verify-tinytex-patterns.yml

name: Verify TinyTeX Pattern Coverage

on:
  schedule:
    - cron: '0 2 * * *'  # Daily 2am UTC (matches TinyTeX daily release)
  workflow_dispatch:      # Manual trigger for testing

permissions:
  contents: read
  issues: write
  actions: write

jobs:
  verify:
    name: Check TinyTeX Pattern Updates
    runs-on: ubuntu-latest

    steps:
      - name: Checkout repository
        uses: actions/checkout@v6

      - name: Download and extract regex.json and hyphen.json
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          if ! gh release download daily --repo rstudio/tinytex-releases --pattern "regex.tar.gz"; then
            echo "::warning::Failed to download TinyTeX daily release - may not be published yet"
            exit 0
          fi
          tar -xzf regex.tar.gz
          # Files compared by the later steps
          PATTERN_FILES="regex.json hyphen.json"
          if [ ! -f hyphen.json ]; then
            echo "::warning::hyphen.json not found in regex.tar.gz"
            PATTERN_FILES="regex.json"
          fi
          echo "PATTERN_FILES=$PATTERN_FILES" >> "$GITHUB_ENV"
          echo "✓ Downloaded and extracted: $PATTERN_FILES"

      - name: Restore cached patterns
        id: cache-restore
        uses: actions/cache/restore@v5
        with:
          path: .cache
          key: tinytex-patterns

      - name: Compare versions
        id: compare
        run: |
          # The download step sets PATTERN_FILES only when it extracted the files
          if [ -z "${PATTERN_FILES:-}" ]; then
            echo "changed=false" >> $GITHUB_OUTPUT
            echo "first_run=false" >> $GITHUB_OUTPUT
            echo "skipped=true" >> $GITHUB_OUTPUT
            echo "::warning::No pattern files downloaded - comparison skipped"
            exit 0
          fi

          if [ ! -f .cache/regex.json ]; then
            echo "changed=false" >> $GITHUB_OUTPUT
            echo "first_run=true" >> $GITHUB_OUTPUT
            echo "⚠ No cached version (first run)"
            exit 0
          fi

          changed=false
          for f in $PATTERN_FILES; do
            if [ ! -f ".cache/$f" ]; then
              echo "✗ $f has no cached version"
              changed=true
            elif ! git diff --no-index --quiet ".cache/$f" "$f"; then
              echo "✗ Changes detected in $f"
              changed=true
            fi
          done
          echo "changed=$changed" >> $GITHUB_OUTPUT
          echo "first_run=false" >> $GITHUB_OUTPUT
          if [ "$changed" = "false" ]; then
            echo "✓ No changes detected"
          fi

      - name: Handle first run
        if: steps.compare.outputs.first_run == 'true'
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          # Get tinytex commit SHA
          TINYTEX_COMMIT=$(gh api repos/rstudio/tinytex/commits/main --jq '.sha')
          TINYTEX_SHORT=$(echo $TINYTEX_COMMIT | cut -c1-7)

          # Count patterns and categories
          PATTERN_COUNT=$(jq '[.[] | length] | add' regex.json)
          CATEGORY_COUNT=$(jq 'keys | length' regex.json)
          # A checked assignment: invalid JSON must fail the step before it is cached
          if [ -f hyphen.json ]; then
            HYPHEN_COUNT=$(jq 'length' hyphen.json)
          fi

          # Write GitHub Actions summary
          echo "## TinyTeX Pattern Baseline Established" >> "$GITHUB_STEP_SUMMARY"
          echo "" >> "$GITHUB_STEP_SUMMARY"
          echo "- **Date:** $(date +%Y-%m-%d)" >> "$GITHUB_STEP_SUMMARY"
          echo "- **TinyTeX commit:** [\`$TINYTEX_SHORT\`](https://github.com/rstudio/tinytex/commit/$TINYTEX_COMMIT)" >> "$GITHUB_STEP_SUMMARY"
          echo "- **Pattern source:** [R/latex.R](https://github.com/rstudio/tinytex/blob/$TINYTEX_COMMIT/R/latex.R)" >> "$GITHUB_STEP_SUMMARY"
          echo "- **Baseline:** $PATTERN_COUNT patterns across $CATEGORY_COUNT categories" >> "$GITHUB_STEP_SUMMARY"
          if [ -f hyphen.json ]; then
            echo "- **Hyphenation map:** $HYPHEN_COUNT names" >> "$GITHUB_STEP_SUMMARY"
          fi
          echo "- **Cache key:** tinytex-patterns" >> "$GITHUB_STEP_SUMMARY"
          echo "" >> "$GITHUB_STEP_SUMMARY"
          echo "No issue created (first run - baseline established)." >> "$GITHUB_STEP_SUMMARY"

