
-        );
-    }
-
-    #[test]
-    fn test_arbitrary_code_followed_by_classes() {
-        let input = r#"
-            - i < 3
-              .flex.items-center
-        "#;
-        Slim::test_extract_contains(input, vec!["flex", "items-center"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/17542
-    #[test]
-    fn test_embedded_ruby_percent_w_extraction() {
-        let input = r#"
-            div[
-              class=%w[bg-blue-500 w-10 h-10]
-            ]
-            div[
-              class=%w[w-10 bg-green-500 h-10]
-            ]
-        "#;
-
-        let expected = "
-            div \n              class=   bg-blue-500 w-10 h-10 \n            ]
-            div \n              class=   w-10 bg-green-500 h-10 \n            ]
-        ";
-
-        Slim::test(input, expected);
-        Slim::test_extract_contains(input, vec!["bg-blue-500", "bg-green-500", "w-10", "h-10"]);
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/20386
-    #[test]
-    fn test_embedded_ruby_percent_w_delimiters() {
-        for (input, expected) in [
-            // %w<…>, Slim only counts `[({` nesting in attribute values, so the code must be
-            // wrapped in parentheses to contain spaces
-            (
-                "div class=(%w<bg-blue-500 w-10 h-10>)",
-                "div class=    bg-blue-500 w-10 h-10 )",
-            ),
-            // Nested `<…>` does not end the literal
-            (
-                "div class=(%w<flex <nested> px-2.5>)",
-                "div class=    flex <nested> px-2.5 )",
-            ),
-            // Custom delimiters
-            ("div class=(%w|flex px-2.5|)", "div class=    flex px-2.5 )"),
-            ("div class=(%W!flex px-2.5!)", "div class=    flex px-2.5 )"),
-            (
-                "div class=(%w#text-sm leading-6#)",
-                "div class=    text-sm leading-6 )",
-            ),
-            (
-                "div class=(%w=italic tracking-wide=)",
-                "div class=    italic tracking-wide )",
-            ),
-            // Nested paired delimiters stay balanced inside the literal
-            (
-                "div class=(%w[content-['[hello]'] p-4])",
-                "div class=    content-['[hello]'] p-4 )",
-            ),
-            // Escaped spaces embed a space in a single array element
-            (
-                r#"div class=(%w[foo\ bar baz-1])"#,
-                r#"div class=    foo  bar baz-1 )"#,
-            ),
-            // Ruby control line, which is plain Ruby code
-            ("- classes = %w<mt-4 flex>", "- classes =    mt-4 flex "),
-            // A `%` that follows a value is not a percent literal
-            ("| hit rate 50%w.", "| hit rate 50%w "),
-        ] {
-            Slim::test(input, expected);
-        }
-
-        let input = r#"
-            div[
-              class=(%w<bg-blue-500 w-10 h-10>)
-            ]
-            - classes = %w|w-10 bg-green-500 h-10|
-            = tag.div class: %W!px-2.5 flex!
-        "#;
-
-        Slim::test_extract_contains(
-            input,
-            vec![
-                "bg-blue-500",
-                "bg-green-500",
-                "w-10",
-                "h-10",
-                "px-2.5",
-                "flex",
-            ],
-        );
-    }
-}

crates/oxide/src/extractor/pre_processors/svelte.rs

@@ -1,43 +0,0 @@
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use bstr::ByteSlice;
-
-#[derive(Debug, Default)]
-pub struct Svelte;
-
-impl PreProcessor for Svelte {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        content
-            .replace(" class:", " class ")
-            .replace("\tclass:", " class ")
-            .replace("\nclass:", " class ")
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Svelte;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_svelte_pre_processor() {
-        for (input, expected) in [
-            // Spaces
-            (
-                "<div class:flex class:px-2.5={condition()}>",
-                "<div class flex class px-2.5={condition()}>",
-            ),
-            // Tabs
-            (
-                "<div\tclass:flex class:px-2.5={condition()}>",
-                "<div class flex class px-2.5={condition()}>",
-            ),
-            // Newlines
-            (
-                "<div\nclass:flex class:px-2.5={condition()}>",
-                "<div class flex class px-2.5={condition()}>",
-            ),
-        ] {
-            Svelte::test(input, expected);
-        }
-    }
-}

crates/oxide/src/extractor/pre_processors/template_toolkit.rs

@@ -1,52 +0,0 @@
-use crate::cursor;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-#[derive(Debug, Default)]
-pub struct TemplateToolkit;
-
-impl PreProcessor for TemplateToolkit {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-
-        while cursor.pos < len {
-            match (cursor.curr(), cursor.next()) {
-                (b'[', b'%') => result[cursor.pos] = b' ',
-                (b'%', b']') => result[cursor.pos + 1] = b' ',
-                _ => {}
-            }
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::TemplateToolkit;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_template_toolkit_pre_processor() {
-        for (input, expected) in [
-            (
-                "[% IF $is_open %]bg-white/40[% ELSE %]bg-white/10[% END %]",
-                " % IF $is_open % bg-white/40 % ELSE % bg-white/10 % END % ",
-            ),
-            ("[% WRAPPER %]flex[% END %]", " % WRAPPER % flex % END % "),
-        ] {
-            TemplateToolkit::test(input, expected);
-        }
-    }
-
-    #[test]
-    fn test_extraction_between_template_tags_works() {
-        TemplateToolkit::test_extract_contains(
-            r#"<div class="[% IF $is_open %]bg-white/40[% ELSE %]bg-white/10[% END %]"></div>"#,
-            vec!["bg-white/40", "bg-white/10"],
-        );
-    }
-}

