mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-11-04 03:53:45 +00:00
87a88a3c87
This PR implements splitting of `pdfminer` elements (`groups of text chunks`) into smaller bounding boxes (`text lines`). This implementation prevents loss of information from the object detection model and facilitates more effective removal of duplicated `pdfminer` text. This PR also addresses #3430. --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
29 lines
1.1 KiB
Python
29 lines
1.1 KiB
Python
from unittest.mock import MagicMock
|
|
|
|
from pdfminer.layout import LTContainer, LTTextLine
|
|
|
|
from unstructured.partition.pdf_image.pdfminer_utils import extract_text_objects
|
|
|
|
|
|
def test_extract_text_objects_nested_containers():
|
|
"""Test extract_text_objects with nested LTContainers."""
|
|
# Mock LTTextLine objects
|
|
mock_text_line1 = MagicMock(spec=LTTextLine)
|
|
mock_text_line2 = MagicMock(spec=LTTextLine)
|
|
|
|
# Mock inner container containing one LTTextLine
|
|
mock_inner_container = MagicMock(spec=LTContainer)
|
|
mock_inner_container.__iter__.return_value = [mock_text_line2]
|
|
|
|
# Mock outer container containing another LTTextLine and the inner container
|
|
mock_outer_container = MagicMock(spec=LTContainer)
|
|
mock_outer_container.__iter__.return_value = [mock_text_line1, mock_inner_container]
|
|
|
|
# Call the function with the outer container
|
|
result = extract_text_objects(mock_outer_container)
|
|
|
|
# Assert both text line objects are extracted, even from nested containers
|
|
assert len(result) == 2
|
|
assert mock_text_line1 in result
|
|
assert mock_text_line2 in result
|