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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import os
import sys
import debian.deb822
import pandas as pd
#from IPython.core import ultratb
#sys.excepthook = ultratb.FormattedTB(mode='Verbose',
# color_scheme='Linux', call_pdb=1)
class BadFormat(Exception):
pass
def read_copyright(fh):
paras = debian.deb822.Deb822.iter_paragraphs(fh)
try:
header = paras.next()
header = dict(header)
paras = [(p.keys()[0], dict(p)) for p in paras]
except (KeyError, TypeError, StopIteration):
raise BadFormat('not in DEP-5 format?')
return
if 'Format' not in header:
raise ValueError('no Format field')
return
files = []
licences = []
#file_fields = set([
# 'Authors', 'Files', 'Comment', 'Copyright', 'Disclaimer', 'Homepage',
# 'License', 'License-Alias', 'Upstream-Authors', 'X-Comment',
# 'X-Notes'])
for (type, d) in paras:
type = type.replace('Licence', 'License')
if 'Licence' in d:
# !!!
d['License'] = d['Licence']
del d['Licence']
if type == 'Files':
if 'debian' in d['Files']:
continue
if 'License' not in d:
raise ValueError('no license: ' + repr(d))
return
#keys = set(d.keys())
#assert keys <= file_fields, keys
files.append(d)
elif type == 'License':
# XXX constrain permissible keys here?
#print d.keys()
licences.append(d)
else:
# Be conservative. Missing license information is a problem.
raise ValueError('bad para: ' + type)
return (header, files, licences)
def import_one(pkgname, fh):
try:
(header, files, licences) = read_copyright(fh)
except BadFormat:
print 'info: not readable'
return None
except ValueError, e:
print 'err:', e
#print 'err:', repr(e)
return None
if licences == []:
return None
header['_srcpkg'] = pkgname
header['_license'] = header.get('License', '').split('\n')[0]
if 'Upstream-Name' in header:
# Make spaces breakable (!).
# Conceivably other characters need replacing.
header['Upstream-Name'] = \
header['Upstream-Name'].replace(u'\xa0', ' ')
#copy_summary['Upstream-Name'].replace('\xc2\xa0', ' ')
if '@' in header['Upstream-Name']:
header['Upstream-Name'] = pkgname
copy_summary = pd.DataFrame([header])
#print copy_summary.T.to_string()
#print
for d in files:
d['_srcpkg'] = pkgname
d['_license'] = d['License'].split('\n')[0]
for d in licences:
d['_srcpkg'] = pkgname
d['_license'] = d['License'].split('\n')[0]
copy_files = pd.DataFrame(files)
licence = pd.DataFrame(licences)
return (copy_summary, copy_files, licence)
def get_pkgname(path):
(dir, base) = os.path.split(path)
if base in ('current', 'stable_copyright'):
return get_pkgname(dir)
else:
return base
def main(paths):
summaries = []
files = []
licenses = []
for path in paths:
pkgname = get_pkgname(path)
print pkgname, path
data = import_one(pkgname, file(path))
if data is not None:
(summary, file_, license) = data
summaries.append(summary)
files.append(file_)
licenses.append(license)
print
summaries = pd.concat(summaries)
files = pd.concat(files)
licenses = pd.concat(licenses)
#from IPython import embed
#embed()
#from IPython.core.debugger import Pdb
#Pdb().set_trace()
store = pd.HDFStore('cp.h5')
store['cp_summary'] = summaries
store['cp_files'] = files
store['licenses'] = licenses
store.close()
if __name__ == '__main__':
main(sys.argv[1:])
|
