Add CI job to auto-update pre-commit dependencies weekly

.cargo/config.toml

@@ -2,9 +2,36 @@
 dev = "run --package ruff_dev --bin ruff_dev"
 benchmark = "bench -p ruff_benchmark --bench linter --bench formatter --"
 
-# statically link the C runtime so the executable does not depend on
-# that shared/dynamic library.
-#
-# See: https://github.com/astral-sh/ruff/issues/11503
-[target.'cfg(all(target_env="msvc", target_os = "windows"))']
-rustflags = ["-C", "target-feature=+crt-static"]
+[target.'cfg(all())']
+rustflags = [
+  # CLIPPY LINT SETTINGS
+  # This is a workaround to configure lints for the entire workspace, pending the ability to configure this via TOML.
+  # See: `https://github.com/rust-lang/cargo/issues/5034`
+  #      `https://github.com/EmbarkStudios/rust-ecosystem/issues/22#issuecomment-947011395`
+  "-Dunsafe_code",
+  "-Wclippy::pedantic",
+  # Allowed pedantic lints
+  "-Wclippy::char_lit_as_u8",
+  "-Aclippy::collapsible_else_if",
+  "-Aclippy::collapsible_if",
+  "-Aclippy::implicit_hasher",
+  "-Aclippy::match_same_arms",
+  "-Aclippy::missing_errors_doc",
+  "-Aclippy::missing_panics_doc",
+  "-Aclippy::module_name_repetitions",
+  "-Aclippy::must_use_candidate",
+  "-Aclippy::similar_names",
+  "-Aclippy::too_many_lines",
+  # Disallowed restriction lints
+  "-Wclippy::print_stdout",
+  "-Wclippy::print_stderr",
+  "-Wclippy::dbg_macro",
+  "-Wclippy::empty_drop",
+  "-Wclippy::empty_structs_with_brackets",
+  "-Wclippy::exit",
+  "-Wclippy::get_unwrap",
+  "-Wclippy::rc_buffer",
+  "-Wclippy::rc_mutex",
+  "-Wclippy::rest_pat_in_fully_bound_structs",
+  "-Wunreachable_pub"
+]

.config/nextest.toml

@@ -1,8 +0,0 @@
-[profile.ci]
-# Print out output for failing tests as soon as they fail, and also at the end
-# of the run (for easy scrollability).
-failure-output = "immediate-final"
-# Do not cancel the test run on the first failure.
-fail-fast = false
-
-status-level = "skip"

.gitattributes

@@ -2,17 +2,6 @@
 
 crates/ruff_linter/resources/test/fixtures/isort/line_ending_crlf.py text eol=crlf
 crates/ruff_linter/resources/test/fixtures/pycodestyle/W605_1.py text eol=crlf
-crates/ruff_linter/resources/test/fixtures/pycodestyle/W391_2.py text eol=crlf
-crates/ruff_linter/resources/test/fixtures/pycodestyle/W391_3.py text eol=crlf
-
-crates/ruff_python_formatter/resources/test/fixtures/ruff/docstring_code_examples_crlf.py text eol=crlf
-crates/ruff_python_formatter/tests/snapshots/format@docstring_code_examples_crlf.py.snap text eol=crlf
-
-crates/ruff_python_parser/resources/invalid/re_lexing/line_continuation_windows_eol.py text eol=crlf
-crates/ruff_python_parser/resources/invalid/re_lex_logical_token_windows_eol.py text eol=crlf
-crates/ruff_python_parser/resources/invalid/re_lex_logical_token_mac_eol.py text eol=cr
-
-crates/ruff_python_parser/resources/inline linguist-generated=true
 
 ruff.schema.json linguist-generated=true text=auto eol=lf
 *.md.snap linguist-language=Markdown

.github/CODEOWNERS

@@ -5,16 +5,5 @@
 # - The '*' pattern is global owners.
 # - Order is important. The last matching pattern has the most precedence.
 
-/crates/ruff_notebook/ @dhruvmanila
-/crates/ruff_formatter/ @MichaReiser
-/crates/ruff_python_formatter/ @MichaReiser
-/crates/ruff_python_parser/ @MichaReiser @dhruvmanila
-
-# flake8-pyi
-/crates/ruff_linter/src/rules/flake8_pyi/ @AlexWaygood
-
-# Script for fuzzing the parser
-/scripts/fuzz-parser/ @AlexWaygood
-
-# red-knot
-/crates/red_knot/ @carljm @MichaReiser
+# Jupyter
+/crates/ruff_linter/src/jupyter/ @dhruvmanila

.github/ISSUE_TEMPLATE.md

@@ -3,8 +3,6 @@ Thank you for taking the time to report an issue! We're glad to have you involve
 
 If you're filing a bug report, please consider including the following information:
 
-* List of keywords you searched for before creating this issue. Write them down here so that others can find this issue more easily and help provide feedback.
-  e.g. "RUF001", "unused variable", "Jupyter notebook"
 * A minimal code snippet that reproduces the bug.
 * The command you invoked (e.g., `ruff /path/to/file.py --fix`), ideally including the `--isolated` flag.
 * The current Ruff settings (any relevant sections from your `pyproject.toml`).

.github/dependabot.yml

@@ -0,0 +1,13 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    labels: ["internal"]
+
+  - package-ecosystem: "cargo"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    labels: ["internal"]

.github/release.yml

@@ -0,0 +1,29 @@
+# https://docs.github.com/en/repositories/releasing-projects-on-github/automatically-generated-release-notes#configuring-automatically-generated-release-notes
+changelog:
+  exclude:
+    labels:
+      - internal
+      - documentation
+  categories:
+    - title: Breaking Changes
+      labels:
+        - breaking
+    - title: Rules
+      labels:
+        - rule
+    - title: Settings
+      labels:
+        - configuration
+        - cli
+    - title: Bug Fixes
+      labels:
+        - bug
+    - title: Formatter
+      labels:
+        - formatter
+    - title: Preview
+      labels:
+        - preview
+    - title: Other Changes
+      labels:
+        - "*"

.github/renovate.json5

@@ -1,86 +0,0 @@
-{
-  $schema: "https://docs.renovatebot.com/renovate-schema.json",
-  dependencyDashboard: true,
-  suppressNotifications: ["prEditedNotification"],
-  extends: ["config:recommended"],
-  labels: ["internal"],
-  schedule: ["before 4am on Monday"],
-  semanticCommits: "disabled",
-  separateMajorMinor: false,
-  prHourlyLimit: 10,
-  enabledManagers: ["github-actions", "pre-commit", "cargo", "pep621", "npm"],
-  cargo: {
-    // See https://docs.renovatebot.com/configuration-options/#rangestrategy
-    rangeStrategy: "update-lockfile",
-  },
-  pep621: {
-    fileMatch: ["^(python|scripts)/.*pyproject\\.toml$"],
-  },
-  npm: {
-    fileMatch: ["^playground/.*package\\.json$"],
-  },
-  "pre-commit": {
-    enabled: true,
-  },
-  packageRules: [
-    {
-      // Group upload/download artifact updates, the versions are dependent
-      groupName: "Artifact GitHub Actions dependencies",
-      matchManagers: ["github-actions"],
-      matchDatasources: ["gitea-tags", "github-tags"],
-      matchPackagePatterns: ["actions/.*-artifact"],
-      description: "Weekly update of artifact-related GitHub Actions dependencies",
-    },
-    {
-      // This package rule disables updates for GitHub runners:
-      // we'd only pin them to a specific version
-      // if there was a deliberate reason to do so
-      groupName: "GitHub runners",
-      matchManagers: ["github-actions"],
-      matchDatasources: ["github-runners"],
-      description: "Disable PRs updating GitHub runners (e.g. 'runs-on: macos-14')",
-      enabled: false,
-    },
-    {
-      // Disable updates of `zip-rs`; intentionally pinned for now due to ownership change
-      // See: https://github.com/astral-sh/uv/issues/3642
-      matchPackagePatterns: ["zip"],
-      matchManagers: ["cargo"],
-      enabled: false,
-    },
-    {
-      groupName: "pre-commit dependencies",
-      matchManagers: ["pre-commit"],
-      description: "Weekly update of pre-commit dependencies",
-    },
-    {
-      groupName: "NPM Development dependencies",
-      matchManagers: ["npm"],
-      matchDepTypes: ["devDependencies"],
-      description: "Weekly update of NPM development dependencies",
-    },
-    {
-      groupName: "Monaco",
-      matchManagers: ["npm"],
-      matchPackagePatterns: ["monaco"],
-      description: "Weekly update of the Monaco editor",
-    },
-    {
-      groupName: "strum",
-      matchManagers: ["cargo"],
-      matchPackagePatterns: ["strum"],
-      description: "Weekly update of strum dependencies",
-    },
-    {
-      groupName: "ESLint",
-      matchManagers: ["npm"],
-      matchPackageNames: ["eslint"],
-      allowedVersions: "<9",
-      description: "Constraint ESLint to version 8 until TypeScript-eslint supports ESLint 9", // https://github.com/typescript-eslint/typescript-eslint/issues/8211
-    },
-  ],
-  vulnerabilityAlerts: {
-    commitMessageSuffix: "",
-    labels: ["internal", "security"],
-  },
-}

.github/workflows/build-docker.yml

@@ -1,68 +0,0 @@
-# Build and publish a Docker image.
-#
-# Assumed to run as a subworkflow of .github/workflows/release.yml; specifically, as a local
-# artifacts job within `cargo-dist`.
-#
-# TODO(charlie): Ideally, the publish step would happen as a publish job within `cargo-dist`, but
-# sharing the built image as an artifact between jobs is challenging.
-name: "[ruff] Build Docker image"
-
-on:
-  workflow_call:
-    inputs:
-      plan:
-        required: true
-        type: string
-  pull_request:
-    paths:
-      - .github/workflows/build-docker.yml
-
-jobs:
-  docker-publish:
-    name: Build Docker image (ghcr.io/astral-sh/ruff)
-    runs-on: ubuntu-latest
-    environment:
-      name: release
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-
-      - uses: docker/setup-buildx-action@v3
-
-      - uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ghcr.io/astral-sh/ruff
-
-      - name: Check tag consistency
-        if: ${{ inputs.plan != '' && !fromJson(inputs.plan).announcement_tag_is_implicit }}
-        run: |
-          version=$(grep "version = " pyproject.toml | sed -e 's/version = "\(.*\)"/\1/g')
-          if [ "${{ fromJson(inputs.plan).announcement_tag }}" != "${version}" ]; then
-            echo "The input tag does not match the version from pyproject.toml:" >&2
-            echo "${{ fromJson(inputs.plan).announcement_tag }}" >&2
-            echo "${version}" >&2
-            exit 1
-          else
-            echo "Releasing ${version}"
-          fi
-
-      - name: "Build and push Docker image"
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          platforms: linux/amd64,linux/arm64
-          # Reuse the builder
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-          push: ${{ inputs.plan != '' && !fromJson(inputs.plan).announcement_tag_is_implicit }}
-          tags: ghcr.io/astral-sh/ruff:latest,ghcr.io/astral-sh/ruff:${{ (inputs.plan != '' && fromJson(inputs.plan).announcement_tag) || 'dry-run' }}
-          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/ci.yaml

@@ -23,35 +23,17 @@ jobs:
     name: "Determine changes"
     runs-on: ubuntu-latest
     outputs:
-      # Flag that is raised when any code that affects parser is changed
-      parser: ${{ steps.changed.outputs.parser_any_changed }}
-      # Flag that is raised when any code that affects linter is changed
       linter: ${{ steps.changed.outputs.linter_any_changed }}
-      # Flag that is raised when any code that affects formatter is changed
       formatter: ${{ steps.changed.outputs.formatter_any_changed }}
-      # Flag that is raised when any code is changed
-      # This is superset of the linter and formatter
-      code: ${{ steps.changed.outputs.code_any_changed }}
     steps:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
-      - uses: tj-actions/changed-files@v44
+      - uses: tj-actions/changed-files@v40
         id: changed
         with:
           files_yaml: |
-            parser:
-              - Cargo.toml
-              - Cargo.lock
-              - crates/ruff_python_trivia/**
-              - crates/ruff_source_file/**
-              - crates/ruff_text_size/**
-              - crates/ruff_python_ast/**
-              - crates/ruff_python_parser/**
-              - scripts/fuzz-parser/**
-              - .github/workflows/ci.yaml
-
             linter:
               - Cargo.toml
               - Cargo.lock
@@ -59,8 +41,8 @@ jobs:
               - "!crates/ruff_python_formatter/**"
               - "!crates/ruff_formatter/**"
               - "!crates/ruff_dev/**"
+              - "!crates/ruff_shrinking/**"
               - scripts/*
-              - python/**
               - .github/workflows/ci.yaml
 
             formatter:
@@ -76,19 +58,11 @@ jobs:
               - crates/ruff_python_parser/**
               - crates/ruff_dev/**
               - scripts/*
-              - python/**
               - .github/workflows/ci.yaml
 
-            code:
-              - "**/*"
-              - "!**/*.md"
-              - "!docs/**"
-              - "!assets/**"
-
   cargo-fmt:
     name: "cargo fmt"
     runs-on: ubuntu-latest
-    timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4
       - name: "Install Rust toolchain"
@@ -98,9 +72,6 @@ jobs:
   cargo-clippy:
     name: "cargo clippy"
     runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
       - name: "Install Rust toolchain"
@@ -109,26 +80,41 @@ jobs:
           rustup target add wasm32-unknown-unknown
       - uses: Swatinem/rust-cache@v2
       - name: "Clippy"
-        run: cargo clippy --workspace --all-targets --all-features --locked -- -D warnings
+        run: cargo clippy --workspace --all-targets --all-features -- -D warnings
       - name: "Clippy (wasm)"
-        run: cargo clippy -p ruff_wasm --target wasm32-unknown-unknown --all-features --locked -- -D warnings
+        run: cargo clippy -p ruff_wasm --target wasm32-unknown-unknown --all-features -- -D warnings
 
   cargo-test-linux:
-    name: "cargo test (linux)"
     runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 20
+    name: "cargo test (linux)"
     steps:
       - uses: actions/checkout@v4
       - name: "Install Rust toolchain"
         run: rustup show
-      - name: "Install mold"
-        uses: rui314/setup-mold@v1
-      - name: "Install cargo nextest"
+      - name: "Install cargo insta"
         uses: taiki-e/install-action@v2
         with:
-          tool: cargo-nextest
+          tool: cargo-insta
+      - uses: Swatinem/rust-cache@v2
+      - name: "Run tests"
+        run: cargo insta test --all --all-features --unreferenced reject
+      # Check for broken links in the documentation.
+      - run: cargo doc --all --no-deps
+        env:
+          # Setting RUSTDOCFLAGS because `cargo doc --check` isn't yet implemented (https://github.com/rust-lang/cargo/issues/10025).
+          RUSTDOCFLAGS: "-D warnings"
+      - uses: actions/upload-artifact@v3
+        with:
+          name: ruff
+          path: target/debug/ruff
+
+  cargo-test-windows:
+    runs-on: windows-latest
+    name: "cargo test (windows)"
+    steps:
+      - uses: actions/checkout@v4
+      - name: "Install Rust toolchain"
+        run: rustup show
       - name: "Install cargo insta"
         uses: taiki-e/install-action@v2
         with:
@@ -136,50 +122,12 @@ jobs:
       - uses: Swatinem/rust-cache@v2
       - name: "Run tests"
         shell: bash
-        env:
-          NEXTEST_PROFILE: "ci"
-        run: cargo insta test --all-features --unreferenced reject --test-runner nextest
-
-      # Check for broken links in the documentation.
-      - run: cargo doc --all --no-deps
-        env:
-          # Setting RUSTDOCFLAGS because `cargo doc --check` isn't yet implemented (https://github.com/rust-lang/cargo/issues/10025).
-          RUSTDOCFLAGS: "-D warnings"
-      - uses: actions/upload-artifact@v4
-        with:
-          name: ruff
-          path: target/debug/ruff
-
-  cargo-test-windows:
-    name: "cargo test (windows)"
-    runs-on: windows-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 20
-    steps:
-      - uses: actions/checkout@v4
-      - name: "Install Rust toolchain"
-        run: rustup show
-      - name: "Install cargo nextest"
-        uses: taiki-e/install-action@v2
-        with:
-          tool: cargo-nextest
-      - uses: Swatinem/rust-cache@v2
-      - name: "Run tests"
-        shell: bash
-        env:
-          # Workaround for <https://github.com/nextest-rs/nextest/issues/1493>.
-          RUSTUP_WINDOWS_PATH_ADD_BIN: 1
-        run: |
-          cargo nextest run --all-features --profile ci
-          cargo test --all-features --doc
+        # We can't reject unreferenced snapshots on windows because flake8_executable can't run on windows
+        run: cargo insta test --all --all-features
 
   cargo-test-wasm:
-    name: "cargo test (wasm)"
     runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 10
+    name: "cargo test (wasm)"
     steps:
       - uses: actions/checkout@v4
       - name: "Install Rust toolchain"
@@ -196,60 +144,9 @@ jobs:
           cd crates/ruff_wasm
           wasm-pack test --node
 
-  cargo-build-release:
-    name: "cargo build (release)"
-    runs-on: macos-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 20
-    steps:
-      - uses: actions/checkout@v4
-      - name: "Install Rust toolchain"
-        run: rustup show
-      - name: "Install mold"
-        uses: rui314/setup-mold@v1
-      - uses: Swatinem/rust-cache@v2
-      - name: "Build"
-        run: cargo build --release --locked
-
-  cargo-build-msrv:
-    name: "cargo build (msrv)"
-    runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 20
-    steps:
-      - uses: actions/checkout@v4
-      - uses: SebRollen/toml-action@v1.2.0
-        id: msrv
-        with:
-          file: "Cargo.toml"
-          field: "workspace.package.rust-version"
-      - name: "Install Rust toolchain"
-        run: rustup default ${{ steps.msrv.outputs.value }}
-      - name: "Install mold"
-        uses: rui314/setup-mold@v1
-      - name: "Install cargo nextest"
-        uses: taiki-e/install-action@v2
-        with:
-          tool: cargo-nextest
-      - name: "Install cargo insta"
-        uses: taiki-e/install-action@v2
-        with:
-          tool: cargo-insta
-      - uses: Swatinem/rust-cache@v2
-      - name: "Run tests"
-        shell: bash
-        env:
-          NEXTEST_PROFILE: "ci"
-        run: cargo +${{ steps.msrv.outputs.value }} insta test --all-features --unreferenced reject --test-runner nextest
-
   cargo-fuzz:
-    name: "cargo fuzz"
     runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 10
+    name: "cargo fuzz"
     steps:
       - uses: actions/checkout@v4
       - name: "Install Rust toolchain"
@@ -257,53 +154,15 @@ jobs:
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: "fuzz -> target"
-      - name: "Install cargo-binstall"
-        uses: cargo-bins/cargo-binstall@main
-        with:
-          tool: cargo-fuzz@0.11.2
       - name: "Install cargo-fuzz"
-        # Download the latest version from quick install and not the github releases because github releases only has MUSL targets.
-        run: cargo binstall cargo-fuzz --force  --disable-strategies crate-meta-data --no-confirm
+        uses: taiki-e/install-action@v2
+        with:
+          tool: cargo-fuzz@0.11
       - run: cargo fuzz build -s none
 
-  fuzz-parser:
-    name: "Fuzz the parser"
-    runs-on: ubuntu-latest
-    needs:
-      - cargo-test-linux
-      - determine_changes
-    if: ${{ needs.determine_changes.outputs.parser == 'true' }}
-    timeout-minutes: 20
-    env:
-      FORCE_COLOR: 1
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-      - name: Install uv
-        run: curl -LsSf https://astral.sh/uv/install.sh | sh
-      - name: Install Python requirements
-        run: uv pip install -r scripts/fuzz-parser/requirements.txt --system
-      - uses: actions/download-artifact@v4
-        name: Download Ruff binary to test
-        id: download-cached-binary
-        with:
-          name: ruff
-          path: ruff-to-test
-      - name: Fuzz
-        run: |
-          # Make executable, since artifact download doesn't preserve this
-          chmod +x ${{ steps.download-cached-binary.outputs.download-path }}/ruff
-
-          python scripts/fuzz-parser/fuzz.py 0-500 --test-executable ${{ steps.download-cached-binary.outputs.download-path }}/ruff
-
   scripts:
     name: "test scripts"
     runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
-    timeout-minutes: 5
     steps:
       - uses: actions/checkout@v4
       - name: "Install Rust toolchain"
@@ -325,35 +184,32 @@ jobs:
       - cargo-test-linux
       - determine_changes
     # Only runs on pull requests, since that is the only we way we can find the base version for comparison.
-    # Ecosystem check needs linter and/or formatter changes.
-    if: ${{ github.event_name == 'pull_request' && needs.determine_changes.outputs.code == 'true' }}
-    timeout-minutes: 20
+    if: github.event_name == 'pull_request'
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         name: Download comparison Ruff binary
         id: ruff-target
         with:
           name: ruff
           path: target/debug
 
-      - uses: dawidd6/action-download-artifact@v6
+      - uses: dawidd6/action-download-artifact@v2
         name: Download baseline Ruff binary
         with:
           name: ruff
           branch: ${{ github.event.pull_request.base.ref }}
-          workflow: "ci.yaml"
           check_artifacts: true
 
       - name: Install ruff-ecosystem
         run: |
           pip install ./python/ruff-ecosystem
 
-      - name: Run `ruff check` stable ecosystem check
+      - name: Run `ruff check` ecosystem check
         if: ${{ needs.determine_changes.outputs.linter == 'true' }}
         run: |
           # Make executable, since artifact download doesn't preserve this
@@ -362,30 +218,13 @@ jobs:
           # Set pipefail to avoid hiding errors with tee
           set -eo pipefail
 
-          ruff-ecosystem check ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff --cache ./checkouts --output-format markdown | tee ecosystem-result-check-stable
+          ruff-ecosystem check ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff --cache ./checkouts --output-format markdown | tee ecosystem-result-check
 
-          cat ecosystem-result-check-stable > $GITHUB_STEP_SUMMARY
-          echo "### Linter (stable)"  > ecosystem-result
-          cat ecosystem-result-check-stable >> ecosystem-result
+          cat ecosystem-result-check > $GITHUB_STEP_SUMMARY
+          cat ecosystem-result-check > ecosystem-result
           echo "" >> ecosystem-result
 
-      - name: Run `ruff check` preview ecosystem check
-        if: ${{ needs.determine_changes.outputs.linter == 'true' }}
-        run: |
-          # Make executable, since artifact download doesn't preserve this
-          chmod +x ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff
-
-          # Set pipefail to avoid hiding errors with tee
-          set -eo pipefail
-
-          ruff-ecosystem check ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff --cache ./checkouts --output-format markdown --force-preview | tee ecosystem-result-check-preview
-
-          cat ecosystem-result-check-preview > $GITHUB_STEP_SUMMARY
-          echo "### Linter (preview)" >> ecosystem-result
-          cat ecosystem-result-check-preview >> ecosystem-result
-          echo "" >> ecosystem-result
-
-      - name: Run `ruff format` stable ecosystem check
+      - name: Run `ruff format` ecosystem check
         if: ${{ needs.determine_changes.outputs.formatter == 'true' }}
         run: |
           # Make executable, since artifact download doesn't preserve this
@@ -394,63 +233,47 @@ jobs:
           # Set pipefail to avoid hiding errors with tee
           set -eo pipefail
 
-          ruff-ecosystem format ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff --cache ./checkouts --output-format markdown | tee ecosystem-result-format-stable
+          ruff-ecosystem format ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff --cache ./checkouts --output-format markdown | tee ecosystem-result-format
 
-          cat ecosystem-result-format-stable > $GITHUB_STEP_SUMMARY
-          echo "### Formatter (stable)" >> ecosystem-result
-          cat ecosystem-result-format-stable >> ecosystem-result
-          echo "" >> ecosystem-result
-
-      - name: Run `ruff format` preview ecosystem check
-        if: ${{ needs.determine_changes.outputs.formatter == 'true' }}
-        run: |
-          # Make executable, since artifact download doesn't preserve this
-          chmod +x ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff
-
-          # Set pipefail to avoid hiding errors with tee
-          set -eo pipefail
-
-          ruff-ecosystem format ./ruff ${{ steps.ruff-target.outputs.download-path }}/ruff --cache ./checkouts --output-format markdown --force-preview | tee ecosystem-result-format-preview
-
-          cat ecosystem-result-format-preview > $GITHUB_STEP_SUMMARY
-          echo "### Formatter (preview)" >> ecosystem-result
-          cat ecosystem-result-format-preview >> ecosystem-result
-          echo "" >> ecosystem-result
+          cat ecosystem-result-format > $GITHUB_STEP_SUMMARY
+          cat ecosystem-result-format >> ecosystem-result
 
       - name: Export pull request number
         run: |
           echo ${{ github.event.number }} > pr-number
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v3
         name: Upload PR Number
         with:
           name: pr-number
           path: pr-number
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v3
         name: Upload Results
         with:
           name: ecosystem-result
           path: ecosystem-result
 
-  cargo-shear:
-    name: "cargo shear"
+  cargo-udeps:
+    name: "cargo udeps"
     runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
     steps:
       - uses: actions/checkout@v4
-      - uses: cargo-bins/cargo-binstall@main
-      - run: cargo binstall --no-confirm cargo-shear
-      - run: cargo shear
+      - name: "Install nightly Rust toolchain"
+        # Only pinned to make caching work, update freely
+        run: rustup toolchain install nightly-2023-10-15
+      - uses: Swatinem/rust-cache@v2
+      - name: "Install cargo-udeps"
+        uses: taiki-e/install-action@cargo-udeps
+      - name: "Run cargo-udeps"
+        run: cargo +nightly-2023-10-15 udeps
 
   python-package:
     name: "python package"
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           architecture: x64
@@ -472,10 +295,9 @@ jobs:
   pre-commit:
     name: "pre-commit"
     runs-on: ubuntu-latest
-    timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: "Install Rust toolchain"
@@ -484,7 +306,7 @@ jobs:
       - name: "Install pre-commit"
         run: pip install pre-commit
       - name: "Cache pre-commit"
-        uses: actions/cache@v4
+        uses: actions/cache@v3
         with:
           path: ~/.cache/pre-commit
           key: pre-commit-${{ hashFiles('.pre-commit-config.yaml') }}
@@ -501,15 +323,14 @@ jobs:
   docs:
     name: "mkdocs"
     runs-on: ubuntu-latest
-    timeout-minutes: 10
     env:
       MKDOCS_INSIDERS_SSH_KEY_EXISTS: ${{ secrets.MKDOCS_INSIDERS_SSH_KEY != '' }}
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v4
       - name: "Add SSH key"
         if: ${{ env.MKDOCS_INSIDERS_SSH_KEY_EXISTS == 'true' }}
-        uses: webfactory/ssh-agent@v0.9.0
+        uses: webfactory/ssh-agent@v0.8.0
         with:
           ssh-private-key: ${{ secrets.MKDOCS_INSIDERS_SSH_KEY }}
       - name: "Install Rust toolchain"
@@ -532,14 +353,13 @@ jobs:
         run: mkdocs build --strict -f mkdocs.insiders.yml
       - name: "Build docs"
         if: ${{ env.MKDOCS_INSIDERS_SSH_KEY_EXISTS != 'true' }}
-        run: mkdocs build --strict -f mkdocs.public.yml
+        run: mkdocs build --strict -f mkdocs.generated.yml
 
   check-formatter-instability-and-black-similarity:
     name: "formatter instabilities and black similarity"
     runs-on: ubuntu-latest
     needs: determine_changes
     if: needs.determine_changes.outputs.formatter == 'true' || github.ref == 'refs/heads/main'
-    timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4
       - name: "Install Rust toolchain"
@@ -556,13 +376,9 @@ jobs:
   check-ruff-lsp:
     name: "test ruff-lsp"
     runs-on: ubuntu-latest
-    timeout-minutes: 5
-    needs:
-      - cargo-test-linux
-      - determine_changes
-    if: ${{ needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main' }}
+    needs: cargo-test-linux
     steps:
-      - uses: extractions/setup-just@v2
+      - uses: extractions/setup-just@v1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -571,11 +387,11 @@ jobs:
         with:
           repository: "astral-sh/ruff-lsp"
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         name: Download development ruff binary
         id: ruff-target
         with:
@@ -598,9 +414,6 @@ jobs:
 
   benchmarks:
     runs-on: ubuntu-latest
-    needs: determine_changes
-    if: ${{ github.repository == 'astral-sh/ruff' && (needs.determine_changes.outputs.code == 'true' || github.ref == 'refs/heads/main') }}
-    timeout-minutes: 20
     steps:
       - name: "Checkout Branch"
         uses: actions/checkout@v4
@@ -619,7 +432,7 @@ jobs:
         run: cargo codspeed build --features codspeed -p ruff_benchmark
 
       - name: "Run benchmarks"
-        uses: CodSpeedHQ/action@v2
+        uses: CodSpeedHQ/action@v1
         with:
           run: cargo codspeed run
           token: ${{ secrets.CODSPEED_TOKEN }}

.github/workflows/daily_fuzz.yaml

@@ -1,72 +0,0 @@
-name: Daily parser fuzz
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 0 * * *"
-  pull_request:
-    paths:
-      - ".github/workflows/daily_fuzz.yaml"
-
-permissions:
-  contents: read
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-env:
-  CARGO_INCREMENTAL: 0
-  CARGO_NET_RETRY: 10
-  CARGO_TERM_COLOR: always
-  RUSTUP_MAX_RETRIES: 10
-  PACKAGE_NAME: ruff
-  FORCE_COLOR: 1
-
-jobs:
-  fuzz:
-    name: Fuzz
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    # Don't run the cron job on forks:
-    if: ${{ github.repository == 'astral-sh/ruff' || github.event_name != 'schedule' }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-      - name: Install uv
-        run: curl -LsSf https://astral.sh/uv/install.sh | sh
-      - name: Install Python requirements
-        run: uv pip install -r scripts/fuzz-parser/requirements.txt --system
-      - name: "Install Rust toolchain"
-        run: rustup show
-      - name: "Install mold"
-        uses: rui314/setup-mold@v1
-      - uses: Swatinem/rust-cache@v2
-      - name: Build ruff
-        # A debug build means the script runs slower once it gets started,
-        # but this is outweighed by the fact that a release build takes *much* longer to compile in CI
-        run: cargo build --locked
-      - name: Fuzz
-        run: python scripts/fuzz-parser/fuzz.py $(shuf -i 0-9999999999999999999 -n 1000) --test-executable target/debug/ruff
-
-  create-issue-on-failure:
-    name: Create an issue if the daily fuzz surfaced any bugs
-    runs-on: ubuntu-latest
-    needs: fuzz
-    if: ${{ github.repository == 'astral-sh/ruff' && always() && github.event_name == 'schedule' && needs.fuzz.result == 'failure' }}
-    permissions:
-      issues: write
-    steps:
-      - uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            await github.rest.issues.create({
-              owner: "astral-sh",
-              repo: "ruff",
-              title: `Daily parser fuzz failed on ${new Date().toDateString()}`,
-              body: "Runs listed here: https://github.com/astral-sh/ruff/actions/workflows/daily_fuzz.yml",
-              labels: ["bug", "parser", "fuzzer"],
-            })

.github/workflows/docs.yaml

@@ -1,7 +1,3 @@
-# Publish the Ruff documentation.
-#
-# Assumed to run as a subworkflow of .github/workflows/release.yml; specifically, as a post-announce
-# job within `cargo-dist`.
 name: mkdocs
 
 on:
@@ -11,11 +7,8 @@ on:
         description: "The commit SHA, tag, or branch to publish. Uses the default branch if not specified."
         default: ""
         type: string
-  workflow_call:
-    inputs:
-      plan:
-        required: true
-        type: string
+  release:
+    types: [published]
 
 jobs:
   mkdocs:
@@ -27,10 +20,10 @@ jobs:
       - uses: actions/checkout@v4
         with:
           ref: ${{ inputs.ref }}
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@v4
       - name: "Add SSH key"
         if: ${{ env.MKDOCS_INSIDERS_SSH_KEY_EXISTS == 'true' }}
-        uses: webfactory/ssh-agent@v0.9.0
+        uses: webfactory/ssh-agent@v0.8.0
         with:
           ssh-private-key: ${{ secrets.MKDOCS_INSIDERS_SSH_KEY }}
       - name: "Install Rust toolchain"
@@ -51,10 +44,10 @@ jobs:
         run: mkdocs build --strict -f mkdocs.insiders.yml
       - name: "Build docs"
         if: ${{ env.MKDOCS_INSIDERS_SSH_KEY_EXISTS != 'true' }}
-        run: mkdocs build --strict -f mkdocs.public.yml
+        run: mkdocs build --strict -f mkdocs.generated.yml
       - name: "Deploy to Cloudflare Pages"
         if: ${{ env.CF_API_TOKEN_EXISTS == 'true' }}
-        uses: cloudflare/wrangler-action@v3.6.1
+        uses: cloudflare/wrangler-action@v3.3.2
         with:
           apiToken: ${{ secrets.CF_API_TOKEN }}
           accountId: ${{ secrets.CF_ACCOUNT_ID }}

.github/workflows/flake8-to-ruff.yaml

@@ -0,0 +1,247 @@
+name: "[flake8-to-ruff] Release"
+
+on: workflow_dispatch
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  PACKAGE_NAME: flake8-to-ruff
+  CRATE_NAME: flake8_to_ruff
+  PYTHON_VERSION: "3.11"
+  CARGO_INCREMENTAL: 0
+  CARGO_NET_RETRY: 10
+  CARGO_TERM_COLOR: always
+  RUSTUP_MAX_RETRIES: 10
+
+jobs:
+  macos-x86_64:
+    runs-on: macos-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          architecture: x64
+      - name: "Install Rust toolchain"
+        run: rustup show
+      - name: "Build wheels - x86_64"
+        uses: PyO3/maturin-action@v1
+        with:
+          target: x86_64
+          args: --release --out dist --sdist -m ./${{ env.CRATE_NAME }}/Cargo.toml
+      - name: "Install built wheel - x86_64"
+        run: |
+          pip install dist/${{ env.CRATE_NAME }}-*.whl --force-reinstall
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+  macos-universal:
+    runs-on: macos-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          architecture: x64
+      - name: "Install Rust toolchain"
+        run: rustup show
+      - name: "Build wheels - universal2"
+        uses: PyO3/maturin-action@v1
+        with:
+          args: --release --target universal2-apple-darwin --out dist -m ./${{ env.CRATE_NAME }}/Cargo.toml
+      - name: "Install built wheel - universal2"
+        run: |
+          pip install dist/${{ env.CRATE_NAME }}-*universal2.whl --force-reinstall
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+
+  windows:
+    runs-on: windows-latest
+    strategy:
+      matrix:
+        target: [x64, x86]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          architecture: ${{ matrix.target }}
+      - name: "Install Rust toolchain"
+        run: rustup show
+      - name: "Build wheels"
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          args: --release --out dist -m ./${{ env.CRATE_NAME }}/Cargo.toml
+      - name: "Install built wheel"
+        shell: bash
+        run: |
+          python -m pip install dist/${{ env.CRATE_NAME }}-*.whl --force-reinstall
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+
+  linux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target: [x86_64, i686]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          architecture: x64
+      - name: "Build wheels"
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          manylinux: auto
+          args: --release --out dist -m ./${{ env.CRATE_NAME }}/Cargo.toml
+      - name: "Install built wheel"
+        if: matrix.target == 'x86_64'
+        run: |
+          pip install dist/${{ env.CRATE_NAME }}-*.whl --force-reinstall
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+
+  linux-cross:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target: [aarch64, armv7, s390x, ppc64le, ppc64]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+      - name: "Build wheels"
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          manylinux: auto
+          args: --no-default-features --release --out dist -m ./${{ env.CRATE_NAME }}/Cargo.toml
+      - uses: uraimo/run-on-arch-action@v2
+        if: matrix.target != 'ppc64'
+        name: Install built wheel
+        with:
+          arch: ${{ matrix.target }}
+          distro: ubuntu20.04
+          githubToken: ${{ github.token }}
+          install: |
+            apt-get update
+            apt-get install -y --no-install-recommends python3 python3-pip
+            pip3 install -U pip
+          run: |
+            pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links dist/ --force-reinstall
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+
+  musllinux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        target:
+          - x86_64-unknown-linux-musl
+          - i686-unknown-linux-musl
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          architecture: x64
+      - name: "Build wheels"
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          manylinux: musllinux_1_2
+          args: --release --out dist -m ./${{ env.CRATE_NAME }}/Cargo.toml
+      - name: "Install built wheel"
+        if: matrix.target == 'x86_64-unknown-linux-musl'
+        uses: addnab/docker-run-action@v3
+        with:
+          image: alpine:latest
+          options: -v ${{ github.workspace }}:/io -w /io
+          run: |
+            apk add py3-pip
+            pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links /io/dist/ --force-reinstall
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+
+  musllinux-cross:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        platform:
+          - target: aarch64-unknown-linux-musl
+            arch: aarch64
+          - target: armv7-unknown-linux-musleabihf
+            arch: armv7
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+      - name: "Build wheels"
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          manylinux: musllinux_1_2
+          args: --release --out dist -m ./${{ env.CRATE_NAME }}/Cargo.toml
+      - uses: uraimo/run-on-arch-action@v2
+        name: Install built wheel
+        with:
+          arch: ${{ matrix.platform.arch }}
+          distro: alpine_latest
+          githubToken: ${{ github.token }}
+          install: |
+            apk add py3-pip
+          run: |
+            pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links dist/ --force-reinstall
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    needs:
+      - macos-universal
+      - macos-x86_64
+      - windows
+      - linux
+      - linux-cross
+      - musllinux
+      - musllinux-cross
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: wheels
+      - uses: actions/setup-python@v4
+      - name: "Publish to PyPi"
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.FLAKE8_TO_RUFF_TOKEN }}
+        run: |
+          pip install --upgrade twine
+          twine upload --skip-existing *

.github/workflows/notify-dependents.yml

@@ -1,29 +0,0 @@
-# Notify downstream repositories of a new release.
-#
-# Assumed to run as a subworkflow of .github/workflows/release.yml; specifically, as a post-announce
-# job within `cargo-dist`.
-name: "[ruff] Notify dependents"
-
-on:
-  workflow_call:
-    inputs:
-      plan:
-        required: true
-        type: string
-
-jobs:
-  update-dependents:
-    name: Notify dependents
-    runs-on: ubuntu-latest
-    steps:
-      - name: "Update pre-commit mirror"
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.RUFF_PRE_COMMIT_PAT }}
-          script: |
-            github.rest.actions.createWorkflowDispatch({
-              owner: 'astral-sh',
-              repo: 'ruff-pre-commit',
-              workflow_id: 'main.yml',
-              ref: 'main',
-            })

.github/workflows/playground.yaml

@@ -1,16 +1,9 @@
-# Publish the Ruff playground.
-#
-# Assumed to run as a subworkflow of .github/workflows/release.yml; specifically, as a post-announce
-# job within `cargo-dist`.
 name: "[Playground] Release"
 
 on:
   workflow_dispatch:
-  workflow_call:
-    inputs:
-      plan:
-        required: true
-        type: string
+  release:
+    types: [published]
 
 env:
   CARGO_INCREMENTAL: 0
@@ -47,7 +40,7 @@ jobs:
         working-directory: playground
       - name: "Deploy to Cloudflare Pages"
         if: ${{ env.CF_API_TOKEN_EXISTS == 'true' }}
-        uses: cloudflare/wrangler-action@v3.6.1
+        uses: cloudflare/wrangler-action@v3.3.2
         with:
           apiToken: ${{ secrets.CF_API_TOKEN }}
           accountId: ${{ secrets.CF_ACCOUNT_ID }}

.github/workflows/pr-comment.yaml

@@ -1,4 +1,4 @@
-name: Ecosystem check comment
+name: PR Check Comment
 
 on:
   workflow_run:
@@ -17,14 +17,14 @@ jobs:
   comment:
     runs-on: ubuntu-latest
     steps:
-      - uses: dawidd6/action-download-artifact@v6
-        name: Download pull request number
+      - uses: dawidd6/action-download-artifact@v2
+        name: Download PR Number
         with:
           name: pr-number
           run_id: ${{ github.event.workflow_run.id ||  github.event.inputs.workflow_run_id }}
           if_no_artifact_found: ignore
 
-      - name: Parse pull request number
+      - name: Extract PR Number
         id: pr-number
         run: |
           if [[ -f pr-number ]]
@@ -32,8 +32,8 @@ jobs:
             echo "pr-number=$(<pr-number)" >> $GITHUB_OUTPUT
           fi
 
-      - uses: dawidd6/action-download-artifact@v6
-        name: "Download ecosystem results"
+      - uses: dawidd6/action-download-artifact@v2
+        name: "Download Ecosystem Result"
         id: download-ecosystem-result
         if: steps.pr-number.outputs.pr-number
         with:
@@ -44,23 +44,13 @@ jobs:
           workflow_conclusion: completed
           if_no_artifact_found: ignore
 
-      - name: Generate comment content
+      - name: Generate Comment
         id: generate-comment
         if: steps.download-ecosystem-result.outputs.found_artifact == 'true'
         run: |
-          # Guard against malicious ecosystem results that symlink to a secret
-          # file on this runner
-          if [[ -L pr/ecosystem/ecosystem-result ]]
-          then
-              echo "Error: ecosystem-result cannot be a symlink"
-              exit 1
-          fi
+          echo '## PR Check Results' >> comment.txt
 
-          # Note this identifier is used to find the comment to update on
-          # subsequent runs
-          echo '<!-- generated-comment ecosystem -->' >> comment.txt
-
-          echo '## `ruff-ecosystem` results' >> comment.txt
+          echo "### Ecosystem" >> comment.txt
           cat pr/ecosystem/ecosystem-result >> comment.txt
           echo "" >> comment.txt
 
@@ -68,18 +58,18 @@ jobs:
           cat comment.txt >> $GITHUB_OUTPUT
           echo 'EOF' >> $GITHUB_OUTPUT
 
-      - name: Find existing comment
-        uses: peter-evans/find-comment@v3
+      - name: Find Comment
+        uses: peter-evans/find-comment@v2
         if: steps.generate-comment.outcome == 'success'
         id: find-comment
         with:
           issue-number: ${{ steps.pr-number.outputs.pr-number }}
           comment-author: "github-actions[bot]"
-          body-includes: "<!-- generated-comment ecosystem -->"
+          body-includes: PR Check Results
 
       - name: Create or update comment
         if: steps.find-comment.outcome == 'success'
-        uses: peter-evans/create-or-update-comment@v4
+        uses: peter-evans/create-or-update-comment@v3
         with:
           comment-id: ${{ steps.find-comment.outputs.comment-id }}
           issue-number: ${{ steps.pr-number.outputs.pr-number }}

.github/workflows/pre-commit.yaml

@@ -0,0 +1,36 @@
+# Until Dependabot support is released https://github.com/dependabot/dependabot-core/issues/1524
+name: Pre-commit update
+
+on:
+  # every week on monday
+  schedule:
+    - cron: "0 0 * * 1"
+  workflow_dispatch:
+
+permissions:
+  pull-requests: write
+
+jobs:
+  upgrade:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Configure Git
+        run: |
+          git config user.name "$GITHUB_ACTOR"
+          git config user.email "$GITHUB_ACTOR@users.noreply.github.com"
+
+      - name: Run autoupdate
+        run: |
+          pre-commit autoupdate
+
+      - name: Commit and push
+        run: |
+          git add ".pre-commit-config.yaml"
+          git commit -m "Upgrade pre-commit dependencies"
+          git push origin upgrade/pre-commit
+
+      - name: Open pull request
+        run: |
+          gh pr create --fill

.github/workflows/publish-pypi.yml

@@ -1,34 +0,0 @@
-# Publish a release to PyPI.
-#
-# Assumed to run as a subworkflow of .github/workflows/release.yml; specifically, as a publish job
-# within `cargo-dist`.
-name: "[ruff] Publish to PyPI"
-
-on:
-  workflow_call:
-    inputs:
-      plan:
-        required: true
-        type: string
-
-jobs:
-  pypi-publish:
-    name: Upload to PyPI
-    runs-on: ubuntu-latest
-    environment:
-      name: release
-    permissions:
-      # For PyPI's trusted publishing.
-      id-token: write
-    steps:
-      - uses: actions/download-artifact@v4
-        with:
-          pattern: wheels-*
-          path: wheels
-          merge-multiple: true
-      - name: Publish to PyPi
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          skip-existing: true
-          packages-dir: wheels
-          verbose: true

.github/workflows/release.yaml

@@ -1,23 +1,21 @@
-# Build ruff on all platforms.
-#
-# Generates both wheels (for PyPI) and archived binaries (for GitHub releases).
-#
-# Assumed to run as a subworkflow of .github/workflows/release.yml; specifically, as a local
-# artifacts job within `cargo-dist`.
-name: "Build binaries"
+name: "[ruff] Release"
 
 on:
-  workflow_call:
+  workflow_dispatch:
     inputs:
-      plan:
-        required: true
+      tag:
+        description: "The version to tag, without the leading 'v'. If omitted, will initiate a dry run (no uploads)."
+        type: string
+      sha:
+        description: "The full sha of the commit to be released. If omitted, the latest commit on the default branch will be used."
+        default: ""
         type: string
   pull_request:
     paths:
-      # When we change pyproject.toml, we want to ensure that the maturin builds still work.
+      # When we change pyproject.toml, we want to ensure that the maturin builds still work
       - pyproject.toml
       # And when we change this workflow itself...
-      - .github/workflows/build-binaries.yml
+      - .github/workflows/release.yaml
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -25,7 +23,6 @@ concurrency:
 
 env:
   PACKAGE_NAME: ruff
-  MODULE_NAME: ruff
   PYTHON_VERSION: "3.11"
   CARGO_INCREMENTAL: 0
   CARGO_NET_RETRY: 10
@@ -34,13 +31,12 @@ env:
 
 jobs:
   sdist:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
         with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: "Prep README.md"
@@ -52,23 +48,23 @@ jobs:
           args: --out dist
       - name: "Test sdist"
         run: |
+          rustup default $(cat rust-toolchain)
           pip install dist/${{ env.PACKAGE_NAME }}-*.tar.gz --force-reinstall
-          ${{ env.MODULE_NAME }} --help
-          python -m ${{ env.MODULE_NAME }} --help
+          ruff --help
+          python -m ruff --help
       - name: "Upload sdist"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: wheels-sdist
+          name: wheels
           path: dist
 
   macos-x86_64:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
-    runs-on: macos-12
+    runs-on: macos-latest
     steps:
       - uses: actions/checkout@v4
         with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           architecture: x64
@@ -78,78 +74,70 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           target: x86_64
-          args: --release --locked --out dist
-      - name: "Upload wheels"
-        uses: actions/upload-artifact@v4
-        with:
-          name: wheels-macos-x86_64
-          path: dist
-      - name: "Archive binary"
-        run: |
-          TARGET=x86_64-apple-darwin
-          ARCHIVE_NAME=ruff-$TARGET
-          ARCHIVE_FILE=$ARCHIVE_NAME.tar.gz
-
-          mkdir -p $ARCHIVE_NAME
-          cp target/$TARGET/release/ruff $ARCHIVE_NAME/ruff
-          tar czvf $ARCHIVE_FILE $ARCHIVE_NAME
-          shasum -a 256 $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
-      - name: "Upload binary"
-        uses: actions/upload-artifact@v4
-        with:
-          name: artifacts-macos-x86_64
-          path: |
-            *.tar.gz
-            *.sha256
-
-  macos-aarch64:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
-    runs-on: macos-14
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-          architecture: arm64
-      - name: "Prep README.md"
-        run: python scripts/transform_readme.py --target pypi
-      - name: "Build wheels - aarch64"
-        uses: PyO3/maturin-action@v1
-        with:
-          target: aarch64
-          args: --release --locked --out dist
-      - name: "Test wheel - aarch64"
+          args: --release --out dist
+      - name: "Test wheel - x86_64"
         run: |
           pip install dist/${{ env.PACKAGE_NAME }}-*.whl --force-reinstall
           ruff --help
           python -m ruff --help
       - name: "Upload wheels"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: wheels-aarch64-apple-darwin
+          name: wheels
           path: dist
       - name: "Archive binary"
         run: |
-          TARGET=aarch64-apple-darwin
-          ARCHIVE_NAME=ruff-$TARGET
-          ARCHIVE_FILE=$ARCHIVE_NAME.tar.gz
-
-          mkdir -p $ARCHIVE_NAME
-          cp target/$TARGET/release/ruff $ARCHIVE_NAME/ruff
-          tar czvf $ARCHIVE_FILE $ARCHIVE_NAME
+          ARCHIVE_FILE=ruff-x86_64-apple-darwin.tar.gz
+          tar czvf $ARCHIVE_FILE -C target/x86_64-apple-darwin/release ruff
           shasum -a 256 $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
       - name: "Upload binary"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: artifacts-aarch64-apple-darwin
+          name: binaries
+          path: |
+            *.tar.gz
+            *.sha256
+
+  macos-universal:
+    runs-on: macos-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          architecture: x64
+      - name: "Prep README.md"
+        run: python scripts/transform_readme.py --target pypi
+      - name: "Build wheels - universal2"
+        uses: PyO3/maturin-action@v1
+        with:
+          args: --release --target universal2-apple-darwin --out dist
+      - name: "Test wheel - universal2"
+        run: |
+          pip install dist/${{ env.PACKAGE_NAME }}-*universal2.whl --force-reinstall
+          ruff --help
+          python -m ruff --help
+      - name: "Upload wheels"
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
+      - name: "Archive binary"
+        run: |
+          ARCHIVE_FILE=ruff-aarch64-apple-darwin.tar.gz
+          tar czvf $ARCHIVE_FILE -C target/aarch64-apple-darwin/release ruff
+          shasum -a 256 $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
+      - name: "Upload binary"
+        uses: actions/upload-artifact@v3
+        with:
+          name: binaries
           path: |
             *.tar.gz
             *.sha256
 
   windows:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
     runs-on: windows-latest
     strategy:
       matrix:
@@ -163,8 +151,8 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           architecture: ${{ matrix.platform.arch }}
@@ -174,21 +162,18 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           target: ${{ matrix.platform.target }}
-          args: --release --locked --out dist
-        env:
-          # aarch64 build fails, see https://github.com/PyO3/maturin/issues/2110
-          XWIN_VERSION: 16
+          args: --release --out dist
       - name: "Test wheel"
         if: ${{ !startsWith(matrix.platform.target, 'aarch64') }}
         shell: bash
         run: |
           python -m pip install dist/${{ env.PACKAGE_NAME }}-*.whl --force-reinstall
-          ${{ env.MODULE_NAME }} --help
-          python -m ${{ env.MODULE_NAME }} --help
+          ruff --help
+          python -m ruff --help
       - name: "Upload wheels"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: wheels-${{ matrix.platform.target }}
+          name: wheels
           path: dist
       - name: "Archive binary"
         shell: bash
@@ -197,15 +182,14 @@ jobs:
           7z a $ARCHIVE_FILE ./target/${{ matrix.platform.target }}/release/ruff.exe
           sha256sum $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
       - name: "Upload binary"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: artifacts-${{ matrix.platform.target }}
+          name: binaries
           path: |
             *.zip
             *.sha256
 
   linux:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -215,8 +199,8 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           architecture: x64
@@ -227,41 +211,32 @@ jobs:
         with:
           target: ${{ matrix.target }}
           manylinux: auto
-          args: --release --locked --out dist
+          args: --release --out dist
       - name: "Test wheel"
         if: ${{ startsWith(matrix.target, 'x86_64') }}
         run: |
           pip install dist/${{ env.PACKAGE_NAME }}-*.whl --force-reinstall
-          ${{ env.MODULE_NAME }} --help
-          python -m ${{ env.MODULE_NAME }} --help
+          ruff --help
+          python -m ruff --help
       - name: "Upload wheels"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: wheels-${{ matrix.target }}
+          name: wheels
           path: dist
       - name: "Archive binary"
-        shell: bash
         run: |
-          set -euo pipefail
-
-          TARGET=${{ matrix.target }}
-          ARCHIVE_NAME=ruff-$TARGET
-          ARCHIVE_FILE=$ARCHIVE_NAME.tar.gz
-
-          mkdir -p $ARCHIVE_NAME
-          cp target/$TARGET/release/ruff $ARCHIVE_NAME/ruff
-          tar czvf $ARCHIVE_FILE $ARCHIVE_NAME
+          ARCHIVE_FILE=ruff-${{ matrix.target }}.tar.gz
+          tar czvf $ARCHIVE_FILE -C target/${{ matrix.target }}/release ruff
           shasum -a 256 $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
       - name: "Upload binary"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: artifacts-${{ matrix.target }}
+          name: binaries
           path: |
             *.tar.gz
             *.sha256
 
   linux-cross:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -277,20 +252,14 @@ jobs:
             arch: s390x
           - target: powerpc64le-unknown-linux-gnu
             arch: ppc64le
-            # see https://github.com/astral-sh/ruff/issues/10073
-            maturin_docker_options: -e JEMALLOC_SYS_WITH_LG_PAGE=16
           - target: powerpc64-unknown-linux-gnu
             arch: ppc64
-            # see https://github.com/astral-sh/ruff/issues/10073
-            maturin_docker_options: -e JEMALLOC_SYS_WITH_LG_PAGE=16
-          - target: arm-unknown-linux-musleabihf
-            arch: arm
 
     steps:
       - uses: actions/checkout@v4
         with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: "Prep README.md"
@@ -301,13 +270,13 @@ jobs:
           target: ${{ matrix.platform.target }}
           manylinux: auto
           docker-options: ${{ matrix.platform.maturin_docker_options }}
-          args: --release --locked --out dist
+          args: --release --out dist
       - uses: uraimo/run-on-arch-action@v2
         if: matrix.platform.arch != 'ppc64'
         name: Test wheel
         with:
-          arch: ${{ matrix.platform.arch == 'arm' && 'armv6' || matrix.platform.arch }}
-          distro: ${{ matrix.platform.arch == 'arm' && 'bullseye' || 'ubuntu20.04' }}
+          arch: ${{ matrix.platform.arch }}
+          distro: ubuntu20.04
           githubToken: ${{ github.token }}
           install: |
             apt-get update
@@ -317,33 +286,24 @@ jobs:
             pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links dist/ --force-reinstall
             ruff --help
       - name: "Upload wheels"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: wheels-${{ matrix.platform.target }}
+          name: wheels
           path: dist
       - name: "Archive binary"
-        shell: bash
         run: |
-          set -euo pipefail
-
-          TARGET=${{ matrix.platform.target }}
-          ARCHIVE_NAME=ruff-$TARGET
-          ARCHIVE_FILE=$ARCHIVE_NAME.tar.gz
-
-          mkdir -p $ARCHIVE_NAME
-          cp target/$TARGET/release/ruff $ARCHIVE_NAME/ruff
-          tar czvf $ARCHIVE_FILE $ARCHIVE_NAME
+          ARCHIVE_FILE=ruff-${{ matrix.platform.target }}.tar.gz
+          tar czvf $ARCHIVE_FILE -C target/${{ matrix.platform.target }}/release ruff
           shasum -a 256 $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
       - name: "Upload binary"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: artifacts-${{ matrix.platform.target }}
+          name: binaries
           path: |
             *.tar.gz
             *.sha256
 
   musllinux:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -353,8 +313,8 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           architecture: x64
@@ -365,7 +325,7 @@ jobs:
         with:
           target: ${{ matrix.target }}
           manylinux: musllinux_1_2
-          args: --release --locked --out dist
+          args: --release --out dist
       - name: "Test wheel"
         if: matrix.target == 'x86_64-unknown-linux-musl'
         uses: addnab/docker-run-action@v3
@@ -373,38 +333,29 @@ jobs:
           image: alpine:latest
           options: -v ${{ github.workspace }}:/io -w /io
           run: |
-            apk add python3
-            python -m venv .venv
-            .venv/bin/pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links dist/ --force-reinstall
-            .venv/bin/${{ env.MODULE_NAME }} --help
+            apk add py3-pip
+            pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links /io/dist/ --force-reinstall
+            ruff --help
+            python -m ruff --help
       - name: "Upload wheels"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: wheels-${{ matrix.target }}
+          name: wheels
           path: dist
       - name: "Archive binary"
-        shell: bash
         run: |
-          set -euo pipefail
-
-          TARGET=${{ matrix.target }}
-          ARCHIVE_NAME=ruff-$TARGET
-          ARCHIVE_FILE=$ARCHIVE_NAME.tar.gz
-
-          mkdir -p $ARCHIVE_NAME
-          cp target/$TARGET/release/ruff $ARCHIVE_NAME/ruff
-          tar czvf $ARCHIVE_FILE $ARCHIVE_NAME
+          ARCHIVE_FILE=ruff-${{ matrix.target }}.tar.gz
+          tar czvf $ARCHIVE_FILE -C target/${{ matrix.target }}/release ruff
           shasum -a 256 $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
       - name: "Upload binary"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: artifacts-${{ matrix.target }}
+          name: binaries
           path: |
             *.tar.gz
             *.sha256
 
   musllinux-cross:
-    if: ${{ !contains(github.event.pull_request.labels.*.name, 'no-build') }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -418,8 +369,8 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
-          submodules: recursive
-      - uses: actions/setup-python@v5
+          ref: ${{ inputs.sha }}
+      - uses: actions/setup-python@v4
         with:
           python-version: ${{ env.PYTHON_VERSION }}
       - name: "Prep README.md"
@@ -429,7 +380,7 @@ jobs:
         with:
           target: ${{ matrix.platform.target }}
           manylinux: musllinux_1_2
-          args: --release --locked --out dist
+          args: --release --out dist
           docker-options: ${{ matrix.platform.maturin_docker_options }}
       - uses: uraimo/run-on-arch-action@v2
         name: Test wheel
@@ -438,33 +389,149 @@ jobs:
           distro: alpine_latest
           githubToken: ${{ github.token }}
           install: |
-            apk add python3
+            apk add py3-pip
           run: |
-            python -m venv .venv
-            .venv/bin/pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links dist/ --force-reinstall
-            .venv/bin/${{ env.MODULE_NAME }} --help
+            pip3 install ${{ env.PACKAGE_NAME }} --no-index --find-links dist/ --force-reinstall
+            ruff check --help
       - name: "Upload wheels"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: wheels-${{ matrix.platform.target }}
+          name: wheels
           path: dist
       - name: "Archive binary"
-        shell: bash
         run: |
-          set -euo pipefail
-
-          TARGET=${{ matrix.platform.target }}
-          ARCHIVE_NAME=ruff-$TARGET
-          ARCHIVE_FILE=$ARCHIVE_NAME.tar.gz
-
-          mkdir -p $ARCHIVE_NAME
-          cp target/$TARGET/release/ruff $ARCHIVE_NAME/ruff
-          tar czvf $ARCHIVE_FILE $ARCHIVE_NAME
+          ARCHIVE_FILE=ruff-${{ matrix.platform.target }}.tar.gz
+          tar czvf $ARCHIVE_FILE -C target/${{ matrix.platform.target }}/release ruff
           shasum -a 256 $ARCHIVE_FILE > $ARCHIVE_FILE.sha256
       - name: "Upload binary"
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
-          name: artifacts-${{ matrix.platform.target }}
+          name: binaries
           path: |
             *.tar.gz
             *.sha256
+
+  validate-tag:
+    name: Validate tag
+    runs-on: ubuntu-latest
+    # If you don't set an input tag, it's a dry run (no uploads).
+    if: ${{ inputs.tag }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: main # We checkout the main branch to check for the commit
+      - name: Check main branch
+        if: ${{ inputs.sha }}
+        run: |
+          # Fetch the main branch since a shallow checkout is used by default
+          git fetch origin main --unshallow
+          if ! git branch --contains ${{ inputs.sha }} | grep -E '(^|\s)main$'; then
+            echo "The specified sha is not on the main branch" >&2
+            exit 1
+          fi
+      - name: Check tag consistency
+        run: |
+          # Switch to the commit we want to release
+          git checkout ${{ inputs.sha }}
+          version=$(grep "version = " pyproject.toml | sed -e 's/version = "\(.*\)"/\1/g')
+          if [ "${{ inputs.tag }}" != "${version}" ]; then
+            echo "The input tag does not match the version from pyproject.toml:" >&2
+            echo "${{ inputs.tag }}" >&2
+            echo "${version}" >&2
+            exit 1
+          else
+            echo "Releasing ${version}"
+          fi
+
+  upload-release:
+    name: Upload to PyPI
+    runs-on: ubuntu-latest
+    needs:
+      - macos-universal
+      - macos-x86_64
+      - windows
+      - linux
+      - linux-cross
+      - musllinux
+      - musllinux-cross
+      - validate-tag
+    # If you don't set an input tag, it's a dry run (no uploads).
+    if: ${{ inputs.tag }}
+    environment:
+      name: release
+    permissions:
+      # For pypi trusted publishing
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: wheels
+          path: wheels
+      - name: Publish to PyPi
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          skip-existing: true
+          packages-dir: wheels
+          verbose: true
+
+  tag-release:
+    name: Tag release
+    runs-on: ubuntu-latest
+    needs: upload-release
+    # If you don't set an input tag, it's a dry run (no uploads).
+    if: ${{ inputs.tag }}
+    permissions:
+      # For git tag
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.sha }}
+      - name: git tag
+        run: |
+          git config user.email "hey@astral.sh"
+          git config user.name "Ruff Release CI"
+          git tag -m "v${{ inputs.tag }}" "v${{ inputs.tag }}"
+          # If there is duplicate tag, this will fail. The publish to pypi action will have been a noop (due to skip
+          # existing), so we make a non-destructive exit here
+          git push --tags
+
+  publish-release:
+    name: Publish to GitHub
+    runs-on: ubuntu-latest
+    needs: tag-release
+    # If you don't set an input tag, it's a dry run (no uploads).
+    if: ${{ inputs.tag }}
+    permissions:
+      # For GitHub release publishing
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: binaries
+          path: binaries
+      - name: "Publish to GitHub"
+        uses: softprops/action-gh-release@v1
+        with:
+          draft: true
+          files: binaries/*
+          tag_name: v${{ inputs.tag }}
+
+  # After the release has been published, we update downstream repositories
+  # This is separate because if this fails the release is still fine, we just need to do some manual workflow triggers
+  update-dependents:
+    name: Update dependents
+    runs-on: ubuntu-latest
+    needs: publish-release
+    steps:
+      - name: "Update pre-commit mirror"
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{ secrets.RUFF_PRE_COMMIT_PAT }}
+          script: |
+            github.rest.actions.createWorkflowDispatch({
+              owner: 'astral-sh',
+              repo: 'ruff-pre-commit',
+              workflow_id: 'main.yml',
+              ref: 'main',
+            })