crates/oxide/src/extractor/pre_processors/test-fixtures/haml/dst-17051.haml

@@ -1,262 +0,0 @@
-/ https://github.com/tailwindlabs/tailwindcss/pull/17051#issuecomment-2711181352
-- star_styles = "size-[800px] mask mask-star bg-gradient-to-r from-secondary via-cyan-400 to-lime-400"
-  ^^^^^^^^^^^    ^^^^^^^^^^^^ ^^^^ ^^^^^^^^^ ^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^ ^^^^^^^^^^^^ ^^^^^^^^^^^
-- crazy_text_styles = "italic font-black bg-gradient-to-r via-60% to-90% from-orange-500 via-secondary to-primary text-transparent bg-clip-text inline-block py-2"
-  ^^^^^^^^^^^^^^^^^    ^^^^^^ ^^^^^^^^^^ ^^^^^^^^^^^^^^^^ ^^^^^^^ ^^^^^^ ^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^ ^^^^^^^^^^ ^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^ ^^^^^^^^^^^^ ^^^^
-
-.relative
- ^^^^^^^^
-  - # Blurred background star
-  .absolute.left-0.z-0{ class: "-top-[400px] -right-[400px]" }
-   ^^^^^^^^ ^^^^^^ ^^^  ^^^^^   ^^^^^^^^^^^^ ^^^^^^^^^^^^^^
-    .flex.justify-end.blur-3xl
-     ^^^^ ^^^^^^^^^^^ ^^^^^^^^
-      %div{ class: star_styles }
-            ^^^^^  ^^^^^^^^^^^
-
-  .relative.z-10
-   ^^^^^^^^ ^^^^
-    %h1.mt-8.text-center.text-5xl.font-black.tracking-wide.drop-shadow-lg
-        ^^^^ ^^^^^^^^^^^ ^^^^^^^^ ^^^^^^^^^^ ^^^^^^^^^^^^^ ^^^^^^^^^^^^^^
-      %div
-        Components, Guides, and Paradigms
-                            ^^^
-      .md:inline-flex.md:items-center.justify-center
-       ^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^
-        %span.-mr-2
-              ^^^^^
-          for
-          ^^^
-        %span.relative.-rotate-3.hover:-rotate-6.hover:scale-125.transition-transform
-              ^^^^^^^^ ^^^^^^^^^ ^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^
-          %span{ class: crazy_text_styles + " absolute blur-xl" }
-                 ^^^^^  ^^^^^^^^^^^^^^^^^     ^^^^^^^^ ^^^^^^^
-             CRAZY 
-          %span{ class: crazy_text_styles + " drop-shadow-[0_0_1px_#fff]" }
-                 ^^^^^  ^^^^^^^^^^^^^^^^^     ^^^^^^^^^^^^^^^^^^^^^^^^^^
-             CRAZY 
-        %span.-ml-3.md:-ml-1
-              ^^^^^ ^^^^^^^^
-          \-fast Development
-      %div
-        in Ruby on Rails!
-        ^^      ^^
-
-    .mt-16.text-center
-     ^^^^^ ^^^^^^^^^^^
-      = daisy_button "😃 Get Started", css: "btn-primary text-xl",
-        ^^^^^^^^^^^^                   ^^^   ^^^^^^^^^^^ ^^^^^^^
-        right_icon: "arrow-right", target: "_blank",
-        ^^^^^^^^^^   ^^^^^^^^^^^   ^^^^^^
-        href: "https://github.com/profoundry-us/loco_motion#locomotion-components"
-        ^^^^                                                ^^^^^^^^^^^^^^^^^^^^^
-
-    .mt-32.lg:flex.lg:space-x-8
-     ^^^^^ ^^^^^^^ ^^^^^^^^^^^^
-      %div{ class: "md:basis-2/5" }
-            ^^^^^   ^^^^^^^^^^^^
-        %h3.text-4xl.font-bold
-            ^^^^^^^^ ^^^^^^^^^
-          Easy, Flexible Components
-        %p.mt-2.text-xl
-           ^^^^ ^^^^^^^
-          Powered by the fabulous
-                  ^^ ^^^ ^^^^^^^^
-          = succeed ',' do
-            ^^^^^^^     ^^
-            = daisy_link("ViewComponent", "https://viewcomponent.org", target: "_blank")
-                                                                 ^^^   ^^^^^^
-          = succeed ', and' do
-            ^^^^^^^    ^^^  ^^
-            = daisy_link "DaisyUI", "https://daisyui.com/", target: "_blank"
-              ^^^^^^^^^^                                    ^^^^^^
-          = daisy_link "TailwindCSS", "https://tailwindcss.com/", target: "_blank"
-            ^^^^^^^^^^                                            ^^^^^^
-          libraries, our components are designed to be fast, flexible, and easy to
-                     ^^^ ^^^^^^^^^^ ^^^ ^^^^^^^^ ^^ ^^                 ^^^ ^^^^ ^^
-          use <i>directly</i> in Ruby on Rails!
-          ^^^    ^^^^^^^^     ^^      ^^
-
-      = doc_example(css: "mt-8 lg:mt-0 lg:basis-3/5 h-44") do
-                    ^^^   ^^^^ ^^^^^^^ ^^^^^^^^^^^^ ^^^^   ^^
-        .flex.flex-col.sm:flex-row.items-center.gap-4
-         ^^^^ ^^^^^^^^ ^^^^^^^^^^^ ^^^^^^^^^^^^ ^^^^^
-          = daisy_button "Accent Button", css: "btn-accent"
-            ^^^^^^^^^^^^                  ^^^   ^^^^^^^^^^
-          = daisy_tip("Click to Swap") do
-                             ^^        ^^
-            = daisy_swap off: "🌚", on: "🌞", css: "swap-rotate text-4xl"
-              ^^^^^^^^^^ ^^^        ^^        ^^^   ^^^^^^^^^^^ ^^^^^^^^
-          = daisy_badge "Large Badge", css: "badge-secondary badge-lg"
-            ^^^^^^^^^^^                ^^^   ^^^^^^^^^^^^^^^ ^^^^^^^^
-
-
-    .mt-32.xl:flex.xl:flex-row-reverse.xl:items-center
-     ^^^^^ ^^^^^^^ ^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^
-      .text-xl.xl:ml-8
-       ^^^^^^^ ^^^^^^^
-        %h3.text-4xl.font-bold
-            ^^^^^^^^ ^^^^^^^^^
-          Simple, Concise Views
-
-        %p.mt-2
-           ^^^^
-          Utilize
-          = daisy_link("HAML", "https://haml.info/", target: "_blank")
-                                                     ^^^^^^
-          so your views are simple, concise, and easy to understand.
-          ^^ ^^^^ ^^^^^ ^^^                  ^^^ ^^^^ ^^ ^^^^^^^^^^
-
-        %p.mt-2
-           ^^^^
-          No more messy ERB files with all of their closing tags and Ruby wrappers.
-             ^^^^ ^^^^^     ^^^^^ ^^^^ ^^^ ^^ ^^^^^ ^^^^^^^ ^^^^ ^^^      ^^^^^^^^
-          HAML feels more natural to write and reduces file sizes, making your
-               ^^^^^ ^^^^ ^^^^^^^ ^^ ^^^^^ ^^^ ^^^^^^^ ^^^^        ^^^^^^ ^^^^
-          views easier to read and maintain.
-          ^^^^^ ^^^^^^ ^^ ^^^^ ^^^ ^^^^^^^^
-
-        %p.mt-2
-           ^^^^
-          :markdown
-            **PLUS!** You can utilize filters like _Markdown_, CoffeeScript,
-                          ^^^ ^^^^^^^ ^^^^^^^ ^^^^
-            Textile, and many more!
-                     ^^^ ^^^^ ^^^^^
-
-      .mt-8.xl:mt-0
-       ^^^^ ^^^^^^^
-        .flex.flex-col.xl:flex.xl:flex-row.w-full
-         ^^^^ ^^^^^^^^ ^^^^^^^ ^^^^^^^^^^^ ^^^^^^
-          = doc_code(css: "grow", code_css: "xl:pl-2 xl:pr-0 xl:rounded-r-none", language: "erb") do
-                     ^^^   ^^^^   ^^^^^^^^   ^^^^^^^ ^^^^^^^ ^^^^^^^^^^^^^^^^^   ^^^^^^^^   ^^^   ^^
-            :escaped
-              <% # Ruby %>
-
-              <% 5.times do |i| %>
-                   ^^^^^ ^^
-                <% if i.even? %>
-                   ^^ ^
-                  <p class="odd">Number <%= i %></p>
-                     ^^^^^  ^^^             ^
-                <% else %>
-                   ^^^^
-                  <p class="even">Numero <%= i %></p>
-                     ^^^^^  ^^^^             ^
-                <% end %>
-                   ^^^
-              <% end %>
-                 ^^^
-
-          = doc_code(css: "grow mt-8 xl:mt-0", pre_css: "xl:h-full", code_css: "xl:pl-0 xl:pr-2 xl:h-full xl:rounded-l-none") do
-                     ^^^   ^^^^ ^^^^ ^^^^^^^   ^^^^^^^   ^^^^^^^^^   ^^^^^^^^   ^^^^^^^ ^^^^^^^ ^^^^^^^^^ ^^^^^^^^^^^^^^^^^   ^^
-            :escaped
-              - # HAML
-
-              - 5.times do |i|
-                  ^^^^^ ^^
-                - if i.even?
-                  ^^
-                  %p.odd Number \#{i}
-                     ^^^           ^
-                - else
-                  ^^^^
-                  %p.even Numero \#{i}
-                     ^^^^           ^
-
-
-    %h3.mt-32.text-4xl.font-bold
-        ^^^^^ ^^^^^^^^ ^^^^^^^^^
-      Build Your <i>OWN</i> Components
-
-    %p.mt-2.text-xl
-       ^^^^ ^^^^^^^
-      Can't find exactly what you need? No problem! Build your own components
-          ^ ^^^^ ^^^^^^^ ^^^^ ^^^          ^^^^^^^^       ^^^^ ^^^ ^^^^^^^^^^
-      with ease using our simple, flexible, and powerful DSL.
-      ^^^^ ^^^^ ^^^^^ ^^^                   ^^^ ^^^^^^^^
-
-    .mt-8.xl:flex.xl:space-x-8
-     ^^^^ ^^^^^^^ ^^^^^^^^^^^^
-      %div
-        = doc_code(language: "ruby") do
-                   ^^^^^^^^   ^^^^   ^^
-          :escaped
-            # app/components/application_component.rb
-                                                   ^^
-            class ApplicationComponent < LocoMotion::BaseComponent
-            ^^^^^
-              # Add your custom / shared component logic here!
-                    ^^^^ ^^^^^^   ^^^^^^ ^^^^^^^^^ ^^^^^ ^^^^^
-            end
-            ^^^
-
-        = doc_code(language: "haml", css: "mt-8") do
-                   ^^^^^^^^   ^^^^   ^^^   ^^^^   ^^
-          :escaped
-            - # app/components/character_component.html.haml
-            = part(:component) do
-                               ^^
-              = part(:head)
-              = part(:body) do
-                            ^^
-                = content
-                  ^^^^^^^
-              = part(:legs)
-
-      %div.mt-8.xl:mt-0
-           ^^^^ ^^^^^^^
-        = doc_code(language: "ruby") do
-                   ^^^^^^^^   ^^^^   ^^
-          :escaped
-            # app/components/character_component.rb
-                                                 ^^
-            class CharacterComponent < ApplicationComponent
-            ^^^^^
-              define_parts :head, :body, :legs
-              ^^^^^^^^^^^^
-
-              def before_render
-              ^^^ ^^^^^^^^^^^^^
-                set_tag_name(:head, :h1)
-                ^^^^^^^^^^^^
-                add_css(:head, "text-3xl font-bold")
-                ^^^^^^^         ^^^^^^^^ ^^^^^^^^^
-
-                set_tag_name(:body, :p)
-                ^^^^^^^^^^^^
-                add_stimulus_controller(:body, "character-body")
-                ^^^^^^^^^^^^^^^^^^^^^^^         ^^^^^^^^^^^^^^
-                add_css(:body, "text-lg")
-                ^^^^^^^         ^^^^^^^
-
-                set_tag_name(:legs, :footer)
-                ^^^^^^^^^^^^
-                add_css(:legs, "text-sm")
-                ^^^^^^^         ^^^^^^^
-              end
-              ^^^
-            end
-            ^^^
-
-    %h3.mt-24.text-center.text-4xl.font-bold.italic
-        ^^^^^ ^^^^^^^^^^^ ^^^^^^^^ ^^^^^^^^^ ^^^^^^
-      More Coming Soon!
-    %p.mt-2.text-xl.text-center
-       ^^^^ ^^^^^^^ ^^^^^^^^^^^
-      Keen an eye out as we'll be adding more components, guides, and
-           ^^ ^^^ ^^^ ^^ ^^ ^^ ^^ ^^^^^^ ^^^^                     ^^^
-      %br.max-sm:hidden
-          ^^^^^^^^^^^^^
-      suggested gems for you to build amazing Rails apps!
-      ^^^^^^^^^ ^^^^ ^^^ ^^^ ^^ ^^^^^ ^^^^^^^       ^^^^^
-    .mt-4.text-center
-     ^^^^ ^^^^^^^^^^^
-      = daisy_button "😉 Get Started", css: "btn-primary text-xl",
-        ^^^^^^^^^^^^                   ^^^   ^^^^^^^^^^^ ^^^^^^^
-        right_icon: "arrow-right", target: "_blank",
-        ^^^^^^^^^^   ^^^^^^^^^^^   ^^^^^^
-        class: "px-2.5"
-        ^^^^^   ^^^^^^
-        href: "https://github.com/profoundry-us/loco_motion#locomotion-components"
-        ^^^^                                                ^^^^^^^^^^^^^^^^^^^^^