          # Prepare cache directory
          mkdir -p .cache
          for f in $PATTERN_FILES; do
            cp "$f" ".cache/$f"
          done

          echo "✓ Baseline established - cache will be saved"

      - name: Exit if unchanged
        if: steps.compare.outputs.changed == 'false' && steps.compare.outputs.first_run == 'false' && steps.compare.outputs.skipped != 'true'
        run: |
          echo "No pattern changes detected. Cache hit - exiting."
          exit 0

      - name: Prepare readable diff
        if: steps.compare.outputs.changed == 'true'
        run: |
          # Pretty-print both versions of each file for a readable diff
          : > readable-diff.txt
          for f in $PATTERN_FILES; do
            if [ -f ".cache/$f" ]; then
              jq --sort-keys . ".cache/$f" > "old-formatted-$f"
            else
              old="/dev/null"
            fi
            jq --sort-keys . "$f" > "new-formatted-$f"
            git diff --no-index "${old:-old-formatted-$f}" "new-formatted-$f" >> readable-diff.txt || true
            unset old
          done

      - name: Create or update issue
        if: steps.compare.outputs.changed == 'true'
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          ISSUE_TITLE="TinyTeX patterns require review"
          CURRENT_DATE=$(date +%Y-%m-%d)

          # Search for existing open issue
          ISSUE_NUM=$(gh issue list \
            --label "tinytex-patterns" \
            --state open \
            --json number,title \
            --jq ".[] | select(.title == \"$ISSUE_TITLE\") | .number")

          if [ -z "$ISSUE_NUM" ]; then
            echo "No matching issue found, creating new one..."

            # Use template and replace placeholders
            sed "s|{{DATE}}|$CURRENT_DATE|g" .github/workflows/templates/tinytex-issue-body.md | \
              sed -e "/{{DIFF}}/r readable-diff.txt" -e "/{{DIFF}}/d" > issue-body.md

            gh issue create \
              --title "$ISSUE_TITLE" \
              --assignee cderv \
              --label "tinytex-patterns" \
              --body-file issue-body.md
          else
            echo "Found existing issue #$ISSUE_NUM, adding comment..."

            # Use template and replace placeholders
            sed "s|{{DATE}}|$CURRENT_DATE|g" .github/workflows/templates/tinytex-comment-body.md | \
              sed -e "/{{DIFF}}/r readable-diff.txt" -e "/{{DIFF}}/d" > comment-body.md

            gh issue comment "$ISSUE_NUM" --body-file comment-body.md
          fi

      - name: Update cache with new patterns
        if: steps.compare.outputs.changed == 'true'
        run: |
          mkdir -p .cache
          for f in $PATTERN_FILES; do
            cp "$f" ".cache/$f"
          done
          echo "✓ Cache updated with new patterns"

      - name: Delete old cache
        if: steps.compare.outputs.changed == 'true'
        continue-on-error: true
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          gh cache delete tinytex-patterns || echo "No existing cache to delete"

      - name: Save new cache
        if: steps.compare.outputs.changed == 'true' || steps.compare.outputs.first_run == 'true'
        uses: actions/cache/save@v5
        with:
          path: .cache
          key: tinytex-patterns

      - name: Summary
        if: always()
        run: |
          if [ "${{ steps.compare.outputs.skipped }}" == "true" ]; then
            echo "⚠ Download failed - comparison skipped"
          elif [ "${{ steps.compare.outputs.first_run }}" == "true" ]; then
            echo "✓ Baseline established - cache created"
          elif [ "${{ steps.compare.outputs.changed }}" == "true" ]; then
            echo "✗ Pattern changes detected - issue created/updated"
          else
            echo "✓ No pattern changes - cache hit"
          fi