mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-12 19:45:56 +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.
41 lines
1.5 KiB
Python
41 lines
1.5 KiB
Python
import pytest
|
|
|
|
from unstructured.documents.base import Document, Page
|
|
from unstructured.documents.elements import NarrativeText, Title
|
|
|
|
|
|
class MockDocument(Document):
|
|
def __init__(self):
|
|
super().__init__()
|
|
elements = [
|
|
Title(text="This is a narrative."),
|
|
NarrativeText(text="This is a narrative."),
|
|
NarrativeText(text="This is a narrative."),
|
|
]
|
|
page = Page(number=0)
|
|
page.elements = elements
|
|
self._pages = [page]
|
|
|
|
|
|
def test_get_narrative():
|
|
document = MockDocument()
|
|
narrative = document.get_narrative()
|
|
for element in narrative:
|
|
assert isinstance(element, NarrativeText)
|
|
document.print_narrative()
|
|
|
|
|
|
@pytest.mark.parametrize("index", [0, 1, 2])
|
|
def test_split(index):
|
|
document = MockDocument()
|
|
elements = document.pages[0].elements
|
|
split_before_doc = document.before_element(elements[index])
|
|
before_elements = split_before_doc.pages[0].elements if split_before_doc.pages else []
|
|
split_after_doc = document.after_element(elements[index])
|
|
after_elements = split_after_doc.pages[0].elements if split_after_doc.pages else []
|
|
expected_before_elements = document.pages[0].elements[:index]
|
|
next_index = index + 1
|
|
expected_after_elements = document.pages[0].elements[next_index:]
|
|
assert all(a.id == b.id for a, b in zip(before_elements, expected_before_elements))
|
|
assert all(a.id == b.id for a, b in zip(after_elements, expected_after_elements))
|