crates/oxide/src/extractor/pre_processors/test-fixtures/haml/dst-17813.haml

@@ -1,30 +0,0 @@
-:ruby
-  - devices_classes = 'size-5 mr-2px'
-    ^^^^^^^^^^^^^^^    ^^^^^^ ^^^^^^
-  - icon_classes = 'w-[12px] h-[12px]'
-    ^^^^^^^^^^^^    ^^^^^^^^ ^^^^^^^^
-!!!
-%html{ lang: 'en' }
-       ^^^^   ^^
-  %head
-    %title Tailwind v4.1.4 + HAML bug
-                    ^^^^^^        ^^^
-
-  -# This is a comment
-          ^^ ^ ^^^^^^^
-
-    A multi-line comment
-      ^^^^^^^^^^ ^^^^^^^
-      With more indentation
-           ^^^^ ^^^^^^^^^^^
-
-    Which can dedent again just fine
-          ^^^ ^^^^^^ ^^^^^ ^^^^ ^^^^
-
-  %body
-  - icon_classes = 'self-center w-[16px] h-[16px]'
-    ^^^^^^^^^^^^    ^^^^^^^^^^^ ^^^^^^^^ ^^^^^^^^
-    .flex{ class: icon_classes }
-     ^^^^  ^^^^^  ^^^^^^^^^^^^
-    .flex{ class: devices_classes }
-     ^^^^  ^^^^^  ^^^^^^^^^^^^^^^

