unstructured/test_unstructured/partition/docx/test_doc.py

import os
from tempfile import SpooledTemporaryFile

import docx
import pytest
from pytest_mock import MockFixture

from test_unstructured.unit_utils import assert_round_trips_through_JSON, example_doc_path
from unstructured.chunking.title import chunk_by_title
from unstructured.documents.elements import (
    Address,
    ListItem,
    NarrativeText,
    Table,
    Text,
    Title,
)
from unstructured.partition.common import convert_office_doc
from unstructured.partition.doc import partition_doc
from unstructured.partition.docx import partition_docx


def test_partition_doc_matches_partition_docx(mock_document, expected_elements, tmpdir):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")
    assert partition_doc(filename=doc_filename) == partition_docx(filename=docx_filename)


# -- document-source (file or filename) ----------------------------------------------------------


def test_partition_doc_from_filename(mock_document, expected_elements, tmpdir, capsys):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")
    elements = partition_doc(filename=doc_filename)
    assert elements == expected_elements
    assert elements[0].metadata.filename == "mock_document.doc"
    assert elements[0].metadata.file_directory == tmpdir.dirname
    assert capsys.readouterr().out == ""
    assert capsys.readouterr().err == ""


def test_partition_doc_from_file_with_filter(mock_document, expected_elements, tmpdir, capsys):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    with open(doc_filename, "rb") as f:
        elements = partition_doc(file=f, libre_office_filter="MS Word 2007 XML")
    assert elements == expected_elements
    assert capsys.readouterr().out == ""
    assert capsys.readouterr().err == ""
    for element in elements:
        assert element.metadata.filename is None


def test_partition_doc_from_file_with_no_filter(mock_document, expected_elements, tmpdir, capsys):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    with open(doc_filename, "rb") as f:
        elements = partition_doc(file=f, libre_office_filter=None)
    assert elements == expected_elements
    assert capsys.readouterr().out == ""
    assert capsys.readouterr().err == ""
    for element in elements:
        assert element.metadata.filename is None


def test_partition_doc_raises_with_both_specified(mock_document, tmpdir):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    with open(doc_filename, "rb") as f, pytest.raises(ValueError):
        partition_doc(filename=doc_filename, file=f)


def test_partition_doc_raises_with_neither():
    with pytest.raises(ValueError):
        partition_doc()


def test_partition_raises_with_missing_doc(mock_document, expected_elements, tmpdir):
    doc_filename = os.path.join(tmpdir.dirname, "asdf.doc")

    with pytest.raises(ValueError):
        partition_doc(filename=doc_filename)


# -- `include_metadata` arg ----------------------------------------------------------------------


def test_partition_doc_from_filename_exclude_metadata(mock_document, tmpdir):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    elements = partition_doc(filename=doc_filename, include_metadata=False)

    assert elements[0].metadata.filetype is None
    assert elements[0].metadata.page_name is None
    assert elements[0].metadata.filename is None


def test_partition_doc_from_file_exclude_metadata(mock_document, tmpdir):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    with open(doc_filename, "rb") as f:
        elements = partition_doc(file=f, include_metadata=False)

    assert elements[0].metadata.filetype is None
    assert elements[0].metadata.page_name is None
    assert elements[0].metadata.filename is None


# -- .metadata.filename --------------------------------------------------------------------------


def test_partition_doc_from_filename_with_metadata_filename(
    mock_document,
    expected_elements,
    tmpdir,
):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    elements = partition_doc(filename=doc_filename, metadata_filename="test")
    assert elements == expected_elements
    assert all(element.metadata.filename == "test" for element in elements)


def test_partition_doc_from_file_with_metadata_filename(mock_document, tmpdir):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    with open(doc_filename, "rb") as f:
        elements = partition_doc(file=f, metadata_filename="test")
    for element in elements:
        assert element.metadata.filename == "test"


