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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
|
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
from __future__ import annotations
import os
import platform
import sys
from pathlib import Path
from subprocess import PIPE, CompletedProcess, run
from typing import List
import pytest
from ocrmypdf import api, pdfinfo
from ocrmypdf._exec import unpaper
from ocrmypdf._plugin_manager import get_parser_options_plugins
from ocrmypdf.exceptions import ExitCode
def is_linux():
return platform.system() == 'Linux'
def is_macos():
return platform.system() == 'Darwin'
def running_in_docker():
# Docker creates a file named /.dockerenv (newer versions) or
# /.dockerinit (older) -- this is undocumented, not an offical test
return Path('/.dockerenv').exists() or Path('/.dockerinit').exists()
def have_unpaper():
try:
unpaper.version()
except Exception: # pylint: disable=broad-except
return False
return True
TESTS_ROOT = Path(__file__).parent.resolve()
PROJECT_ROOT = TESTS_ROOT
@pytest.fixture(scope="session")
def resources() -> Path:
return Path(TESTS_ROOT) / 'resources'
@pytest.fixture
def ocrmypdf_exec() -> list[str]:
return [sys.executable, '-m', 'ocrmypdf']
@pytest.fixture(scope="function")
def outdir(tmp_path) -> Path:
return tmp_path
@pytest.fixture(scope="function")
def outpdf(tmp_path) -> Path:
return tmp_path / 'out.pdf'
@pytest.fixture(scope="function")
def outtxt(tmp_path) -> Path:
return tmp_path / 'out.txt'
@pytest.fixture(scope="function")
def no_outpdf(tmp_path) -> Path:
"""This just documents the fact that a test is not expected to produce
output. Unfortunately an assertion failure inside a test fixture produces
an error rather than a test failure, so no testing is done. It's up to
the test to confirm that no output file was created."""
return tmp_path / 'no_output.pdf'
@pytest.fixture(scope="session")
def multipage(resources):
return resources / 'multipage.pdf'
def check_ocrmypdf(input_file: Path, output_file: Path, *args) -> Path:
"""Run ocrmypdf and confirm that a valid plausible PDF was created."""
api_args = [str(input_file), str(output_file)] + [
str(arg) for arg in args if arg is not None
]
_parser, options, plugin_manager = get_parser_options_plugins(args=api_args)
api.check_options(options, plugin_manager)
result = api.run_pipeline(options, plugin_manager=plugin_manager, api=True)
assert result == 0
assert output_file.exists(), "Output file not created"
assert output_file.stat().st_size > 100, "PDF too small or empty"
return output_file
def run_ocrmypdf_api(input_file: Path, output_file: Path, *args) -> ExitCode:
"""Run ocrmypdf via its API in-process, and let test deal with results.
This simulates calling the command line interface in a subprocess, but
is easier for debuggers and code coverage to follow.
Any exception raised will be trapped and converted to an exit code.
The return code must always be checked or the test may declare a failure
to be pass.
"""
api_args = [str(input_file), str(output_file)] + [
str(arg) for arg in args if arg is not None
]
_parser, options, plugin_manager = get_parser_options_plugins(args=api_args)
api.check_options(options, plugin_manager)
return api.run_pipeline(options, plugin_manager=None, api=False)
def run_ocrmypdf(
input_file: Path, output_file: Path, *args, text: bool = True
) -> CompletedProcess:
"""Run ocrmypdf in a subprocess and let test deal with results.
If an exception is thrown this fact will be returned as part of the result
text and return code rather than exception objects.
"""
p_args = (
[sys.executable, '-m', 'ocrmypdf']
+ [str(arg) for arg in args if arg is not None]
+ [str(input_file), str(output_file)]
)
p = run(
p_args,
capture_output=True,
text=text,
check=False,
)
# print(p.stderr)
return p
def first_page_dimensions(pdf: Path):
info = pdfinfo.PdfInfo(pdf)
page0 = info[0]
return (page0.width_inches, page0.height_inches)
def pytest_addoption(parser):
parser.addoption(
"--runslow",
action="store_true",
default=False,
help=(
"run slow tests only useful for development (unlikely to be "
"useful for downstream packagers)"
),
)
def pytest_collection_modifyitems(config, items):
if config.getoption("--runslow"):
# --runslow given in cli: do not skip slow tests
return
skip_slow = pytest.mark.skip(reason="need --runslow option to run")
for item in items:
if "slow" in item.keywords:
item.add_marker(skip_slow)
|