.github/workflows/release.yml

@@ -1,267 +0,0 @@
-# Copyright 2022-2024, axodotdev
-# SPDX-License-Identifier: MIT or Apache-2.0
-#
-# CI that:
-#
-# * checks for a Git Tag that looks like a release
-# * builds artifacts with cargo-dist (archives, installers, hashes)
-# * uploads those artifacts to temporary workflow zip
-# * on success, uploads the artifacts to a GitHub Release
-#
-# Note that the GitHub Release will be created with a generated
-# title/body based on your changelogs.
-
-name: Release
-
-permissions:
-  contents: write
-
-# This task will run whenever you workflow_dispatch with a tag that looks like a version
-# like "1.0.0", "v0.1.0-prerelease.1", "my-app/0.1.0", "releases/v1.0.0", etc.
-# Various formats will be parsed into a VERSION and an optional PACKAGE_NAME, where
-# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION
-# must be a Cargo-style SemVer Version (must have at least major.minor.patch).
-#
-# If PACKAGE_NAME is specified, then the announcement will be for that
-# package (erroring out if it doesn't have the given version or isn't cargo-dist-able).
-#
-# If PACKAGE_NAME isn't specified, then the announcement will be for all
-# (cargo-dist-able) packages in the workspace with that version (this mode is
-# intended for workspaces with only one dist-able package, or with all dist-able
-# packages versioned/released in lockstep).
-#
-# If you push multiple tags at once, separate instances of this workflow will
-# spin up, creating an independent announcement for each one. However, GitHub
-# will hard limit this to 3 tags per commit, as it will assume more tags is a
-# mistake.
-#
-# If there's a prerelease-style suffix to the version, then the release(s)
-# will be marked as a prerelease.
-on:
-  workflow_dispatch:
-    inputs:
-      tag:
-        description: Release Tag
-        required: true
-        default: dry-run
-        type: string
-
-jobs:
-  # Run 'cargo dist plan' (or host) to determine what tasks we need to do
-  plan:
-    runs-on: ubuntu-latest
-    outputs:
-      val: ${{ steps.plan.outputs.manifest }}
-      tag: ${{ (inputs.tag != 'dry-run' && inputs.tag) || '' }}
-      tag-flag: ${{ inputs.tag && inputs.tag != 'dry-run' && format('--tag={0}', inputs.tag) || '' }}
-      publishing: ${{ inputs.tag && inputs.tag != 'dry-run' }}
-    env:
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - name: Install cargo-dist
-        # we specify bash to get pipefail; it guards against the `curl` command
-        # failing. otherwise `sh` won't catch that `curl` returned non-0
-        shell: bash
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.14.0/cargo-dist-installer.sh | sh"
-      # sure would be cool if github gave us proper conditionals...
-      # so here's a doubly-nested ternary-via-truthiness to try to provide the best possible
-      # functionality based on whether this is a pull_request, and whether it's from a fork.
-      # (PRs run on the *source* but secrets are usually on the *target* -- that's *good*
-      # but also really annoying to build CI around when it needs secrets to work right.)
-      - id: plan
-        run: |
-          cargo dist ${{ (inputs.tag && inputs.tag != 'dry-run' && format('host --steps=create --tag={0}', inputs.tag)) || 'plan' }} --output-format=json > plan-dist-manifest.json
-          echo "cargo dist ran successfully"
-          cat plan-dist-manifest.json
-          echo "manifest=$(jq -c "." plan-dist-manifest.json)" >> "$GITHUB_OUTPUT"
-      - name: "Upload dist-manifest.json"
-        uses: actions/upload-artifact@v4
-        with:
-          name: artifacts-plan-dist-manifest
-          path: plan-dist-manifest.json
-
-  custom-build-binaries:
-    needs:
-      - plan
-    if: ${{ needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload' || inputs.tag == 'dry-run' }}
-    uses: ./.github/workflows/build-binaries.yml
-    with:
-      plan: ${{ needs.plan.outputs.val }}
-    secrets: inherit
-
-  custom-build-docker:
-    needs:
-      - plan
-    if: ${{ needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload' || inputs.tag == 'dry-run' }}
-    uses: ./.github/workflows/build-docker.yml
-    with:
-      plan: ${{ needs.plan.outputs.val }}
-    secrets: inherit
-    permissions:
-      packages: write
-      contents: read
-
-  # Build and package all the platform-agnostic(ish) things
-  build-global-artifacts:
-    needs:
-      - plan
-      - custom-build-binaries
-      - custom-build-docker
-    runs-on: "ubuntu-20.04"
-    env:
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      BUILD_MANIFEST_NAME: target/distrib/global-dist-manifest.json
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - name: Install cargo-dist
-        shell: bash
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.14.0/cargo-dist-installer.sh | sh"
-      # Get all the local artifacts for the global tasks to use (for e.g. checksums)
-      - name: Fetch local artifacts
-        uses: actions/download-artifact@v4
-        with:
-          pattern: artifacts-*
-          path: target/distrib/
-          merge-multiple: true
-      - id: cargo-dist
-        shell: bash
-        run: |
-          cargo dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json
-          echo "cargo dist ran successfully"
-
-          # Parse out what we just built and upload it to scratch storage
-          echo "paths<<EOF" >> "$GITHUB_OUTPUT"
-          jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
-          echo "EOF" >> "$GITHUB_OUTPUT"
-
-          cp dist-manifest.json "$BUILD_MANIFEST_NAME"
-      - name: "Upload artifacts"
-        uses: actions/upload-artifact@v4
-        with:
-          name: artifacts-build-global
-          path: |
-            ${{ steps.cargo-dist.outputs.paths }}
-            ${{ env.BUILD_MANIFEST_NAME }}
-  # Determines if we should publish/announce
-  host:
-    needs:
-      - plan
-      - custom-build-binaries
-      - custom-build-docker
-      - build-global-artifacts
-    # Only run if we're "publishing", and only if local and global didn't fail (skipped is fine)
-    if: ${{ always() && needs.plan.outputs.publishing == 'true' && (needs.build-global-artifacts.result == 'skipped' || needs.build-global-artifacts.result == 'success') && (needs.custom-build-binaries.result == 'skipped' || needs.custom-build-binaries.result == 'success') && (needs.custom-build-docker.result == 'skipped' || needs.custom-build-docker.result == 'success') }}
-    env:
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    runs-on: "ubuntu-20.04"
-    outputs:
-      val: ${{ steps.host.outputs.manifest }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - name: Install cargo-dist
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.14.0/cargo-dist-installer.sh | sh"
-      # Fetch artifacts from scratch-storage
-      - name: Fetch artifacts
-        uses: actions/download-artifact@v4
-        with:
-          pattern: artifacts-*
-          path: target/distrib/
-          merge-multiple: true
-      # This is a harmless no-op for GitHub Releases, hosting for that happens in "announce"
-      - id: host
-        shell: bash
-        run: |
-          cargo dist host ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json
-          echo "artifacts uploaded and released successfully"
-          cat dist-manifest.json
-          echo "manifest=$(jq -c "." dist-manifest.json)" >> "$GITHUB_OUTPUT"
-      - name: "Upload dist-manifest.json"
-        uses: actions/upload-artifact@v4
-        with:
-          # Overwrite the previous copy
-          name: artifacts-dist-manifest
-          path: dist-manifest.json
-
-  custom-publish-pypi:
-    needs:
-      - plan
-      - host
-    if: ${{ !fromJson(needs.plan.outputs.val).announcement_is_prerelease || fromJson(needs.plan.outputs.val).publish_prereleases }}
-    uses: ./.github/workflows/publish-pypi.yml
-    with:
-      plan: ${{ needs.plan.outputs.val }}
-    secrets: inherit
-    # publish jobs get escalated permissions
-    permissions:
-      id-token: write
-      packages: write
-
-  # Create a GitHub Release while uploading all files to it
-  announce:
-    needs:
-      - plan
-      - host
-      - custom-publish-pypi
-    # use "always() && ..." to allow us to wait for all publish jobs while
-    # still allowing individual publish jobs to skip themselves (for prereleases).
-    # "host" however must run to completion, no skipping allowed!
-    if: ${{ always() && needs.host.result == 'success' && (needs.custom-publish-pypi.result == 'skipped' || needs.custom-publish-pypi.result == 'success') }}
-    runs-on: "ubuntu-20.04"
-    env:
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - name: "Download GitHub Artifacts"
-        uses: actions/download-artifact@v4
-        with:
-          pattern: artifacts-*
-          path: artifacts
-          merge-multiple: true
-      - name: Cleanup
-        run: |
-          # Remove the granular manifests
-          rm -f artifacts/*-dist-manifest.json
-      - name: Create GitHub Release
-        uses: ncipollo/release-action@v1
-        with:
-          tag: ${{ needs.plan.outputs.tag }}
-          name: ${{ fromJson(needs.host.outputs.val).announcement_title }}
-          body: ${{ fromJson(needs.host.outputs.val).announcement_github_body }}
-          prerelease: ${{ fromJson(needs.host.outputs.val).announcement_is_prerelease }}
-          artifacts: "artifacts/*"
-
-  custom-notify-dependents:
-    needs:
-      - plan
-      - announce
-    uses: ./.github/workflows/notify-dependents.yml
-    with:
-      plan: ${{ needs.plan.outputs.val }}
-    secrets: inherit
-
-  custom-publish-docs:
-    needs:
-      - plan
-      - announce
-    uses: ./.github/workflows/publish-docs.yml
-    with:
-      plan: ${{ needs.plan.outputs.val }}
-    secrets: inherit
-
-  custom-publish-playground:
-    needs:
-      - plan
-      - announce
-    uses: ./.github/workflows/publish-playground.yml
-    with:
-      plan: ${{ needs.plan.outputs.val }}
-    secrets: inherit

.github/workflows/sync_typeshed.yaml

@@ -1,80 +0,0 @@
-name: Sync typeshed
-
-on:
-  workflow_dispatch:
-  schedule:
-    # Run on the 1st and the 15th of every month:
-    - cron: "0 0 1,15 * *"
-
-env:
-  FORCE_COLOR: 1
-  GH_TOKEN: ${{ github.token }}
-
-jobs:
-  sync:
-    name: Sync typeshed
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    # Don't run the cron job on forks:
-    if: ${{ github.repository == 'astral-sh/ruff' || github.event_name != 'schedule' }}
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - uses: actions/checkout@v4
-        name: Checkout Ruff
-        with:
-          path: ruff
-      - uses: actions/checkout@v4
-        name: Checkout typeshed
-        with:
-          repository: python/typeshed
-          path: typeshed
-      - name: Setup git
-        run: |
-          git config --global user.name typeshedbot
-          git config --global user.email '<>'
-      - name: Sync typeshed
-        id: sync
-        run: |
-          rm -rf ruff/crates/red_knot_module_resolver/vendor/typeshed
-          mkdir ruff/crates/red_knot_module_resolver/vendor/typeshed
-          cp typeshed/README.md ruff/crates/red_knot_module_resolver/vendor/typeshed
-          cp typeshed/LICENSE ruff/crates/red_knot_module_resolver/vendor/typeshed
-          cp -r typeshed/stdlib ruff/crates/red_knot_module_resolver/vendor/typeshed/stdlib
-          rm -rf ruff/crates/red_knot_module_resolver/vendor/typeshed/stdlib/@tests
-          git -C typeshed rev-parse HEAD > ruff/crates/red_knot_module_resolver/vendor/typeshed/source_commit.txt
-      - name: Commit the changes
-        id: commit
-        if: ${{ steps.sync.outcome == 'success' }}
-        run: |
-          cd ruff
-          git checkout -b typeshedbot/sync-typeshed
-          git add .
-          git diff --staged --quiet || git commit -m "Sync typeshed. Source commit: https://github.com/python/typeshed/commit/$(git -C ../typeshed rev-parse HEAD)"
-      - name: Create a PR
-        if: ${{ steps.sync.outcome == 'success' && steps.commit.outcome == 'success' }}
-        run: |
-          cd ruff
-          git push --force origin typeshedbot/sync-typeshed
-          gh pr list --repo $GITHUB_REPOSITORY --head typeshedbot/sync-typeshed --json id --jq length | grep 1 && exit 0 # exit if there is existing pr
-          gh pr create --title "Sync vendored typeshed stubs" --body "Close and reopen this PR to trigger CI" --label "internal"
-
-  create-issue-on-failure:
-    name: Create an issue if the typeshed sync failed
-    runs-on: ubuntu-latest
-    needs: [sync]
-    if: ${{ github.repository == 'astral-sh/ruff' && always() && github.event_name == 'schedule' && needs.sync.result == 'failure' }}
-    permissions:
-      issues: write
-    steps:
-      - uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            await github.rest.issues.create({
-              owner: "astral-sh",
-              repo: "ruff",
-              title: `Automated typeshed sync failed on ${new Date().toDateString()}`,
-              body: "Runs are listed here: https://github.com/astral-sh/ruff/actions/workflows/sync_typeshed.yaml",
-            })

.gitignore

@@ -92,7 +92,6 @@ coverage.xml
 .hypothesis/
 .pytest_cache/
 cover/
-repos/
 
 # Translations
 *.mo

.markdownlint.yaml

@@ -17,4 +17,4 @@ MD013: false
 # MD024/no-duplicate-heading
 MD024:
   # Allow when nested under different parents e.g. CHANGELOG.md
-  siblings_only: true
+  allow_different_nesting: true

.pre-commit-config.yaml

@@ -2,10 +2,9 @@ fail_fast: true
 
 exclude: |
   (?x)^(
-    crates/red_knot_module_resolver/vendor/.*|
     crates/ruff_linter/resources/.*|
     crates/ruff_linter/src/rules/.*/snapshots/.*|
-    crates/ruff/resources/.*|
+    crates/ruff_cli/resources/.*|
     crates/ruff_python_formatter/resources/.*|
     crates/ruff_python_formatter/tests/snapshots/.*|
     crates/ruff_python_resolver/resources/.*|
@@ -14,12 +13,12 @@ exclude: |
 
 repos:
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.18
+    rev: v0.12.1
     hooks:
       - id: validate-pyproject
 
   - repo: https://github.com/executablebooks/mdformat
-    rev: 0.7.17
+    rev: 0.7.16
     hooks:
       - id: mdformat
         additional_dependencies:
@@ -27,22 +26,16 @@ repos:
           - mdformat-admon
         exclude: |
           (?x)^(
-            docs/formatter/black\.md
-            | docs/\w+\.md
+            docs/formatter/black.md
           )$
 
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.41.0
+    rev: v0.33.0
     hooks:
       - id: markdownlint-fix
-        exclude: |
-          (?x)^(
-            docs/formatter/black\.md
-            | docs/\w+\.md
-          )$
 
   - repo: https://github.com/crate-ci/typos
-    rev: v1.22.9
+    rev: v1.14.12
     hooks:
       - id: typos
 
@@ -54,13 +47,10 @@ repos:
         language: system
         types: [rust]
         pass_filenames: false # This makes it a lot faster
-
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.10
-    hooks:
-      - id: ruff-format
       - id: ruff
-        args: [--fix, --exit-non-zero-on-fix]
+        name: ruff
+        entry: cargo run --bin ruff -- check --no-cache --force-exclude --fix --exit-non-zero-on-fix
+        language: system
         types_or: [python, pyi]
         require_serial: true
         exclude: |
@@ -69,9 +59,15 @@ repos:
             crates/ruff_python_formatter/resources/.*
           )$
 
+  # Black
+  - repo: https://github.com/psf/black
+    rev: 23.1.0
+    hooks:
+      - id: black
+
   # Prettier
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: v3.1.0
+    rev: v3.0.0
     hooks:
       - id: prettier
         types: [yaml]

.prettierignore

@@ -1,2 +0,0 @@
-# Auto-generated by `cargo-dist`.
-.github/workflows/release.yml

.vscode/extensions.json

@@ -1,5 +0,0 @@
-{
-    "recommendations": [
-        "rust-lang.rust-analyzer"
-    ]
-}

.vscode/settings.json

@@ -1,6 +0,0 @@
-{
-    "rust-analyzer.check.extraArgs": [
-        "--all-features"
-    ],
-    "rust-analyzer.check.command": "clippy",
-}

BREAKING_CHANGES.md

@@ -1,100 +1,5 @@
 # Breaking Changes
 
-## 0.5.0
-
-- Follow the XDG specification to discover user-level configurations on macOS (same as on other Unix platforms)
-- Selecting `ALL` now excludes deprecated rules
-- The released archives now include an extra level of nesting, which can be removed with `--strip-components=1` when untarring.
-- The release artifact's file name no longer includes the version tag. This enables users to install via `/latest` URLs on GitHub.
-
-## 0.3.0
-
-### Ruff 2024.2 style
-
-The formatter now formats code according to the Ruff 2024.2 style guide. Read the [changelog](./CHANGELOG.md#030) for a detailed list of stabilized style changes.
-
-### `isort`: Use one blank line after imports in typing stub files ([#9971](https://github.com/astral-sh/ruff/pull/9971))
-
-Previously, Ruff used one or two blank lines (or the number configured by `isort.lines-after-imports`) after imports in typing stub files (`.pyi` files).
-The [typing style guide for stubs](https://typing.readthedocs.io/en/latest/source/stubs.html#style-guide) recommends using at most 1 blank line for grouping.
-As of this release, `isort` now always uses one blank line after imports in stub files, the same as the formatter.
-
-### `build` is no longer excluded by default ([#10093](https://github.com/astral-sh/ruff/pull/10093))
-
-Ruff maintains a list of directories and files that are excluded by default. This list now consists of the following patterns:
-
-- `.bzr`
-- `.direnv`
-- `.eggs`
-- `.git`
-- `.git-rewrite`
-- `.hg`
-- `.ipynb_checkpoints`
-- `.mypy_cache`
-- `.nox`
-- `.pants.d`
-- `.pyenv`
-- `.pytest_cache`
-- `.pytype`
-- `.ruff_cache`
-- `.svn`
-- `.tox`
-- `.venv`
-- `.vscode`
-- `__pypackages__`
-- `_build`
-- `buck-out`
-- `dist`
-- `node_modules`
-- `site-packages`
-- `venv`
-
-Previously, the `build` directory was included in this list. However, the `build` directory tends to be a not-unpopular directory
-name, and excluding it by default caused confusion. Ruff now no longer excludes `build` except if it is excluded by a `.gitignore` file
-or because it is listed in `extend-exclude`.
-
-### `--format` is no longer a valid `rule` or `linter` command option
-
-Previously, `ruff rule` and `ruff linter` accepted the `--format <FORMAT>` option as an alias for `--output-format`. Ruff no longer
-supports this alias. Please use `ruff rule --output-format <FORMAT>` and `ruff linter --output-format <FORMAT>` instead.
-
-## 0.1.9
-
-### `site-packages` is now excluded by default ([#5513](https://github.com/astral-sh/ruff/pull/5513))
-
-Ruff maintains a list of default exclusions, which now consists of the following patterns:
-
-- `.bzr`
-- `.direnv`
-- `.eggs`
-- `.git-rewrite`
-- `.git`
-- `.hg`
-- `.ipynb_checkpoints`
-- `.mypy_cache`
-- `.nox`
-- `.pants.d`
-- `.pyenv`
-- `.pytest_cache`
-- `.pytype`
-- `.ruff_cache`
-- `.svn`
-- `.tox`
-- `.venv`
-- `.vscode`
-- `__pypackages__`
-- `_build`
-- `buck-out`
-- `build`
-- `dist`
-- `node_modules`
-- `site-packages`
-- `venv`
-
-Previously, the `site-packages` directory was not excluded by default. While `site-packages` tends
-to be excluded anyway by virtue of the `.venv` exclusion, this may not be the case when using Ruff
-from VS Code outside a virtual environment.
-
 ## 0.1.0
 
 ### The deprecated `format` setting has been removed

CODE_OF_CONDUCT.md

@@ -72,7 +72,7 @@ representative at an online or offline event.
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
 reported to the community leaders responsible for enforcement at
-<charlie.r.marsh@gmail.com>.
+charlie.r.marsh@gmail.com.
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the

CONTRIBUTING.md

@@ -26,25 +26,30 @@ Welcome! We're happy to have you here. Thank you in advance for your contributio
 - [`cargo dev`](#cargo-dev)
 - [Subsystems](#subsystems)
     - [Compilation Pipeline](#compilation-pipeline)
-    - [Import Categorization](#import-categorization)
-        - [Project root](#project-root)
-        - [Package root](#package-root)
-        - [Import categorization](#import-categorization-1)
 
 ## The Basics
 
-Ruff welcomes contributions in the form of pull requests.
+Ruff welcomes contributions in the form of Pull Requests.
 
 For small changes (e.g., bug fixes), feel free to submit a PR.
 
 For larger changes (e.g., new lint rules, new functionality, new configuration options), consider
 creating an [**issue**](https://github.com/astral-sh/ruff/issues) outlining your proposed change.
-You can also join us on [Discord](https://discord.com/invite/astral-sh) to discuss your idea with the
+You can also join us on [**Discord**](https://discord.gg/c9MhzV8aU5) to discuss your idea with the
 community. We've labeled [beginner-friendly tasks](https://github.com/astral-sh/ruff/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22)
 in the issue tracker, along with [bugs](https://github.com/astral-sh/ruff/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
 and [improvements](https://github.com/astral-sh/ruff/issues?q=is%3Aissue+is%3Aopen+label%3Aaccepted)
 that are ready for contributions.
 
+If you're looking for a place to start, we recommend implementing a new lint rule (see:
+[_Adding a new lint rule_](#example-adding-a-new-lint-rule), which will allow you to learn from and
+pattern-match against the examples in the existing codebase. Many lint rules are inspired by
+existing Python plugins, which can be used as a reference implementation.
+
+As a concrete example: consider taking on one of the rules from the [`flake8-pyi`](https://github.com/astral-sh/ruff/issues/848)
+plugin, and looking to the originating [Python source](https://github.com/PyCQA/flake8-pyi) for
+guidance.
+
 If you have suggestions on how we might improve the contributing documentation, [let us know](https://github.com/astral-sh/ruff/discussions/5693)!
 
 ### Prerequisites
@@ -58,7 +63,7 @@ You'll also need [Insta](https://insta.rs/docs/) to update snapshot tests:
 cargo install cargo-insta
 ```
 
-And you'll need pre-commit to run some validation checks:
+and pre-commit to run some validation checks:
 
 ```shell
 pipx install pre-commit  # or `pip install pre-commit` if you have a virtualenv
@@ -71,22 +76,12 @@ when making a commit:
 pre-commit install
 ```
 
-We recommend [nextest](https://nexte.st/) to run Ruff's test suite (via `cargo nextest run`),
-though it's not strictly necessary:
-
-```shell
-cargo install cargo-nextest --locked
-```
-
-Throughout this guide, any usages of `cargo test` can be replaced with `cargo nextest run`,
-if you choose to install `nextest`.
-
 ### Development
 
 After cloning the repository, run Ruff locally from the repository root with:
 
 ```shell
-cargo run -p ruff -- check /path/to/file.py --no-cache
+cargo run -p ruff_cli -- check /path/to/file.py --no-cache
 ```
 
 Prior to opening a pull request, ensure that your code has been auto-formatted,
@@ -98,11 +93,9 @@ RUFF_UPDATE_SCHEMA=1 cargo test  # Rust testing and updating ruff.schema.json
 pre-commit run --all-files --show-diff-on-failure  # Rust and Python formatting, Markdown and Python linting, etc.
 ```
 
-These checks will run on GitHub Actions when you open your pull request, but running them locally
+These checks will run on GitHub Actions when you open your Pull Request, but running them locally
 will save you time and expedite the merge process.
 
-If you're using VS Code, you can also install the recommended [rust-analyzer](https://marketplace.visualstudio.com/items?itemName=rust-lang.rust-analyzer) extension to get these checks while editing.
-
 Note that many code changes also require updating the snapshot tests, which is done interactively
 after running `cargo test` like so:
 
@@ -110,14 +103,7 @@ after running `cargo test` like so:
 cargo insta review
 ```
 
-If your pull request relates to a specific lint rule, include the category and rule code in the
-title, as in the following examples:
-
-- \[`flake8-bugbear`\] Avoid false positive for usage after `continue` (`B031`)
-- \[`flake8-simplify`\] Detect implicit `else` cases in `needless-bool` (`SIM103`)
-- \[`pycodestyle`\] Implement `redundant-backslash` (`E502`)
-
-Your pull request will be reviewed by a maintainer, which may involve a few rounds of iteration
+Your Pull Request will be reviewed by a maintainer, which may involve a few rounds of iteration
 prior to merging.
 
 ### Project Structure
@@ -125,8 +111,8 @@ prior to merging.
 Ruff is structured as a monorepo with a [flat crate structure](https://matklad.github.io/2021/08/22/large-rust-workspaces.html),
 such that all crates are contained in a flat `crates` directory.
 
-The vast majority of the code, including all lint rules, lives in the `ruff_linter` crate (located
-at `crates/ruff_linter`). As a contributor, that's the crate that'll be most relevant to you.
+The vast majority of the code, including all lint rules, lives in the `ruff` crate (located at
+`crates/ruff_linter`). As a contributor, that's the crate that'll be most relevant to you.
 
 At the time of writing, the repository includes the following crates:
 
@@ -134,7 +120,7 @@ At the time of writing, the repository includes the following crates:
     If you're working on a rule, this is the crate for you.
 - `crates/ruff_benchmark`: binary crate for running micro-benchmarks.
 - `crates/ruff_cache`: library crate for caching lint results.
-- `crates/ruff`: binary crate containing Ruff's command-line interface.
+- `crates/ruff_cli`: binary crate containing Ruff's command-line interface.
 - `crates/ruff_dev`: binary crate containing utilities used in the development of Ruff itself (e.g.,
     `cargo dev generate-all`), see the [`cargo dev`](#cargo-dev) section below.
 - `crates/ruff_diagnostics`: library crate for the rule-independent abstractions in the lint
@@ -199,14 +185,11 @@ and calling out to lint rule analyzer functions as it goes.
 If you need to inspect the AST, you can run `cargo dev print-ast` with a Python file. Grep
 for the `Diagnostic::new` invocations to understand how other, similar rules are implemented.
 
-Once you're satisfied with your code, add tests for your rule
-(see: [rule testing](#rule-testing-fixtures-and-snapshots)), and regenerate the documentation and
-associated assets (like our JSON Schema) with `cargo dev generate-all`.
+Once you're satisfied with your code, add tests for your rule. See [rule testing](#rule-testing-fixtures-and-snapshots)
+for more details.
 
-Finally, submit a pull request, and include the category, rule name, and rule code in the title, as
-in:
-
-> \[`pycodestyle`\] Implement `redundant-backslash` (`E502`)
+Finally, regenerate the documentation and other generated assets (like our JSON Schema) with:
+`cargo dev generate-all`.
 
 #### Rule naming convention
 
@@ -248,7 +231,7 @@ Once you've completed the code for the rule itself, you can define tests with th
     For example, if you're adding a new rule named `E402`, you would run:
 
     ```shell
-    cargo run -p ruff -- check crates/ruff_linter/resources/test/fixtures/pycodestyle/E402.py --no-cache --preview --select E402
+    cargo run -p ruff_cli -- check crates/ruff_linter/resources/test/fixtures/pycodestyle/E402.py --no-cache --select E402
     ```
 
     **Note:** Only a subset of rules are enabled by default. When testing a new rule, ensure that
@@ -269,7 +252,7 @@ Once you've completed the code for the rule itself, you can define tests with th
 
 Ruff's user-facing settings live in a few different places.
 
-First, the command-line options are defined via the `Args` struct in `crates/ruff/src/args.rs`.
+First, the command-line options are defined via the `Args` struct in `crates/ruff_cli/src/args.rs`.
 
 Second, the `pyproject.toml` options are defined in `crates/ruff_workspace/src/options.rs` (via the
 `Options` struct), `crates/ruff_workspace/src/configuration.rs` (via the `Configuration` struct),
@@ -312,14 +295,14 @@ To preview any changes to the documentation locally:
 
     ```shell
     # For contributors.
-    mkdocs serve -f mkdocs.public.yml
+    mkdocs serve -f mkdocs.generated.yml
 
     # For members of the Astral org, which has access to MkDocs Insiders via sponsorship.
     mkdocs serve -f mkdocs.insiders.yml
     ```
 
 The documentation should then be available locally at
-[http://127.0.0.1:8000/ruff/](http://127.0.0.1:8000/ruff/).
+[http://127.0.0.1:8000/docs/](http://127.0.0.1:8000/docs/).
 
 ## Release Process
 
@@ -332,68 +315,47 @@ even patch releases may contain [non-backwards-compatible changes](https://semve
 
 ### Creating a new release
 
-1. Install `uv`: `curl -LsSf https://astral.sh/uv/install.sh | sh`
-1. Run `./scripts/release/bump.sh`; this command will:
-    - Generate a temporary virtual environment with `rooster`
-    - Generate a changelog entry in `CHANGELOG.md`
-    - Update versions in `pyproject.toml` and `Cargo.toml`
-    - Update references to versions in the `README.md` and documentation
-    - Display contributors for the release
-1. The changelog should then be editorialized for consistency
-    - Often labels will be missing from pull requests they will need to be manually organized into the proper section
-    - Changes should be edited to be user-facing descriptions, avoiding internal details
-1. Highlight any breaking changes in `BREAKING_CHANGES.md`
-1. Run `cargo check`. This should update the lock file with new versions.
-1. Create a pull request with the changelog and version updates
+1. Update the version with `rg 0.0.269 --files-with-matches | xargs sed -i 's/0.0.269/0.0.270/g'`
+1. Update `BREAKING_CHANGES.md`
+1. Create a PR with the version and `BREAKING_CHANGES.md` updated
 1. Merge the PR
-1. Run the [release workflow](https://github.com/astral-sh/ruff/actions/workflows/release.yml) with:
-    - The new version number (without starting `v`)
+1. Run the release workflow with the version number (without starting `v`) as input. Make sure
+    main has your merged PR as last commit
 1. The release workflow will do the following:
     1. Build all the assets. If this fails (even though we tested in step 4), we haven't tagged or
-        uploaded anything, you can restart after pushing a fix. If you just need to rerun the build,
-        make sure you're [re-running all the failed
-        jobs](https://docs.github.com/en/actions/managing-workflow-runs/re-running-workflows-and-jobs#re-running-failed-jobs-in-a-workflow) and not just a single failed job.
+        uploaded anything, you can restart after pushing a fix.
     1. Upload to PyPI.
     1. Create and push the Git tag (as extracted from `pyproject.toml`). We create the Git tag only
-        after building the wheels and uploading to PyPI, since we can't delete or modify the tag ([#4468](https://github.com/astral-sh/ruff/issues/4468)).
+        after building the wheels and uploading to PyPI, since we can't delete or modify the tag ([#4468](https://github.com/charliermarsh/ruff/issues/4468)).
     1. Attach artifacts to draft GitHub release
     1. Trigger downstream repositories. This can fail non-catastrophically, as we can run any
         downstream jobs manually if needed.
-1. Verify the GitHub release:
-    1. The Changelog should match the content of `CHANGELOG.md`
-    1. Append the contributors from the `bump.sh` script
-1. If needed, [update the schemastore](https://github.com/astral-sh/ruff/blob/main/scripts/update_schemastore.py).
-    1. One can determine if an update is needed when
-        `git diff old-version-tag new-version-tag -- ruff.schema.json` returns a non-empty diff.
-    1. Once run successfully, you should follow the link in the output to create a PR.
+1. Create release notes in GitHub UI and promote from draft.
+1. If needed, [update the schemastore](https://github.com/charliermarsh/ruff/blob/main/scripts/update_schemastore.py)
 1. If needed, update the `ruff-lsp` and `ruff-vscode` repositories.
 
 ## Ecosystem CI
 
 GitHub Actions will run your changes against a number of real-world projects from GitHub and
-report on any linter or formatter differences. You can also run those checks locally via:
+report on any diagnostic differences. You can also run those checks locally via:
 
 ```shell
-pip install -e ./python/ruff-ecosystem
-ruff-ecosystem check ruff "./target/debug/ruff"
-ruff-ecosystem format ruff "./target/debug/ruff"
+python scripts/check_ecosystem.py path/to/your/ruff path/to/older/ruff
 ```
 
-See the [ruff-ecosystem package](https://github.com/astral-sh/ruff/tree/main/python/ruff-ecosystem) for more details.
+You can also run the Ecosystem CI check in a Docker container across a larger set of projects by
+downloading the [`known-github-tomls.json`](https://github.com/akx/ruff-usage-aggregate/blob/master/data/known-github-tomls.jsonl)
+as `github_search.jsonl` and following the instructions in [scripts/Dockerfile.ecosystem](https://github.com/astral-sh/ruff/blob/main/scripts/Dockerfile.ecosystem).
+Note that this check will take a while to run.
 
 ## Benchmarking and Profiling
 
 We have several ways of benchmarking and profiling Ruff:
 
 - Our main performance benchmark comparing Ruff with other tools on the CPython codebase
-- Microbenchmarks which run the linter or the formatter on individual files. These run on pull requests.
+- Microbenchmarks which the linter or the formatter on individual files. There run on pull requests.
 - Profiling the linter on either the microbenchmarks or entire projects
 
-> \[!NOTE\]
-> When running benchmarks, ensure that your CPU is otherwise idle (e.g., close any background
-> applications, like web browsers). You may also want to switch your CPU to a "performance"
-> mode, if it exists, especially when benchmarking short-lived processes.
-
 ### CPython Benchmark
 
 First, clone [CPython](https://github.com/python/cpython). It's a large and diverse Python codebase,
@@ -539,10 +501,10 @@ if the benchmark improved/regressed compared to that baseline.
 
 ```shell
 # Run once on your "baseline" code
-cargo bench -p ruff_benchmark -- --save-baseline=main
+cargo benchmark --save-baseline=main
 
 # Then iterate with
-cargo bench -p ruff_benchmark -- --baseline=main
+cargo benchmark --baseline=main
 ```
 
 #### PR Summary
@@ -552,10 +514,10 @@ This is useful to illustrate the improvements of a PR.
 
 ```shell
 # On main
-cargo bench -p ruff_benchmark -- --save-baseline=main
+cargo benchmark --save-baseline=main
 
 # After applying your changes
-cargo bench -p ruff_benchmark -- --save-baseline=pr
+cargo benchmark --save-baseline=pr
 
 critcmp main pr
 ```
@@ -568,10 +530,10 @@ cargo install critcmp
 
 #### Tips
 
-- Use `cargo bench -p ruff_benchmark <filter>` to only run specific benchmarks. For example: `cargo benchmark lexer`
-    to only run the lexer benchmarks.
-- Use `cargo bench -p ruff_benchmark -- --quiet` for a more cleaned up output (without statistical relevance)
-- Use `cargo bench -p ruff_benchmark -- --quick` to get faster results (more prone to noise)
+- Use `cargo benchmark <filter>` to only run specific benchmarks. For example: `cargo benchmark linter/pydantic`
+    to only run the pydantic tests.
+- Use `cargo benchmark --quiet` for a more cleaned up output (without statistical relevance)
+- Use `cargo benchmark --quick` to get faster results (more prone to noise)
 
 ### Profiling Projects
 
@@ -582,10 +544,10 @@ examples.
 
 #### Linux
 
-Install `perf` and build `ruff_benchmark` with the `profiling` profile and then run it with perf
+Install `perf` and build `ruff_benchmark` with the `release-debug` profile and then run it with perf
 
 ```shell
-cargo bench -p ruff_benchmark --no-run --profile=profiling && perf record --call-graph dwarf -F 9999 cargo bench -p ruff_benchmark --profile=profiling -- --profile-time=1
+cargo bench -p ruff_benchmark --no-run --profile=release-debug && perf record --call-graph dwarf -F 9999 cargo bench -p ruff_benchmark --profile=release-debug -- --profile-time=1
 ```
 
 You can also use the `ruff_dev` launcher to run `ruff check` multiple times on a repository to
@@ -593,8 +555,8 @@ gather enough samples for a good flamegraph (change the 999, the sample rate, an
 of checks, to your liking)
 
 ```shell
-cargo build --bin ruff_dev --profile=profiling
-perf record -g -F 999 target/profiling/ruff_dev repeat --repeat 30 --exit-zero --no-cache path/to/cpython > /dev/null
+cargo build --bin ruff_dev --profile=release-debug
+perf record -g -F 999 target/release-debug/ruff_dev repeat --repeat 30 --exit-zero --no-cache path/to/cpython > /dev/null
 ```
 
 Then convert the recorded profile
@@ -624,7 +586,7 @@ cargo install cargo-instruments
 Then run the profiler with
 
 ```shell
-cargo instruments -t time --bench linter --profile profiling -p ruff_benchmark -- --profile-time=1
+cargo instruments -t time --bench linter --profile release-debug -p ruff_benchmark -- --profile-time=1
 ```
 
 - `-t`: Specifies what to profile. Useful options are `time` to profile the wall time and `alloc`
@@ -638,11 +600,11 @@ Otherwise, follow the instructions from the linux section.
 `cargo dev` is a shortcut for `cargo run --package ruff_dev --bin ruff_dev`. You can run some useful
 utils with it:
 
-- `cargo dev print-ast <file>`: Print the AST of a python file using Ruff's
-    [Python parser](https://github.com/astral-sh/ruff/tree/main/crates/ruff_python_parser).
-    For `if True: pass # comment`, you can see the syntax tree, the byte offsets for start and
-    stop of each node and also how the `:` token, the comment and whitespace are not represented
-    anymore:
+- `cargo dev print-ast <file>`: Print the AST of a python file using the
+    [RustPython parser](https://github.com/astral-sh/RustPython-Parser/tree/main/parser) that is
+    mainly used in Ruff. For `if True: pass # comment`, you can see the syntax tree, the byte offsets
+    for start and stop of each node and also how the `:` token, the comment and whitespace are not
+    represented anymore:
 
 ```text
 [
@@ -815,8 +777,8 @@ To understand Ruff's import categorization system, we first need to define two c
     "project root".)
 - "Package root": The top-most directory defining the Python package that includes a given Python
     file. To find the package root for a given Python file, traverse up its parent directories until
-    you reach a parent directory that doesn't contain an `__init__.py` file (and isn't in a subtree
-    marked as a [namespace package](https://docs.astral.sh/ruff/settings/#namespace-packages)); take the directory
+    you reach a parent directory that doesn't contain an `__init__.py` file (and isn't marked as
+    a [namespace package](https://docs.astral.sh/ruff/settings/#namespace-packages)); take the directory
     just before that, i.e., the first directory in the package.
 
 For example, given:

Cargo.toml

@@ -4,7 +4,7 @@ resolver = "2"
 
 [workspace.package]
 edition = "2021"
-rust-version = "1.75"
+rust-version = "1.71"
 homepage = "https://docs.astral.sh/ruff"
 documentation = "https://docs.astral.sh/ruff"
 repository = "https://github.com/astral-sh/ruff"
@@ -12,195 +12,51 @@ authors = ["Charlie Marsh <charlie.r.marsh@gmail.com>"]
 license = "MIT"
 
 [workspace.dependencies]
-ruff = { path = "crates/ruff" }
-ruff_cache = { path = "crates/ruff_cache" }
-ruff_db = { path = "crates/ruff_db" }
-ruff_diagnostics = { path = "crates/ruff_diagnostics" }
-ruff_formatter = { path = "crates/ruff_formatter" }
-ruff_index = { path = "crates/ruff_index" }
-ruff_linter = { path = "crates/ruff_linter" }
-ruff_macros = { path = "crates/ruff_macros" }
-ruff_notebook = { path = "crates/ruff_notebook" }
-ruff_python_ast = { path = "crates/ruff_python_ast" }
-ruff_python_codegen = { path = "crates/ruff_python_codegen" }
-ruff_python_formatter = { path = "crates/ruff_python_formatter" }
-ruff_python_index = { path = "crates/ruff_python_index" }
-ruff_python_literal = { path = "crates/ruff_python_literal" }
-ruff_python_parser = { path = "crates/ruff_python_parser" }
-ruff_python_semantic = { path = "crates/ruff_python_semantic" }
-ruff_python_stdlib = { path = "crates/ruff_python_stdlib" }
-ruff_python_trivia = { path = "crates/ruff_python_trivia" }
-ruff_server = { path = "crates/ruff_server" }
-ruff_source_file = { path = "crates/ruff_source_file" }
-ruff_text_size = { path = "crates/ruff_text_size" }
-ruff_workspace = { path = "crates/ruff_workspace" }
-
-red_knot_module_resolver = { path = "crates/red_knot_module_resolver" }
-
-aho-corasick = { version = "1.1.3" }
-annotate-snippets = { version = "0.9.2", features = ["color"] }
-anyhow = { version = "1.0.80" }
-argfile = { version = "0.2.0" }
-bincode = { version = "1.3.3" }
-bitflags = { version = "2.5.0" }
-bstr = { version = "1.9.1" }
-cachedir = { version = "0.3.1" }
-camino = { version = "1.1.7" }
-chrono = { version = "0.4.35", default-features = false, features = ["clock"] }
-clap = { version = "4.5.3", features = ["derive"] }
-clap_complete_command = { version = "0.5.1" }
-clearscreen = { version = "3.0.0" }
-codspeed-criterion-compat = { version = "2.6.0", default-features = false }
-colored = { version = "2.1.0" }
-console_error_panic_hook = { version = "0.1.7" }
-console_log = { version = "1.0.0" }
-countme = { version = "3.0.1" }
-criterion = { version = "0.5.1", default-features = false }
-crossbeam = { version = "0.8.4" }
-dashmap = { version = "5.5.3" }
-drop_bomb = { version = "0.1.5" }
-env_logger = { version = "0.11.0" }
-etcetera = { version = "0.8.0" }
-fern = { version = "0.6.1" }
-filetime = { version = "0.2.23" }
+anyhow = { version = "1.0.69" }
+bitflags = { version = "2.3.1" }
+chrono = { version = "0.4.31", default-features = false, features = ["clock"] }
+clap = { version = "4.4.7", features = ["derive"] }
+colored = { version = "2.0.0" }
+filetime = { version = "0.2.20" }
 glob = { version = "0.3.1" }
-globset = { version = "0.4.14" }
-hashbrown = "0.14.3"
-ignore = { version = "0.4.22" }
-imara-diff = { version = "0.1.5" }
-imperative = { version = "1.0.4" }
-indexmap = { version = "2.2.6" }
-indicatif = { version = "0.17.8" }
-indoc = { version = "2.0.4" }
-insta = { version = "1.35.1" }
-insta-cmd = { version = "0.6.0" }
-is-macro = { version = "0.3.5" }
-is-wsl = { version = "0.4.0" }
-itertools = { version = "0.13.0" }
-js-sys = { version = "0.3.69" }
-jod-thread = { version = "0.1.2" }
-libc = { version = "0.2.153" }
+globset = { version = "0.4.10" }
+ignore = { version = "0.4.20" }
+insta = { version = "1.34.0", feature = ["filters", "glob"] }
+is-macro = { version = "0.3.0" }
+itertools = { version = "0.11.0" }
 libcst = { version = "1.1.0", default-features = false }
 log = { version = "0.4.17" }
-lsp-server = { version = "0.7.6" }
-lsp-types = { git = "https://github.com/astral-sh/lsp-types.git", rev = "3512a9f", features = [
-  "proposed",
-] }
-matchit = { version = "0.8.1" }
-memchr = { version = "2.7.1" }
-mimalloc = { version = "0.1.39" }
-natord = { version = "1.0.9" }
-notify = { version = "6.1.1" }
-once_cell = { version = "1.19.0" }
+memchr = { version = "2.6.4" }
+once_cell = { version = "1.17.1" }
 path-absolutize = { version = "3.1.1" }
-path-slash = { version = "0.2.1" }
-pathdiff = { version = "0.2.1" }
-parking_lot = "0.12.1"
-pep440_rs = { version = "0.6.0", features = ["serde"] }
-pretty_assertions = "1.3.0"
-proc-macro2 = { version = "1.0.79" }
-pyproject-toml = { version = "0.9.0" }
-quick-junit = { version = "0.4.0" }
+proc-macro2 = { version = "1.0.69" }
 quote = { version = "1.0.23" }
-rand = { version = "0.8.5" }
-rayon = { version = "1.10.0" }
 regex = { version = "1.10.2" }
-rustc-hash = { version = "2.0.0" }
-salsa = { git = "https://github.com/salsa-rs/salsa.git", rev = "f706aa2d32d473ee633a77c1af01d180c85da308" }
-schemars = { version = "0.8.16" }
-seahash = { version = "4.1.0" }
-serde = { version = "1.0.197", features = ["derive"] }
-serde-wasm-bindgen = { version = "0.6.4" }
-serde_json = { version = "1.0.113" }
-serde_test = { version = "1.0.152" }
-serde_with = { version = "3.6.0", default-features = false, features = [
-  "macros",
-] }
+rustc-hash = { version = "1.1.0" }
+schemars = { version = "0.8.15" }
+serde = { version = "1.0.190", features = ["derive"] }
+serde_json = { version = "1.0.107" }
 shellexpand = { version = "3.0.0" }
-similar = { version = "2.4.0", features = ["inline"] }
-smallvec = { version = "1.13.2" }
-smol_str = { version = "0.2.2" }
+similar = { version = "2.3.0", features = ["inline"] }
+smallvec = { version = "1.11.1" }
 static_assertions = "1.1.0"
-strum = { version = "0.26.0", features = ["strum_macros"] }
-strum_macros = { version = "0.26.0" }
-syn = { version = "2.0.55" }
-tempfile = { version = "3.9.0" }
-test-case = { version = "3.3.1" }
-thiserror = { version = "1.0.58" }
-tikv-jemallocator = { version = "0.5.0" }
-toml = { version = "0.8.11" }
+strum = { version = "0.25.0", features = ["strum_macros"] }
+strum_macros = { version = "0.25.3" }
+syn = { version = "2.0.38" }
+test-case = { version = "3.2.1" }
+thiserror = { version = "1.0.50" }
+toml = { version = "0.7.8" }
 tracing = { version = "0.1.40" }
-tracing-indicatif = { version = "0.3.6" }
-tracing-subscriber = { version = "0.3.18", features = ["env-filter"] }
-tracing-tree = { version = "0.3.0" }
-typed-arena = { version = "2.0.2" }
-unic-ucd-category = { version = "0.9" }
+tracing-indicatif = { version = "0.3.4" }
+tracing-subscriber = { version = "0.3.17", features = ["env-filter"] }
 unicode-ident = { version = "1.0.12" }
+unicode_names2 = { version = "1.2.0" }
 unicode-width = { version = "0.1.11" }
-unicode_names2 = { version = "1.2.2" }
-unicode-normalization = { version = "0.1.23" }
-ureq = { version = "2.9.6" }
-url = { version = "2.5.0" }
-uuid = { version = "1.6.1", features = [
-  "v4",
-  "fast-rng",
-  "macro-diagnostics",
-  "js",
-] }
-walkdir = { version = "2.3.2" }
-wasm-bindgen = { version = "0.2.92" }
-wasm-bindgen-test = { version = "0.3.42" }
-wild = { version = "2" }
-zip = { version = "0.6.6", default-features = false, features = ["zstd"] }
-
-[workspace.lints.rust]
-unsafe_code = "warn"
-unreachable_pub = "warn"
-
-[workspace.lints.clippy]
-pedantic = { level = "warn", priority = -2 }
-# Allowed pedantic lints
-char_lit_as_u8 = "allow"
-collapsible_else_if = "allow"
-collapsible_if = "allow"
-implicit_hasher = "allow"
-map_unwrap_or = "allow"
-match_same_arms = "allow"
-missing_errors_doc = "allow"
-missing_panics_doc = "allow"
-module_name_repetitions = "allow"
-must_use_candidate = "allow"
-similar_names = "allow"
-too_many_lines = "allow"
-# To allow `#[allow(clippy::all)]` in `crates/ruff_python_parser/src/python.rs`.
-needless_raw_string_hashes = "allow"
-# Disallowed restriction lints
-print_stdout = "warn"
-print_stderr = "warn"
-dbg_macro = "warn"
-empty_drop = "warn"
-empty_structs_with_brackets = "warn"
-exit = "warn"
-get_unwrap = "warn"
-rc_buffer = "warn"
-rc_mutex = "warn"
-rest_pat_in_fully_bound_structs = "warn"
+uuid = { version = "1.5.0", features = ["v4", "fast-rng", "macro-diagnostics", "js"] }
+wsl = { version = "0.1.0" }
 
 [profile.release]
-# Note that we set these explicitly, and these values
-# were chosen based on a trade-off between compile times
-# and runtime performance[1].
-#
-# [1]: https://github.com/astral-sh/ruff/pull/9031
-lto = "thin"
-codegen-units = 16
-
-# Some crates don't change as much but benefit more from
-# more expensive optimization passes, so we selectively
-# decrease codegen-units in some cases.
-[profile.release.package.ruff_python_parser]
-codegen-units = 1
-[profile.release.package.ruff_python_ast]
+lto = "fat"
 codegen-units = 1
 
 [profile.dev.package.insta]
@@ -214,65 +70,8 @@ opt-level = 3
 [profile.dev.package.ruff_python_parser]
 opt-level = 1
 
-# Use the `--profile profiling` flag to show symbols in release mode.
-# e.g. `cargo build --profile profiling`
-[profile.profiling]
+# Use the `--profile release-debug` flag to show symbols in release mode.
+# e.g. `cargo build --profile release-debug`
+[profile.release-debug]
 inherits = "release"
 debug = 1
-
-# The profile that 'cargo dist' will build with.
-[profile.dist]
-inherits = "release"
-
-# Config for 'cargo dist'
-[workspace.metadata.dist]
-# The preferred cargo-dist version to use in CI (Cargo.toml SemVer syntax)
-cargo-dist-version = "0.14.0"
-# CI backends to support
-ci = ["github"]
-# The installers to generate for each app
-installers = ["shell", "powershell"]
-# The archive format to use for windows builds (defaults .zip)
-windows-archive = ".zip"
-# The archive format to use for non-windows builds (defaults .tar.xz)
-unix-archive = ".tar.gz"
-# Target platforms to build apps for (Rust target-triple syntax)
-targets = [
-  "aarch64-apple-darwin",
-  "aarch64-pc-windows-msvc",
-  "aarch64-unknown-linux-gnu",
-  "aarch64-unknown-linux-musl",
-  "arm-unknown-linux-musleabihf",
-  "armv7-unknown-linux-gnueabihf",
-  "armv7-unknown-linux-musleabihf",
-  "i686-pc-windows-msvc",
-  "i686-unknown-linux-gnu",
-  "i686-unknown-linux-musl",
-  "powerpc64-unknown-linux-gnu",
-  "powerpc64le-unknown-linux-gnu",
-  "s390x-unknown-linux-gnu",
-  "x86_64-apple-darwin",
-  "x86_64-pc-windows-msvc",
-  "x86_64-unknown-linux-gnu",
-  "x86_64-unknown-linux-musl",
-]
-# Whether to auto-include files like READMEs, LICENSEs, and CHANGELOGs (default true)
-auto-includes = false
-# Whether cargo-dist should create a Github Release or use an existing draft
-create-release = true
-# Publish jobs to run in CI
-pr-run-mode = "skip"
-# Whether CI should trigger releases with dispatches instead of tag pushes
-dispatch-releases = true
-# Whether CI should include auto-generated code to build local artifacts
-build-local-artifacts = false
-# Local artifacts jobs to run in CI
-local-artifacts-jobs = ["./build-binaries", "./build-docker"]
-# Publish jobs to run in CI
-publish-jobs = ["./publish-pypi"]
-# Announcement jobs to run in CI
-post-announce-jobs = ["./notify-dependents", "./publish-docs", "./publish-playground"]
-# Skip checking whether the specified configuration files are up to date
-allow-dirty = ["ci"]
-# Whether to install an updater program
-install-updater = false

Dockerfile

@@ -1,38 +0,0 @@
-FROM --platform=$BUILDPLATFORM ubuntu as build
-ENV HOME="/root"
-WORKDIR $HOME
-
-RUN apt update && apt install -y build-essential curl python3-venv
-
-# Setup zig as cross compiling linker
-RUN python3 -m venv $HOME/.venv
-RUN .venv/bin/pip install cargo-zigbuild
-ENV PATH="$HOME/.venv/bin:$PATH"
-
-# Install rust
-ARG TARGETPLATFORM
-RUN case "$TARGETPLATFORM" in \
-    "linux/arm64") echo "aarch64-unknown-linux-musl" > rust_target.txt ;; \
-    "linux/amd64") echo "x86_64-unknown-linux-musl" > rust_target.txt ;; \
-    *) exit 1 ;; \
-    esac
-# Update rustup whenever we bump the rust version
-COPY rust-toolchain.toml rust-toolchain.toml
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --target $(cat rust_target.txt) --profile minimal --default-toolchain none
-ENV PATH="$HOME/.cargo/bin:$PATH"
-# Installs the correct toolchain version from rust-toolchain.toml and then the musl target
-RUN rustup target add $(cat rust_target.txt)
-
-# Build
-COPY crates crates
-COPY Cargo.toml Cargo.toml
-COPY Cargo.lock Cargo.lock
-RUN cargo zigbuild --bin ruff --target $(cat rust_target.txt) --release
-RUN cp target/$(cat rust_target.txt)/release/ruff /ruff
-# TODO: Optimize binary size, with a version that also works when cross compiling
-# RUN strip --strip-all /ruff
-
-FROM scratch
-COPY --from=build /ruff /ruff
-WORKDIR /io
-ENTRYPOINT ["/ruff"]

LICENSE

@@ -1269,31 +1269,6 @@ are:
     SOFTWARE.
   """
 
-- flake8-trio, licensed as follows:
-  """
-    MIT License
-
-    Copyright (c) 2022 Zac Hatfield-Dodds
-
-    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.
-  """
-
 - Pyright, licensed as follows:
   """
     MIT License

README.md

@@ -4,12 +4,11 @@
 
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![image](https://img.shields.io/pypi/v/ruff.svg)](https://pypi.python.org/pypi/ruff)
-[![image](https://img.shields.io/pypi/l/ruff.svg)](https://github.com/astral-sh/ruff/blob/main/LICENSE)
+[![image](https://img.shields.io/pypi/l/ruff.svg)](https://pypi.python.org/pypi/ruff)
 [![image](https://img.shields.io/pypi/pyversions/ruff.svg)](https://pypi.python.org/pypi/ruff)
 [![Actions status](https://github.com/astral-sh/ruff/workflows/CI/badge.svg)](https://github.com/astral-sh/ruff/actions)
-[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?logo=discord&logoColor=white)](https://discord.com/invite/astral-sh)
 
-[**Docs**](https://docs.astral.sh/ruff/) | [**Playground**](https://play.ruff.rs/)
+[**Discord**](https://discord.gg/c9MhzV8aU5) | [**Docs**](https://docs.astral.sh/ruff/) | [**Playground**](https://play.ruff.rs/)
 
 An extremely fast Python linter and code formatter, written in Rust.
 
@@ -28,11 +27,11 @@ An extremely fast Python linter and code formatter, written in Rust.
 - ⚡️ 10-100x faster than existing linters (like Flake8) and formatters (like Black)
 - 🐍 Installable via `pip`
 - 🛠️ `pyproject.toml` support
-- 🤝 Python 3.13 compatibility
+- 🤝 Python 3.12 compatibility
 - ⚖️ Drop-in parity with [Flake8](https://docs.astral.sh/ruff/faq/#how-does-ruff-compare-to-flake8), isort, and Black
 - 📦 Built-in caching, to avoid re-analyzing unchanged files
 - 🔧 Fix support, for automatic error correction (e.g., automatically remove unused imports)
-- 📏 Over [800 built-in rules](https://docs.astral.sh/ruff/rules/), with native re-implementations
+- 📏 Over [700 built-in rules](https://docs.astral.sh/ruff/rules/), with native re-implementations
     of popular Flake8 plugins, like flake8-bugbear
 - ⌨️ First-party [editor integrations](https://docs.astral.sh/ruff/integrations/) for
     [VS Code](https://github.com/astral-sh/ruff-vscode) and [more](https://github.com/astral-sh/ruff-lsp)
@@ -50,13 +49,12 @@ times faster than any individual tool.
 Ruff is extremely actively developed and used in major open-source projects like:
 
 - [Apache Airflow](https://github.com/apache/airflow)
-- [Apache Superset](https://github.com/apache/superset)
 - [FastAPI](https://github.com/tiangolo/fastapi)
 - [Hugging Face](https://github.com/huggingface/transformers)
 - [Pandas](https://github.com/pandas-dev/pandas)
 - [SciPy](https://github.com/scipy/scipy)
 
-...and [many more](#whos-using-ruff).
+...and many more.
 
