Move change detection to separate workflow in CI (#122336)

2 files changed, 163 insertions, 118 deletions

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 6568b50..4f3995a 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -1,8 +1,5 @@
 name: Tests
 
-# gh-84728: "paths-ignore" is not used to skip documentation-only PRs, because
-# it prevents to mark a job as mandatory. A PR cannot be merged if a job is
-# mandatory but not scheduled because of "paths-ignore".
 on:
   workflow_dispatch:
   push:
@@ -23,121 +20,19 @@ concurrency:
 
 jobs:
   check_source:
-    name: 'Check for source changes'
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    outputs:
-      # Some of the referenced steps set outputs conditionally and there may be
-      # cases when referencing them evaluates to empty strings. It is nice to
-      # work with proper booleans so they have to be evaluated through JSON
-      # conversion in the expressions. However, empty strings used like that
-      # may trigger all sorts of undefined and hard-to-debug behaviors in
-      # GitHub Actions CI/CD. To help with this, all of the outputs set here
-      # that are meant to be used as boolean flags (and not arbitrary strings),
-      # MUST have fallbacks with default values set. A common pattern would be
-      # to add ` || false` to all such expressions here, in the output
-      # definitions. They can then later be safely used through the following
-      # idiom in job conditionals and other expressions. Here's some examples:
-      #
-      #   if: fromJSON(needs.check_source.outputs.run-docs)
-      #
-      #   ${{
-      #        fromJSON(needs.check_source.outputs.run_tests)
-      #        && 'truthy-branch'
-      #        || 'falsy-branch'
-      #   }}
-      #
-      run-docs: ${{ steps.docs-changes.outputs.run-docs || false }}
-      run-win-msi: ${{ steps.win-msi-changes.outputs.run-win-msi || false }}
-      run_tests: ${{ steps.check.outputs.run_tests || false }}
-      run_hypothesis: ${{ steps.check.outputs.run_hypothesis || false }}
-      run_cifuzz: ${{ steps.check.outputs.run_cifuzz || false }}
-      config_hash: ${{ steps.config_hash.outputs.hash }}  # str
-    steps:
-      - uses: actions/checkout@v4
-      - name: Check for source changes
-        id: check
-        run: |
-          if [ -z "$GITHUB_BASE_REF" ]; then
-            echo "run_tests=true" >> $GITHUB_OUTPUT
-          else
-            git fetch origin $GITHUB_BASE_REF --depth=1
-            # git diff "origin/$GITHUB_BASE_REF..." (3 dots) may be more
-            # reliable than git diff "origin/$GITHUB_BASE_REF.." (2 dots),
-            # but it requires to download more commits (this job uses
-            # "git fetch --depth=1").
-            #
-            # git diff "origin/$GITHUB_BASE_REF..." (3 dots) works with Git
-            # 2.26, but Git 2.28 is stricter and fails with "no merge base".
-            #
-            # git diff "origin/$GITHUB_BASE_REF.." (2 dots) should be enough on
-            # GitHub, since GitHub starts by merging origin/$GITHUB_BASE_REF
-            # into the PR branch anyway.
-            #
-            # https://github.com/python/core-workflow/issues/373
-            git diff --name-only origin/$GITHUB_BASE_REF.. | grep -qvE '(\.rst$|^Doc|^Misc|^\.pre-commit-config\.yaml$|\.ruff\.toml$|\.md$|mypy\.ini$)' && echo "run_tests=true" >> $GITHUB_OUTPUT || true
-          fi
-
-          # Check if we should run hypothesis tests
-          GIT_BRANCH=${GITHUB_BASE_REF:-${GITHUB_REF#refs/heads/}}
-          echo $GIT_BRANCH
-          if $(echo "$GIT_BRANCH" | grep -q -w '3\.\(8\|9\|10\|11\)'); then
-            echo "Branch too old for hypothesis tests"
-            echo "run_hypothesis=false" >> $GITHUB_OUTPUT
-          else
-            echo "Run hypothesis tests"
-            echo "run_hypothesis=true" >> $GITHUB_OUTPUT
-          fi
-
-          # oss-fuzz maintains a configuration for fuzzing the main branch of
-          # CPython, so CIFuzz should be run only for code that is likely to be
-          # merged into the main branch; compatibility with older branches may
-          # be broken.
-          FUZZ_RELEVANT_FILES='(\.c$|\.h$|\.cpp$|^configure$|^\.github/workflows/build\.yml$|^Modules/_xxtestfuzz)'
-          if [ "$GITHUB_BASE_REF" = "main" ] && [ "$(git diff --name-only origin/$GITHUB_BASE_REF.. | grep -qE $FUZZ_RELEVANT_FILES; echo $?)" -eq 0 ]; then
-            # The tests are pretty slow so they are executed only for PRs
-            # changing relevant files.
-            echo "Run CIFuzz tests"
-            echo "run_cifuzz=true" >> $GITHUB_OUTPUT
-          else
-            echo "Branch too old for CIFuzz tests; or no C files were changed"
-            echo "run_cifuzz=false" >> $GITHUB_OUTPUT
-          fi
-      - name: Compute hash for config cache key
-        id: config_hash
-        run: |
-          echo "hash=${{ hashFiles('configure', 'configure.ac', '.github/workflows/build.yml') }}" >> $GITHUB_OUTPUT
-      - name: Get a list of the changed documentation-related files
-        if: github.event_name == 'pull_request'
-        id: changed-docs-files
-        uses: Ana06/get-changed-files@v2.3.0
-        with:
-          filter: |
-            Doc/**
-            Misc/**
-            .github/workflows/reusable-docs.yml
-          format: csv  # works for paths with spaces
-      - name: Check for docs changes
-        if: >-
-          github.event_name == 'pull_request'
-          && steps.changed-docs-files.outputs.added_modified_renamed != ''
-        id: docs-changes
-        run: |
-          echo "run-docs=true" >> "${GITHUB_OUTPUT}"
-      - name: Get a list of the MSI installer-related files
-        id: changed-win-msi-files
-        uses: Ana06/get-changed-files@v2.3.0
-        with:
-          filter: |
-            Tools/msi/**
-            .github/workflows/reusable-windows-msi.yml
-          format: csv  # works for paths with spaces
-      - name: Check for changes in MSI installer-related files
-        if: >-
-          steps.changed-win-msi-files.outputs.added_modified_renamed != ''
-        id: win-msi-changes
-        run: |
-          echo "run-win-msi=true" >> "${GITHUB_OUTPUT}"
+    name: Change detection
+    # To use boolean outputs from this job, parse them as JSON.
+    # Here's some examples:
+    #
+    #   if: fromJSON(needs.check_source.outputs.run-docs)
+    #
+    #   ${{
+    #        fromJSON(needs.check_source.outputs.run_tests)
+    #        && 'truthy-branch'
+    #        || 'falsy-branch'
+    #   }}
+    #
+    uses: ./.github/workflows/reusable-change-detection.yml
 
