test_md_header_text_splitter_preserve_headers_1() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 1384–1414

def test_md_header_text_splitter_preserve_headers_1() -> None:
    """Test markdown splitter by header: Preserve Headers."""
    markdown_document = (
        "# Foo\n\n"
        "    ## Bat\n\n"
        "Hi this is Jim\n\n"
        "Hi Joe\n\n"
        "## Baz\n\n"
        "# Bar\n\n"
        "This is Alice\n\n"
        "This is Bob"
    )
    headers_to_split_on = [
        ("#", "Header 1"),
    ]
    markdown_splitter = MarkdownHeaderTextSplitter(
        headers_to_split_on=headers_to_split_on,
        strip_headers=False,
    )
    output = markdown_splitter.split_text(markdown_document)
    expected_output = [
        Document(
            page_content="# Foo  \n## Bat  \nHi this is Jim  \nHi Joe  \n## Baz",
            metadata={"Header 1": "Foo"},
        ),
        Document(
            page_content="# Bar  \nThis is Alice  \nThis is Bob",
            metadata={"Header 1": "Bar"},
        ),
    ]
    assert output == expected_output