crates/oxide/src/extractor/pre_processors/test-fixtures/haml/src-17051.haml

@@ -1,155 +0,0 @@
-/ https://github.com/tailwindlabs/tailwindcss/pull/17051#issuecomment-2711181352
-- star_styles = "size-[800px] mask mask-star bg-gradient-to-r from-secondary via-cyan-400 to-lime-400"
-- crazy_text_styles = "italic font-black bg-gradient-to-r via-60% to-90% from-orange-500 via-secondary to-primary text-transparent bg-clip-text inline-block py-2"
-
-.relative
-  - # Blurred background star
-  .absolute.left-0.z-0{ class: "-top-[400px] -right-[400px]" }
-    .flex.justify-end.blur-3xl
-      %div{ class: star_styles }
-
-  .relative.z-10
-    %h1.mt-8.text-center.text-5xl.font-black.tracking-wide.drop-shadow-lg
-      %div
-        Components, Guides, and Paradigms
-      .md:inline-flex.md:items-center.justify-center
-        %span.-mr-2
-          for
-        %span.relative.-rotate-3.hover:-rotate-6.hover:scale-125.transition-transform
-          %span{ class: crazy_text_styles + " absolute blur-xl" }
-             CRAZY 
-          %span{ class: crazy_text_styles + " drop-shadow-[0_0_1px_#fff]" }
-             CRAZY 
-        %span.-ml-3.md:-ml-1
-          \-fast Development
-      %div
-        in Ruby on Rails!
-
-    .mt-16.text-center
-      = daisy_button "😃 Get Started", css: "btn-primary text-xl",
-        right_icon: "arrow-right", target: "_blank",
-        href: "https://github.com/profoundry-us/loco_motion#locomotion-components"
-
-    .mt-32.lg:flex.lg:space-x-8
-      %div{ class: "md:basis-2/5" }
-        %h3.text-4xl.font-bold
-          Easy, Flexible Components
-        %p.mt-2.text-xl
-          Powered by the fabulous
-          = succeed ',' do
-            = daisy_link("ViewComponent", "https://viewcomponent.org", target: "_blank")
-          = succeed ', and' do
-            = daisy_link "DaisyUI", "https://daisyui.com/", target: "_blank"
-          = daisy_link "TailwindCSS", "https://tailwindcss.com/", target: "_blank"
-          libraries, our components are designed to be fast, flexible, and easy to
-          use <i>directly</i> in Ruby on Rails!
-
-      = doc_example(css: "mt-8 lg:mt-0 lg:basis-3/5 h-44") do
-        .flex.flex-col.sm:flex-row.items-center.gap-4
-          = daisy_button "Accent Button", css: "btn-accent"
-          = daisy_tip("Click to Swap") do
-            = daisy_swap off: "🌚", on: "🌞", css: "swap-rotate text-4xl"
-          = daisy_badge "Large Badge", css: "badge-secondary badge-lg"
-
-
-    .mt-32.xl:flex.xl:flex-row-reverse.xl:items-center
-      .text-xl.xl:ml-8
-        %h3.text-4xl.font-bold
-          Simple, Concise Views
-
-        %p.mt-2
-          Utilize
-          = daisy_link("HAML", "https://haml.info/", target: "_blank")
-          so your views are simple, concise, and easy to understand.
-
-        %p.mt-2
-          No more messy ERB files with all of their closing tags and Ruby wrappers.
-          HAML feels more natural to write and reduces file sizes, making your
-          views easier to read and maintain.
-
-        %p.mt-2
-          :markdown
-            **PLUS!** You can utilize filters like _Markdown_, CoffeeScript,
-            Textile, and many more!
-
-      .mt-8.xl:mt-0
-        .flex.flex-col.xl:flex.xl:flex-row.w-full
-          = doc_code(css: "grow", code_css: "xl:pl-2 xl:pr-0 xl:rounded-r-none", language: "erb") do
-            :escaped
-              <% # Ruby %>
-
-              <% 5.times do |i| %>
-                <% if i.even? %>
-                  <p class="odd">Number <%= i %></p>
-                <% else %>
-                  <p class="even">Numero <%= i %></p>
-                <% end %>
-              <% end %>
-
-          = doc_code(css: "grow mt-8 xl:mt-0", pre_css: "xl:h-full", code_css: "xl:pl-0 xl:pr-2 xl:h-full xl:rounded-l-none") do
-            :escaped
-              - # HAML
-
-              - 5.times do |i|
-                - if i.even?
-                  %p.odd Number \#{i}
-                - else
-                  %p.even Numero \#{i}
-
-
-    %h3.mt-32.text-4xl.font-bold
-      Build Your <i>OWN</i> Components
-
-    %p.mt-2.text-xl
-      Can't find exactly what you need? No problem! Build your own components
-      with ease using our simple, flexible, and powerful DSL.
-
-    .mt-8.xl:flex.xl:space-x-8
-      %div
-        = doc_code(language: "ruby") do
-          :escaped
-            # app/components/application_component.rb
-            class ApplicationComponent < LocoMotion::BaseComponent
-              # Add your custom / shared component logic here!
-            end
-
-        = doc_code(language: "haml", css: "mt-8") do
-          :escaped
-            - # app/components/character_component.html.haml
-            = part(:component) do
-              = part(:head)
-              = part(:body) do
-                = content
-              = part(:legs)
-
-      %div.mt-8.xl:mt-0
-        = doc_code(language: "ruby") do
-          :escaped
-            # app/components/character_component.rb
-            class CharacterComponent < ApplicationComponent
-              define_parts :head, :body, :legs
-
-              def before_render
-                set_tag_name(:head, :h1)
-                add_css(:head, "text-3xl font-bold")
-
-                set_tag_name(:body, :p)
-                add_stimulus_controller(:body, "character-body")
-                add_css(:body, "text-lg")
-
-                set_tag_name(:legs, :footer)
-                add_css(:legs, "text-sm")
-              end
-            end
-
-    %h3.mt-24.text-center.text-4xl.font-bold.italic
-      More Coming Soon!
-    %p.mt-2.text-xl.text-center
-      Keen an eye out as we'll be adding more components, guides, and
-      %br.max-sm:hidden
-      suggested gems for you to build amazing Rails apps!
-    .mt-4.text-center
-      = daisy_button "😉 Get Started", css: "btn-primary text-xl",
-        right_icon: "arrow-right", target: "_blank",
-        class: "px-2.5"
-        href: "https://github.com/profoundry-us/loco_motion#locomotion-components"

crates/oxide/src/extractor/pre_processors/test-fixtures/haml/src-17813.haml

@@ -1,19 +0,0 @@
-:ruby
-  - devices_classes = 'size-5 mr-2px'
-  - icon_classes = 'w-[12px] h-[12px]'
-!!!
-%html{ lang: 'en' }
-  %head
-    %title Tailwind v4.1.4 + HAML bug
-
-  -# This is a comment
-
-    A multi-line comment
-      With more indentation
-
-    Which can dedent again just fine
-
-  %body
-  - icon_classes = 'self-center w-[16px] h-[16px]'
-    .flex{ class: icon_classes }
-    .flex{ class: devices_classes }