 Ruff is backed by [Astral](https://astral.sh). Read the [launch post](https://astral.sh/blog/announcing-astral-the-company-behind-ruff),
 or the original [project announcement](https://notes.crmarsh.com/python-tooling-could-be-much-much-faster).
@@ -130,7 +128,7 @@ and with [a variety of other package managers](https://docs.astral.sh/ruff/insta
 To run Ruff as a linter, try any of the following:
 
 ```shell
-ruff check                          # Lint all files in the current directory (and any subdirectories).
+ruff check .                        # Lint all files in the current directory (and any subdirectories).
 ruff check path/to/code/            # Lint all files in `/path/to/code` (and any subdirectories).
 ruff check path/to/code/*.py        # Lint all `.py` files in `/path/to/code`.
 ruff check path/to/code/to/file.py  # Lint `file.py`.
@@ -140,7 +138,7 @@ ruff check @arguments.txt           # Lint using an input file, treating its con
 Or, to run Ruff as a formatter:
 
 ```shell
-ruff format                          # Format all files in the current directory (and any subdirectories).
+ruff format .                        # Format all files in the current directory (and any subdirectories).
 ruff format path/to/code/            # Format all files in `/path/to/code` (and any subdirectories).
 ruff format path/to/code/*.py        # Format all `.py` files in `/path/to/code`.
 ruff format path/to/code/to/file.py  # Format `file.py`.
@@ -150,14 +148,14 @@ ruff format @arguments.txt           # Format using an input file, treating its
 Ruff can also be used as a [pre-commit](https://pre-commit.com/) hook via [`ruff-pre-commit`](https://github.com/astral-sh/ruff-pre-commit):
 
 ```yaml
+# Run the Ruff linter.
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: v0.5.0
+  rev: v0.1.3
   hooks:
-    # Run the linter.
+    # Run the Ruff linter.
     - id: ruff
-      args: [ --fix ]
-    # Run the formatter.
+    # Run the Ruff formatter.
     - id: ruff-format
 ```
 
@@ -174,7 +172,7 @@ jobs:
   ruff:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: chartboost/ruff-action@v1
 ```
 
@@ -184,9 +182,10 @@ Ruff can be configured through a `pyproject.toml`, `ruff.toml`, or `.ruff.toml`
 [_Configuration_](https://docs.astral.sh/ruff/configuration/), or [_Settings_](https://docs.astral.sh/ruff/settings/)
 for a complete list of all configuration options).
 
-If left unspecified, Ruff's default configuration is equivalent to the following `ruff.toml` file:
+If left unspecified, Ruff's default configuration is equivalent to:
 
 ```toml
+[tool.ruff]
 # Exclude a variety of commonly ignored directories.
 exclude = [
     ".bzr",
@@ -195,25 +194,20 @@ exclude = [
     ".git",
     ".git-rewrite",
     ".hg",
-    ".ipynb_checkpoints",
     ".mypy_cache",
     ".nox",
     ".pants.d",
-    ".pyenv",
-    ".pytest_cache",
     ".pytype",
     ".ruff_cache",
     ".svn",
     ".tox",
     ".venv",
-    ".vscode",
     "__pypackages__",
     "_build",
     "buck-out",
     "build",
     "dist",
     "node_modules",
-    "site-packages",
     "venv",
 ]
 
@@ -224,7 +218,7 @@ indent-width = 4
 # Assume Python 3.8
 target-version = "py38"
 
-[lint]
+[tool.ruff.lint]
 # Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
 select = ["E4", "E7", "E9", "F"]
 ignore = []
@@ -236,7 +230,7 @@ unfixable = []
 # Allow unused variables when underscore-prefixed.
 dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
 
-[format]
+[tool.ruff.format]
 # Like Black, use double quotes for strings.
 quote-style = "double"
 
@@ -250,27 +244,13 @@ skip-magic-trailing-comma = false
 line-ending = "auto"
 ```
 
-Note that, in a `pyproject.toml`, each section header should be prefixed with `tool.ruff`. For
-example, `[lint]` should be replaced with `[tool.ruff.lint]`.
-
-Some configuration options can be provided via dedicated command-line arguments, such as those
-related to rule enablement and disablement, file discovery, and logging level:
+Some configuration options can be provided via the command-line, such as those related to
+rule enablement and disablement, file discovery, and logging level:
 
 ```shell
-ruff check --select F401 --select F403 --quiet
+ruff check path/to/code/ --select F401 --select F403 --quiet
 ```
 
-The remaining configuration options can be provided through a catch-all `--config` argument:
-
-```shell
-ruff check --config "lint.per-file-ignores = {'some_file.py' = ['F841']}"
-```
-
-To opt in to the latest lint rules, formatter style changes, interface updates, and more, enable
-[preview mode](https://docs.astral.sh/ruff/rules/) by setting `preview = true` in your configuration
-file or passing `--preview` on the command line. Preview mode enables a collection of unstable
-features that may change prior to stabilization.
-
 See `ruff help` for more on Ruff's top-level commands, or `ruff help check` and `ruff help format`
 for more on the linting and formatting commands, respectively.
 
@@ -278,7 +258,7 @@ for more on the linting and formatting commands, respectively.
 
 <!-- Begin section: Rules -->
 
-**Ruff supports over 800 lint rules**, many of which are inspired by popular tools like Flake8,
+**Ruff supports over 700 lint rules**, many of which are inspired by popular tools like Flake8,
 isort, pyupgrade, and others. Regardless of the rule's origin, Ruff re-implements every rule in
 Rust as a first-party feature.
 
@@ -355,14 +335,14 @@ For a complete enumeration of the supported rules, see [_Rules_](https://docs.as
 Contributions are welcome and highly appreciated. To get started, check out the
 [**contributing guidelines**](https://docs.astral.sh/ruff/contributing/).
 
-You can also join us on [**Discord**](https://discord.com/invite/astral-sh).
+You can also join us on [**Discord**](https://discord.gg/c9MhzV8aU5).
 
 ## Support
 
 Having trouble? Check out the existing issues on [**GitHub**](https://github.com/astral-sh/ruff/issues),
 or feel free to [**open a new one**](https://github.com/astral-sh/ruff/issues/new).
 
-You can also ask for help on [**Discord**](https://discord.com/invite/astral-sh).
+You can also ask for help on [**Discord**](https://discord.gg/c9MhzV8aU5).
 
 ## Acknowledgements
 
@@ -392,37 +372,31 @@ Ruff is released under the MIT license.
 
 Ruff is used by a number of major open-source projects and companies, including:
 
-- [Albumentations](https://github.com/albumentations-team/albumentations)
 - Amazon ([AWS SAM](https://github.com/aws/serverless-application-model))
 - Anthropic ([Python SDK](https://github.com/anthropics/anthropic-sdk-python))
 - [Apache Airflow](https://github.com/apache/airflow)
 - AstraZeneca ([Magnus](https://github.com/AstraZeneca/magnus-core))
-- [Babel](https://github.com/python-babel/babel)
 - Benchling ([Refac](https://github.com/benchling/refac))
+- [Babel](https://github.com/python-babel/babel)
 - [Bokeh](https://github.com/bokeh/bokeh)
 - [Cryptography (PyCA)](https://github.com/pyca/cryptography)
-- CERN ([Indico](https://getindico.io/))
 - [DVC](https://github.com/iterative/dvc)
 - [Dagger](https://github.com/dagger/dagger)
 - [Dagster](https://github.com/dagster-io/dagster)
 - Databricks ([MLflow](https://github.com/mlflow/mlflow))
 - [FastAPI](https://github.com/tiangolo/fastapi)
-- [Godot](https://github.com/godotengine/godot)
 - [Gradio](https://github.com/gradio-app/gradio)
 - [Great Expectations](https://github.com/great-expectations/great_expectations)
 - [HTTPX](https://github.com/encode/httpx)
-- [Hatch](https://github.com/pypa/hatch)
-- [Home Assistant](https://github.com/home-assistant/core)
 - Hugging Face ([Transformers](https://github.com/huggingface/transformers),
     [Datasets](https://github.com/huggingface/datasets),
     [Diffusers](https://github.com/huggingface/diffusers))
+- [Hatch](https://github.com/pypa/hatch)
+- [Home Assistant](https://github.com/home-assistant/core)
 - ING Bank ([popmon](https://github.com/ing-bank/popmon), [probatus](https://github.com/ing-bank/probatus))
 - [Ibis](https://github.com/ibis-project/ibis)
-- [ivy](https://github.com/unifyai/ivy)
 - [Jupyter](https://github.com/jupyter-server/jupyter_server)
-- [Kraken Tech](https://kraken.tech/)
 - [LangChain](https://github.com/hwchase17/langchain)
-- [Litestar](https://litestar.dev/)
 - [LlamaIndex](https://github.com/jerryjliu/llama_index)
 - Matrix ([Synapse](https://github.com/matrix-org/synapse))
 - [MegaLinter](https://github.com/oxsecurity/megalinter)
@@ -430,46 +404,35 @@ Ruff is used by a number of major open-source projects and companies, including:
 - Microsoft ([Semantic Kernel](https://github.com/microsoft/semantic-kernel),
     [ONNX Runtime](https://github.com/microsoft/onnxruntime),
     [LightGBM](https://github.com/microsoft/LightGBM))
-- Modern Treasury ([Python SDK](https://github.com/Modern-Treasury/modern-treasury-python))
+- Modern Treasury ([Python SDK](https://github.com/Modern-Treasury/modern-treasury-python-sdk))
 - Mozilla ([Firefox](https://github.com/mozilla/gecko-dev))
 - [Mypy](https://github.com/python/mypy)
-- [Nautobot](https://github.com/nautobot/nautobot)
 - Netflix ([Dispatch](https://github.com/Netflix/dispatch))
 - [Neon](https://github.com/neondatabase/neon)
-- [Nokia](https://nokia.com/)
 - [NoneBot](https://github.com/nonebot/nonebot2)
-- [NumPyro](https://github.com/pyro-ppl/numpyro)
 - [ONNX](https://github.com/onnx/onnx)
 - [OpenBB](https://github.com/OpenBB-finance/OpenBBTerminal)
-- [Open Wine Components](https://github.com/Open-Wine-Components/umu-launcher)
 - [PDM](https://github.com/pdm-project/pdm)
 - [PaddlePaddle](https://github.com/PaddlePaddle/Paddle)
 - [Pandas](https://github.com/pandas-dev/pandas)
-- [Pillow](https://github.com/python-pillow/Pillow)
 - [Poetry](https://github.com/python-poetry/poetry)
 - [Polars](https://github.com/pola-rs/polars)
 - [PostHog](https://github.com/PostHog/posthog)
 - Prefect ([Python SDK](https://github.com/PrefectHQ/prefect), [Marvin](https://github.com/PrefectHQ/marvin))
 - [PyInstaller](https://github.com/pyinstaller/pyinstaller)
-- [PyMC](https://github.com/pymc-devs/pymc/)
-- [PyMC-Marketing](https://github.com/pymc-labs/pymc-marketing)
-- [pytest](https://github.com/pytest-dev/pytest)
 - [PyTorch](https://github.com/pytorch/pytorch)
 - [Pydantic](https://github.com/pydantic/pydantic)
 - [Pylint](https://github.com/PyCQA/pylint)
-- [PyVista](https://github.com/pyvista/pyvista)
 - [Reflex](https://github.com/reflex-dev/reflex)
-- [River](https://github.com/online-ml/river)
 - [Rippling](https://rippling.com)
 - [Robyn](https://github.com/sansyrox/robyn)
-- [Saleor](https://github.com/saleor/saleor)
 - Scale AI ([Launch SDK](https://github.com/scaleapi/launch-python-client))
-- [SciPy](https://github.com/scipy/scipy)
 - Snowflake ([SnowCLI](https://github.com/Snowflake-Labs/snowcli))
+- [Saleor](https://github.com/saleor/saleor)
+- [SciPy](https://github.com/scipy/scipy)
 - [Sphinx](https://github.com/sphinx-doc/sphinx)
 - [Stable Baselines3](https://github.com/DLR-RM/stable-baselines3)
-- [Starlette](https://github.com/encode/starlette)
-- [Streamlit](https://github.com/streamlit/streamlit)
+- [Litestar](https://litestar.dev/)
 - [The Algorithms](https://github.com/TheAlgorithms/Python)
 - [Vega-Altair](https://github.com/altair-viz/altair)
 - WordPress ([Openverse](https://github.com/WordPress/openverse))
@@ -485,7 +448,7 @@ Ruff is used by a number of major open-source projects and companies, including:
 
 ### Show Your Support
 
-If you're using Ruff, consider adding the Ruff badge to your project's `README.md`:
+If you're using Ruff, consider adding the Ruff badge to project's `README.md`:
 
 ```md
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
@@ -507,10 +470,10 @@ If you're using Ruff, consider adding the Ruff badge to your project's `README.m
 
 ## License
 
-This repository is licensed under the [MIT License](https://github.com/astral-sh/ruff/blob/main/LICENSE)
+MIT
 
 <div align="center">
   <a target="_blank" href="https://astral.sh" style="background:none">
-    <img src="https://raw.githubusercontent.com/astral-sh/ruff/main/assets/svg/Astral.svg" alt="Made by Astral">
+    <img src="https://raw.githubusercontent.com/astral-sh/ruff/main/assets/svg/Astral.svg">
   </a>
 </div>

_typos.toml

@@ -1,21 +1,10 @@
 [files]
-# https://github.com/crate-ci/typos/issues/868
-extend-exclude = ["crates/red_knot_module_resolver/vendor/**/*", "**/resources/**/*", "**/snapshots/**/*"]
+extend-exclude = ["resources", "snapshots"]
 
 [default.extend-words]
-"arange" = "arange"  # e.g. `numpy.arange`
 hel = "hel"
 whos = "whos"
 spawnve = "spawnve"
 ned = "ned"
-pn = "pn"  # `import panel as pd` is a thing
 poit = "poit"
 BA = "BA" # acronym for "Bad Allowed", used in testing.
-jod = "jod" # e.g., `jod-thread`
-
-[default]
-extend-ignore-re = [
-  # Line ignore with trailing "spellchecker:disable-line"
-  "(?Rm)^.*#\\s*spellchecker:disable-line$",
-  "LICENSEs",
-]

clippy.toml

@@ -1,13 +1,7 @@
 doc-valid-idents = [
-  "..",
-  "CodeQL",
-  "FastAPI",
-  "IPython",
-  "LangChain",
-  "LibCST",
-  "McCabe",
-  "NumPy",
-  "SCREAMING_SNAKE_CASE",
-  "SQLAlchemy",
   "StackOverflow",
+  "CodeQL",
+  "IPython",
+  "NumPy",
+  "..",
 ]

crates/flake8_to_ruff/Cargo.toml

@@ -0,0 +1,36 @@
+[package]
+name = "flake8-to-ruff"
+version = "0.1.3"
+description = """
+Convert Flake8 configuration files to Ruff configuration files.
+"""
+authors = { workspace = true }
+edition = { workspace = true }
+rust-version = { workspace = true }
+homepage = { workspace = true }
+documentation = { workspace = true }
+repository = { workspace = true }
+license = { workspace = true }
+
+[dependencies]
+ruff_linter = { path = "../ruff_linter", default-features = false }
+ruff_workspace = { path = "../ruff_workspace" }
+
+anyhow = { workspace = true }
+clap = { workspace = true }
+colored = { workspace = true }
+configparser = { version = "3.0.2" }
+itertools = { workspace = true }
+log = { workspace = true }
+once_cell = { workspace = true }
+pep440_rs = { version = "0.3.12", features = ["serde"] }
+regex = { workspace = true }
+rustc-hash = { workspace = true }
+serde = { workspace = true }
+serde_json = { workspace = true }
+strum = { workspace = true }
+strum_macros = { workspace = true }
+toml = { workspace = true }
+
+[dev-dependencies]
+pretty_assertions = "1.3.0"

crates/flake8_to_ruff/README.md

@@ -0,0 +1,99 @@
+# flake8-to-ruff
+
+Convert existing Flake8 configuration files (`setup.cfg`, `tox.ini`, or `.flake8`) for use with
+[Ruff](https://github.com/astral-sh/ruff).
+
+Generates a Ruff-compatible `pyproject.toml` section.
+
+## Installation and Usage
+
+### Installation
+
+Available as [`flake8-to-ruff`](https://pypi.org/project/flake8-to-ruff/) on PyPI:
+
+```shell
+pip install flake8-to-ruff
+```
+
+### Usage
+
+To run `flake8-to-ruff`:
+
+```shell
+flake8-to-ruff path/to/setup.cfg
+flake8-to-ruff path/to/tox.ini
+flake8-to-ruff path/to/.flake8
+```
+
+`flake8-to-ruff` will print the relevant `pyproject.toml` sections to standard output, like so:
+
+```toml
+[tool.ruff]
+exclude = [
+    '.svn',
+    'CVS',
+    '.bzr',
+    '.hg',
+    '.git',
+    '__pycache__',
+    '.tox',
+    '.idea',
+    '.mypy_cache',
+    '.venv',
+    'node_modules',
+    '_state_machine.py',
+    'test_fstring.py',
+    'bad_coding2.py',
+    'badsyntax_*.py',
+]
+select = [
+    'A',
+    'E',
+    'F',
+    'Q',
+]
+ignore = []
+
+[tool.ruff.flake8-quotes]
+inline-quotes = 'single'
+
+[tool.ruff.pep8-naming]
+ignore-names = [
+    'foo',
+    'bar',
+]
+```
+
+### Plugins
+
+`flake8-to-ruff` will attempt to infer any activated plugins based on the settings provided in your
+configuration file.
+
+For example, if your `.flake8` file includes a `docstring-convention` property, `flake8-to-ruff`
+will enable the appropriate [`flake8-docstrings`](https://pypi.org/project/flake8-docstrings/)
+checks.
+
+Alternatively, you can manually specify plugins on the command-line:
+
+```shell
+flake8-to-ruff path/to/.flake8 --plugin flake8-builtins --plugin flake8-quotes
+```
+
+## Limitations
+
+1. Ruff only supports a subset of the Flake configuration options. `flake8-to-ruff` will warn on and
+    ignore unsupported options in the `.flake8` file (or equivalent). (Similarly, Ruff has a few
+    configuration options that don't exist in Flake8.)
+1. Ruff will omit any rule codes that are unimplemented or unsupported by Ruff, including rule
+    codes from unsupported plugins. (See the
+    [documentation](https://docs.astral.sh/ruff/faq/#how-does-ruff-compare-to-flake8) for the complete
+    list of supported plugins.)
+
+## License
+
+MIT
+
+## Contributing
+
+Contributions are welcome and hugely appreciated. To get started, check out the
+[contributing guidelines](https://github.com/astral-sh/ruff/blob/main/CONTRIBUTING.md).

crates/flake8_to_ruff/examples/cryptography/pyproject.toml

@@ -0,0 +1,65 @@
+[build-system]
+requires = [
+    # The minimum setuptools version is specific to the PEP 517 backend,
+    # and may be stricter than the version required in `setup.cfg`
+    "setuptools>=40.6.0,!=60.9.0",
+    "wheel",
+    # Must be kept in sync with the `install_requirements` in `setup.cfg`
+    "cffi>=1.12; platform_python_implementation != 'PyPy'",
+    "setuptools-rust>=0.11.4",
+]
+build-backend = "setuptools.build_meta"
+
+[tool.black]
+line-length = 79
+target-version = ["py36"]
+
+[tool.pytest.ini_options]
+addopts = "-r s --capture=no --strict-markers --benchmark-disable"
+markers = [
+    "skip_fips: this test is not executed in FIPS mode",
+    "supported: parametrized test requiring only_if and skip_message",
+]
+
+[tool.mypy]
+show_error_codes = true
+check_untyped_defs = true
+no_implicit_reexport = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+warn_unused_configs = true
+strict_equality = true
+
+[[tool.mypy.overrides]]
+module = [
+    "pretend"
+]
+ignore_missing_imports = true
+
+[tool.coverage.run]
+branch = true
+relative_files = true
+source = [
+    "cryptography",
+    "tests/",
+]
+
+[tool.coverage.paths]
+source = [
+   "src/cryptography",
+   "*.tox/*/lib*/python*/site-packages/cryptography",
+   "*.tox\\*\\Lib\\site-packages\\cryptography",
+   "*.tox/pypy/site-packages/cryptography",
+]
+tests =[
+   "tests/",
+   "*tests\\",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "@abc.abstractmethod",
+    "@abc.abstractproperty",
+    "@typing.overload",
+    "if typing.TYPE_CHECKING",
+]

crates/flake8_to_ruff/examples/cryptography/setup.cfg

@@ -0,0 +1,91 @@
+[metadata]
+name = cryptography
+version = attr: cryptography.__version__
+description = cryptography is a package which provides cryptographic recipes and primitives to Python developers.
+long_description = file: README.rst
+long_description_content_type = text/x-rst
+license = BSD-3-Clause OR Apache-2.0
+url = https://github.com/pyca/cryptography
+author = The Python Cryptographic Authority and individual contributors
+author_email = cryptography-dev@python.org
+project_urls =
+    Documentation=https://cryptography.io/
+    Source=https://github.com/pyca/cryptography/
+    Issues=https://github.com/pyca/cryptography/issues
+    Changelog=https://cryptography.io/en/latest/changelog/
+classifiers =
+    Development Status :: 5 - Production/Stable
+    Intended Audience :: Developers
+    License :: OSI Approved :: Apache Software License
+    License :: OSI Approved :: BSD License
+    Natural Language :: English
+    Operating System :: MacOS :: MacOS X
+    Operating System :: POSIX
+    Operating System :: POSIX :: BSD
+    Operating System :: POSIX :: Linux
+    Operating System :: Microsoft :: Windows
+    Programming Language :: Python
+    Programming Language :: Python :: 3
+    Programming Language :: Python :: 3 :: Only
+    Programming Language :: Python :: 3.6
+    Programming Language :: Python :: 3.7
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
+    Programming Language :: Python :: 3.11
+    Programming Language :: Python :: Implementation :: CPython
+    Programming Language :: Python :: Implementation :: PyPy
+    Topic :: Security :: Cryptography
+
+[options]
+python_requires = >=3.6
+include_package_data = True
+zip_safe = False
+package_dir =
+    =src
+packages = find:
+# `install_requires` must be kept in sync with `pyproject.toml`
+install_requires =
+    cffi >=1.12
+
+[options.packages.find]
+where = src
+exclude =
+    _cffi_src
+    _cffi_src.*
+
+[options.extras_require]
+test =
+    pytest>=6.2.0
+    pytest-benchmark
+    pytest-cov
+    pytest-subtests
+    pytest-xdist
+    pretend
+    iso8601
+    pytz
+    hypothesis>=1.11.4,!=3.79.2
+docs =
+    sphinx >= 1.6.5,!=1.8.0,!=3.1.0,!=3.1.1,!=5.2.0,!=5.2.0.post0
+    sphinx_rtd_theme
+docstest =
+    pyenchant >= 1.6.11
+    twine >= 1.12.0
+    sphinxcontrib-spelling >= 4.0.1
+sdist =
+    setuptools_rust >= 0.11.4
+pep8test =
+    black
+    flake8
+    flake8-import-order
+    pep8-naming
+# This extra is for OpenSSH private keys that use bcrypt KDF
+# Versions: v3.1.3 - ignore_few_rounds, v3.1.5 - abi3
+ssh =
+    bcrypt >= 3.1.5
+
+[flake8]
+ignore = E203,E211,W503,W504,N818
+exclude = .tox,*.egg,.git,_build,.hypothesis
+select = E,W,F,N,I
+application-import-names = cryptography,cryptography_vectors,tests

crates/flake8_to_ruff/examples/jupyterhub.ini

@@ -0,0 +1,19 @@
+[flake8]
+# Ignore style and complexity
+# E: style errors
+# W: style warnings
+# C: complexity
+# D: docstring warnings (unused pydocstyle extension)
+# F841: local variable assigned but never used
+ignore = E, C, W, D, F841
+builtins = c, get_config
+exclude =
+    .cache,
+    .github,
+    docs,
+    jupyterhub/alembic*,
+    onbuild,
+    scripts,
+    share,
+    tools,
+    setup.py

crates/flake8_to_ruff/examples/manim.ini

@@ -0,0 +1,43 @@
+[flake8]
+# Exclude the grpc generated code
+exclude = ./manim/grpc/gen/*
+max-complexity = 15
+max-line-length = 88
+statistics = True
+# Prevents some flake8-rst-docstrings errors
+rst-roles = attr,class,func,meth,mod,obj,ref,doc,exc
+rst-directives = manim, SEEALSO, seealso
+docstring-convention=numpy
+
+select = A,A00,B,B9,C4,C90,D,E,F,F,PT,RST,SIM,W
+
+                # General Compatibility
+extend-ignore = E203, W503, D202, D212, D213, D404
+
+                # Misc
+                F401, F403, F405, F841, E501, E731, E402, F811, F821,
+
+                # Plug-in: flake8-builtins
+                A001, A002, A003,
+
+                # Plug-in: flake8-bugbear
+                B006, B007, B008, B009, B010, B903, B950,
+
+                # Plug-in: flake8-simplify
+                SIM105, SIM106, SIM119,
+
+                # Plug-in: flake8-comprehensions
+                C901
+
+                # Plug-in: flake8-pytest-style
+                PT001, PT004, PT006, PT011, PT018, PT022, PT023,
+
+                # Plug-in: flake8-docstrings
+                D100, D101, D102, D103, D104, D105, D106, D107,
+                D200, D202, D204, D205, D209,
+                D301,
+                D400, D401, D402, D403, D405, D406, D407, D409, D411, D412, D414,
+
+                # Plug-in: flake8-rst-docstrings
+                RST201, RST203, RST210, RST212, RST213, RST215,
+                RST301, RST303,

crates/flake8_to_ruff/examples/poetry.ini

@@ -0,0 +1,36 @@
+[flake8]
+min_python_version = 3.7.0
+max-line-length = 88
+ban-relative-imports = true
+# flake8-use-fstring: https://github.com/MichaelKim0407/flake8-use-fstring#--percent-greedy-and---format-greedy
+format-greedy = 1
+inline-quotes = double
+enable-extensions = TC, TC1
+type-checking-strict = true
+eradicate-whitelist-extend = ^-.*;
+extend-ignore =
+    # E203: Whitespace before ':' (pycqa/pycodestyle#373)
+    E203,
+    # SIM106: Handle error-cases first
+    SIM106,
+    # ANN101: Missing type annotation for self in method
+    ANN101,
+    # ANN102: Missing type annotation for cls in classmethod
+    ANN102,
+    # PIE781: assign-and-return
+    PIE781,
+    # PIE798 no-unnecessary-class: Consider using a module for namespacing instead
+    PIE798,
+per-file-ignores =
+    # TC002: Move third-party import '...' into a type-checking block
+    __init__.py:TC002,
+    # ANN201: Missing return type annotation for public function
+    tests/test_*:ANN201
+    tests/**/test_*:ANN201
+extend-exclude =
+    # Frozen and not subject to change in this repo:
+    get-poetry.py,
+    install-poetry.py,
+    # External to the project's coding standards:
+    tests/fixtures/*,
+    tests/**/fixtures/*,

crates/flake8_to_ruff/examples/python-discord.ini

@@ -0,0 +1,19 @@
+[flake8]
+max-line-length=120
+docstring-convention=all
+import-order-style=pycharm
+application_import_names=bot,tests
+exclude=.cache,.venv,.git,constants.py
+extend-ignore=
+    B311,W503,E226,S311,T000,E731
+    # Missing Docstrings
+    D100,D104,D105,D107,
+    # Docstring Whitespace
+    D203,D212,D214,D215,
+    # Docstring Quotes
+    D301,D302,
+    # Docstring Content
+    D400,D401,D402,D404,D405,D406,D407,D408,D409,D410,D411,D412,D413,D414,D416,D417
+    # Type Annotations
+    ANN002,ANN003,ANN101,ANN102,ANN204,ANN206,ANN401
+per-file-ignores=tests/*:D,ANN

crates/flake8_to_ruff/examples/requests.ini

@@ -0,0 +1,6 @@
+[flake8]
+ignore = E203, E501, W503
+per-file-ignores =
+    requests/__init__.py:E402, F401
+    requests/compat.py:E402, F401
+    tests/compat.py:F401

crates/flake8_to_ruff/pyproject.toml

@@ -0,0 +1,34 @@
+[project]
+name = "flake8-to-ruff"
+keywords = ["automation", "flake8", "pycodestyle", "pyflakes", "pylint", "clippy"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3.7",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3 :: Only",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Software Development :: Quality Assurance",
+]
+author = "Charlie Marsh"
+author_email = "charlie.r.marsh@gmail.com"
+description = "Convert existing Flake8 configuration to Ruff."
+requires-python = ">=3.7"
+
+[project.urls]
+repository = "https://github.com/astral-sh/ruff#subdirectory=crates/flake8_to_ruff"
+
+[build-system]
+requires = ["maturin>=1.0,<2.0"]
+build-backend = "maturin"
+
+[tool.maturin]
+bindings = "bin"
+strip = true

crates/flake8_to_ruff/src/black.rs

@@ -0,0 +1,13 @@
+//! Extract Black configuration settings from a pyproject.toml.
+
+use ruff_linter::line_width::LineLength;
+use ruff_linter::settings::types::PythonVersion;
+use serde::{Deserialize, Serialize};
+
+#[derive(Debug, PartialEq, Eq, Serialize, Deserialize, Default)]
+pub(crate) struct Black {
+    #[serde(alias = "line-length", alias = "line_length")]
+    pub(crate) line_length: Option<LineLength>,
+    #[serde(alias = "target-version", alias = "target_version")]
+    pub(crate) target_version: Option<Vec<PythonVersion>>,
+}

crates/flake8_to_ruff/src/converter.rs

@@ -0,0 +1,687 @@
+use std::collections::{HashMap, HashSet};
+use std::str::FromStr;
+
+use itertools::Itertools;
+
+use ruff_linter::line_width::LineLength;
+use ruff_linter::registry::Linter;
+use ruff_linter::rule_selector::RuleSelector;
+use ruff_linter::rules::flake8_pytest_style::types::{
+    ParametrizeNameType, ParametrizeValuesRowType, ParametrizeValuesType,
+};
+use ruff_linter::rules::flake8_quotes::settings::Quote;
+use ruff_linter::rules::flake8_tidy_imports::settings::Strictness;
+use ruff_linter::rules::pydocstyle::settings::Convention;
+use ruff_linter::settings::types::PythonVersion;
+use ruff_linter::settings::DEFAULT_SELECTORS;
+use ruff_linter::warn_user;
+use ruff_workspace::options::{
+    Flake8AnnotationsOptions, Flake8BugbearOptions, Flake8BuiltinsOptions, Flake8ErrMsgOptions,
+    Flake8PytestStyleOptions, Flake8QuotesOptions, Flake8TidyImportsOptions, LintCommonOptions,
+    LintOptions, McCabeOptions, Options, Pep8NamingOptions, PydocstyleOptions,
+};
+use ruff_workspace::pyproject::Pyproject;
+
+use super::external_config::ExternalConfig;
+use super::plugin::Plugin;
+use super::{parser, plugin};
+
+pub(crate) fn convert(
+    config: &HashMap<String, HashMap<String, Option<String>>>,
+    external_config: &ExternalConfig,
+    plugins: Option<Vec<Plugin>>,
+) -> Pyproject {
+    // Extract the Flake8 section.
+    let flake8 = config
+        .get("flake8")
+        .expect("Unable to find flake8 section in INI file");
+
+    // Extract all referenced rule code prefixes, to power plugin inference.
+    let mut referenced_codes: HashSet<RuleSelector> = HashSet::default();
+    for (key, value) in flake8 {
+        if let Some(value) = value {
+            match key.as_str() {
+                "select" | "ignore" | "extend-select" | "extend_select" | "extend-ignore"
+                | "extend_ignore" => {
+                    referenced_codes.extend(parser::parse_prefix_codes(value.as_ref()));
+                }
+                "per-file-ignores" | "per_file_ignores" => {
+                    if let Ok(per_file_ignores) =
+                        parser::parse_files_to_codes_mapping(value.as_ref())
+                    {
+                        for (_, codes) in parser::collect_per_file_ignores(per_file_ignores) {
+                            referenced_codes.extend(codes);
+                        }
+                    }
+                }
+                _ => {}
+            }
+        }
+    }
+
+    // Infer plugins, if not provided.
+    let plugins = plugins.unwrap_or_else(|| {
+        let from_options = plugin::infer_plugins_from_options(flake8);
+        if !from_options.is_empty() {
+            #[allow(clippy::print_stderr)]
+            {
+                eprintln!("Inferred plugins from settings: {from_options:#?}");
+            }
+        }
+        let from_codes = plugin::infer_plugins_from_codes(&referenced_codes);
+        if !from_codes.is_empty() {
+            #[allow(clippy::print_stderr)]
+            {
+                eprintln!("Inferred plugins from referenced codes: {from_codes:#?}");
+            }
+        }
+        from_options.into_iter().chain(from_codes).collect()
+    });
+
+    // Check if the user has specified a `select`. If not, we'll add our own
+    // default `select`, and populate it based on user plugins.
+    let mut select = flake8
+        .get("select")
+        .and_then(|value| {
+            value
+                .as_ref()
+                .map(|value| HashSet::from_iter(parser::parse_prefix_codes(value)))
+        })
+        .unwrap_or_else(|| resolve_select(&plugins));
+    let mut ignore: HashSet<RuleSelector> = flake8
+        .get("ignore")
+        .and_then(|value| {
+            value
+                .as_ref()
+                .map(|value| HashSet::from_iter(parser::parse_prefix_codes(value)))
+        })
+        .unwrap_or_default();
+
+    // Parse each supported option.
+    let mut options = Options::default();
+    let mut lint_options = LintCommonOptions::default();
+    let mut flake8_annotations = Flake8AnnotationsOptions::default();
+    let mut flake8_bugbear = Flake8BugbearOptions::default();
+    let mut flake8_builtins = Flake8BuiltinsOptions::default();
+    let mut flake8_errmsg = Flake8ErrMsgOptions::default();
+    let mut flake8_pytest_style = Flake8PytestStyleOptions::default();
+    let mut flake8_quotes = Flake8QuotesOptions::default();
+    let mut flake8_tidy_imports = Flake8TidyImportsOptions::default();
+    let mut mccabe = McCabeOptions::default();
+    let mut pep8_naming = Pep8NamingOptions::default();
+    let mut pydocstyle = PydocstyleOptions::default();
+    for (key, value) in flake8 {
+        if let Some(value) = value {
+            match key.as_str() {
+                // flake8
+                "builtins" => {
+                    options.builtins = Some(parser::parse_strings(value.as_ref()));
+                }
+                "max-line-length" | "max_line_length" => match LineLength::from_str(value) {
+                    Ok(line_length) => options.line_length = Some(line_length),
+                    Err(e) => {
+                        warn_user!("Unable to parse '{key}' property: {e}");
+                    }
+                },
+                "select" => {
+                    // No-op (handled above).
+                    select.extend(parser::parse_prefix_codes(value.as_ref()));
+                }
+                "ignore" => {
+                    // No-op (handled above).
+                }
+                "extend-select" | "extend_select" => {
+                    // Unlike Flake8, use a single explicit `select`.
+                    select.extend(parser::parse_prefix_codes(value.as_ref()));
+                }
+                "extend-ignore" | "extend_ignore" => {
+                    // Unlike Flake8, use a single explicit `ignore`.
+                    ignore.extend(parser::parse_prefix_codes(value.as_ref()));
+                }
+                "exclude" => {
+                    options.exclude = Some(parser::parse_strings(value.as_ref()));
+                }
+                "extend-exclude" | "extend_exclude" => {
+                    options.extend_exclude = Some(parser::parse_strings(value.as_ref()));
+                }
+                "per-file-ignores" | "per_file_ignores" => {
+                    match parser::parse_files_to_codes_mapping(value.as_ref()) {
+                        Ok(per_file_ignores) => {
+                            lint_options.per_file_ignores =
+                                Some(parser::collect_per_file_ignores(per_file_ignores));
+                        }
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                // flake8-bugbear
+                "extend-immutable-calls" | "extend_immutable_calls" => {
+                    flake8_bugbear.extend_immutable_calls =
+                        Some(parser::parse_strings(value.as_ref()));
+                }
+                // flake8-builtins
+                "builtins-ignorelist" | "builtins_ignorelist" => {
+                    flake8_builtins.builtins_ignorelist =
+                        Some(parser::parse_strings(value.as_ref()));
+                }
+                // flake8-annotations
+                "suppress-none-returning" | "suppress_none_returning" => {
+                    match parser::parse_bool(value.as_ref()) {
+                        Ok(bool) => flake8_annotations.suppress_none_returning = Some(bool),
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                "suppress-dummy-args" | "suppress_dummy_args" => {
+                    match parser::parse_bool(value.as_ref()) {
+                        Ok(bool) => flake8_annotations.suppress_dummy_args = Some(bool),
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                "mypy-init-return" | "mypy_init_return" => {
+                    match parser::parse_bool(value.as_ref()) {
+                        Ok(bool) => flake8_annotations.mypy_init_return = Some(bool),
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                "allow-star-arg-any" | "allow_star_arg_any" => {
+                    match parser::parse_bool(value.as_ref()) {
+                        Ok(bool) => flake8_annotations.allow_star_arg_any = Some(bool),
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                // flake8-quotes
+                "quotes" | "inline-quotes" | "inline_quotes" => match value.trim() {
+                    "'" | "single" => flake8_quotes.inline_quotes = Some(Quote::Single),
+                    "\"" | "double" => flake8_quotes.inline_quotes = Some(Quote::Double),
+                    _ => {
+                        warn_user!("Unexpected '{key}' value: {value}");
+                    }
+                },
+                "multiline-quotes" | "multiline_quotes" => match value.trim() {
+                    "'" | "single" => flake8_quotes.multiline_quotes = Some(Quote::Single),
+                    "\"" | "double" => flake8_quotes.multiline_quotes = Some(Quote::Double),
+                    _ => {
+                        warn_user!("Unexpected '{key}' value: {value}");
+                    }
+                },
+                "docstring-quotes" | "docstring_quotes" => match value.trim() {
+                    "'" | "single" => flake8_quotes.docstring_quotes = Some(Quote::Single),
+                    "\"" | "double" => flake8_quotes.docstring_quotes = Some(Quote::Double),
+                    _ => {
+                        warn_user!("Unexpected '{key}' value: {value}");
+                    }
+                },
+                "avoid-escape" | "avoid_escape" => match parser::parse_bool(value.as_ref()) {
+                    Ok(bool) => flake8_quotes.avoid_escape = Some(bool),
+                    Err(e) => {
+                        warn_user!("Unable to parse '{key}' property: {e}");
+                    }
+                },
+                // pep8-naming
+                "ignore-names" | "ignore_names" => {
+                    pep8_naming.ignore_names = Some(parser::parse_strings(value.as_ref()));
+                }
+                "classmethod-decorators" | "classmethod_decorators" => {
+                    pep8_naming.classmethod_decorators =
+                        Some(parser::parse_strings(value.as_ref()));
+                }
+                "staticmethod-decorators" | "staticmethod_decorators" => {
+                    pep8_naming.staticmethod_decorators =
+                        Some(parser::parse_strings(value.as_ref()));
+                }
+                // flake8-tidy-imports
+                "ban-relative-imports" | "ban_relative_imports" => match value.trim() {
+                    "true" => flake8_tidy_imports.ban_relative_imports = Some(Strictness::All),
+                    "parents" => {
+                        flake8_tidy_imports.ban_relative_imports = Some(Strictness::Parents);
+                    }
+                    _ => {
+                        warn_user!("Unexpected '{key}' value: {value}");
+                    }
+                },
+                // flake8-docstrings
+                "docstring-convention" => match value.trim() {
+                    "google" => pydocstyle.convention = Some(Convention::Google),
+                    "numpy" => pydocstyle.convention = Some(Convention::Numpy),
+                    "pep257" => pydocstyle.convention = Some(Convention::Pep257),
+                    "all" => pydocstyle.convention = None,
+                    _ => {
+                        warn_user!("Unexpected '{key}' value: {value}");
+                    }
+                },
+                // mccabe
+                "max-complexity" | "max_complexity" => match value.parse::<usize>() {
+                    Ok(max_complexity) => mccabe.max_complexity = Some(max_complexity),
+                    Err(e) => {
+                        warn_user!("Unable to parse '{key}' property: {e}");
+                    }
+                },
+                // flake8-errmsg
+                "errmsg-max-string-length" | "errmsg_max_string_length" => {
+                    match value.parse::<usize>() {
+                        Ok(max_string_length) => {
+                            flake8_errmsg.max_string_length = Some(max_string_length);
+                        }
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                // flake8-pytest-style
+                "pytest-fixture-no-parentheses" | "pytest_fixture_no_parentheses " => {
+                    match parser::parse_bool(value.as_ref()) {
+                        Ok(bool) => flake8_pytest_style.fixture_parentheses = Some(!bool),
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                "pytest-parametrize-names-type" | "pytest_parametrize_names_type" => {
+                    match value.trim() {
+                        "csv" => {
+                            flake8_pytest_style.parametrize_names_type =
+                                Some(ParametrizeNameType::Csv);
+                        }
+                        "tuple" => {
+                            flake8_pytest_style.parametrize_names_type =
+                                Some(ParametrizeNameType::Tuple);
+                        }
+                        "list" => {
+                            flake8_pytest_style.parametrize_names_type =
+                                Some(ParametrizeNameType::List);
+                        }
+                        _ => {
+                            warn_user!("Unexpected '{key}' value: {value}");
+                        }
+                    }
+                }
+                "pytest-parametrize-values-type" | "pytest_parametrize_values_type" => {
+                    match value.trim() {
+                        "tuple" => {
+                            flake8_pytest_style.parametrize_values_type =
+                                Some(ParametrizeValuesType::Tuple);
+                        }
+                        "list" => {
+                            flake8_pytest_style.parametrize_values_type =
+                                Some(ParametrizeValuesType::List);
+                        }
+                        _ => {
+                            warn_user!("Unexpected '{key}' value: {value}");
+                        }
+                    }
+                }
+                "pytest-parametrize-values-row-type" | "pytest_parametrize_values_row_type" => {
+                    match value.trim() {
+                        "tuple" => {
+                            flake8_pytest_style.parametrize_values_row_type =
+                                Some(ParametrizeValuesRowType::Tuple);
+                        }
+                        "list" => {
+                            flake8_pytest_style.parametrize_values_row_type =
+                                Some(ParametrizeValuesRowType::List);
+                        }
+                        _ => {
+                            warn_user!("Unexpected '{key}' value: {value}");
+                        }
+                    }
+                }
+                "pytest-raises-require-match-for" | "pytest_raises_require_match_for" => {
+                    flake8_pytest_style.raises_require_match_for =
+                        Some(parser::parse_strings(value.as_ref()));
+                }
+                "pytest-mark-no-parentheses" | "pytest_mark_no_parentheses" => {
+                    match parser::parse_bool(value.as_ref()) {
+                        Ok(bool) => flake8_pytest_style.mark_parentheses = Some(!bool),
+                        Err(e) => {
+                            warn_user!("Unable to parse '{key}' property: {e}");
+                        }
+                    }
+                }
+                // Unknown
+                _ => {
+                    warn_user!("Skipping unsupported property: {}", key);
+                }
+            }
+        }
+    }
+
+    // Deduplicate and sort.
+    lint_options.select = Some(
+        select
+            .into_iter()
+            .sorted_by_key(RuleSelector::prefix_and_code)
+            .collect(),
+    );
+    lint_options.ignore = Some(
+        ignore
+            .into_iter()
+            .sorted_by_key(RuleSelector::prefix_and_code)
+            .collect(),
+    );
+    if flake8_annotations != Flake8AnnotationsOptions::default() {
+        lint_options.flake8_annotations = Some(flake8_annotations);
+    }
+    if flake8_bugbear != Flake8BugbearOptions::default() {
+        lint_options.flake8_bugbear = Some(flake8_bugbear);
+    }
+    if flake8_builtins != Flake8BuiltinsOptions::default() {
+        lint_options.flake8_builtins = Some(flake8_builtins);
+    }
+    if flake8_errmsg != Flake8ErrMsgOptions::default() {
+        lint_options.flake8_errmsg = Some(flake8_errmsg);
+    }
+    if flake8_pytest_style != Flake8PytestStyleOptions::default() {
+        lint_options.flake8_pytest_style = Some(flake8_pytest_style);
+    }
+    if flake8_quotes != Flake8QuotesOptions::default() {
+        lint_options.flake8_quotes = Some(flake8_quotes);
+    }
+    if flake8_tidy_imports != Flake8TidyImportsOptions::default() {
+        lint_options.flake8_tidy_imports = Some(flake8_tidy_imports);
+    }
+    if mccabe != McCabeOptions::default() {
+        lint_options.mccabe = Some(mccabe);
+    }
+    if pep8_naming != Pep8NamingOptions::default() {
+        lint_options.pep8_naming = Some(pep8_naming);
+    }
+    if pydocstyle != PydocstyleOptions::default() {
+        lint_options.pydocstyle = Some(pydocstyle);
+    }
+
+    // Extract any settings from the existing `pyproject.toml`.
+    if let Some(black) = &external_config.black {
+        if let Some(line_length) = &black.line_length {
+            options.line_length = Some(*line_length);
+        }
+
+        if let Some(target_version) = &black.target_version {
+            if let Some(target_version) = target_version.iter().min() {
+                options.target_version = Some(*target_version);
+            }
+        }
+    }
+
+    if let Some(isort) = &external_config.isort {
+        if let Some(src_paths) = &isort.src_paths {
+            match options.src.as_mut() {
+                Some(src) => {
+                    src.extend_from_slice(src_paths);
+                }
+                None => {
+                    options.src = Some(src_paths.clone());
+                }
+            }
+        }
+    }
+
+    if let Some(project) = &external_config.project {
+        if let Some(requires_python) = &project.requires_python {
+            if options.target_version.is_none() {
+                options.target_version =
+                    PythonVersion::get_minimum_supported_version(requires_python);
+            }
+        }
+    }
+
+    if lint_options != LintCommonOptions::default() {
+        options.lint = Some(LintOptions {
+            common: lint_options,
+            ..LintOptions::default()
+        });
+    }
+
+    // Create the pyproject.toml.
+    Pyproject::new(options)
+}
+
+/// Resolve the set of enabled `RuleSelector` values for the given
+/// plugins.
+fn resolve_select(plugins: &[Plugin]) -> HashSet<RuleSelector> {
+    let mut select: HashSet<_> = DEFAULT_SELECTORS.iter().cloned().collect();
+    select.extend(plugins.iter().map(|p| Linter::from(p).into()));
+    select
+}
+
+#[cfg(test)]
+mod tests {
+    use std::collections::HashMap;
+    use std::str::FromStr;
+
+    use anyhow::Result;
+    use itertools::Itertools;
+    use pep440_rs::VersionSpecifiers;
+
+    use pretty_assertions::assert_eq;
+    use ruff_linter::line_width::LineLength;
+    use ruff_linter::registry::Linter;
+    use ruff_linter::rule_selector::RuleSelector;
+    use ruff_linter::rules::flake8_quotes;
+    use ruff_linter::rules::pydocstyle::settings::Convention;
+    use ruff_linter::settings::types::PythonVersion;
+    use ruff_workspace::options::{
+        Flake8QuotesOptions, LintCommonOptions, LintOptions, Options, PydocstyleOptions,
+    };
+    use ruff_workspace::pyproject::Pyproject;
+
+    use crate::converter::DEFAULT_SELECTORS;
+    use crate::pep621::Project;
+    use crate::ExternalConfig;
+
+    use super::super::plugin::Plugin;
+    use super::convert;
+
+    fn lint_default_options(plugins: impl IntoIterator<Item = RuleSelector>) -> LintCommonOptions {
+        LintCommonOptions {
+            ignore: Some(vec![]),
+            select: Some(
+                DEFAULT_SELECTORS
+                    .iter()
+                    .cloned()
+                    .chain(plugins)
+                    .sorted_by_key(RuleSelector::prefix_and_code)
+                    .collect(),
+            ),
+            ..LintCommonOptions::default()
+        }
+    }
+
+    #[test]
+    fn it_converts_empty() {
+        let actual = convert(
+            &HashMap::from([("flake8".to_string(), HashMap::default())]),
+            &ExternalConfig::default(),
+            None,
+        );
+        let expected = Pyproject::new(Options {
+            lint: Some(LintOptions {
+                common: lint_default_options([]),
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_converts_dashes() {
+        let actual = convert(
+            &HashMap::from([(
+                "flake8".to_string(),
+                HashMap::from([("max-line-length".to_string(), Some("100".to_string()))]),
+            )]),
+            &ExternalConfig::default(),
+            Some(vec![]),
+        );
+        let expected = Pyproject::new(Options {
+            line_length: Some(LineLength::try_from(100).unwrap()),
+            lint: Some(LintOptions {
+                common: lint_default_options([]),
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_converts_underscores() {
+        let actual = convert(
+            &HashMap::from([(
+                "flake8".to_string(),
+                HashMap::from([("max_line_length".to_string(), Some("100".to_string()))]),
+            )]),
+            &ExternalConfig::default(),
+            Some(vec![]),
+        );
+        let expected = Pyproject::new(Options {
+            line_length: Some(LineLength::try_from(100).unwrap()),
+            lint: Some(LintOptions {
+                common: lint_default_options([]),
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_ignores_parse_errors() {
+        let actual = convert(
+            &HashMap::from([(
+                "flake8".to_string(),
+                HashMap::from([("max_line_length".to_string(), Some("abc".to_string()))]),
+            )]),
+            &ExternalConfig::default(),
+            Some(vec![]),
+        );
+        let expected = Pyproject::new(Options {
+            lint: Some(LintOptions {
+                common: lint_default_options([]),
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_converts_plugin_options() {
+        let actual = convert(
+            &HashMap::from([(
+                "flake8".to_string(),
+                HashMap::from([("inline-quotes".to_string(), Some("single".to_string()))]),
+            )]),
+            &ExternalConfig::default(),
+            Some(vec![]),
+        );
+        let expected = Pyproject::new(Options {
+            lint: Some(LintOptions {
+                common: LintCommonOptions {
+                    flake8_quotes: Some(Flake8QuotesOptions {
+                        inline_quotes: Some(flake8_quotes::settings::Quote::Single),
+                        multiline_quotes: None,
+                        docstring_quotes: None,
+                        avoid_escape: None,
+                    }),
+                    ..lint_default_options([])
+                },
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_converts_docstring_conventions() {
+        let actual = convert(
+            &HashMap::from([(
+                "flake8".to_string(),
+                HashMap::from([(
+                    "docstring-convention".to_string(),
+                    Some("numpy".to_string()),
+                )]),
+            )]),
+            &ExternalConfig::default(),
+            Some(vec![Plugin::Flake8Docstrings]),
+        );
+        let expected = Pyproject::new(Options {
+            lint: Some(LintOptions {
+                common: LintCommonOptions {
+                    pydocstyle: Some(PydocstyleOptions {
+                        convention: Some(Convention::Numpy),
+                        ignore_decorators: None,
+                        property_decorators: None,
+                    }),
+                    ..lint_default_options([Linter::Pydocstyle.into()])
+                },
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_infers_plugins_if_omitted() {
+        let actual = convert(
+            &HashMap::from([(
+                "flake8".to_string(),
+                HashMap::from([("inline-quotes".to_string(), Some("single".to_string()))]),
+            )]),
+            &ExternalConfig::default(),
+            None,
+        );
+        let expected = Pyproject::new(Options {
+            lint: Some(LintOptions {
+                common: LintCommonOptions {
+                    flake8_quotes: Some(Flake8QuotesOptions {
+                        inline_quotes: Some(flake8_quotes::settings::Quote::Single),
+                        multiline_quotes: None,
+                        docstring_quotes: None,
+                        avoid_escape: None,
+                    }),
+                    ..lint_default_options([Linter::Flake8Quotes.into()])
+                },
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_converts_project_requires_python() -> Result<()> {
+        let actual = convert(
+            &HashMap::from([("flake8".to_string(), HashMap::default())]),
+            &ExternalConfig {
+                project: Some(&Project {
+                    requires_python: Some(VersionSpecifiers::from_str(">=3.8.16, <3.11")?),
+                }),
+                ..ExternalConfig::default()
+            },
+            Some(vec![]),
+        );
+        let expected = Pyproject::new(Options {
+            target_version: Some(PythonVersion::Py38),
+            lint: Some(LintOptions {
+                common: lint_default_options([]),
+                ..LintOptions::default()
+            }),
+            ..Options::default()
+        });
+        assert_eq!(actual, expected);
+
+        Ok(())
+    }
+}

crates/flake8_to_ruff/src/external_config.rs

@@ -0,0 +1,10 @@
+use super::black::Black;
+use super::isort::Isort;
+use super::pep621::Project;
+
+#[derive(Default)]
+pub(crate) struct ExternalConfig<'a> {
+    pub(crate) black: Option<&'a Black>,
+    pub(crate) isort: Option<&'a Isort>,
+    pub(crate) project: Option<&'a Project>,
+}

crates/flake8_to_ruff/src/isort.rs

@@ -0,0 +1,10 @@
+//! Extract isort configuration settings from a pyproject.toml.
+
+use serde::{Deserialize, Serialize};
+
+/// The [isort configuration](https://pycqa.github.io/isort/docs/configuration/config_files.html).
+#[derive(Debug, PartialEq, Eq, Serialize, Deserialize, Default)]
+pub(crate) struct Isort {
+    #[serde(alias = "src-paths", alias = "src_paths")]
+    pub(crate) src_paths: Option<Vec<String>>,
+}

crates/flake8_to_ruff/src/main.rs

@@ -0,0 +1,80 @@
+//! Utility to generate Ruff's `pyproject.toml` section from a Flake8 INI file.
+
+mod black;
+mod converter;
+mod external_config;
+mod isort;
+mod parser;
+mod pep621;
+mod plugin;
+mod pyproject;
+
+use std::path::PathBuf;
+
+use anyhow::Result;
+use clap::Parser;
+use configparser::ini::Ini;
+
+use crate::converter::convert;
+use crate::external_config::ExternalConfig;
+use crate::plugin::Plugin;
+use crate::pyproject::parse;
+use ruff_linter::logging::{set_up_logging, LogLevel};
+
+#[derive(Parser)]
+#[command(
+    about = "Convert existing Flake8 configuration to Ruff.",
+    long_about = None
+)]
+struct Args {
+    /// Path to the Flake8 configuration file (e.g., `setup.cfg`, `tox.ini`, or
+    /// `.flake8`).
+    #[arg(required = true)]
+    file: PathBuf,
+    /// Optional path to a `pyproject.toml` file, used to ensure compatibility
+    /// with Black.
+    #[arg(long)]
+    pyproject: Option<PathBuf>,
+    /// List of plugins to enable.
+    #[arg(long, value_delimiter = ',')]
+    plugin: Option<Vec<Plugin>>,
+}
+
+fn main() -> Result<()> {
+    set_up_logging(&LogLevel::Default)?;
+
+    let args = Args::parse();
+
+    // Read the INI file.
+    let mut ini = Ini::new_cs();
+    ini.set_multiline(true);
+    let config = ini.load(args.file).map_err(|msg| anyhow::anyhow!(msg))?;
+
+    // Read the pyproject.toml file.
+    let pyproject = args.pyproject.map(parse).transpose()?;
+    let external_config = pyproject
+        .as_ref()
+        .and_then(|pyproject| pyproject.tool.as_ref())
+        .map(|tool| ExternalConfig {
+            black: tool.black.as_ref(),
+            isort: tool.isort.as_ref(),
+            ..Default::default()
+        })
+        .unwrap_or_default();
+    let external_config = ExternalConfig {
+        project: pyproject
+            .as_ref()
+            .and_then(|pyproject| pyproject.project.as_ref()),
+        ..external_config
+    };
+
+    // Create Ruff's pyproject.toml section.
+    let pyproject = convert(&config, &external_config, args.plugin);
+
+    #[allow(clippy::print_stdout)]
+    {
+        println!("{}", toml::to_string_pretty(&pyproject)?);
+    }
+
+    Ok(())
+}

crates/flake8_to_ruff/src/parser.rs

@@ -0,0 +1,391 @@
+use std::str::FromStr;
+
+use anyhow::{bail, Result};
+use once_cell::sync::Lazy;
+use regex::Regex;
+use rustc_hash::FxHashMap;
+
+use ruff_linter::settings::types::PatternPrefixPair;
+use ruff_linter::{warn_user, RuleSelector};
+
+static COMMA_SEPARATED_LIST_RE: Lazy<Regex> = Lazy::new(|| Regex::new(r"[,\s]").unwrap());
+
+/// Parse a comma-separated list of `RuleSelector` values (e.g.,
+/// "F401,E501").
+pub(crate) fn parse_prefix_codes(value: &str) -> Vec<RuleSelector> {
+    let mut codes: Vec<RuleSelector> = vec![];
+    for code in COMMA_SEPARATED_LIST_RE.split(value) {
+        let code = code.trim();
+        if code.is_empty() {
+            continue;
+        }
+        if let Ok(code) = RuleSelector::from_str(code) {
+            codes.push(code);
+        } else {
+            warn_user!("Unsupported prefix code: {code}");
+        }
+    }
+    codes
+}
+
+/// Parse a comma-separated list of strings (e.g., "__init__.py,__main__.py").
+pub(crate) fn parse_strings(value: &str) -> Vec<String> {
+    COMMA_SEPARATED_LIST_RE
+        .split(value)
+        .map(str::trim)
+        .filter(|part| !part.is_empty())
+        .map(String::from)
+        .collect()
+}
+
+/// Parse a boolean.
+pub(crate) fn parse_bool(value: &str) -> Result<bool> {
+    match value.trim() {
+        "true" => Ok(true),
+        "false" => Ok(false),
+        _ => bail!("Unexpected boolean value: {value}"),
+    }
+}
+
+#[derive(Debug)]
+struct Token {
+    token_name: TokenType,
+    src: String,
+}
+
+#[derive(Debug, Copy, Clone)]
+enum TokenType {
+    Code,
+    File,
+    Colon,
+    Comma,
+    Ws,
+    Eof,
+}
+
+struct State {
+    seen_sep: bool,
+    seen_colon: bool,
+    filenames: Vec<String>,
+    codes: Vec<String>,
+}
+
+impl State {
+    const fn new() -> Self {
+        Self {
+            seen_sep: true,
+            seen_colon: false,
+            filenames: vec![],
+            codes: vec![],
+        }
+    }
+
+    /// Generate the list of `StrRuleCodePair` pairs for the current
+    /// state.
+    fn parse(&self) -> Vec<PatternPrefixPair> {
+        let mut codes: Vec<PatternPrefixPair> = vec![];
+        for code in &self.codes {
+            if let Ok(code) = RuleSelector::from_str(code) {
+                for filename in &self.filenames {
+                    codes.push(PatternPrefixPair {
+                        pattern: filename.clone(),
+                        prefix: code.clone(),
+                    });
+                }
+            } else {
+                warn_user!("Unsupported prefix code: {code}");
+            }
+        }
+        codes
+    }
+}
+
+/// Tokenize the raw 'files-to-codes' mapping.
+fn tokenize_files_to_codes_mapping(value: &str) -> Vec<Token> {
+    let mut tokens = vec![];
+    let mut i = 0;
+    while i < value.len() {
+        for (token_re, token_name) in [
+            (
+                Regex::new(r"([A-Z]+[0-9]*)(?:$|\s|,)").unwrap(),
+                TokenType::Code,
+            ),
+            (Regex::new(r"([^\s:,]+)").unwrap(), TokenType::File),
+            (Regex::new(r"(\s*:\s*)").unwrap(), TokenType::Colon),
+            (Regex::new(r"(\s*,\s*)").unwrap(), TokenType::Comma),
+            (Regex::new(r"(\s+)").unwrap(), TokenType::Ws),
+        ] {
+            if let Some(cap) = token_re.captures(&value[i..]) {
+                let mat = cap.get(1).unwrap();
+                if mat.start() == 0 {
+                    tokens.push(Token {
+                        token_name,
+                        src: mat.as_str().trim().to_string(),
+                    });
+                    i += mat.end();
+                    break;
+                }
+            }
+        }
+    }
+    tokens.push(Token {
+        token_name: TokenType::Eof,
+        src: String::new(),
+    });
+    tokens
+}
+
+/// Parse a 'files-to-codes' mapping, mimicking Flake8's internal logic.
+/// See: <https://github.com/PyCQA/flake8/blob/7dfe99616fc2f07c0017df2ba5fa884158f3ea8a/src/flake8/utils.py#L45>
+pub(crate) fn parse_files_to_codes_mapping(value: &str) -> Result<Vec<PatternPrefixPair>> {
+    if value.trim().is_empty() {
+        return Ok(vec![]);
+    }
+    let mut codes: Vec<PatternPrefixPair> = vec![];
+    let mut state = State::new();
+    for token in tokenize_files_to_codes_mapping(value) {
+        if matches!(token.token_name, TokenType::Comma | TokenType::Ws) {
+            state.seen_sep = true;
+        } else if !state.seen_colon {
+            if matches!(token.token_name, TokenType::Colon) {
+                state.seen_colon = true;
+                state.seen_sep = true;
+            } else if state.seen_sep && matches!(token.token_name, TokenType::File) {
+                state.filenames.push(token.src);
+                state.seen_sep = false;
+            } else {
+                bail!("Unexpected token: {:?}", token.token_name);
+            }
+        } else {
+            if matches!(token.token_name, TokenType::Eof) {
+                codes.extend(state.parse());
+                state = State::new();
+            } else if state.seen_sep && matches!(token.token_name, TokenType::Code) {
+                state.codes.push(token.src);
+                state.seen_sep = false;
+            } else if state.seen_sep && matches!(token.token_name, TokenType::File) {
+                codes.extend(state.parse());
+                state = State::new();
+                state.filenames.push(token.src);
+                state.seen_sep = false;
+            } else {
+                bail!("Unexpected token: {:?}", token.token_name);
+            }
+        }
+    }
+    Ok(codes)
+}
+
+/// Collect a list of `PatternPrefixPair` structs as a `BTreeMap`.
+pub(crate) fn collect_per_file_ignores(
+    pairs: Vec<PatternPrefixPair>,
+) -> FxHashMap<String, Vec<RuleSelector>> {
+    let mut per_file_ignores: FxHashMap<String, Vec<RuleSelector>> = FxHashMap::default();
+    for pair in pairs {
+        per_file_ignores
+            .entry(pair.pattern)
+            .or_default()
+            .push(pair.prefix);
+    }
+    per_file_ignores
+}
+
+#[cfg(test)]
+mod tests {
+    use anyhow::Result;
+
+    use ruff_linter::codes;
+    use ruff_linter::registry::Linter;
+    use ruff_linter::settings::types::PatternPrefixPair;
+    use ruff_linter::RuleSelector;
+
+    use super::{parse_files_to_codes_mapping, parse_prefix_codes, parse_strings};
+
+    #[test]
+    fn it_parses_prefix_codes() {
+        let actual = parse_prefix_codes("");
+        let expected: Vec<RuleSelector> = vec![];
+        assert_eq!(actual, expected);
+
+        let actual = parse_prefix_codes(" ");
+        let expected: Vec<RuleSelector> = vec![];
+        assert_eq!(actual, expected);
+
+        let actual = parse_prefix_codes("F401");
+        let expected = vec![codes::Pyflakes::_401.into()];
+        assert_eq!(actual, expected);
+
+        let actual = parse_prefix_codes("F401,");
+        let expected = vec![codes::Pyflakes::_401.into()];
+        assert_eq!(actual, expected);
+
+        let actual = parse_prefix_codes("F401,E501");
+        let expected = vec![
+            codes::Pyflakes::_401.into(),
+            codes::Pycodestyle::E501.into(),
+        ];
+        assert_eq!(actual, expected);
+
+        let actual = parse_prefix_codes("F401, E501");
+        let expected = vec![
+            codes::Pyflakes::_401.into(),
+            codes::Pycodestyle::E501.into(),
+        ];
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_parses_strings() {
+        let actual = parse_strings("");
+        let expected: Vec<String> = vec![];
+        assert_eq!(actual, expected);
+
+        let actual = parse_strings(" ");
+        let expected: Vec<String> = vec![];
+        assert_eq!(actual, expected);
+
+        let actual = parse_strings("__init__.py");
+        let expected = vec!["__init__.py".to_string()];
+        assert_eq!(actual, expected);
+
+        let actual = parse_strings("__init__.py,");
+        let expected = vec!["__init__.py".to_string()];
+        assert_eq!(actual, expected);
+
+        let actual = parse_strings("__init__.py,__main__.py");
+        let expected = vec!["__init__.py".to_string(), "__main__.py".to_string()];
+        assert_eq!(actual, expected);
+
+        let actual = parse_strings("__init__.py, __main__.py");
+        let expected = vec!["__init__.py".to_string(), "__main__.py".to_string()];
+        assert_eq!(actual, expected);
+    }
+
+    #[test]
+    fn it_parse_files_to_codes_mapping() -> Result<()> {
+        let actual = parse_files_to_codes_mapping("")?;
+        let expected: Vec<PatternPrefixPair> = vec![];
+        assert_eq!(actual, expected);
+
+        let actual = parse_files_to_codes_mapping(" ")?;
+        let expected: Vec<PatternPrefixPair> = vec![];
+        assert_eq!(actual, expected);
+
+        // Ex) locust
+        let actual = parse_files_to_codes_mapping(
+            "per-file-ignores =
+    locust/test/*: F841
+    examples/*: F841
+    *.pyi: E302,E704"
+                .strip_prefix("per-file-ignores =")
+                .unwrap(),
+        )?;
+        let expected: Vec<PatternPrefixPair> = vec![
+            PatternPrefixPair {
+                pattern: "locust/test/*".to_string(),
+                prefix: codes::Pyflakes::_841.into(),
+            },
+            PatternPrefixPair {
+                pattern: "examples/*".to_string(),
+                prefix: codes::Pyflakes::_841.into(),
+            },
+        ];
+        assert_eq!(actual, expected);
+
+        // Ex) celery
+        let actual = parse_files_to_codes_mapping(
+            "per-file-ignores =
+   t/*,setup.py,examples/*,docs/*,extra/*:
+       D,"
+            .strip_prefix("per-file-ignores =")
+            .unwrap(),
+        )?;
+        let expected: Vec<PatternPrefixPair> = vec![
+            PatternPrefixPair {
+                pattern: "t/*".to_string(),
+                prefix: Linter::Pydocstyle.into(),
+            },
+            PatternPrefixPair {
+                pattern: "setup.py".to_string(),
+                prefix: Linter::Pydocstyle.into(),
+            },
+            PatternPrefixPair {
+                pattern: "examples/*".to_string(),
+                prefix: Linter::Pydocstyle.into(),
+            },
+            PatternPrefixPair {
+                pattern: "docs/*".to_string(),
+                prefix: Linter::Pydocstyle.into(),
+            },
+            PatternPrefixPair {
+                pattern: "extra/*".to_string(),
+                prefix: Linter::Pydocstyle.into(),
+            },
+        ];
+        assert_eq!(actual, expected);
+
+        // Ex) scrapy
+        let actual = parse_files_to_codes_mapping(
+            "per-file-ignores =
+    scrapy/__init__.py:E402
+    scrapy/core/downloader/handlers/http.py:F401
+    scrapy/http/__init__.py:F401
+    scrapy/linkextractors/__init__.py:E402,F401
+    scrapy/selector/__init__.py:F401
+    scrapy/spiders/__init__.py:E402,F401
+    scrapy/utils/url.py:F403,F405
+    tests/test_loader.py:E741"
+                .strip_prefix("per-file-ignores =")
+                .unwrap(),
+        )?;
+        let expected: Vec<PatternPrefixPair> = vec![
+            PatternPrefixPair {
+                pattern: "scrapy/__init__.py".to_string(),
+                prefix: codes::Pycodestyle::E402.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/core/downloader/handlers/http.py".to_string(),
+                prefix: codes::Pyflakes::_401.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/http/__init__.py".to_string(),
+                prefix: codes::Pyflakes::_401.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/linkextractors/__init__.py".to_string(),
+                prefix: codes::Pycodestyle::E402.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/linkextractors/__init__.py".to_string(),
+                prefix: codes::Pyflakes::_401.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/selector/__init__.py".to_string(),
+                prefix: codes::Pyflakes::_401.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/spiders/__init__.py".to_string(),
+                prefix: codes::Pycodestyle::E402.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/spiders/__init__.py".to_string(),
+                prefix: codes::Pyflakes::_401.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/utils/url.py".to_string(),
+                prefix: codes::Pyflakes::_403.into(),
+            },
+            PatternPrefixPair {
+                pattern: "scrapy/utils/url.py".to_string(),
+                prefix: codes::Pyflakes::_405.into(),
+            },
+            PatternPrefixPair {
+                pattern: "tests/test_loader.py".to_string(),
+                prefix: codes::Pycodestyle::E741.into(),
+            },
+        ];
+        assert_eq!(actual, expected);
+
+        Ok(())
+    }
+}

