Repository navigation
Expand file tree
/
Copy pathdeps.py
More file actions
166 lines (137 loc) · 5.44 KB
/
Copy pathdeps.py
File metadata and controls
166 lines (137 loc) · 5.44 KB
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
import os
import re
import sys
import json
import shutil
import urllib
import httplib
import argparse
import warnings
import traceback
import functools
import xmlrpclib
import subprocess
from pkg_resources import parse_version, parse_requirements
from concurrent.futures import ThreadPoolExecutor
def dload(storage_dir, (idx, package)):
if idx % 100 == 99:
print "Processing {0} package".format(idx + 1)
try:
client = xmlrpclib.ServerProxy('https://pypi.python.org/pypi')
releases = client.package_releases(package)
_, latest = max((parse_version(ver), ver) for ver in releases)
for ext in ('tar.gz', 'zip'):
fname = "{0}-{1}.{2}".format(package, latest, ext)
head_url = "/packages/source/{0}/{1}/{2}".format(package[0], package, fname)
conn = httplib.HTTPSConnection("pypi.python.org")
conn.request("HEAD", head_url)
if conn.getresponse().status != 200:
continue
url = "http://pypi.python.org" + head_url
dst = os.path.join(storage_dir, fname)
urllib.urlretrieve(url, dst)
return package, latest, fname
return package, None, "Failed to found link"
except Exception as exc:
return package, None, "Failed to process: " + str(exc).replace("\n", ' ')
rr = re.compile(r'(?ims)"?install_requires"?\s*(=|:)\s*\[(?P<deps>.*?)\]')
def analyze_package((idx, path)):
package = os.path.basename(path).rsplit('-', 1)[0]
try:
return _analyze_package(path, package)
except:
msg = "-" * 60 + "\n" + package + ":" + traceback.format_exc() + "\n"
sys.stderr.write(msg)
return package, None
def _analyze_package(path, package):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
dname = os.tmpnam()
os.mkdir(dname)
arch_name = os.path.join(dname, os.path.basename(path))
new_files = []
if path.endswith('.zip'):
arch_name = arch_name.rsplit(".", 1)[0] + ".zip"
shutil.copyfile(path, arch_name)
cmd = "cd {0} ; unzip {1} >/dev/null 2>&1".format(dname, arch_name)
subprocess.check_call(cmd, shell=True)
new_files = set(os.listdir(dname)) - set([os.path.basename(arch_name)])
elif path.endswith('.tar.gz'):
shutil.copyfile(path, arch_name)
cmd = "cd {0} ; tar -zxvf {1} >/dev/null 2>&1".format(dname, arch_name)
subprocess.check_call(cmd, shell=True)
new_files = set(os.listdir(dname)) - set([os.path.basename(arch_name)])
if len(new_files) == 1:
setup_py = os.path.join(dname, list(new_files)[0], 'setup.py')
if not os.path.isfile(setup_py):
setup_py = None
requirements_txt = os.path.join(dname, list(new_files)[0], 'requirements.txt')
if not os.path.isfile(requirements_txt):
requirements_txt = None
else:
setup_py = None
requirements_txt = None
res = None
if requirements_txt is not None:
try:
res = [next(parse_requirements(line)).project_name
for line in open(requirements_txt)
if line.strip() != ""
and not line.strip().startswith('#')
and not line.strip().startswith('-')]
except:
msg = "-" * 60 + "\n" + package + \
" requirements.txt - BROKEN\n" + traceback.format_exc() + "\n"
sys.stderr.write(msg)
if setup_py is not None and res is None:
data = open(setup_py).read()
re_res = rr.search(data)
if re_res is not None:
sres = re_res.group('deps').strip()
if sres == "":
res = []
else:
sres_list = [i.strip() for i in eval('[\n' + sres + '\n]') if i.strip() != '']
res = [next(parse_requirements(i)).project_name for i in sres_list]
elif 'install_requires' not in data:
res = []
shutil.rmtree(dname)
return package, res
def download_all(store_path):
client = xmlrpclib.ServerProxy('https://pypi.python.org/pypi')
with ThreadPoolExecutor(64) as pool:
with open(os.path.join(store_path, 'index.js'), 'w') as fd:
fd.write("[\n")
dload_1p = functools.partial(dload, store_path)
it = pool.map(dload_1p, enumerate(client.list_packages()))
for package, version, fname in it:
fd.write(json.dumps((package, version, fname)) + ",\n")
fd.flush()
fd.write("]\n")
def parse_args(argv):
p = argparse.ArgumentParser()
p.add_argument('cmd', choices=("collect", "report"), help="CMD")
p.add_argument('storage', help="storage directory")
return p.parse_args(argv)
def main(argv):
args = parse_args(argv)
if args.cmd == 'collect':
download_all(args.storage)
elif args.cmd == 'report':
packages = []
for arch in sorted(os.listdir(args.storage)):
path = os.path.join(args.storage, arch)
if os.path.isfile(path):
packages.append(path)
with ThreadPoolExecutor(64) as pool:
for package, deps in pool.map(analyze_package, enumerate(packages)):
if deps is None:
print package + ", null"
else:
print package + ',' + ','.join(deps)
else:
print "Unknown command"
return 1
return 0
if __name__ == "__main__":
exit(main(sys.argv[1:]))