test_md_header_text_splitter_preserve_headers_2() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 1417–1460

def test_md_header_text_splitter_preserve_headers_2() -> None:
    """Test markdown splitter by header: Preserve Headers."""
    markdown_document = (
        "# Foo\n\n"
        "    ## Bar\n\n"
        "Hi this is Jim\n\n"
        "Hi this is Joe\n\n"
        "### Boo \n\n"
        "Hi this is Lance\n\n"
        "## Baz\n\n"
        "Hi this is Molly\n"
        "    ## Buz\n"
        "# Bop"
    )
    headers_to_split_on = [
        ("#", "Header 1"),
        ("##", "Header 2"),
        ("###", "Header 3"),
    ]
    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## Bar  \nHi this is Jim  \nHi this is Joe",
            metadata={"Header 1": "Foo", "Header 2": "Bar"},
        ),
        Document(
            page_content="### Boo  \nHi this is Lance",
            metadata={"Header 1": "Foo", "Header 2": "Bar", "Header 3": "Boo"},
        ),
        Document(
            page_content="## Baz  \nHi this is Molly",
            metadata={"Header 1": "Foo", "Header 2": "Baz"},
        ),
        Document(
            page_content="## Buz",
            metadata={"Header 1": "Foo", "Header 2": "Buz"},
        ),
        Document(page_content="# Bop", metadata={"Header 1": "Bop"}),
    ]
    assert output == expected_output