import unittest from pathlib import Path from docreader.parser.html_parser import HTMLParser from docreader.parser.registry import BUILTIN_ENGINE, registry REPO_ROOT = Path(__file__).resolve().parents[2] class HTMLParserTest(unittest.TestCase): def test_parse_static_html_fixture_into_markdown(self): content = (REPO_ROOT / "docreader" / "testdata" / "test.html").read_bytes() document = HTMLParser(file_name="test.html", file_type="html").parse(content) self.assertIn("# 测试 HTML 文档", document.content) self.assertIn("[测试链接](https://example.com)", document.content) self.assertIn("| 表头1 | 表头2 |", document.content) self.assertIn("内容4", document.content) def test_parse_empty_html_returns_empty_document(self): document = HTMLParser(file_name="empty.htm", file_type="htm").parse(b"") self.assertEqual("", document.content) def test_parse_honors_declared_windows_1252_charset(self): html = ( '' "
further reference
" document = HTMLParser(file_name="space.html", file_type="html").parse(html) self.assertEqual("further reference", document.content) def test_registry_routes_html_extensions_to_html_parser(self): self.assertIs(registry.get_parser_class("", "html"), HTMLParser) self.assertIs(registry.get_parser_class("", "htm"), HTMLParser) builtin_types = registry._engines[BUILTIN_ENGINE] self.assertIn("html", builtin_types) self.assertIn("htm", builtin_types) if __name__ == "__main__": unittest.main()