mirror of
				https://github.com/Unstructured-IO/unstructured.git
				synced 2025-11-04 03:53:45 +00:00 
			
		
		
		
	* added msg-parser dependency * pass through kwargs in convert_file_to_text * added partition_msg for processing msft outlook files * version bump and changelog * added tests for partition_msg * added test for msg with plain text * add partition_msg docs; fix underlines in integration docs * add .msg to file list * finish tests for auto msg * linting, linting, linting
		
			
				
	
	
		
			358 lines
		
	
	
		
			13 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			358 lines
		
	
	
		
			13 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
import os
 | 
						|
import pathlib
 | 
						|
import warnings
 | 
						|
from unittest.mock import patch
 | 
						|
 | 
						|
import docx
 | 
						|
import pytest
 | 
						|
 | 
						|
from unstructured.documents.elements import (
 | 
						|
    Address,
 | 
						|
    ListItem,
 | 
						|
    NarrativeText,
 | 
						|
    PageBreak,
 | 
						|
    Text,
 | 
						|
    Title,
 | 
						|
)
 | 
						|
from unstructured.partition import auto
 | 
						|
from unstructured.partition.auto import partition
 | 
						|
from unstructured.partition.common import convert_office_doc
 | 
						|
 | 
						|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
 | 
						|
EXAMPLE_DOCS_DIRECTORY = os.path.join(DIRECTORY, "..", "..", "example-docs")
 | 
						|
 | 
						|
EXPECTED_EMAIL_OUTPUT = [
 | 
						|
    NarrativeText(text="This is a test email to use for unit tests."),
 | 
						|
    Title(text="Important points:"),
 | 
						|
    ListItem(text="Roses are red"),
 | 
						|
    ListItem(text="Violets are blue"),
 | 
						|
]
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_email_from_filename():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-email.eml")
 | 
						|
    elements = partition(filename=filename)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements == EXPECTED_EMAIL_OUTPUT
 | 
						|
    assert elements[0].metadata.filename == filename
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_email_from_file():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-email.eml")
 | 
						|
    with open(filename) as f:
 | 
						|
        elements = partition(file=f)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements == EXPECTED_EMAIL_OUTPUT
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_email_from_file_rb():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-email.eml")
 | 
						|
    with open(filename, "rb") as f:
 | 
						|
        elements = partition(file=f)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements == EXPECTED_EMAIL_OUTPUT
 | 
						|
 | 
						|
 | 
						|
@pytest.fixture()
 | 
						|
def mock_docx_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")
 | 
						|
    document.add_paragraph("Hockey", 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")
 | 
						|
 | 
						|
    return document
 | 
						|
 | 
						|
 | 
						|
@pytest.fixture()
 | 
						|
def expected_docx_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"),
 | 
						|
    ]
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_docx_with_filename(mock_docx_document, expected_docx_elements, tmpdir):
 | 
						|
    filename = os.path.join(tmpdir.dirname, "mock_document.docx")
 | 
						|
    mock_docx_document.save(filename)
 | 
						|
 | 
						|
    elements = partition(filename=filename)
 | 
						|
    assert elements == expected_docx_elements
 | 
						|
    assert elements[0].metadata.filename == filename
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_docx_with_file(mock_docx_document, expected_docx_elements, tmpdir):
 | 
						|
    filename = os.path.join(tmpdir.dirname, "mock_document.docx")
 | 
						|
    mock_docx_document.save(filename)
 | 
						|
 | 
						|
    with open(filename, "rb") as f:
 | 
						|
        elements = partition(file=f)
 | 
						|
    assert elements == expected_docx_elements
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize(
 | 
						|
    ("pass_file_filename", "content_type"),
 | 
						|
    [(False, None), (False, "application/msword"), (True, "application/msword"), (True, None)],
 | 
						|
)
 | 
						|
def test_auto_partition_doc_with_filename(
 | 
						|
    mock_docx_document,
 | 
						|
    expected_docx_elements,
 | 
						|
    tmpdir,
 | 
						|
    pass_file_filename,
 | 
						|
    content_type,
 | 
						|
):
 | 
						|
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
 | 
						|
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
 | 
						|
    mock_docx_document.save(docx_filename)
 | 
						|
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")
 | 
						|
    file_filename = doc_filename if pass_file_filename else None
 | 
						|
    elements = partition(
 | 
						|
        filename=doc_filename,
 | 
						|
        file_filename=file_filename,
 | 
						|
        content_type=content_type,
 | 
						|
    )
 | 
						|
    assert elements == expected_docx_elements
 | 
						|
    assert elements[0].metadata.filename == doc_filename
 | 
						|
 | 
						|
 | 
						|
# NOTE(robinson) - the application/x-ole-storage mime type is not specific enough to
 | 
						|
