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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277
|
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# © 2015 James R. Barlow: github.com/jbarlow83
#
# This file is part of OCRmyPDF.
#
# OCRmyPDF is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# OCRmyPDF is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with OCRmyPDF. If not, see <http://www.gnu.org/licenses/>.
from __future__ import print_function, unicode_literals
import sys
if sys.version_info < (3, 6):
print("Python 3.6 or newer is required", file=sys.stderr)
sys.exit(1)
from setuptools import setup, find_packages
from subprocess import STDOUT, check_output, CalledProcessError
from collections.abc import Mapping
import re
# pylint: disable=w0613
missing_program = '''
The program '{program}' could not be executed or was not found on your
system PATH.
'''
unknown_version = '''
OCRmyPDF requires '{program}' {need_version} or higher. Your system has
'{program}' but we cannot tell what version is installed. Contact the
package maintainer.
'''
old_version = '''
OCRmyPDF requires '{program}' {need_version} or higher. Your system appears
to have {found_version}. Please update this program.
'''
okay_its_optional = '''
This program is OPTIONAL, so installation of OCRmyPDF can proceed, but
some functionality may be missing.
'''
not_okay_its_required = '''
This program is REQUIRED for OCRmyPDF to work. Installation will abort.
'''
osx_install_advice = '''
If you have homebrew installed, try these command to install the missing
packages:
brew update
brew upgrade
brew install {package}
'''
linux_install_advice = '''
On systems with the aptitude package manager (Debian, Ubuntu), try these
commands:
sudo apt-get update
sudo apt-get install {package}
On RPM-based systems (Red Hat, Fedora), search for instructions on
installing the RPM for {program}.
'''
def get_platform():
if sys.platform.startswith('freebsd'):
return 'freebsd'
elif sys.platform.startswith('linux'):
return 'linux'
return sys.platform
def _error_trailer(program, package, optional, **kwargs):
if optional:
print(okay_its_optional.format(**locals()), file=sys.stderr)
else:
print(not_okay_its_required.format(**locals()), file=sys.stderr)
if isinstance(package, Mapping):
package = package[get_platform()]
if get_platform() == 'darwin':
print(osx_install_advice.format(**locals()), file=sys.stderr)
elif get_platform() == 'linux':
print(linux_install_advice.format(**locals()), file=sys.stderr)
def error_missing_program(
program,
package,
optional
):
print(missing_program.format(**locals()), file=sys.stderr)
_error_trailer(**locals())
def error_unknown_version(
program,
package,
optional,
need_version
):
print(unknown_version.format(**locals()), file=sys.stderr)
_error_trailer(**locals())
def error_old_version(
program,
package,
optional,
need_version,
found_version
):
print(old_version.format(**locals()), file=sys.stderr)
_error_trailer(**locals())
def check_external_program(
program,
need_version,
package,
version_check_args=None,
version_scrape_regex=re.compile(r'(\d+\.\d+(?:\.\d+)?)'),
optional=False):
if not version_check_args:
version_check_args = ['--version']
print(f'Checking for {program} >= {need_version}...')
try:
result = check_output(
[program] + version_check_args,
universal_newlines=True, stderr=STDOUT)
except (CalledProcessError, FileNotFoundError):
error_missing_program(program, package, optional)
if not optional:
sys.exit(1)
print(f'Continuing install without {program}')
return
try:
found_version = version_scrape_regex.search(result).group(1)
except AttributeError:
error_unknown_version(program, package, optional, need_version)
sys.exit(1)
if found_version < need_version:
error_old_version(program, package, optional, need_version,
found_version)
print(f'Found {program} {found_version}')
command = next((arg for arg in sys.argv[1:] if not arg.startswith('-')), '')
forced = ('--force' in sys.argv)
if not forced and command.startswith('install') or \
command in ['check', 'test', 'nosetests', 'easy_install']:
check_external_program(
program='tesseract',
need_version='4.0.0', # using backport for Travis CI
package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'}
)
check_external_program(
program='gs',
need_version='9.15', # limited by Travis CI / Ubuntu 14.04 backports
package='ghostscript'
)
check_external_program(
program='unpaper',
need_version='6.1', # latest sane version
package='unpaper',
optional=True
)
check_external_program(
program='qpdf',
need_version='8.0.2', # test suite known to fail on 5.1.1
package='qpdf'
)
check_external_program(
program='pngquant',
need_version='2.0.0',
package='pngquant',
optional=True
)
if 'upload' in sys.argv[1:]:
print('Use twine to upload the package - setup.py upload is insecure')
sys.exit(1)
tests_require = open('requirements/test.txt', encoding='utf-8').read().splitlines()
def readme():
with open('README.md', encoding='utf-8') as f:
return f.read()
setup(
name='ocrmypdf',
description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
long_description=readme(),
long_description_content_type='text/markdown',
url='https://github.com/jbarlow83/OCRmyPDF',
author='James R. Barlow',
author_email='jim@purplerock.ca',
packages=find_packages('src', exclude=["tests", "tests.*"]),
package_dir={'': 'src'},
keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
classifiers=[
"Programming Language :: Python :: 3.6",
"Programming Language :: Python :: 3.7",
"Development Status :: 5 - Production/Stable",
"Environment :: Console",
"Intended Audience :: End Users/Desktop",
"Intended Audience :: Science/Research",
"Intended Audience :: System Administrators",
"License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
"Operating System :: MacOS :: MacOS X",
"Operating System :: POSIX",
"Operating System :: POSIX :: BSD",
"Operating System :: POSIX :: Linux",
"Topic :: Scientific/Engineering :: Image Recognition",
"Topic :: Text Processing :: Indexing",
"Topic :: Text Processing :: Linguistic",
],
python_requires=' >= 3.6',
setup_requires=[
'cffi >= 1.9.1', # to build the leptonica module
'pytest-runner', # to enable python setup.py test
'setuptools_scm', # so that version will work
],
use_scm_version={'version_scheme': 'post-release'},
cffi_modules=[
'src/ocrmypdf/lib/compile_leptonica.py:ffibuilder'
],
install_requires=[
'chardet >= 3.0.4, < 4', # unlisted requirement of pdfminer.six 20181108
'cffi >= 1.9.1', # must be a setup and install requirement
'img2pdf >= 0.3.0, < 0.4', # pure Python, so track HEAD closely
'pdfminer.six == 20181108 ; sys_platform != "darwin"',
'pikepdf >= 1.0.5, < 2',
'Pillow >= 4.0.0, != 5.1.0 ; sys_platform == "darwin"',
# Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
# block 5.1.0, broken wheels
'reportlab >= 3.3.0', # oldest released version with sane image handling
'ruffus >= 2.7.0',
],
extras_require={
'pdfminer': ['pdfminer.six == 20181108'],
},
tests_require=tests_require,
entry_points={
'console_scripts': [
'ocrmypdf = ocrmypdf.__main__:run_pipeline'
],
},
package_data={'ocrmypdf': ['data/sRGB.icc']},
include_package_data=True,
zip_safe=False,
project_urls={
'Documentation': 'https://ocrmypdf.readthedocs.io/',
'Source': 'https://github.com/jbarlow83/ocrmypdf',
'Tracker': 'https://github.com/jbarlow83/ocrmypdf/issues'
}
)
|