test_additional_html_header_text_splitter() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 2807–2848

def test_additional_html_header_text_splitter(
    html_header_splitter_splitter_factory: Callable[
        [list[tuple[str, str]]], HTMLHeaderTextSplitter
    ],
    headers_to_split_on: list[tuple[str, str]],
    html_content: str,
    expected_output: list[Document],
    test_case: str,
) -> None:
    """Test the HTML header text splitter.

    Args:
        html_header_splitter_splitter_factory: Factory function to create the HTML
            header splitter.
        headers_to_split_on: List of headers to split on.
        html_content: HTML content to be split.
        expected_output: Expected list of `Document` objects.
        test_case: Description of the test case.

    Raises:
        AssertionError: If the number of documents or their content/metadata
            does not match the expected output.
    """
    splitter = html_header_splitter_splitter_factory(headers_to_split_on)
    docs = splitter.split_text(html_content)

    assert len(docs) == len(expected_output), (
        f"{test_case} Failed: Number of documents mismatch. "
        f"Expected {len(expected_output)}, got {len(docs)}."
    )
    for idx, (doc, expected) in enumerate(
        zip(docs, expected_output, strict=False), start=1
    ):
        assert doc.page_content == expected.page_content, (
            f"{test_case} Failed at Document {idx}: "
            f"Content mismatch.\nExpected: {expected.page_content}\n"
            "Got: {doc.page_content}"
        )
        assert doc.metadata == expected.metadata, (
            f"{test_case} Failed at Document {idx}: "
            f"Metadata mismatch.\nExpected: {expected.metadata}\nGot: {doc.metadata}"
        )