crates/flake8_to_ruff/src/pep621.rs

@@ -0,0 +1,10 @@
+//! Extract PEP 621 configuration settings from a pyproject.toml.
+
+use pep440_rs::VersionSpecifiers;
+use serde::{Deserialize, Serialize};
+
+#[derive(Debug, PartialEq, Eq, Serialize, Deserialize, Default)]
+pub(crate) struct Project {
+    #[serde(alias = "requires-python", alias = "requires_python")]
+    pub(crate) requires_python: Option<VersionSpecifiers>,
+}

crates/flake8_to_ruff/src/plugin.rs

@@ -0,0 +1,368 @@
+use std::collections::{BTreeSet, HashMap, HashSet};
+use std::fmt;
+use std::str::FromStr;
+
+use anyhow::anyhow;
+use ruff_linter::registry::Linter;
+use ruff_linter::rule_selector::PreviewOptions;
+use ruff_linter::RuleSelector;
+
+#[derive(Copy, Clone, Ord, PartialOrd, Eq, PartialEq)]
+pub enum Plugin {
+    Flake82020,
+    Flake8Annotations,
+    Flake8Bandit,
+    Flake8BlindExcept,
+    Flake8BooleanTrap,
+    Flake8Bugbear,
+    Flake8Builtins,
+    Flake8Commas,
+    Flake8Comprehensions,
+    Flake8Datetimez,
+    Flake8Debugger,
+    Flake8Docstrings,
+    Flake8Eradicate,
+    Flake8ErrMsg,
+    Flake8Executable,
+    Flake8ImplicitStrConcat,
+    Flake8ImportConventions,
+    Flake8NoPep420,
+    Flake8Pie,
+    Flake8Print,
+    Flake8PytestStyle,
+    Flake8Quotes,
+    Flake8Return,
+    Flake8Simplify,
+    Flake8TidyImports,
+    Flake8TypeChecking,
+    Flake8UnusedArguments,
+    Flake8UsePathlib,
+    McCabe,
+    PEP8Naming,
+    PandasVet,
+    Pyupgrade,
+    Tryceratops,
+}
+
+impl FromStr for Plugin {
+    type Err = anyhow::Error;
+
+    fn from_str(string: &str) -> Result<Self, Self::Err> {
+        match string {
+            "flake8-2020" => Ok(Plugin::Flake82020),
+            "flake8-annotations" => Ok(Plugin::Flake8Annotations),
+            "flake8-bandit" => Ok(Plugin::Flake8Bandit),
+            "flake8-blind-except" => Ok(Plugin::Flake8BlindExcept),
+            "flake8-boolean-trap" => Ok(Plugin::Flake8BooleanTrap),
+            "flake8-bugbear" => Ok(Plugin::Flake8Bugbear),
+            "flake8-builtins" => Ok(Plugin::Flake8Builtins),
+            "flake8-commas" => Ok(Plugin::Flake8Commas),
+            "flake8-comprehensions" => Ok(Plugin::Flake8Comprehensions),
+            "flake8-datetimez" => Ok(Plugin::Flake8Datetimez),
+            "flake8-debugger" => Ok(Plugin::Flake8Debugger),
+            "flake8-docstrings" => Ok(Plugin::Flake8Docstrings),
+            "flake8-eradicate" => Ok(Plugin::Flake8Eradicate),
+            "flake8-errmsg" => Ok(Plugin::Flake8ErrMsg),
+            "flake8-executable" => Ok(Plugin::Flake8Executable),
+            "flake8-implicit-str-concat" => Ok(Plugin::Flake8ImplicitStrConcat),
+            "flake8-import-conventions" => Ok(Plugin::Flake8ImportConventions),
+            "flake8-no-pep420" => Ok(Plugin::Flake8NoPep420),
+            "flake8-pie" => Ok(Plugin::Flake8Pie),
+            "flake8-print" => Ok(Plugin::Flake8Print),
+            "flake8-pytest-style" => Ok(Plugin::Flake8PytestStyle),
+            "flake8-quotes" => Ok(Plugin::Flake8Quotes),
+            "flake8-return" => Ok(Plugin::Flake8Return),
+            "flake8-simplify" => Ok(Plugin::Flake8Simplify),
+            "flake8-tidy-imports" => Ok(Plugin::Flake8TidyImports),
+            "flake8-type-checking" => Ok(Plugin::Flake8TypeChecking),
+            "flake8-unused-arguments" => Ok(Plugin::Flake8UnusedArguments),
+            "flake8-use-pathlib" => Ok(Plugin::Flake8UsePathlib),
+            "mccabe" => Ok(Plugin::McCabe),
+            "pep8-naming" => Ok(Plugin::PEP8Naming),
+            "pandas-vet" => Ok(Plugin::PandasVet),
+            "pyupgrade" => Ok(Plugin::Pyupgrade),
+            "tryceratops" => Ok(Plugin::Tryceratops),
+            _ => Err(anyhow!("Unknown plugin: {string}")),
+        }
+    }
+}
+
+impl fmt::Debug for Plugin {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(
+            f,
+            "{}",
+            match self {
+                Plugin::Flake82020 => "flake8-2020",
+                Plugin::Flake8Annotations => "flake8-annotations",
+                Plugin::Flake8Bandit => "flake8-bandit",
+                Plugin::Flake8BlindExcept => "flake8-blind-except",
+                Plugin::Flake8BooleanTrap => "flake8-boolean-trap",
+                Plugin::Flake8Bugbear => "flake8-bugbear",
+                Plugin::Flake8Builtins => "flake8-builtins",
+                Plugin::Flake8Commas => "flake8-commas",
+                Plugin::Flake8Comprehensions => "flake8-comprehensions",
+                Plugin::Flake8Datetimez => "flake8-datetimez",
+                Plugin::Flake8Debugger => "flake8-debugger",
+                Plugin::Flake8Docstrings => "flake8-docstrings",
+                Plugin::Flake8Eradicate => "flake8-eradicate",
+                Plugin::Flake8ErrMsg => "flake8-errmsg",
+                Plugin::Flake8Executable => "flake8-executable",
+                Plugin::Flake8ImplicitStrConcat => "flake8-implicit-str-concat",
+                Plugin::Flake8ImportConventions => "flake8-import-conventions",
+                Plugin::Flake8NoPep420 => "flake8-no-pep420",
+                Plugin::Flake8Pie => "flake8-pie",
+                Plugin::Flake8Print => "flake8-print",
+                Plugin::Flake8PytestStyle => "flake8-pytest-style",
+                Plugin::Flake8Quotes => "flake8-quotes",
+                Plugin::Flake8Return => "flake8-return",
+                Plugin::Flake8Simplify => "flake8-simplify",
+                Plugin::Flake8TidyImports => "flake8-tidy-imports",
+                Plugin::Flake8TypeChecking => "flake8-type-checking",
+                Plugin::Flake8UnusedArguments => "flake8-unused-arguments",
+                Plugin::Flake8UsePathlib => "flake8-use-pathlib",
+                Plugin::McCabe => "mccabe",
+                Plugin::PEP8Naming => "pep8-naming",
+                Plugin::PandasVet => "pandas-vet",
+                Plugin::Pyupgrade => "pyupgrade",
+                Plugin::Tryceratops => "tryceratops",
+            }
+        )
+    }
+}
+
+impl From<&Plugin> for Linter {
+    fn from(plugin: &Plugin) -> Self {
+        match plugin {
+            Plugin::Flake82020 => Linter::Flake82020,
+            Plugin::Flake8Annotations => Linter::Flake8Annotations,
+            Plugin::Flake8Bandit => Linter::Flake8Bandit,
+            Plugin::Flake8BlindExcept => Linter::Flake8BlindExcept,
+            Plugin::Flake8BooleanTrap => Linter::Flake8BooleanTrap,
+            Plugin::Flake8Bugbear => Linter::Flake8Bugbear,
+            Plugin::Flake8Builtins => Linter::Flake8Builtins,
+            Plugin::Flake8Commas => Linter::Flake8Commas,
+            Plugin::Flake8Comprehensions => Linter::Flake8Comprehensions,
+            Plugin::Flake8Datetimez => Linter::Flake8Datetimez,
+            Plugin::Flake8Debugger => Linter::Flake8Debugger,
+            Plugin::Flake8Docstrings => Linter::Pydocstyle,
+            Plugin::Flake8Eradicate => Linter::Eradicate,
+            Plugin::Flake8ErrMsg => Linter::Flake8ErrMsg,
+            Plugin::Flake8Executable => Linter::Flake8Executable,
+            Plugin::Flake8ImplicitStrConcat => Linter::Flake8ImplicitStrConcat,
+            Plugin::Flake8ImportConventions => Linter::Flake8ImportConventions,
+            Plugin::Flake8NoPep420 => Linter::Flake8NoPep420,
+            Plugin::Flake8Pie => Linter::Flake8Pie,
+            Plugin::Flake8Print => Linter::Flake8Print,
+            Plugin::Flake8PytestStyle => Linter::Flake8PytestStyle,
+            Plugin::Flake8Quotes => Linter::Flake8Quotes,
+            Plugin::Flake8Return => Linter::Flake8Return,
+            Plugin::Flake8Simplify => Linter::Flake8Simplify,
+            Plugin::Flake8TidyImports => Linter::Flake8TidyImports,
+            Plugin::Flake8TypeChecking => Linter::Flake8TypeChecking,
+            Plugin::Flake8UnusedArguments => Linter::Flake8UnusedArguments,
+            Plugin::Flake8UsePathlib => Linter::Flake8UsePathlib,
+            Plugin::McCabe => Linter::McCabe,
+            Plugin::PEP8Naming => Linter::PEP8Naming,
+            Plugin::PandasVet => Linter::PandasVet,
+            Plugin::Pyupgrade => Linter::Pyupgrade,
+            Plugin::Tryceratops => Linter::Tryceratops,
+        }
+    }
+}
+
+/// Infer the enabled plugins based on user-provided options.
+///
+/// For example, if the user specified a `mypy-init-return` setting, we should
+/// infer that `flake8-annotations` is active.
+pub(crate) fn infer_plugins_from_options(flake8: &HashMap<String, Option<String>>) -> Vec<Plugin> {
+    let mut plugins = BTreeSet::new();
+    for key in flake8.keys() {
+        match key.as_str() {
+            // flake8-annotations
+            "suppress-none-returning" | "suppress_none_returning" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            "suppress-dummy-args" | "suppress_dummy_args" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            "allow-untyped-defs" | "allow_untyped_defs" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            "allow-untyped-nested" | "allow_untyped_nested" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            "mypy-init-return" | "mypy_init_return" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            "dispatch-decorators" | "dispatch_decorators" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            "overload-decorators" | "overload_decorators" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            "allow-star-arg-any" | "allow_star_arg_any" => {
+                plugins.insert(Plugin::Flake8Annotations);
+            }
+            // flake8-bugbear
+            "extend-immutable-calls" | "extend_immutable_calls" => {
+                plugins.insert(Plugin::Flake8Bugbear);
+            }
+            // flake8-builtins
+            "builtins-ignorelist" | "builtins_ignorelist" => {
+                plugins.insert(Plugin::Flake8Builtins);
+            }
+            // flake8-docstrings
+            "docstring-convention" | "docstring_convention" => {
+                plugins.insert(Plugin::Flake8Docstrings);
+            }
+            // flake8-eradicate
+            "eradicate-aggressive" | "eradicate_aggressive" => {
+                plugins.insert(Plugin::Flake8Eradicate);
+            }
+            "eradicate-whitelist" | "eradicate_whitelist" => {
+                plugins.insert(Plugin::Flake8Eradicate);
+            }
+            "eradicate-whitelist-extend" | "eradicate_whitelist_extend" => {
+                plugins.insert(Plugin::Flake8Eradicate);
+            }
+            // flake8-pytest-style
+            "pytest-fixture-no-parentheses" | "pytest_fixture_no_parentheses " => {
+                plugins.insert(Plugin::Flake8PytestStyle);
+            }
+            "pytest-parametrize-names-type" | "pytest_parametrize_names_type" => {
+                plugins.insert(Plugin::Flake8PytestStyle);
+            }
+            "pytest-parametrize-values-type" | "pytest_parametrize_values_type" => {
+                plugins.insert(Plugin::Flake8PytestStyle);
+            }
+            "pytest-parametrize-values-row-type" | "pytest_parametrize_values_row_type" => {
+                plugins.insert(Plugin::Flake8PytestStyle);
+            }
+            "pytest-raises-require-match-for" | "pytest_raises_require_match_for" => {
+                plugins.insert(Plugin::Flake8PytestStyle);
+            }
+            "pytest-mark-no-parentheses" | "pytest_mark_no_parentheses" => {
+                plugins.insert(Plugin::Flake8PytestStyle);
+            }
+            // flake8-quotes
+            "quotes" | "inline-quotes" | "inline_quotes" => {
+                plugins.insert(Plugin::Flake8Quotes);
+            }
+            "multiline-quotes" | "multiline_quotes" => {
+                plugins.insert(Plugin::Flake8Quotes);
+            }
+            "docstring-quotes" | "docstring_quotes" => {
+                plugins.insert(Plugin::Flake8Quotes);
+            }
+            "avoid-escape" | "avoid_escape" => {
+                plugins.insert(Plugin::Flake8Quotes);
+            }
+            // flake8-tidy-imports
+            "ban-relative-imports" | "ban_relative_imports" => {
+                plugins.insert(Plugin::Flake8TidyImports);
+            }
+            "banned-modules" | "banned_modules" => {
+                plugins.insert(Plugin::Flake8TidyImports);
+            }
+            // mccabe
+            "max-complexity" | "max_complexity" => {
+                plugins.insert(Plugin::McCabe);
+            }
+            // pep8-naming
+            "ignore-names" | "ignore_names" => {
+                plugins.insert(Plugin::PEP8Naming);
+            }
+            "classmethod-decorators" | "classmethod_decorators" => {
+                plugins.insert(Plugin::PEP8Naming);
+            }
+            "staticmethod-decorators" | "staticmethod_decorators" => {
+                plugins.insert(Plugin::PEP8Naming);
+            }
+            "max-string-length" | "max_string_length" => {
+                plugins.insert(Plugin::Flake8ErrMsg);
+            }
+            _ => {}
+        }
+    }
+    Vec::from_iter(plugins)
+}
+
+/// Infer the enabled plugins based on the referenced prefixes.
+///
+/// For example, if the user ignores `ANN101`, we should infer that
+/// `flake8-annotations` is active.
+pub(crate) fn infer_plugins_from_codes(selectors: &HashSet<RuleSelector>) -> Vec<Plugin> {
+    // Ignore cases in which we've knowingly changed rule prefixes.
+    [
+        Plugin::Flake82020,
+        Plugin::Flake8Annotations,
+        Plugin::Flake8Bandit,
+        // Plugin::Flake8BlindExcept,
+        Plugin::Flake8BooleanTrap,
+        Plugin::Flake8Bugbear,
+        Plugin::Flake8Builtins,
+        // Plugin::Flake8Commas,
+        Plugin::Flake8Comprehensions,
+        Plugin::Flake8Datetimez,
+        Plugin::Flake8Debugger,
+        Plugin::Flake8Docstrings,
+        // Plugin::Flake8Eradicate,
+        Plugin::Flake8ErrMsg,
+        Plugin::Flake8Executable,
+        Plugin::Flake8ImplicitStrConcat,
+        // Plugin::Flake8ImportConventions,
+        Plugin::Flake8NoPep420,
+        Plugin::Flake8Pie,
+        Plugin::Flake8Print,
+        Plugin::Flake8PytestStyle,
+        Plugin::Flake8Quotes,
+        Plugin::Flake8Return,
+        Plugin::Flake8Simplify,
+        // Plugin::Flake8TidyImports,
+        // Plugin::Flake8TypeChecking,
+        Plugin::Flake8UnusedArguments,
+        // Plugin::Flake8UsePathlib,
+        Plugin::McCabe,
+        Plugin::PEP8Naming,
+        Plugin::PandasVet,
+        Plugin::Tryceratops,
+    ]
+    .into_iter()
+    .filter(|plugin| {
+        for selector in selectors {
+            if selector
+                .rules(&PreviewOptions::default())
+                .any(|rule| Linter::from(plugin).rules().any(|r| r == rule))
+            {
+                return true;
+            }
+        }
+        false
+    })
+    .collect()
+}
+
+#[cfg(test)]
+mod tests {
+    use std::collections::HashMap;
+
+    use super::{infer_plugins_from_options, Plugin};
+
+    #[test]
+    fn it_infers_plugins() {
+        let actual = infer_plugins_from_options(&HashMap::from([(
+            "inline-quotes".to_string(),
+            Some("single".to_string()),
+        )]));
+        let expected = vec![Plugin::Flake8Quotes];
+        assert_eq!(actual, expected);
+
+        let actual = infer_plugins_from_options(&HashMap::from([(
+            "staticmethod-decorators".to_string(),
+            Some("[]".to_string()),
+        )]));
+        let expected = vec![Plugin::PEP8Naming];
+        assert_eq!(actual, expected);
+    }
+}

crates/flake8_to_ruff/src/pyproject.rs

@@ -0,0 +1,26 @@
+use std::path::Path;
+
+use anyhow::Result;
+use serde::{Deserialize, Serialize};
+
+use super::black::Black;
+use super::isort::Isort;
+use super::pep621::Project;
+
+#[derive(Debug, PartialEq, Eq, Serialize, Deserialize)]
+pub(crate) struct Tools {
+    pub(crate) black: Option<Black>,
+    pub(crate) isort: Option<Isort>,
+}
+
+#[derive(Debug, PartialEq, Eq, Serialize, Deserialize)]
+pub(crate) struct Pyproject {
+    pub(crate) tool: Option<Tools>,
+    pub(crate) project: Option<Project>,
+}
+
+pub(crate) fn parse<P: AsRef<Path>>(path: P) -> Result<Pyproject> {
+    let contents = std::fs::read_to_string(path)?;
+    let pyproject = toml::from_str::<Pyproject>(&contents)?;
+    Ok(pyproject)
+}

crates/red_knot/Cargo.toml

@@ -1,44 +0,0 @@
-[package]
-name = "red_knot"
-version = "0.1.0"
-edition.workspace = true
-rust-version.workspace = true
-homepage.workspace = true
-documentation.workspace = true
-repository.workspace = true
-authors.workspace = true
-license.workspace = true
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-red_knot_module_resolver = { workspace = true }
-
-ruff_python_parser = { workspace = true }
-ruff_python_ast = { workspace = true }
-ruff_text_size = { workspace = true }
-ruff_index = { workspace = true }
-ruff_notebook = { workspace = true }
-
-anyhow = { workspace = true }
-bitflags = { workspace = true }
-crossbeam = { workspace = true }
-ctrlc = { version = "3.4.4" }
-dashmap = { workspace = true }
-hashbrown = { workspace = true }
-indexmap = { workspace = true }
-is-macro = { workspace = true }
-notify = { workspace = true }
-parking_lot = { workspace = true }
-rayon = { workspace = true }
-rustc-hash = { workspace = true }
-smol_str = { version = "0.2.1" }
-tracing = { workspace = true }
-tracing-subscriber = { workspace = true }
-tracing-tree = { workspace = true }
-
-[dev-dependencies]
-tempfile = { workspace = true }
-
-[lints]
-workspace = true

crates/red_knot/src/ast_ids.rs

@@ -1,418 +0,0 @@
-use std::any::type_name;
-use std::fmt::{Debug, Formatter};
-use std::hash::{Hash, Hasher};
-use std::marker::PhantomData;
-
-use rustc_hash::FxHashMap;
-
-use ruff_index::{Idx, IndexVec};
-use ruff_python_ast::visitor::source_order;
-use ruff_python_ast::visitor::source_order::{SourceOrderVisitor, TraversalSignal};
-use ruff_python_ast::{
-    AnyNodeRef, AstNode, ExceptHandler, ExceptHandlerExceptHandler, Expr, MatchCase, ModModule,
-    NodeKind, Parameter, Stmt, StmtAnnAssign, StmtAssign, StmtAugAssign, StmtClassDef,
-    StmtFunctionDef, StmtGlobal, StmtImport, StmtImportFrom, StmtNonlocal, StmtTypeAlias,
-    TypeParam, TypeParamParamSpec, TypeParamTypeVar, TypeParamTypeVarTuple, WithItem,
-};
-use ruff_text_size::{Ranged, TextRange};
-
-/// A type agnostic ID that uniquely identifies an AST node in a file.
-#[ruff_index::newtype_index]
-pub struct AstId;
-
-/// A typed ID that uniquely identifies an AST node in a file.
-///
-/// This is different from [`AstId`] in that it is a combination of ID and the type of the node the ID identifies.
-/// Typing the ID prevents mixing IDs of different node types and allows to restrict the API to only accept
-/// nodes for which an ID has been created (not all AST nodes get an ID).
-pub struct TypedAstId<N: HasAstId> {
-    erased: AstId,
-    _marker: PhantomData<fn() -> N>,
-}
-
-impl<N: HasAstId> TypedAstId<N> {
-    /// Upcasts this ID from a more specific node type to a more general node type.
-    pub fn upcast<M: HasAstId>(self) -> TypedAstId<M>
-    where
-        N: Into<M>,
-    {
-        TypedAstId {
-            erased: self.erased,
-            _marker: PhantomData,
-        }
-    }
-}
-
-impl<N: HasAstId> Copy for TypedAstId<N> {}
-impl<N: HasAstId> Clone for TypedAstId<N> {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-
-impl<N: HasAstId> PartialEq for TypedAstId<N> {
-    fn eq(&self, other: &Self) -> bool {
-        self.erased == other.erased
-    }
-}
-
-impl<N: HasAstId> Eq for TypedAstId<N> {}
-impl<N: HasAstId> Hash for TypedAstId<N> {
-    fn hash<H: Hasher>(&self, state: &mut H) {
-        self.erased.hash(state);
-    }
-}
-
-impl<N: HasAstId> Debug for TypedAstId<N> {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        f.debug_tuple("TypedAstId")
-            .field(&self.erased)
-            .field(&type_name::<N>())
-            .finish()
-    }
-}
-
-pub struct AstIds {
-    ids: IndexVec<AstId, NodeKey>,
-    reverse: FxHashMap<NodeKey, AstId>,
-}
-
-impl AstIds {
-    // TODO rust analyzer doesn't allocate an ID for every node. It only allocates ids for
-    //  nodes with a corresponding HIR element, that is nodes that are definitions.
-    pub fn from_module(module: &ModModule) -> Self {
-        let mut visitor = AstIdsVisitor::default();
-
-        // TODO: visit_module?
-        // Make sure we visit the root
-        visitor.create_id(module);
-        visitor.visit_body(&module.body);
-
-        while let Some(deferred) = visitor.deferred.pop() {
-            match deferred {
-                DeferredNode::FunctionDefinition(def) => {
-                    def.visit_source_order(&mut visitor);
-                }
-                DeferredNode::ClassDefinition(def) => def.visit_source_order(&mut visitor),
-            }
-        }
-
-        AstIds {
-            ids: visitor.ids,
-            reverse: visitor.reverse,
-        }
-    }
-
-    /// Returns the ID to the root node.
-    pub fn root(&self) -> NodeKey {
-        self.ids[AstId::new(0)]
-    }
-
-    /// Returns the [`TypedAstId`] for a node.
-    pub fn ast_id<N: HasAstId>(&self, node: &N) -> TypedAstId<N> {
-        let key = node.syntax_node_key();
-        TypedAstId {
-            erased: self.reverse.get(&key).copied().unwrap(),
-            _marker: PhantomData,
-        }
-    }
-
-    /// Returns the [`TypedAstId`] for the node identified with the given [`TypedNodeKey`].
-    pub fn ast_id_for_key<N: HasAstId>(&self, node: &TypedNodeKey<N>) -> TypedAstId<N> {
-        let ast_id = self.ast_id_for_node_key(node.inner);
-
-        TypedAstId {
-            erased: ast_id,
-            _marker: PhantomData,
-        }
-    }
-
-    /// Returns the untyped [`AstId`] for the node identified by the given `node` key.
-    pub fn ast_id_for_node_key(&self, node: NodeKey) -> AstId {
-        self.reverse
-            .get(&node)
-            .copied()
-            .expect("Can't find node in AstIds map.")
-    }
-
-    /// Returns the [`TypedNodeKey`] for the node identified by the given [`TypedAstId`].
-    pub fn key<N: HasAstId>(&self, id: TypedAstId<N>) -> TypedNodeKey<N> {
-        let syntax_key = self.ids[id.erased];
-
-        TypedNodeKey::new(syntax_key).unwrap()
-    }
-
-    pub fn node_key<H: HasAstId>(&self, id: TypedAstId<H>) -> NodeKey {
-        self.ids[id.erased]
-    }
-}
-
-impl std::fmt::Debug for AstIds {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        let mut map = f.debug_map();
-        for (key, value) in self.ids.iter_enumerated() {
-            map.entry(&key, &value);
-        }
-
-        map.finish()
-    }
-}
-
-impl PartialEq for AstIds {
-    fn eq(&self, other: &Self) -> bool {
-        self.ids == other.ids
-    }
-}
-
-impl Eq for AstIds {}
-
-#[derive(Default)]
-struct AstIdsVisitor<'a> {
-    ids: IndexVec<AstId, NodeKey>,
-    reverse: FxHashMap<NodeKey, AstId>,
-    deferred: Vec<DeferredNode<'a>>,
-}
-
-impl<'a> AstIdsVisitor<'a> {
-    fn create_id<A: HasAstId>(&mut self, node: &A) {
-        let node_key = node.syntax_node_key();
-
-        let id = self.ids.push(node_key);
-        self.reverse.insert(node_key, id);
-    }
-}
-
-impl<'a> SourceOrderVisitor<'a> for AstIdsVisitor<'a> {
-    fn visit_stmt(&mut self, stmt: &'a Stmt) {
-        match stmt {
-            Stmt::FunctionDef(def) => {
-                self.create_id(def);
-                self.deferred.push(DeferredNode::FunctionDefinition(def));
-                return;
-            }
-            // TODO defer visiting the assignment body, type alias parameters etc?
-            Stmt::ClassDef(def) => {
-                self.create_id(def);
-                self.deferred.push(DeferredNode::ClassDefinition(def));
-                return;
-            }
-            Stmt::Expr(_) => {
-                // Skip
-                return;
-            }
-            Stmt::Return(_) => {}
-            Stmt::Delete(_) => {}
-            Stmt::Assign(assignment) => self.create_id(assignment),
-            Stmt::AugAssign(assignment) => {
-                self.create_id(assignment);
-            }
-            Stmt::AnnAssign(assignment) => self.create_id(assignment),
-            Stmt::TypeAlias(assignment) => self.create_id(assignment),
-            Stmt::For(_) => {}
-            Stmt::While(_) => {}
-            Stmt::If(_) => {}
-            Stmt::With(_) => {}
-            Stmt::Match(_) => {}
-            Stmt::Raise(_) => {}
-            Stmt::Try(_) => {}
-            Stmt::Assert(_) => {}
-            Stmt::Import(import) => self.create_id(import),
-            Stmt::ImportFrom(import_from) => self.create_id(import_from),
-            Stmt::Global(global) => self.create_id(global),
-            Stmt::Nonlocal(non_local) => self.create_id(non_local),
-            Stmt::Pass(_) => {}
-            Stmt::Break(_) => {}
-            Stmt::Continue(_) => {}
-            Stmt::IpyEscapeCommand(_) => {}
-        }
-
-        source_order::walk_stmt(self, stmt);
-    }
-
-    fn visit_expr(&mut self, _expr: &'a Expr) {}
-
-    fn visit_parameter(&mut self, parameter: &'a Parameter) {
-        self.create_id(parameter);
-        source_order::walk_parameter(self, parameter);
-    }
-
-    fn visit_except_handler(&mut self, except_handler: &'a ExceptHandler) {
-        match except_handler {
-            ExceptHandler::ExceptHandler(except_handler) => {
-                self.create_id(except_handler);
-            }
-        }
-
-        source_order::walk_except_handler(self, except_handler);
-    }
-
-    fn visit_with_item(&mut self, with_item: &'a WithItem) {
-        self.create_id(with_item);
-        source_order::walk_with_item(self, with_item);
-    }
-
-    fn visit_match_case(&mut self, match_case: &'a MatchCase) {
-        self.create_id(match_case);
-        source_order::walk_match_case(self, match_case);
-    }
-
-    fn visit_type_param(&mut self, type_param: &'a TypeParam) {
-        self.create_id(type_param);
-    }
-}
-
-enum DeferredNode<'a> {
-    FunctionDefinition(&'a StmtFunctionDef),
-    ClassDefinition(&'a StmtClassDef),
-}
-
-#[derive(Copy, Clone, Debug, Eq, PartialEq, Hash)]
-pub struct TypedNodeKey<N: AstNode> {
-    /// The type erased node key.
-    inner: NodeKey,
-    _marker: PhantomData<fn() -> N>,
-}
-
-impl<N: AstNode> TypedNodeKey<N> {
-    pub fn from_node(node: &N) -> Self {
-        let inner = NodeKey::from_node(node.as_any_node_ref());
-        Self {
-            inner,
-            _marker: PhantomData,
-        }
-    }
-
-    pub fn new(node_key: NodeKey) -> Option<Self> {
-        N::can_cast(node_key.kind).then_some(TypedNodeKey {
-            inner: node_key,
-            _marker: PhantomData,
-        })
-    }
-
-    pub fn resolve<'a>(&self, root: AnyNodeRef<'a>) -> Option<N::Ref<'a>> {
-        let node_ref = self.inner.resolve(root)?;
-
-        Some(N::cast_ref(node_ref).unwrap())
-    }
-
-    pub fn resolve_unwrap<'a>(&self, root: AnyNodeRef<'a>) -> N::Ref<'a> {
-        self.resolve(root).expect("node should resolve")
-    }
-
-    pub fn erased(&self) -> &NodeKey {
-        &self.inner
-    }
-}
-
-struct FindNodeKeyVisitor<'a> {
-    key: NodeKey,
-    result: Option<AnyNodeRef<'a>>,
-}
-
-impl<'a> SourceOrderVisitor<'a> for FindNodeKeyVisitor<'a> {
-    fn enter_node(&mut self, node: AnyNodeRef<'a>) -> TraversalSignal {
-        if self.result.is_some() {
-            return TraversalSignal::Skip;
-        }
-
-        if node.range() == self.key.range && node.kind() == self.key.kind {
-            self.result = Some(node);
-            TraversalSignal::Skip
-        } else if node.range().contains_range(self.key.range) {
-            TraversalSignal::Traverse
-        } else {
-            TraversalSignal::Skip
-        }
-    }
-
-    fn visit_body(&mut self, body: &'a [Stmt]) {
-        // TODO it would be more efficient to use binary search instead of linear
-        for stmt in body {
-            if stmt.range().start() > self.key.range.end() {
-                break;
-            }
-
-            self.visit_stmt(stmt);
-        }
-    }
-}
-
-// TODO an alternative to this is to have a `NodeId` on each node (in increasing order depending on the position).
-//  This would allow to reduce the size of this to a u32.
-//  What would be nice if we could use an `Arc::weak_ref` here but that only works if we use
-//   `Arc` internally
-// TODO: Implement the logic to resolve a node, given a db (and the correct file).
-#[derive(Copy, Clone, Debug, Eq, PartialEq, Hash)]
-pub struct NodeKey {
-    kind: NodeKind,
-    range: TextRange,
-}
-
-impl NodeKey {
-    pub fn from_node(node: AnyNodeRef) -> Self {
-        NodeKey {
-            kind: node.kind(),
-            range: node.range(),
-        }
-    }
-    pub fn resolve<'a>(&self, root: AnyNodeRef<'a>) -> Option<AnyNodeRef<'a>> {
-        // We need to do a binary search here. Only traverse into a node if the range is withint the node
-        let mut visitor = FindNodeKeyVisitor {
-            key: *self,
-            result: None,
-        };
-
-        if visitor.enter_node(root) == TraversalSignal::Traverse {
-            root.visit_preorder(&mut visitor);
-        }
-
-        visitor.result
-    }
-}
-
-/// Marker trait implemented by AST nodes for which we extract the `AstId`.
-pub trait HasAstId: AstNode {
-    fn node_key(&self) -> TypedNodeKey<Self>
-    where
-        Self: Sized,
-    {
-        TypedNodeKey {
-            inner: self.syntax_node_key(),
-            _marker: PhantomData,
-        }
-    }
-
-    fn syntax_node_key(&self) -> NodeKey {
-        NodeKey {
-            kind: self.as_any_node_ref().kind(),
-            range: self.range(),
-        }
-    }
-}
-
-impl HasAstId for StmtFunctionDef {}
-impl HasAstId for StmtClassDef {}
-impl HasAstId for StmtAnnAssign {}
-impl HasAstId for StmtAugAssign {}
-impl HasAstId for StmtAssign {}
-impl HasAstId for StmtTypeAlias {}
-
-impl HasAstId for ModModule {}
-
-impl HasAstId for StmtImport {}
-
-impl HasAstId for StmtImportFrom {}
-
-impl HasAstId for Parameter {}
-
-impl HasAstId for TypeParam {}
-impl HasAstId for Stmt {}
-impl HasAstId for TypeParamTypeVar {}
-impl HasAstId for TypeParamTypeVarTuple {}
-impl HasAstId for TypeParamParamSpec {}
-impl HasAstId for StmtGlobal {}
-impl HasAstId for StmtNonlocal {}
-
-impl HasAstId for ExceptHandlerExceptHandler {}
-impl HasAstId for WithItem {}
-impl HasAstId for MatchCase {}

crates/red_knot/src/cache.rs

@@ -1,165 +0,0 @@
-use std::fmt::Formatter;
-use std::hash::Hash;
-use std::sync::atomic::{AtomicUsize, Ordering};
-
-use crate::db::QueryResult;
-use dashmap::mapref::entry::Entry;
-
-use crate::FxDashMap;
-
-/// Simple key value cache that locks on a per-key level.
-pub struct KeyValueCache<K, V> {
-    map: FxDashMap<K, V>,
-    statistics: CacheStatistics,
-}
-
-impl<K, V> KeyValueCache<K, V>
-where
-    K: Eq + Hash + Clone,
-    V: Clone,
-{
-    pub fn try_get(&self, key: &K) -> Option<V> {
-        if let Some(existing) = self.map.get(key) {
-            self.statistics.hit();
-            Some(existing.clone())
-        } else {
-            self.statistics.miss();
-            None
-        }
-    }
-
-    pub fn get<F>(&self, key: &K, compute: F) -> QueryResult<V>
-    where
-        F: FnOnce(&K) -> QueryResult<V>,
-    {
-        Ok(match self.map.entry(key.clone()) {
-            Entry::Occupied(cached) => {
-                self.statistics.hit();
-
-                cached.get().clone()
-            }
-            Entry::Vacant(vacant) => {
-                self.statistics.miss();
-
-                let value = compute(key)?;
-                vacant.insert(value.clone());
-                value
-            }
-        })
-    }
-
-    pub fn set(&mut self, key: K, value: V) {
-        self.map.insert(key, value);
-    }
-
-    pub fn remove(&mut self, key: &K) -> Option<V> {
-        self.map.remove(key).map(|(_, value)| value)
-    }
-
-    pub fn clear(&mut self) {
-        self.map.clear();
-        self.map.shrink_to_fit();
-    }
-
-    pub fn statistics(&self) -> Option<Statistics> {
-        self.statistics.to_statistics()
-    }
-}
-
-impl<K, V> Default for KeyValueCache<K, V>
-where
-    K: Eq + Hash,
-    V: Clone,
-{
-    fn default() -> Self {
-        Self {
-            map: FxDashMap::default(),
-            statistics: CacheStatistics::default(),
-        }
-    }
-}
-
-impl<K, V> std::fmt::Debug for KeyValueCache<K, V>
-where
-    K: std::fmt::Debug + Eq + Hash,
-    V: std::fmt::Debug,
-{
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        let mut debug = f.debug_map();
-
-        for entry in &self.map {
-            debug.entry(&entry.value(), &entry.key());
-        }
-
-        debug.finish()
-    }
-}
-
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct Statistics {
-    pub hits: usize,
-    pub misses: usize,
-}
-
-impl Statistics {
-    #[allow(clippy::cast_precision_loss)]
-    pub fn hit_rate(&self) -> Option<f64> {
-        if self.hits + self.misses == 0 {
-            return None;
-        }
-
-        Some((self.hits as f64) / (self.hits + self.misses) as f64)
-    }
-}
-
-#[cfg(debug_assertions)]
-pub type CacheStatistics = DebugStatistics;
-
-#[cfg(not(debug_assertions))]
-pub type CacheStatistics = ReleaseStatistics;
-
-pub trait StatisticsRecorder {
-    fn hit(&self);
-    fn miss(&self);
-    fn to_statistics(&self) -> Option<Statistics>;
-}
-
-#[derive(Debug, Default)]
-pub struct DebugStatistics {
-    hits: AtomicUsize,
-    misses: AtomicUsize,
-}
-
-impl StatisticsRecorder for DebugStatistics {
-    // TODO figure out appropriate Ordering
-    fn hit(&self) {
-        self.hits.fetch_add(1, Ordering::SeqCst);
-    }
-
-    fn miss(&self) {
-        self.misses.fetch_add(1, Ordering::SeqCst);
-    }
-
-    fn to_statistics(&self) -> Option<Statistics> {
-        let hits = self.hits.load(Ordering::SeqCst);
-        let misses = self.misses.load(Ordering::SeqCst);
-
-        Some(Statistics { hits, misses })
-    }
-}
-
-#[derive(Debug, Default)]
-pub struct ReleaseStatistics;
-
-impl StatisticsRecorder for ReleaseStatistics {
-    #[inline]
-    fn hit(&self) {}
-
-    #[inline]
-    fn miss(&self) {}
-
-    #[inline]
-    fn to_statistics(&self) -> Option<Statistics> {
-        None
-    }
-}

crates/red_knot/src/cancellation.rs

@@ -1,42 +0,0 @@
-use std::sync::atomic::AtomicBool;
-use std::sync::Arc;
-
-#[derive(Debug, Clone, Default)]
-pub struct CancellationTokenSource {
-    signal: Arc<AtomicBool>,
-}
-
-impl CancellationTokenSource {
-    pub fn new() -> Self {
-        Self {
-            signal: Arc::new(AtomicBool::new(false)),
-        }
-    }
-
-    #[tracing::instrument(level = "trace", skip_all)]
-    pub fn cancel(&self) {
-        self.signal.store(true, std::sync::atomic::Ordering::SeqCst);
-    }
-
-    pub fn is_cancelled(&self) -> bool {
-        self.signal.load(std::sync::atomic::Ordering::SeqCst)
-    }
-
-    pub fn token(&self) -> CancellationToken {
-        CancellationToken {
-            signal: self.signal.clone(),
-        }
-    }
-}
-
-#[derive(Clone, Debug)]
-pub struct CancellationToken {
-    signal: Arc<AtomicBool>,
-}
-
-impl CancellationToken {
-    /// Returns `true` if cancellation has been requested.
-    pub fn is_cancelled(&self) -> bool {
-        self.signal.load(std::sync::atomic::Ordering::SeqCst)
-    }
-}

crates/red_knot/src/db.rs

@@ -1,248 +0,0 @@
-use std::sync::Arc;
-
-pub use jars::{HasJar, HasJars};
-pub use query::{QueryError, QueryResult};
-pub use runtime::DbRuntime;
-pub use storage::JarsStorage;
-
-use crate::files::FileId;
-use crate::lint::{LintSemanticStorage, LintSyntaxStorage};
-use crate::module::ModuleResolver;
-use crate::parse::ParsedStorage;
-use crate::semantic::SemanticIndexStorage;
-use crate::semantic::TypeStore;
-use crate::source::SourceStorage;
-
-mod jars;
-mod query;
-mod runtime;
-mod storage;
-
-pub trait Database {
-    /// Returns a reference to the runtime of the current worker.
-    fn runtime(&self) -> &DbRuntime;
-
-    /// Returns a mutable reference to the runtime. Only one worker can hold a mutable reference to the runtime.
-    fn runtime_mut(&mut self) -> &mut DbRuntime;
-
-    /// Returns `Ok` if the queries have not been cancelled and `Err(QueryError::Cancelled)` otherwise.
-    fn cancelled(&self) -> QueryResult<()> {
-        self.runtime().cancelled()
-    }
-
-    /// Returns `true` if the queries have been cancelled.
-    fn is_cancelled(&self) -> bool {
-        self.runtime().is_cancelled()
-    }
-}
-
-/// Database that supports running queries from multiple threads.
-pub trait ParallelDatabase: Database + Send {
-    /// Creates a snapshot of the database state that can be used to query the database in another thread.
-    ///
-    /// The snapshot is a read-only view of the database but query results are shared between threads.
-    /// All queries will be automatically cancelled when applying any mutations (calling [`HasJars::jars_mut`])
-    /// to the database (not the snapshot, because they're readonly).
-    ///
-    /// ## Creating a snapshot
-    ///
-    /// Creating a snapshot of the database's jars is cheap but creating a snapshot of
-    /// other state stored on the database might require deep-cloning data. That's why you should
-    /// avoid creating snapshots in a hot function (e.g. don't create a snapshot for each file, instead
-    /// create a snapshot when scheduling the check of an entire program).
-    ///
-    /// ## Salsa compatibility
-    /// Salsa prohibits creating a snapshot while running a local query (it's fine if other workers run a query) [[source](https://github.com/salsa-rs/salsa/issues/80)].
-    /// We should avoid creating snapshots while running a query because we might want to adopt Salsa in the future (if we can figure out persistent caching).
-    /// Unfortunately, the infrastructure doesn't provide an automated way of knowing when a query is run, that's
-    /// why we have to "enforce" this constraint manually.
-    #[must_use]
-    fn snapshot(&self) -> Snapshot<Self>;
-}
-
-pub trait DbWithJar<Jar>: Database + HasJar<Jar> {}
-
-/// Readonly snapshot of a database.
-///
-/// ## Dead locks
-/// A snapshot should always be dropped as soon as it is no longer necessary to run queries.
-/// Storing the snapshot without running a query or periodically checking if cancellation was requested
-/// can lead to deadlocks because mutating the [`Database`] requires cancels all pending queries
-/// and waiting for all [`Snapshot`]s to be dropped.
-#[derive(Debug)]
-pub struct Snapshot<DB: ?Sized>
-where
-    DB: ParallelDatabase,
-{
-    db: DB,
-}
-
-impl<DB> Snapshot<DB>
-where
-    DB: ParallelDatabase,
-{
-    pub fn new(db: DB) -> Self {
-        Snapshot { db }
-    }
-}
-
-impl<DB> std::ops::Deref for Snapshot<DB>
-where
-    DB: ParallelDatabase,
-{
-    type Target = DB;
-
-    fn deref(&self) -> &DB {
-        &self.db
-    }
-}
-
-pub trait Upcast<T: ?Sized> {
-    fn upcast(&self) -> &T;
-}
-
-// Red knot specific databases code.
-
-pub trait SourceDb: DbWithJar<SourceJar> {
-    // queries
-    fn file_id(&self, path: &std::path::Path) -> FileId;
-
-    fn file_path(&self, file_id: FileId) -> Arc<std::path::Path>;
-}
-
-pub trait SemanticDb: SourceDb + DbWithJar<SemanticJar> + Upcast<dyn SourceDb> {}
-
-pub trait LintDb: SemanticDb + DbWithJar<LintJar> + Upcast<dyn SemanticDb> {}
-
-pub trait Db: LintDb + Upcast<dyn LintDb> {}
-
-#[derive(Debug, Default)]
-pub struct SourceJar {
-    pub sources: SourceStorage,
-    pub parsed: ParsedStorage,
-}
-
-#[derive(Debug, Default)]
-pub struct SemanticJar {
-    pub module_resolver: ModuleResolver,
-    pub semantic_indices: SemanticIndexStorage,
-    pub type_store: TypeStore,
-}
-
-#[derive(Debug, Default)]
-pub struct LintJar {
-    pub lint_syntax: LintSyntaxStorage,
-    pub lint_semantic: LintSemanticStorage,
-}
-
-#[cfg(test)]
-pub(crate) mod tests {
-    use std::path::Path;
-    use std::sync::Arc;
-
-    use crate::db::{
-        Database, DbRuntime, DbWithJar, HasJar, HasJars, JarsStorage, LintDb, LintJar, QueryResult,
-        SourceDb, SourceJar, Upcast,
-    };
-    use crate::files::{FileId, Files};
-
-    use super::{SemanticDb, SemanticJar};
-
-    // This can be a partial database used in a single crate for testing.
-    // It would hold fewer data than the full database.
-    #[derive(Debug, Default)]
-    pub(crate) struct TestDb {
-        files: Files,
-        jars: JarsStorage<Self>,
-    }
-
-    impl HasJar<SourceJar> for TestDb {
-        fn jar(&self) -> QueryResult<&SourceJar> {
-            Ok(&self.jars()?.0)
-        }
-
-        fn jar_mut(&mut self) -> &mut SourceJar {
-            &mut self.jars_mut().0
-        }
-    }
-
-    impl HasJar<SemanticJar> for TestDb {
-        fn jar(&self) -> QueryResult<&SemanticJar> {
-            Ok(&self.jars()?.1)
-        }
-
-        fn jar_mut(&mut self) -> &mut SemanticJar {
-            &mut self.jars_mut().1
-        }
-    }
-
-    impl HasJar<LintJar> for TestDb {
-        fn jar(&self) -> QueryResult<&LintJar> {
-            Ok(&self.jars()?.2)
-        }
-
-        fn jar_mut(&mut self) -> &mut LintJar {
-            &mut self.jars_mut().2
-        }
-    }
-
-    impl SourceDb for TestDb {
-        fn file_id(&self, path: &Path) -> FileId {
-            self.files.intern(path)
-        }
-
-        fn file_path(&self, file_id: FileId) -> Arc<Path> {
-            self.files.path(file_id)
-        }
-    }
-
-    impl DbWithJar<SourceJar> for TestDb {}
-
-    impl Upcast<dyn SourceDb> for TestDb {
-        fn upcast(&self) -> &(dyn SourceDb + 'static) {
-            self
-        }
-    }
-
-    impl SemanticDb for TestDb {}
-
-    impl DbWithJar<SemanticJar> for TestDb {}
-
-    impl Upcast<dyn SemanticDb> for TestDb {
-        fn upcast(&self) -> &(dyn SemanticDb + 'static) {
-            self
-        }
-    }
-
-    impl LintDb for TestDb {}
-
-    impl Upcast<dyn LintDb> for TestDb {
-        fn upcast(&self) -> &(dyn LintDb + 'static) {
-            self
-        }
-    }
-
-    impl DbWithJar<LintJar> for TestDb {}
-
-    impl HasJars for TestDb {
-        type Jars = (SourceJar, SemanticJar, LintJar);
-
-        fn jars(&self) -> QueryResult<&Self::Jars> {
-            self.jars.jars()
-        }
-
-        fn jars_mut(&mut self) -> &mut Self::Jars {
-            self.jars.jars_mut()
-        }
-    }
-
-    impl Database for TestDb {
-        fn runtime(&self) -> &DbRuntime {
-            self.jars.runtime()
-        }
-
-        fn runtime_mut(&mut self) -> &mut DbRuntime {
-            self.jars.runtime_mut()
-        }
-    }
-}

crates/red_knot/src/db/jars.rs

@@ -1,37 +0,0 @@
-use crate::db::query::QueryResult;
-
-/// Gives access to a specific jar in the database.
-///
-/// Nope, the terminology isn't borrowed from Java but from Salsa <https://salsa-rs.github.io/salsa/>,
-/// which is an analogy to storing the salsa in different jars.
-///
-/// The basic idea is that each crate can define its own jar and the jars can be combined to a single
-/// database in the top level crate. Each crate also defines its own `Database` trait. The combination of
-/// `Database` trait and the jar allows to write queries in isolation without having to know how they get composed at the upper levels.
-///
-/// Salsa further defines a `HasIngredient` trait which slices the jar to a specific storage (e.g. a specific cache).
-/// We don't need this just yet because we write our queries by hand. We may want a similar trait if we decide
-/// to use a macro to generate the queries.
-pub trait HasJar<T> {
-    /// Gives a read-only reference to the jar.
-    fn jar(&self) -> QueryResult<&T>;
-
-    /// Gives a mutable reference to the jar.
-    fn jar_mut(&mut self) -> &mut T;
-}
-
-/// Gives access to the jars in a database.
-pub trait HasJars {
-    /// A type storing the jars.
-    ///
-    /// Most commonly, this is a tuple where each jar is a tuple element.
-    type Jars: Default;
-
-    /// Gives access to the underlying jars but tests if the queries have been cancelled.
-    ///
-    /// Returns `Err(QueryError::Cancelled)` if the queries have been cancelled.
-    fn jars(&self) -> QueryResult<&Self::Jars>;
-
-    /// Gives mutable access to the underlying jars.
-    fn jars_mut(&mut self) -> &mut Self::Jars;
-}

crates/red_knot/src/db/query.rs

@@ -1,20 +0,0 @@
-use std::fmt::{Display, Formatter};
-
-/// Reason why a db query operation failed.
-#[derive(Debug, Clone, Copy)]
-pub enum QueryError {
-    /// The query was cancelled because the DB was mutated or the query was cancelled by the host (e.g. on a file change or when pressing CTRL+C).
-    Cancelled,
-}
-
-impl Display for QueryError {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        match self {
-            QueryError::Cancelled => f.write_str("query was cancelled"),
-        }
-    }
-}
-
-impl std::error::Error for QueryError {}
-
-pub type QueryResult<T> = Result<T, QueryError>;

crates/red_knot/src/db/runtime.rs

@@ -1,41 +0,0 @@
-use crate::cancellation::CancellationTokenSource;
-use crate::db::{QueryError, QueryResult};
-
-/// Holds the jar agnostic state of the database.
-#[derive(Debug, Default)]
-pub struct DbRuntime {
-    /// The cancellation token source used to signal other works that the queries should be aborted and
-    /// exit at the next possible point.
-    cancellation_token: CancellationTokenSource,
-}
-
-impl DbRuntime {
-    pub(super) fn snapshot(&self) -> Self {
-        Self {
-            cancellation_token: self.cancellation_token.clone(),
-        }
-    }
-
-    /// Cancels the pending queries of other workers. The current worker cannot have any pending
-    /// queries because we're holding a mutable reference to the runtime.
-    pub(super) fn cancel_other_workers(&mut self) {
-        self.cancellation_token.cancel();
-        // Set a new cancellation token so that we're in a non-cancelled state again when running the next
-        // query.
-        self.cancellation_token = CancellationTokenSource::default();
-    }
-
-    /// Returns `Ok` if the queries have not been cancelled and `Err(QueryError::Cancelled)` otherwise.
-    pub(super) fn cancelled(&self) -> QueryResult<()> {
-        if self.cancellation_token.is_cancelled() {
-            Err(QueryError::Cancelled)
-        } else {
-            Ok(())
-        }
-    }
-
-    /// Returns `true` if the queries have been cancelled.
-    pub(super) fn is_cancelled(&self) -> bool {
-        self.cancellation_token.is_cancelled()
-    }
-}

crates/red_knot/src/db/storage.rs

@@ -1,117 +0,0 @@
-use std::fmt::Formatter;
-use std::sync::Arc;
-
-use crossbeam::sync::WaitGroup;
-
-use crate::db::query::QueryResult;
-use crate::db::runtime::DbRuntime;
-use crate::db::{HasJars, ParallelDatabase};
-
-/// Stores the jars of a database and the state for each worker.
-///
-/// Today, all state is shared across all workers, but it may be desired to store data per worker in the future.
-pub struct JarsStorage<T>
-where
-    T: HasJars + Sized,
-{
-    // It's important that `jars_wait_group` is declared after `jars` to ensure that `jars` is dropped first.
-    // See https://doc.rust-lang.org/reference/destructors.html
-    /// Stores the jars of the database.
-    jars: Arc<T::Jars>,
-
-    /// Used to count the references to `jars`. Allows implementing `jars_mut` without requiring to clone `jars`.
-    jars_wait_group: WaitGroup,
-
-    /// The data agnostic state.
-    runtime: DbRuntime,
-}
-
-impl<Db> JarsStorage<Db>
-where
-    Db: HasJars,
-{
-    pub(super) fn new() -> Self {
-        Self {
-            jars: Arc::new(Db::Jars::default()),
-            jars_wait_group: WaitGroup::default(),
-            runtime: DbRuntime::default(),
-        }
-    }
-
-    /// Creates a snapshot of the jars.
-    ///
-    /// Creating the snapshot is cheap because it doesn't clone the jars, it only increments a ref counter.
-    #[must_use]
-    pub fn snapshot(&self) -> JarsStorage<Db>
-    where
-        Db: ParallelDatabase,
-    {
-        Self {
-            jars: self.jars.clone(),
-            jars_wait_group: self.jars_wait_group.clone(),
-            runtime: self.runtime.snapshot(),
-        }
-    }
-
-    pub(crate) fn jars(&self) -> QueryResult<&Db::Jars> {
-        self.runtime.cancelled()?;
-        Ok(&self.jars)
-    }
-
-    /// Returns a mutable reference to the jars without cloning their content.
-    ///
-    /// The method cancels any pending queries of other works and waits for them to complete so that
-    /// this instance is the only instance holding a reference to the jars.
-    pub(crate) fn jars_mut(&mut self) -> &mut Db::Jars {
-        // We have a mutable ref here, so no more workers can be spawned between calling this function and taking the mut ref below.
-        self.cancel_other_workers();
-
-        // Now all other references to `self.jars` should have been released. We can now safely return a mutable reference
-        // to the Arc's content.
-        let jars =
-            Arc::get_mut(&mut self.jars).expect("All references to jars should have been released");
-
-        jars
-    }
-
-    pub(crate) fn runtime(&self) -> &DbRuntime {
-        &self.runtime
-    }
-
-    pub(crate) fn runtime_mut(&mut self) -> &mut DbRuntime {
-        // Note: This method may need to use a similar trick to `jars_mut` if `DbRuntime` is ever to store data that is shared between workers.
-        &mut self.runtime
-    }
-
-    #[tracing::instrument(level = "trace", skip(self))]
-    fn cancel_other_workers(&mut self) {
-        self.runtime.cancel_other_workers();
-
-        // Wait for all other works to complete.
-        let existing_wait = std::mem::take(&mut self.jars_wait_group);
-        existing_wait.wait();
-    }
-}
-
-impl<Db> Default for JarsStorage<Db>
-where
-    Db: HasJars,
-{
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
-impl<T> std::fmt::Debug for JarsStorage<T>
-where
-    T: HasJars,
-    <T as HasJars>::Jars: std::fmt::Debug,
-{
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        f.debug_struct("SharedStorage")
-            .field("jars", &self.jars)
-            .field("jars_wait_group", &self.jars_wait_group)
-            .field("runtime", &self.runtime)
-            .finish()
-    }
-}

crates/red_knot/src/files.rs

@@ -1,180 +0,0 @@
-use std::fmt::{Debug, Formatter};
-use std::hash::{Hash, Hasher};
-use std::path::Path;
-use std::sync::Arc;
-
-use hashbrown::hash_map::RawEntryMut;
-use parking_lot::RwLock;
-use rustc_hash::FxHasher;
-
-use ruff_index::{newtype_index, IndexVec};
-
-type Map<K, V> = hashbrown::HashMap<K, V, ()>;
-
-#[newtype_index]
-pub struct FileId;
-
-// TODO we'll need a higher level virtual file system abstraction that allows testing if a file exists
-//  or retrieving its content (ideally lazily and in a way that the memory can be retained later)
-//  I suspect that we'll end up with a FileSystem trait and our own Path abstraction.
-#[derive(Default)]
-pub struct Files {
-    inner: Arc<RwLock<FilesInner>>,
-}
-
-impl Files {
-    #[tracing::instrument(level = "debug", skip(self))]
-    pub fn intern(&self, path: &Path) -> FileId {
-        self.inner.write().intern(path)
-    }
-
-    pub fn try_get(&self, path: &Path) -> Option<FileId> {
-        self.inner.read().try_get(path)
-    }
-
-    #[tracing::instrument(level = "debug", skip(self))]
-    pub fn path(&self, id: FileId) -> Arc<Path> {
-        self.inner.read().path(id)
-    }
-
-    /// Snapshots files for a new database snapshot.
-    ///
-    /// This method should not be used outside a database snapshot.
-    #[must_use]
-    pub fn snapshot(&self) -> Files {
-        Files {
-            inner: self.inner.clone(),
-        }
-    }
-}
-
-impl Debug for Files {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        let files = self.inner.read();
-        let mut debug = f.debug_map();
-        for item in files.iter() {
-            debug.entry(&item.0, &item.1);
-        }
-
-        debug.finish()
-    }
-}
-
-impl PartialEq for Files {
-    fn eq(&self, other: &Self) -> bool {
-        self.inner.read().eq(&other.inner.read())
-    }
-}
-
-impl Eq for Files {}
-
-#[derive(Default)]
-struct FilesInner {
-    by_path: Map<FileId, ()>,
-    // TODO should we use a map here to reclaim the space for removed files?
-    // TODO I think we should use our own path abstraction here to avoid having to normalize paths
-    //  and dealing with non-utf paths everywhere.
-    by_id: IndexVec<FileId, Arc<Path>>,
-}
-
-impl FilesInner {
-    /// Inserts the path and returns a new id for it or returns the id if it is an existing path.
-    // TODO should this accept Path or PathBuf?
-    pub(crate) fn intern(&mut self, path: &Path) -> FileId {
-        let hash = FilesInner::hash_path(path);
-
-        let entry = self
-            .by_path
-            .raw_entry_mut()
-            .from_hash(hash, |existing_file| &*self.by_id[*existing_file] == path);
-
-        match entry {
-            RawEntryMut::Occupied(entry) => *entry.key(),
-            RawEntryMut::Vacant(entry) => {
-                let id = self.by_id.push(Arc::from(path));
-                entry.insert_with_hasher(hash, id, (), |file| {
-                    FilesInner::hash_path(&self.by_id[*file])
-                });
-                id
-            }
-        }
-    }
-
-    fn hash_path(path: &Path) -> u64 {
-        let mut hasher = FxHasher::default();
-        path.hash(&mut hasher);
-        hasher.finish()
-    }
-
-    pub(crate) fn try_get(&self, path: &Path) -> Option<FileId> {
-        let mut hasher = FxHasher::default();
-        path.hash(&mut hasher);
-        let hash = hasher.finish();
-
-        Some(
-            *self
-                .by_path
-                .raw_entry()
-                .from_hash(hash, |existing_file| &*self.by_id[*existing_file] == path)?
-                .0,
-        )
-    }
-
-    /// Returns the path for the file with the given id.
-    pub(crate) fn path(&self, id: FileId) -> Arc<Path> {
-        self.by_id[id].clone()
-    }
-
-    pub(crate) fn iter(&self) -> impl Iterator<Item = (FileId, Arc<Path>)> + '_ {
-        self.by_path.keys().map(|id| (*id, self.by_id[*id].clone()))
-    }
-}
-
-impl PartialEq for FilesInner {
-    fn eq(&self, other: &Self) -> bool {
-        self.by_id == other.by_id
-    }
-}
-
-impl Eq for FilesInner {}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use std::path::PathBuf;
-
-    #[test]
-    fn insert_path_twice_same_id() {
-        let files = Files::default();
-        let path = PathBuf::from("foo/bar");
-        let id1 = files.intern(&path);
-        let id2 = files.intern(&path);
-        assert_eq!(id1, id2);
-    }
-
-    #[test]
-    fn insert_different_paths_different_ids() {
-        let files = Files::default();
-        let path1 = PathBuf::from("foo/bar");
-        let path2 = PathBuf::from("foo/bar/baz");
-        let id1 = files.intern(&path1);
-        let id2 = files.intern(&path2);
-        assert_ne!(id1, id2);
-    }
-
-    #[test]
-    fn four_files() {
-        let files = Files::default();
-        let foo_path = PathBuf::from("foo");
-        let foo_id = files.intern(&foo_path);
-        let bar_path = PathBuf::from("bar");
-        files.intern(&bar_path);
-        let baz_path = PathBuf::from("baz");
-        files.intern(&baz_path);
-        let qux_path = PathBuf::from("qux");
-        files.intern(&qux_path);
-
-        let foo_id_2 = files.try_get(&foo_path).expect("foo_path to be found");
-        assert_eq!(foo_id_2, foo_id);
-    }
-}

