test_experimental_markdown_syntax_text_splitter_with_headers() — langchain Function Reference

Source Code

libs/text-splitters/tests/unit_tests/test_text_splitters.py lines 1796–1851

def test_experimental_markdown_syntax_text_splitter_with_headers() -> None:
    """Test experimental markdown syntax splitter."""
    markdown_splitter = ExperimentalMarkdownSyntaxTextSplitter(strip_headers=False)
    output = markdown_splitter.split_text(EXPERIMENTAL_MARKDOWN_DOCUMENT)

    expected_output = [
        Document(
            page_content="# My Header 1\nContent for header 1\n",
            metadata={"Header 1": "My Header 1"},
        ),
        Document(
            page_content="## Header 2\nContent for header 2\n",
            metadata={"Header 1": "My Header 1", "Header 2": "Header 2"},
        ),
        Document(
            page_content="### Header 3\nContent for header 3\n",
            metadata={
                "Header 1": "My Header 1",
                "Header 2": "Header 2",
                "Header 3": "Header 3",
            },
        ),
        Document(
            page_content=(
                "## Header 2 Again\n"
                "This should be tagged with Header 1 and Header 2 Again\n"
            ),
            metadata={"Header 1": "My Header 1", "Header 2": "Header 2 Again"},
        ),
        Document(
            page_content=(
                "```python\ndef func_definition():\n   "
                "print('Keep the whitespace consistent')\n```\n"
            ),
            metadata={
                "Code": "python",
                "Header 1": "My Header 1",
                "Header 2": "Header 2 Again",
            },
        ),
        Document(
            page_content=(
                "# Header 1 again\nWe should also split on the horizontal line\n"
            ),
            metadata={"Header 1": "Header 1 again"},
        ),
        Document(
            page_content=(
                "This will be a new doc but with the same header metadata\n\n"
                "And it includes a new paragraph"
            ),
            metadata={"Header 1": "Header 1 again"},
        ),
    ]

    assert output == expected_output