Manual Spellcheck Review & Approval #164
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Manual Spellcheck Review & Approval | |
| on: | |
| workflow_dispatch: # Runs only when manually triggered | |
| permissions: | |
| contents: write # Needed to push changes after approval | |
| jobs: | |
| spellcheck_review: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout Repository | |
| uses: actions/checkout@v4 | |
| - name: Install Dependencies | |
| run: | | |
| pip install codespell | |
| pip install fuzzywuzzy[speedup] | |
| pip install sentence-splitter | |
| - name: Verify Spellcheck Ignore List Exists | |
| run: | | |
| if [ ! -f .github/spellcheck-ignore.txt ]; then | |
| echo "Error: spellcheck-ignore.txt not found!" && exit 1 | |
| fi | |
| - name: Run Spellcheck and Generate Corrections | |
| run: | | |
| set -e # Exit on error | |
| python3 <<EOF | |
| import re | |
| import os | |
| import subprocess | |
| from fuzzywuzzy import process | |
| from sentence_splitter import SentenceSplitter | |
| # Load ignore list with correct case preservation | |
| ignore_list = {} | |
| ignore_file = ".github/spellcheck-ignore.txt" | |
| if os.path.exists(ignore_file): | |
| with open(ignore_file, "r", encoding="utf-8") as f: | |
| ignore_list = {word.strip().lower(): word.strip() for word in f.readlines()} | |
| # Context phrases to prioritize in spellcheck corrections | |
| context_phrases = { | |
| "identity provider": ["identiy provider", "identify provider"], | |
| "access token": ["access toekn", "acess token"], | |
| "user authentication": ["user authentification", "user authenthication"], | |
| "API gateway": ["API getway", "API gatway"] | |
| } | |
| # Function to check if a word is inside a Markdown link | |
| def is_inside_markdown_link(line, original): | |
| return bool(re.search(r'\[.*?\]\(.*' + re.escape(original) + r'.*\)', line)) | |
| # Function to check if a word is in a title or hint block | |
| def is_in_title_or_hint(line): | |
| return bool(re.search(r'{% (tab title|hint style)=', line)) | |
| # Run codespell and capture output | |
| result = subprocess.run([ | |
| "codespell", | |
| "--ignore-words=.github/spellcheck-ignore.txt", | |
| "--skip=.git,*.lock,*.json,*.yaml,*.yml,*.css,*.html", | |
| "--quiet-level=2" | |
| ], capture_output=True, text=True, check=False) | |
| spellcheck_output = result.stdout.strip() | |
| if not spellcheck_output: | |
| print("✅ No spelling corrections found. Exiting.") | |
| exit(0) | |
| # Save corrections for manual review | |
| os.makedirs(".github/corrections", exist_ok=True) | |
| corrections_path = ".github/corrections/corrections.txt" | |
| with open(corrections_path, "w", encoding="utf-8") as f: | |
| for line in spellcheck_output.splitlines(): | |
| match = re.match(r"(.*):(\d+): (\S+) ==> (\S+)", line) | |
| if match: | |
| file_path, line_number, original, suggestion = match.groups() | |
| # Read the full line for context | |
| with open(file_path, "r", encoding="utf-8") as file: | |
| lines = file.readlines() | |
| context_line = lines[int(line_number) - 1].strip() if 0 <= int(line_number) - 1 < len(lines) else "" | |
| # ✅ Ignore words inside Markdown links | |
| if is_inside_markdown_link(context_line, original): | |
| continue | |
| # ✅ Use case-sensitive ignore words if 90% match | |
| best_match, score = process.extractOne(original, ignore_list.keys()) if ignore_list else (None, 0) | |
| if score >= 90: | |
| suggestion = ignore_list[best_match] # Replace with exact capitalization from ignore list | |
| # ✅ Replace entire phrase if a context match is found | |
| for correct_phrase, wrong_variants in context_phrases.items(): | |
| for wrong_phrase in wrong_variants: | |
| if wrong_phrase in context_line: | |
| suggestion = correct_phrase # Replace entire phrase | |
| # ✅ Prevent punctuation modifications | |
| if suggestion.endswith((",", ".", ";")) and not original.endswith((",", ".", ";")): | |
| suggestion = suggestion.rstrip(",.;") | |
| f.write(f"File: {file_path}, Line: {line_number}\n") | |
| f.write(f"**Original:** {original}\n") | |
| f.write(f"**Suggested:** {suggestion}\n") | |
| f.write("Approve? (yes/no)\n\n") | |
| print(f"✅ {len(spellcheck_output.splitlines())} corrections generated. Review in `corrections.txt` and upload the approved version.") | |
| EOF | |
| - name: Upload Corrections for Review | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: corrections_review | |
| path: .github/corrections/corrections.txt | |
| - name: Wait for Review and Approval | |
| run: echo "⏳ Please review and approve the corrections. Re-upload `corrections.txt` when ready." | |
| apply_approved_corrections: | |
| needs: spellcheck_review | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout Repository | |
| uses: actions/checkout@v4 | |
| - name: Download Reviewed Corrections | |
| uses: actions/download-artifact@v4 | |
| with: | |
| name: corrections_review | |
| path: .github/corrections/ | |
| - name: Apply Approved Corrections | |
| run: | | |
| python3 .github/scripts/apply_corrections.py || { echo "❌ Failed to apply corrections!"; exit 1; } | |
| - name: Commit and Push Changes | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.PAT_GITHUB_ACTIONS }} | |
| run: | | |
| git config --global user.name "github-actions[bot]" | |
| git config --global user.email "github-actions[bot]@users.noreply.github.com" | |
| if git diff --quiet; then | |
| echo "No changes detected after approval. Exiting." | |
| exit 0 | |
| fi | |
| git checkout -b spellcheck-approved-fixes | |
| git add . | |
| git commit -m "✅ Spellcheck & Grammar Fixes (Manually Approved)" | |
| git push origin spellcheck-approved-fixes | |
| gh pr create --base main --head spellcheck-approved-fixes --title "Spellcheck & Grammar Fixes (Approved)" --body "This PR contains manually approved spellcheck and grammar fixes." |