crates/red_knot/src/hir.rs

@@ -1,67 +0,0 @@
-//! Key observations
-//!
-//! The HIR (High-Level Intermediate Representation) avoids allocations to large extends by:
-//! * Using an arena per node type
-//! * using ids and id ranges to reference items.
-//!
-//! Using separate arena per node type has the advantage that the IDs are relatively stable, because
-//! they only change when a node of the same kind has been added or removed. (What's unclear is if that matters or if
-//! it still triggers a re-compute because the AST-id in the node has changed).
-//!
-//! The HIR does not store all details. It mainly stores the *public* interface. There's a reference
-//! back to the AST node to get more details.
-//!
-//!
-
-use crate::ast_ids::{HasAstId, TypedAstId};
-use crate::files::FileId;
-use std::fmt::Formatter;
-use std::hash::{Hash, Hasher};
-
-pub struct HirAstId<N: HasAstId> {
-    file_id: FileId,
-    node_id: TypedAstId<N>,
-}
-
-impl<N: HasAstId> Copy for HirAstId<N> {}
-impl<N: HasAstId> Clone for HirAstId<N> {
-    fn clone(&self) -> Self {
-        *self
-    }
-}
-
-impl<N: HasAstId> PartialEq for HirAstId<N> {
-    fn eq(&self, other: &Self) -> bool {
-        self.file_id == other.file_id && self.node_id == other.node_id
-    }
-}
-
-impl<N: HasAstId> Eq for HirAstId<N> {}
-
-impl<N: HasAstId> std::fmt::Debug for HirAstId<N> {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        f.debug_struct("HirAstId")
-            .field("file_id", &self.file_id)
-            .field("node_id", &self.node_id)
-            .finish()
-    }
-}
-
-impl<N: HasAstId> Hash for HirAstId<N> {
-    fn hash<H: Hasher>(&self, state: &mut H) {
-        self.file_id.hash(state);
-        self.node_id.hash(state);
-    }
-}
-
-impl<N: HasAstId> HirAstId<N> {
-    pub fn upcast<M: HasAstId>(self) -> HirAstId<M>
-    where
-        N: Into<M>,
-    {
-        HirAstId {
-            file_id: self.file_id,
-            node_id: self.node_id.upcast(),
-        }
-    }
-}

crates/red_knot/src/hir/definition.rs

@@ -1,556 +0,0 @@
-use std::ops::{Index, Range};
-
-use ruff_index::{newtype_index, IndexVec};
-use ruff_python_ast::visitor::preorder;
-use ruff_python_ast::visitor::preorder::PreorderVisitor;
-use ruff_python_ast::{
-    Decorator, ExceptHandler, ExceptHandlerExceptHandler, Expr, MatchCase, ModModule, Stmt,
-    StmtAnnAssign, StmtAssign, StmtClassDef, StmtFunctionDef, StmtGlobal, StmtImport,
-    StmtImportFrom, StmtNonlocal, StmtTypeAlias, TypeParam, TypeParamParamSpec, TypeParamTypeVar,
-    TypeParamTypeVarTuple, WithItem,
-};
-
-use crate::ast_ids::{AstIds, HasAstId};
-use crate::files::FileId;
-use crate::hir::HirAstId;
-use crate::Name;
-
-#[newtype_index]
-pub struct FunctionId;
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct Function {
-    ast_id: HirAstId<StmtFunctionDef>,
-    name: Name,
-    parameters: Range<ParameterId>,
-    type_parameters: Range<TypeParameterId>, // TODO: type_parameters, return expression, decorators
-}
-
-#[newtype_index]
-pub struct ParameterId;
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct Parameter {
-    kind: ParameterKind,
-    name: Name,
-    default: Option<()>, // TODO use expression HIR
-    ast_id: HirAstId<ruff_python_ast::Parameter>,
-}
-
-// TODO or should `Parameter` be an enum?
-#[derive(Copy, Clone, Debug, Eq, PartialEq, Hash)]
-pub enum ParameterKind {
-    PositionalOnly,
-    Arguments,
-    Vararg,
-    KeywordOnly,
-    Kwarg,
-}
-
-#[newtype_index]
-pub struct ClassId;
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct Class {
-    name: Name,
-    ast_id: HirAstId<StmtClassDef>,
-    // TODO type parameters, inheritance, decorators, members
-}
-
-#[newtype_index]
-pub struct AssignmentId;
-
-// This can have more than one name...
-// but that means we can't implement `name()` on `ModuleItem`.
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct Assignment {
-    // TODO: Handle multiple names  / targets
-    name: Name,
-    ast_id: HirAstId<StmtAssign>,
-}
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct AnnotatedAssignment {
-    name: Name,
-    ast_id: HirAstId<StmtAnnAssign>,
-}
-
-#[newtype_index]
-pub struct AnnotatedAssignmentId;
-
-#[newtype_index]
-pub struct TypeAliasId;
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct TypeAlias {
-    name: Name,
-    ast_id: HirAstId<StmtTypeAlias>,
-    parameters: Range<TypeParameterId>,
-}
-
-#[newtype_index]
-pub struct TypeParameterId;
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub enum TypeParameter {
-    TypeVar(TypeParameterTypeVar),
-    ParamSpec(TypeParameterParamSpec),
-    TypeVarTuple(TypeParameterTypeVarTuple),
-}
-
-impl TypeParameter {
-    pub fn ast_id(&self) -> HirAstId<TypeParam> {
-        match self {
-            TypeParameter::TypeVar(type_var) => type_var.ast_id.upcast(),
-            TypeParameter::ParamSpec(param_spec) => param_spec.ast_id.upcast(),
-            TypeParameter::TypeVarTuple(type_var_tuple) => type_var_tuple.ast_id.upcast(),
-        }
-    }
-}
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct TypeParameterTypeVar {
-    name: Name,
-    ast_id: HirAstId<TypeParamTypeVar>,
-}
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct TypeParameterParamSpec {
-    name: Name,
-    ast_id: HirAstId<TypeParamParamSpec>,
-}
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct TypeParameterTypeVarTuple {
-    name: Name,
-    ast_id: HirAstId<TypeParamTypeVarTuple>,
-}
-
-#[newtype_index]
-pub struct GlobalId;
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct Global {
-    // TODO track names
-    ast_id: HirAstId<StmtGlobal>,
-}
-
-#[newtype_index]
-pub struct NonLocalId;
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-pub struct NonLocal {
-    // TODO track names
-    ast_id: HirAstId<StmtNonlocal>,
-}
-
-pub enum DefinitionId {
-    Function(FunctionId),
-    Parameter(ParameterId),
-    Class(ClassId),
-    Assignment(AssignmentId),
-    AnnotatedAssignment(AnnotatedAssignmentId),
-    Global(GlobalId),
-    NonLocal(NonLocalId),
-    TypeParameter(TypeParameterId),
-    TypeAlias(TypeAlias),
-}
-
-pub enum DefinitionItem {
-    Function(Function),
-    Parameter(Parameter),
-    Class(Class),
-    Assignment(Assignment),
-    AnnotatedAssignment(AnnotatedAssignment),
-    Global(Global),
-    NonLocal(NonLocal),
-    TypeParameter(TypeParameter),
-    TypeAlias(TypeAlias),
-}
-
-// The closest is rust-analyzers item-tree. It only represents "Items" which make the public interface of a module
-// (it excludes any other statement or expressions). rust-analyzer uses it as the main input to the name resolution
-// algorithm
-// > It is the input to the name resolution algorithm, as well as to the queries defined in `adt.rs`,
-// > `data.rs`, and most things in `attr.rs`.
-//
-// > One important purpose of this layer is to provide an "invalidation barrier" for incremental
-// > computations: when typing inside an item body, the `ItemTree` of the modified file is typically
-// > unaffected, so we don't have to recompute name resolution results or item data (see `data.rs`).
-//
-// I haven't fully figured this out but I think that this composes the "public" interface of a module?
-// But maybe that's too optimistic.
-//
-//
-#[derive(Debug, Clone, Default, Eq, PartialEq)]
-pub struct Definitions {
-    functions: IndexVec<FunctionId, Function>,
-    parameters: IndexVec<ParameterId, Parameter>,
-    classes: IndexVec<ClassId, Class>,
-    assignments: IndexVec<AssignmentId, Assignment>,
-    annotated_assignments: IndexVec<AnnotatedAssignmentId, AnnotatedAssignment>,
-    type_aliases: IndexVec<TypeAliasId, TypeAlias>,
-    type_parameters: IndexVec<TypeParameterId, TypeParameter>,
-    globals: IndexVec<GlobalId, Global>,
-    non_locals: IndexVec<NonLocalId, NonLocal>,
-}
-
-impl Definitions {
-    pub fn from_module(module: &ModModule, ast_ids: &AstIds, file_id: FileId) -> Self {
-        let mut visitor = DefinitionsVisitor {
-            definitions: Definitions::default(),
-            ast_ids,
-            file_id,
-        };
-
-        visitor.visit_body(&module.body);
-
-        visitor.definitions
-    }
-}
-
-impl Index<FunctionId> for Definitions {
-    type Output = Function;
-
-    fn index(&self, index: FunctionId) -> &Self::Output {
-        &self.functions[index]
-    }
-}
-
-impl Index<ParameterId> for Definitions {
-    type Output = Parameter;
-
-    fn index(&self, index: ParameterId) -> &Self::Output {
-        &self.parameters[index]
-    }
-}
-
-impl Index<ClassId> for Definitions {
-    type Output = Class;
-
-    fn index(&self, index: ClassId) -> &Self::Output {
-        &self.classes[index]
-    }
-}
-
-impl Index<AssignmentId> for Definitions {
-    type Output = Assignment;
-
-    fn index(&self, index: AssignmentId) -> &Self::Output {
-        &self.assignments[index]
-    }
-}
-
-impl Index<AnnotatedAssignmentId> for Definitions {
-    type Output = AnnotatedAssignment;
-
-    fn index(&self, index: AnnotatedAssignmentId) -> &Self::Output {
-        &self.annotated_assignments[index]
-    }
-}
-
-impl Index<TypeAliasId> for Definitions {
-    type Output = TypeAlias;
-
-    fn index(&self, index: TypeAliasId) -> &Self::Output {
-        &self.type_aliases[index]
-    }
-}
-
-impl Index<GlobalId> for Definitions {
-    type Output = Global;
-
-    fn index(&self, index: GlobalId) -> &Self::Output {
-        &self.globals[index]
-    }
-}
-
-impl Index<NonLocalId> for Definitions {
-    type Output = NonLocal;
-
-    fn index(&self, index: NonLocalId) -> &Self::Output {
-        &self.non_locals[index]
-    }
-}
-
-impl Index<TypeParameterId> for Definitions {
-    type Output = TypeParameter;
-
-    fn index(&self, index: TypeParameterId) -> &Self::Output {
-        &self.type_parameters[index]
-    }
-}
-
-struct DefinitionsVisitor<'a> {
-    definitions: Definitions,
-    ast_ids: &'a AstIds,
-    file_id: FileId,
-}
-
-impl DefinitionsVisitor<'_> {
-    fn ast_id<N: HasAstId>(&self, node: &N) -> HirAstId<N> {
-        HirAstId {
-            file_id: self.file_id,
-            node_id: self.ast_ids.ast_id(node),
-        }
-    }
-
-    fn lower_function_def(&mut self, function: &StmtFunctionDef) -> FunctionId {
-        let name = Name::new(&function.name);
-
-        let first_type_parameter_id = self.definitions.type_parameters.next_index();
-        let mut last_type_parameter_id = first_type_parameter_id;
-
-        if let Some(type_params) = &function.type_params {
-            for parameter in &type_params.type_params {
-                let id = self.lower_type_parameter(parameter);
-                last_type_parameter_id = id;
-            }
-        }
-
-        let parameters = self.lower_parameters(&function.parameters);
-
-        self.definitions.functions.push(Function {
-            name,
-            ast_id: self.ast_id(function),
-            parameters,
-            type_parameters: first_type_parameter_id..last_type_parameter_id,
-        })
-    }
-
-    fn lower_parameters(&mut self, parameters: &ruff_python_ast::Parameters) -> Range<ParameterId> {
-        let first_parameter_id = self.definitions.parameters.next_index();
-        let mut last_parameter_id = first_parameter_id;
-
-        for parameter in &parameters.posonlyargs {
-            last_parameter_id = self.definitions.parameters.push(Parameter {
-                kind: ParameterKind::PositionalOnly,
-                name: Name::new(&parameter.parameter.name),
-                default: None,
-                ast_id: self.ast_id(&parameter.parameter),
-            });
-        }
-
-        if let Some(vararg) = &parameters.vararg {
-            last_parameter_id = self.definitions.parameters.push(Parameter {
-                kind: ParameterKind::Vararg,
-                name: Name::new(&vararg.name),
-                default: None,
-                ast_id: self.ast_id(vararg),
-            });
-        }
-
-        for parameter in &parameters.kwonlyargs {
-            last_parameter_id = self.definitions.parameters.push(Parameter {
-                kind: ParameterKind::KeywordOnly,
-                name: Name::new(&parameter.parameter.name),
-                default: None,
-                ast_id: self.ast_id(&parameter.parameter),
-            });
-        }
-
-        if let Some(kwarg) = &parameters.kwarg {
-            last_parameter_id = self.definitions.parameters.push(Parameter {
-                kind: ParameterKind::KeywordOnly,
-                name: Name::new(&kwarg.name),
-                default: None,
-                ast_id: self.ast_id(kwarg),
-            });
-        }
-
-        first_parameter_id..last_parameter_id
-    }
-
-    fn lower_class_def(&mut self, class: &StmtClassDef) -> ClassId {
-        let name = Name::new(&class.name);
-
-        self.definitions.classes.push(Class {
-            name,
-            ast_id: self.ast_id(class),
-        })
-    }
-
-    fn lower_assignment(&mut self, assignment: &StmtAssign) {
-        // FIXME handle multiple names
-        if let Some(Expr::Name(name)) = assignment.targets.first() {
-            self.definitions.assignments.push(Assignment {
-                name: Name::new(&name.id),
-                ast_id: self.ast_id(assignment),
-            });
-        }
-    }
-
-    fn lower_annotated_assignment(&mut self, annotated_assignment: &StmtAnnAssign) {
-        if let Expr::Name(name) = &*annotated_assignment.target {
-            self.definitions
-                .annotated_assignments
-                .push(AnnotatedAssignment {
-                    name: Name::new(&name.id),
-                    ast_id: self.ast_id(annotated_assignment),
-                });
-        }
-    }
-
-    fn lower_type_alias(&mut self, type_alias: &StmtTypeAlias) {
-        if let Expr::Name(name) = &*type_alias.name {
-            let name = Name::new(&name.id);
-
-            let lower_parameters_id = self.definitions.type_parameters.next_index();
-            let mut last_parameter_id = lower_parameters_id;
-
-            if let Some(type_params) = &type_alias.type_params {
-                for type_parameter in &type_params.type_params {
-                    let id = self.lower_type_parameter(type_parameter);
-                    last_parameter_id = id;
-                }
-            }
-
-            self.definitions.type_aliases.push(TypeAlias {
-                name,
-                ast_id: self.ast_id(type_alias),
-                parameters: lower_parameters_id..last_parameter_id,
-            });
-        }
-    }
-
-    fn lower_type_parameter(&mut self, type_parameter: &TypeParam) -> TypeParameterId {
-        match type_parameter {
-            TypeParam::TypeVar(type_var) => {
-                self.definitions
-                    .type_parameters
-                    .push(TypeParameter::TypeVar(TypeParameterTypeVar {
-                        name: Name::new(&type_var.name),
-                        ast_id: self.ast_id(type_var),
-                    }))
-            }
-            TypeParam::ParamSpec(param_spec) => {
-                self.definitions
-                    .type_parameters
-                    .push(TypeParameter::ParamSpec(TypeParameterParamSpec {
-                        name: Name::new(&param_spec.name),
-                        ast_id: self.ast_id(param_spec),
-                    }))
-            }
-            TypeParam::TypeVarTuple(type_var_tuple) => {
-                self.definitions
-                    .type_parameters
-                    .push(TypeParameter::TypeVarTuple(TypeParameterTypeVarTuple {
-                        name: Name::new(&type_var_tuple.name),
-                        ast_id: self.ast_id(type_var_tuple),
-                    }))
-            }
-        }
-    }
-
-    fn lower_import(&mut self, _import: &StmtImport) {
-        // TODO
-    }
-
-    fn lower_import_from(&mut self, _import_from: &StmtImportFrom) {
-        // TODO
-    }
-
-    fn lower_global(&mut self, global: &StmtGlobal) -> GlobalId {
-        self.definitions.globals.push(Global {
-            ast_id: self.ast_id(global),
-        })
-    }
-
-    fn lower_non_local(&mut self, non_local: &StmtNonlocal) -> NonLocalId {
-        self.definitions.non_locals.push(NonLocal {
-            ast_id: self.ast_id(non_local),
-        })
-    }
-
-    fn lower_except_handler(&mut self, _except_handler: &ExceptHandlerExceptHandler) {
-        // TODO
-    }
-
-    fn lower_with_item(&mut self, _with_item: &WithItem) {
-        // TODO
-    }
-
-    fn lower_match_case(&mut self, _match_case: &MatchCase) {
-        // TODO
-    }
-}
-
-impl PreorderVisitor<'_> for DefinitionsVisitor<'_> {
-    fn visit_stmt(&mut self, stmt: &Stmt) {
-        match stmt {
-            // Definition statements
-            Stmt::FunctionDef(definition) => {
-                self.lower_function_def(definition);
-                self.visit_body(&definition.body);
-            }
-            Stmt::ClassDef(definition) => {
-                self.lower_class_def(definition);
-                self.visit_body(&definition.body);
-            }
-            Stmt::Assign(assignment) => {
-                self.lower_assignment(assignment);
-            }
-            Stmt::AnnAssign(annotated_assignment) => {
-                self.lower_annotated_assignment(annotated_assignment);
-            }
-            Stmt::TypeAlias(type_alias) => {
-                self.lower_type_alias(type_alias);
-            }
-
-            Stmt::Import(import) => self.lower_import(import),
-            Stmt::ImportFrom(import_from) => self.lower_import_from(import_from),
-            Stmt::Global(global) => {
-                self.lower_global(global);
-            }
-            Stmt::Nonlocal(non_local) => {
-                self.lower_non_local(non_local);
-            }
-
-            // Visit the compound statement bodies because they can contain other definitions.
-            Stmt::For(_)
-            | Stmt::While(_)
-            | Stmt::If(_)
-            | Stmt::With(_)
-            | Stmt::Match(_)
-            | Stmt::Try(_) => {
-                preorder::walk_stmt(self, stmt);
-            }
-
-            // Skip over simple statements because they can't contain any other definitions.
-            Stmt::Return(_)
-            | Stmt::Delete(_)
-            | Stmt::AugAssign(_)
-            | Stmt::Raise(_)
-            | Stmt::Assert(_)
-            | Stmt::Expr(_)
-            | Stmt::Pass(_)
-            | Stmt::Break(_)
-            | Stmt::Continue(_)
-            | Stmt::IpyEscapeCommand(_) => {
-                // No op
-            }
-        }
-    }
-
-    fn visit_expr(&mut self, _: &'_ Expr) {}
-
-    fn visit_decorator(&mut self, _decorator: &'_ Decorator) {}
-
-    fn visit_except_handler(&mut self, except_handler: &'_ ExceptHandler) {
-        match except_handler {
-            ExceptHandler::ExceptHandler(except_handler) => {
-                self.lower_except_handler(except_handler);
-            }
-        }
-    }
-
-    fn visit_with_item(&mut self, with_item: &'_ WithItem) {
-        self.lower_with_item(with_item);
-    }
-
-    fn visit_match_case(&mut self, match_case: &'_ MatchCase) {
-        self.lower_match_case(match_case);
-        self.visit_body(&match_case.body);
-    }
-}

crates/red_knot/src/lib.rs

@@ -1,108 +0,0 @@
-use std::fmt::Formatter;
-use std::hash::BuildHasherDefault;
-use std::ops::Deref;
-use std::path::{Path, PathBuf};
-
-use rustc_hash::{FxHashSet, FxHasher};
-
-use crate::files::FileId;
-
-pub mod ast_ids;
-pub mod cache;
-pub mod cancellation;
-pub mod db;
-pub mod files;
-pub mod hir;
-pub mod lint;
-pub mod module;
-mod parse;
-pub mod program;
-mod semantic;
-pub mod source;
-pub mod watch;
-
-pub(crate) type FxDashMap<K, V> = dashmap::DashMap<K, V, BuildHasherDefault<FxHasher>>;
-#[allow(unused)]
-pub(crate) type FxDashSet<V> = dashmap::DashSet<V, BuildHasherDefault<FxHasher>>;
-pub(crate) type FxIndexSet<V> = indexmap::set::IndexSet<V, BuildHasherDefault<FxHasher>>;
-
-#[derive(Debug, Clone)]
-pub struct Workspace {
-    /// TODO this should be a resolved path. We should probably use a newtype wrapper that guarantees that
-    /// PATH is a UTF-8 path and is normalized.
-    root: PathBuf,
-    /// The files that are open in the workspace.
-    ///
-    /// * Editor: The files that are actively being edited in the editor (the user has a tab open with the file).
-    /// * CLI: The resolved files passed as arguments to the CLI.
-    open_files: FxHashSet<FileId>,
-}
-
-impl Workspace {
-    pub fn new(root: PathBuf) -> Self {
-        Self {
-            root,
-            open_files: FxHashSet::default(),
-        }
-    }
-
-    pub fn root(&self) -> &Path {
-        self.root.as_path()
-    }
-
-    // TODO having the content in workspace feels wrong.
-    pub fn open_file(&mut self, file_id: FileId) {
-        self.open_files.insert(file_id);
-    }
-
-    pub fn close_file(&mut self, file_id: FileId) {
-        self.open_files.remove(&file_id);
-    }
-
-    // TODO introduce an `OpenFile` type instead of using an anonymous tuple.
-    pub fn open_files(&self) -> impl Iterator<Item = FileId> + '_ {
-        self.open_files.iter().copied()
-    }
-
-    pub fn is_file_open(&self, file_id: FileId) -> bool {
-        self.open_files.contains(&file_id)
-    }
-}
-
-#[derive(Debug, Clone, Eq, PartialEq, Hash)]
-pub struct Name(smol_str::SmolStr);
-
-impl Name {
-    #[inline]
-    pub fn new(name: &str) -> Self {
-        Self(smol_str::SmolStr::new(name))
-    }
-
-    pub fn as_str(&self) -> &str {
-        self.0.as_str()
-    }
-}
-
-impl Deref for Name {
-    type Target = str;
-
-    #[inline]
-    fn deref(&self) -> &Self::Target {
-        self.as_str()
-    }
-}
-
-impl<T> From<T> for Name
-where
-    T: Into<smol_str::SmolStr>,
-{
-    fn from(value: T) -> Self {
-        Self(value.into())
-    }
-}
-
-impl std::fmt::Display for Name {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        f.write_str(self.as_str())
-    }
-}

crates/red_knot/src/lint.rs

@@ -1,332 +0,0 @@
-use std::cell::RefCell;
-use std::ops::{Deref, DerefMut};
-use std::sync::Arc;
-use std::time::Duration;
-
-use ruff_python_ast::visitor::Visitor;
-use ruff_python_ast::{ModModule, StringLiteral};
-use ruff_python_parser::Parsed;
-
-use crate::cache::KeyValueCache;
-use crate::db::{LintDb, LintJar, QueryResult};
-use crate::files::FileId;
-use crate::module::{resolve_module, ModuleName};
-use crate::parse::parse;
-use crate::semantic::{infer_definition_type, infer_symbol_public_type, Type};
-use crate::semantic::{
-    resolve_global_symbol, semantic_index, Definition, GlobalSymbolId, SemanticIndex, SymbolId,
-};
-use crate::source::{source_text, Source};
-
-#[tracing::instrument(level = "debug", skip(db))]
-pub(crate) fn lint_syntax(db: &dyn LintDb, file_id: FileId) -> QueryResult<Diagnostics> {
-    let lint_jar: &LintJar = db.jar()?;
-    let storage = &lint_jar.lint_syntax;
-
-    #[allow(clippy::print_stdout)]
-    if std::env::var("RED_KNOT_SLOW_LINT").is_ok() {
-        for i in 0..10 {
-            db.cancelled()?;
-            println!("RED_KNOT_SLOW_LINT is set, sleeping for {i}/10 seconds");
-            std::thread::sleep(Duration::from_secs(1));
-        }
-    }
-
-    storage.get(&file_id, |file_id| {
-        let mut diagnostics = Vec::new();
-
-        let source = source_text(db.upcast(), *file_id)?;
-        lint_lines(source.text(), &mut diagnostics);
-
-        let parsed = parse(db.upcast(), *file_id)?;
-
-        if parsed.errors().is_empty() {
-            let ast = parsed.syntax();
-
-            let mut visitor = SyntaxLintVisitor {
-                diagnostics,
-                source: source.text(),
-            };
-            visitor.visit_body(&ast.body);
-            diagnostics = visitor.diagnostics;
-        } else {
-            diagnostics.extend(parsed.errors().iter().map(std::string::ToString::to_string));
-        }
-
-        Ok(Diagnostics::from(diagnostics))
-    })
-}
-
-fn lint_lines(source: &str, diagnostics: &mut Vec<String>) {
-    for (line_number, line) in source.lines().enumerate() {
-        if line.len() < 88 {
-            continue;
-        }
-
-        let char_count = line.chars().count();
-        if char_count > 88 {
-            diagnostics.push(format!(
-                "Line {} is too long ({} characters)",
-                line_number + 1,
-                char_count
-            ));
-        }
-    }
-}
-
-#[tracing::instrument(level = "debug", skip(db))]
-pub(crate) fn lint_semantic(db: &dyn LintDb, file_id: FileId) -> QueryResult<Diagnostics> {
-    let lint_jar: &LintJar = db.jar()?;
-    let storage = &lint_jar.lint_semantic;
-
-    storage.get(&file_id, |file_id| {
-        let source = source_text(db.upcast(), *file_id)?;
-        let parsed = parse(db.upcast(), *file_id)?;
-        let semantic_index = semantic_index(db.upcast(), *file_id)?;
-
-        let context = SemanticLintContext {
-            file_id: *file_id,
-            source,
-            parsed: &parsed,
-            semantic_index,
-            db,
-            diagnostics: RefCell::new(Vec::new()),
-        };
-
-        lint_unresolved_imports(&context)?;
-        lint_bad_overrides(&context)?;
-
-        Ok(Diagnostics::from(context.diagnostics.take()))
-    })
-}
-
-fn lint_unresolved_imports(context: &SemanticLintContext) -> QueryResult<()> {
-    // TODO: Consider iterating over the dependencies (imports) only instead of all definitions.
-    for (symbol, definition) in context.semantic_index().symbol_table().all_definitions() {
-        match definition {
-            Definition::Import(import) => {
-                let ty = context.infer_symbol_public_type(symbol)?;
-
-                if ty.is_unknown() {
-                    context.push_diagnostic(format!("Unresolved module {}", import.module));
-                }
-            }
-            Definition::ImportFrom(import) => {
-                let ty = context.infer_symbol_public_type(symbol)?;
-
-                if ty.is_unknown() {
-                    let module_name = import.module().map(Deref::deref).unwrap_or_default();
-                    let message = if import.level() > 0 {
-                        format!(
-                            "Unresolved relative import '{}' from {}{}",
-                            import.name(),
-                            ".".repeat(import.level() as usize),
-                            module_name
-                        )
-                    } else {
-                        format!(
-                            "Unresolved import '{}' from '{}'",
-                            import.name(),
-                            module_name
-                        )
-                    };
-
-                    context.push_diagnostic(message);
-                }
-            }
-            _ => {}
-        }
-    }
-
-    Ok(())
-}
-
-fn lint_bad_overrides(context: &SemanticLintContext) -> QueryResult<()> {
-    // TODO we should have a special marker on the real typing module (from typeshed) so if you
-    // have your own "typing" module in your project, we don't consider it THE typing module (and
-    // same for other stdlib modules that our lint rules care about)
-    let Some(typing_override) = context.resolve_global_symbol("typing", "override")? else {
-        // TODO once we bundle typeshed, this should be unreachable!()
-        return Ok(());
-    };
-
-    // TODO we should maybe index definitions by type instead of iterating all, or else iterate all
-    // just once, match, and branch to all lint rules that care about a type of definition
-    for (symbol, definition) in context.semantic_index().symbol_table().all_definitions() {
-        if !matches!(definition, Definition::FunctionDef(_)) {
-            continue;
-        }
-        let ty = infer_definition_type(
-            context.db.upcast(),
-            GlobalSymbolId {
-                file_id: context.file_id,
-                symbol_id: symbol,
-            },
-            definition.clone(),
-        )?;
-        let Type::Function(func) = ty else {
-            unreachable!("type of a FunctionDef should always be a Function");
-        };
-        let Some(class) = func.get_containing_class(context.db.upcast())? else {
-            // not a method of a class
-            continue;
-        };
-        if func.has_decorator(context.db.upcast(), typing_override)? {
-            let method_name = func.name(context.db.upcast())?;
-            if class
-                .get_super_class_member(context.db.upcast(), &method_name)?
-                .is_none()
-            {
-                // TODO should have a qualname() method to support nested classes
-                context.push_diagnostic(
-                    format!(
-                        "Method {}.{} is decorated with `typing.override` but does not override any base class method",
-                        class.name(context.db.upcast())?,
-                        method_name,
-                    ));
-            }
-        }
-    }
-    Ok(())
-}
-
-pub struct SemanticLintContext<'a> {
-    file_id: FileId,
-    source: Source,
-    parsed: &'a Parsed<ModModule>,
-    semantic_index: Arc<SemanticIndex>,
-    db: &'a dyn LintDb,
-    diagnostics: RefCell<Vec<String>>,
-}
-
-impl<'a> SemanticLintContext<'a> {
-    pub fn source_text(&self) -> &str {
-        self.source.text()
-    }
-
-    pub fn file_id(&self) -> FileId {
-        self.file_id
-    }
-
-    pub fn ast(&self) -> &'a ModModule {
-        self.parsed.syntax()
-    }
-
-    pub fn semantic_index(&self) -> &SemanticIndex {
-        &self.semantic_index
-    }
-
-    pub fn infer_symbol_public_type(&self, symbol_id: SymbolId) -> QueryResult<Type> {
-        infer_symbol_public_type(
-            self.db.upcast(),
-            GlobalSymbolId {
-                file_id: self.file_id,
-                symbol_id,
-            },
-        )
-    }
-
-    pub fn push_diagnostic(&self, diagnostic: String) {
-        self.diagnostics.borrow_mut().push(diagnostic);
-    }
-
-    pub fn extend_diagnostics(&mut self, diagnostics: impl IntoIterator<Item = String>) {
-        self.diagnostics.get_mut().extend(diagnostics);
-    }
-
-    pub fn resolve_global_symbol(
-        &self,
-        module: &str,
-        symbol_name: &str,
-    ) -> QueryResult<Option<GlobalSymbolId>> {
-        let Some(module) = resolve_module(self.db.upcast(), ModuleName::new(module))? else {
-            return Ok(None);
-        };
-
-        resolve_global_symbol(self.db.upcast(), module, symbol_name)
-    }
-}
-
-#[derive(Debug)]
-struct SyntaxLintVisitor<'a> {
-    diagnostics: Vec<String>,
-    source: &'a str,
-}
-
-impl Visitor<'_> for SyntaxLintVisitor<'_> {
-    fn visit_string_literal(&mut self, string_literal: &'_ StringLiteral) {
-        // A very naive implementation of use double quotes
-        let text = &self.source[string_literal.range];
-
-        if text.starts_with('\'') {
-            self.diagnostics
-                .push("Use double quotes for strings".to_string());
-        }
-    }
-}
-
-#[derive(Debug, Clone)]
-pub enum Diagnostics {
-    Empty,
-    List(Arc<Vec<String>>),
-}
-
-impl Diagnostics {
-    pub fn as_slice(&self) -> &[String] {
-        match self {
-            Diagnostics::Empty => &[],
-            Diagnostics::List(list) => list.as_slice(),
-        }
-    }
-}
-
-impl Deref for Diagnostics {
-    type Target = [String];
-    fn deref(&self) -> &Self::Target {
-        self.as_slice()
-    }
-}
-
-impl From<Vec<String>> for Diagnostics {
-    fn from(value: Vec<String>) -> Self {
-        if value.is_empty() {
-            Diagnostics::Empty
-        } else {
-            Diagnostics::List(Arc::new(value))
-        }
-    }
-}
-
-#[derive(Default, Debug)]
-pub struct LintSyntaxStorage(KeyValueCache<FileId, Diagnostics>);
-
-impl Deref for LintSyntaxStorage {
-    type Target = KeyValueCache<FileId, Diagnostics>;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl DerefMut for LintSyntaxStorage {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}
-
-#[derive(Default, Debug)]
-pub struct LintSemanticStorage(KeyValueCache<FileId, Diagnostics>);
-
-impl Deref for LintSemanticStorage {
-    type Target = KeyValueCache<FileId, Diagnostics>;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl DerefMut for LintSemanticStorage {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

crates/red_knot/src/main.rs

@@ -1,364 +0,0 @@
-#![allow(clippy::dbg_macro)]
-
-use std::path::Path;
-use std::sync::Mutex;
-
-use crossbeam::channel as crossbeam_channel;
-use tracing::subscriber::Interest;
-use tracing::{Level, Metadata};
-use tracing_subscriber::filter::LevelFilter;
-use tracing_subscriber::layer::{Context, Filter, SubscriberExt};
-use tracing_subscriber::{Layer, Registry};
-use tracing_tree::time::Uptime;
-
-use red_knot::db::{HasJar, ParallelDatabase, QueryError, SourceDb, SourceJar};
-use red_knot::module::{set_module_search_paths, ModuleResolutionInputs};
-use red_knot::program::check::ExecutionMode;
-use red_knot::program::{FileWatcherChange, Program};
-use red_knot::watch::FileWatcher;
-use red_knot::Workspace;
-
-#[allow(clippy::print_stdout, clippy::unnecessary_wraps, clippy::print_stderr)]
-fn main() -> anyhow::Result<()> {
-    setup_tracing();
-
-    let arguments: Vec<_> = std::env::args().collect();
-
-    if arguments.len() < 2 {
-        eprintln!("Usage: red_knot <path>");
-        return Err(anyhow::anyhow!("Invalid arguments"));
-    }
-
-    let entry_point = Path::new(&arguments[1]);
-
-    if !entry_point.exists() {
-        eprintln!("The entry point does not exist.");
-        return Err(anyhow::anyhow!("Invalid arguments"));
-    }
-
-    if !entry_point.is_file() {
-        eprintln!("The entry point is not a file.");
-        return Err(anyhow::anyhow!("Invalid arguments"));
-    }
-
-    let workspace_folder = entry_point.parent().unwrap();
-    let workspace = Workspace::new(workspace_folder.to_path_buf());
-
-    let workspace_search_path = workspace.root().to_path_buf();
-
-    let search_paths = ModuleResolutionInputs {
-        extra_paths: vec![],
-        workspace_root: workspace_search_path,
-        site_packages: None,
-        custom_typeshed: None,
-    };
-
-    let mut program = Program::new(workspace);
-    set_module_search_paths(&mut program, search_paths);
-
-    let entry_id = program.file_id(entry_point);
-    program.workspace_mut().open_file(entry_id);
-
-    let (main_loop, main_loop_cancellation_token) = MainLoop::new();
-
-    // Listen to Ctrl+C and abort the watch mode.
-    let main_loop_cancellation_token = Mutex::new(Some(main_loop_cancellation_token));
-    ctrlc::set_handler(move || {
-        let mut lock = main_loop_cancellation_token.lock().unwrap();
-
-        if let Some(token) = lock.take() {
-            token.stop();
-        }
-    })?;
-
-    let file_changes_notifier = main_loop.file_changes_notifier();
-
-    // Watch for file changes and re-trigger the analysis.
-    let mut file_watcher = FileWatcher::new(move |changes| {
-        file_changes_notifier.notify(changes);
-    })?;
-
-    file_watcher.watch_folder(workspace_folder)?;
-
-    main_loop.run(&mut program);
-
-    let source_jar: &SourceJar = program.jar().unwrap();
-
-    dbg!(source_jar.parsed.statistics());
-    dbg!(source_jar.sources.statistics());
-
-    Ok(())
-}
-
-struct MainLoop {
-    orchestrator_sender: crossbeam_channel::Sender<OrchestratorMessage>,
-    main_loop_receiver: crossbeam_channel::Receiver<MainLoopMessage>,
-}
-
-impl MainLoop {
-    fn new() -> (Self, MainLoopCancellationToken) {
-        let (orchestrator_sender, orchestrator_receiver) = crossbeam_channel::bounded(1);
-        let (main_loop_sender, main_loop_receiver) = crossbeam_channel::bounded(1);
-
-        let mut orchestrator = Orchestrator {
-            receiver: orchestrator_receiver,
-            sender: main_loop_sender.clone(),
-            revision: 0,
-        };
-
-        std::thread::spawn(move || {
-            orchestrator.run();
-        });
-
-        (
-            Self {
-                orchestrator_sender,
-                main_loop_receiver,
-            },
-            MainLoopCancellationToken {
-                sender: main_loop_sender,
-            },
-        )
-    }
-
-    fn file_changes_notifier(&self) -> FileChangesNotifier {
-        FileChangesNotifier {
-            sender: self.orchestrator_sender.clone(),
-        }
-    }
-
-    fn run(self, program: &mut Program) {
-        self.orchestrator_sender
-            .send(OrchestratorMessage::Run)
-            .unwrap();
-
-        for message in &self.main_loop_receiver {
-            tracing::trace!("Main Loop: Tick");
-
-            match message {
-                MainLoopMessage::CheckProgram { revision } => {
-                    let program = program.snapshot();
-                    let sender = self.orchestrator_sender.clone();
-
-                    // Spawn a new task that checks the program. This needs to be done in a separate thread
-                    // to prevent blocking the main loop here.
-                    rayon::spawn(move || match program.check(ExecutionMode::ThreadPool) {
-                        Ok(result) => {
-                            sender
-                                .send(OrchestratorMessage::CheckProgramCompleted {
-                                    diagnostics: result,
-                                    revision,
-                                })
-                                .unwrap();
-                        }
-                        Err(QueryError::Cancelled) => {}
-                    });
-                }
-                MainLoopMessage::ApplyChanges(changes) => {
-                    // Automatically cancels any pending queries and waits for them to complete.
-                    program.apply_changes(changes);
-                }
-                MainLoopMessage::CheckCompleted(diagnostics) => {
-                    dbg!(diagnostics);
-                }
-                MainLoopMessage::Exit => {
-                    return;
-                }
-            }
-        }
-    }
-}
-
-impl Drop for MainLoop {
-    fn drop(&mut self) {
-        self.orchestrator_sender
-            .send(OrchestratorMessage::Shutdown)
-            .unwrap();
-    }
-}
-
-#[derive(Debug, Clone)]
-struct FileChangesNotifier {
-    sender: crossbeam_channel::Sender<OrchestratorMessage>,
-}
-
-impl FileChangesNotifier {
-    fn notify(&self, changes: Vec<FileWatcherChange>) {
-        self.sender
-            .send(OrchestratorMessage::FileChanges(changes))
-            .unwrap();
-    }
-}
-
-#[derive(Debug)]
-struct MainLoopCancellationToken {
-    sender: crossbeam_channel::Sender<MainLoopMessage>,
-}
-
-impl MainLoopCancellationToken {
-    fn stop(self) {
-        self.sender.send(MainLoopMessage::Exit).unwrap();
-    }
-}
-
-struct Orchestrator {
-    /// Sends messages to the main loop.
-    sender: crossbeam_channel::Sender<MainLoopMessage>,
-    /// Receives messages from the main loop.
-    receiver: crossbeam_channel::Receiver<OrchestratorMessage>,
-    revision: usize,
-}
-
-impl Orchestrator {
-    fn run(&mut self) {
-        while let Ok(message) = self.receiver.recv() {
-            match message {
-                OrchestratorMessage::Run => {
-                    self.sender
-                        .send(MainLoopMessage::CheckProgram {
-                            revision: self.revision,
-                        })
-                        .unwrap();
-                }
-
-                OrchestratorMessage::CheckProgramCompleted {
-                    diagnostics,
-                    revision,
-                } => {
-                    // Only take the diagnostics if they are for the latest revision.
-                    if self.revision == revision {
-                        self.sender
-                            .send(MainLoopMessage::CheckCompleted(diagnostics))
-                            .unwrap();
-                    } else {
-                        tracing::debug!("Discarding diagnostics for outdated revision {revision} (current: {}).", self.revision);
-                    }
-                }
-
-                OrchestratorMessage::FileChanges(changes) => {
-                    // Request cancellation, but wait until all analysis tasks have completed to
-                    // avoid stale messages in the next main loop.
-
-                    self.revision += 1;
-                    self.debounce_changes(changes);
-                }
-                OrchestratorMessage::Shutdown => {
-                    return self.shutdown();
-                }
-            }
-        }
-    }
-
-    fn debounce_changes(&self, mut changes: Vec<FileWatcherChange>) {
-        loop {
-            // Consume possibly incoming file change messages before running a new analysis, but don't wait for more than 100ms.
-            crossbeam_channel::select! {
-                recv(self.receiver) -> message => {
-                    match message {
-                        Ok(OrchestratorMessage::Shutdown) => {
-                            return self.shutdown();
-                        }
-                        Ok(OrchestratorMessage::FileChanges(file_changes)) => {
-                            changes.extend(file_changes);
-                        }
-
-                        Ok(OrchestratorMessage::CheckProgramCompleted { .. })=> {
-                            // disregard any outdated completion message.
-                        }
-                        Ok(OrchestratorMessage::Run) => unreachable!("The orchestrator is already running."),
-
-                        Err(_) => {
-                            // There are no more senders, no point in waiting for more messages
-                            return;
-                        }
-                    }
-                },
-                default(std::time::Duration::from_millis(10)) => {
-                    // No more file changes after 10 ms, send the changes and schedule a new analysis
-                    self.sender.send(MainLoopMessage::ApplyChanges(changes)).unwrap();
-                    self.sender.send(MainLoopMessage::CheckProgram { revision: self.revision}).unwrap();
-                    return;
-                }
-            }
-        }
-    }
-
-    #[allow(clippy::unused_self)]
-    fn shutdown(&self) {
-        tracing::trace!("Shutting down orchestrator.");
-    }
-}
-
-/// Message sent from the orchestrator to the main loop.
-#[derive(Debug)]
-enum MainLoopMessage {
-    CheckProgram { revision: usize },
-    CheckCompleted(Vec<String>),
-    ApplyChanges(Vec<FileWatcherChange>),
-    Exit,
-}
-
-#[derive(Debug)]
-enum OrchestratorMessage {
-    Run,
-    Shutdown,
-
-    CheckProgramCompleted {
-        diagnostics: Vec<String>,
-        revision: usize,
-    },
-
-    FileChanges(Vec<FileWatcherChange>),
-}
-
-fn setup_tracing() {
-    let subscriber = Registry::default().with(
-        tracing_tree::HierarchicalLayer::default()
-            .with_indent_lines(true)
-            .with_indent_amount(2)
-            .with_bracketed_fields(true)
-            .with_thread_ids(true)
-            .with_targets(true)
-            .with_writer(|| Box::new(std::io::stderr()))
-            .with_timer(Uptime::default())
-            .with_filter(LoggingFilter {
-                trace_level: Level::TRACE,
-            }),
-    );
-
-    tracing::subscriber::set_global_default(subscriber).unwrap();
-}
-
-struct LoggingFilter {
-    trace_level: Level,
-}
-
-impl LoggingFilter {
-    fn is_enabled(&self, meta: &Metadata<'_>) -> bool {
-        let filter = if meta.target().starts_with("red_knot") || meta.target().starts_with("ruff") {
-            self.trace_level
-        } else {
-            Level::INFO
-        };
-
-        meta.level() <= &filter
-    }
-}
-
-impl<S> Filter<S> for LoggingFilter {
-    fn enabled(&self, meta: &Metadata<'_>, _cx: &Context<'_, S>) -> bool {
-        self.is_enabled(meta)
-    }
-
-    fn callsite_enabled(&self, meta: &'static Metadata<'static>) -> Interest {
-        if self.is_enabled(meta) {
-            Interest::always()
-        } else {
-            Interest::never()
-        }
-    }
-
-    fn max_level_hint(&self) -> Option<LevelFilter> {
-        Some(LevelFilter::from_level(self.trace_level))
-    }
-}

crates/red_knot/src/parse.rs

@@ -1,41 +0,0 @@
-use std::ops::{Deref, DerefMut};
-use std::sync::Arc;
-
-use ruff_python_ast::ModModule;
-use ruff_python_parser::Parsed;
-
-use crate::cache::KeyValueCache;
-use crate::db::{QueryResult, SourceDb};
-use crate::files::FileId;
-use crate::source::source_text;
-
-#[tracing::instrument(level = "debug", skip(db))]
-pub(crate) fn parse(db: &dyn SourceDb, file_id: FileId) -> QueryResult<Arc<Parsed<ModModule>>> {
-    let jar = db.jar()?;
-
-    jar.parsed.get(&file_id, |file_id| {
-        let source = source_text(db, *file_id)?;
-
-        Ok(Arc::new(ruff_python_parser::parse_unchecked_source(
-            source.text(),
-            source.kind().into(),
-        )))
-    })
-}
-
-#[derive(Debug, Default)]
-pub struct ParsedStorage(KeyValueCache<FileId, Arc<Parsed<ModModule>>>);
-
-impl Deref for ParsedStorage {
-    type Target = KeyValueCache<FileId, Arc<Parsed<ModModule>>>;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl DerefMut for ParsedStorage {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

crates/red_knot/src/program/check.rs

@@ -1,413 +0,0 @@
-use rayon::{current_num_threads, yield_local};
-use rustc_hash::FxHashSet;
-
-use crate::db::{Database, QueryError, QueryResult};
-use crate::files::FileId;
-use crate::lint::{lint_semantic, lint_syntax, Diagnostics};
-use crate::module::{file_to_module, resolve_module};
-use crate::program::Program;
-use crate::semantic::{semantic_index, Dependency};
-
-impl Program {
-    /// Checks all open files in the workspace and its dependencies.
-    #[tracing::instrument(level = "debug", skip_all)]
-    pub fn check(&self, mode: ExecutionMode) -> QueryResult<Vec<String>> {
-        self.cancelled()?;
-
-        let mut context = CheckContext::new(self);
-
-        match mode {
-            ExecutionMode::SingleThreaded => SingleThreadedExecutor.run(&mut context)?,
-            ExecutionMode::ThreadPool => ThreadPoolExecutor.run(&mut context)?,
-        };
-
-        Ok(context.finish())
-    }
-
-    #[tracing::instrument(level = "debug", skip(self, context))]
-    fn check_file(&self, file: FileId, context: &CheckFileContext) -> QueryResult<Diagnostics> {
-        self.cancelled()?;
-
-        let index = semantic_index(self, file)?;
-        let dependencies = index.symbol_table().dependencies();
-
-        if !dependencies.is_empty() {
-            let module = file_to_module(self, file)?;
-
-            // TODO scheduling all dependencies here is wasteful if we don't infer any types on them
-            //  but I think that's unlikely, so it is okay?
-            //  Anyway, we need to figure out a way to retrieve the dependencies of a module
-            //  from the persistent cache. So maybe it should be a separate query after all.
-            for dependency in dependencies {
-                let dependency_name = match dependency {
-                    Dependency::Module(name) => Some(name.clone()),
-                    Dependency::Relative { .. } => match &module {
-                        Some(module) => module.resolve_dependency(self, dependency)?,
-                        None => None,
-                    },
-                };
-
-                if let Some(dependency_name) = dependency_name {
-                    // TODO We may want to have a different check functions for non-first-party
-                    //   files because we only need to index them and not check them.
-                    //   Supporting non-first-party code also requires supporting typing stubs.
-                    if let Some(dependency) = resolve_module(self, dependency_name)? {
-                        if dependency.path(self)?.root().kind().is_first_party() {
-                            context.schedule_dependency(dependency.path(self)?.file());
-                        }
-                    }
-                }
-            }
-        }
-
-        let mut diagnostics = Vec::new();
-
-        if self.workspace().is_file_open(file) {
-            diagnostics.extend_from_slice(&lint_syntax(self, file)?);
-            diagnostics.extend_from_slice(&lint_semantic(self, file)?);
-        }
-
-        Ok(Diagnostics::from(diagnostics))
-    }
-}
-
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub enum ExecutionMode {
-    SingleThreaded,
-    ThreadPool,
-}
-
-/// Context that stores state information about the entire check operation.
-struct CheckContext<'a> {
-    /// IDs of the files that have been queued for checking.
-    ///
-    /// Used to avoid queuing the same file twice.
-    scheduled_files: FxHashSet<FileId>,
-
-    /// Reference to the program that is checked.
-    program: &'a Program,
-
-    /// The aggregated diagnostics
-    diagnostics: Vec<String>,
-}
-
-impl<'a> CheckContext<'a> {
-    fn new(program: &'a Program) -> Self {
-        Self {
-            scheduled_files: FxHashSet::default(),
-            program,
-            diagnostics: Vec::new(),
-        }
-    }
-
-    /// Returns the tasks to check all open files in the workspace.
-    fn check_open_files(&mut self) -> Vec<CheckOpenFileTask> {
-        self.scheduled_files
-            .extend(self.program.workspace().open_files());
-
-        self.program
-            .workspace()
-            .open_files()
-            .map(|file_id| CheckOpenFileTask { file_id })
-            .collect()
-    }
-
-    /// Returns the task to check a dependency.
-    fn check_dependency(&mut self, file_id: FileId) -> Option<CheckDependencyTask> {
-        if self.scheduled_files.insert(file_id) {
-            Some(CheckDependencyTask { file_id })
-        } else {
-            None
-        }
-    }
-
-    /// Pushes the result for a single file check operation
-    fn push_diagnostics(&mut self, diagnostics: &Diagnostics) {
-        self.diagnostics.extend_from_slice(diagnostics);
-    }
-
-    /// Returns a reference to the program that is being checked.
-    fn program(&self) -> &'a Program {
-        self.program
-    }
-
-    /// Creates a task context that is used to check a single file.
-    fn task_context<'b, S>(&self, dependency_scheduler: &'b S) -> CheckTaskContext<'a, 'b, S>
-    where
-        S: ScheduleDependency,
-    {
-        CheckTaskContext {
-            program: self.program,
-            dependency_scheduler,
-        }
-    }
-
-    fn finish(self) -> Vec<String> {
-        self.diagnostics
-    }
-}
-
-/// Trait that abstracts away how a dependency of a file gets scheduled for checking.
-trait ScheduleDependency {
-    /// Schedules the file with the given ID for checking.
-    fn schedule(&self, file_id: FileId);
-}
-
-impl<T> ScheduleDependency for T
-where
-    T: Fn(FileId),
-{
-    fn schedule(&self, file_id: FileId) {
-        let f = self;
-        f(file_id);
-    }
-}
-
-/// Context that is used to run a single file check task.
-///
-/// The task is generic over `S` because it is passed across thread boundaries and
-/// we don't want to add the requirement that [`ScheduleDependency`] must be [`Send`].
-struct CheckTaskContext<'a, 'scheduler, S>
-where
-    S: ScheduleDependency,
-{
-    dependency_scheduler: &'scheduler S,
-    program: &'a Program,
-}
-
-impl<'a, 'scheduler, S> CheckTaskContext<'a, 'scheduler, S>
-where
-    S: ScheduleDependency,
-{
-    fn as_file_context(&self) -> CheckFileContext<'scheduler> {
-        CheckFileContext {
-            dependency_scheduler: self.dependency_scheduler,
-        }
-    }
-}
-
-/// Context passed when checking a single file.
-///
-/// This is a trimmed down version of [`CheckTaskContext`] with the type parameter `S` erased
-/// to avoid monomorphization of [`Program:check_file`].
-struct CheckFileContext<'a> {
-    dependency_scheduler: &'a dyn ScheduleDependency,
-}
-
-impl<'a> CheckFileContext<'a> {
-    fn schedule_dependency(&self, file_id: FileId) {
-        self.dependency_scheduler.schedule(file_id);
-    }
-}
-
-#[derive(Debug)]
-enum CheckFileTask {
-    OpenFile(CheckOpenFileTask),
-    Dependency(CheckDependencyTask),
-}
-
-impl CheckFileTask {
-    /// Runs the task and returns the results for checking this file.
-    fn run<S>(&self, context: &CheckTaskContext<S>) -> QueryResult<Diagnostics>
-    where
-        S: ScheduleDependency,
-    {
-        match self {
-            Self::OpenFile(task) => task.run(context),
-            Self::Dependency(task) => task.run(context),
-        }
-    }
-
-    fn file_id(&self) -> FileId {
-        match self {
-            CheckFileTask::OpenFile(task) => task.file_id,
-            CheckFileTask::Dependency(task) => task.file_id,
-        }
-    }
-}
-
-/// Task to check an open file.
-
-#[derive(Debug)]
-struct CheckOpenFileTask {
-    file_id: FileId,
-}
-
-impl CheckOpenFileTask {
-    fn run<S>(&self, context: &CheckTaskContext<S>) -> QueryResult<Diagnostics>
-    where
-        S: ScheduleDependency,
-    {
-        context
-            .program
-            .check_file(self.file_id, &context.as_file_context())
-    }
-}
-
-/// Task to check a dependency file.
-#[derive(Debug)]
-struct CheckDependencyTask {
-    file_id: FileId,
-}
-
-impl CheckDependencyTask {
-    fn run<S>(&self, context: &CheckTaskContext<S>) -> QueryResult<Diagnostics>
-    where
-        S: ScheduleDependency,
-    {
-        context
-            .program
-            .check_file(self.file_id, &context.as_file_context())
-    }
-}
-
-/// Executor that schedules the checking of individual program files.
-trait CheckExecutor {
-    fn run(self, context: &mut CheckContext) -> QueryResult<()>;
-}
-
-/// Executor that runs all check operations on the current thread.
-///
-/// The executor does not schedule dependencies for checking.
-/// The main motivation for scheduling dependencies
-/// in a multithreaded environment is to parse and index the dependencies concurrently.
-/// However, that doesn't make sense in a single threaded environment, because the dependencies then compute
-/// with checking the open files. Checking dependencies in a single threaded environment is more likely
-/// to hurt performance because we end up analyzing files in their entirety, even if we only need to type check parts of them.
-#[derive(Debug, Default)]
-struct SingleThreadedExecutor;
-
-impl CheckExecutor for SingleThreadedExecutor {
-    fn run(self, context: &mut CheckContext) -> QueryResult<()> {
-        let mut queue = context.check_open_files();
-
-        let noop_schedule_dependency = |_| {};
-
-        while let Some(file) = queue.pop() {
-            context.program().cancelled()?;
-
-            let task_context = context.task_context(&noop_schedule_dependency);
-            context.push_diagnostics(&file.run(&task_context)?);
-        }
-
-        Ok(())
-    }
-}
-
-/// Executor that runs the check operations on a thread pool.
-///
-/// The executor runs each check operation as its own task using a thread pool.
-///
-/// Other than [`SingleThreadedExecutor`], this executor schedules dependencies for checking. It
-/// even schedules dependencies for checking when the thread pool size is 1 for a better debugging experience.
-#[derive(Debug, Default)]
-struct ThreadPoolExecutor;
-
-impl CheckExecutor for ThreadPoolExecutor {
-    fn run(self, context: &mut CheckContext) -> QueryResult<()> {
-        let num_threads = current_num_threads();
-        let single_threaded = num_threads == 1;
-        let span = tracing::trace_span!("ThreadPoolExecutor::run", num_threads);
-        let _ = span.enter();
-
-        let mut queue: Vec<_> = context
-            .check_open_files()
-            .into_iter()
-            .map(CheckFileTask::OpenFile)
-            .collect();
-
-        let (sender, receiver) = if single_threaded {
-            // Use an unbounded queue for single threaded execution to prevent deadlocks
-            // when a single file schedules multiple dependencies.
-            crossbeam::channel::unbounded()
-        } else {
-            // Use a bounded queue to apply backpressure when the orchestration thread isn't able to keep
-            // up processing messages from the worker threads.
-            crossbeam::channel::bounded(num_threads)
-        };
-
-        let schedule_sender = sender.clone();
-        let schedule_dependency = move |file_id| {
-            schedule_sender
-                .send(ThreadPoolMessage::ScheduleDependency(file_id))
-                .unwrap();
-        };
-
-        let result = rayon::in_place_scope(|scope| {
-            let mut pending = 0usize;
-
-            loop {
-                context.program().cancelled()?;
-
-                // 1. Try to get a queued message to ensure that we have always remaining space in the channel to prevent blocking the worker threads.
-                // 2. Try to process a queued file
-                // 3. If there's no queued file wait for the next incoming message.
-                // 4. Exit if there are no more messages and no senders.
-                let message = if let Ok(message) = receiver.try_recv() {
-                    message
-                } else if let Some(task) = queue.pop() {
-                    pending += 1;
-
-                    let task_context = context.task_context(&schedule_dependency);
-                    let sender = sender.clone();
-                    let task_span = tracing::trace_span!(
-                        parent: &span,
-                        "CheckFileTask::run",
-                        file_id = task.file_id().as_u32(),
-                    );
-
-                    scope.spawn(move |_| {
-                        task_span.in_scope(|| match task.run(&task_context) {
-                            Ok(result) => {
-                                sender.send(ThreadPoolMessage::Completed(result)).unwrap();
-                            }
-                            Err(err) => sender.send(ThreadPoolMessage::Errored(err)).unwrap(),
-                        });
-                    });
-
-                    // If this is a single threaded rayon thread pool, yield the current thread
-                    // or we never start processing the work items.
-                    if single_threaded {
-                        yield_local();
-                    }
-
-                    continue;
-                } else if let Ok(message) = receiver.recv() {
-                    message
-                } else {
-                    break;
-                };
-
-                match message {
-                    ThreadPoolMessage::ScheduleDependency(dependency) => {
-                        if let Some(task) = context.check_dependency(dependency) {
-                            queue.push(CheckFileTask::Dependency(task));
-                        }
-                    }
-                    ThreadPoolMessage::Completed(diagnostics) => {
-                        context.push_diagnostics(&diagnostics);
-                        pending -= 1;
-
-                        if pending == 0 && queue.is_empty() {
-                            break;
-                        }
-                    }
-                    ThreadPoolMessage::Errored(err) => {
-                        return Err(err);
-                    }
-                }
-            }
-
-            Ok(())
-        });
-
-        result
-    }
-}
-
-#[derive(Debug)]
-enum ThreadPoolMessage {
-    ScheduleDependency(FileId),
-    Completed(Diagnostics),
-    Errored(QueryError),
-}

