mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-06-27 02:30:08 +00:00
5eb1466acc
* Apply import sorting ruff . --select I --fix * Remove unnecessary open mode parameter ruff . --select UP015 --fix * Use f-string formatting rather than .format * Remove extraneous parentheses Also use "" instead of str() * Resolve missing trailing commas ruff . --select COM --fix * Rewrite list() and dict() calls using literals ruff . --select C4 --fix * Add () to pytest.fixture, use tuples for parametrize, etc. ruff . --select PT --fix * Simplify code: merge conditionals, context managers ruff . --select SIM --fix * Import without unnecessary alias ruff . --select PLR0402 --fix * Apply formatting via black * Rewrite ValueError somewhat Slightly unrelated to the rest of the PR * Apply formatting to tests via black * Update expected exception message to match 0d81564 * Satisfy E501 line too long in test * Update changelog & version * Add ruff to make tidy and test deps * Run 'make tidy' * Update changelog & version * Update changelog & version * Add ruff to 'check' target Doing so required me to also fix some non-auto-fixable issues. Two of them I fixed with a noqa: SIM115, but especially the one in __init__ may need some attention. That said, that refactor is out of scope of this PR.
108 lines
3.3 KiB
Python
108 lines
3.3 KiB
Python
import datetime
|
|
import os
|
|
import pathlib
|
|
|
|
import docx
|
|
import openpyxl
|
|
import pytest
|
|
|
|
import unstructured.file_utils.metadata as meta
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
EXAMPLE_JPG_FILENAME = os.path.join(DIRECTORY, "..", "..", "example-docs", "example.jpg")
|
|
|
|
|
|
def test_get_docx_metadata_from_filename(tmpdir):
|
|
filename = os.path.join(tmpdir, "test-doc.docx")
|
|
|
|
document = docx.Document()
|
|
document.add_paragraph("Lorem ipsum dolor sit amet.")
|
|
document.core_properties.author = "Mr. Miagi"
|
|
document.save(filename)
|
|
|
|
metadata = meta.get_docx_metadata(filename=filename)
|
|
assert metadata.author == "Mr. Miagi"
|
|
assert metadata.to_dict()["author"] == "Mr. Miagi"
|
|
|
|
|
|
def test_get_docx_metadata_from_file(tmpdir):
|
|
filename = os.path.join(tmpdir, "test-doc.docx")
|
|
|
|
document = docx.Document()
|
|
document.add_paragraph("Lorem ipsum dolor sit amet.")
|
|
document.core_properties.author = "Mr. Miagi"
|
|
document.save(filename)
|
|
|
|
with open(filename, "rb") as f:
|
|
metadata = meta.get_docx_metadata(file=f)
|
|
assert metadata.author == "Mr. Miagi"
|
|
|
|
|
|
def test_get_docx_metadata_raises_without_file_or_filename():
|
|
with pytest.raises(FileNotFoundError):
|
|
meta.get_docx_metadata()
|
|
|
|
|
|
def test_get_xlsx_metadata_from_filename(tmpdir):
|
|
filename = os.path.join(tmpdir, "test-excel.xlsx")
|
|
|
|
workbook = openpyxl.Workbook()
|
|
workbook.properties.creator = "Mr. Miagi"
|
|
workbook.save(filename)
|
|
|
|
metadata = meta.get_xlsx_metadata(filename=filename)
|
|
metadata.author = "Mr. Miagi"
|
|
|
|
|
|
def test_get_xlsx_metadata_from_file(tmpdir):
|
|
filename = os.path.join(tmpdir, "test-excel.xlsx")
|
|
|
|
workbook = openpyxl.Workbook()
|
|
workbook.properties.creator = "Mr. Miagi"
|
|
workbook.save(filename)
|
|
|
|
with open(filename, "rb") as f:
|
|
metadata = meta.get_xlsx_metadata(file=f)
|
|
metadata.author = "Mr. Miagi"
|
|
|
|
|
|
def test_get_xlsx_metadata_raises_without_file_or_filename():
|
|
with pytest.raises(FileNotFoundError):
|
|
meta.get_xlsx_metadata()
|
|
|
|
|
|
def test_get_jpg_metadata_from_filename():
|
|
metadata = meta.get_jpg_metadata(filename=EXAMPLE_JPG_FILENAME)
|
|
assert metadata.modified == datetime.datetime(2003, 12, 14, 12, 1, 44)
|
|
assert metadata.exif_data["Make"] == "Canon"
|
|
|
|
|
|
def test_get_jpg_metadata_from_file():
|
|
with open(EXAMPLE_JPG_FILENAME, "rb") as f:
|
|
metadata = meta.get_jpg_metadata(file=f)
|
|
assert metadata.modified == datetime.datetime(2003, 12, 14, 12, 1, 44)
|
|
assert metadata.exif_data["Make"] == "Canon"
|
|
|
|
|
|
def test_get_jpg_metadata_raises_without_file_or_filename():
|
|
with pytest.raises(FileNotFoundError):
|
|
meta.get_jpg_metadata()
|
|
|
|
|
|
def test_get_exif_datetime():
|
|
exif_data = {"DateTime": "2022:12:23 15:49:00", "DateTimeOriginal": "2020:12:14 12:00:00"}
|
|
date = meta._get_exif_datetime(exif_data, "DateTime")
|
|
assert date == datetime.datetime(2022, 12, 23, 15, 49, 0)
|
|
|
|
|
|
def test_get_exif_datetime_ignores_bad_formats():
|
|
exif_data = {"DateTime": "2022-12-23TZ15:49:00", "DateTimeOriginal": "2020:12:14 12:00:00"}
|
|
date = meta._get_exif_datetime(exif_data, "DateTime")
|
|
assert date is None
|
|
|
|
|
|
def test_get_exif_datetime_ignores_missing_key():
|
|
exif_data = {"Datetime": "2022-12-23TZ15:49:00", "DateTimeOriginal": "2020:12:14 12:00:00"}
|
|
date = meta._get_exif_datetime(exif_data, "DateTimeDigitized")
|
|
assert date is None
|