forked from explosion/spaCy
-
Notifications
You must be signed in to change notification settings - Fork 0
/
setup.py
176 lines (146 loc) · 5.95 KB
/
setup.py
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
#!/usr/bin/env python
from setuptools import setup
import shutil
import sys
import os
from os import path
from setuptools import Extension
from distutils import sysconfig
import platform
# PyPy --- NB! PyPy doesn't really work, it segfaults all over the place. But,
# this is necessary to get it compile.
# We have to resort to monkey-patching to set the compiler, because pypy broke
# all the everything.
pre_patch_customize_compiler = sysconfig.customize_compiler
def my_customize_compiler(compiler):
pre_patch_customize_compiler(compiler)
compiler.compiler_cxx = ['c++']
if platform.python_implementation() == 'PyPy':
sysconfig.customize_compiler = my_customize_compiler
#def install_headers():
# dest_dir = path.join(sys.prefix, 'include', 'murmurhash')
# if not path.exists(dest_dir):
# shutil.copytree('murmurhash/headers/murmurhash', dest_dir)
#
# dest_dir = path.join(sys.prefix, 'include', 'numpy')
includes = ['.', path.join(sys.prefix, 'include')]
try:
import numpy
numpy_headers = path.join(numpy.get_include(), 'numpy')
shutil.copytree(numpy_headers, path.join(sys.prefix, 'include', 'numpy'))
except ImportError:
pass
except OSError:
pass
def clean(mod_names):
for name in mod_names:
name = name.replace('.', '/')
so = name + '.so'
html = name + '.html'
cpp = name + '.cpp'
c = name + '.c'
for file_path in [so, html, cpp, c]:
if os.path.exists(file_path):
os.unlink(file_path)
def name_to_path(mod_name, ext):
return '%s.%s' % (mod_name.replace('.', '/'), ext)
def c_ext(mod_name, language, includes, compile_args, link_args):
mod_path = name_to_path(mod_name, language)
return Extension(mod_name, [mod_path], include_dirs=includes,
extra_compile_args=compile_args, extra_link_args=link_args)
def cython_setup(mod_names, language, includes, compile_args, link_args):
import Cython.Distutils
import Cython.Build
import distutils.core
if language == 'cpp':
language = 'c++'
exts = []
for mod_name in mod_names:
mod_path = mod_name.replace('.', '/') + '.pyx'
e = Extension(mod_name, [mod_path], language=language, include_dirs=includes,
extra_compile_args=compile_args, extra_link_args=link_args)
exts.append(e)
distutils.core.setup(
name='spacy',
packages=['spacy', 'spacy.tokens', 'spacy.en', 'spacy.serialize',
'spacy.syntax', 'spacy.munge'],
description="Industrial-strength NLP",
author='Matthew Honnibal',
author_email='[email protected]',
version=VERSION,
url="http://honnibal.github.io/spaCy/",
package_data={"spacy": ["*.pxd"],
"spacy.en": ["*.pxd", "data/pos/*",
"data/wordnet/*", "data/tokenizer/*",
"data/vocab/lexemes.bin",
"data/vocab/strings.txt"],
"spacy.syntax": ["*.pxd"]},
ext_modules=exts,
cmdclass={'build_ext': Cython.Distutils.build_ext},
license="Dual: Commercial or AGPL",
)
def run_setup(exts):
setup(
name='spacy',
packages=['spacy', 'spacy.tokens', 'spacy.en', 'spacy.serialize',
'spacy.syntax', 'spacy.munge'],
description="Industrial-strength NLP",
author='Matthew Honnibal',
author_email='[email protected]',
version=VERSION,
url="http://honnibal.github.io/spaCy/",
package_data={"spacy": ["*.pxd"],
"spacy.en": ["*.pxd", "data/pos/*",
"data/wordnet/*", "data/tokenizer/*",
"data/vocab/lexemes.bin",
"data/vocab/serializer.json",
"data/vocab/oov_prob",
"data/vocab/strings.txt"],
"spacy.syntax": ["*.pxd"]},
ext_modules=exts,
license="MIT",
install_requires=['numpy', 'murmurhash', 'cymem >= 1.11', 'preshed == 0.41',
'thinc == 3.3', "text_unidecode", 'wget', 'plac', 'six',
'ujson'],
setup_requires=["headers_workaround"],
)
import headers_workaround
headers_workaround.fix_venv_pypy_include()
headers_workaround.install_headers('murmurhash')
headers_workaround.install_headers('numpy')
VERSION = '0.93'
def main(modules, is_pypy):
language = "cpp"
includes = ['.', path.join(sys.prefix, 'include')]
compile_args = ['-O3', '-Wno-strict-prototypes']
link_args = []
if sys.prefix == 'darwin':
compile_args.append(['-mmacosx-version-min=10.8', '-stdlib=libc++'])
link_args.append('-lc++')
if use_cython:
cython_setup(modules, language, includes, compile_args, link_args)
else:
exts = [c_ext(mn, language, includes, compile_args, link_args)
for mn in modules]
run_setup(exts)
MOD_NAMES = ['spacy.parts_of_speech', 'spacy.strings',
'spacy.lexeme', 'spacy.vocab', 'spacy.attrs',
'spacy.morphology', 'spacy.tagger',
'spacy.syntax.stateclass',
'spacy._ml', 'spacy._theano',
'spacy.tokenizer', 'spacy.en.attrs',
'spacy.en.pos', 'spacy.syntax.parser',
'spacy.syntax.transition_system',
'spacy.syntax.arc_eager',
'spacy.syntax._parse_features',
'spacy.gold', 'spacy.orth',
'spacy.tokens.doc', 'spacy.tokens.spans', 'spacy.tokens.token',
'spacy.serialize.packer', 'spacy.serialize.huffman', 'spacy.serialize.bits',
'spacy.cfile', 'spacy.matcher',
'spacy.syntax.ner']
if __name__ == '__main__':
if sys.argv[1] == 'clean':
clean(MOD_NAMES)
else:
use_cython = sys.argv[1] == 'build_ext'
main(MOD_NAMES, use_cython)