   check-docs:
     name: Docs
diff --git a/.github/workflows/reusable-change-detection.yml b/.github/workflows/reusable-change-detection.yml
new file mode 100644
index 0000000..25c789d
--- /dev/null
+++ b/.github/workflows/reusable-change-detection.yml
@@ -0,0 +1,150 @@
+---
+
+name: Change detection
+
+on:  # yamllint disable-line rule:truthy
+  workflow_call:
+    outputs:
+      # Some of the referenced steps set outputs conditionally and there may be
+      # cases when referencing them evaluates to empty strings. It is nice to
+      # work with proper booleans so they have to be evaluated through JSON
+      # conversion in the expressions. However, empty strings used like that
+      # may trigger all sorts of undefined and hard-to-debug behaviors in
+      # GitHub Actions CI/CD. To help with this, all of the outputs set here
+      # that are meant to be used as boolean flags (and not arbitrary strings),
+      # MUST have fallbacks with default values set. A common pattern would be
+      # to add ` || false` to all such expressions here, in the output
+      # definitions. They can then later be safely used through the following
+      # idiom in job conditionals and other expressions. Here's some examples:
+      #
+      #   if: fromJSON(needs.change-detection.outputs.run-docs)
+      #
+      #   ${{
+      #        fromJSON(needs.change-detection.outputs.run-tests)
+      #        && 'truthy-branch'
+      #        || 'falsy-branch'
+      #   }}
+      #
+      config_hash:
+        description: Config hash value for use in cache keys
+        value: ${{ jobs.compute-changes.outputs.config-hash }}  # str
+      run-docs:
+        description: Whether to build the docs
+        value: ${{ jobs.compute-changes.outputs.run-docs || false }}  # bool
+      run_tests:
+        description: Whether to run the regular tests
+        value: ${{ jobs.compute-changes.outputs.run-tests || false }}  # bool
+      run-win-msi:
+        description: Whether to run the MSI installer smoke tests
+        value: >-  # bool
+          ${{ jobs.compute-changes.outputs.run-win-msi || false }}
+      run_hypothesis:
+        description: Whether to run the Hypothesis tests
+        value: >-  # bool
+          ${{ jobs.compute-changes.outputs.run-hypothesis || false }}
+      run_cifuzz:
+        description: Whether to run the CIFuzz job
+        value: >-  # bool
+          ${{ jobs.compute-changes.outputs.run-cifuzz || false }}
+
+jobs:
+  compute-changes:
+    name: Compute changed files
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    outputs:
+      config-hash: ${{ steps.config-hash.outputs.hash }}
+      run-cifuzz: ${{ steps.check.outputs.run-cifuzz }}
+      run-docs: ${{ steps.docs-changes.outputs.run-docs }}
+      run-hypothesis: ${{ steps.check.outputs.run-hypothesis }}
+      run-tests: ${{ steps.check.outputs.run-tests }}
+      run-win-msi: ${{ steps.win-msi-changes.outputs.run-win-msi }}
+    steps:
+    - run: >-
+        echo '${{ github.event_name }}'
+    - uses: actions/checkout@v4
+    - name: Check for source changes
+      id: check
+      run: |
+        if [ -z "$GITHUB_BASE_REF" ]; then
+          echo "run-tests=true" >> $GITHUB_OUTPUT
+        else
+          git fetch origin $GITHUB_BASE_REF --depth=1
+          # git diff "origin/$GITHUB_BASE_REF..." (3 dots) may be more
+          # reliable than git diff "origin/$GITHUB_BASE_REF.." (2 dots),