crates/oxide/src/extractor/pre_processors/twig.rs

@@ -1,179 +0,0 @@
-use crate::cursor;
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-#[derive(Debug, Default)]
-pub struct Twig;
-
-impl PreProcessor for Twig {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let len = content.len();
-        let mut result = content.to_vec();
-        let mut cursor = cursor::Cursor::new(content);
-        let mut bracket_stack = vec![];
-
-        const ADD_CLASS: &[u8] = b"addClass";
-        const REMOVE_CLASS: &[u8] = b"removeClass";
-
-        while cursor.pos < len {
-            match (!bracket_stack.is_empty(), cursor.curr()) {
-                // addClass(
-                //         ^
-                (false, b'(')
-                    if cursor.pos >= ADD_CLASS.len()
-                        && matches!(
-                            &content[cursor.pos - ADD_CLASS.len()..cursor.pos],
-                            ADD_CLASS
-                        ) =>
-                {
-                    bracket_stack.push(cursor.curr());
-                    result[cursor.pos] = b' ';
-                }
-
-                // removeClass(
-                //            ^
-                (false, b'(')
-                    if cursor.pos >= REMOVE_CLASS.len()
-                        && matches!(
-                            &content[cursor.pos - REMOVE_CLASS.len()..cursor.pos],
-                            REMOVE_CLASS
-                        ) =>
-                {
-                    bracket_stack.push(cursor.curr());
-                    result[cursor.pos] = b' ';
-                }
-
-                (true, b'(') => {
-                    bracket_stack.push(cursor.curr());
-                }
-
-                (true, b')') => {
-                    bracket_stack.pop();
-
-                    if bracket_stack.is_empty() {
-                        result[cursor.pos] = b' ';
-                    }
-                }
-
-                _ => {}
-            }
-
-            cursor.advance();
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Twig;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_twig_pre_processor() {
-        for (input, expected) in [
-            (
-                // Ensure we don't crash when we encounter an `(`
-                "(p-(--value))",
-                "(p-(--value))",
-            ),
-            (
-                // addClass with single argument
-                "addClass(p-(--value))",
-                "addClass p-(--value) ",
-            ),
-            (
-                // addClass with single argument
-                "addClass(m-4 p-8 w-full)",
-                "addClass m-4 p-8 w-full ",
-            ),
-            (
-                // removeClass with single argument
-                "removeClass(p-(--value))",
-                "removeClass p-(--value) ",
-            ),
-            (
-                // removeClass with single argument
-                "removeClass(m-4 p-8 w-full)",
-                "removeClass m-4 p-8 w-full ",
-            ),
-            (
-                // Combined with single arguments
-                "addClass(m-(--value))|removeClass(p-(--value))",
-                "addClass m-(--value) |removeClass p-(--value) ",
-            ),
-        ] {
-            Twig::test(input, expected);
-        }
-    }
-
-    // https://github.com/tailwindlabs/tailwindcss/issues/19458
-    #[test]
-    fn test_extraction_in_add_class_and_remove_class_works() {
-        // Inside normal HTML
-        let input = r#"
-          <div data-loading="addClass(opacity-50)">
-            <!-- -->
-          </div>
-        "#;
-
-        let expected = r#"
-          <div data-loading="addClass opacity-50 ">
-            <!-- -->
-          </div>
-        "#;
-
-        Twig::test(input, expected);
-        Twig::test_extract_contains(input, vec!["opacity-50"]);
-
-        // Inside a component
-        let input = r#"
-            <twig:d:Card
-              {{ ...attributes.defaults({
-                  as: "a",
-                  class: "cursor-pointer bg-base-200 card-sm md:card-md lg:card-lg",
-                  role: "button",
-                  tabindex: "0",
-                  "data-action": "live#$render",
-                  "data-loading": "addAttribute(disabled)",
-                  "data-poll": "delay(60000)|$render",
-                  "data-loading": "addClass(border border-red-500 opacity-75)",
-                 })
-              }}
-            >
-        "#;
-
-        let expected = r#"
-            <twig:d:Card
-              {{ ...attributes.defaults({
-                  as: "a",
-                  class: "cursor-pointer bg-base-200 card-sm md:card-md lg:card-lg",
-                  role: "button",
-                  tabindex: "0",
-                  "data-action": "live#$render",
-                  "data-loading": "addAttribute(disabled)",
-                  "data-poll": "delay(60000)|$render",
-                  "data-loading": "addClass border border-red-500 opacity-75 ",
-                 })
-              }}
-            >
-        "#;
-
-        Twig::test(input, expected);
-        Twig::test_extract_contains(
-            input,
-            vec![
-                // class
-                "cursor-pointer",
-                "bg-base-200",
-                "card-sm",
-                "md:card-md",
-                "lg:card-lg",
-                // data-loading
-                "border",
-                "border-red-500",
-                "opacity-75",
-            ],
-        );
-    }
-}

crates/oxide/src/extractor/pre_processors/vue.rs

@@ -1,60 +0,0 @@
-use crate::extractor::pre_processors::pre_processor::PreProcessor;
-use crate::scanner::pre_process_input;
-use bstr::ByteSlice;
-use regex::Regex;
-use std::sync;
-
-static TEMPLATE_REGEX: sync::LazyLock<Regex> = sync::LazyLock::new(|| {
-    Regex::new(r#"<template lang=['"]([^"']*)['"]>([\s\S]*)<\/template>"#).unwrap()
-});
-
-#[derive(Debug, Default)]
-pub struct Vue;
-
-impl PreProcessor for Vue {
-    fn process(&self, content: &[u8]) -> Vec<u8> {
-        let mut result = content.to_vec();
-
-        // Only process template tags if content is valid UTF-8
-        if let Ok(content_as_str) = std::str::from_utf8(content) {
-            for (_, [lang, body]) in TEMPLATE_REGEX
-                .captures_iter(content_as_str)
-                .map(|c| c.extract())
-            {
-                let replaced = pre_process_input(body.as_bytes().to_vec(), lang);
-                result = result.replace(body, replaced);
-            }
-        }
-
-        result
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::Vue;
-    use crate::extractor::pre_processors::pre_processor::PreProcessor;
-
-    #[test]
-    fn test_vue_template_pug() {
-        let input = r#"
-            <template lang="pug">
-            .bg-neutral-900.text-red-500 This is a test.
-            </template>
-        "#;
-
-        Vue::test_extract_contains(input, vec!["bg-neutral-900", "text-red-500"]);
-    }
-
-    #[test]
-    fn test_invalid_utf8_does_not_panic() {
-        // Invalid UTF-8 sequence: 0x80 is a continuation byte without a leading byte
-        let invalid_utf8: &[u8] = &[0x80, 0x81, 0x82];
-
-        let processor = Vue::default();
-
-        // Should not panic, just return the input unchanged
-        let result = processor.process(invalid_utf8);
-        assert_eq!(result, invalid_utf8);
-    }
-}

