test_html_splitter_with_nested_elements() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 3415–3439

def test_html_splitter_with_nested_elements() -> None:
    """Test HTML splitting with nested elements."""
    html_content = """
    <h1>Main Section</h1>
    <div>
        <p>Some text here.</p>
        <div>
            <p>Nested content.</p>
        </div>
    </div>
    """
    with suppress_langchain_beta_warning():
        splitter = HTMLSemanticPreservingSplitter(
            headers_to_split_on=[("h1", "Header 1")], max_chunk_size=1000
        )
    documents = splitter.split_text(html_content)

    expected = [
        Document(
            page_content="Some text here. Nested content.",
            metadata={"Header 1": "Main Section"},
        ),
    ]

    assert documents == expected