Spaces:
Running
Running
| """Render public Markdown originals to static HTML; --check detects stale pages.""" | |
| import argparse | |
| import html | |
| import re | |
| from pathlib import Path | |
| import markdown2 | |
| ROOT = Path(__file__).resolve().parents[1] | |
| PAGES = {'INSTALL.md': 'install.html', 'RELEASE_NOTES.md': 'release-notes.html', | |
| 'THIRD_PARTY_NOTICES.md': 'licenses.html', 'LICENSE': 'license.html', | |
| 'BENCHMARKS.md': 'benchmarks.html', 'CONNECTORS.md': 'connectors.html', 'docs/legal/PUBLIC_SCOPE.md': 'legal-scope.html'} | |
| def render(name): | |
| source = (ROOT/name).read_text(encoding='utf-8') | |
| # Strip fence language hints so optional Pygments cannot change generated bytes. | |
| source = re.sub(r'^```[^\n]+$', '```', source, flags=re.MULTILINE) | |
| title = source.splitlines()[0].lstrip('# ').strip() if name != 'LICENSE' else 'Application license — AGPL-3.0-only' | |
| body = '<pre>'+html.escape(source)+'</pre>' if name == 'LICENSE' else markdown2.markdown(source, extras=['fenced-code-blocks', 'tables'], safe_mode='escape') | |
| for old, new in PAGES.items(): | |
| body = body.replace('href="'+old+'"', 'href="'+new+'"') | |
| return ('<!doctype html>\n<html lang="en"><head><meta charset="utf-8">' | |
| '<meta name="viewport" content="width=device-width,initial-scale=1"><title>'+html.escape(title)+'</title>' | |
| '<style>body{margin:0;background:#f5f4ef;color:#18342f;font:17px/1.65 system-ui,sans-serif}' | |
| 'main{max-width:900px;margin:auto;padding:35px 24px}a{color:#215947}h1{line-height:1.2}' | |
| 'pre{background:#e8ebe3;padding:18px;overflow-x:auto;white-space:pre-wrap;overflow-wrap:anywhere}' | |
| 'code{font-size:.88em}table{border-collapse:collapse;display:block;overflow:auto}' | |
| 'td,th{padding:9px;border:1px solid #becbbf;text-align:left}nav{margin-bottom:32px}' | |
| '</style></head><body><main><nav><a href="index.html">Book OCR Studio</a> · ' | |
| '<a href="install.html">Install</a> · <a href="benchmarks.html">Comparison</a> · ' | |
| '<a href="release-notes.html">Release notes</a></nav>'+body+ | |
| '<hr><p><a href="'+html.escape(name)+'" download>Download original text</a></p></main></body></html>\n') | |
| def main(): | |
| parser = argparse.ArgumentParser(description=__doc__) | |
| parser.add_argument('--check', action='store_true') | |
| args = parser.parse_args() | |
| for source, target in PAGES.items(): | |
| output = render(source) | |
| path = ROOT/target | |
| if args.check: | |
| if not path.exists() or path.read_text(encoding='utf-8') != output: | |
| raise SystemExit('Stale public HTML: '+target) | |
| else: | |
| path.write_text(output, encoding='utf-8') | |
| print('Public HTML pages match Markdown originals:', len(PAGES)) | |
| if __name__ == '__main__': | |
| main() | |