crates/red_knot/src/program/mod.rs

@@ -1,275 +0,0 @@
-use std::collections::hash_map::Entry;
-use std::path::{Path, PathBuf};
-use std::sync::Arc;
-
-use rustc_hash::FxHashMap;
-
-use crate::db::{
-    Database, Db, DbRuntime, DbWithJar, HasJar, HasJars, JarsStorage, LintDb, LintJar,
-    ParallelDatabase, QueryResult, SemanticDb, SemanticJar, Snapshot, SourceDb, SourceJar, Upcast,
-};
-use crate::files::{FileId, Files};
-use crate::Workspace;
-
-pub mod check;
-
-#[derive(Debug)]
-pub struct Program {
-    jars: JarsStorage<Program>,
-    files: Files,
-    workspace: Workspace,
-}
-
-impl Program {
-    pub fn new(workspace: Workspace) -> Self {
-        Self {
-            jars: JarsStorage::default(),
-            files: Files::default(),
-            workspace,
-        }
-    }
-
-    pub fn apply_changes<I>(&mut self, changes: I)
-    where
-        I: IntoIterator<Item = FileWatcherChange>,
-    {
-        let mut aggregated_changes = AggregatedChanges::default();
-
-        aggregated_changes.extend(changes.into_iter().map(|change| FileChange {
-            id: self.files.intern(&change.path),
-            kind: change.kind,
-        }));
-
-        let (source, semantic, lint) = self.jars_mut();
-        for change in aggregated_changes.iter() {
-            semantic.module_resolver.remove_module_by_file(change.id);
-            semantic.semantic_indices.remove(&change.id);
-            source.sources.remove(&change.id);
-            source.parsed.remove(&change.id);
-            // TODO: remove all dependent modules as well
-            semantic.type_store.remove_module(change.id);
-            lint.lint_syntax.remove(&change.id);
-            lint.lint_semantic.remove(&change.id);
-        }
-    }
-
-    pub fn files(&self) -> &Files {
-        &self.files
-    }
-
-    pub fn workspace(&self) -> &Workspace {
-        &self.workspace
-    }
-
-    pub fn workspace_mut(&mut self) -> &mut Workspace {
-        &mut self.workspace
-    }
-}
-
-impl SourceDb for Program {
-    fn file_id(&self, path: &Path) -> FileId {
-        self.files.intern(path)
-    }
-
-    fn file_path(&self, file_id: FileId) -> Arc<Path> {
-        self.files.path(file_id)
-    }
-}
-
-impl DbWithJar<SourceJar> for Program {}
-
-impl SemanticDb for Program {}
-
-impl DbWithJar<SemanticJar> for Program {}
-
-impl LintDb for Program {}
-
-impl DbWithJar<LintJar> for Program {}
-
-impl Upcast<dyn SemanticDb> for Program {
-    fn upcast(&self) -> &(dyn SemanticDb + 'static) {
-        self
-    }
-}
-
-impl Upcast<dyn SourceDb> for Program {
-    fn upcast(&self) -> &(dyn SourceDb + 'static) {
-        self
-    }
-}
-
-impl Upcast<dyn LintDb> for Program {
-    fn upcast(&self) -> &(dyn LintDb + 'static) {
-        self
-    }
-}
-
-impl Db for Program {}
-
-impl Database for Program {
-    fn runtime(&self) -> &DbRuntime {
-        self.jars.runtime()
-    }
-
-    fn runtime_mut(&mut self) -> &mut DbRuntime {
-        self.jars.runtime_mut()
-    }
-}
-
-impl ParallelDatabase for Program {
-    fn snapshot(&self) -> Snapshot<Self> {
-        Snapshot::new(Self {
-            jars: self.jars.snapshot(),
-            files: self.files.snapshot(),
-            workspace: self.workspace.clone(),
-        })
-    }
-}
-
-impl HasJars for Program {
-    type Jars = (SourceJar, SemanticJar, LintJar);
-
-    fn jars(&self) -> QueryResult<&Self::Jars> {
-        self.jars.jars()
-    }
-
-    fn jars_mut(&mut self) -> &mut Self::Jars {
-        self.jars.jars_mut()
-    }
-}
-
-impl HasJar<SourceJar> for Program {
-    fn jar(&self) -> QueryResult<&SourceJar> {
-        Ok(&self.jars()?.0)
-    }
-
-    fn jar_mut(&mut self) -> &mut SourceJar {
-        &mut self.jars_mut().0
-    }
-}
-
-impl HasJar<SemanticJar> for Program {
-    fn jar(&self) -> QueryResult<&SemanticJar> {
-        Ok(&self.jars()?.1)
-    }
-
-    fn jar_mut(&mut self) -> &mut SemanticJar {
-        &mut self.jars_mut().1
-    }
-}
-
-impl HasJar<LintJar> for Program {
-    fn jar(&self) -> QueryResult<&LintJar> {
-        Ok(&self.jars()?.2)
-    }
-
-    fn jar_mut(&mut self) -> &mut LintJar {
-        &mut self.jars_mut().2
-    }
-}
-
-#[derive(Clone, Debug)]
-pub struct FileWatcherChange {
-    path: PathBuf,
-    kind: FileChangeKind,
-}
-
-impl FileWatcherChange {
-    pub fn new(path: PathBuf, kind: FileChangeKind) -> Self {
-        Self { path, kind }
-    }
-}
-
-#[derive(Copy, Clone, Debug)]
-struct FileChange {
-    id: FileId,
-    kind: FileChangeKind,
-}
-
-impl FileChange {
-    fn file_id(self) -> FileId {
-        self.id
-    }
-
-    fn kind(self) -> FileChangeKind {
-        self.kind
-    }
-}
-
-#[derive(Copy, Clone, Debug, Eq, PartialEq)]
-pub enum FileChangeKind {
-    Created,
-    Modified,
-    Deleted,
-}
-
-#[derive(Default, Debug)]
-struct AggregatedChanges {
-    changes: FxHashMap<FileId, FileChangeKind>,
-}
-
-impl AggregatedChanges {
-    fn add(&mut self, change: FileChange) {
-        match self.changes.entry(change.file_id()) {
-            Entry::Occupied(mut entry) => {
-                let merged = entry.get_mut();
-
-                match (merged, change.kind()) {
-                    (FileChangeKind::Created, FileChangeKind::Deleted) => {
-                        // Deletion after creations means that ruff never saw the file.
-                        entry.remove();
-                    }
-                    (FileChangeKind::Created, FileChangeKind::Modified) => {
-                        // No-op, for ruff, modifying a file that it doesn't yet know that it exists is still considered a creation.
-                    }
-
-                    (FileChangeKind::Modified, FileChangeKind::Created) => {
-                        // Uhh, that should probably not happen. Continue considering it a modification.
-                    }
-
-                    (FileChangeKind::Modified, FileChangeKind::Deleted) => {
-                        *entry.get_mut() = FileChangeKind::Deleted;
-                    }
-
-                    (FileChangeKind::Deleted, FileChangeKind::Created) => {
-                        *entry.get_mut() = FileChangeKind::Modified;
-                    }
-
-                    (FileChangeKind::Deleted, FileChangeKind::Modified) => {
-                        // That's weird, but let's consider it a modification.
-                        *entry.get_mut() = FileChangeKind::Modified;
-                    }
-
-                    (FileChangeKind::Created, FileChangeKind::Created)
-                    | (FileChangeKind::Modified, FileChangeKind::Modified)
-                    | (FileChangeKind::Deleted, FileChangeKind::Deleted) => {
-                        // No-op transitions. Some of them should be impossible but we handle them anyway.
-                    }
-                }
-            }
-            Entry::Vacant(entry) => {
-                entry.insert(change.kind());
-            }
-        }
-    }
-
-    fn extend<I>(&mut self, changes: I)
-    where
-        I: IntoIterator<Item = FileChange>,
-    {
-        let iter = changes.into_iter();
-        let (lower, _) = iter.size_hint();
-        self.changes.reserve(lower);
-
-        for change in iter {
-            self.add(change);
-        }
-    }
-
-    fn iter(&self) -> impl Iterator<Item = FileChange> + '_ {
-        self.changes.iter().map(|(id, kind)| FileChange {
-            id: *id,
-            kind: *kind,
-        })
-    }
-}

crates/red_knot/src/semantic.rs

@@ -1,882 +0,0 @@
-use std::num::NonZeroU32;
-
-use ruff_python_ast as ast;
-use ruff_python_ast::visitor::source_order::SourceOrderVisitor;
-use ruff_python_ast::AstNode;
-
-use crate::ast_ids::{NodeKey, TypedNodeKey};
-use crate::cache::KeyValueCache;
-use crate::db::{QueryResult, SemanticDb, SemanticJar};
-use crate::files::FileId;
-use crate::module::Module;
-use crate::module::ModuleName;
-use crate::parse::parse;
-use crate::Name;
-pub(crate) use definitions::Definition;
-use definitions::{ImportDefinition, ImportFromDefinition};
-pub(crate) use flow_graph::ConstrainedDefinition;
-use flow_graph::{FlowGraph, FlowGraphBuilder, FlowNodeId, ReachableDefinitionsIterator};
-use ruff_index::{newtype_index, IndexVec};
-use rustc_hash::FxHashMap;
-use std::ops::{Deref, DerefMut};
-use std::sync::Arc;
-pub(crate) use symbol_table::{Dependency, SymbolId};
-use symbol_table::{ScopeId, ScopeKind, SymbolFlags, SymbolTable, SymbolTableBuilder};
-pub(crate) use types::{infer_definition_type, infer_symbol_public_type, Type, TypeStore};
-
-mod definitions;
-mod flow_graph;
-mod symbol_table;
-mod types;
-
-#[tracing::instrument(level = "debug", skip(db))]
-pub fn semantic_index(db: &dyn SemanticDb, file_id: FileId) -> QueryResult<Arc<SemanticIndex>> {
-    let jar: &SemanticJar = db.jar()?;
-
-    jar.semantic_indices.get(&file_id, |_| {
-        let parsed = parse(db.upcast(), file_id)?;
-        Ok(Arc::from(SemanticIndex::from_ast(parsed.syntax())))
-    })
-}
-
-#[tracing::instrument(level = "debug", skip(db))]
-pub fn resolve_global_symbol(
-    db: &dyn SemanticDb,
-    module: Module,
-    name: &str,
-) -> QueryResult<Option<GlobalSymbolId>> {
-    let file_id = module.path(db)?.file();
-    let symbol_table = &semantic_index(db, file_id)?.symbol_table;
-    let Some(symbol_id) = symbol_table.root_symbol_id_by_name(name) else {
-        return Ok(None);
-    };
-    Ok(Some(GlobalSymbolId { file_id, symbol_id }))
-}
-
-#[newtype_index]
-pub struct ExpressionId;
-
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub struct GlobalSymbolId {
-    pub(crate) file_id: FileId,
-    pub(crate) symbol_id: SymbolId,
-}
-
-#[derive(Debug)]
-pub struct SemanticIndex {
-    symbol_table: SymbolTable,
-    flow_graph: FlowGraph,
-    expressions: FxHashMap<NodeKey, ExpressionId>,
-    expressions_by_id: IndexVec<ExpressionId, NodeKey>,
-}
-
-impl SemanticIndex {
-    pub fn from_ast(module: &ast::ModModule) -> Self {
-        let root_scope_id = SymbolTable::root_scope_id();
-        let mut indexer = SemanticIndexer {
-            symbol_table_builder: SymbolTableBuilder::new(),
-            flow_graph_builder: FlowGraphBuilder::new(),
-            scopes: vec![ScopeState {
-                scope_id: root_scope_id,
-                current_flow_node_id: FlowGraph::start(),
-            }],
-            expressions: FxHashMap::default(),
-            expressions_by_id: IndexVec::default(),
-            current_definition: None,
-        };
-        indexer.visit_body(&module.body);
-        indexer.finish()
-    }
-
-    fn resolve_expression_id<'a>(
-        &self,
-        ast: &'a ast::ModModule,
-        expression_id: ExpressionId,
-    ) -> ast::AnyNodeRef<'a> {
-        let node_key = self.expressions_by_id[expression_id];
-        node_key
-            .resolve(ast.as_any_node_ref())
-            .expect("node to resolve")
-    }
-
-    /// Return an iterator over all definitions of `symbol_id` reachable from `use_expr`. The value
-    /// of `symbol_id` in `use_expr` must originate from one of the iterated definitions (or from
-    /// an external reassignment of the name outside of this scope).
-    pub fn reachable_definitions(
-        &self,
-        symbol_id: SymbolId,
-        use_expr: &ast::Expr,
-    ) -> ReachableDefinitionsIterator {
-        let expression_id = self.expression_id(use_expr);
-        ReachableDefinitionsIterator::new(
-            &self.flow_graph,
-            symbol_id,
-            self.flow_graph.for_expr(expression_id),
-        )
-    }
-
-    pub fn expression_id(&self, expression: &ast::Expr) -> ExpressionId {
-        self.expressions[&NodeKey::from_node(expression.into())]
-    }
-
-    pub fn symbol_table(&self) -> &SymbolTable {
-        &self.symbol_table
-    }
-}
-
-#[derive(Debug)]
-struct ScopeState {
-    scope_id: ScopeId,
-    current_flow_node_id: FlowNodeId,
-}
-
-#[derive(Debug)]
-struct SemanticIndexer {
-    symbol_table_builder: SymbolTableBuilder,
-    flow_graph_builder: FlowGraphBuilder,
-    scopes: Vec<ScopeState>,
-    /// the definition whose target(s) we are currently walking
-    current_definition: Option<Definition>,
-    expressions: FxHashMap<NodeKey, ExpressionId>,
-    expressions_by_id: IndexVec<ExpressionId, NodeKey>,
-}
-
-impl SemanticIndexer {
-    pub(crate) fn finish(mut self) -> SemanticIndex {
-        let SemanticIndexer {
-            flow_graph_builder,
-            symbol_table_builder,
-            ..
-        } = self;
-        self.expressions.shrink_to_fit();
-        self.expressions_by_id.shrink_to_fit();
-        SemanticIndex {
-            flow_graph: flow_graph_builder.finish(),
-            symbol_table: symbol_table_builder.finish(),
-            expressions: self.expressions,
-            expressions_by_id: self.expressions_by_id,
-        }
-    }
-
-    fn set_current_flow_node(&mut self, new_flow_node_id: FlowNodeId) {
-        let scope_state = self.scopes.last_mut().expect("scope stack is never empty");
-        scope_state.current_flow_node_id = new_flow_node_id;
-    }
-
-    fn current_flow_node(&self) -> FlowNodeId {
-        self.scopes
-            .last()
-            .expect("scope stack is never empty")
-            .current_flow_node_id
-    }
-
-    fn add_or_update_symbol(&mut self, identifier: &str, flags: SymbolFlags) -> SymbolId {
-        self.symbol_table_builder
-            .add_or_update_symbol(self.cur_scope(), identifier, flags)
-    }
-
-    fn add_or_update_symbol_with_def(
-        &mut self,
-        identifier: &str,
-        definition: Definition,
-    ) -> SymbolId {
-        let symbol_id = self.add_or_update_symbol(identifier, SymbolFlags::IS_DEFINED);
-        self.symbol_table_builder
-            .add_definition(symbol_id, definition.clone());
-        let new_flow_node_id =
-            self.flow_graph_builder
-                .add_definition(symbol_id, definition, self.current_flow_node());
-        self.set_current_flow_node(new_flow_node_id);
-        symbol_id
-    }
-
-    fn push_scope(
-        &mut self,
-        name: &str,
-        kind: ScopeKind,
-        definition: Option<Definition>,
-        defining_symbol: Option<SymbolId>,
-    ) -> ScopeId {
-        let scope_id = self.symbol_table_builder.add_child_scope(
-            self.cur_scope(),
-            name,
-            kind,
-            definition,
-            defining_symbol,
-        );
-        self.scopes.push(ScopeState {
-            scope_id,
-            current_flow_node_id: FlowGraph::start(),
-        });
-        scope_id
-    }
-
-    fn pop_scope(&mut self) -> ScopeId {
-        self.scopes
-            .pop()
-            .expect("Scope stack should never be empty")
-            .scope_id
-    }
-
-    fn cur_scope(&self) -> ScopeId {
-        self.scopes
-            .last()
-            .expect("Scope stack should never be empty")
-            .scope_id
-    }
-
-    fn record_scope_for_node(&mut self, node_key: NodeKey, scope_id: ScopeId) {
-        self.symbol_table_builder
-            .record_scope_for_node(node_key, scope_id);
-    }
-
-    fn insert_constraint(&mut self, expr: &ast::Expr) {
-        let node_key = NodeKey::from_node(expr.into());
-        let expression_id = self.expressions[&node_key];
-        let constraint = self
-            .flow_graph_builder
-            .add_constraint(self.current_flow_node(), expression_id);
-        self.set_current_flow_node(constraint);
-    }
-
-    fn with_type_params(
-        &mut self,
-        name: &str,
-        params: &Option<Box<ast::TypeParams>>,
-        definition: Option<Definition>,
-        defining_symbol: Option<SymbolId>,
-        nested: impl FnOnce(&mut Self) -> ScopeId,
-    ) -> ScopeId {
-        if let Some(type_params) = params {
-            self.push_scope(name, ScopeKind::Annotation, definition, defining_symbol);
-            for type_param in &type_params.type_params {
-                let name = match type_param {
-                    ast::TypeParam::TypeVar(ast::TypeParamTypeVar { name, .. }) => name,
-                    ast::TypeParam::ParamSpec(ast::TypeParamParamSpec { name, .. }) => name,
-                    ast::TypeParam::TypeVarTuple(ast::TypeParamTypeVarTuple { name, .. }) => name,
-                };
-                self.add_or_update_symbol(name, SymbolFlags::IS_DEFINED);
-            }
-        }
-        let scope_id = nested(self);
-        if params.is_some() {
-            self.pop_scope();
-        }
-        scope_id
-    }
-}
-
-impl SourceOrderVisitor<'_> for SemanticIndexer {
-    fn visit_expr(&mut self, expr: &ast::Expr) {
-        let node_key = NodeKey::from_node(expr.into());
-        let expression_id = self.expressions_by_id.push(node_key);
-
-        let flow_expression_id = self
-            .flow_graph_builder
-            .record_expr(self.current_flow_node());
-        debug_assert_eq!(expression_id, flow_expression_id);
-
-        let symbol_expression_id = self
-            .symbol_table_builder
-            .record_expression(self.cur_scope());
-
-        debug_assert_eq!(expression_id, symbol_expression_id);
-
-        self.expressions.insert(node_key, expression_id);
-
-        match expr {
-            ast::Expr::Name(ast::ExprName { id, ctx, .. }) => {
-                let flags = match ctx {
-                    ast::ExprContext::Load => SymbolFlags::IS_USED,
-                    ast::ExprContext::Store => SymbolFlags::IS_DEFINED,
-                    ast::ExprContext::Del => SymbolFlags::IS_DEFINED,
-                    ast::ExprContext::Invalid => SymbolFlags::empty(),
-                };
-                self.add_or_update_symbol(id, flags);
-                if flags.contains(SymbolFlags::IS_DEFINED) {
-                    if let Some(curdef) = self.current_definition.clone() {
-                        self.add_or_update_symbol_with_def(id, curdef);
-                    }
-                }
-                ast::visitor::source_order::walk_expr(self, expr);
-            }
-            ast::Expr::Named(node) => {
-                debug_assert!(self.current_definition.is_none());
-                self.current_definition =
-                    Some(Definition::NamedExpr(TypedNodeKey::from_node(node)));
-                // TODO walrus in comprehensions is implicitly nonlocal
-                self.visit_expr(&node.target);
-                self.current_definition = None;
-                self.visit_expr(&node.value);
-            }
-            ast::Expr::If(ast::ExprIf {
-                body, test, orelse, ..
-            }) => {
-                // TODO detect statically known truthy or falsy test (via type inference, not naive
-                // AST inspection, so we can't simplify here, need to record test expression in CFG
-                // for later checking)
-
-                self.visit_expr(test);
-
-                let if_branch = self.flow_graph_builder.add_branch(self.current_flow_node());
-
-                self.set_current_flow_node(if_branch);
-                self.insert_constraint(test);
-                self.visit_expr(body);
-
-                let post_body = self.current_flow_node();
-
-                self.set_current_flow_node(if_branch);
-                self.visit_expr(orelse);
-
-                let post_else = self
-                    .flow_graph_builder
-                    .add_phi(self.current_flow_node(), post_body);
-
-                self.set_current_flow_node(post_else);
-            }
-            _ => {
-                ast::visitor::source_order::walk_expr(self, expr);
-            }
-        }
-    }
-
-    fn visit_stmt(&mut self, stmt: &ast::Stmt) {
-        // TODO need to capture more definition statements here
-        match stmt {
-            ast::Stmt::ClassDef(node) => {
-                let node_key = TypedNodeKey::from_node(node);
-                let def = Definition::ClassDef(node_key.clone());
-                let symbol_id = self.add_or_update_symbol_with_def(&node.name, def.clone());
-                for decorator in &node.decorator_list {
-                    self.visit_decorator(decorator);
-                }
-                let scope_id = self.with_type_params(
-                    &node.name,
-                    &node.type_params,
-                    Some(def.clone()),
-                    Some(symbol_id),
-                    |indexer| {
-                        if let Some(arguments) = &node.arguments {
-                            indexer.visit_arguments(arguments);
-                        }
-                        let scope_id = indexer.push_scope(
-                            &node.name,
-                            ScopeKind::Class,
-                            Some(def.clone()),
-                            Some(symbol_id),
-                        );
-                        indexer.visit_body(&node.body);
-                        indexer.pop_scope();
-                        scope_id
-                    },
-                );
-                self.record_scope_for_node(*node_key.erased(), scope_id);
-            }
-            ast::Stmt::FunctionDef(node) => {
-                let node_key = TypedNodeKey::from_node(node);
-                let def = Definition::FunctionDef(node_key.clone());
-                let symbol_id = self.add_or_update_symbol_with_def(&node.name, def.clone());
-                for decorator in &node.decorator_list {
-                    self.visit_decorator(decorator);
-                }
-                let scope_id = self.with_type_params(
-                    &node.name,
-                    &node.type_params,
-                    Some(def.clone()),
-                    Some(symbol_id),
-                    |indexer| {
-                        indexer.visit_parameters(&node.parameters);
-                        for expr in &node.returns {
-                            indexer.visit_annotation(expr);
-                        }
-                        let scope_id = indexer.push_scope(
-                            &node.name,
-                            ScopeKind::Function,
-                            Some(def.clone()),
-                            Some(symbol_id),
-                        );
-                        indexer.visit_body(&node.body);
-                        indexer.pop_scope();
-                        scope_id
-                    },
-                );
-                self.record_scope_for_node(*node_key.erased(), scope_id);
-            }
-            ast::Stmt::Import(ast::StmtImport { names, .. }) => {
-                for alias in names {
-                    let symbol_name = if let Some(asname) = &alias.asname {
-                        asname.id.as_str()
-                    } else {
-                        alias.name.id.split('.').next().unwrap()
-                    };
-
-                    let module = ModuleName::new(&alias.name.id);
-
-                    let def = Definition::Import(ImportDefinition {
-                        module: module.clone(),
-                    });
-                    self.add_or_update_symbol_with_def(symbol_name, def);
-                    self.symbol_table_builder
-                        .add_dependency(Dependency::Module(module));
-                }
-            }
-            ast::Stmt::ImportFrom(ast::StmtImportFrom {
-                module,
-                names,
-                level,
-                ..
-            }) => {
-                let module = module.as_ref().map(|m| ModuleName::new(&m.id));
-
-                for alias in names {
-                    let symbol_name = if let Some(asname) = &alias.asname {
-                        asname.id.as_str()
-                    } else {
-                        alias.name.id.as_str()
-                    };
-                    let def = Definition::ImportFrom(ImportFromDefinition {
-                        module: module.clone(),
-                        name: Name::new(&alias.name.id),
-                        level: *level,
-                    });
-                    self.add_or_update_symbol_with_def(symbol_name, def);
-                }
-
-                let dependency = if let Some(module) = module {
-                    match NonZeroU32::new(*level) {
-                        Some(level) => Dependency::Relative {
-                            level,
-                            module: Some(module),
-                        },
-                        None => Dependency::Module(module),
-                    }
-                } else {
-                    Dependency::Relative {
-                        level: NonZeroU32::new(*level)
-                            .expect("Import without a module to have a level > 0"),
-                        module,
-                    }
-                };
-
-                self.symbol_table_builder.add_dependency(dependency);
-            }
-            ast::Stmt::Assign(node) => {
-                debug_assert!(self.current_definition.is_none());
-                self.visit_expr(&node.value);
-                self.current_definition =
-                    Some(Definition::Assignment(TypedNodeKey::from_node(node)));
-                for expr in &node.targets {
-                    self.visit_expr(expr);
-                }
-
-                self.current_definition = None;
-            }
-            ast::Stmt::If(node) => {
-                // TODO detect statically known truthy or falsy test (via type inference, not naive
-                // AST inspection, so we can't simplify here, need to record test expression in CFG
-                // for later checking)
-
-                // we visit the if "test" condition first regardless
-                self.visit_expr(&node.test);
-
-                // create branch node: does the if test pass or not?
-                let if_branch = self.flow_graph_builder.add_branch(self.current_flow_node());
-
-                // visit the body of the `if` clause
-                self.set_current_flow_node(if_branch);
-                self.insert_constraint(&node.test);
-                self.visit_body(&node.body);
-
-                // Flow node for the last if/elif condition branch; represents the "no branch
-                // taken yet" possibility (where "taking a branch" means that the condition in an
-                // if or elif evaluated to true and control flow went into that clause).
-                let mut prior_branch = if_branch;
-
-                // Flow node for the state after the prior if/elif/else clause; represents "we have
-                // taken one of the branches up to this point." Initially set to the post-if-clause
-                // state, later will be set to the phi node joining that possible path with the
-                // possibility that we took a later if/elif/else clause instead.
-                let mut post_prior_clause = self.current_flow_node();
-
-                // Flag to mark if the final clause is an "else" -- if so, that means the "match no
-                // clauses" path is not possible, we have to go through one of the clauses.
-                let mut last_branch_is_else = false;
-
-                for clause in &node.elif_else_clauses {
-                    if let Some(test) = &clause.test {
-                        self.visit_expr(test);
-                        // This is an elif clause. Create a new branch node. Its predecessor is the
-                        // previous branch node, because we can only take one branch in an entire
-                        // if/elif/else chain, so if we take this branch, it can only be because we
-                        // didn't take the previous one.
-                        prior_branch = self.flow_graph_builder.add_branch(prior_branch);
-                        self.set_current_flow_node(prior_branch);
-                        self.insert_constraint(test);
-                    } else {
-                        // This is an else clause. No need to create a branch node; there's no
-                        // branch here, if we haven't taken any previous branch, we definitely go
-                        // into the "else" clause.
-                        self.set_current_flow_node(prior_branch);
-                        last_branch_is_else = true;
-                    }
-                    self.visit_elif_else_clause(clause);
-                    // Update `post_prior_clause` to a new phi node joining the possibility that we
-                    // took any of the previous branches with the possibility that we took the one
-                    // just visited.
-                    post_prior_clause = self
-                        .flow_graph_builder
-                        .add_phi(self.current_flow_node(), post_prior_clause);
-                }
-
-                if !last_branch_is_else {
-                    // Final branch was not an "else", which means it's possible we took zero
-                    // branches in the entire if/elif chain, so we need one more phi node to join
-                    // the "no branches taken" possibility.
-                    post_prior_clause = self
-                        .flow_graph_builder
-                        .add_phi(post_prior_clause, prior_branch);
-                }
-
-                // Onward, with current flow node set to our final Phi node.
-                self.set_current_flow_node(post_prior_clause);
-            }
-            _ => {
-                ast::visitor::source_order::walk_stmt(self, stmt);
-            }
-        }
-    }
-}
-
-#[derive(Debug, Default)]
-pub struct SemanticIndexStorage(KeyValueCache<FileId, Arc<SemanticIndex>>);
-
-impl Deref for SemanticIndexStorage {
-    type Target = KeyValueCache<FileId, Arc<SemanticIndex>>;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl DerefMut for SemanticIndexStorage {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use crate::semantic::symbol_table::{Symbol, SymbolIterator};
-    use ruff_python_ast as ast;
-    use ruff_python_ast::ModModule;
-    use ruff_python_parser::{Mode, Parsed};
-
-    use super::{Definition, ScopeKind, SemanticIndex, SymbolId};
-
-    fn parse(code: &str) -> Parsed<ModModule> {
-        ruff_python_parser::parse_unchecked(code, Mode::Module)
-            .try_into_module()
-            .unwrap()
-    }
-
-    fn names<I>(it: SymbolIterator<I>) -> Vec<&str>
-    where
-        I: Iterator<Item = SymbolId>,
-    {
-        let mut symbols: Vec<_> = it.map(Symbol::name).collect();
-        symbols.sort_unstable();
-        symbols
-    }
-
-    #[test]
-    fn empty() {
-        let parsed = parse("");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()).len(), 0);
-    }
-
-    #[test]
-    fn simple() {
-        let parsed = parse("x");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["x"]);
-        assert_eq!(
-            table
-                .definitions(table.root_symbol_id_by_name("x").unwrap())
-                .len(),
-            0
-        );
-    }
-
-    #[test]
-    fn annotation_only() {
-        let parsed = parse("x: int");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["int", "x"]);
-        // TODO record definition
-    }
-
-    #[test]
-    fn import() {
-        let parsed = parse("import foo");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["foo"]);
-        assert_eq!(
-            table
-                .definitions(table.root_symbol_id_by_name("foo").unwrap())
-                .len(),
-            1
-        );
-    }
-
-    #[test]
-    fn import_sub() {
-        let parsed = parse("import foo.bar");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["foo"]);
-    }
-
-    #[test]
-    fn import_as() {
-        let parsed = parse("import foo.bar as baz");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["baz"]);
-    }
-
-    #[test]
-    fn import_from() {
-        let parsed = parse("from bar import foo");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["foo"]);
-        assert_eq!(
-            table
-                .definitions(table.root_symbol_id_by_name("foo").unwrap())
-                .len(),
-            1
-        );
-        assert!(
-            table.root_symbol_id_by_name("foo").is_some_and(|sid| {
-                let s = sid.symbol(&table);
-                s.is_defined() || !s.is_used()
-            }),
-            "symbols that are defined get the defined flag"
-        );
-    }
-
-    #[test]
-    fn assign() {
-        let parsed = parse("x = foo");
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["foo", "x"]);
-        assert_eq!(
-            table
-                .definitions(table.root_symbol_id_by_name("x").unwrap())
-                .len(),
-            1
-        );
-        assert!(
-            table.root_symbol_id_by_name("foo").is_some_and(|sid| {
-                let s = sid.symbol(&table);
-                !s.is_defined() && s.is_used()
-            }),
-            "a symbol used but not defined in a scope should have only the used flag"
-        );
-    }
-
-    #[test]
-    fn class_scope() {
-        let parsed = parse(
-            "
-                class C:
-                    x = 1
-                y = 2
-                ",
-        );
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["C", "y"]);
-        let scopes = table.root_child_scope_ids();
-        assert_eq!(scopes.len(), 1);
-        let c_scope = scopes[0].scope(&table);
-        assert_eq!(c_scope.kind(), ScopeKind::Class);
-        assert_eq!(c_scope.name(), "C");
-        assert_eq!(names(table.symbols_for_scope(scopes[0])), vec!["x"]);
-        assert_eq!(
-            table
-                .definitions(table.root_symbol_id_by_name("C").unwrap())
-                .len(),
-            1
-        );
-    }
-
-    #[test]
-    fn func_scope() {
-        let parsed = parse(
-            "
-                def func():
-                    x = 1
-                y = 2
-                ",
-        );
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["func", "y"]);
-        let scopes = table.root_child_scope_ids();
-        assert_eq!(scopes.len(), 1);
-        let func_scope = scopes[0].scope(&table);
-        assert_eq!(func_scope.kind(), ScopeKind::Function);
-        assert_eq!(func_scope.name(), "func");
-        assert_eq!(names(table.symbols_for_scope(scopes[0])), vec!["x"]);
-        assert_eq!(
-            table
-                .definitions(table.root_symbol_id_by_name("func").unwrap())
-                .len(),
-            1
-        );
-    }
-
-    #[test]
-    fn dupes() {
-        let parsed = parse(
-            "
-                def func():
-                    x = 1
-                def func():
-                    y = 2
-                ",
-        );
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["func"]);
-        let scopes = table.root_child_scope_ids();
-        assert_eq!(scopes.len(), 2);
-        let func_scope_1 = scopes[0].scope(&table);
-        let func_scope_2 = scopes[1].scope(&table);
-        assert_eq!(func_scope_1.kind(), ScopeKind::Function);
-        assert_eq!(func_scope_1.name(), "func");
-        assert_eq!(func_scope_2.kind(), ScopeKind::Function);
-        assert_eq!(func_scope_2.name(), "func");
-        assert_eq!(names(table.symbols_for_scope(scopes[0])), vec!["x"]);
-        assert_eq!(names(table.symbols_for_scope(scopes[1])), vec!["y"]);
-        assert_eq!(
-            table
-                .definitions(table.root_symbol_id_by_name("func").unwrap())
-                .len(),
-            2
-        );
-    }
-
-    #[test]
-    fn generic_func() {
-        let parsed = parse(
-            "
-                def func[T]():
-                    x = 1
-                ",
-        );
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["func"]);
-        let scopes = table.root_child_scope_ids();
-        assert_eq!(scopes.len(), 1);
-        let ann_scope_id = scopes[0];
-        let ann_scope = ann_scope_id.scope(&table);
-        assert_eq!(ann_scope.kind(), ScopeKind::Annotation);
-        assert_eq!(ann_scope.name(), "func");
-        assert_eq!(names(table.symbols_for_scope(ann_scope_id)), vec!["T"]);
-        let scopes = table.child_scope_ids_of(ann_scope_id);
-        assert_eq!(scopes.len(), 1);
-        let func_scope_id = scopes[0];
-        let func_scope = func_scope_id.scope(&table);
-        assert_eq!(func_scope.kind(), ScopeKind::Function);
-        assert_eq!(func_scope.name(), "func");
-        assert_eq!(names(table.symbols_for_scope(func_scope_id)), vec!["x"]);
-    }
-
-    #[test]
-    fn generic_class() {
-        let parsed = parse(
-            "
-                class C[T]:
-                    x = 1
-                ",
-        );
-        let table = SemanticIndex::from_ast(parsed.syntax()).symbol_table;
-        assert_eq!(names(table.root_symbols()), vec!["C"]);
-        let scopes = table.root_child_scope_ids();
-        assert_eq!(scopes.len(), 1);
-        let ann_scope_id = scopes[0];
-        let ann_scope = ann_scope_id.scope(&table);
-        assert_eq!(ann_scope.kind(), ScopeKind::Annotation);
-        assert_eq!(ann_scope.name(), "C");
-        assert_eq!(names(table.symbols_for_scope(ann_scope_id)), vec!["T"]);
-        assert!(
-            table
-                .symbol_by_name(ann_scope_id, "T")
-                .is_some_and(|s| s.is_defined() && !s.is_used()),
-            "type parameters are defined by the scope that introduces them"
-        );
-        let scopes = table.child_scope_ids_of(ann_scope_id);
-        assert_eq!(scopes.len(), 1);
-        let func_scope_id = scopes[0];
-        let func_scope = func_scope_id.scope(&table);
-        assert_eq!(func_scope.kind(), ScopeKind::Class);
-        assert_eq!(func_scope.name(), "C");
-        assert_eq!(names(table.symbols_for_scope(func_scope_id)), vec!["x"]);
-    }
-
-    #[test]
-    fn reachability_trivial() {
-        let parsed = parse("x = 1; x");
-        let ast = parsed.syntax();
-        let index = SemanticIndex::from_ast(ast);
-        let table = &index.symbol_table;
-        let x_sym = table
-            .root_symbol_id_by_name("x")
-            .expect("x symbol should exist");
-        let ast::Stmt::Expr(ast::StmtExpr { value: x_use, .. }) = &ast.body[1] else {
-            panic!("should be an expr")
-        };
-        let x_defs: Vec<_> = index
-            .reachable_definitions(x_sym, x_use)
-            .map(|constrained_definition| constrained_definition.definition)
-            .collect();
-        assert_eq!(x_defs.len(), 1);
-        let Definition::Assignment(node_key) = &x_defs[0] else {
-            panic!("def should be an assignment")
-        };
-        let Some(def_node) = node_key.resolve(ast.into()) else {
-            panic!("node key should resolve")
-        };
-        let ast::Expr::NumberLiteral(ast::ExprNumberLiteral {
-            value: ast::Number::Int(num),
-            ..
-        }) = &*def_node.value
-        else {
-            panic!("should be a number literal")
-        };
-        assert_eq!(*num, 1);
-    }
-
-    #[test]
-    fn expression_scope() {
-        let parsed = parse("x = 1;\ndef test():\n  y = 4");
-        let ast = parsed.syntax();
-        let index = SemanticIndex::from_ast(ast);
-        let table = &index.symbol_table;
-
-        let x_sym = table
-            .root_symbol_by_name("x")
-            .expect("x symbol should exist");
-
-        let x_stmt = ast.body[0].as_assign_stmt().unwrap();
-
-        let x_id = index.expression_id(&x_stmt.targets[0]);
-
-        assert_eq!(table.scope_of_expression(x_id).kind(), ScopeKind::Module);
-        assert_eq!(table.scope_id_of_expression(x_id), x_sym.scope_id());
-
-        let def = ast.body[1].as_function_def_stmt().unwrap();
-        let y_stmt = def.body[0].as_assign_stmt().unwrap();
-        let y_id = index.expression_id(&y_stmt.targets[0]);
-
-        assert_eq!(table.scope_of_expression(y_id).kind(), ScopeKind::Function);
-    }
-}

crates/red_knot/src/semantic/definitions.rs

@@ -1,52 +0,0 @@
-use crate::ast_ids::TypedNodeKey;
-use crate::semantic::ModuleName;
-use crate::Name;
-use ruff_python_ast as ast;
-
-// TODO storing TypedNodeKey for definitions means we have to search to find them again in the AST;
-// this is at best O(log n). If looking up definitions is a bottleneck we should look for
-// alternatives here.
-// TODO intern Definitions in SymbolTable and reference using IDs?
-#[derive(Clone, Debug)]
-pub enum Definition {
-    // For the import cases, we don't need reference to any arbitrary AST subtrees (annotations,
-    // RHS), and referencing just the import statement node is imprecise (a single import statement
-    // can assign many symbols, we'd have to re-search for the one we care about), so we just copy
-    // the small amount of information we need from the AST.
-    Import(ImportDefinition),
-    ImportFrom(ImportFromDefinition),
-    ClassDef(TypedNodeKey<ast::StmtClassDef>),
-    FunctionDef(TypedNodeKey<ast::StmtFunctionDef>),
-    Assignment(TypedNodeKey<ast::StmtAssign>),
-    AnnotatedAssignment(TypedNodeKey<ast::StmtAnnAssign>),
-    NamedExpr(TypedNodeKey<ast::ExprNamed>),
-    /// represents the implicit initial definition of every name as "unbound"
-    Unbound,
-    // TODO with statements, except handlers, function args...
-}
-
-#[derive(Clone, Debug)]
-pub struct ImportDefinition {
-    pub module: ModuleName,
-}
-
-#[derive(Clone, Debug)]
-pub struct ImportFromDefinition {
-    pub module: Option<ModuleName>,
-    pub name: Name,
-    pub level: u32,
-}
-
-impl ImportFromDefinition {
-    pub fn module(&self) -> Option<&ModuleName> {
-        self.module.as_ref()
-    }
-
-    pub fn name(&self) -> &Name {
-        &self.name
-    }
-
-    pub fn level(&self) -> u32 {
-        self.level
-    }
-}

crates/red_knot/src/semantic/flow_graph.rs

@@ -1,270 +0,0 @@
-use super::symbol_table::SymbolId;
-use crate::semantic::{Definition, ExpressionId};
-use ruff_index::{newtype_index, IndexVec};
-use std::iter::FusedIterator;
-use std::ops::Range;
-
-#[newtype_index]
-pub struct FlowNodeId;
-
-#[derive(Debug)]
-pub(crate) enum FlowNode {
-    Start,
-    Definition(DefinitionFlowNode),
-    Branch(BranchFlowNode),
-    Phi(PhiFlowNode),
-    Constraint(ConstraintFlowNode),
-}
-
-/// A point in control flow where a symbol is defined
-#[derive(Debug)]
-pub(crate) struct DefinitionFlowNode {
-    symbol_id: SymbolId,
-    definition: Definition,
-    predecessor: FlowNodeId,
-}
-
-/// A branch in control flow
-#[derive(Debug)]
-pub(crate) struct BranchFlowNode {
-    predecessor: FlowNodeId,
-}
-
-/// A join point where control flow paths come together
-#[derive(Debug)]
-pub(crate) struct PhiFlowNode {
-    first_predecessor: FlowNodeId,
-    second_predecessor: FlowNodeId,
-}
-
-/// A branch test which may apply constraints to a symbol's type
-#[derive(Debug)]
-pub(crate) struct ConstraintFlowNode {
-    predecessor: FlowNodeId,
-    test_expression: ExpressionId,
-}
-
-#[derive(Debug)]
-pub struct FlowGraph {
-    flow_nodes_by_id: IndexVec<FlowNodeId, FlowNode>,
-    expression_map: IndexVec<ExpressionId, FlowNodeId>,
-}
-
-impl FlowGraph {
-    pub fn start() -> FlowNodeId {
-        FlowNodeId::from_usize(0)
-    }
-
-    pub fn for_expr(&self, expr: ExpressionId) -> FlowNodeId {
-        self.expression_map[expr]
-    }
-}
-
-#[derive(Debug)]
-pub(crate) struct FlowGraphBuilder {
-    flow_graph: FlowGraph,
-}
-
-impl FlowGraphBuilder {
-    pub(crate) fn new() -> Self {
-        let mut graph = FlowGraph {
-            flow_nodes_by_id: IndexVec::default(),
-            expression_map: IndexVec::default(),
-        };
-        graph.flow_nodes_by_id.push(FlowNode::Start);
-        Self { flow_graph: graph }
-    }
-
-    pub(crate) fn add(&mut self, node: FlowNode) -> FlowNodeId {
-        self.flow_graph.flow_nodes_by_id.push(node)
-    }
-
-    pub(crate) fn add_definition(
-        &mut self,
-        symbol_id: SymbolId,
-        definition: Definition,
-        predecessor: FlowNodeId,
-    ) -> FlowNodeId {
-        self.add(FlowNode::Definition(DefinitionFlowNode {
-            symbol_id,
-            definition,
-            predecessor,
-        }))
-    }
-
-    pub(crate) fn add_branch(&mut self, predecessor: FlowNodeId) -> FlowNodeId {
-        self.add(FlowNode::Branch(BranchFlowNode { predecessor }))
-    }
-
-    pub(crate) fn add_phi(
-        &mut self,
-        first_predecessor: FlowNodeId,
-        second_predecessor: FlowNodeId,
-    ) -> FlowNodeId {
-        self.add(FlowNode::Phi(PhiFlowNode {
-            first_predecessor,
-            second_predecessor,
-        }))
-    }
-
-    pub(crate) fn add_constraint(
-        &mut self,
-        predecessor: FlowNodeId,
-        test_expression: ExpressionId,
-    ) -> FlowNodeId {
-        self.add(FlowNode::Constraint(ConstraintFlowNode {
-            predecessor,
-            test_expression,
-        }))
-    }
-
-    pub(super) fn record_expr(&mut self, node_id: FlowNodeId) -> ExpressionId {
-        self.flow_graph.expression_map.push(node_id)
-    }
-
-    pub(super) fn finish(mut self) -> FlowGraph {
-        self.flow_graph.flow_nodes_by_id.shrink_to_fit();
-        self.flow_graph.expression_map.shrink_to_fit();
-        self.flow_graph
-    }
-}
-
-/// A definition, and the set of constraints between a use and the definition
-#[derive(Debug, Clone)]
-pub struct ConstrainedDefinition {
-    pub definition: Definition,
-    pub constraints: Vec<ExpressionId>,
-}
-
-/// A flow node and the constraints we passed through to reach it
-#[derive(Debug)]
-struct FlowState {
-    node_id: FlowNodeId,
-    constraints_range: Range<usize>,
-}
-
-#[derive(Debug)]
-pub struct ReachableDefinitionsIterator<'a> {
-    flow_graph: &'a FlowGraph,
-    symbol_id: SymbolId,
-    pending: Vec<FlowState>,
-    constraints: Vec<ExpressionId>,
-}
-
-impl<'a> ReachableDefinitionsIterator<'a> {
-    pub fn new(flow_graph: &'a FlowGraph, symbol_id: SymbolId, start_node_id: FlowNodeId) -> Self {
-        Self {
-            flow_graph,
-            symbol_id,
-            pending: vec![FlowState {
-                node_id: start_node_id,
-                constraints_range: 0..0,
-            }],
-            constraints: vec![],
-        }
-    }
-}
-
-impl<'a> Iterator for ReachableDefinitionsIterator<'a> {
-    type Item = ConstrainedDefinition;
-
-    fn next(&mut self) -> Option<Self::Item> {
-        let FlowState {
-            mut node_id,
-            mut constraints_range,
-        } = self.pending.pop()?;
-        self.constraints.truncate(constraints_range.end + 1);
-        loop {
-            match &self.flow_graph.flow_nodes_by_id[node_id] {
-                FlowNode::Start => {
-                    // constraints on unbound are irrelevant
-                    return Some(ConstrainedDefinition {
-                        definition: Definition::Unbound,
-                        constraints: vec![],
-                    });
-                }
-                FlowNode::Definition(def_node) => {
-                    if def_node.symbol_id == self.symbol_id {
-                        return Some(ConstrainedDefinition {
-                            definition: def_node.definition.clone(),
-                            constraints: self.constraints[constraints_range].to_vec(),
-                        });
-                    }
-                    node_id = def_node.predecessor;
-                }
-                FlowNode::Branch(branch_node) => {
-                    node_id = branch_node.predecessor;
-                }
-                FlowNode::Phi(phi_node) => {
-                    self.pending.push(FlowState {
-                        node_id: phi_node.first_predecessor,
-                        constraints_range: constraints_range.clone(),
-                    });
-                    node_id = phi_node.second_predecessor;
-                }
-                FlowNode::Constraint(constraint_node) => {
-                    node_id = constraint_node.predecessor;
-                    self.constraints.push(constraint_node.test_expression);
-                    constraints_range.end += 1;
-                }
-            }
-        }
-    }
-}
-
-impl<'a> FusedIterator for ReachableDefinitionsIterator<'a> {}
-
-impl std::fmt::Display for FlowGraph {
-    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
-        writeln!(f, "flowchart TD")?;
-        for (id, node) in self.flow_nodes_by_id.iter_enumerated() {
-            write!(f, "  id{}", id.as_u32())?;
-            match node {
-                FlowNode::Start => writeln!(f, r"[\Start/]")?,
-                FlowNode::Definition(def_node) => {
-                    writeln!(f, r"(Define symbol {})", def_node.symbol_id.as_u32())?;
-                    writeln!(
-                        f,
-                        r"  id{}-->id{}",
-                        def_node.predecessor.as_u32(),
-                        id.as_u32()
-                    )?;
-                }
-                FlowNode::Branch(branch_node) => {
-                    writeln!(f, r"{{Branch}}")?;
-                    writeln!(
-                        f,
-                        r"  id{}-->id{}",
-                        branch_node.predecessor.as_u32(),
-                        id.as_u32()
-                    )?;
-                }
-                FlowNode::Phi(phi_node) => {
-                    writeln!(f, r"((Phi))")?;
-                    writeln!(
-                        f,
-                        r"  id{}-->id{}",
-                        phi_node.second_predecessor.as_u32(),
-                        id.as_u32()
-                    )?;
-                    writeln!(
-                        f,
-                        r"  id{}-->id{}",
-                        phi_node.first_predecessor.as_u32(),
-                        id.as_u32()
-                    )?;
-                }
-                FlowNode::Constraint(constraint_node) => {
-                    writeln!(f, r"((Constraint))")?;
-                    writeln!(
-                        f,
-                        r"  id{}-->id{}",
-                        constraint_node.predecessor.as_u32(),
-                        id.as_u32()
-                    )?;
-                }
-            }
-        }
-        Ok(())
-    }
-}

crates/red_knot/src/semantic/symbol_table.rs

@@ -1,560 +0,0 @@
-#![allow(dead_code)]
-
-use std::hash::{Hash, Hasher};
-use std::iter::{Copied, DoubleEndedIterator, FusedIterator};
-use std::num::NonZeroU32;
-
-use bitflags::bitflags;
-use hashbrown::hash_map::{Keys, RawEntryMut};
-use rustc_hash::{FxHashMap, FxHasher};
-
-use ruff_index::{newtype_index, IndexVec};
-
-use crate::ast_ids::NodeKey;
-use crate::module::ModuleName;
-use crate::semantic::{Definition, ExpressionId};
-use crate::Name;
-
-type Map<K, V> = hashbrown::HashMap<K, V, ()>;
-
-#[newtype_index]
-pub struct ScopeId;
-
-impl ScopeId {
-    pub fn scope(self, table: &SymbolTable) -> &Scope {
-        &table.scopes_by_id[self]
-    }
-}
-
-#[newtype_index]
-pub struct SymbolId;
-
-impl SymbolId {
-    pub fn symbol(self, table: &SymbolTable) -> &Symbol {
-        &table.symbols_by_id[self]
-    }
-}
-
-#[derive(Copy, Clone, Debug, PartialEq)]
-pub enum ScopeKind {
-    Module,
-    Annotation,
-    Class,
-    Function,
-}
-
-#[derive(Debug)]
-pub struct Scope {
-    name: Name,
-    kind: ScopeKind,
-    parent: Option<ScopeId>,
-    children: Vec<ScopeId>,
-    /// the definition (e.g. class or function) that created this scope
-    definition: Option<Definition>,
-    /// the symbol (e.g. class or function) that owns this scope
-    defining_symbol: Option<SymbolId>,
-    /// symbol IDs, hashed by symbol name
-    symbols_by_name: Map<SymbolId, ()>,
-}
-
-impl Scope {
-    pub fn name(&self) -> &str {
-        self.name.as_str()
-    }
-
-    pub fn kind(&self) -> ScopeKind {
-        self.kind
-    }
-
-    pub fn definition(&self) -> Option<Definition> {
-        self.definition.clone()
-    }
-
-    pub fn defining_symbol(&self) -> Option<SymbolId> {
-        self.defining_symbol
-    }
-}
-
-#[derive(Debug)]
-pub(crate) enum Kind {
-    FreeVar,
-    CellVar,
-    CellVarAssigned,
-    ExplicitGlobal,
-    ImplicitGlobal,
-}
-
-bitflags! {
-    #[derive(Copy,Clone,Debug)]
-    pub struct SymbolFlags: u8 {
-        const IS_USED         = 1 << 0;
-        const IS_DEFINED      = 1 << 1;
-        /// TODO: This flag is not yet set by anything
-        const MARKED_GLOBAL   = 1 << 2;
-        /// TODO: This flag is not yet set by anything
-        const MARKED_NONLOCAL = 1 << 3;
-    }
-}
-
-#[derive(Debug)]
-pub struct Symbol {
-    name: Name,
-    flags: SymbolFlags,
-    scope_id: ScopeId,
-    // kind: Kind,
-}
-
-impl Symbol {
-    pub fn name(&self) -> &str {
-        self.name.as_str()
-    }
-
-    pub fn scope_id(&self) -> ScopeId {
-        self.scope_id
-    }
-
-    /// Is the symbol used in its containing scope?
-    pub fn is_used(&self) -> bool {
-        self.flags.contains(SymbolFlags::IS_USED)
-    }
-
-    /// Is the symbol defined in its containing scope?
-    pub fn is_defined(&self) -> bool {
-        self.flags.contains(SymbolFlags::IS_DEFINED)
-    }
-
-    // TODO: implement Symbol.kind 2-pass analysis to categorize as: free-var, cell-var,
-    // explicit-global, implicit-global and implement Symbol.kind by modifying the preorder
-    // traversal code
-}
-
-#[derive(Debug, Clone)]
-pub enum Dependency {
-    Module(ModuleName),
-    Relative {
-        level: NonZeroU32,
-        module: Option<ModuleName>,
-    },
-}
-
-/// Table of all symbols in all scopes for a module.
-#[derive(Debug)]
-pub struct SymbolTable {
-    scopes_by_id: IndexVec<ScopeId, Scope>,
-    symbols_by_id: IndexVec<SymbolId, Symbol>,
-    /// the definitions for each symbol
-    defs: FxHashMap<SymbolId, Vec<Definition>>,
-    /// map of AST node (e.g. class/function def) to sub-scope it creates
-    scopes_by_node: FxHashMap<NodeKey, ScopeId>,
-    /// Maps expressions to their enclosing scope.
-    expression_scopes: IndexVec<ExpressionId, ScopeId>,
-    /// dependencies of this module
-    dependencies: Vec<Dependency>,
-}
-
-impl SymbolTable {
-    pub fn dependencies(&self) -> &[Dependency] {
-        &self.dependencies
-    }
-
-    pub const fn root_scope_id() -> ScopeId {
-        ScopeId::from_usize(0)
-    }
-
-    pub fn root_scope(&self) -> &Scope {
-        &self.scopes_by_id[SymbolTable::root_scope_id()]
-    }
-
-    pub fn symbol_ids_for_scope(&self, scope_id: ScopeId) -> Copied<Keys<SymbolId, ()>> {
-        self.scopes_by_id[scope_id].symbols_by_name.keys().copied()
-    }
-
-    pub fn symbols_for_scope(
-        &self,
-        scope_id: ScopeId,
-    ) -> SymbolIterator<Copied<Keys<SymbolId, ()>>> {
-        SymbolIterator {
-            table: self,
-            ids: self.symbol_ids_for_scope(scope_id),
-        }
-    }
-
-    pub fn root_symbol_ids(&self) -> Copied<Keys<SymbolId, ()>> {
-        self.symbol_ids_for_scope(SymbolTable::root_scope_id())
-    }
-
-    pub fn root_symbols(&self) -> SymbolIterator<Copied<Keys<SymbolId, ()>>> {
-        self.symbols_for_scope(SymbolTable::root_scope_id())
-    }
-
-    pub fn child_scope_ids_of(&self, scope_id: ScopeId) -> &[ScopeId] {
-        &self.scopes_by_id[scope_id].children
-    }
-
-    pub fn child_scopes_of(&self, scope_id: ScopeId) -> ScopeIterator<&[ScopeId]> {
-        ScopeIterator {
-            table: self,
-            ids: self.child_scope_ids_of(scope_id),
-        }
-    }
-
-    pub fn root_child_scope_ids(&self) -> &[ScopeId] {
-        self.child_scope_ids_of(SymbolTable::root_scope_id())
-    }
-
-    pub fn root_child_scopes(&self) -> ScopeIterator<&[ScopeId]> {
-        self.child_scopes_of(SymbolTable::root_scope_id())
-    }
-
-    pub fn symbol_id_by_name(&self, scope_id: ScopeId, name: &str) -> Option<SymbolId> {
-        let scope = &self.scopes_by_id[scope_id];
-        let hash = SymbolTable::hash_name(name);
-        let name = Name::new(name);
-        Some(
-            *scope
-                .symbols_by_name
-                .raw_entry()
-                .from_hash(hash, |symid| self.symbols_by_id[*symid].name == name)?
-                .0,
-        )
-    }
-
-    pub fn symbol_by_name(&self, scope_id: ScopeId, name: &str) -> Option<&Symbol> {
-        Some(&self.symbols_by_id[self.symbol_id_by_name(scope_id, name)?])
-    }
-
-    pub fn root_symbol_id_by_name(&self, name: &str) -> Option<SymbolId> {
-        self.symbol_id_by_name(SymbolTable::root_scope_id(), name)
-    }
-
-    pub fn root_symbol_by_name(&self, name: &str) -> Option<&Symbol> {
-        self.symbol_by_name(SymbolTable::root_scope_id(), name)
-    }
-
-    pub fn scope_id_of_symbol(&self, symbol_id: SymbolId) -> ScopeId {
-        self.symbols_by_id[symbol_id].scope_id
-    }
-
-    pub fn scope_of_symbol(&self, symbol_id: SymbolId) -> &Scope {
-        &self.scopes_by_id[self.scope_id_of_symbol(symbol_id)]
-    }
-
-    pub fn scope_id_of_expression(&self, expression: ExpressionId) -> ScopeId {
-        self.expression_scopes[expression]
-    }
-
-    pub fn scope_of_expression(&self, expr_id: ExpressionId) -> &Scope {
-        &self.scopes_by_id[self.scope_id_of_expression(expr_id)]
-    }
-
-    pub fn parent_scopes(
-        &self,
-        scope_id: ScopeId,
-    ) -> ScopeIterator<impl Iterator<Item = ScopeId> + '_> {
-        ScopeIterator {
-            table: self,
-            ids: std::iter::successors(Some(scope_id), |scope| self.scopes_by_id[*scope].parent),
-        }
-    }
-
-    pub fn parent_scope(&self, scope_id: ScopeId) -> Option<ScopeId> {
-        self.scopes_by_id[scope_id].parent
-    }
-
-    pub fn scope_id_for_node(&self, node_key: &NodeKey) -> ScopeId {
-        self.scopes_by_node[node_key]
-    }
-
-    pub fn definitions(&self, symbol_id: SymbolId) -> &[Definition] {
-        self.defs
-            .get(&symbol_id)
-            .map(std::vec::Vec::as_slice)
-            .unwrap_or_default()
-    }
-
-    pub fn all_definitions(&self) -> impl Iterator<Item = (SymbolId, &Definition)> + '_ {
-        self.defs
-            .iter()
-            .flat_map(|(sym_id, defs)| defs.iter().map(move |def| (*sym_id, def)))
-    }
-
-    fn hash_name(name: &str) -> u64 {
-        let mut hasher = FxHasher::default();
-        name.hash(&mut hasher);
-        hasher.finish()
-    }
-}
-
-pub struct SymbolIterator<'a, I> {
-    table: &'a SymbolTable,
-    ids: I,
-}
-
-impl<'a, I> Iterator for SymbolIterator<'a, I>
-where
-    I: Iterator<Item = SymbolId>,
-{
-    type Item = &'a Symbol;
-
-    fn next(&mut self) -> Option<Self::Item> {
-        let id = self.ids.next()?;
-        Some(&self.table.symbols_by_id[id])
-    }
-
-    fn size_hint(&self) -> (usize, Option<usize>) {
-        self.ids.size_hint()
-    }
-}
-
-impl<'a, I> FusedIterator for SymbolIterator<'a, I> where
-    I: Iterator<Item = SymbolId> + FusedIterator
-{
-}
-
-impl<'a, I> DoubleEndedIterator for SymbolIterator<'a, I>
-where
-    I: Iterator<Item = SymbolId> + DoubleEndedIterator,
-{
-    fn next_back(&mut self) -> Option<Self::Item> {
-        let id = self.ids.next_back()?;
-        Some(&self.table.symbols_by_id[id])
-    }
-}
-
-// TODO maybe get rid of this and just do all data access via methods on ScopeId?
-pub struct ScopeIterator<'a, I> {
-    table: &'a SymbolTable,
-    ids: I,
-}
-
-/// iterate (`ScopeId`, `Scope`) pairs for given `ScopeId` iterator
-impl<'a, I> Iterator for ScopeIterator<'a, I>
-where
-    I: Iterator<Item = ScopeId>,
-{
-    type Item = (ScopeId, &'a Scope);
-
-    fn next(&mut self) -> Option<Self::Item> {
-        let id = self.ids.next()?;
-        Some((id, &self.table.scopes_by_id[id]))
-    }
-
-    fn size_hint(&self) -> (usize, Option<usize>) {
-        self.ids.size_hint()
-    }
-}
-
-impl<'a, I> FusedIterator for ScopeIterator<'a, I> where I: Iterator<Item = ScopeId> + FusedIterator {}
-
-impl<'a, I> DoubleEndedIterator for ScopeIterator<'a, I>
-where
-    I: Iterator<Item = ScopeId> + DoubleEndedIterator,
-{
-    fn next_back(&mut self) -> Option<Self::Item> {
-        let id = self.ids.next_back()?;
-        Some((id, &self.table.scopes_by_id[id]))
-    }
-}
-
-#[derive(Debug)]
-pub(super) struct SymbolTableBuilder {
-    symbol_table: SymbolTable,
-}
-
-impl SymbolTableBuilder {
-    pub(super) fn new() -> Self {
-        let mut table = SymbolTable {
-            scopes_by_id: IndexVec::new(),
-            symbols_by_id: IndexVec::new(),
-            defs: FxHashMap::default(),
-            scopes_by_node: FxHashMap::default(),
-            expression_scopes: IndexVec::new(),
-            dependencies: Vec::new(),
-        };
-        table.scopes_by_id.push(Scope {
-            name: Name::new("<module>"),
-            kind: ScopeKind::Module,
-            parent: None,
-            children: Vec::new(),
-            definition: None,
-            defining_symbol: None,
-            symbols_by_name: Map::default(),
-        });
-        Self {
-            symbol_table: table,
-        }
-    }
-
-    pub(super) fn finish(self) -> SymbolTable {
-        let mut symbol_table = self.symbol_table;
-        symbol_table.scopes_by_id.shrink_to_fit();
-        symbol_table.symbols_by_id.shrink_to_fit();
-        symbol_table.defs.shrink_to_fit();
-        symbol_table.scopes_by_node.shrink_to_fit();
-        symbol_table.expression_scopes.shrink_to_fit();
-        symbol_table.dependencies.shrink_to_fit();
-        symbol_table
-    }
-
-    pub(super) fn add_or_update_symbol(
-        &mut self,
-        scope_id: ScopeId,
-        name: &str,
-        flags: SymbolFlags,
-    ) -> SymbolId {
-        let hash = SymbolTable::hash_name(name);
-        let scope = &mut self.symbol_table.scopes_by_id[scope_id];
-        let name = Name::new(name);
-
-        let entry = scope
-            .symbols_by_name
-            .raw_entry_mut()
-            .from_hash(hash, |existing| {
-                self.symbol_table.symbols_by_id[*existing].name == name
-            });
-
-        match entry {
-            RawEntryMut::Occupied(entry) => {
-                if let Some(symbol) = self.symbol_table.symbols_by_id.get_mut(*entry.key()) {
-                    symbol.flags.insert(flags);
-                };
-                *entry.key()
-            }
-            RawEntryMut::Vacant(entry) => {
-                let id = self.symbol_table.symbols_by_id.push(Symbol {
-                    name,
-                    flags,
-                    scope_id,
-                });
-                entry.insert_with_hasher(hash, id, (), |symid| {
-                    SymbolTable::hash_name(&self.symbol_table.symbols_by_id[*symid].name)
-                });
-                id
-            }
-        }
-    }
-
-    pub(super) fn add_definition(&mut self, symbol_id: SymbolId, definition: Definition) {
-        self.symbol_table
-            .defs
-            .entry(symbol_id)
-            .or_default()
-            .push(definition);
-    }
-
-    pub(super) fn add_child_scope(
-        &mut self,
-        parent_scope_id: ScopeId,
-        name: &str,
-        kind: ScopeKind,
-        definition: Option<Definition>,
-        defining_symbol: Option<SymbolId>,
-    ) -> ScopeId {
-        let new_scope_id = self.symbol_table.scopes_by_id.push(Scope {
-            name: Name::new(name),
-            kind,
-            parent: Some(parent_scope_id),
-            children: Vec::new(),
-            definition,
-            defining_symbol,
-            symbols_by_name: Map::default(),
-        });
-        let parent_scope = &mut self.symbol_table.scopes_by_id[parent_scope_id];
-        parent_scope.children.push(new_scope_id);
-        new_scope_id
-    }
-
-    pub(super) fn record_scope_for_node(&mut self, node_key: NodeKey, scope_id: ScopeId) {
-        self.symbol_table.scopes_by_node.insert(node_key, scope_id);
-    }
-
-    pub(super) fn add_dependency(&mut self, dependency: Dependency) {
-        self.symbol_table.dependencies.push(dependency);
-    }
-
-    /// Records the scope for the current expression
-    pub(super) fn record_expression(&mut self, scope: ScopeId) -> ExpressionId {
-        self.symbol_table.expression_scopes.push(scope)
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::{ScopeKind, SymbolFlags, SymbolTable, SymbolTableBuilder};
-
-    #[test]
-    fn insert_same_name_symbol_twice() {
-        let mut builder = SymbolTableBuilder::new();
-        let root_scope_id = SymbolTable::root_scope_id();
-        let symbol_id_1 =
-            builder.add_or_update_symbol(root_scope_id, "foo", SymbolFlags::IS_DEFINED);
-        let symbol_id_2 = builder.add_or_update_symbol(root_scope_id, "foo", SymbolFlags::IS_USED);
-        let table = builder.finish();
-
-        assert_eq!(symbol_id_1, symbol_id_2);
-        assert!(symbol_id_1.symbol(&table).is_used(), "flags must merge");
-        assert!(symbol_id_1.symbol(&table).is_defined(), "flags must merge");
-    }
-
-    #[test]
-    fn insert_different_named_symbols() {
-        let mut builder = SymbolTableBuilder::new();
-        let root_scope_id = SymbolTable::root_scope_id();
-        let symbol_id_1 = builder.add_or_update_symbol(root_scope_id, "foo", SymbolFlags::empty());
-        let symbol_id_2 = builder.add_or_update_symbol(root_scope_id, "bar", SymbolFlags::empty());
-
-        assert_ne!(symbol_id_1, symbol_id_2);
-    }
-
-    #[test]
-    fn add_child_scope_with_symbol() {
-        let mut builder = SymbolTableBuilder::new();
-        let root_scope_id = SymbolTable::root_scope_id();
-        let foo_symbol_top =
-            builder.add_or_update_symbol(root_scope_id, "foo", SymbolFlags::empty());
-        let c_scope = builder.add_child_scope(root_scope_id, "C", ScopeKind::Class, None, None);
-        let foo_symbol_inner = builder.add_or_update_symbol(c_scope, "foo", SymbolFlags::empty());
-
-        assert_ne!(foo_symbol_top, foo_symbol_inner);
-    }
-
-    #[test]
-    fn scope_from_id() {
-        let table = SymbolTableBuilder::new().finish();
-        let root_scope_id = SymbolTable::root_scope_id();
-        let scope = root_scope_id.scope(&table);
-
-        assert_eq!(scope.name.as_str(), "<module>");
-        assert_eq!(scope.kind, ScopeKind::Module);
-    }
-
-    #[test]
-    fn symbol_from_id() {
-        let mut builder = SymbolTableBuilder::new();
-        let root_scope_id = SymbolTable::root_scope_id();
-        let foo_symbol_id =
-            builder.add_or_update_symbol(root_scope_id, "foo", SymbolFlags::empty());
-        let table = builder.finish();
-        let symbol = foo_symbol_id.symbol(&table);
-
-        assert_eq!(symbol.name(), "foo");
-    }
-
-    #[test]
-    fn bigger_symbol_table() {
-        let mut builder = SymbolTableBuilder::new();
-        let root_scope_id = SymbolTable::root_scope_id();
-        let foo_symbol_id =
-            builder.add_or_update_symbol(root_scope_id, "foo", SymbolFlags::empty());
-        builder.add_or_update_symbol(root_scope_id, "bar", SymbolFlags::empty());
-        builder.add_or_update_symbol(root_scope_id, "baz", SymbolFlags::empty());
-        builder.add_or_update_symbol(root_scope_id, "qux", SymbolFlags::empty());
-        let table = builder.finish();
-
-        let foo_symbol_id_2 = table
-            .root_symbol_id_by_name("foo")
-            .expect("foo symbol to be found");
-
-        assert_eq!(foo_symbol_id_2, foo_symbol_id);
-    }
-}