+          # but it requires to download more commits (this job uses
+          # "git fetch --depth=1").
+          #
+          # git diff "origin/$GITHUB_BASE_REF..." (3 dots) works with Git
+          # 2.26, but Git 2.28 is stricter and fails with "no merge base".
+          #
+          # git diff "origin/$GITHUB_BASE_REF.." (2 dots) should be enough on
+          # GitHub, since GitHub starts by merging origin/$GITHUB_BASE_REF
+          # into the PR branch anyway.
+          #
+          # https://github.com/python/core-workflow/issues/373
+          git diff --name-only origin/$GITHUB_BASE_REF.. | grep -qvE '(\.rst$|^Doc|^Misc|^\.pre-commit-config\.yaml$|\.ruff\.toml$|\.md$|mypy\.ini$)' && echo "run-tests=true" >> $GITHUB_OUTPUT || true
+        fi
+
+        # Check if we should run hypothesis tests
+        GIT_BRANCH=${GITHUB_BASE_REF:-${GITHUB_REF#refs/heads/}}
+        echo $GIT_BRANCH
+        if $(echo "$GIT_BRANCH" | grep -q -w '3\.\(8\|9\|10\|11\)'); then
+          echo "Branch too old for hypothesis tests"
+          echo "run-hypothesis=false" >> $GITHUB_OUTPUT
+        else
+          echo "Run hypothesis tests"
+          echo "run-hypothesis=true" >> $GITHUB_OUTPUT
+        fi
+
+        # oss-fuzz maintains a configuration for fuzzing the main branch of
+        # CPython, so CIFuzz should be run only for code that is likely to be
+        # merged into the main branch; compatibility with older branches may
+        # be broken.
+        FUZZ_RELEVANT_FILES='(\.c$|\.h$|\.cpp$|^configure$|^\.github/workflows/build\.yml$|^Modules/_xxtestfuzz)'
+        if [ "$GITHUB_BASE_REF" = "main" ] && [ "$(git diff --name-only origin/$GITHUB_BASE_REF.. | grep -qE $FUZZ_RELEVANT_FILES; echo $?)" -eq 0 ]; then
+          # The tests are pretty slow so they are executed only for PRs
+          # changing relevant files.
+          echo "Run CIFuzz tests"
+          echo "run-cifuzz=true" >> $GITHUB_OUTPUT
+        else
+          echo "Branch too old for CIFuzz tests; or no C files were changed"
+          echo "run-cifuzz=false" >> $GITHUB_OUTPUT
+        fi
+    - name: Compute hash for config cache key
+      id: config-hash
+      run: |
+        echo "hash=${{ hashFiles('configure', 'configure.ac', '.github/workflows/build.yml') }}" >> $GITHUB_OUTPUT
+    - name: Get a list of the changed documentation-related files
+      if: github.event_name == 'pull_request'
+      id: changed-docs-files
+      uses: Ana06/get-changed-files@v2.3.0
+      with:
+        filter: |
+          Doc/**
+          Misc/**
+          .github/workflows/reusable-docs.yml
+        format: csv  # works for paths with spaces
+    - name: Check for docs changes
+      if: >-
+        github.event_name == 'pull_request'
+        && steps.changed-docs-files.outputs.added_modified_renamed != ''
+      id: docs-changes
+      run: |
+        echo "run-docs=true" >> "${GITHUB_OUTPUT}"
+    - name: Get a list of the MSI installer-related files
+      id: changed-win-msi-files
+      uses: Ana06/get-changed-files@v2.3.0
+      with:
+        filter: |
+          Tools/msi/**
+          .github/workflows/reusable-windows-msi.yml
+        format: csv  # works for paths with spaces
+    - name: Check for changes in MSI installer-related files
+      if: >-
+        steps.changed-win-msi-files.outputs.added_modified_renamed != ''
+      id: win-msi-changes
+      run: |
+        echo "run-win-msi=true" >> "${GITHUB_OUTPUT}"
+
+...