Function test_get_pdf_doc_path

tests/test_pdf_parser_extra.py:40–57

(pdflib: str)

@pytest.mark.parametrize("pdflib", ["unstructured"])
def test_get_pdf_doc_path(pdflib: str):
    current_dir = os.path.dirname(os.path.abspath(__file__))
    tests_root = os.path.abspath(os.path.join(current_dir, ".."))
    path = os.path.join(tests_root, "main", "data", "dummy.pdf")
    pdf_parser = DocumentParser.create(
        path, ParsingConfig(pdf=PdfParsingConfig(library=pdflib))
    )
    doc = pdf_parser.get_doc()

    # Check the results
    assert isinstance(doc.content, str)
    assert len(doc.content) > 0  # assuming the PDF is not empty
    assert doc.metadata.source == path

    docs = pdf_parser.get_doc_chunks()
    assert len(docs) > 0
    assert all(d.metadata.is_chunk for d in docs)
    assert all(path in d.metadata.source for d in docs)