mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-10-31 01:54:25 +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.
50 lines
1.6 KiB
Python
50 lines
1.6 KiB
Python
import os
|
|
import pathlib
|
|
|
|
import pytest
|
|
|
|
from unstructured.documents.elements import ListItem, NarrativeText, Title
|
|
from unstructured.partition.ppt import partition_ppt
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
EXAMPLE_DOCS_DIRECTORY = os.path.join(DIRECTORY, "..", "..", "example-docs")
|
|
|
|
EXPECTED_PPT_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_partition_ppt_from_filename():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-power-point.ppt")
|
|
elements = partition_ppt(filename=filename)
|
|
assert elements == EXPECTED_PPT_OUTPUT
|
|
|
|
|
|
def test_partition_ppt_raises_with_missing_file():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "doesnt-exist.ppt")
|
|
with pytest.raises(ValueError):
|
|
partition_ppt(filename=filename)
|
|
|
|
|
|
def test_partition_ppt_from_file():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-power-point.ppt")
|
|
with open(filename, "rb") as f:
|
|
elements = partition_ppt(file=f)
|
|
assert elements == EXPECTED_PPT_OUTPUT
|
|
|
|
|
|
def test_partition_ppt_raises_with_both_specified():
|
|
filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-power-point.ppt")
|
|
with open(filename, "rb") as f, pytest.raises(ValueError):
|
|
partition_ppt(filename=filename, file=f)
|
|
|
|
|
|
def test_partition_ppt_raises_with_neither():
|
|
with pytest.raises(ValueError):
|
|
partition_ppt()
|