# determine that the file is an .doc document
 | 
						|
@pytest.mark.xfail()
 | 
						|
def test_auto_partition_doc_with_file(mock_docx_document, expected_docx_elements, tmpdir):
 | 
						|
    docx_filename = os.path.join(tmpdir.dirname, "mock_document.docx")
 | 
						|
    doc_filename = os.path.join(tmpdir.dirname, "mock_document.doc")
 | 
						|
    mock_docx_document.save(docx_filename)
 | 
						|
    convert_office_doc(docx_filename, tmpdir.dirname, "doc")
 | 
						|
 | 
						|
    with open(doc_filename, "rb") as f:
 | 
						|
        elements = partition(file=f)
 | 
						|
    assert elements == expected_docx_elements
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize(
 | 
						|
    ("pass_file_filename", "content_type"),
 | 
						|
    [(False, None), (False, "text/html"), (True, "text/html"), (True, None)],
 | 
						|
)
 | 
						|
def test_auto_partition_html_from_filename(pass_file_filename, content_type):
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "example-10k.html")
 | 
						|
    file_filename = filename if pass_file_filename else None
 | 
						|
    elements = partition(filename=filename, file_filename=file_filename, content_type=content_type)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements[0].metadata.filename == filename
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize(
 | 
						|
    ("pass_file_filename", "content_type"),
 | 
						|
    [(False, None), (False, "text/html"), (True, "text/html"), (True, None)],
 | 
						|
)
 | 
						|
def test_auto_partition_html_from_file(pass_file_filename, content_type):
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-html.html")
 | 
						|
    file_filename = filename if pass_file_filename else None
 | 
						|
    with open(filename) as f:
 | 
						|
        elements = partition(file=f, file_filename=file_filename, content_type=content_type)
 | 
						|
    assert len(elements) > 0
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_html_from_file_rb():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-html.html")
 | 
						|
    with open(filename, "rb") as f:
 | 
						|
        elements = partition(file=f)
 | 
						|
    assert len(elements) > 0
 | 
						|
 | 
						|
 | 
						|
EXPECTED_TEXT_OUTPUT = [
 | 
						|
    NarrativeText(text="This is a test document to use for unit tests."),
 | 
						|
    Address(text="Doylestown, PA 18901"),
 | 
						|
    Title(text="Important points:"),
 | 
						|
    ListItem(text="Hamburgers are delicious"),
 | 
						|
    ListItem(text="Dogs are the best"),
 | 
						|
    ListItem(text="I love fuzzy blankets"),
 | 
						|
]
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_text_from_filename():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-text.txt")
 | 
						|
    elements = partition(filename=filename)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements == EXPECTED_TEXT_OUTPUT
 | 
						|
    assert elements[0].metadata.filename == filename
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_text_from_file():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-text.txt")
 | 
						|
    with open(filename) as f:
 | 
						|
        elements = partition(file=f)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements == EXPECTED_TEXT_OUTPUT
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize(
 | 
						|
    ("pass_file_filename", "content_type"),
 | 
						|
    [(False, None), (False, "application/pdf"), (True, "application/pdf"), (True, None)],
 | 
						|
)
 | 
						|
def test_auto_partition_pdf_from_filename(pass_file_filename, content_type):
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
 | 
						|
    file_filename = filename if pass_file_filename else None
 | 
						|
 | 
						|
    elements = partition(filename=filename, file_filename=file_filename, content_type=content_type)
 | 
						|
 | 
						|
    assert isinstance(elements[0], Title)
 | 
						|
    assert elements[0].text.startswith("LayoutParser")
 | 
						|
 | 
						|
    assert isinstance(elements[1], NarrativeText)
 | 
						|
    assert elements[1].text.startswith("Zejiang Shen 1")
 | 
						|
 | 
						|
    assert elements[0].metadata.filename == filename
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_pdf_with_fast_strategy():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
 | 
						|
 | 
						|
    mock_return = [NarrativeText("Hello there!")]
 | 
						|
    with patch.object(auto, "partition_pdf", return_value=mock_return) as mock_partition:
 | 
						|
        partition(filename=filename, strategy="fast")
 | 
						|
 | 
						|
    mock_partition.assert_called_once_with(
 | 
						|
        filename=filename,
 | 
						|
        file=None,
 | 
						|
        url=None,
 | 
						|
        include_page_breaks=False,
 | 
						|
        encoding="utf-8",
 | 
						|
        strategy="fast",
 | 
						|
    )
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize(
 | 
						|
    ("pass_file_filename", "content_type"),
 | 
						|
    [(False, None), (False, "application/pdf"), (True, "application/pdf"), (True, None)],
 | 
						|
)
 | 
						|
def test_auto_partition_pdf_from_file(pass_file_filename, content_type):
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
 | 
						|
