mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-23 17:10:35 +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.
106 lines
3.5 KiB
Python
106 lines
3.5 KiB
Python
from unstructured_inference.inference.layout import LayoutElement
|
|
|
|
from unstructured.documents.elements import (
|
|
CheckBox,
|
|
FigureCaption,
|
|
ListItem,
|
|
NarrativeText,
|
|
Text,
|
|
Title,
|
|
)
|
|
from unstructured.partition import common
|
|
|
|
|
|
def test_normalize_layout_element_dict():
|
|
layout_element = {
|
|
"type": "Title",
|
|
"coordinates": [[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
"text": "Some lovely text",
|
|
}
|
|
element = common.normalize_layout_element(layout_element)
|
|
assert element == Title(text="Some lovely text", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]])
|
|
|
|
|
|
def test_normalize_layout_element_dict_caption():
|
|
layout_element = {
|
|
"type": "Figure",
|
|
"coordinates": [[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
"text": "Some lovely text",
|
|
}
|
|
element = common.normalize_layout_element(layout_element)
|
|
assert element == FigureCaption(
|
|
text="Some lovely text",
|
|
coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
)
|
|
|
|
|
|
def test_normalize_layout_element_dict_misc():
|
|
layout_element = {
|
|
"type": "Misc",
|
|
"coordinates": [[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
"text": "Some lovely text",
|
|
}
|
|
element = common.normalize_layout_element(layout_element)
|
|
assert element == Text(text="Some lovely text", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]])
|
|
|
|
|
|
def test_normalize_layout_element_layout_element():
|
|
layout_element = LayoutElement(
|
|
type="Text",
|
|
coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
text="Some lovely text",
|
|
)
|
|
element = common.normalize_layout_element(layout_element)
|
|
assert element == NarrativeText(
|
|
text="Some lovely text",
|
|
coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
)
|
|
|
|
|
|
def test_normalize_layout_element_checked_box():
|
|
layout_element = LayoutElement(
|
|
type="Checked",
|
|
coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
text="",
|
|
)
|
|
element = common.normalize_layout_element(layout_element)
|
|
assert element == CheckBox(checked=True, coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]])
|
|
|
|
|
|
def test_normalize_layout_element_unchecked_box():
|
|
layout_element = LayoutElement(
|
|
type="Unchecked",
|
|
coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
text="",
|
|
)
|
|
element = common.normalize_layout_element(layout_element)
|
|
assert element == CheckBox(checked=False, coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]])
|
|
|
|
|
|
def test_normalize_layout_element_enumerated_list():
|
|
layout_element = LayoutElement(
|
|
type="List",
|
|
coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
text="1. I'm so cool! 2. You're cool too. 3. We're all cool!",
|
|
)
|
|
elements = common.normalize_layout_element(layout_element)
|
|
assert elements == [
|
|
ListItem(text="I'm so cool!", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]]),
|
|
ListItem(text="You're cool too.", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]]),
|
|
ListItem(text="We're all cool!", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]]),
|
|
]
|
|
|
|
|
|
def test_normalize_layout_element_bulleted_list():
|
|
layout_element = LayoutElement(
|
|
type="List",
|
|
coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]],
|
|
text="* I'm so cool! * You're cool too. * We're all cool!",
|
|
)
|
|
elements = common.normalize_layout_element(layout_element)
|
|
assert elements == [
|
|
ListItem(text="I'm so cool!", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]]),
|
|
ListItem(text="You're cool too.", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]]),
|
|
ListItem(text="We're all cool!", coordinates=[[1, 2], [3, 4], [5, 6], [7, 8]]),
|
|
]
|