crates/red_knot/src/semantic/types/infer.rs

@@ -1,762 +0,0 @@
-#![allow(dead_code)]
-
-use ruff_python_ast as ast;
-use ruff_python_ast::AstNode;
-use std::fmt::Debug;
-
-use crate::db::{QueryResult, SemanticDb, SemanticJar};
-
-use crate::module::{resolve_module, ModuleName};
-use crate::parse::parse;
-use crate::semantic::types::{ModuleTypeId, Type};
-use crate::semantic::{
-    resolve_global_symbol, semantic_index, ConstrainedDefinition, Definition, GlobalSymbolId,
-    ImportDefinition, ImportFromDefinition,
-};
-use crate::{FileId, Name};
-
-// FIXME: Figure out proper dead-lock free synchronisation now that this takes `&db` instead of `&mut db`.
-/// Resolve the public-facing type for a symbol (the type seen by other scopes: other modules, or
-/// nested functions). Because calls to nested functions and imports can occur anywhere in control
-/// flow, this type must be conservative and consider all definitions of the symbol that could
-/// possibly be seen by another scope. Currently we take the most conservative approach, which is
-/// the union of all definitions. We may be able to narrow this in future to eliminate definitions
-/// which can't possibly (or at least likely) be seen by any other scope, so that e.g. we could
-/// infer `Literal["1"]` instead of `Literal[1] | Literal["1"]` for `x` in `x = x; x = str(x);`.
-#[tracing::instrument(level = "trace", skip(db))]
-pub fn infer_symbol_public_type(db: &dyn SemanticDb, symbol: GlobalSymbolId) -> QueryResult<Type> {
-    let index = semantic_index(db, symbol.file_id)?;
-    let defs = index.symbol_table().definitions(symbol.symbol_id).to_vec();
-    let jar: &SemanticJar = db.jar()?;
-
-    if let Some(ty) = jar.type_store.get_cached_symbol_public_type(symbol) {
-        return Ok(ty);
-    }
-
-    let ty = infer_type_from_definitions(db, symbol, defs.iter().cloned())?;
-
-    jar.type_store.cache_symbol_public_type(symbol, ty);
-
-    // TODO record dependencies
-    Ok(ty)
-}
-
-/// Infer type of a symbol as union of the given `Definitions`.
-fn infer_type_from_definitions<T>(
-    db: &dyn SemanticDb,
-    symbol: GlobalSymbolId,
-    definitions: T,
-) -> QueryResult<Type>
-where
-    T: Debug + IntoIterator<Item = Definition>,
-{
-    infer_type_from_constrained_definitions(
-        db,
-        symbol,
-        definitions
-            .into_iter()
-            .map(|definition| ConstrainedDefinition {
-                definition,
-                constraints: vec![],
-            }),
-    )
-}
-
-/// Infer type of a symbol as union of the given `ConstrainedDefinitions`.
-fn infer_type_from_constrained_definitions<T>(
-    db: &dyn SemanticDb,
-    symbol: GlobalSymbolId,
-    constrained_definitions: T,
-) -> QueryResult<Type>
-where
-    T: IntoIterator<Item = ConstrainedDefinition>,
-{
-    let jar: &SemanticJar = db.jar()?;
-    let mut tys = constrained_definitions
-        .into_iter()
-        .map(|def| infer_constrained_definition_type(db, symbol, def.clone()))
-        .peekable();
-    if let Some(first) = tys.next() {
-        if tys.peek().is_some() {
-            Ok(jar.type_store.add_union(
-                symbol.file_id,
-                &Iterator::chain(std::iter::once(first), tys).collect::<QueryResult<Vec<_>>>()?,
-            ))
-        } else {
-            first
-        }
-    } else {
-        Ok(Type::Unknown)
-    }
-}
-
-/// Infer type for a ConstrainedDefinition (intersection of the definition type and the
-/// constraints)
-#[tracing::instrument(level = "trace", skip(db))]
-pub fn infer_constrained_definition_type(
-    db: &dyn SemanticDb,
-    symbol: GlobalSymbolId,
-    constrained_definition: ConstrainedDefinition,
-) -> QueryResult<Type> {
-    let ConstrainedDefinition {
-        definition,
-        constraints,
-    } = constrained_definition;
-    let index = semantic_index(db, symbol.file_id)?;
-    let parsed = parse(db.upcast(), symbol.file_id)?;
-    let mut intersected_types = vec![infer_definition_type(db, symbol, definition)?];
-    for constraint in constraints {
-        if let Some(constraint_type) = infer_constraint_type(
-            db,
-            symbol,
-            index.resolve_expression_id(parsed.syntax(), constraint),
-        )? {
-            intersected_types.push(constraint_type);
-        }
-    }
-    let jar: &SemanticJar = db.jar()?;
-    Ok(jar
-        .type_store
-        .add_intersection(symbol.file_id, &intersected_types, &[]))
-}
-
-/// Infer a type for a Definition
-#[tracing::instrument(level = "trace", skip(db))]
-pub fn infer_definition_type(
-    db: &dyn SemanticDb,
-    symbol: GlobalSymbolId,
-    definition: Definition,
-) -> QueryResult<Type> {
-    let jar: &SemanticJar = db.jar()?;
-    let type_store = &jar.type_store;
-    let file_id = symbol.file_id;
-
-    match definition {
-        Definition::Unbound => Ok(Type::Unbound),
-        Definition::Import(ImportDefinition {
-            module: module_name,
-        }) => {
-            if let Some(module) = resolve_module(db, module_name.clone())? {
-                Ok(Type::Module(ModuleTypeId { module, file_id }))
-            } else {
-                Ok(Type::Unknown)
-            }
-        }
-        Definition::ImportFrom(ImportFromDefinition {
-            module,
-            name,
-            level,
-        }) => {
-            // TODO relative imports
-            assert!(matches!(level, 0));
-            let module_name = ModuleName::new(module.as_ref().expect("TODO relative imports"));
-            let Some(module) = resolve_module(db, module_name.clone())? else {
-                return Ok(Type::Unknown);
-            };
-
-            if let Some(remote_symbol) = resolve_global_symbol(db, module, &name)? {
-                infer_symbol_public_type(db, remote_symbol)
-            } else {
-                Ok(Type::Unknown)
-            }
-        }
-        Definition::ClassDef(node_key) => {
-            if let Some(ty) = type_store.get_cached_node_type(file_id, node_key.erased()) {
-                Ok(ty)
-            } else {
-                let parsed = parse(db.upcast(), file_id)?;
-                let ast = parsed.syntax();
-                let index = semantic_index(db, file_id)?;
-                let node = node_key.resolve_unwrap(ast.as_any_node_ref());
-
-                let mut bases = Vec::with_capacity(node.bases().len());
-
-                for base in node.bases() {
-                    bases.push(infer_expr_type(db, file_id, base)?);
-                }
-                let scope_id = index.symbol_table().scope_id_for_node(node_key.erased());
-                let ty = type_store.add_class(file_id, &node.name.id, scope_id, bases);
-                type_store.cache_node_type(file_id, *node_key.erased(), ty);
-                Ok(ty)
-            }
-        }
-        Definition::FunctionDef(node_key) => {
-            if let Some(ty) = type_store.get_cached_node_type(file_id, node_key.erased()) {
-                Ok(ty)
-            } else {
-                let parsed = parse(db.upcast(), file_id)?;
-                let ast = parsed.syntax();
-                let index = semantic_index(db, file_id)?;
-                let node = node_key
-                    .resolve(ast.as_any_node_ref())
-                    .expect("node key should resolve");
-
-                let decorator_tys = node
-                    .decorator_list
-                    .iter()
-                    .map(|decorator| infer_expr_type(db, file_id, &decorator.expression))
-                    .collect::<QueryResult<_>>()?;
-                let scope_id = index.symbol_table().scope_id_for_node(node_key.erased());
-                let ty = type_store.add_function(
-                    file_id,
-                    &node.name.id,
-                    symbol.symbol_id,
-                    scope_id,
-                    decorator_tys,
-                );
-                type_store.cache_node_type(file_id, *node_key.erased(), ty);
-                Ok(ty)
-            }
-        }
-        Definition::Assignment(node_key) => {
-            let parsed = parse(db.upcast(), file_id)?;
-            let ast = parsed.syntax();
-            let node = node_key.resolve_unwrap(ast.as_any_node_ref());
-            // TODO handle unpacking assignment
-            infer_expr_type(db, file_id, &node.value)
-        }
-        Definition::AnnotatedAssignment(node_key) => {
-            let parsed = parse(db.upcast(), file_id)?;
-            let ast = parsed.syntax();
-            let node = node_key.resolve_unwrap(ast.as_any_node_ref());
-            // TODO actually look at the annotation
-            let Some(value) = &node.value else {
-                return Ok(Type::Unknown);
-            };
-            // TODO handle unpacking assignment
-            infer_expr_type(db, file_id, value)
-        }
-        Definition::NamedExpr(node_key) => {
-            let parsed = parse(db.upcast(), file_id)?;
-            let ast = parsed.syntax();
-            let node = node_key.resolve_unwrap(ast.as_any_node_ref());
-            infer_expr_type(db, file_id, &node.value)
-        }
-    }
-}
-
-/// Return the type that the given constraint (an expression from a control-flow test) requires the
-/// given symbol to have. For example, returns the Type "~None" as the constraint type if given the
-/// symbol ID for x and the expression ID for `x is not None`. Returns (Rust) None if the given
-/// expression applies no constraints on the given symbol.
-#[tracing::instrument(level = "trace", skip(db))]
-fn infer_constraint_type(
-    db: &dyn SemanticDb,
-    symbol_id: GlobalSymbolId,
-    // TODO this should preferably take an &ast::Expr instead of AnyNodeRef
-    expression: ast::AnyNodeRef,
-) -> QueryResult<Option<Type>> {
-    let file_id = symbol_id.file_id;
-    let index = semantic_index(db, file_id)?;
-    let jar: &SemanticJar = db.jar()?;
-    let symbol_name = symbol_id.symbol_id.symbol(&index.symbol_table).name();
-    // TODO narrowing attributes
-    // TODO narrowing dict keys
-    // TODO isinstance, ==/!=, type(...), literals, bools...
-    match expression {
-        ast::AnyNodeRef::ExprCompare(ast::ExprCompare {
-            left,
-            ops,
-            comparators,
-            ..
-        }) => {
-            // TODO chained comparisons
-            match left.as_ref() {
-                ast::Expr::Name(ast::ExprName { id, .. }) if id == symbol_name => match ops[0] {
-                    ast::CmpOp::Is | ast::CmpOp::IsNot => {
-                        Ok(match infer_expr_type(db, file_id, &comparators[0])? {
-                            Type::None => Some(Type::None),
-                            _ => None,
-                        }
-                        .map(|ty| {
-                            if matches!(ops[0], ast::CmpOp::IsNot) {
-                                jar.type_store.add_intersection(file_id, &[], &[ty])
-                            } else {
-                                ty
-                            }
-                        }))
-                    }
-                    _ => Ok(None),
-                },
-                _ => Ok(None),
-            }
-        }
-        _ => Ok(None),
-    }
-}
-
-/// Infer type of the given expression.
-fn infer_expr_type(db: &dyn SemanticDb, file_id: FileId, expr: &ast::Expr) -> QueryResult<Type> {
-    // TODO cache the resolution of the type on the node
-    let index = semantic_index(db, file_id)?;
-    match expr {
-        ast::Expr::NoneLiteral(_) => Ok(Type::None),
-        ast::Expr::NumberLiteral(ast::ExprNumberLiteral { value, .. }) => {
-            match value {
-                ast::Number::Int(n) => {
-                    // TODO support big int literals
-                    Ok(n.as_i64().map(Type::IntLiteral).unwrap_or(Type::Unknown))
-                }
-                // TODO builtins.float or builtins.complex
-                _ => Ok(Type::Unknown),
-            }
-        }
-        ast::Expr::Name(name) => {
-            // TODO look up in the correct scope, don't assume global
-            if let Some(symbol_id) = index.symbol_table().root_symbol_id_by_name(&name.id) {
-                infer_type_from_constrained_definitions(
-                    db,
-                    GlobalSymbolId { file_id, symbol_id },
-                    index.reachable_definitions(symbol_id, expr),
-                )
-            } else {
-                Ok(Type::Unknown)
-            }
-        }
-        ast::Expr::Attribute(ast::ExprAttribute { value, attr, .. }) => {
-            let value_type = infer_expr_type(db, file_id, value)?;
-            let attr_name = &Name::new(&attr.id);
-            value_type
-                .get_member(db, attr_name)
-                .map(|ty| ty.unwrap_or(Type::Unknown))
-        }
-        ast::Expr::BinOp(ast::ExprBinOp {
-            left, op, right, ..
-        }) => {
-            let left_ty = infer_expr_type(db, file_id, left)?;
-            let right_ty = infer_expr_type(db, file_id, right)?;
-            // TODO add reverse bin op support if right <: left
-            left_ty.resolve_bin_op(db, *op, right_ty)
-        }
-        ast::Expr::Named(ast::ExprNamed { value, .. }) => infer_expr_type(db, file_id, value),
-        ast::Expr::If(ast::ExprIf { body, orelse, .. }) => {
-            // TODO detect statically known truthy or falsy test
-            let body_ty = infer_expr_type(db, file_id, body)?;
-            let else_ty = infer_expr_type(db, file_id, orelse)?;
-            let jar: &SemanticJar = db.jar()?;
-            Ok(jar.type_store.add_union(file_id, &[body_ty, else_ty]))
-        }
-        _ => todo!("expression type resolution for {:?}", expr),
-    }
-}
-
-#[cfg(test)]
-mod tests {
-
-    use std::path::PathBuf;
-
-    use crate::db::tests::TestDb;
-    use crate::db::{HasJar, SemanticJar};
-    use crate::module::{
-        resolve_module, set_module_search_paths, ModuleName, ModuleResolutionInputs,
-    };
-    use crate::semantic::{infer_symbol_public_type, resolve_global_symbol, Type};
-    use crate::Name;
-
-    // TODO with virtual filesystem we shouldn't have to write files to disk for these
-    // tests
-
-    struct TestCase {
-        temp_dir: tempfile::TempDir,
-        db: TestDb,
-
-        src: PathBuf,
-    }
-
-    fn create_test() -> std::io::Result<TestCase> {
-        let temp_dir = tempfile::tempdir()?;
-
-        let src = temp_dir.path().join("src");
-        std::fs::create_dir(&src)?;
-        let src = src.canonicalize()?;
-
-        let search_paths = ModuleResolutionInputs {
-            extra_paths: vec![],
-            workspace_root: src.clone(),
-            site_packages: None,
-            custom_typeshed: None,
-        };
-
-        let mut db = TestDb::default();
-        set_module_search_paths(&mut db, search_paths);
-
-        Ok(TestCase { temp_dir, db, src })
-    }
-
-    fn write_to_path(case: &TestCase, relative_path: &str, contents: &str) -> anyhow::Result<()> {
-        let path = case.src.join(relative_path);
-        std::fs::write(path, contents)?;
-        Ok(())
-    }
-
-    fn get_public_type(
-        case: &TestCase,
-        module_name: &str,
-        variable_name: &str,
-    ) -> anyhow::Result<Type> {
-        let db = &case.db;
-        let module = resolve_module(db, ModuleName::new(module_name))?.expect("Module to exist");
-        let symbol = resolve_global_symbol(db, module, variable_name)?.expect("symbol to exist");
-
-        Ok(infer_symbol_public_type(db, symbol)?)
-    }
-
-    fn assert_public_type(
-        case: &TestCase,
-        module_name: &str,
-        variable_name: &str,
-        type_name: &str,
-    ) -> anyhow::Result<()> {
-        let ty = get_public_type(case, module_name, variable_name)?;
-
-        let jar = HasJar::<SemanticJar>::jar(&case.db)?;
-        assert_eq!(format!("{}", ty.display(&jar.type_store)), type_name);
-        Ok(())
-    }
-
-    #[test]
-    fn follow_import_to_class() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(&case, "a.py", "from b import C as D; E = D")?;
-        write_to_path(&case, "b.py", "class C: pass")?;
-
-        assert_public_type(&case, "a", "E", "Literal[C]")
-    }
-
-    #[test]
-    fn resolve_base_class_by_name() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "mod.py",
-            "
-                class Base: pass
-                class Sub(Base): pass
-            ",
-        )?;
-
-        let ty = get_public_type(&case, "mod", "Sub")?;
-
-        let Type::Class(class_id) = ty else {
-            panic!("Sub is not a Class")
-        };
-        let jar = HasJar::<SemanticJar>::jar(&case.db)?;
-        let base_names: Vec<_> = jar
-            .type_store
-            .get_class(class_id)
-            .bases()
-            .iter()
-            .map(|base_ty| format!("{}", base_ty.display(&jar.type_store)))
-            .collect();
-
-        assert_eq!(base_names, vec!["Literal[Base]"]);
-
-        Ok(())
-    }
-
-    #[test]
-    fn resolve_method() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "mod.py",
-            "
-                class C:
-                    def f(self): pass
-            ",
-        )?;
-
-        let ty = get_public_type(&case, "mod", "C")?;
-
-        let Type::Class(class_id) = ty else {
-            panic!("C is not a Class");
-        };
-
-        let member_ty = class_id
-            .get_own_class_member(&case.db, &Name::new("f"))
-            .expect("C.f to resolve");
-
-        let Some(Type::Function(func_id)) = member_ty else {
-            panic!("C.f is not a Function");
-        };
-
-        let jar = HasJar::<SemanticJar>::jar(&case.db)?;
-        let function = jar.type_store.get_function(func_id);
-        assert_eq!(function.name(), "f");
-
-        Ok(())
-    }
-
-    #[test]
-    fn resolve_module_member() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(&case, "a.py", "import b; D = b.C")?;
-        write_to_path(&case, "b.py", "class C: pass")?;
-
-        assert_public_type(&case, "a", "D", "Literal[C]")
-    }
-
-    #[test]
-    fn resolve_literal() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(&case, "a.py", "x = 1")?;
-
-        assert_public_type(&case, "a", "x", "Literal[1]")
-    }
-
-    #[test]
-    fn resolve_union() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                if flag:
-                    x = 1
-                else:
-                    x = 2
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[1, 2]")
-    }
-
-    #[test]
-    fn resolve_visible_def() -> anyhow::Result<()> {
-        let case = create_test()?;
-        write_to_path(&case, "a.py", "y = 1; y = 2; x = y")?;
-        assert_public_type(&case, "a", "x", "Literal[2]")
-    }
-
-    #[test]
-    fn join_paths() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                y = 1
-                y = 2
-                if flag:
-                    y = 3
-                x = y
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[2, 3]")
-    }
-
-    #[test]
-    fn maybe_unbound() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                if flag:
-                    y = 1
-                x = y
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[1] | Unbound")
-    }
-
-    #[test]
-    fn if_elif_else() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                y = 1
-                y = 2
-                if flag:
-                    y = 3
-                elif flag2:
-                    y = 4
-                else:
-                    r = y
-                    y = 5
-                    s = y
-                x = y
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[3, 4, 5]")?;
-        assert_public_type(&case, "a", "r", "Literal[2]")?;
-        assert_public_type(&case, "a", "s", "Literal[5]")
-    }
-
-    #[test]
-    fn if_elif() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                y = 1
-                y = 2
-                if flag:
-                    y = 3
-                elif flag2:
-                    y = 4
-                x = y
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[2, 3, 4]")
-    }
-
-    #[test]
-    fn literal_int_arithmetic() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                a = 2 + 1
-                b = a - 4
-                c = a * b
-                d = c / 3
-                e = 5 % 3
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "a", "Literal[3]")?;
-        assert_public_type(&case, "a", "b", "Literal[-1]")?;
-        assert_public_type(&case, "a", "c", "Literal[-3]")?;
-        assert_public_type(&case, "a", "d", "Literal[-1]")?;
-        assert_public_type(&case, "a", "e", "Literal[2]")
-    }
-
-    #[test]
-    fn walrus() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                x = (y := 1) + 1
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[2]")?;
-        assert_public_type(&case, "a", "y", "Literal[1]")
-    }
-
-    #[test]
-    fn ifexpr() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                x = 1 if flag else 2
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[1, 2]")
-    }
-
-    #[test]
-    fn ifexpr_walrus() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                y = z = 0
-                x = (y := 1) if flag else (z := 2)
-                a = y
-                b = z
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[1, 2]")?;
-        assert_public_type(&case, "a", "a", "Literal[0, 1]")?;
-        assert_public_type(&case, "a", "b", "Literal[0, 2]")
-    }
-
-    #[test]
-    fn ifexpr_walrus_2() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                y = 0
-                (y := 1) if flag else (y := 2)
-                a = y
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "a", "Literal[1, 2]")
-    }
-
-    #[test]
-    fn ifexpr_nested() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                x = 1 if flag else 2 if flag2 else 3
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[1, 2, 3]")
-    }
-
-    #[test]
-    fn none() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                x = 1 if flag else None
-            ",
-        )?;
-
-        assert_public_type(&case, "a", "x", "Literal[1] | None")
-    }
-
-    #[test]
-    fn narrow_none() -> anyhow::Result<()> {
-        let case = create_test()?;
-
-        write_to_path(
-            &case,
-            "a.py",
-            "
-                x = 1 if flag else None
-                y = 0
-                if x is not None:
-                    y = x
-                z = y
-            ",
-        )?;
-
-        // TODO normalization of unions and intersections: this type is technically correct but
-        // begging for normalization
-        assert_public_type(&case, "a", "z", "Literal[0] | Literal[1] | None & ~None")
-    }
-}

crates/red_knot/src/source.rs

@@ -1,105 +0,0 @@
-use std::ops::{Deref, DerefMut};
-use std::sync::Arc;
-
-use ruff_notebook::Notebook;
-use ruff_python_ast::PySourceType;
-
-use crate::cache::KeyValueCache;
-use crate::db::{QueryResult, SourceDb};
-use crate::files::FileId;
-
-#[tracing::instrument(level = "debug", skip(db))]
-pub(crate) fn source_text(db: &dyn SourceDb, file_id: FileId) -> QueryResult<Source> {
-    let jar = db.jar()?;
-    let sources = &jar.sources;
-
-    sources.get(&file_id, |file_id| {
-        let path = db.file_path(*file_id);
-
-        let source_text = std::fs::read_to_string(&path).unwrap_or_else(|err| {
-            tracing::error!("Failed to read file '{path:?}: {err}'. Falling back to empty text");
-            String::new()
-        });
-
-        let python_ty = PySourceType::from(&path);
-
-        let kind = match python_ty {
-            PySourceType::Python => {
-                SourceKind::Python(Arc::from(source_text))
-            }
-            PySourceType::Stub => SourceKind::Stub(Arc::from(source_text)),
-            PySourceType::Ipynb => {
-                let notebook = Notebook::from_source_code(&source_text).unwrap_or_else(|err| {
-                    // TODO should this be changed to never fail?
-                    // or should we instead add a diagnostic somewhere? But what would we return in this case?
-                    tracing::error!(
-                        "Failed to parse notebook '{path:?}: {err}'. Falling back to an empty notebook"
-                    );
-                    Notebook::from_source_code("").unwrap()
-                });
-
-                SourceKind::IpyNotebook(Arc::new(notebook))
-            }
-        };
-
-        Ok(Source { kind })
-    })
-}
-
-#[derive(Debug, Clone, PartialEq)]
-pub enum SourceKind {
-    Python(Arc<str>),
-    Stub(Arc<str>),
-    IpyNotebook(Arc<Notebook>),
-}
-
-impl<'a> From<&'a SourceKind> for PySourceType {
-    fn from(value: &'a SourceKind) -> Self {
-        match value {
-            SourceKind::Python(_) => PySourceType::Python,
-            SourceKind::Stub(_) => PySourceType::Stub,
-            SourceKind::IpyNotebook(_) => PySourceType::Ipynb,
-        }
-    }
-}
-
-#[derive(Debug, Clone, PartialEq)]
-pub struct Source {
-    kind: SourceKind,
-}
-
-impl Source {
-    pub fn python<T: Into<Arc<str>>>(source: T) -> Self {
-        Self {
-            kind: SourceKind::Python(source.into()),
-        }
-    }
-    pub fn kind(&self) -> &SourceKind {
-        &self.kind
-    }
-
-    pub fn text(&self) -> &str {
-        match &self.kind {
-            SourceKind::Python(text) => text,
-            SourceKind::Stub(text) => text,
-            SourceKind::IpyNotebook(notebook) => notebook.source_code(),
-        }
-    }
-}
-
-#[derive(Debug, Default)]
-pub struct SourceStorage(pub(crate) KeyValueCache<FileId, Source>);
-
-impl Deref for SourceStorage {
-    type Target = KeyValueCache<FileId, Source>;
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-impl DerefMut for SourceStorage {
-    fn deref_mut(&mut self) -> &mut Self::Target {
-        &mut self.0
-    }
-}

crates/red_knot/src/watch.rs

@@ -1,77 +0,0 @@
-use std::path::Path;
-
-use anyhow::Context;
-use notify::event::{CreateKind, RemoveKind};
-use notify::{recommended_watcher, Event, EventKind, RecommendedWatcher, RecursiveMode, Watcher};
-
-use crate::program::{FileChangeKind, FileWatcherChange};
-
-pub struct FileWatcher {
-    watcher: RecommendedWatcher,
-}
-
-pub trait EventHandler: Send + 'static {
-    fn handle(&self, changes: Vec<FileWatcherChange>);
-}
-
-impl<F> EventHandler for F
-where
-    F: Fn(Vec<FileWatcherChange>) + Send + 'static,
-{
-    fn handle(&self, changes: Vec<FileWatcherChange>) {
-        let f = self;
-        f(changes);
-    }
-}
-
-impl FileWatcher {
-    pub fn new<E>(handler: E) -> anyhow::Result<Self>
-    where
-        E: EventHandler,
-    {
-        Self::from_handler(Box::new(handler))
-    }
-
-    fn from_handler(handler: Box<dyn EventHandler>) -> anyhow::Result<Self> {
-        let watcher = recommended_watcher(move |changes: notify::Result<Event>| {
-            match changes {
-                Ok(event) => {
-                    // TODO verify that this handles all events correctly
-                    let change_kind = match event.kind {
-                        EventKind::Create(CreateKind::File) => FileChangeKind::Created,
-                        EventKind::Modify(_) => FileChangeKind::Modified,
-                        EventKind::Remove(RemoveKind::File) => FileChangeKind::Deleted,
-                        _ => {
-                            return;
-                        }
-                    };
-
-                    let mut changes = Vec::new();
-
-                    for path in event.paths {
-                        if path.is_file() {
-                            changes.push(FileWatcherChange::new(path, change_kind));
-                        }
-                    }
-
-                    if !changes.is_empty() {
-                        handler.handle(changes);
-                    }
-                }
-                // TODO proper error handling
-                Err(err) => {
-                    panic!("Error: {err}");
-                }
-            }
-        })
-        .context("Failed to create file watcher.")?;
-
-        Ok(Self { watcher })
-    }
-
-    pub fn watch_folder(&mut self, path: &Path) -> anyhow::Result<()> {
-        self.watcher.watch(path, RecursiveMode::Recursive)?;
-
-        Ok(())
-    }
-}

crates/red_knot_module_resolver/Cargo.toml

@@ -1,35 +0,0 @@
-[package]
-name = "red_knot_module_resolver"
-version = "0.0.0"
-publish = false
-authors = { workspace = true }
-edition = { workspace = true }
-rust-version = { workspace = true }
-homepage = { workspace = true }
-documentation = { workspace = true }
-repository = { workspace = true }
-license = { workspace = true }
-
-[dependencies]
-ruff_db = { workspace = true }
-ruff_python_stdlib = { workspace = true }
-
-rustc-hash = { workspace = true }
-salsa = { workspace = true }
-smol_str = { workspace = true }
-tracing = { workspace = true }
-zip = { workspace = true }
-
-[build-dependencies]
-path-slash = { workspace = true }
-walkdir = { workspace = true }
-zip = { workspace = true }
-
-[dev-dependencies]
-anyhow = { workspace = true }
-insta = { workspace = true }
-tempfile = { workspace = true }
-walkdir = { workspace = true }
-
-[lints]
-workspace = true

crates/red_knot_module_resolver/README.md

@@ -1,9 +0,0 @@
-# Red Knot
-
-A work-in-progress multifile module resolver for Ruff.
-
-## Vendored types for the stdlib
-
-This crate vendors [typeshed](https://github.com/python/typeshed)'s stubs for the standard library. The vendored stubs can be found in `crates/red_knot_module_resolver/vendor/typeshed`. The file `crates/red_knot_module_resolver/vendor/typeshed/source_commit.txt` tells you the typeshed commit that our vendored stdlib stubs currently correspond to.
-
-The typeshed stubs are updated every two weeks via an automated PR using the `sync_typeshed.yaml` workflow in the `.github/workflows` directory. This workflow can also be triggered at any time via [workflow dispatch](https://docs.github.com/en/actions/using-workflows/manually-running-a-workflow#running-a-workflow).

crates/red_knot_module_resolver/build.rs

@@ -1,74 +0,0 @@
-//! Build script to package our vendored typeshed files
-//! into a zip archive that can be included in the Ruff binary.
-//!
-//! This script should be automatically run at build time
-//! whenever the script itself changes, or whenever any files
-//! in `crates/red_knot_module_resolver/vendor/typeshed` change.
-
-use std::fs::File;
-use std::path::Path;
-
-use path_slash::PathExt;
-use zip::result::ZipResult;
-use zip::write::{FileOptions, ZipWriter};
-use zip::CompressionMethod;
-
-const TYPESHED_SOURCE_DIR: &str = "vendor/typeshed";
-const TYPESHED_ZIP_LOCATION: &str = "/zipped_typeshed.zip";
-
-/// Recursively zip the contents of an entire directory.
-///
-/// This routine is adapted from a recipe at
-/// <https://github.com/zip-rs/zip-old/blob/5d0f198124946b7be4e5969719a7f29f363118cd/examples/write_dir.rs>
-fn zip_dir(directory_path: &str, writer: File) -> ZipResult<File> {
-    let mut zip = ZipWriter::new(writer);
-
-    let options = FileOptions::default()
-        .compression_method(CompressionMethod::Zstd)
-        .unix_permissions(0o644);
-
-    for entry in walkdir::WalkDir::new(directory_path) {
-        let dir_entry = entry.unwrap();
-        let absolute_path = dir_entry.path();
-        let normalized_relative_path = absolute_path
-            .strip_prefix(Path::new(directory_path))
-            .unwrap()
-            .to_slash()
-            .expect("Unexpected non-utf8 typeshed path!");
-
-        // Write file or directory explicitly
-        // Some unzip tools unzip files with directory paths correctly, some do not!
-        if absolute_path.is_file() {
-            println!("adding file {absolute_path:?} as {normalized_relative_path:?} ...");
-            zip.start_file(normalized_relative_path, options)?;
-            let mut f = File::open(absolute_path)?;
-            std::io::copy(&mut f, &mut zip).unwrap();
-        } else if !normalized_relative_path.is_empty() {
-            // Only if not root! Avoids path spec / warning
-            // and mapname conversion failed error on unzip
-            println!("adding dir {absolute_path:?} as {normalized_relative_path:?} ...");
-            zip.add_directory(normalized_relative_path, options)?;
-        }
-    }
-    zip.finish()
-}
-
-fn main() {
-    println!("cargo:rerun-if-changed={TYPESHED_SOURCE_DIR}");
-    assert!(
-        Path::new(TYPESHED_SOURCE_DIR).is_dir(),
-        "Where is typeshed?"
-    );
-    let out_dir = std::env::var("OUT_DIR").unwrap();
-
-    // N.B. Deliberately using `format!()` instead of `Path::join()` here,
-    // so that we use `/` as a path separator on all platforms.
-    // That enables us to load the typeshed zip at compile time in `module.rs`
-    // (otherwise we'd have to dynamically determine the exact path to the typeshed zip
-    // based on the default path separator for the specific platform we're on,
-    // which can't be done at compile time.)
-    let zipped_typeshed_location = format!("{out_dir}{TYPESHED_ZIP_LOCATION}");
-
-    let zipped_typeshed = File::create(zipped_typeshed_location).unwrap();
-    zip_dir(TYPESHED_SOURCE_DIR, zipped_typeshed).unwrap();
-}

crates/red_knot_module_resolver/src/db.rs

@@ -1,156 +0,0 @@
-use ruff_db::Upcast;
-
-use crate::resolver::{
-    file_to_module,
-    internal::{ModuleNameIngredient, ModuleResolverSearchPaths},
-    resolve_module_query,
-};
-
-#[salsa::jar(db=Db)]
-pub struct Jar(
-    ModuleNameIngredient<'_>,
-    ModuleResolverSearchPaths,
-    resolve_module_query,
-    file_to_module,
-);
-
-pub trait Db: salsa::DbWithJar<Jar> + ruff_db::Db + Upcast<dyn ruff_db::Db> {}
-
-pub(crate) mod tests {
-    use std::sync;
-
-    use salsa::DebugWithDb;
-
-    use ruff_db::file_system::{FileSystem, MemoryFileSystem, OsFileSystem};
-    use ruff_db::vfs::Vfs;
-
-    use super::*;
-
-    #[salsa::db(Jar, ruff_db::Jar)]
-    pub(crate) struct TestDb {
-        storage: salsa::Storage<Self>,
-        file_system: TestFileSystem,
-        events: sync::Arc<sync::Mutex<Vec<salsa::Event>>>,
-        vfs: Vfs,
-    }
-
-    impl TestDb {
-        #[allow(unused)]
-        pub(crate) fn new() -> Self {
-            Self {
-                storage: salsa::Storage::default(),
-                file_system: TestFileSystem::Memory(MemoryFileSystem::default()),
-                events: sync::Arc::default(),
-                vfs: Vfs::with_stubbed_vendored(),
-            }
-        }
-
-        /// Returns the memory file system.
-        ///
-        /// ## Panics
-        /// If this test db isn't using a memory file system.
-        #[allow(unused)]
-        pub(crate) fn memory_file_system(&self) -> &MemoryFileSystem {
-            if let TestFileSystem::Memory(fs) = &self.file_system {
-                fs
-            } else {
-                panic!("The test db is not using a memory file system");
-            }
-        }
-
-        /// Uses the real file system instead of the memory file system.
-        ///
-        /// This useful for testing advanced file system features like permissions, symlinks, etc.
-        ///
-        /// Note that any files written to the memory file system won't be copied over.
-        #[allow(unused)]
-        pub(crate) fn with_os_file_system(&mut self) {
-            self.file_system = TestFileSystem::Os(OsFileSystem);
-        }
-
-        #[allow(unused)]
-        pub(crate) fn vfs_mut(&mut self) -> &mut Vfs {
-            &mut self.vfs
-        }
-
-        /// Takes the salsa events.
-        ///
-        /// ## Panics
-        /// If there are any pending salsa snapshots.
-        #[allow(unused)]
-        pub(crate) fn take_salsa_events(&mut self) -> Vec<salsa::Event> {
-            let inner = sync::Arc::get_mut(&mut self.events).expect("no pending salsa snapshots");
-
-            let events = inner.get_mut().unwrap();
-            std::mem::take(&mut *events)
-        }
-
-        /// Clears the salsa events.
-        ///
-        /// ## Panics
-        /// If there are any pending salsa snapshots.
-        #[allow(unused)]
-        pub(crate) fn clear_salsa_events(&mut self) {
-            self.take_salsa_events();
-        }
-    }
-
-    impl Upcast<dyn ruff_db::Db> for TestDb {
-        fn upcast(&self) -> &(dyn ruff_db::Db + 'static) {
-            self
-        }
-    }
-
-    impl ruff_db::Db for TestDb {
-        fn file_system(&self) -> &dyn ruff_db::file_system::FileSystem {
-            self.file_system.inner()
-        }
-
-        fn vfs(&self) -> &ruff_db::vfs::Vfs {
-            &self.vfs
-        }
-    }
-
-    impl Db for TestDb {}
-
-    impl salsa::Database for TestDb {
-        fn salsa_event(&self, event: salsa::Event) {
-            tracing::trace!("event: {:?}", event.debug(self));
-            let mut events = self.events.lock().unwrap();
-            events.push(event);
-        }
-    }
-
-    impl salsa::ParallelDatabase for TestDb {
-        fn snapshot(&self) -> salsa::Snapshot<Self> {
-            salsa::Snapshot::new(Self {
-                storage: self.storage.snapshot(),
-                file_system: self.file_system.snapshot(),
-                events: self.events.clone(),
-                vfs: self.vfs.snapshot(),
-            })
-        }
-    }
-
-    enum TestFileSystem {
-        Memory(MemoryFileSystem),
-        #[allow(unused)]
-        Os(OsFileSystem),
-    }
-
-    impl TestFileSystem {
-        fn inner(&self) -> &dyn FileSystem {
-            match self {
-                Self::Memory(inner) => inner,
-                Self::Os(inner) => inner,
-            }
-        }
-
-        fn snapshot(&self) -> Self {
-            match self {
-                Self::Memory(inner) => Self::Memory(inner.snapshot()),
-                Self::Os(inner) => Self::Os(inner.snapshot()),
-            }
-        }
-    }
-}

crates/red_knot_module_resolver/src/lib.rs

@@ -1,9 +0,0 @@
-mod db;
-mod module;
-mod resolver;
-mod typeshed;
-
-pub use db::{Db, Jar};
-pub use module::{ModuleKind, ModuleName};
-pub use resolver::{resolve_module, set_module_resolution_settings, ModuleResolutionSettings};
-pub use typeshed::versions::TypeshedVersions;

crates/red_knot_module_resolver/src/module.rs

@@ -1,346 +0,0 @@
-use std::fmt::Formatter;
-use std::ops::Deref;
-use std::sync::Arc;
-
-use ruff_db::file_system::FileSystemPath;
-use ruff_db::vfs::{VfsFile, VfsPath};
-use ruff_python_stdlib::identifiers::is_identifier;
-
-use crate::Db;
-
-/// A module name, e.g. `foo.bar`.
-///
-/// Always normalized to the absolute form (never a relative module name, i.e., never `.foo`).
-#[derive(Clone, Debug, Eq, PartialEq, Hash, PartialOrd, Ord)]
-pub struct ModuleName(smol_str::SmolStr);
-
-impl ModuleName {
-    /// Creates a new module name for `name`. Returns `Some` if `name` is a valid, absolute
-    /// module name and `None` otherwise.
-    ///
-    /// The module name is invalid if:
-    ///
-    /// * The name is empty
-    /// * The name is relative
-    /// * The name ends with a `.`
-    /// * The name contains a sequence of multiple dots
-    /// * A component of a name (the part between two dots) isn't a valid python identifier.
-    #[inline]
-    pub fn new(name: &str) -> Option<Self> {
-        Self::new_from_smol(smol_str::SmolStr::new(name))
-    }
-
-    /// Creates a new module name for `name` where `name` is a static string.
-    /// Returns `Some` if `name` is a valid, absolute module name and `None` otherwise.
-    ///
-    /// The module name is invalid if:
-    ///
-    /// * The name is empty
-    /// * The name is relative
-    /// * The name ends with a `.`
-    /// * The name contains a sequence of multiple dots
-    /// * A component of a name (the part between two dots) isn't a valid python identifier.
-    ///
-    /// ## Examples
-    ///
-    /// ```
-    /// use red_knot_module_resolver::ModuleName;
-    ///
-    /// assert_eq!(ModuleName::new_static("foo.bar").as_deref(), Some("foo.bar"));
-    /// assert_eq!(ModuleName::new_static(""), None);
-    /// assert_eq!(ModuleName::new_static("..foo"), None);
-    /// assert_eq!(ModuleName::new_static(".foo"), None);
-    /// assert_eq!(ModuleName::new_static("foo."), None);
-    /// assert_eq!(ModuleName::new_static("foo..bar"), None);
-    /// assert_eq!(ModuleName::new_static("2000"), None);
-    /// ```
-    #[inline]
-    pub fn new_static(name: &'static str) -> Option<Self> {
-        Self::new_from_smol(smol_str::SmolStr::new_static(name))
-    }
-
-    fn new_from_smol(name: smol_str::SmolStr) -> Option<Self> {
-        if name.is_empty() {
-            return None;
-        }
-
-        if name.split('.').all(is_identifier) {
-            Some(Self(name))
-        } else {
-            None
-        }
-    }
-
-    /// An iterator over the components of the module name:
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// use red_knot_module_resolver::ModuleName;
-    ///
-    /// assert_eq!(ModuleName::new_static("foo.bar.baz").unwrap().components().collect::<Vec<_>>(), vec!["foo", "bar", "baz"]);
-    /// ```
-    pub fn components(&self) -> impl DoubleEndedIterator<Item = &str> {
-        self.0.split('.')
-    }
-
-    /// The name of this module's immediate parent, if it has a parent.
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// use red_knot_module_resolver::ModuleName;
-    ///
-    /// assert_eq!(ModuleName::new_static("foo.bar").unwrap().parent(), Some(ModuleName::new_static("foo").unwrap()));
-    /// assert_eq!(ModuleName::new_static("foo.bar.baz").unwrap().parent(), Some(ModuleName::new_static("foo.bar").unwrap()));
-    /// assert_eq!(ModuleName::new_static("root").unwrap().parent(), None);
-    /// ```
-    pub fn parent(&self) -> Option<ModuleName> {
-        let (parent, _) = self.0.rsplit_once('.')?;
-
-        Some(Self(smol_str::SmolStr::new(parent)))
-    }
-
-    /// Returns `true` if the name starts with `other`.
-    ///
-    /// This is equivalent to checking if `self` is a sub-module of `other`.
-    ///
-    /// # Examples
-    ///
-    /// ```
-    /// use red_knot_module_resolver::ModuleName;
-    ///
-    /// assert!(ModuleName::new_static("foo.bar").unwrap().starts_with(&ModuleName::new_static("foo").unwrap()));
-    ///
-    /// assert!(!ModuleName::new_static("foo.bar").unwrap().starts_with(&ModuleName::new_static("bar").unwrap()));
-    /// assert!(!ModuleName::new_static("foo_bar").unwrap().starts_with(&ModuleName::new_static("foo").unwrap()));
-    /// ```
-    pub fn starts_with(&self, other: &ModuleName) -> bool {
-        let mut self_components = self.components();
-        let other_components = other.components();
-
-        for other_component in other_components {
-            if self_components.next() != Some(other_component) {
-                return false;
-            }
-        }
-
-        true
-    }
-
-    #[inline]
-    pub fn as_str(&self) -> &str {
-        &self.0
-    }
-
-    pub(crate) fn from_relative_path(path: &FileSystemPath) -> Option<Self> {
-        let path = if path.ends_with("__init__.py") || path.ends_with("__init__.pyi") {
-            path.parent()?
-        } else {
-            path
-        };
-
-        let name = if let Some(parent) = path.parent() {
-            let mut name = String::with_capacity(path.as_str().len());
-
-            for component in parent.components() {
-                name.push_str(component.as_os_str().to_str()?);
-                name.push('.');
-            }
-
-            // SAFETY: Unwrap is safe here or `parent` would have returned `None`.
-            name.push_str(path.file_stem().unwrap());
-
-            smol_str::SmolStr::from(name)
-        } else {
-            smol_str::SmolStr::new(path.file_stem()?)
-        };
-
-        Some(Self(name))
-    }
-}
-
-impl Deref for ModuleName {
-    type Target = str;
-
-    #[inline]
-    fn deref(&self) -> &Self::Target {
-        self.as_str()
-    }
-}
-
-impl PartialEq<str> for ModuleName {
-    fn eq(&self, other: &str) -> bool {
-        self.as_str() == other
-    }
-}
-
-impl PartialEq<ModuleName> for str {
-    fn eq(&self, other: &ModuleName) -> bool {
-        self == other.as_str()
-    }
-}
-
-impl std::fmt::Display for ModuleName {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        f.write_str(&self.0)
-    }
-}
-
-/// Representation of a Python module.
-#[derive(Clone, PartialEq, Eq)]
-pub struct Module {
-    inner: Arc<ModuleInner>,
-}
-
-impl Module {
-    pub(crate) fn new(
-        name: ModuleName,
-        kind: ModuleKind,
-        search_path: ModuleSearchPath,
-        file: VfsFile,
-    ) -> Self {
-        Self {
-            inner: Arc::new(ModuleInner {
-                name,
-                kind,
-                search_path,
-                file,
-            }),
-        }
-    }
-
-    /// The absolute name of the module (e.g. `foo.bar`)
-    pub fn name(&self) -> &ModuleName {
-        &self.inner.name
-    }
-
-    /// The file to the source code that defines this module
-    pub fn file(&self) -> VfsFile {
-        self.inner.file
-    }
-
-    /// The search path from which the module was resolved.
-    pub fn search_path(&self) -> &ModuleSearchPath {
-        &self.inner.search_path
-    }
-
-    /// Determine whether this module is a single-file module or a package
-    pub fn kind(&self) -> ModuleKind {
-        self.inner.kind
-    }
-}
-
-impl std::fmt::Debug for Module {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        f.debug_struct("Module")
-            .field("name", &self.name())
-            .field("kind", &self.kind())
-            .field("file", &self.file())
-            .field("search_path", &self.search_path())
-            .finish()
-    }
-}
-
-impl salsa::DebugWithDb<dyn Db> for Module {
-    fn fmt(&self, f: &mut Formatter<'_>, db: &dyn Db) -> std::fmt::Result {
-        f.debug_struct("Module")
-            .field("name", &self.name())
-            .field("kind", &self.kind())
-            .field("file", &self.file().debug(db.upcast()))
-            .field("search_path", &self.search_path())
-            .finish()
-    }
-}
-
-#[derive(PartialEq, Eq)]
-struct ModuleInner {
-    name: ModuleName,
-    kind: ModuleKind,
-    search_path: ModuleSearchPath,
-    file: VfsFile,
-}
-
-#[derive(Copy, Clone, Debug, Eq, PartialEq, Hash)]
-pub enum ModuleKind {
-    /// A single-file module (e.g. `foo.py` or `foo.pyi`)
-    Module,
-
-    /// A python package (`foo/__init__.py` or `foo/__init__.pyi`)
-    Package,
-}
-
-/// A search path in which to search modules.
-/// Corresponds to a path in [`sys.path`](https://docs.python.org/3/library/sys_path_init.html) at runtime.
-///
-/// Cloning a search path is cheap because it's an `Arc`.
-#[derive(Clone, PartialEq, Eq)]
-pub struct ModuleSearchPath {
-    inner: Arc<ModuleSearchPathInner>,
-}
-
-impl ModuleSearchPath {
-    pub fn new<P>(path: P, kind: ModuleSearchPathKind) -> Self
-    where
-        P: Into<VfsPath>,
-    {
-        Self {
-            inner: Arc::new(ModuleSearchPathInner {
-                path: path.into(),
-                kind,
-            }),
-        }
-    }
-
-    /// Determine whether this is a first-party, third-party or standard-library search path
-    pub fn kind(&self) -> ModuleSearchPathKind {
-        self.inner.kind
-    }
-
-    /// Return the location of the search path on the file system
-    pub fn path(&self) -> &VfsPath {
-        &self.inner.path
-    }
-}
-
-impl std::fmt::Debug for ModuleSearchPath {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        f.debug_struct("ModuleSearchPath")
-            .field("path", &self.inner.path)
-            .field("kind", &self.kind())
-            .finish()
-    }
-}
-
-#[derive(Eq, PartialEq)]
-struct ModuleSearchPathInner {
-    path: VfsPath,
-    kind: ModuleSearchPathKind,
-}
-
-/// Enumeration of the different kinds of search paths type checkers are expected to support.
-///
-/// N.B. Although we don't implement `Ord` for this enum, they are ordered in terms of the
-/// priority that we want to give these modules when resolving them.
-/// This is roughly [the order given in the typing spec], but typeshed's stubs
-/// for the standard library are moved higher up to match Python's semantics at runtime.
-///
-/// [the order given in the typing spec]: https://typing.readthedocs.io/en/latest/spec/distributing.html#import-resolution-ordering
-#[derive(Copy, Clone, Debug, Eq, PartialEq, Hash)]
-pub enum ModuleSearchPathKind {
-    /// "Extra" paths provided by the user in a config file, env var or CLI flag.
-    /// E.g. mypy's `MYPYPATH` env var, or pyright's `stubPath` configuration setting
-    Extra,
-
-    /// Files in the project we're directly being invoked on
-    FirstParty,
-
-    /// The `stdlib` directory of typeshed (either vendored or custom)
-    StandardLibrary,
-
-    /// Stubs or runtime modules installed in site-packages
-    SitePackagesThirdParty,
-
-    /// Vendored third-party stubs from typeshed
-    VendoredThirdParty,
-}

