| #!/usr/bin/env python3 | |
| # *************************************************************************************************************************** | |
| # * Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file * | |
| # * distributed with this work for additional information regarding copyright ownership. The ASF licenses this file * | |
| # * to you under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance * | |
| # * with the License. You may obtain a copy of the License at * | |
| # * * | |
| # * http://www.apache.org/licenses/LICENSE-2.0 * | |
| # * * | |
| # * Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an * | |
| # * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the * | |
| # * specific language governing permissions and limitations under the License. * | |
| # *************************************************************************************************************************** | |
| """ | |
| Fail on HTML anchors that open a line inside fenced code blocks in the docs pages. | |
| Full docs: check-code-fences.md | |
| """ | |
| import argparse | |
| import re | |
| import sys | |
| from pathlib import Path | |
| from code_fences import iter_fences, page_files | |
| ANCHOR_RE = re.compile(r'^\s*<a\s[^>]*\bhref\s*=', re.IGNORECASE) | |
| def find_anchors(docs_root): | |
| """Return (relative path, line, text) for each anchor tag inside a fenced code block under pages/.""" | |
| findings = [] | |
| for page in page_files(docs_root): | |
| text = page.read_text(encoding='utf-8') | |
| for start, _info, body in iter_fences(text): | |
| for offset, line in enumerate(body.split('\n'), start=1): | |
| if ANCHOR_RE.search(line): | |
| findings.append((str(page.relative_to(docs_root)), start + offset, line.strip())) | |
| return findings | |
| def parse_args(argv=None): | |
| parser = argparse.ArgumentParser(description='Fail on HTML anchors inside fenced code blocks in pages/.') | |
| parser.add_argument('--docs-root', type=Path, default=Path(__file__).resolve().parent.parent, | |
| help='docs checkout to scan (default: parent of scripts/)') | |
| return parser.parse_args(argv) | |
| def main(argv=None): | |
| args = parse_args(argv) | |
| findings = find_anchors(args.docs_root.resolve()) | |
| for rel, line, text in findings: | |
| print(f"{rel}:{line}: HTML anchor in code fence: {text}") | |
| if findings: | |
| print(f"FAILED: {len(findings)} HTML anchor(s) inside code fences.") | |
| return 1 | |
| print("No HTML anchors inside code fences.") | |
| return 0 | |
| if __name__ == "__main__": | |
| sys.exit(main()) |