test_html_splitter_with_mixed_preserve_and_filter() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 3727–3759

def test_html_splitter_with_mixed_preserve_and_filter() -> None:
    """Test HTML splitting with both preserved elements and denylist tags."""
    html_content = """
    <h1>Section 1</h1>
    <table>
        <tr>
            <td>Keep this table</td>
            <td>Cell contents kept, span removed
                <span>This span should be removed.</span>
            </td>
        </tr>
    </table>
    <p>This paragraph should be kept.</p>
    <span>This span should be removed.</span>
    """
    with suppress_langchain_beta_warning():
        splitter = HTMLSemanticPreservingSplitter(
            headers_to_split_on=[("h1", "Header 1")],
            elements_to_preserve=["table"],
            denylist_tags=["span"],
            max_chunk_size=1000,
        )
    documents = splitter.split_text(html_content)

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

    assert documents == expected