Improve SMILEidx for PUFA molecules #95
This file contains hidden or 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: AutocompleteMetadata | |
| on: | |
| pull_request_target: | |
| paths: | |
| - 'Molecules/membrane/**/metadata.yaml' | |
| - 'Molecules/solution/**/metadata.yaml' | |
| permissions: | |
| contents: read | |
| pull-requests: write | |
| jobs: | |
| add-metadata: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout BilayerData | |
| uses: actions/checkout@v6 | |
| with: | |
| repository: ${{ github.event.pull_request.head.repo.full_name }} | |
| ref: ${{ github.event.pull_request.head.ref }} | |
| persist-credentials: false | |
| - name: Clone Databank and install | |
| run: | | |
| git clone --depth 1 https://github.com/NMRlipids/FAIRMD_lipids.git "$RUNNER_TEMP/Databank" | |
| pip install "$RUNNER_TEMP/Databank" | |
| - name: Install the gh cli | |
| uses: ksivamuthu/actions-setup-gh-cli@v3 | |
| with: | |
| version: 2.83.0 | |
| - name: Find changed metadata.yaml files | |
| id: files | |
| env: | |
| GH_TOKEN: ${{ github.token }} | |
| run: | | |
| changed_files=$(gh api --paginate \ | |
| "repos/${{ github.repository }}/pulls/${{ github.event.pull_request.number }}/files" \ | |
| --jq '.[] | select(.status != "removed") | .filename' \ | |
| | grep -E '^Molecules/(membrane|solution)/[^/]+/metadata\.yaml$' || true) | |
| { | |
| echo "changed_files<<EOF" | |
| echo "$changed_files" | |
| echo "EOF" | |
| } >> "$GITHUB_OUTPUT" | |
| echo "Changed files:" | |
| echo "$changed_files" | |
| - name: Run AddMetadata.py and create suggestions | |
| if: steps.files.outputs.changed_files != '' | |
| env: | |
| CHANGED_FILES: ${{ steps.files.outputs.changed_files }} | |
| run: | | |
| printf '%s\n' "$CHANGED_FILES" | while IFS= read -r f; do | |
| [ -n "$f" ] && python "$RUNNER_TEMP/Databank/developer/autocomplete_metadata.py" "$f" | |
| done | |
| - name: Suggest changes on PR | |
| if: steps.files.outputs.changed_files != '' | |
| env: | |
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| PR_NUMBER: ${{ github.event.pull_request.number }} | |
| HEAD_SHA: ${{ github.event.pull_request.head.sha }} | |
| run: | | |
| python3 << 'PYEOF' | |
| import subprocess, json, re, os, sys | |
| repo = os.environ['GITHUB_REPOSITORY'] | |
| pr_number = os.environ['PR_NUMBER'] | |
| head_sha = os.environ['HEAD_SHA'] | |
| diff_output = subprocess.check_output(['git', 'diff', 'HEAD', '--unified=0'], text=True) | |
| print('=== git diff HEAD ===') | |
| print(diff_output or '(empty — autocomplete made no changes)') | |
| def head_line(filepath, line_num): | |
| out = subprocess.check_output(['git', 'show', f'HEAD:{filepath}'], text=True) | |
| lines = out.splitlines(keepends=True) | |
| return lines[line_num - 1] if 0 < line_num <= len(lines) else '' | |
| comments = [] | |
| current_file = None | |
| current_old_start = 0 | |
| minus_lines = [] | |
| plus_lines = [] | |
| def flush_hunk(): | |
| if current_file is None or (not minus_lines and not plus_lines): | |
| return | |
| if not minus_lines: | |
| # Pure addition after line current_old_start — anchor to that line | |
| anchor_num = max(current_old_start, 1) | |
| anchor = head_line(current_file, anchor_num) | |
| body = '```suggestion\n' + anchor + ''.join(plus_lines) + '```' | |
| comment = {'path': current_file, 'body': body, 'side': 'RIGHT', 'line': anchor_num} | |
| else: | |
| start_line = current_old_start | |
| end_line = current_old_start + len(minus_lines) - 1 | |
| body = '```suggestion\n' + ''.join(plus_lines) + '```' | |
| comment = {'path': current_file, 'body': body, 'side': 'RIGHT', 'line': end_line} | |
| if start_line != end_line: | |
| comment['start_line'] = start_line | |
| comment['start_side'] = 'RIGHT' | |
| print(f' hunk -> {current_file}:{comment["line"]} ({len(minus_lines)} removed, {len(plus_lines)} added)') | |
| comments.append(comment) | |
| for line in diff_output.splitlines(keepends=True): | |
| if line.startswith('diff --git'): | |
| flush_hunk(); minus_lines = []; plus_lines = [] | |
| elif line.startswith('+++ '): | |
| current_file = line[6:].rstrip('\n') | |
| elif line.startswith('@@ '): | |
| flush_hunk(); minus_lines = []; plus_lines = [] | |
| m = re.match(r'@@ -(\d+)(?:,\d+)? ', line) | |
| if m: | |
| current_old_start = int(m.group(1)) | |
| elif line.startswith('-') and not line.startswith('---'): | |
| minus_lines.append(line[1:]) | |
| elif line.startswith('+') and not line.startswith('+++'): | |
| plus_lines.append(line[1:]) | |
| flush_hunk() | |
| print(f'Built {len(comments)} suggestion(s)') | |
| if not comments: | |
| print('No changes to suggest'); sys.exit(0) | |
| review = {'commit_id': head_sha, 'body': '', 'event': 'COMMENT', 'comments': comments} | |
| result = subprocess.run( | |
| ['gh', 'api', f'repos/{repo}/pulls/{pr_number}/reviews', | |
| '--method', 'POST', '--input', '-'], | |
| input=json.dumps(review), text=True, capture_output=True | |
| ) | |
| print('API response:', result.stdout[:300]) | |
| if result.stderr: | |
| print('API error:', result.stderr[:300], file=sys.stderr) | |
| if result.returncode != 0: | |
| sys.exit(1) | |
| print(f'Posted {len(comments)} inline suggestion(s)') | |
| PYEOF |