test_html_splitter_with_allowlist_tags() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 3700–3723

def test_html_splitter_with_allowlist_tags() -> None:
    """Test HTML splitting with allowlist tag filtering."""
    html_content = """
    <h1>Section 1</h1>
    <p>This paragraph should be kept.</p>
    <span>This span should be kept.</span>
    <div>This div should be removed.</div>
    """
    with suppress_langchain_beta_warning():
        splitter = HTMLSemanticPreservingSplitter(
            headers_to_split_on=[("h1", "Header 1")],
            allowlist_tags=["p", "span"],
            max_chunk_size=1000,
        )
    documents = splitter.split_text(html_content)

    expected = [
        Document(
            page_content="This paragraph should be kept. This span should be kept.",
            metadata={"Header 1": "Section 1"},
        ),
    ]

    assert documents == expected