    file_filename = filename if pass_file_filename else None
 | 
						|
 | 
						|
    with open(filename, "rb") as f:
 | 
						|
        elements = partition(file=f, file_filename=file_filename, content_type=content_type)
 | 
						|
 | 
						|
    assert isinstance(elements[0], Title)
 | 
						|
    assert elements[0].text.startswith("LayoutParser")
 | 
						|
 | 
						|
    assert isinstance(elements[1], NarrativeText)
 | 
						|
    assert elements[1].text.startswith("Zejiang Shen 1")
 | 
						|
 | 
						|
 | 
						|
def test_partition_pdf_doesnt_raise_warning():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
 | 
						|
    # NOTE(robinson): This is the recommended way to check that no warning is emitted,
 | 
						|
    # per the pytest docs.
 | 
						|
    # ref: https://docs.pytest.org/en/7.0.x/how-to/capture-warnings.html
 | 
						|
    #      #additional-use-cases-of-warnings-in-tests
 | 
						|
    with warnings.catch_warnings():
 | 
						|
        warnings.simplefilter("error")
 | 
						|
        partition(filename=filename)
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize(
 | 
						|
    ("pass_file_filename", "content_type"),
 | 
						|
    [(False, None), (False, "image/jpeg"), (True, "image/jpeg"), (True, None)],
 | 
						|
)
 | 
						|
def test_auto_partition_jpg(pass_file_filename, content_type):
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "example.jpg")
 | 
						|
    file_filename = filename if pass_file_filename else None
 | 
						|
    elements = partition(filename=filename, file_filename=file_filename, content_type=content_type)
 | 
						|
    assert len(elements) > 0
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.parametrize(
 | 
						|
    ("pass_file_filename", "content_type"),
 | 
						|
    [(False, None), (False, "image/jpeg"), (True, "image/jpeg"), (True, None)],
 | 
						|
)
 | 
						|
def test_auto_partition_jpg_from_file(pass_file_filename, content_type):
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "example.jpg")
 | 
						|
    file_filename = filename if pass_file_filename else None
 | 
						|
    with open(filename, "rb") as f:
 | 
						|
        elements = partition(file=f, file_filename=file_filename, content_type=content_type)
 | 
						|
    assert len(elements) > 0
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_raises_with_bad_type(monkeypatch):
 | 
						|
    monkeypatch.setattr(auto, "detect_filetype", lambda *args, **kwargs: None)
 | 
						|
    with pytest.raises(ValueError):
 | 
						|
        partition(filename="made-up.fake")
 | 
						|
 | 
						|
 | 
						|
EXPECTED_PPTX_OUTPUT = [
 | 
						|
    Title(text="Adding a Bullet Slide"),
 | 
						|
    ListItem(text="Find the bullet slide layout"),
 | 
						|
    ListItem(text="Use _TextFrame.text for first bullet"),
 | 
						|
    ListItem(text="Use _TextFrame.add_paragraph() for subsequent bullets"),
 | 
						|
    NarrativeText(text="Here is a lot of text!"),
 | 
						|
    NarrativeText(text="Here is some text in a text box!"),
 | 
						|
]
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_pptx_from_filename():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-power-point.pptx")
 | 
						|
    elements = partition(filename=filename)
 | 
						|
    assert elements == EXPECTED_PPTX_OUTPUT
 | 
						|
    assert elements[0].metadata.filename == filename
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
 | 
						|
def test_auto_partition_ppt_from_filename():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-power-point.ppt")
 | 
						|
    elements = partition(filename=filename)
 | 
						|
    assert elements == EXPECTED_PPTX_OUTPUT
 | 
						|
    assert elements[0].metadata.filename == filename
 | 
						|
 | 
						|
 | 
						|
def test_auto_with_page_breaks():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
 | 
						|
    elements = partition(filename=filename, include_page_breaks=True)
 | 
						|
    assert PageBreak() in elements
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
 | 
						|
def test_auto_partition_epub_from_filename():
 | 
						|
    filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
 | 
						|
    elements = partition(filename=filename)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
 | 
						|
 | 
						|
 | 
						|
@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
 | 
						|
def test_auto_partition_epub_from_file():
 | 
						|
    filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
 | 
						|
    with open(filename, "rb") as f:
 | 
						|
        elements = partition(file=f)
 | 
						|
    assert len(elements) > 0
 | 
						|
    assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
 | 
						|
 | 
						|
 | 
						|
EXPECTED_MSG_OUTPUT = [
 | 
						|
    NarrativeText(text="This is a test email to use for unit tests."),
 | 
						|
    Title(text="Important points:"),
 | 
						|
    ListItem(text="Roses are red"),
 | 
						|
    ListItem(text="Violets are blue"),
 | 
						|
]
 | 
						|
 | 
						|
 | 
						|
def test_auto_partition_msg_from_filename():
 | 
						|
    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-email.msg")
 | 
						|
    elements = partition(filename=filename)
 | 
						|
    assert elements == EXPECTED_MSG_OUTPUT
 |