crates/oxide/src/extractor/string_machine.rs

@@ -1,138 +0,0 @@
-use crate::cursor;
-use crate::extractor::machine::{Machine, MachineState};
-use classification_macros::ClassifyBytes;
-
-/// Extracts a string (including the quotes) from the input.
-///
-/// Rules:
-///
-/// - The string must start and end with the same quote character.
-/// - The string cannot contain any whitespace characters.
-/// - The string can contain any other character except for the quote character (unless it's escaped).
-/// - Balancing of brackets is not required.
-///
-///
-/// E.g.:
-///
-/// ```text
-/// 'hello_world'
-/// ^^^^^^^^^^^^^
-///
-/// content-['hello_world']
-///          ^^^^^^^^^^^^^
-/// ```
-#[derive(Debug, Default)]
-pub struct StringMachine;
-
-impl Machine for StringMachine {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        if Class::Quote != cursor.curr().into() {
-            return MachineState::Idle;
-        }
-
-        // Start of a string
-        let len = cursor.input.len();
-        let start_pos = cursor.pos;
-        let end_char = cursor.curr();
-
-        cursor.advance();
-
-        while cursor.pos < len {
-            match cursor.curr().into() {
-                Class::Escape => match cursor.next().into() {
-                    // An escaped whitespace character is not allowed
-                    Class::Whitespace => return MachineState::Idle,
-
-                    // An escaped character, skip ahead to the next character
-                    _ => cursor.advance(),
-                },
-
-                // End of the string
-                Class::Quote if cursor.curr() == end_char => return self.done(start_pos, cursor),
-
-                // Any kind of whitespace is not allowed
-                Class::Whitespace => return MachineState::Idle,
-
-                // Everything else is valid
-                _ => {}
-            };
-
-            cursor.advance()
-        }
-
-        MachineState::Idle
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq, ClassifyBytes)]
-enum Class {
-    #[bytes(b'"', b'\'', b'`')]
-    Quote,
-
-    #[bytes(b'\\')]
-    Escape,
-
-    #[bytes(b' ', b'\t', b'\n', b'\r', b'\x0C')]
-    Whitespace,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::StringMachine;
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_string_machine_performance() {
-        let input = r#"There will be a 'string' in this input, even "strings_with_other_quotes_and_\#escaped_characters"  "#.repeat(100);
-
-        StringMachine::test_throughput(100_000, &input);
-        StringMachine::test_duration_once(&input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_string_machine_extraction() {
-        for (input, expected) in [
-            // Simple string
-            ("'foo'", vec!["'foo'"]),
-            // String as part of a candidate
-            ("content-['hello_world']", vec!["'hello_world'"]),
-            // With nested quotes
-            (r#"'"`hello`"'"#, vec![r#"'"`hello`"'"#]),
-            // With escaped opening quote
-            (r#"'Tailwind\'s_parser'"#, vec![r#"'Tailwind\'s_parser'"#]),
-            (
-                r#"'Tailwind\'\'s_parser'"#,
-                vec![r#"'Tailwind\'\'s_parser'"#],
-            ),
-            (
-                r#"'Tailwind\'\'\'s_parser'"#,
-                vec![r#"'Tailwind\'\'\'s_parser'"#],
-            ),
-            (
-                r#"'Tailwind\'\'\'\'s_parser'"#,
-                vec![r#"'Tailwind\'\'\'\'s_parser'"#],
-            ),
-            // Spaces are not allowed
-            ("' hello world '", vec![]),
-            // With unfinished quote
-            ("'unfinished_quote", vec![]),
-            // An escape at the end will never be valid, because it _must_ be followed by the
-            // ending quote.
-            (r#"'escaped_ending_quote\'"#, vec![]),
-            (r#"'escaped_end\"#, vec![]),
-        ] {
-            assert_eq!(StringMachine::test_extract_all(input), expected);
-        }
-    }
-}

