feat: Add translation tag checker for issue #1102

.github/workflows/pre-release.yml

@@ -51,6 +51,15 @@
               token: ${{ secrets.QLTY_COVERAGE_TOKEN }}
               total-parts-count: 3
               files: converter/coverage/cobertura.xml
+          # Check translation tags
+          - name: Check translation tags
+            id: translation_check
+            run: |
+              pipenv run python scripts/check_translations.py > translation_check_report.md || echo "Translation issues found, continuing..."
+              # Read the report content and save it as an output
+              echo "TRANSLATION_REPORT<<EOF" >> $GITHUB_ENV
+              cat translation_check_report.md >> $GITHUB_ENV
+              echo "EOF" >> $GITHUB_ENV
           - name: Generate new output files
             run: |
               #
@@ -121,6 +130,21 @@
 
               cp output/owasp_cornucopia_webapp_3.0_cards_bridge_en.idml output/owasp_cornucopia_webapp_3.0_cards_bridge_qr_en.idml output/owasp_cornucopia_webapp_3.0_cards_tarot_en.idml output/owasp_cornucopia_webapp_3.0_cards_tarot_qr_en.idml output/owasp_cornucopia_webapp_3.0_leaflet_bridge_en.idml output/owasp_cornucopia_webapp_3.0_leaflet_tarot_en.idml output/cornucopia_webapp/
               zip -r output/owasp_cornucopia_webapp_3.0_en.zip output/cornucopia_webapp/Links/* output/cornucopia_webapp/Fonts/* output/cornucopia_webapp/owasp_cornucopia_webapp_3.0_cards_bridge_en.idml output/cornucopia_webapp/owasp_cornucopia_webapp_3.0_cards_bridge_qr_en.idml output/cornucopia_webapp/owasp_cornucopia_webapp_3.0_cards_tarot_en.idml output/cornucopia_webapp/owasp_cornucopia_webapp_3.0_cards_tarot_qr_en.idml output/cornucopia_webapp/owasp_cornucopia_webapp_3.0_leaflet_bridge_en.idml output/cornucopia_webapp/owasp_cornucopia_webapp_3.0_leaflet_tarot_en.idml ./resources/templates/owasp_cornucopia_webapp_scoresheet.pdf
+          - name: Prepare release body with translation report
+            id: prepare_release
+            run: |
+              # Read the translation report
+              TRANSLATION_REPORT=$(cat translation_check_report.md)
+              # Create a combined release body
+              cat > release_body.md << 'EOF'
+              ## OWASP Cornucopia Pre-Release
+
+              This is an automated pre-release build from the latest master branch.
+
+              ---
+
+              EOF
+              cat translation_check_report.md >> release_body.md
           - name: Delete existing release and tag
             run: gh release delete "pre-release" --cleanup-tag -y
             env:
@@ -133,6 +157,7 @@
               tag_name: pre-release
               prerelease: true
               name: Latest pre-release
+              body_path: release_body.md
               files: |
                 CHANGELOG.md
                 LICENSE.md

.github/workflows/run-tests-generate-output.yaml

@@ -61,6 +61,16 @@ jobs:
           token: ${{ secrets.QLTY_COVERAGE_TOKEN }}
           total-parts-count: 3
           files: converter/coverage/cobertura.xml
+      - name: Check translation tags
+        run: |
+          pipenv run python scripts/check_translations.py > translation_check_report.md || echo "Translation issues found, continuing..."
+      - name: Upload translation check report
+        if: always()
+        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5.0.0
+        with:
+          retention-days: 5
+          name: translation-check-report.${{ github.sha }}.md
+          path: translation_check_report.md
       - name: Generate new output files
         run: |
           #
@@ -160,23 +170,44 @@ jobs:
       issues: write
     needs: uploadoutputfiles
     steps:
+      - name: Checkout repository
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+      - name: Download translation check report
+        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
+        with:
+          name: translation-check-report.${{ github.sha }}.md
+          path: .
       - uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
         env:
           PR_NUMBER: ${{ github.event.number }}
-          PR_NOTES: |
-            [badge]: https://img.shields.io/badge/Build-Success!-3fb950?logo=github&style=for-the-badge
+          ARTIFACT_URL: ${{needs.uploadoutputfiles.outputs.artifact-url}}
+        with:
+          script: |
+            const fs = require('fs');
+            let translationReport = '';
+            try {
+              translationReport = fs.readFileSync('translation_check_report.md', 'utf8');
+            } catch (error) {
+              translationReport = 'Translation check report not found.';
+            }
+
+            const prNotes = `[badge]: https://img.shields.io/badge/Build-Success!-3fb950?logo=github&style=for-the-badge
 
