diff --git a/.github/workflows/check-non-re2-regex.yml b/.github/workflows/check-non-re2-regex.yml new file mode 100644 index 000000000..d4911e00f --- /dev/null +++ b/.github/workflows/check-non-re2-regex.yml @@ -0,0 +1,51 @@ +name: Detect Non-RE2 Regex + +on: + pull_request: + types: [opened, synchronize] + +jobs: + check-non-re2-regex: + runs-on: ubuntu-latest + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Get diff of backend/* + run: | + git diff --unified=0 "origin/${{ github.base_ref }}"...HEAD -- backend/ > diff.txt + + - name: Scan backend diff for non-RE2 regex + run: | + grep '^+' diff.txt | grep -v '^+++' | sed 's/^\+//' > added_lines.txt + + if [ ! -s added_lines.txt ]; then + echo "✅ No added lines in backend/ to check for regex usage." + exit 0 + fi + + regex_usage_pattern='(^|[^A-Za-z0-9_])(\/[^\/]+\/[gimsuy]*|new RegExp\()' + + # Find all added lines that contain the regex_usage_pattern. + grep -E "$regex_usage_pattern" added_lines.txt > potential_violations.txt + + if [ -s potential_violations.txt ]; then # If any lines match the regex usage pattern + # Filter out lines that also contain the string 'new RE2' + grep -v 'new RE2' potential_violations.txt > actual_violations.txt + + if [ -s actual_violations.txt ]; then # If there are lines left after filtering out 'new RE2' + echo "🚨 ERROR: Found forbidden regex pattern (raw literal '/.../' or 'new RegExp(...)') in added/modified backend code." + echo "Please use 'new RE2(...)' for all regular expressions in the backend." + echo "Offending lines:" + cat actual_violations.txt + exit 1 + else + # All lines that matched regex_usage_pattern also contained 'new RE2'. + echo "✅ All identified regex usages are correctly using 'new RE2(...)'." + fi + else + # No lines matched the regex_usage_pattern at all. + echo "✅ No raw regex literals ('/.../') or 'new RegExp(...)' usage found in added/modified backend lines." + fi