crates/red_knot_module_resolver/src/resolver.rs

@@ -1,938 +0,0 @@
-use salsa::DebugWithDb;
-use std::ops::Deref;
-
-use ruff_db::file_system::{FileSystem, FileSystemPath, FileSystemPathBuf};
-use ruff_db::vfs::{system_path_to_file, vfs_path_to_file, VfsFile, VfsPath};
-
-use crate::module::{Module, ModuleKind, ModuleName, ModuleSearchPath, ModuleSearchPathKind};
-use crate::resolver::internal::ModuleResolverSearchPaths;
-use crate::Db;
-
-const TYPESHED_STDLIB_DIRECTORY: &str = "stdlib";
-
-/// Configures the module search paths for the module resolver.
-///
-/// Must be called before calling any other module resolution functions.
-pub fn set_module_resolution_settings(db: &mut dyn Db, config: ModuleResolutionSettings) {
-    // There's no concurrency issue here because we hold a `&mut dyn Db` reference. No other
-    // thread can mutate the `Db` while we're in this call, so using `try_get` to test if
-    // the settings have already been set is safe.
-    if let Some(existing) = ModuleResolverSearchPaths::try_get(db) {
-        existing
-            .set_search_paths(db)
-            .to(config.into_ordered_search_paths());
-    } else {
-        ModuleResolverSearchPaths::new(db, config.into_ordered_search_paths());
-    }
-}
-
-/// Resolves a module name to a module.
-pub fn resolve_module(db: &dyn Db, module_name: ModuleName) -> Option<Module> {
-    let interned_name = internal::ModuleNameIngredient::new(db, module_name);
-
-    resolve_module_query(db, interned_name)
-}
-
-/// Salsa query that resolves an interned [`ModuleNameIngredient`] to a module.
-///
-/// This query should not be called directly. Instead, use [`resolve_module`]. It only exists
-/// because Salsa requires the module name to be an ingredient.
-#[salsa::tracked]
-pub(crate) fn resolve_module_query<'db>(
-    db: &'db dyn Db,
-    module_name: internal::ModuleNameIngredient<'db>,
-) -> Option<Module> {
-    let _ = tracing::trace_span!("resolve_module", module_name = ?module_name.debug(db)).enter();
-
-    let name = module_name.name(db);
-
-    let (search_path, module_file, kind) = resolve_name(db, name)?;
-
-    let module = Module::new(name.clone(), kind, search_path, module_file);
-
-    Some(module)
-}
-
-/// Resolves the module for the given path.
-///
-/// Returns `None` if the path is not a module locatable via `sys.path`.
-#[tracing::instrument(level = "debug", skip(db))]
-pub fn path_to_module(db: &dyn Db, path: &VfsPath) -> Option<Module> {
-    // It's not entirely clear on first sight why this method calls `file_to_module` instead of
-    // it being the other way round, considering that the first thing that `file_to_module` does
-    // is to retrieve the file's path.
-    //
-    // The reason is that `file_to_module` is a tracked Salsa query and salsa queries require that
-    // all arguments are Salsa ingredients (something stored in Salsa). `Path`s aren't salsa ingredients but
-    // `VfsFile` is. So what we do here is to retrieve the `path`'s `VfsFile` so that we can make
-    // use of Salsa's caching and invalidation.
-    let file = vfs_path_to_file(db.upcast(), path)?;
-    file_to_module(db, file)
-}
-
-/// Resolves the module for the file with the given id.
-///
-/// Returns `None` if the file is not a module locatable via `sys.path`.
-#[salsa::tracked]
-#[allow(unused)]
-pub(crate) fn file_to_module(db: &dyn Db, file: VfsFile) -> Option<Module> {
-    let _ = tracing::trace_span!("file_to_module", file = ?file.debug(db.upcast())).enter();
-
-    let path = file.path(db.upcast());
-
-    let search_paths = module_search_paths(db);
-
-    let relative_path = search_paths
-        .iter()
-        .find_map(|root| match (root.path(), path) {
-            (VfsPath::FileSystem(root_path), VfsPath::FileSystem(path)) => {
-                let relative_path = path.strip_prefix(root_path).ok()?;
-                Some(relative_path)
-            }
-            (VfsPath::Vendored(_), VfsPath::Vendored(_)) => {
-                todo!("Add support for vendored modules")
-            }
-            (VfsPath::Vendored(_), VfsPath::FileSystem(_))
-            | (VfsPath::FileSystem(_), VfsPath::Vendored(_)) => None,
-        })?;
-
-    let module_name = ModuleName::from_relative_path(relative_path)?;
-
-    // Resolve the module name to see if Python would resolve the name to the same path.
-    // If it doesn't, then that means that multiple modules have the same name in different
-    // root paths, but that the module corresponding to `path` is in a lower priority search path,
-    // in which case we ignore it.
-    let module = resolve_module(db, module_name)?;
-
-    if file == module.file() {
-        Some(module)
-    } else {
-        // This path is for a module with the same name but with a different precedence. For example:
-        // ```
-        // src/foo.py
-        // src/foo/__init__.py
-        // ```
-        // The module name of `src/foo.py` is `foo`, but the module loaded by Python is `src/foo/__init__.py`.
-        // That means we need to ignore `src/foo.py` even though it resolves to the same module name.
-        None
-    }
-}
-
-/// Configures the search paths that are used to resolve modules.
-#[derive(Eq, PartialEq, Debug)]
-pub struct ModuleResolutionSettings {
-    /// List of user-provided paths that should take first priority in the module resolution.
-    /// Examples in other type checkers are mypy's MYPYPATH environment variable,
-    /// or pyright's stubPath configuration setting.
-    pub extra_paths: Vec<FileSystemPathBuf>,
-
-    /// The root of the workspace, used for finding first-party modules.
-    pub workspace_root: FileSystemPathBuf,
-
-    /// The path to the user's `site-packages` directory, where third-party packages from ``PyPI`` are installed.
-    pub site_packages: Option<FileSystemPathBuf>,
-
-    /// Optional path to standard-library typeshed stubs.
-    /// Currently this has to be a directory that exists on disk.
-    ///
-    /// (TODO: fall back to vendored stubs if no custom directory is provided.)
-    pub custom_typeshed: Option<FileSystemPathBuf>,
-}
-
-impl ModuleResolutionSettings {
-    /// Implementation of PEP 561's module resolution order
-    /// (with some small, deliberate, differences)
-    fn into_ordered_search_paths(self) -> OrderedSearchPaths {
-        let ModuleResolutionSettings {
-            extra_paths,
-            workspace_root,
-            site_packages,
-            custom_typeshed,
-        } = self;
-
-        let mut paths: Vec<_> = extra_paths
-            .into_iter()
-            .map(|path| ModuleSearchPath::new(path, ModuleSearchPathKind::Extra))
-            .collect();
-
-        paths.push(ModuleSearchPath::new(
-            workspace_root,
-            ModuleSearchPathKind::FirstParty,
-        ));
-
-        // TODO fallback to vendored typeshed stubs if no custom typeshed directory is provided by the user
-        if let Some(custom_typeshed) = custom_typeshed {
-            paths.push(ModuleSearchPath::new(
-                custom_typeshed.join(TYPESHED_STDLIB_DIRECTORY),
-                ModuleSearchPathKind::StandardLibrary,
-            ));
-        }
-
-        // TODO vendor typeshed's third-party stubs as well as the stdlib and fallback to them as a final step
-        if let Some(site_packages) = site_packages {
-            paths.push(ModuleSearchPath::new(
-                site_packages,
-                ModuleSearchPathKind::SitePackagesThirdParty,
-            ));
-        }
-
-        OrderedSearchPaths(paths)
-    }
-}
-
-/// A resolved module resolution order, implementing PEP 561
-/// (with some small, deliberate differences)
-#[derive(Clone, Debug, Default, Eq, PartialEq)]
-pub(crate) struct OrderedSearchPaths(Vec<ModuleSearchPath>);
-
-impl Deref for OrderedSearchPaths {
-    type Target = [ModuleSearchPath];
-
-    fn deref(&self) -> &Self::Target {
-        &self.0
-    }
-}
-
-// The singleton methods generated by salsa are all `pub` instead of `pub(crate)` which triggers
-// `unreachable_pub`. Work around this by creating a module and allow `unreachable_pub` for it.
-// Salsa also generates uses to `_db` variables for `interned` which triggers `clippy::used_underscore_binding`. Suppress that too
-// TODO(micha): Contribute a fix for this upstream where the singleton methods have the same visibility as the struct.
-#[allow(unreachable_pub, clippy::used_underscore_binding)]
-pub(crate) mod internal {
-    use crate::module::ModuleName;
-    use crate::resolver::OrderedSearchPaths;
-
-    #[salsa::input(singleton)]
-    pub(crate) struct ModuleResolverSearchPaths {
-        #[return_ref]
-        pub(super) search_paths: OrderedSearchPaths,
-    }
-
-    /// A thin wrapper around `ModuleName` to make it a Salsa ingredient.
-    ///
-    /// This is needed because Salsa requires that all query arguments are salsa ingredients.
-    #[salsa::interned]
-    pub(crate) struct ModuleNameIngredient<'db> {
-        #[return_ref]
-        pub(super) name: ModuleName,
-    }
-}
-
-fn module_search_paths(db: &dyn Db) -> &[ModuleSearchPath] {
-    ModuleResolverSearchPaths::get(db).search_paths(db)
-}
-
-/// Given a module name and a list of search paths in which to lookup modules,
-/// attempt to resolve the module name
-fn resolve_name(db: &dyn Db, name: &ModuleName) -> Option<(ModuleSearchPath, VfsFile, ModuleKind)> {
-    let search_paths = module_search_paths(db);
-
-    for search_path in search_paths {
-        let mut components = name.components();
-        let module_name = components.next_back()?;
-
-        let VfsPath::FileSystem(fs_search_path) = search_path.path() else {
-            todo!("Vendored search paths are not yet supported");
-        };
-
-        match resolve_package(db.file_system(), fs_search_path, components) {
-            Ok(resolved_package) => {
-                let mut package_path = resolved_package.path;
-
-                package_path.push(module_name);
-
-                // Must be a `__init__.pyi` or `__init__.py` or it isn't a package.
-                let kind = if db.file_system().is_directory(&package_path) {
-                    package_path.push("__init__");
-                    ModuleKind::Package
-                } else {
-                    ModuleKind::Module
-                };
-
-                // TODO Implement full https://peps.python.org/pep-0561/#type-checker-module-resolution-order resolution
-                let stub = package_path.with_extension("pyi");
-
-                if let Some(stub) = system_path_to_file(db.upcast(), &stub) {
-                    return Some((search_path.clone(), stub, kind));
-                }
-
-                let module = package_path.with_extension("py");
-
-                if let Some(module) = system_path_to_file(db.upcast(), &module) {
-                    return Some((search_path.clone(), module, kind));
-                }
-
-                // For regular packages, don't search the next search path. All files of that
-                // package must be in the same location
-                if resolved_package.kind.is_regular_package() {
-                    return None;
-                }
-            }
-            Err(parent_kind) => {
-                if parent_kind.is_regular_package() {
-                    // For regular packages, don't search the next search path.
-                    return None;
-                }
-            }
-        }
-    }
-
-    None
-}
-
-fn resolve_package<'a, I>(
-    fs: &dyn FileSystem,
-    module_search_path: &FileSystemPath,
-    components: I,
-) -> Result<ResolvedPackage, PackageKind>
-where
-    I: Iterator<Item = &'a str>,
-{
-    let mut package_path = module_search_path.to_path_buf();
-
-    // `true` if inside a folder that is a namespace package (has no `__init__.py`).
-    // Namespace packages are special because they can be spread across multiple search paths.
-    // https://peps.python.org/pep-0420/
-    let mut in_namespace_package = false;
-
-    // `true` if resolving a sub-package. For example, `true` when resolving `bar` of `foo.bar`.
-    let mut in_sub_package = false;
-
-    // For `foo.bar.baz`, test that `foo` and `baz` both contain a `__init__.py`.
-    for folder in components {
-        package_path.push(folder);
-
-        let has_init_py = fs.is_file(&package_path.join("__init__.py"))
-            || fs.is_file(&package_path.join("__init__.pyi"));
-
-        if has_init_py {
-            in_namespace_package = false;
-        } else if fs.is_directory(&package_path) {
-            // A directory without an `__init__.py` is a namespace package, continue with the next folder.
-            in_namespace_package = true;
-        } else if in_namespace_package {
-            // Package not found but it is part of a namespace package.
-            return Err(PackageKind::Namespace);
-        } else if in_sub_package {
-            // A regular sub package wasn't found.
-            return Err(PackageKind::Regular);
-        } else {
-            // We couldn't find `foo` for `foo.bar.baz`, search the next search path.
-            return Err(PackageKind::Root);
-        }
-
-        in_sub_package = true;
-    }
-
-    let kind = if in_namespace_package {
-        PackageKind::Namespace
-    } else if in_sub_package {
-        PackageKind::Regular
-    } else {
-        PackageKind::Root
-    };
-
-    Ok(ResolvedPackage {
-        kind,
-        path: package_path,
-    })
-}
-
-#[derive(Debug)]
-struct ResolvedPackage {
-    path: FileSystemPathBuf,
-    kind: PackageKind,
-}
-
-#[derive(Copy, Clone, Eq, PartialEq, Debug)]
-enum PackageKind {
-    /// A root package or module. E.g. `foo` in `foo.bar.baz` or just `foo`.
-    Root,
-
-    /// A regular sub-package where the parent contains an `__init__.py`.
-    ///
-    /// For example, `bar` in `foo.bar` when the `foo` directory contains an `__init__.py`.
-    Regular,
-
-    /// A sub-package in a namespace package. A namespace package is a package without an `__init__.py`.
-    ///
-    /// For example, `bar` in `foo.bar` if the `foo` directory contains no `__init__.py`.
-    Namespace,
-}
-
-impl PackageKind {
-    const fn is_regular_package(self) -> bool {
-        matches!(self, PackageKind::Regular)
-    }
-}
-
-#[cfg(test)]
-mod tests {
-
-    use ruff_db::file_system::{FileSystemPath, FileSystemPathBuf};
-    use ruff_db::vfs::{system_path_to_file, VfsFile, VfsPath};
-
-    use crate::db::tests::TestDb;
-    use crate::module::{ModuleKind, ModuleName};
-
-    use super::{
-        path_to_module, resolve_module, set_module_resolution_settings, ModuleResolutionSettings,
-        TYPESHED_STDLIB_DIRECTORY,
-    };
-
-    struct TestCase {
-        db: TestDb,
-
-        src: FileSystemPathBuf,
-        custom_typeshed: FileSystemPathBuf,
-        site_packages: FileSystemPathBuf,
-    }
-
-    fn create_resolver() -> std::io::Result<TestCase> {
-        let mut db = TestDb::new();
-
-        let src = FileSystemPath::new("src").to_path_buf();
-        let site_packages = FileSystemPath::new("site_packages").to_path_buf();
-        let custom_typeshed = FileSystemPath::new("typeshed").to_path_buf();
-
-        let fs = db.memory_file_system();
-
-        fs.create_directory_all(&src)?;
-        fs.create_directory_all(&site_packages)?;
-        fs.create_directory_all(&custom_typeshed)?;
-
-        let settings = ModuleResolutionSettings {
-            extra_paths: vec![],
-            workspace_root: src.clone(),
-            site_packages: Some(site_packages.clone()),
-            custom_typeshed: Some(custom_typeshed.clone()),
-        };
-
-        set_module_resolution_settings(&mut db, settings);
-
-        Ok(TestCase {
-            db,
-            src,
-            custom_typeshed,
-            site_packages,
-        })
-    }
-
-    #[test]
-    fn first_party_module() -> anyhow::Result<()> {
-        let TestCase { db, src, .. } = create_resolver()?;
-
-        let foo_module_name = ModuleName::new_static("foo").unwrap();
-        let foo_path = src.join("foo.py");
-        db.memory_file_system()
-            .write_file(&foo_path, "print('Hello, world!')")?;
-
-        let foo_module = resolve_module(&db, foo_module_name.clone()).unwrap();
-
-        assert_eq!(
-            Some(&foo_module),
-            resolve_module(&db, foo_module_name.clone()).as_ref()
-        );
-
-        assert_eq!("foo", foo_module.name());
-        assert_eq!(&src, foo_module.search_path().path());
-        assert_eq!(ModuleKind::Module, foo_module.kind());
-        assert_eq!(&foo_path, foo_module.file().path(&db));
-
-        assert_eq!(
-            Some(foo_module),
-            path_to_module(&db, &VfsPath::FileSystem(foo_path))
-        );
-
-        Ok(())
-    }
-
-    #[test]
-    fn stdlib() -> anyhow::Result<()> {
-        let TestCase {
-            db,
-            custom_typeshed,
-            ..
-        } = create_resolver()?;
-
-        let stdlib_dir = custom_typeshed.join(TYPESHED_STDLIB_DIRECTORY);
-        let functools_path = stdlib_dir.join("functools.py");
-        db.memory_file_system()
-            .write_file(&functools_path, "def update_wrapper(): ...")?;
-
-        let functools_module_name = ModuleName::new_static("functools").unwrap();
-        let functools_module = resolve_module(&db, functools_module_name.clone()).unwrap();
-
-        assert_eq!(
-            Some(&functools_module),
-            resolve_module(&db, functools_module_name).as_ref()
-        );
-
-        assert_eq!(&stdlib_dir, functools_module.search_path().path());
-        assert_eq!(ModuleKind::Module, functools_module.kind());
-        assert_eq!(&functools_path.clone(), functools_module.file().path(&db));
-
-        assert_eq!(
-            Some(functools_module),
-            path_to_module(&db, &VfsPath::FileSystem(functools_path))
-        );
-
-        Ok(())
-    }
-
-    #[test]
-    fn first_party_precedence_over_stdlib() -> anyhow::Result<()> {
-        let TestCase {
-            db,
-            src,
-            custom_typeshed,
-            ..
-        } = create_resolver()?;
-
-        let stdlib_dir = custom_typeshed.join(TYPESHED_STDLIB_DIRECTORY);
-        let stdlib_functools_path = stdlib_dir.join("functools.py");
-        let first_party_functools_path = src.join("functools.py");
-
-        db.memory_file_system().write_files([
-            (&stdlib_functools_path, "def update_wrapper(): ..."),
-            (&first_party_functools_path, "def update_wrapper(): ..."),
-        ])?;
-
-        let functools_module_name = ModuleName::new_static("functools").unwrap();
-        let functools_module = resolve_module(&db, functools_module_name.clone()).unwrap();
-
-        assert_eq!(
-            Some(&functools_module),
-            resolve_module(&db, functools_module_name).as_ref()
-        );
-        assert_eq!(&src, functools_module.search_path().path());
-        assert_eq!(ModuleKind::Module, functools_module.kind());
-        assert_eq!(
-            &first_party_functools_path.clone(),
-            functools_module.file().path(&db)
-        );
-
-        assert_eq!(
-            Some(functools_module),
-            path_to_module(&db, &VfsPath::FileSystem(first_party_functools_path))
-        );
-
-        Ok(())
-    }
-
-    // TODO: Port typeshed test case. Porting isn't possible at the moment because the vendored zip
-    //   is part of the red knot crate
-    // #[test]
-    // fn typeshed_zip_created_at_build_time() -> anyhow::Result<()> {
-    //     // The file path here is hardcoded in this crate's `build.rs` script.
-    //     // Luckily this crate will fail to build if this file isn't available at build time.
-    //     const TYPESHED_ZIP_BYTES: &[u8] =
-    //         include_bytes!(concat!(env!("OUT_DIR"), "/zipped_typeshed.zip"));
-    //     assert!(!TYPESHED_ZIP_BYTES.is_empty());
-    //     let mut typeshed_zip_archive = ZipArchive::new(Cursor::new(TYPESHED_ZIP_BYTES))?;
-    //
-    //     let path_to_functools = Path::new("stdlib").join("functools.pyi");
-    //     let mut functools_module_stub = typeshed_zip_archive
-    //         .by_name(path_to_functools.to_str().unwrap())
-    //         .unwrap();
-    //     assert!(functools_module_stub.is_file());
-    //
-    //     let mut functools_module_stub_source = String::new();
-    //     functools_module_stub.read_to_string(&mut functools_module_stub_source)?;
-    //
-    //     assert!(functools_module_stub_source.contains("def update_wrapper("));
-    //     Ok(())
-    // }
-
-    #[test]
-    fn resolve_package() -> anyhow::Result<()> {
-        let TestCase { src, db, .. } = create_resolver()?;
-
-        let foo_dir = src.join("foo");
-        let foo_path = foo_dir.join("__init__.py");
-
-        db.memory_file_system()
-            .write_file(&foo_path, "print('Hello, world!')")?;
-
-        let foo_module = resolve_module(&db, ModuleName::new_static("foo").unwrap()).unwrap();
-
-        assert_eq!("foo", foo_module.name());
-        assert_eq!(&src, foo_module.search_path().path());
-        assert_eq!(&foo_path, foo_module.file().path(&db));
-
-        assert_eq!(
-            Some(&foo_module),
-            path_to_module(&db, &VfsPath::FileSystem(foo_path)).as_ref()
-        );
-
-        // Resolving by directory doesn't resolve to the init file.
-        assert_eq!(None, path_to_module(&db, &VfsPath::FileSystem(foo_dir)));
-
-        Ok(())
-    }
-
-    #[test]
-    fn package_priority_over_module() -> anyhow::Result<()> {
-        let TestCase { db, src, .. } = create_resolver()?;
-
-        let foo_dir = src.join("foo");
-        let foo_init = foo_dir.join("__init__.py");
-
-        db.memory_file_system()
-            .write_file(&foo_init, "print('Hello, world!')")?;
-
-        let foo_py = src.join("foo.py");
-        db.memory_file_system()
-            .write_file(&foo_py, "print('Hello, world!')")?;
-
-        let foo_module = resolve_module(&db, ModuleName::new_static("foo").unwrap()).unwrap();
-
-        assert_eq!(&src, foo_module.search_path().path());
-        assert_eq!(&foo_init, foo_module.file().path(&db));
-        assert_eq!(ModuleKind::Package, foo_module.kind());
-
-        assert_eq!(
-            Some(foo_module),
-            path_to_module(&db, &VfsPath::FileSystem(foo_init))
-        );
-        assert_eq!(None, path_to_module(&db, &VfsPath::FileSystem(foo_py)));
-
-        Ok(())
-    }
-
-    #[test]
-    fn typing_stub_over_module() -> anyhow::Result<()> {
-        let TestCase { db, src, .. } = create_resolver()?;
-
-        let foo_stub = src.join("foo.pyi");
-        let foo_py = src.join("foo.py");
-        db.memory_file_system()
-            .write_files([(&foo_stub, "x: int"), (&foo_py, "print('Hello, world!')")])?;
-
-        let foo = resolve_module(&db, ModuleName::new_static("foo").unwrap()).unwrap();
-
-        assert_eq!(&src, foo.search_path().path());
-        assert_eq!(&foo_stub, foo.file().path(&db));
-
-        assert_eq!(
-            Some(foo),
-            path_to_module(&db, &VfsPath::FileSystem(foo_stub))
-        );
-        assert_eq!(None, path_to_module(&db, &VfsPath::FileSystem(foo_py)));
-
-        Ok(())
-    }
-
-    #[test]
-    fn sub_packages() -> anyhow::Result<()> {
-        let TestCase { db, src, .. } = create_resolver()?;
-
-        let foo = src.join("foo");
-        let bar = foo.join("bar");
-        let baz = bar.join("baz.py");
-
-        db.memory_file_system().write_files([
-            (&foo.join("__init__.py"), ""),
-            (&bar.join("__init__.py"), ""),
-            (&baz, "print('Hello, world!')"),
-        ])?;
-
-        let baz_module =
-            resolve_module(&db, ModuleName::new_static("foo.bar.baz").unwrap()).unwrap();
-
-        assert_eq!(&src, baz_module.search_path().path());
-        assert_eq!(&baz, baz_module.file().path(&db));
-
-        assert_eq!(
-            Some(baz_module),
-            path_to_module(&db, &VfsPath::FileSystem(baz))
-        );
-
-        Ok(())
-    }
-
-    #[test]
-    fn namespace_package() -> anyhow::Result<()> {
-        let TestCase {
-            db,
-            src,
-            site_packages,
-            ..
-        } = create_resolver()?;
-
-        // From [PEP420](https://peps.python.org/pep-0420/#nested-namespace-packages).
-        // But uses `src` for `project1` and `site_packages2` for `project2`.
-        // ```
-        // src
-        //   parent
-        //     child
-        //       one.py
-        // site_packages
-        //   parent
-        //     child
-        //       two.py
-        // ```
-
-        let parent1 = src.join("parent");
-        let child1 = parent1.join("child");
-        let one = child1.join("one.py");
-
-        let parent2 = site_packages.join("parent");
-        let child2 = parent2.join("child");
-        let two = child2.join("two.py");
-
-        db.memory_file_system().write_files([
-            (&one, "print('Hello, world!')"),
-            (&two, "print('Hello, world!')"),
-        ])?;
-
-        let one_module =
-            resolve_module(&db, ModuleName::new_static("parent.child.one").unwrap()).unwrap();
-
-        assert_eq!(
-            Some(one_module),
-            path_to_module(&db, &VfsPath::FileSystem(one))
-        );
-
-        let two_module =
-            resolve_module(&db, ModuleName::new_static("parent.child.two").unwrap()).unwrap();
-        assert_eq!(
-            Some(two_module),
-            path_to_module(&db, &VfsPath::FileSystem(two))
-        );
-
-        Ok(())
-    }
-
-    #[test]
-    fn regular_package_in_namespace_package() -> anyhow::Result<()> {
-        let TestCase {
-            db,
-            src,
-            site_packages,
-            ..
-        } = create_resolver()?;
-
-        // Adopted test case from the [PEP420 examples](https://peps.python.org/pep-0420/#nested-namespace-packages).
-        // The `src/parent/child` package is a regular package. Therefore, `site_packages/parent/child/two.py` should not be resolved.
-        // ```
-        // src
-        //   parent
-        //     child
-        //       one.py
-        // site_packages
-        //   parent
-        //     child
-        //       two.py
-        // ```
-
-        let parent1 = src.join("parent");
-        let child1 = parent1.join("child");
-        let one = child1.join("one.py");
-
-        let parent2 = site_packages.join("parent");
-        let child2 = parent2.join("child");
-        let two = child2.join("two.py");
-
-        db.memory_file_system().write_files([
-            (&child1.join("__init__.py"), "print('Hello, world!')"),
-            (&one, "print('Hello, world!')"),
-            (&two, "print('Hello, world!')"),
-        ])?;
-
-        let one_module =
-            resolve_module(&db, ModuleName::new_static("parent.child.one").unwrap()).unwrap();
-
-        assert_eq!(
-            Some(one_module),
-            path_to_module(&db, &VfsPath::FileSystem(one))
-        );
-
-        assert_eq!(
-            None,
-            resolve_module(&db, ModuleName::new_static("parent.child.two").unwrap())
-        );
-        Ok(())
-    }
-
-    #[test]
-    fn module_search_path_priority() -> anyhow::Result<()> {
-        let TestCase {
-            db,
-            src,
-            site_packages,
-            ..
-        } = create_resolver()?;
-
-        let foo_src = src.join("foo.py");
-        let foo_site_packages = site_packages.join("foo.py");
-
-        db.memory_file_system()
-            .write_files([(&foo_src, ""), (&foo_site_packages, "")])?;
-
-        let foo_module = resolve_module(&db, ModuleName::new_static("foo").unwrap()).unwrap();
-
-        assert_eq!(&src, foo_module.search_path().path());
-        assert_eq!(&foo_src, foo_module.file().path(&db));
-
-        assert_eq!(
-            Some(foo_module),
-            path_to_module(&db, &VfsPath::FileSystem(foo_src))
-        );
-        assert_eq!(
-            None,
-            path_to_module(&db, &VfsPath::FileSystem(foo_site_packages))
-        );
-
-        Ok(())
-    }
-
-    #[test]
-    #[cfg(target_family = "unix")]
-    fn symlink() -> anyhow::Result<()> {
-        let TestCase {
-            mut db,
-            src,
-            site_packages,
-            custom_typeshed,
-        } = create_resolver()?;
-
-        db.with_os_file_system();
-
-        let temp_dir = tempfile::tempdir()?;
-        let root = FileSystemPath::from_std_path(temp_dir.path()).unwrap();
-
-        let src = root.join(src);
-        let site_packages = root.join(site_packages);
-        let custom_typeshed = root.join(custom_typeshed);
-
-        let foo = src.join("foo.py");
-        let bar = src.join("bar.py");
-
-        std::fs::create_dir_all(src.as_std_path())?;
-        std::fs::create_dir_all(site_packages.as_std_path())?;
-        std::fs::create_dir_all(custom_typeshed.as_std_path())?;
-
-        std::fs::write(foo.as_std_path(), "")?;
-        std::os::unix::fs::symlink(foo.as_std_path(), bar.as_std_path())?;
-
-        let settings = ModuleResolutionSettings {
-            extra_paths: vec![],
-            workspace_root: src.clone(),
-            site_packages: Some(site_packages),
-            custom_typeshed: Some(custom_typeshed),
-        };
-
-        set_module_resolution_settings(&mut db, settings);
-
-        let foo_module = resolve_module(&db, ModuleName::new_static("foo").unwrap()).unwrap();
-        let bar_module = resolve_module(&db, ModuleName::new_static("bar").unwrap()).unwrap();
-
-        assert_ne!(foo_module, bar_module);
-
-        assert_eq!(&src, foo_module.search_path().path());
-        assert_eq!(&foo, foo_module.file().path(&db));
-
-        // `foo` and `bar` shouldn't resolve to the same file
-
-        assert_eq!(&src, bar_module.search_path().path());
-        assert_eq!(&bar, bar_module.file().path(&db));
-        assert_eq!(&foo, foo_module.file().path(&db));
-
-        assert_ne!(&foo_module, &bar_module);
-
-        assert_eq!(
-            Some(foo_module),
-            path_to_module(&db, &VfsPath::FileSystem(foo))
-        );
-        assert_eq!(
-            Some(bar_module),
-            path_to_module(&db, &VfsPath::FileSystem(bar))
-        );
-
-        Ok(())
-    }
-
-    #[test]
-    fn deleting_an_unrealted_file_doesnt_change_module_resolution() -> anyhow::Result<()> {
-        let TestCase { mut db, src, .. } = create_resolver()?;
-
-        let foo_path = src.join("foo.py");
-        let bar_path = src.join("bar.py");
-
-        db.memory_file_system()
-            .write_files([(&foo_path, "x = 1"), (&bar_path, "y = 2")])?;
-
-        let foo_module_name = ModuleName::new_static("foo").unwrap();
-        let foo_module = resolve_module(&db, foo_module_name.clone()).unwrap();
-
-        let bar = system_path_to_file(&db, &bar_path).expect("bar.py to exist");
-
-        db.clear_salsa_events();
-
-        // Delete `bar.py`
-        db.memory_file_system().remove_file(&bar_path)?;
-        bar.touch(&mut db);
-
-        // Re-query the foo module. The foo module should still be cached because `bar.py` isn't relevant
-        // for resolving `foo`.
-
-        let foo_module2 = resolve_module(&db, foo_module_name);
-
-        assert!(!db
-            .take_salsa_events()
-            .iter()
-            .any(|event| { matches!(event.kind, salsa::EventKind::WillExecute { .. }) }));
-
-        assert_eq!(Some(foo_module), foo_module2);
-
-        Ok(())
-    }
-
-    #[test]
-    fn adding_a_file_on_which_the_module_resolution_depends_on_invalidates_the_query(
-    ) -> anyhow::Result<()> {
-        let TestCase { mut db, src, .. } = create_resolver()?;
-        let foo_path = src.join("foo.py");
-
-        let foo_module_name = ModuleName::new_static("foo").unwrap();
-        assert_eq!(resolve_module(&db, foo_module_name.clone()), None);
-
-        // Now write the foo file
-        db.memory_file_system().write_file(&foo_path, "x = 1")?;
-        VfsFile::touch_path(&mut db, &VfsPath::FileSystem(foo_path.clone()));
-        let foo_file = system_path_to_file(&db, &foo_path).expect("foo.py to exist");
-
-        let foo_module = resolve_module(&db, foo_module_name).expect("Foo module to resolve");
-        assert_eq!(foo_file, foo_module.file());
-
-        Ok(())
-    }
-
-    #[test]
-    fn removing_a_file_that_the_module_resolution_depends_on_invalidates_the_query(
-    ) -> anyhow::Result<()> {
-        let TestCase { mut db, src, .. } = create_resolver()?;
-        let foo_path = src.join("foo.py");
-        let foo_init_path = src.join("foo/__init__.py");
-
-        db.memory_file_system()
-            .write_files([(&foo_path, "x = 1"), (&foo_init_path, "x = 2")])?;
-
-        let foo_module_name = ModuleName::new_static("foo").unwrap();
-        let foo_module = resolve_module(&db, foo_module_name.clone()).expect("foo module to exist");
-
-        assert_eq!(&foo_init_path, foo_module.file().path(&db));
-
-        // Delete `foo/__init__.py` and the `foo` folder. `foo` should now resolve to `foo.py`
-        db.memory_file_system().remove_file(&foo_init_path)?;
-        db.memory_file_system()
-            .remove_directory(foo_init_path.parent().unwrap())?;
-        VfsFile::touch_path(&mut db, &VfsPath::FileSystem(foo_init_path.clone()));
-
-        let foo_module = resolve_module(&db, foo_module_name).expect("Foo module to resolve");
-        assert_eq!(&foo_path, foo_module.file().path(&db));
-
-        Ok(())
-    }
-}

crates/red_knot_module_resolver/src/typeshed.rs

@@ -1,91 +0,0 @@
-pub(crate) mod versions;
-
-#[cfg(test)]
-mod tests {
-    use std::io::{self, Read};
-    use std::path::Path;
-
-    use ruff_db::vendored::VendoredFileSystem;
-    use ruff_db::vfs::VendoredPath;
-
-    // The file path here is hardcoded in this crate's `build.rs` script.
-    // Luckily this crate will fail to build if this file isn't available at build time.
-    const TYPESHED_ZIP_BYTES: &[u8] =
-        include_bytes!(concat!(env!("OUT_DIR"), "/zipped_typeshed.zip"));
-
-    #[test]
-    fn typeshed_zip_created_at_build_time() {
-        let mut typeshed_zip_archive =
-            zip::ZipArchive::new(io::Cursor::new(TYPESHED_ZIP_BYTES)).unwrap();
-
-        let mut functools_module_stub = typeshed_zip_archive
-            .by_name("stdlib/functools.pyi")
-            .unwrap();
-        assert!(functools_module_stub.is_file());
-
-        let mut functools_module_stub_source = String::new();
-        functools_module_stub
-            .read_to_string(&mut functools_module_stub_source)
-            .unwrap();
-
-        assert!(functools_module_stub_source.contains("def update_wrapper("));
-    }
-
-    #[test]
-    fn typeshed_vfs_consistent_with_vendored_stubs() {
-        let vendored_typeshed_dir = Path::new("vendor/typeshed").canonicalize().unwrap();
-        let vendored_typeshed_stubs = VendoredFileSystem::new(TYPESHED_ZIP_BYTES).unwrap();
-
-        let mut empty_iterator = true;
-        for entry in walkdir::WalkDir::new(&vendored_typeshed_dir).min_depth(1) {
-            empty_iterator = false;
-            let entry = entry.unwrap();
-            let absolute_path = entry.path();
-            let file_type = entry.file_type();
-
-            let relative_path = absolute_path
-                .strip_prefix(&vendored_typeshed_dir)
-                .unwrap_or_else(|_| {
-                    panic!("Expected {absolute_path:?} to be a child of {vendored_typeshed_dir:?}")
-                });
-
-            let vendored_path = <&VendoredPath>::try_from(relative_path)
-                .unwrap_or_else(|_| panic!("Expected {relative_path:?} to be valid UTF-8"));
-
-            assert!(
-                vendored_typeshed_stubs.exists(vendored_path),
-                "Expected {vendored_path:?} to exist in the `VendoredFileSystem`!
-
-                Vendored file system:
-
-                {vendored_typeshed_stubs:#?}
-                "
-            );
-
-            let vendored_path_kind = vendored_typeshed_stubs
-                .metadata(vendored_path)
-                .unwrap_or_else(|| {
-                    panic!(
-                        "Expected metadata for {vendored_path:?} to be retrievable from the `VendoredFileSystem!
-
-                        Vendored file system:
-
-                        {vendored_typeshed_stubs:#?}
-                        "
-                    )
-                })
-                .kind();
-
-            assert_eq!(
-                vendored_path_kind.is_directory(),
-                file_type.is_dir(),
-                "{vendored_path:?} had type {vendored_path_kind:?}, inconsistent with fs path {relative_path:?}: {file_type:?}"
-            );
-        }
-
-        assert!(
-            !empty_iterator,
-            "Expected there to be at least one file or directory in the vendored typeshed stubs!"
-        );
-    }
-}

crates/red_knot_module_resolver/src/typeshed/versions.rs

@@ -1,590 +0,0 @@
-use std::collections::BTreeMap;
-use std::fmt;
-use std::num::{NonZeroU16, NonZeroUsize};
-use std::ops::{RangeFrom, RangeInclusive};
-use std::str::FromStr;
-
-use rustc_hash::FxHashMap;
-
-use crate::module::ModuleName;
-
-#[derive(Debug, PartialEq, Eq)]
-pub struct TypeshedVersionsParseError {
-    line_number: NonZeroU16,
-    reason: TypeshedVersionsParseErrorKind,
-}
-
-impl fmt::Display for TypeshedVersionsParseError {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        let TypeshedVersionsParseError {
-            line_number,
-            reason,
-        } = self;
-        write!(
-            f,
-            "Error while parsing line {line_number} of typeshed's VERSIONS file: {reason}"
-        )
-    }
-}
-
-impl std::error::Error for TypeshedVersionsParseError {
-    fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
-        if let TypeshedVersionsParseErrorKind::IntegerParsingFailure { err, .. } = &self.reason {
-            Some(err)
-        } else {
-            None
-        }
-    }
-}
-
-#[derive(Debug, PartialEq, Eq)]
-pub enum TypeshedVersionsParseErrorKind {
-    TooManyLines(NonZeroUsize),
-    UnexpectedNumberOfColons,
-    InvalidModuleName(String),
-    UnexpectedNumberOfHyphens,
-    UnexpectedNumberOfPeriods(String),
-    IntegerParsingFailure {
-        version: String,
-        err: std::num::ParseIntError,
-    },
-}
-
-impl fmt::Display for TypeshedVersionsParseErrorKind {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match self {
-            Self::TooManyLines(num_lines) => write!(
-                f,
-                "File has too many lines ({num_lines}); maximum allowed is {}",
-                NonZeroU16::MAX
-            ),
-            Self::UnexpectedNumberOfColons => {
-                f.write_str("Expected every non-comment line to have exactly one colon")
-            }
-            Self::InvalidModuleName(name) => write!(
-                f,
-                "Expected all components of '{name}' to be valid Python identifiers"
-            ),
-            Self::UnexpectedNumberOfHyphens => {
-                f.write_str("Expected every non-comment line to have exactly one '-' character")
-            }
-            Self::UnexpectedNumberOfPeriods(format) => write!(
-                f,
-                "Expected all versions to be in the form {{MAJOR}}.{{MINOR}}; got '{format}'"
-            ),
-            Self::IntegerParsingFailure { version, err } => write!(
-                f,
-                "Failed to convert '{version}' to a pair of integers due to {err}",
-            ),
-        }
-    }
-}
-
-#[derive(Debug, PartialEq, Eq)]
-pub struct TypeshedVersions(FxHashMap<ModuleName, PyVersionRange>);
-
-impl TypeshedVersions {
-    pub fn len(&self) -> usize {
-        self.0.len()
-    }
-
-    pub fn is_empty(&self) -> bool {
-        self.0.is_empty()
-    }
-
-    pub fn contains_module(&self, module_name: &ModuleName) -> bool {
-        self.0.contains_key(module_name)
-    }
-
-    pub fn module_exists_on_version(
-        &self,
-        module: ModuleName,
-        version: impl Into<PyVersion>,
-    ) -> bool {
-        let version = version.into();
-        let mut module: Option<ModuleName> = Some(module);
-        while let Some(module_to_try) = module {
-            if let Some(range) = self.0.get(&module_to_try) {
-                return range.contains(version);
-            }
-            module = module_to_try.parent();
-        }
-        false
-    }
-}
-
-impl FromStr for TypeshedVersions {
-    type Err = TypeshedVersionsParseError;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        let mut map = FxHashMap::default();
-
-        for (line_index, line) in s.lines().enumerate() {
-            // humans expect line numbers to be 1-indexed
-            let line_number = NonZeroUsize::new(line_index.saturating_add(1)).unwrap();
-
-            let Ok(line_number) = NonZeroU16::try_from(line_number) else {
-                return Err(TypeshedVersionsParseError {
-                    line_number: NonZeroU16::MAX,
-                    reason: TypeshedVersionsParseErrorKind::TooManyLines(line_number),
-                });
-            };
-
-            let Some(content) = line.split('#').map(str::trim).next() else {
-                continue;
-            };
-            if content.is_empty() {
-                continue;
-            }
-
-            let mut parts = content.split(':').map(str::trim);
-            let (Some(module_name), Some(rest), None) = (parts.next(), parts.next(), parts.next())
-            else {
-                return Err(TypeshedVersionsParseError {
-                    line_number,
-                    reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfColons,
-                });
-            };
-
-            let Some(module_name) = ModuleName::new(module_name) else {
-                return Err(TypeshedVersionsParseError {
-                    line_number,
-                    reason: TypeshedVersionsParseErrorKind::InvalidModuleName(
-                        module_name.to_string(),
-                    ),
-                });
-            };
-
-            match PyVersionRange::from_str(rest) {
-                Ok(version) => map.insert(module_name, version),
-                Err(reason) => {
-                    return Err(TypeshedVersionsParseError {
-                        line_number,
-                        reason,
-                    })
-                }
-            };
-        }
-
-        Ok(Self(map))
-    }
-}
-
-impl fmt::Display for TypeshedVersions {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        let sorted_items: BTreeMap<&ModuleName, &PyVersionRange> = self.0.iter().collect();
-        for (module_name, range) in sorted_items {
-            writeln!(f, "{module_name}: {range}")?;
-        }
-        Ok(())
-    }
-}
-
-#[derive(Debug, Clone, Eq, PartialEq)]
-enum PyVersionRange {
-    AvailableFrom(RangeFrom<PyVersion>),
-    AvailableWithin(RangeInclusive<PyVersion>),
-}
-
-impl PyVersionRange {
-    fn contains(&self, version: PyVersion) -> bool {
-        match self {
-            Self::AvailableFrom(inner) => inner.contains(&version),
-            Self::AvailableWithin(inner) => inner.contains(&version),
-        }
-    }
-}
-
-impl FromStr for PyVersionRange {
-    type Err = TypeshedVersionsParseErrorKind;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        let mut parts = s.split('-').map(str::trim);
-        match (parts.next(), parts.next(), parts.next()) {
-            (Some(lower), Some(""), None) => Ok(Self::AvailableFrom((lower.parse()?)..)),
-            (Some(lower), Some(upper), None) => {
-                Ok(Self::AvailableWithin((lower.parse()?)..=(upper.parse()?)))
-            }
-            _ => Err(TypeshedVersionsParseErrorKind::UnexpectedNumberOfHyphens),
-        }
-    }
-}
-
-impl fmt::Display for PyVersionRange {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        match self {
-            Self::AvailableFrom(range_from) => write!(f, "{}-", range_from.start),
-            Self::AvailableWithin(range_inclusive) => {
-                write!(f, "{}-{}", range_inclusive.start(), range_inclusive.end())
-            }
-        }
-    }
-}
-
-#[derive(Debug, Clone, Copy, Eq, PartialEq, Ord, PartialOrd, Hash)]
-pub struct PyVersion {
-    major: u8,
-    minor: u8,
-}
-
-impl FromStr for PyVersion {
-    type Err = TypeshedVersionsParseErrorKind;
-
-    fn from_str(s: &str) -> Result<Self, Self::Err> {
-        let mut parts = s.split('.').map(str::trim);
-        let (Some(major), Some(minor), None) = (parts.next(), parts.next(), parts.next()) else {
-            return Err(TypeshedVersionsParseErrorKind::UnexpectedNumberOfPeriods(
-                s.to_string(),
-            ));
-        };
-        let major = match u8::from_str(major) {
-            Ok(major) => major,
-            Err(err) => {
-                return Err(TypeshedVersionsParseErrorKind::IntegerParsingFailure {
-                    version: s.to_string(),
-                    err,
-                })
-            }
-        };
-        let minor = match u8::from_str(minor) {
-            Ok(minor) => minor,
-            Err(err) => {
-                return Err(TypeshedVersionsParseErrorKind::IntegerParsingFailure {
-                    version: s.to_string(),
-                    err,
-                })
-            }
-        };
-        Ok(Self { major, minor })
-    }
-}
-
-impl fmt::Display for PyVersion {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        let PyVersion { major, minor } = self;
-        write!(f, "{major}.{minor}")
-    }
-}
-
-// TODO: unify with the PythonVersion enum in the linter/formatter crates?
-#[derive(Copy, Clone, Hash, Debug, PartialEq, Eq, PartialOrd, Ord, Default)]
-pub enum SupportedPyVersion {
-    Py37,
-    #[default]
-    Py38,
-    Py39,
-    Py310,
-    Py311,
-    Py312,
-    Py313,
-}
-
-impl From<SupportedPyVersion> for PyVersion {
-    fn from(value: SupportedPyVersion) -> Self {
-        match value {
-            SupportedPyVersion::Py37 => PyVersion { major: 3, minor: 7 },
-            SupportedPyVersion::Py38 => PyVersion { major: 3, minor: 8 },
-            SupportedPyVersion::Py39 => PyVersion { major: 3, minor: 9 },
-            SupportedPyVersion::Py310 => PyVersion {
-                major: 3,
-                minor: 10,
-            },
-            SupportedPyVersion::Py311 => PyVersion {
-                major: 3,
-                minor: 11,
-            },
-            SupportedPyVersion::Py312 => PyVersion {
-                major: 3,
-                minor: 12,
-            },
-            SupportedPyVersion::Py313 => PyVersion {
-                major: 3,
-                minor: 13,
-            },
-        }
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use std::num::{IntErrorKind, NonZeroU16};
-    use std::path::Path;
-
-    use super::*;
-
-    use insta::assert_snapshot;
-
-    const TYPESHED_STDLIB_DIR: &str = "stdlib";
-
-    #[allow(unsafe_code)]
-    const ONE: NonZeroU16 = unsafe { NonZeroU16::new_unchecked(1) };
-
-    #[test]
-    fn can_parse_vendored_versions_file() {
-        let versions_data = include_str!(concat!(
-            env!("CARGO_MANIFEST_DIR"),
-            "/vendor/typeshed/stdlib/VERSIONS"
-        ));
-
-        let versions = TypeshedVersions::from_str(versions_data).unwrap();
-        assert!(versions.len() > 100);
-        assert!(versions.len() < 1000);
-
-        let asyncio = ModuleName::new_static("asyncio").unwrap();
-        let asyncio_staggered = ModuleName::new_static("asyncio.staggered").unwrap();
-        let audioop = ModuleName::new_static("audioop").unwrap();
-
-        assert!(versions.contains_module(&asyncio));
-        assert!(versions.module_exists_on_version(asyncio, SupportedPyVersion::Py310));
-
-        assert!(versions.contains_module(&asyncio_staggered));
-        assert!(
-            versions.module_exists_on_version(asyncio_staggered.clone(), SupportedPyVersion::Py38)
-        );
-        assert!(!versions.module_exists_on_version(asyncio_staggered, SupportedPyVersion::Py37));
-
-        assert!(versions.contains_module(&audioop));
-        assert!(versions.module_exists_on_version(audioop.clone(), SupportedPyVersion::Py312));
-        assert!(!versions.module_exists_on_version(audioop, SupportedPyVersion::Py313));
-    }
-
-    #[test]
-    fn typeshed_versions_consistent_with_vendored_stubs() {
-        const VERSIONS_DATA: &str = include_str!("../../vendor/typeshed/stdlib/VERSIONS");
-        let vendored_typeshed_dir = Path::new("vendor/typeshed").canonicalize().unwrap();
-        let vendored_typeshed_versions = TypeshedVersions::from_str(VERSIONS_DATA).unwrap();
-
-        let mut empty_iterator = true;
-
-        let stdlib_stubs_path = vendored_typeshed_dir.join(TYPESHED_STDLIB_DIR);
-
-        for entry in std::fs::read_dir(&stdlib_stubs_path).unwrap() {
-            empty_iterator = false;
-            let entry = entry.unwrap();
-            let absolute_path = entry.path();
-
-            let relative_path = absolute_path
-                .strip_prefix(&stdlib_stubs_path)
-                .unwrap_or_else(|_| panic!("Expected path to be a child of {stdlib_stubs_path:?} but found {absolute_path:?}"));
-
-            let relative_path_str = relative_path.as_os_str().to_str().unwrap_or_else(|| {
-                panic!("Expected all typeshed paths to be valid UTF-8; got {relative_path:?}")
-            });
-            if relative_path_str == "VERSIONS" {
-                continue;
-            }
-
-            let top_level_module = if let Some(extension) = relative_path.extension() {
-                // It was a file; strip off the file extension to get the module name:
-                let extension = extension
-                    .to_str()
-                    .unwrap_or_else(||panic!("Expected all file extensions to be UTF-8; was not true for {relative_path:?}"));
-
-                relative_path_str
-                    .strip_suffix(extension)
-                    .and_then(|string| string.strip_suffix('.')).unwrap_or_else(|| {
-                        panic!("Expected path {relative_path_str:?} to end with computed extension {extension:?}")
-                })
-            } else {
-                // It was a directory; no need to do anything to get the module name
-                relative_path_str
-            };
-
-            let top_level_module = ModuleName::new(top_level_module)
-                .unwrap_or_else(|| panic!("{top_level_module:?} was not a valid module name!"));
-
-            assert!(vendored_typeshed_versions.contains_module(&top_level_module));
-        }
-
-        assert!(
-            !empty_iterator,
-            "Expected there to be at least one file or directory in the vendored typeshed stubs"
-        );
-    }
-
-    #[test]
-    fn can_parse_mock_versions_file() {
-        const VERSIONS: &str = "\
-# a comment
-    # some more comment
-# yet more comment
-
-
-# and some more comment
-
-bar: 2.7-3.10
-
-# more comment
-bar.baz: 3.1-3.9
-foo: 3.8-   # trailing comment
-";
-        let parsed_versions = TypeshedVersions::from_str(VERSIONS).unwrap();
-        assert_eq!(parsed_versions.len(), 3);
-        assert_snapshot!(parsed_versions.to_string(), @r###"
-        bar: 2.7-3.10
-        bar.baz: 3.1-3.9
-        foo: 3.8-
-        "###
-        );
-
-        let foo = ModuleName::new_static("foo").unwrap();
-        let bar = ModuleName::new_static("bar").unwrap();
-        let bar_baz = ModuleName::new_static("bar.baz").unwrap();
-        let spam = ModuleName::new_static("spam").unwrap();
-
-        assert!(parsed_versions.contains_module(&foo));
-        assert!(!parsed_versions.module_exists_on_version(foo.clone(), SupportedPyVersion::Py37));
-        assert!(parsed_versions.module_exists_on_version(foo.clone(), SupportedPyVersion::Py38));
-        assert!(parsed_versions.module_exists_on_version(foo, SupportedPyVersion::Py311));
-
-        assert!(parsed_versions.contains_module(&bar));
-        assert!(parsed_versions.module_exists_on_version(bar.clone(), SupportedPyVersion::Py37));
-        assert!(parsed_versions.module_exists_on_version(bar.clone(), SupportedPyVersion::Py310));
-        assert!(!parsed_versions.module_exists_on_version(bar, SupportedPyVersion::Py311));
-
-        assert!(parsed_versions.contains_module(&bar_baz));
-        assert!(parsed_versions.module_exists_on_version(bar_baz.clone(), SupportedPyVersion::Py37));
-        assert!(parsed_versions.module_exists_on_version(bar_baz.clone(), SupportedPyVersion::Py39));
-        assert!(!parsed_versions.module_exists_on_version(bar_baz, SupportedPyVersion::Py310));
-
-        assert!(!parsed_versions.contains_module(&spam));
-        assert!(!parsed_versions.module_exists_on_version(spam.clone(), SupportedPyVersion::Py37));
-        assert!(!parsed_versions.module_exists_on_version(spam, SupportedPyVersion::Py313));
-    }
-
-    #[test]
-    fn invalid_huge_versions_file() {
-        let offset = 100;
-        let too_many = u16::MAX as usize + offset;
-
-        let mut massive_versions_file = String::new();
-        for i in 0..too_many {
-            massive_versions_file.push_str(&format!("x{i}: 3.8-\n"));
-        }
-
-        assert_eq!(
-            TypeshedVersions::from_str(&massive_versions_file),
-            Err(TypeshedVersionsParseError {
-                line_number: NonZeroU16::MAX,
-                reason: TypeshedVersionsParseErrorKind::TooManyLines(
-                    NonZeroUsize::new(too_many + 1 - offset).unwrap()
-                )
-            })
-        );
-    }
-
-    #[test]
-    fn invalid_typeshed_versions_bad_colon_number() {
-        assert_eq!(
-            TypeshedVersions::from_str("foo 3.7"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfColons
-            })
-        );
-        assert_eq!(
-            TypeshedVersions::from_str("foo:: 3.7"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfColons
-            })
-        );
-    }
-
-    #[test]
-    fn invalid_typeshed_versions_non_identifier_modules() {
-        assert_eq!(
-            TypeshedVersions::from_str("not!an!identifier!: 3.7"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::InvalidModuleName(
-                    "not!an!identifier!".to_string()
-                )
-            })
-        );
-        assert_eq!(
-            TypeshedVersions::from_str("(also_not).(an_identifier): 3.7"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::InvalidModuleName(
-                    "(also_not).(an_identifier)".to_string()
-                )
-            })
-        );
-    }
-
-    #[test]
-    fn invalid_typeshed_versions_bad_hyphen_number() {
-        assert_eq!(
-            TypeshedVersions::from_str("foo: 3.8"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfHyphens
-            })
-        );
-        assert_eq!(
-            TypeshedVersions::from_str("foo: 3.8--"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfHyphens
-            })
-        );
-        assert_eq!(
-            TypeshedVersions::from_str("foo: 3.8--3.9"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfHyphens
-            })
-        );
-    }
-
-    #[test]
-    fn invalid_typeshed_versions_bad_period_number() {
-        assert_eq!(
-            TypeshedVersions::from_str("foo: 38-"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfPeriods("38".to_string())
-            })
-        );
-        assert_eq!(
-            TypeshedVersions::from_str("foo: 3..8-"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfPeriods(
-                    "3..8".to_string()
-                )
-            })
-        );
-        assert_eq!(
-            TypeshedVersions::from_str("foo: 3.8-3..11"),
-            Err(TypeshedVersionsParseError {
-                line_number: ONE,
-                reason: TypeshedVersionsParseErrorKind::UnexpectedNumberOfPeriods(
-                    "3..11".to_string()
-                )
-            })
-        );
-    }
-
-    #[test]
-    fn invalid_typeshed_versions_non_digits() {
-        let err = TypeshedVersions::from_str("foo: 1.two-").unwrap_err();
-        assert_eq!(err.line_number, ONE);
-        let TypeshedVersionsParseErrorKind::IntegerParsingFailure { version, err } = err.reason
-        else {
-            panic!()
-        };
-        assert_eq!(version, "1.two".to_string());
-        assert_eq!(*err.kind(), IntErrorKind::InvalidDigit);
-
-        let err = TypeshedVersions::from_str("foo: 3.8-four.9").unwrap_err();
-        assert_eq!(err.line_number, ONE);
-        let TypeshedVersionsParseErrorKind::IntegerParsingFailure { version, err } = err.reason
-        else {
-            panic!()
-        };
-        assert_eq!(version, "four.9".to_string());
-        assert_eq!(*err.kind(), IntErrorKind::InvalidDigit);
-    }
-}

crates/red_knot_module_resolver/vendor/typeshed/LICENSE

@@ -1,237 +0,0 @@
-The "typeshed" project is licensed under the terms of the Apache license, as
-reproduced below.
-
-= = = = =
-
-Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "{}"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright {yyyy} {name of copyright owner}
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
-
-= = = = =
-
-Parts of typeshed are licensed under different licenses (like the MIT
-license), reproduced below.
-
-= = = = =
-
-The MIT License
-
-Copyright (c) 2015 Jukka Lehtosalo and contributors
-
-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/red_knot_module_resolver/vendor/typeshed/README.md

@@ -1,124 +0,0 @@
-# typeshed
-
-[![Tests](https://github.com/python/typeshed/actions/workflows/tests.yml/badge.svg)](https://github.com/python/typeshed/actions/workflows/tests.yml)
-[![Chat at https://gitter.im/python/typing](https://badges.gitter.im/python/typing.svg)](https://gitter.im/python/typing?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
-[![Pull Requests Welcome](https://img.shields.io/badge/pull%20requests-welcome-brightgreen.svg)](https://github.com/python/typeshed/blob/main/CONTRIBUTING.md)
-
-## About
-
-Typeshed contains external type annotations for the Python standard library
-and Python builtins, as well as third party packages as contributed by
-people external to those projects.
-
-This data can e.g. be used for static analysis, type checking, type inference,
-and autocompletion.
-
-For information on how to use typeshed, read below.  Information for
-contributors can be found in [CONTRIBUTING.md](CONTRIBUTING.md).  **Please read
-it before submitting pull requests; do not report issues with annotations to
-the project the stubs are for, but instead report them here to typeshed.**
-
-Further documentation on stub files, typeshed, and Python's typing system in
-general, can also be found at https://typing.readthedocs.io/en/latest/.
-
-Typeshed supports Python versions 3.8 and up.
-
-## Using
-
-If you're just using a type checker ([mypy](https://github.com/python/mypy/),
-[pyright](https://github.com/microsoft/pyright),
-[pytype](https://github.com/google/pytype/), PyCharm, ...), as opposed to
-developing it, you don't need to interact with the typeshed repo at
-all: a copy of standard library part of typeshed is bundled with type checkers.
-And type stubs for third party packages and modules you are using can
-be installed from PyPI. For example, if you are using `html5lib` and `requests`,
-you can install the type stubs using
-
-```bash
-$ pip install types-html5lib types-requests
-```
-
-These PyPI packages follow [PEP 561](http://www.python.org/dev/peps/pep-0561/)
-and are automatically released (up to once a day) by
-[typeshed internal machinery](https://github.com/typeshed-internal/stub_uploader).
-
-Type checkers should be able to use these stub packages when installed. For more
-details, see the documentation for your type checker.
-
-### Package versioning for third-party stubs
-
-Version numbers of third-party stub packages consist of at least four parts.
-All parts of the stub version, except for the last part, correspond to the
-version of the runtime package being stubbed. For example, if the `types-foo`
-package has version `1.2.0.20240309`, this guarantees that the `types-foo` package
-contains stubs targeted against `foo==1.2.*` and tested against the latest
-version of `foo` matching that specifier. In this example, the final element
-of the version number (20240309) indicates that the stub package was pushed on
-March 9, 2024.
-
-At typeshed, we try to keep breaking changes to a minimum. However, due to the
-nature of stubs, any version bump can introduce changes that might make your
-code fail to type check.
-
-There are several strategies available for specifying the version of a stubs
-package you're using, each with its own tradeoffs:
-
-1. Use the same bounds that you use for the package being stubbed. For example,
-   if you use `requests>=2.30.0,<2.32`, you can use
-   `types-requests>=2.30.0,<2.32`. This ensures that the stubs are compatible
-   with the package you are using, but it carries a small risk of breaking
-   type checking due to changes in the stubs.
-
-   Another risk of this strategy is that stubs often lag behind
-   the package being stubbed. You might want to force the package being stubbed
-   to a certain minimum version because it fixes a critical bug, but if
-   correspondingly updated stubs have not been released, your type
-   checking results may not be fully accurate.
-2. Pin the stubs to a known good version and update the pin from time to time
-   (either manually, or using a tool such as dependabot or renovate).
-
-   For example, if you use `types-requests==2.31.0.1`, you can have confidence
-   that upgrading dependencies will not break type checking. However, you will
-   miss out on improvements in the stubs that could potentially improve type
-   checking until you update the pin. This strategy also has the risk that the
-   stubs you are using might become incompatible with the package being stubbed.
-3. Don't pin the stubs. This is the option that demands the least work from
-   you when it comes to updating version pins, and has the advantage that you
-   will automatically benefit from improved stubs whenever a new version of the
-   stubs package is released. However, it carries the risk that the stubs
-   become incompatible with the package being stubbed.
-
-   For example, if a new major version of the package is released, there's a
-   chance the stubs might be updated to reflect the new version of the runtime
-   package before you update the package being stubbed.
-
-You can also switch between the different strategies as needed. For example,
-you could default to strategy (1), but fall back to strategy (2) when
-a problem arises that can't easily be fixed.
-
-### The `_typeshed` package
-
-typeshed includes a package `_typeshed` as part of the standard library.
-This package and its submodules contain utility types, but are not
-available at runtime. For more information about how to use this package,
-[see the `stdlib/_typeshed` directory](https://github.com/python/typeshed/tree/main/stdlib/_typeshed).
-
-## Discussion
-
-If you've run into behavior in the type checker that suggests the type
-stubs for a given library are incorrect or incomplete,
-we want to hear from you!
-
-Our main forum for discussion is the project's [GitHub issue
-tracker](https://github.com/python/typeshed/issues).  This is the right
-place to start a discussion of any of the above or most any other
-topic concerning the project.
-
-If you have general questions about typing with Python, or you need
-a review of your type annotations or stubs outside of typeshed, head over to
-[our discussion forum](https://github.com/python/typing/discussions).
-For less formal discussion, try the typing chat room on
-[gitter.im](https://gitter.im/python/typing).  Some typeshed maintainers
-are almost always present; feel free to find us there and we're happy
-to chat.  Substantive technical discussion will be directed to the
-issue tracker.

crates/red_knot_module_resolver/vendor/typeshed/source_commit.txt

@@ -1 +0,0 @@
-114409d49b43ba62a179ebb856fa70a5161f751e

crates/red_knot_module_resolver/vendor/typeshed/stdlib/VERSIONS

@@ -1,310 +0,0 @@
-# The structure of this file is as follows:
-# - Blank lines and comments starting with `#` are ignored.
-# - Lines contain the name of a module, followed by a colon,
-#   a space, and a version range (for example: `symbol: 3.0-3.9`).
-#
-# Version ranges may be of the form "X.Y-A.B" or "X.Y-". The
-# first form means that a module was introduced in version X.Y and last
-# available in version A.B. The second form means that the module was
-# introduced in version X.Y and is still available in the latest
-# version of Python.
-#
-# If a submodule is not listed separately, it has the same lifetime as
-# its parent module.
-#
-# Python versions before 3.0 are ignored, so any module that was already
-# present in 3.0 will have "3.0" as its minimum version. Version ranges
-# for unsupported versions of Python 3 are generally accurate but we do
-# not guarantee their correctness.
-
-__future__: 3.0-
-__main__: 3.0-
-_ast: 3.0-
-_bisect: 3.0-
-_bootlocale: 3.4-3.9
-_codecs: 3.0-
-_collections_abc: 3.3-
-_compat_pickle: 3.1-
-_compression: 3.5-
-_csv: 3.0-
-_ctypes: 3.0-
-_curses: 3.0-
-_decimal: 3.3-
-_dummy_thread: 3.0-3.8
-_dummy_threading: 3.0-3.8
-_heapq: 3.0-
-_imp: 3.0-
-_json: 3.0-
-_locale: 3.0-
-_lsprof: 3.0-
-_markupbase: 3.0-
-_msi: 3.0-
-_operator: 3.4-
-_osx_support: 3.0-
-_posixsubprocess: 3.2-
-_py_abc: 3.7-
-_pydecimal: 3.5-
-_random: 3.0-
-_sitebuiltins: 3.4-
-_socket: 3.0-  # present in 3.0 at runtime, but not in typeshed
-_stat: 3.4-
-_thread: 3.0-
-_threading_local: 3.0-
-_tkinter: 3.0-
-_tracemalloc: 3.4-
-_typeshed: 3.0-  # not present at runtime, only for type checking
-_warnings: 3.0-
-_weakref: 3.0-
-_weakrefset: 3.0-
-_winapi: 3.3-
-abc: 3.0-
-aifc: 3.0-3.12
-antigravity: 3.0-
-argparse: 3.0-
-array: 3.0-
-ast: 3.0-
-asynchat: 3.0-3.11
-asyncio: 3.4-
-asyncio.exceptions: 3.8-
-asyncio.format_helpers: 3.7-
-asyncio.mixins: 3.10-
-asyncio.runners: 3.7-
-asyncio.staggered: 3.8-
-asyncio.taskgroups: 3.11-
-asyncio.threads: 3.9-
-asyncio.timeouts: 3.11-
-asyncio.trsock: 3.8-
-asyncore: 3.0-3.11
-atexit: 3.0-
-audioop: 3.0-3.12
-base64: 3.0-
-bdb: 3.0-
-binascii: 3.0-
-binhex: 3.0-3.10
-bisect: 3.0-
-builtins: 3.0-
-bz2: 3.0-
-cProfile: 3.0-
-calendar: 3.0-
-cgi: 3.0-3.12
-cgitb: 3.0-3.12
-chunk: 3.0-3.12
-cmath: 3.0-
-cmd: 3.0-
-code: 3.0-
-codecs: 3.0-
-codeop: 3.0-
-collections: 3.0-
-collections.abc: 3.3-
-colorsys: 3.0-
-compileall: 3.0-
-concurrent: 3.2-
-configparser: 3.0-
-contextlib: 3.0-
-contextvars: 3.7-
-copy: 3.0-
-copyreg: 3.0-
-crypt: 3.0-3.12
-csv: 3.0-
-ctypes: 3.0-
-curses: 3.0-
-dataclasses: 3.7-
-datetime: 3.0-
-dbm: 3.0-
-decimal: 3.0-
-difflib: 3.0-
-dis: 3.0-
-distutils: 3.0-3.11
-distutils.command.bdist_msi: 3.0-3.10
-distutils.command.bdist_wininst: 3.0-3.9
-doctest: 3.0-
-dummy_threading: 3.0-3.8
-email: 3.0-
-encodings: 3.0-
-ensurepip: 3.0-
-enum: 3.4-
-errno: 3.0-
-faulthandler: 3.3-
-fcntl: 3.0-
-filecmp: 3.0-
-fileinput: 3.0-
-fnmatch: 3.0-
-formatter: 3.0-3.9
-fractions: 3.0-
-ftplib: 3.0-
-functools: 3.0-
-gc: 3.0-
-genericpath: 3.0-
-getopt: 3.0-
-getpass: 3.0-
-gettext: 3.0-
-glob: 3.0-
-graphlib: 3.9-
-grp: 3.0-
-gzip: 3.0-
-hashlib: 3.0-
-heapq: 3.0-
-hmac: 3.0-
-html: 3.0-
-http: 3.0-
-imaplib: 3.0-
-imghdr: 3.0-3.12
-imp: 3.0-3.11
-importlib: 3.0-
-importlib._abc: 3.10-
-importlib.metadata: 3.8-
-importlib.metadata._meta: 3.10-
-importlib.readers: 3.10-
-importlib.resources: 3.7-
-importlib.resources.abc: 3.11-
-importlib.resources.readers: 3.11-
-importlib.resources.simple: 3.11-
-importlib.simple: 3.11-
-inspect: 3.0-
-io: 3.0-
-ipaddress: 3.3-
-itertools: 3.0-
-json: 3.0-
-keyword: 3.0-
-lib2to3: 3.0-3.12
-linecache: 3.0-
-locale: 3.0-
-logging: 3.0-
-lzma: 3.3-
-mailbox: 3.0-
-mailcap: 3.0-3.12
-marshal: 3.0-
-math: 3.0-
-mimetypes: 3.0-
-mmap: 3.0-
-modulefinder: 3.0-
-msilib: 3.0-3.12
-msvcrt: 3.0-
-multiprocessing: 3.0-
-multiprocessing.resource_tracker: 3.8-
-multiprocessing.shared_memory: 3.8-
-netrc: 3.0-
-nis: 3.0-3.12
-nntplib: 3.0-3.12
-nt: 3.0-
-ntpath: 3.0-
-nturl2path: 3.0-
-numbers: 3.0-
-opcode: 3.0-
-operator: 3.0-
-optparse: 3.0-
-os: 3.0-
-ossaudiodev: 3.0-3.12
-parser: 3.0-3.9
-pathlib: 3.4-
-pdb: 3.0-
-pickle: 3.0-
-pickletools: 3.0-
-pipes: 3.0-3.12
-pkgutil: 3.0-
-platform: 3.0-
-plistlib: 3.0-
-poplib: 3.0-
-posix: 3.0-
-posixpath: 3.0-
-pprint: 3.0-
-profile: 3.0-
-pstats: 3.0-
-pty: 3.0-
-pwd: 3.0-
-py_compile: 3.0-
-pyclbr: 3.0-
-pydoc: 3.0-
-pydoc_data: 3.0-
-pyexpat: 3.0-
-queue: 3.0-
-quopri: 3.0-
-random: 3.0-
-re: 3.0-
-readline: 3.0-
-reprlib: 3.0-
-resource: 3.0-
-rlcompleter: 3.0-
-runpy: 3.0-
-sched: 3.0-
-secrets: 3.6-
-select: 3.0-
-selectors: 3.4-
-shelve: 3.0-
-shlex: 3.0-
-shutil: 3.0-
-signal: 3.0-
-site: 3.0-
-smtpd: 3.0-3.11
-smtplib: 3.0-
-sndhdr: 3.0-3.12
-socket: 3.0-
-socketserver: 3.0-
-spwd: 3.0-3.12
-sqlite3: 3.0-
-sre_compile: 3.0-
-sre_constants: 3.0-
-sre_parse: 3.0-
-ssl: 3.0-
-stat: 3.0-
-statistics: 3.4-
-string: 3.0-
-stringprep: 3.0-
-struct: 3.0-
-subprocess: 3.0-
-sunau: 3.0-3.12
-symbol: 3.0-3.9
-symtable: 3.0-
-sys: 3.0-
-sys._monitoring: 3.12-  # Doesn't actually exist. See comments in the stub.
-sysconfig: 3.0-
-syslog: 3.0-
-tabnanny: 3.0-
-tarfile: 3.0-
-telnetlib: 3.0-3.12
-tempfile: 3.0-
-termios: 3.0-
-textwrap: 3.0-
-this: 3.0-
-threading: 3.0-
-time: 3.0-
-timeit: 3.0-
-tkinter: 3.0-
-tkinter.tix: 3.0-3.12
-token: 3.0-
-tokenize: 3.0-
-tomllib: 3.11-
-trace: 3.0-
-traceback: 3.0-
-tracemalloc: 3.4-
-tty: 3.0-
-turtle: 3.0-
-types: 3.0-
-typing: 3.5-
-typing_extensions: 3.0-
-unicodedata: 3.0-
-unittest: 3.0-
-unittest._log: 3.9-
-unittest.async_case: 3.8-
-urllib: 3.0-
-uu: 3.0-3.12
-uuid: 3.0-
-venv: 3.3-
-warnings: 3.0-
-wave: 3.0-
-weakref: 3.0-
-webbrowser: 3.0-
-winreg: 3.0-
-winsound: 3.0-
-wsgiref: 3.0-
-wsgiref.types: 3.11-
-xdrlib: 3.0-3.12
-xml: 3.0-
-xmlrpc: 3.0-
-xxlimited: 3.2-
-zipapp: 3.5-
-zipfile: 3.0-
-zipfile._path: 3.12-
-zipimport: 3.0-
-zlib: 3.0-
-zoneinfo: 3.9-

crates/red_knot_module_resolver/vendor/typeshed/stdlib/__future__.pyi

@@ -1,36 +0,0 @@
-from typing_extensions import TypeAlias
-
-_VersionInfo: TypeAlias = tuple[int, int, int, str, int]
-
-class _Feature:
-    def __init__(self, optionalRelease: _VersionInfo, mandatoryRelease: _VersionInfo | None, compiler_flag: int) -> None: ...
-    def getOptionalRelease(self) -> _VersionInfo: ...
-    def getMandatoryRelease(self) -> _VersionInfo | None: ...
-    compiler_flag: int
-
-absolute_import: _Feature
-division: _Feature
-generators: _Feature
-nested_scopes: _Feature
-print_function: _Feature
-unicode_literals: _Feature
-with_statement: _Feature
-barry_as_FLUFL: _Feature
-generator_stop: _Feature
-annotations: _Feature
-
-all_feature_names: list[str]  # undocumented
-
-__all__ = [
-    "all_feature_names",
-    "absolute_import",
-    "division",
-    "generators",
-    "nested_scopes",
-    "print_function",
-    "unicode_literals",
-    "with_statement",
-    "barry_as_FLUFL",
-    "generator_stop",
-    "annotations",
-]

crates/red_knot_module_resolver/vendor/typeshed/stdlib/__main__.pyi

@@ -1,3 +0,0 @@
-from typing import Any
-
-def __getattr__(name: str) -> Any: ...