             ## Build artifacts:
 
             | Name | Link |
             |------|------|
             | Output files | [cornucopia-build-files.${{ github.event.pull_request.head.sha }}.zip](${{needs.uploadoutputfiles.outputs.artifact-url}}) |
 
-        with:
-          script: |
+            ---
+
+            ${translationReport}`;
+
             github.rest.issues.createComment({
               issue_number: process.env.PR_NUMBER,
               owner: context.repo.owner,
               repo: context.repo.repo,
-              body: process.env.PR_NOTES
+              body: prNotes
             })

scripts/check_translations.py

@@ -0,0 +1,238 @@
+"""
+Translation Tag Checker for OWASP Cornucopia
+
+This script checks that translation files have the same T0xxx tags as the English version.
+It detects:
+- Missing tags in translations
+- Untranslated tags (text identical to English)
+- Empty tag values
+"""
+
+import sys
+import yaml
+from pathlib import Path
+from typing import Dict, List, Tuple, Any
+from collections import defaultdict
+
+
+class TranslationChecker:
+    """Check translations for missing, untranslated, or empty tags."""
+
+    def __init__(self, source_dir: Path):
+        self.source_dir = source_dir
+        self.results: Dict[str, Dict[str, Any]] = defaultdict(lambda: defaultdict(dict))
+
+    def extract_tags(self, yaml_file: Path) -> Dict[str, str]:
+        """Extract T0xxx tags and their text from a YAML file."""
+        tags = {}
+        try:
+            with open(yaml_file, "r", encoding="utf-8") as f:
+                data = yaml.safe_load(f)
+
+            # Extract tags from paragraphs.sentences
+            if data and "paragraphs" in data:
+                for paragraph in data["paragraphs"]:
+                    if "sentences" in paragraph:
+                        for sentence in paragraph["sentences"]:
+                            tag_id = sentence.get("id", "")
+                            if tag_id.startswith("T0"):
+                                tags[tag_id] = sentence.get("text", "")
+
+        except Exception as e:
+            print(f"Error reading {yaml_file}: {e}", file=sys.stderr)
+
+        return tags
+
+    def get_file_groups(self) -> Dict[str, List[Path]]:
+        """Group YAML files by their base name (e.g., webapp-cards-2.2)."""
+        file_groups = defaultdict(list)
+
+        for yaml_file in self.source_dir.glob("*-*.yaml"):
+            # Skip archived files
+            if "archive" in str(yaml_file):
+                continue
+
+            # Extract base name and language
+            # Format: {edition}-{component}-{version}-{lang}.yaml
+            parts = yaml_file.stem.split("-")
+            if len(parts) >= 3:
+                # Find language code (usually last part or second to last)
+                lang = parts[-1]
+                base_name = "-".join(parts[:-1])
+
+                # Only process card files with language codes
+                if "cards" in base_name and len(lang) == 2:
+                    file_groups[base_name].append(yaml_file)
+
+        return file_groups
+
+    def _separate_english_and_translations(self, files: List[Path]) -> Tuple[Path | None, List[Path]]:
+        """Separate English reference file from translation files."""
+        english_file = None
+        translation_files = []
+
+        for f in files:
+            lang = f.stem.split("-")[-1]
+            if lang == "en":
+                english_file = f
+            else:
+                translation_files.append(f)
+
+        return english_file, translation_files
+
+    def _check_translation_tags(self, english_tags: Dict[str, str], trans_tags: Dict[str, str]) -> Dict[str, Any]:
+        """Check translation tags against English reference."""
+        missing = []
+        untranslated = []
+        empty = []
+
+        for tag_id, eng_text in english_tags.items():
+            if tag_id not in trans_tags:
+                missing.append(tag_id)
+            elif not trans_tags[tag_id]:
+                empty.append(tag_id)
+            elif trans_tags[tag_id] == eng_text:
+                untranslated.append(tag_id)
+
+        return {
+            "missing": sorted(missing),
+            "untranslated": sorted(untranslated),
+            "empty": sorted(empty),
+        }
+
+    def check_translations(self) -> Dict[str, Dict[str, Any]]:
+        """
+        Check all translation files against English versions.
+
+        Returns:
+            Dict with structure:
+            {
+                'base_name': {
+                    'language': {