# -- .metadata.last_modified ---------------------------------------------------------------------


def test_partition_doc_metadata_date(
    mocker,
    filename="example-docs/fake.doc",
):
    mocked_last_modification_date = "2029-07-05T09:24:28"

    mocker.patch(
        "unstructured.partition.doc.get_last_modified_date",
        return_value=mocked_last_modification_date,
    )

    elements = partition_doc(filename=filename)

    assert elements[0].metadata.last_modified == mocked_last_modification_date


def test_partition_doc_metadata_date_with_custom_metadata(
    mocker,
    filename="example-docs/fake.doc",
):
    mocked_last_modification_date = "2029-07-05T09:24:28"
    expected_last_modified_date = "2020-07-05T09:24:28"

    mocker.patch(
        "unstructured.partition.doc.get_last_modified_date",
        return_value=mocked_last_modification_date,
    )

    elements = partition_doc(
        filename=filename,
        metadata_last_modified=expected_last_modified_date,
    )

    assert elements[0].metadata.last_modified == expected_last_modified_date


def test_partition_doc_suppresses_modified_date_from_file_by_default(mocker: MockFixture):
    modified_date_on_file = "2029-07-05T09:24:28"
    mocker.patch(
        "unstructured.partition.doc.get_last_modified_date_from_file",
        return_value=modified_date_on_file,
    )

    with open(example_doc_path("fake.doc"), "rb") as f:
        elements = partition_doc(file=f)

    assert elements[0].metadata.last_modified is None


def test_partition_doc_pulls_modified_date_from_file_when_date_from_file_object_arg_is_True(
    mocker: MockFixture,
):
    modified_date_on_file = "2024-05-01T09:24:28"
    mocker.patch(
        "unstructured.partition.doc.get_last_modified_date_from_file",
        return_value=modified_date_on_file,
    )

    with open(example_doc_path("fake.doc"), "rb") as f:
        elements = partition_doc(file=f, date_from_file_object=True)

    assert elements[0].metadata.last_modified == modified_date_on_file


def test_partition_doc_from_file_explicit_get_metadata_date(
    mocker,
    filename="example-docs/fake.doc",
):
    mocked_last_modification_date = "2029-07-05T09:24:28"

    mocker.patch(
        "unstructured.partition.doc.get_last_modified_date_from_file",
        return_value=mocked_last_modification_date,
    )

    with open(filename, "rb") as f:
        elements = partition_doc(file=f, date_from_file_object=True)

    assert elements[0].metadata.last_modified == mocked_last_modification_date


def test_partition_doc_from_file_without_metadata_date(
    filename="example-docs/fake.doc",
):
    """Test partition_doc() with file that are not possible to get last modified date"""
    with open(filename, "rb") as f:
        sf = SpooledTemporaryFile()
        sf.write(f.read())
        sf.seek(0)
        elements = partition_doc(file=sf, date_from_file_object=True)

    assert elements[0].metadata.last_modified is None


def test_partition_doc_from_file_metadata_date_with_custom_metadata(
    mocker,
    filename="example-docs/fake.doc",
):
    mocked_last_modification_date = "2029-07-05T09:24:28"
    expected_last_modified_date = "2020-07-05T09:24:28"

    mocker.patch(
        "unstructured.partition.doc.get_last_modified_date_from_file",
        return_value=mocked_last_modification_date,
    )
    with open(filename, "rb") as f:
        elements = partition_doc(
            file=f, metadata_last_modified=expected_last_modified_date, date_from_file_object=True
        )

    assert elements[0].metadata.last_modified == expected_last_modified_date


# -- language-recognition metadata ---------------------------------------------------------------


def test_partition_doc_element_metadata_has_languages():
    filename = "example-docs/fake-doc-emphasized-text.doc"
    elements = partition_doc(filename=filename)
    assert elements[0].metadata.languages == ["eng"]


def test_partition_doc_respects_detect_language_per_element():
    filename = "example-docs/language-docs/eng_spa_mult.doc"
    elements = partition_doc(filename=filename, detect_language_per_element=True)
    langs = [element.metadata.languages for element in elements]
    assert langs == [["eng"], ["spa", "eng"], ["eng"], ["eng"], ["spa"]]


