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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
|
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
from __future__ import annotations
import logging
import os
import subprocess
from os import fspath
from pathlib import Path
import pytest
from ocrmypdf import pdfinfo
from ocrmypdf._exec import tesseract
from ocrmypdf.exceptions import MissingDependencyError
from .conftest import check_ocrmypdf
# pylint: disable=redefined-outer-name
@pytest.mark.parametrize('basename', ['graph_ocred.pdf', 'cardinal.pdf'])
def test_skip_pages_does_not_replicate(resources, basename, outdir):
infile = resources / basename
outpdf = outdir / basename
check_ocrmypdf(
infile,
outpdf,
'--pdf-renderer',
'sandwich',
'--force-ocr',
'--tesseract-timeout',
'0',
)
info_in = pdfinfo.PdfInfo(infile)
info = pdfinfo.PdfInfo(outpdf)
for page in info:
assert len(page.images) == 1, "skipped page was replicated"
for n, info_out_n in enumerate(info):
assert info_out_n.width_inches == info_in[n].width_inches, "output resized"
assert info_out_n.height_inches == info_in[n].height_inches, "output resized"
def test_content_preservation(resources, outpdf):
infile = resources / 'masks.pdf'
check_ocrmypdf(
infile, outpdf, '--pdf-renderer', 'sandwich', '--tesseract-timeout', '0'
)
info = pdfinfo.PdfInfo(outpdf)
page = info[0]
assert len(page.images) > 1, "masks were rasterized"
@pytest.mark.skipif(tesseract.version() > '5', reason="doesn't fool Tess 5")
def test_no_languages(tmp_path, monkeypatch):
(tmp_path / 'tessdata').mkdir()
monkeypatch.setenv('TESSDATA_PREFIX', fspath(tmp_path))
with pytest.raises(MissingDependencyError):
tesseract.get_languages()
def test_image_too_large_hocr(monkeypatch, resources, outdir):
def dummy_run(args, *, env=None, **kwargs):
raise subprocess.CalledProcessError(1, 'tesseract', output=b'Image too large')
monkeypatch.setattr(tesseract, 'run', dummy_run)
tesseract.generate_hocr(
input_file=resources / 'crom.png',
output_hocr=outdir / 'out.hocr',
output_text=outdir / 'out.txt',
languages=['eng'],
engine_mode=None,
tessconfig=[],
timeout=180.0,
pagesegmode=None,
thresholding=0,
user_words=None,
user_patterns=None,
)
assert "name='ocr-capabilities'" in Path(outdir / 'out.hocr').read_text()
def test_image_too_large_pdf(monkeypatch, resources, outdir):
def dummy_run(args, *, env=None, **kwargs):
raise subprocess.CalledProcessError(1, 'tesseract', output=b'Image too large')
monkeypatch.setattr(tesseract, 'run', dummy_run)
tesseract.generate_pdf(
input_file=resources / 'crom.png',
output_pdf=outdir / 'pdf.pdf',
output_text=outdir / 'txt.txt',
languages=['eng'],
engine_mode=None,
tessconfig=[],
timeout=180.0,
pagesegmode=None,
thresholding=0,
user_words=None,
user_patterns=None,
)
assert Path(outdir / 'txt.txt').read_text() == '[skipped page]'
if os.name != 'nt': # different semantics
assert Path(outdir / 'pdf.pdf').stat().st_size == 0
def test_timeout(caplog):
tesseract.page_timedout(5)
assert "took too long" in caplog.text
@pytest.mark.parametrize(
'in_, logged',
[
(b'Tesseract Open Source', ''),
(b'lots of diacritics blah blah', 'diacritics'),
(b'Warning in pixReadMem', ''),
(b'OSD: Weak margin', 'unsure about page orientation'),
(b'Error in pixScanForForeground', ''),
(b'Error in boxClipToRectangle', ''),
(b'an unexpected error', 'an unexpected error'),
(b'a dire warning', 'a dire warning'),
(b'read_params_file something', 'read_params_file'),
(b'an innocent message', 'innocent'),
(b'\x7f\x7f\x80innocent unicode failure', 'innocent'),
],
)
def test_tesseract_log_output(caplog, in_, logged):
caplog.set_level(logging.INFO)
tesseract.tesseract_log_output(in_)
if logged == '':
assert caplog.text == ''
else:
assert logged in caplog.text
def test_tesseract_log_output_raises(caplog):
with pytest.raises(tesseract.TesseractConfigError):
tesseract.tesseract_log_output(b'parameter not found: moo')
assert 'not found' in caplog.text
|
