test_html_splitter_with_no_further_splits() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 3573–3592

def test_html_splitter_with_no_further_splits() -> None:
    """Test HTML splitting that requires no further splits beyond sections."""
    html_content = """
    <h1>Section 1</h1>
    <p>Some content here.</p>
    <h1>Section 2</h1>
    <p>More content here.</p>
    """
    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 content here.", metadata={"Header 1": "Section 1"}),
        Document(page_content="More content here.", metadata={"Header 1": "Section 2"}),
    ]

    assert documents == expected  # No further splits, just sections