1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
|
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
from __future__ import annotations
from unittest.mock import patch
import img2pdf
import pikepdf
import pytest
from PIL import Image
import ocrmypdf
from .conftest import check_ocrmypdf, run_ocrmypdf_api
# pylint: disable=redefined-outer-name
@pytest.fixture
def baiona(resources):
return Image.open(resources / 'baiona_gray.png')
def test_image_to_pdf(resources, outpdf):
check_ocrmypdf(
resources / 'crom.png',
outpdf,
'--image-dpi',
'200',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
def test_no_dpi_info(caplog, baiona, outdir, no_outpdf):
im = baiona
assert 'dpi' not in im.info
input_image = outdir / 'baiona_no_dpi.png'
im.save(input_image)
rc = run_ocrmypdf_api(input_image, no_outpdf)
assert rc == ocrmypdf.ExitCode.input_file
assert "--image-dpi" in caplog.text
def test_dpi_not_credible(caplog, baiona, outdir, no_outpdf):
im = baiona
assert 'dpi' not in im.info
input_image = outdir / 'baiona_no_dpi.png'
im.save(input_image, dpi=(30, 30))
rc = run_ocrmypdf_api(input_image, no_outpdf)
assert rc == ocrmypdf.ExitCode.input_file
assert "not credible" in caplog.text
def test_cmyk_no_icc(caplog, resources, no_outpdf):
rc = run_ocrmypdf_api(resources / 'baiona_cmyk.jpg', no_outpdf)
assert rc == ocrmypdf.ExitCode.input_file
assert "no ICC profile" in caplog.text
def test_img2pdf_fails(resources, no_outpdf):
with patch(
'ocrmypdf._pipeline.img2pdf.convert', side_effect=img2pdf.ImageOpenError()
) as mock:
rc = run_ocrmypdf_api(
resources / 'baiona_gray.png', no_outpdf, '--image-dpi', '200'
)
assert rc == ocrmypdf.ExitCode.input_file
mock.assert_called()
@pytest.mark.xfail(reason="remove background disabled")
def test_jpeg_in_jpeg_out(resources, outpdf):
check_ocrmypdf(
resources / 'congress.jpg',
outpdf,
'--image-dpi',
'100',
'--output-type',
'pdf', # specifically check pdf because Ghostscript may convert to JPEG
'--remove-background',
'--plugin',
'tests/plugins/tesseract_noop.py',
)
with pikepdf.open(outpdf) as pdf:
assert next(iter(pdf.pages[0].images.values())).Filter == pikepdf.Name.DCTDecode
|