crates/oxide/src/extractor/utility_machine.rs

@@ -1,346 +0,0 @@
-use crate::cursor;
-use crate::extractor::arbitrary_property_machine::ArbitraryPropertyMachine;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::modifier_machine::ModifierMachine;
-use crate::extractor::named_utility_machine::NamedUtilityMachine;
-use classification_macros::ClassifyBytes;
-
-#[derive(Debug, Default)]
-pub struct UtilityMachine {
-    /// Start position of the utility
-    start_pos: usize,
-
-    /// Whether the legacy important marker `!` was used
-    legacy_important: bool,
-
-    arbitrary_property_machine: ArbitraryPropertyMachine,
-    named_utility_machine: NamedUtilityMachine,
-    modifier_machine: ModifierMachine,
-}
-
-impl Machine for UtilityMachine {
-    #[inline(always)]
-    fn reset(&mut self) {
-        self.start_pos = 0;
-        self.legacy_important = false;
-    }
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.curr().into() {
-            // LEGACY: Important marker
-            Class::Exclamation => {
-                self.legacy_important = true;
-
-                match cursor.next().into() {
-                    // Start of an arbitrary property
-                    //
-                    // E.g.: `![color:red]`
-                    //        ^
-                    Class::OpenBracket => {
-                        self.start_pos = cursor.pos;
-                        cursor.advance();
-                        self.parse_arbitrary_property(cursor)
-                    }
-
-                    // Start of a named utility
-                    //
-                    // E.g.: `!flex`
-                    //        ^
-                    _ => {
-                        self.start_pos = cursor.pos;
-                        cursor.advance();
-                        self.parse_named_utility(cursor)
-                    }
-                }
-            }
-
-            // Start of an arbitrary property
-            //
-            // E.g.: `[color:red]`
-            //        ^
-            Class::OpenBracket => {
-                self.start_pos = cursor.pos;
-                self.parse_arbitrary_property(cursor)
-            }
-
-            // Everything else might be a named utility. Delegate to the named utility machine
-            // to determine if it's a named utility or not.
-            _ => {
-                self.start_pos = cursor.pos;
-                self.parse_named_utility(cursor)
-            }
-        }
-    }
-}
-
-impl UtilityMachine {
-    fn parse_arbitrary_property(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match self.arbitrary_property_machine.next(cursor) {
-            MachineState::Idle => self.restart(),
-            MachineState::Done(_) => match cursor.next().into() {
-                // End of arbitrary property, but there is a potential modifier.
-                //
-                // E.g.: `[color:#0088cc]/`
-                //                       ^
-                Class::Slash => {
-                    cursor.advance();
-                    self.parse_modifier(cursor)
-                }
-
-                // End of arbitrary property, but there is an `!`.
-                //
-                // E.g.: `[color:#0088cc]!`
-                //                       ^
-                Class::Exclamation => {
-                    cursor.advance();
-                    self.parse_important(cursor)
-                }
-
-                // End of arbitrary property
-                //
-                // E.g.: `[color:#0088cc]`
-                //                      ^
-                _ => self.done(self.start_pos, cursor),
-            },
-        }
-    }
-
-    fn parse_named_utility(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match self.named_utility_machine.next(cursor) {
-            MachineState::Idle => self.restart(),
-            MachineState::Done(_) => match cursor.next().into() {
-                // End of a named utility, but there is a potential modifier.
-                //
-                // E.g.: `bg-red-500/`
-                //                  ^
-                Class::Slash => {
-                    cursor.advance();
-                    self.parse_modifier(cursor)
-                }
-
-                // End of named utility, but there is an `!`.
-                //
-                // E.g.: `bg-red-500!`
-                //                  ^
-                Class::Exclamation => {
-                    cursor.advance();
-                    self.parse_important(cursor)
-                }
-
-                // End of a named utility
-                //
-                // E.g.: `bg-red-500`
-                //                 ^
-                _ => self.done(self.start_pos, cursor),
-            },
-        }
-    }
-
-    fn parse_modifier(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match self.modifier_machine.next(cursor) {
-            MachineState::Idle => self.restart(),
-            MachineState::Done(_) => match cursor.next().into() {
-                // A modifier followed by a modifier is invalid
-                Class::Slash => self.restart(),
-
-                // A modifier followed by the important marker `!`
-                Class::Exclamation => {
-                    cursor.advance();
-                    self.parse_important(cursor)
-                }
-
-                // Everything else is valid
-                _ => self.done(self.start_pos, cursor),
-            },
-        }
-    }
-
-    fn parse_important(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        // Only the `!` is valid if we didn't start with `!`
-        //
-        // E.g.:
-        //
-        // ```
-        // !bg-red-500!
-        //            ^ invalid because of the first `!`
-        // ```
-        if self.legacy_important {
-            return self.restart();
-        }
-
-        self.done(self.start_pos, cursor)
-    }
-}
-
-#[derive(Debug, Clone, Copy, ClassifyBytes)]
-enum Class {
-    #[bytes(b'!')]
-    Exclamation,
-
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b'/')]
-    Slash,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::UtilityMachine;
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_utility_machine_performance() {
-        let input = r#"<button type="button" class="absolute -top-1 -left-1.5 flex items-center justify-center p-1.5 text-gray-400">"#.repeat(100);
-
-        UtilityMachine::test_throughput(100_000, &input);
-        UtilityMachine::test_duration_once(&input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_utility_extraction() {
-        for (input, expected) in [
-            // Simple utility
-            ("flex", vec!["flex"]),
-            // Simple utility with special character(s)
-            ("@container", vec!["@container"]),
-            // Single character utility
-            ("a", vec!["a"]),
-            // Important utilities
-            ("!flex", vec!["!flex"]),
-            ("flex!", vec!["flex!"]),
-            ("flex! block", vec!["flex!", "block"]),
-            // With dashes
-            ("items-center", vec!["items-center"]),
-            ("items--center", vec!["items--center"]),
-            // Inside a string
-            ("'flex'", vec!["flex"]),
-            // Multiple utilities
-            ("flex items-center", vec!["flex", "items-center"]),
-            // Arbitrary property
-            ("[color:red]", vec!["[color:red]"]),
-            ("![color:red]", vec!["![color:red]"]),
-            ("[color:red]!", vec!["[color:red]!"]),
-            ("[color:red]/20", vec!["[color:red]/20"]),
-            ("![color:red]/20", vec!["![color:red]/20"]),
-            ("[color:red]/20!", vec!["[color:red]/20!"]),
-            // Modifiers
-            ("bg-red-500/20", vec!["bg-red-500/20"]),
-            ("bg-red-500/[20%]", vec!["bg-red-500/[20%]"]),
-            (
-                "bg-red-500/(--my-opacity)",
-                vec!["bg-red-500/(--my-opacity)"],
-            ),
-            // Modifiers with important (legacy)
-            ("!bg-red-500/20", vec!["!bg-red-500/20"]),
-            ("!bg-red-500/[20%]", vec!["!bg-red-500/[20%]"]),
-            (
-                "!bg-red-500/(--my-opacity)",
-                vec!["!bg-red-500/(--my-opacity)"],
-            ),
-            // Modifiers with important
-            ("bg-red-500/20!", vec!["bg-red-500/20!"]),
-            ("bg-red-500/[20%]!", vec!["bg-red-500/[20%]!"]),
-            (
-                "bg-red-500/(--my-opacity)!",
-                vec!["bg-red-500/(--my-opacity)!"],
-            ),
-            // Arbitrary value with bracket notation
-            ("bg-[#0088cc]", vec!["bg-[#0088cc]"]),
-            // Arbitrary value with arbitrary property shorthand modifier
-            (
-                "bg-[#0088cc]/(--my-opacity)",
-                vec!["bg-[#0088cc]/(--my-opacity)"],
-            ),
-            // Arbitrary value with CSS property shorthand
-            ("bg-(--my-color)", vec!["bg-(--my-color)"]),
-            // Multiple utilities including arbitrary property shorthand
-            (
-                "bg-(--my-color) flex px-(--my-padding)",
-                vec!["bg-(--my-color)", "flex", "px-(--my-padding)"],
-            ),
-            // --------------------------------------------------------
-
-            // Exceptions:
-            ("bg-red-500/20/20", vec![]),
-            ("bg-[#0088cc]/20/20", vec![]),
-        ] {
-            for (wrapper, additional) in [
-                // No wrapper
-                ("{}", vec![]),
-                // With leading spaces
-                (" {}", vec![]),
-                // With trailing spaces
-                ("{} ", vec![]),
-                // Surrounded by spaces
-                (" {} ", vec![]),
-                // Inside a string
-                ("'{}'", vec![]),
-                // Inside a function call
-                ("fn('{}')", vec![]),
-                // Inside nested function calls
-                ("fn1(fn2('{}'))", vec!["fn1", "fn2"]),
-                // --------------------------
-                //
-                // HTML
-                // Inside a class (on its own)
-                (r#"<div class="{}"></div>"#, vec!["div", "class"]),
-                // Inside a class (first)
-                (r#"<div class="{} foo"></div>"#, vec!["div", "class", "foo"]),
-                // Inside a class (second)
-                (r#"<div class="foo {}"></div>"#, vec!["div", "class", "foo"]),
-                // Inside a class (surrounded)
-                (
-                    r#"<div class="foo {} bar"></div>"#,
-                    vec!["div", "class", "foo", "bar"],
-                ),
-                // --------------------------
-                //
-                // JavaScript
-                // Inside a variable
-                (r#"let classes = '{}';"#, vec!["let", "classes"]),
-                // Inside an object (key)
-                (
-                    r#"let classes = { '{}': true };"#,
-                    vec!["let", "classes", "true"],
-                ),
-                // Inside an object (no spaces, key)
-                (r#"let classes = {'{}':true};"#, vec!["let", "classes"]),
-                // Inside an object (value)
-                (
-                    r#"let classes = { primary: '{}' };"#,
-                    vec!["let", "classes", "primary"],
-                ),
-                // Inside an object (no spaces, value)
-                (
-                    r#"let classes = {primary:'{}'};"#,
-                    vec!["let", "classes", "primary"],
-                ),
-                // Inside an array
-                (r#"let classes = ['{}'];"#, vec!["let", "classes"]),
-            ] {
-                let input = wrapper.replace("{}", input);
-
-                let mut expected = expected.clone();
-                expected.extend(additional);
-                expected.sort();
-
-                let mut actual = UtilityMachine::test_extract_all(&input);
-                actual.sort();
-
-                if actual != expected {
-                    dbg!(&input);
-                }
-                assert_eq!(actual, expected);
-            }
-        }
-    }
-}