# -- miscellaneous -------------------------------------------------------------------------------


def test_partition_doc_grabs_emphasized_texts():
    expected_emphasized_text_contents = ["bold", "italic", "bold-italic", "bold-italic"]
    expected_emphasized_text_tags = ["b", "i", "b", "i"]

    elements = partition_doc("example-docs/fake-doc-emphasized-text.doc")

    assert isinstance(elements[0], Table)
    assert elements[0].metadata.emphasized_text_contents == expected_emphasized_text_contents
    assert elements[0].metadata.emphasized_text_tags == expected_emphasized_text_tags

    assert elements[1] == NarrativeText("I am a bold italic bold-italic text.")
    assert elements[1].metadata.emphasized_text_contents == expected_emphasized_text_contents
    assert elements[1].metadata.emphasized_text_tags == expected_emphasized_text_tags

    assert elements[2] == NarrativeText("I am a normal text.")
    assert elements[2].metadata.emphasized_text_contents is None
    assert elements[2].metadata.emphasized_text_tags is None


def test_partition_doc_with_json(mock_document, tmpdir):
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
    mock_document.save(docx_filename)
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")

    elements = partition_doc(filename=doc_filename)
    assert_round_trips_through_JSON(elements)


def test_add_chunking_strategy_on_partition_doc(filename="example-docs/fake.doc"):
    chunk_elements = partition_doc(filename, chunking_strategy="by_title")
    elements = partition_doc(filename)
    chunks = chunk_by_title(elements)
    assert chunk_elements != elements
    assert chunk_elements == chunks


def test_partition_doc_for_deterministic_and_unique_ids():
    ids = [element.id for element in partition_doc("example-docs/duplicate-paragraphs.doc")]

    assert ids == [
        "ade273c622c48d67a7be7b3816d5b4d8",
        "7d0b32fdf169f9578723486cb4bc1235",
        "1feb6e8e9c1662cfaef75907aeeb0900",
        "aa2a8ac10143b12f0fe2087837ea11d2",
        "da31ba7ed3919067d2c6572dc1617271",
        "1914359c179a160df921b769acf8c353",
        "f9d0d379fc791bae487b7a45f65caa50",
    ]


# == module-level fixtures =======================================================================


@pytest.fixture()
def expected_elements():
    return [
        Title("These are a few of my favorite things:"),
        ListItem("Parrots"),
        ListItem("Hockey"),
        Title("Analysis"),
        NarrativeText("This is my first thought. This is my second thought."),
        NarrativeText("This is my third thought."),
        Text("2023"),
        Address("DOYLESTOWN, PA 18901"),
    ]


@pytest.fixture()
def mock_document():
    document = docx.Document()

    document.add_paragraph("These are a few of my favorite things:", style="Heading 1")
    # NOTE(robinson) - this should get picked up as a list item due to the •
    document.add_paragraph("• Parrots", style="Normal")
    # NOTE(robinson) - this should get dropped because it's empty
    document.add_paragraph("• ", style="Normal")
    document.add_paragraph("Hockey", style="List Bullet")
    # NOTE(robinson) - this should get dropped because it's empty
    document.add_paragraph("", style="List Bullet")
    # NOTE(robinson) - this should get picked up as a title
    document.add_paragraph("Analysis", style="Normal")
    # NOTE(robinson) - this should get dropped because it is empty
    document.add_paragraph("", style="Normal")
    # NOTE(robinson) - this should get picked up as a narrative text
    document.add_paragraph("This is my first thought. This is my second thought.", style="Normal")
    document.add_paragraph("This is my third thought.", style="Body Text")
    # NOTE(robinson) - this should just be regular text
    document.add_paragraph("2023")
    # NOTE(robinson) - this should be an address
    document.add_paragraph("DOYLESTOWN, PA 18901")

    return document