yujunjun/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2025-06-26 23:49:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix broken test_hocrtransform_matches_sandwich

Browse Source 
Expect word similarity rather than exact match. Difference appears to be due to quote styles.

Thanks @QuLogic for reporting.
This commit is contained in:
James R. Barlow 2025-02-09 13:55:54 -08:00
parent 6b09129911
commit 32322a9fe9
No known key found for this signature in database
GPG Key ID: E54A300D567E1260
1 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
tests/test_hocrtransform.py
View File

@ -84,13 +84,19 @@ def test_hocrtransform_matches_sandwich(resources, outdir):
def clean(s):
s = re.sub(r'\s+', ' ', s)
words = s.split(' ')
return '\n'.join(sorted(words))
return set(words)
hocr_txt = clean(text_from_pdf(outdir / 'hocr.pdf'))
tess_txt = clean(text_from_pdf(outdir / 'tess.pdf'))
hocr_words = clean(text_from_pdf(outdir / 'hocr.pdf'))
tess_words = clean(text_from_pdf(outdir / 'tess.pdf'))
similarity = len(hocr_words & tess_words) / len(hocr_words | tess_words)
# from pathlib import Path
# Path('hocr.txt').write_text(hocr_txt)
# Path('tess.txt').write_text(tess_txt)
assert hocr_txt == tess_txt
# Path('hocr.txt').write_text(sorted('\n'.join(hocr_words)))
# Path('tess.txt').write_text(sorted('\n'.join(tess_words)))
# Path('mismatch.txt').write_text(
# '\n'.join(sorted(hocr_words ^ tess_words)), encoding='utf8'
# )
assert similarity > 0.99