这是段落内容。
第二段。
" s = HTMLSplitter(max_size=500) chunks = s.split(html, source_file="test.html") assert len(chunks) >= 1 all_text = "".join(c["content"] for c in chunks) assert "标题" in all_text assert "段落内容" in all_text assert "第二段" in all_text def test_strips_script_and_style(self): from src.core.splitters.html import HTMLSplitter html = """可见内容。
""" s = HTMLSplitter() chunks = s.split(html, source_file="test.html") all_text = "".join(c["content"] for c in chunks) assert "可见内容" in all_text assert "alert" not in all_text assert ".a{color:red}" not in all_text def test_empty_html(self): from src.core.splitters.html import HTMLSplitter s = HTMLSplitter() assert s.split("") == [] assert s.split("") == [] def test_html_has_split_method(self): """HTMLSplitter 遵循 Splitter Protocol.""" from src.core.splitters.html import HTMLSplitter s = HTMLSplitter() assert hasattr(s, "split")