crates/oxide/src/extractor/variant_machine.rs

@@ -1,146 +0,0 @@
-use crate::cursor;
-use crate::extractor::arbitrary_value_machine::ArbitraryValueMachine;
-use crate::extractor::machine::{Machine, MachineState};
-use crate::extractor::named_variant_machine::NamedVariantMachine;
-use classification_macros::ClassifyBytes;
-
-#[derive(Debug, Default)]
-pub struct VariantMachine {
-    arbitrary_value_machine: ArbitraryValueMachine,
-    named_variant_machine: NamedVariantMachine,
-}
-
-impl Machine for VariantMachine {
-    #[inline(always)]
-    fn reset(&mut self) {}
-
-    #[inline]
-    fn next(&mut self, cursor: &mut cursor::Cursor<'_>) -> MachineState {
-        match cursor.curr().into() {
-            // Start of an arbitrary variant
-            //
-            // E.g.: `[&:hover]:`
-            //        ^
-            Class::OpenBracket => {
-                let start_pos = cursor.pos;
-                match self.arbitrary_value_machine.next(cursor) {
-                    MachineState::Idle => self.restart(),
-                    MachineState::Done(_) => self.parse_arbitrary_end(start_pos, cursor),
-                }
-            }
-
-            // Start of a named variant
-            _ => {
-                let start_pos = cursor.pos;
-                match self.named_variant_machine.next(cursor) {
-                    MachineState::Idle => self.restart(),
-                    MachineState::Done(_) => self.done(start_pos, cursor),
-                }
-            }
-        }
-    }
-}
-
-impl VariantMachine {
-    #[inline(always)]
-    fn parse_arbitrary_end(
-        &mut self,
-        start_pos: usize,
-        cursor: &mut cursor::Cursor<'_>,
-    ) -> MachineState {
-        match cursor.next().into() {
-            // End of an arbitrary value, must be followed by a `:`
-            //
-            // E.g.: `[&:hover]:`
-            //                 ^
-            Class::Colon => {
-                cursor.advance();
-                self.done(start_pos, cursor)
-            }
-
-            // Everything else is invalid
-            _ => self.restart(),
-        }
-    }
-}
-
-#[derive(Debug, Clone, Copy, ClassifyBytes)]
-enum Class {
-    #[bytes(b'[')]
-    OpenBracket,
-
-    #[bytes(b':')]
-    Colon,
-
-    #[fallback]
-    Other,
-}
-
-#[cfg(test)]
-mod tests {
-    use super::VariantMachine;
-    use crate::extractor::machine::Machine;
-    use pretty_assertions::assert_eq;
-
-    #[test]
-    #[ignore]
-    fn test_variant_machine_performance() {
-        let input = r#"<button class="hover:focus:flex data-[state=pending]:[&.in-progress]:flex supports-(--my-variable):flex group-hover/named:not-has-peer-data-disabled:flex">"#;
-
-        VariantMachine::test_throughput(100_000, input);
-        VariantMachine::test_duration_once(input);
-
-        todo!()
-    }
-
-    #[test]
-    fn test_variant_extraction() {
-        for (input, expected) in [
-            // Simple variant
-            ("hover:flex", vec!["hover:"]),
-            // Single character variant
-            ("a:flex", vec!["a:"]),
-            ("*:flex", vec!["*:"]),
-            // With special characters
-            ("**:flex", vec!["**:"]),
-            // With dashes
-            ("data-disabled:flex", vec!["data-disabled:"]),
-            // Multiple variants
-            ("hover:focus:flex", vec!["hover:", "focus:"]),
-            // Arbitrary variant
-            ("[&:hover:focus]:flex", vec!["[&:hover:focus]:"]),
-            // Arbitrary variant with nested brackets
-            (
-                "[&>[data-slot=icon]:last-child]:",
-                vec!["[&>[data-slot=icon]:last-child]:"],
-            ),
-            (
-                "sm:[&>[data-slot=icon]:last-child]:",
-                vec!["sm:", "[&>[data-slot=icon]:last-child]:"],
-            ),
-            (
-                "[:is(italic):is(underline)]:",
-                vec!["[:is(italic):is(underline)]:"],
-            ),
-            // Modifiers
-            ("group-hover/foo:flex", vec!["group-hover/foo:"]),
-            ("group-hover/[.parent]:flex", vec!["group-hover/[.parent]:"]),
-            // Arbitrary variant with bracket notation
-            ("data-[state=pending]:flex", vec!["data-[state=pending]:"]),
-            // Arbitrary variant with CSS property shorthand
-            ("supports-(--my-color):flex", vec!["supports-(--my-color):"]),
-            // -------------------------------------------------------------
-
-            // Exceptions
-            // Empty arbitrary variant is not allowed
-            ("[]:flex", vec![]),
-            // Named variant must be followed by `:`
-            ("hover", vec![]),
-            // Modifier cannot be followed by another modifier. However, we don't check boundary
-            // characters in this state machine so we will get `bar:`.
-            ("group-hover/foo/bar:flex", vec!["bar:"]),
-        ] {
-            assert_eq!(VariantMachine::test_extract_all(input), expected);
-        }
-    }
-}

crates/oxide/src/fast_skip.rs

@@ -10,7 +10,7 @@ pub fn fast_skip(cursor: &Cursor) -> Option<usize> {
         return None;
     }
 
-    if !cursor.curr().is_ascii_whitespace() {
+    if !cursor.curr.is_ascii_whitespace() {
         return None;
     }
 

crates/oxide/src/fixtures/binary-extensions.txt

@@ -3,6 +3,7 @@
 3g2
 3gp
 7z
+DS_Store
 a
 aac
 adp
@@ -37,7 +38,6 @@ cpio
 cr2
 cur
 dat
-db
 dcm
 deb
 dex
@@ -51,7 +51,6 @@ docx
 dot
 dotm
 dra
-DS_Store
 dsk
 dts
 dtshd
@@ -66,7 +65,6 @@ eol
 eot
 epub
 exe
-exr
 f4v
 fbs
 fh
@@ -79,7 +77,6 @@ fpx
 fst
 fvt
 g3
-geojson
 gh
 gif
 graffle
@@ -88,7 +85,6 @@ gzip
 h261
 h263
 h264
-hdr
 icns
 ico
 ief
@@ -135,12 +131,10 @@ mpg
 mpga
 mxu
 nef
-node
 npx
 numbers
 nupkg
 o
-oa
 odp
 ods
 odt
@@ -157,7 +151,6 @@ pdf
 pea
 pgm
 pic
-plist
 png
 pnm
 pot
@@ -203,13 +196,13 @@ snap
 snk
 so
 sqlite
+sqlite
+sqlite3
 sqlite3
 stl
-storedata
 sub
 suo
 swf
-symbolsarchive
 tar
 tbz
 tbz2
@@ -232,7 +225,6 @@ uvu
 viv
 vob
 war
-wasm
 wav
 wax
 wbmp