Files
ocrmypdf/tests/test_graft.py
T

42 lines
1.1 KiB
Python
Raw Normal View History

2022-07-28 01:06:46 -07:00
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
2022-07-23 00:39:24 -07:00
from __future__ import annotations
2019-11-28 16:52:56 -08:00
from unittest.mock import patch
2019-12-19 15:29:56 -08:00
import pikepdf
import pytest
2019-06-12 17:52:25 -07:00
import ocrmypdf
2019-06-13 01:16:56 -07:00
def test_no_glyphless_graft(resources, outdir):
with pikepdf.open(resources / 'francais.pdf') as pdf, pikepdf.open(
resources / 'aspect.pdf'
) as pdf_aspect, pikepdf.open(resources / 'cmyk.pdf') as pdf_cmyk:
pdf.pages.extend(pdf_aspect.pages)
pdf.pages.extend(pdf_cmyk.pages)
pdf.save(outdir / 'test.pdf')
2019-11-28 16:52:56 -08:00
with patch('ocrmypdf._graft.MAX_REPLACE_PAGES', 2):
2019-07-07 02:11:44 -07:00
ocrmypdf.ocr(
outdir / 'test.pdf',
outdir / 'out.pdf',
deskew=True,
tesseract_timeout=0,
force_ocr=True,
2019-05-22 23:53:48 -07:00
)
# This test needs asserts
2019-05-12 03:36:33 -07:00
def test_links(resources, outpdf):
2019-07-07 02:11:44 -07:00
ocrmypdf.ocr(
2019-05-22 23:53:48 -07:00
resources / 'link.pdf', outpdf, redo_ocr=True, oversample=200, output_type='pdf'
2019-05-12 03:36:33 -07:00
)
with pikepdf.open(outpdf) as pdf:
p1 = pdf.pages[0]
p2 = pdf.pages[1]
assert p1.Annots[0].A.D[0].objgen == p2.objgen
assert p2.Annots[0].A.D[0].objgen == p1.objgen