test_md_header_text_splitter_fenced_code_block() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 1464–1487

def test_md_header_text_splitter_fenced_code_block(fence: str) -> None:
    """Test markdown splitter by header: Fenced code block."""
    markdown_document = (
        f"# This is a Header\n\n{fence}\nfoo()\n# Not a header\nbar()\n{fence}"
    )

    headers_to_split_on = [
        ("#", "Header 1"),
        ("##", "Header 2"),
    ]

    markdown_splitter = MarkdownHeaderTextSplitter(
        headers_to_split_on=headers_to_split_on,
    )
    output = markdown_splitter.split_text(markdown_document)

    expected_output = [
        Document(
            page_content=f"{fence}\nfoo()\n# Not a header\nbar()\n{fence}",
            metadata={"Header 1": "This is a Header"},
        ),
    ]

    assert output == expected_output