+                        'missing': ['T00145', ...],
+                        'untranslated': ['T00100', ...],
+                        'empty': ['T00200', ...]
+                    }
+                }
+            }
+        """
+        file_groups = self.get_file_groups()
+
+        for base_name, files in file_groups.items():
+            english_file, translation_files = self._separate_english_and_translations(files)
+
+            if not english_file:
+                print(f"Warning: No English file found for {base_name}", file=sys.stderr)
+                continue
+
+            english_tags = self.extract_tags(english_file)
+            if not english_tags:
+                continue
+
+            for trans_file in translation_files:
+                lang = trans_file.stem.split("-")[-1]
+                trans_tags = self.extract_tags(trans_file)
+                issues = self._check_translation_tags(english_tags, trans_tags)
+
+                if any(issues.values()):
+                    issues["file"] = str(trans_file.name)
+                    self.results[base_name][lang] = issues
+
+        return dict(self.results)
+
+    def generate_markdown_report(self) -> str:
+        """Generate a Markdown report of translation issues."""
+        report_lines = []
+
+        if not self.results:
+            report_lines.append("# Translation Check Report\n")
+            report_lines.append("✅ All existing translations have been completed.\n")
+            return "\n".join(report_lines)
+
+        report_lines.append("# Translation Check Report\n")
+        report_lines.append("The following sentences/tags have issues in the translations:\n")
+
+        # Language name mapping
+        lang_names = {
+            "es": "Spanish",
+            "fr": "French",
+            "hu": "Hungarian",
+            "it": "Italian",
+            "nl": "Dutch",
+            "no-nb": "Norwegian",
+            "pt-br": "Portuguese (Brazil)",
+            "pt-pt": "Portuguese (Portugal)",
+            "ru": "Russian",
+        }
+
+        for base_name in sorted(self.results.keys()):
+            languages = self.results[base_name]
+
+            for lang in sorted(languages.keys()):
+                lang_name = lang_names.get(lang, lang)
+                issues = languages[lang]
+                filename = issues.get("file", "")
+
+                report_lines.append(f"\n## {lang_name}\n")
+                report_lines.append(f"**File:** `{filename}`\n")
+
+                if issues["missing"]:
+                    report_lines.append("### Missing Tags\n")
+                    report_lines.append(
+                        "The following tags are present in the English version but missing in this translation:\n"
+                    )
+                    tags_str = ", ".join(issues["missing"])
+                    report_lines.append(f"{tags_str}\n")
+
+                if issues["untranslated"]:
+                    report_lines.append("### Untranslated Tags\n")
+                    report_lines.append("The following tags have identical text to English (not translated):\n")
+                    tags_str = ", ".join(issues["untranslated"])
+                    report_lines.append(f"{tags_str}\n")
+
+                if issues["empty"]:
+                    report_lines.append("### Empty Tags\n")
+                    report_lines.append("The following tags are empty:\n")
+                    tags_str = ", ".join(issues["empty"])
+                    report_lines.append(f"{tags_str}\n")
+
+        return "\n".join(report_lines)
+
+
+def main() -> None:
+    """Main entry point for the translation checker."""
+    # Determine source directory
+    script_dir = Path(__file__).parent
+    base_dir = script_dir.parent
+    source_dir = base_dir / "source"
+
+    if not source_dir.exists():
+        print(f"Error: Source directory not found: {source_dir}", file=sys.stderr)
+        sys.exit(1)
+
+    # Run checker
+    checker = TranslationChecker(source_dir)
+    results = checker.check_translations()
+
+    # Generate report
+    report = checker.generate_markdown_report()
+
+    # Output report
+    print(report)
+
+    # Write to file
+    output_file = base_dir / "translation_check_report.md"
+    with open(output_file, "w", encoding="utf-8") as f:
+        f.write(report)
+
+    print(f"\n---\nReport written to: {output_file}", file=sys.stderr)
+
+    # Exit with error code if issues found
+    if results:
+        sys.exit(1)
+    else:
+        sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()