mirror of
https://github.com/qurator-spk/dinglehopper.git
synced 2025-07-08 01:49:58 +02:00
Gerber, Mike
f94e8b9b1c
This reverts commit a3c1eee8f31349edcfb1e36920763bcecceb1129, reversing changes made to dc76213ffc1fbabc2c45f0e52ced55449bdf2e83.
23 lines
776 B
Python
23 lines
776 B
Python
from __future__ import division, print_function
|
|
|
|
import os
|
|
|
|
import pytest
|
|
from lxml import etree as ET
|
|
|
|
from .. import align, page_text
|
|
|
|
data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'data')
|
|
|
|
|
|
@pytest.mark.integration
|
|
def test_align_page_files():
|
|
# In the fake OCR file, we changed 2 characters and replaced a fi ligature with fi.
|
|
# → 4 elements in the alignment should be different.
|
|
# NOTE: In this example, it doesn't matter that we work with "characters", not grapheme clusters.
|
|
|
|
gt = page_text(ET.parse(os.path.join(data_dir, 'test-gt.page2018.xml')))
|
|
ocr = page_text(ET.parse(os.path.join(data_dir, 'test-fake-ocr.page2018.xml')))
|
|
|
|
result = list(align(gt, ocr))
|
|
assert sum(left != right for left, right in result) == 4
|