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
|
#!/usr/bin/env python3
from optparse import OptionParser
import fnmatch
import tarfile
from io import BytesIO
import re
import os
import sys
import email.message
import urllib.request
from urllib.parse import urlparse
class URLFile(object):
'''Simple proxy to urllib.request.urlopen, that responds to seek only if
it's called before read. This is enough for tarfile to be happy'''
def __init__(self, url):
self.file = urllib.request.urlopen(url)
def seekable(self):
return True
def seek(self, offset, whence = os.SEEK_SET):
if whence != os.SEEK_SET or offset != 0 or self.read == self._read:
raise Exception("unsupported")
def _read(self, size = -1):
return self.file.read(size)
def read(self, size = -1):
self.read = self._read
return self._read(size)
def close(self):
self.file.close()
def dirname(filespec):
'''Returns os.path.dirname if a file, and '' if an url'''
if urlparse(filespec).scheme:
return ''
return os.path.dirname(filespec)
class TarFilterList(object):
def __init__(self, filename):
self.patterns = {}
for filt in open(filename).readlines():
f = filt.strip().split(None, 1)
if len(f) == 1:
[pat] = f
cmd = None
else:
[pat, cmd] = f
pat = pat.split(os.sep)
self.add_pattern(pat, self.patterns, cmd)
def add_pattern(self, pat, patterns, cmd):
if re.search(r'[\[\?\*]', pat[0]):
if not '*' in patterns:
patterns['*'] = []
patterns['*'].append([os.sep.join(pat), cmd, False])
else:
if len(pat) >= 2:
if not pat[0] in patterns:
patterns[pat[0]] = {}
self.add_pattern(pat[1:], patterns[pat[0]], cmd)
else:
if not '*' in patterns:
patterns['*'] = []
patterns['*'].append([pat[0], cmd, False])
def match(self, name):
name = name.split(os.sep)[1:]
if len(name) == 0:
return False
return self._match(name, self.patterns)
def _match(self, name, patterns):
if len(name) > 1 and name[0] in patterns:
cmd = self._match(name[1:], patterns[name[0]])
if cmd != False:
return cmd
if '*' in patterns:
for pat in patterns['*']:
if fnmatch.fnmatch(name[0], pat[0]) or fnmatch.fnmatch(os.sep.join(name), pat[0]):
pat[2] = True
return pat[1]
return False
def unused(self, patterns=None, root=''):
result = []
if root:
root += '/'
if not patterns:
patterns = self.patterns
for pat in patterns:
if pat != '*':
result += self.unused(patterns[pat], root + pat)
else:
for p in patterns[pat]:
if not p[2]:
result.append(root + p[0])
return result
def file_extension(name):
return os.path.splitext(name)[1][1:]
def filter_tar(orig, new, filt, topdir = None):
filt = TarFilterList(filt)
if urlparse(orig).scheme:
tar = tarfile.open(orig, "r:" + file_extension(orig), URLFile(orig))
else:
tar = tarfile.open(orig, "r:" + file_extension(orig))
new_tar = tarfile.open(new + ".new", "w:" + file_extension(new))
while True:
info = tar.next()
if not info:
break
if topdir:
info.name = "/".join([topdir] + info.name.split("/")[1:])
do_filt = filt.match(info.name)
if do_filt == None:
print("Removing", info.name, file=sys.stderr)
continue
if info.isfile():
file = tar.extractfile(info)
if do_filt:
print("Filtering", info.name, file=sys.stderr)
orig = file
file = BytesIO()
the_filt = lambda l: l
if do_filt[0].isalpha():
f = do_filt.split(do_filt[1])
if f[0] == 's':
the_filt = lambda l: re.sub(f[1], f[2],
l.decode()).encode('utf-8')
else:
f = do_filt.split(do_filt[0])
if f[2] == 'd':
the_filt = lambda l: b'' if re.search(f[1],
l.decode()) else l
for l in orig.readlines():
file.write(the_filt(l))
info.size = file.tell()
file.seek(0);
new_tar.addfile(info, file)
else:
new_tar.addfile(info)
tar.close()
new_tar.close()
os.rename(new_tar.name, new)
unused = filt.unused()
if unused:
print('Unused filters:')
print('', '\n '.join(unused))
def get_package_name():
control = os.path.join(os.path.dirname(__file__), "control")
return email.message.Message(open(control))["Source"]
def main():
parser = OptionParser()
parser.add_option("-u", "--upstream-version", dest="upstream_version",
help="define upstream version number to use when creating the file",
metavar="VERSION")
parser.add_option("-f", "--filter", dest="filter",
help="use the given filter list", metavar="FILE")
parser.add_option("-p", "--package", dest="package",
help="use the given package name", metavar="NAME")
parser.add_option("-o", "--output", dest="new_file",
help="save the filtered tarball as the given file name", metavar="FILE")
parser.add_option("-t", "--topdir", dest="topdir",
help="replace the top directory with the given name", metavar="NAME")
(options, args) = parser.parse_args()
if not options.upstream_version and not options.new_file:
parser.error("Need an upstream version")
return
if len(args) < 1:
parser.error("Too few arguments")
return
if len(args) > 1:
parser.error("Too many arguments")
return
if not options.filter:
options.filter = os.path.join(os.path.dirname(__file__), "source.filter")
if not options.package:
options.package = get_package_name()
if options.new_file:
new_file = options.new_file
if os.path.islink(args[0]):
orig = os.path.realpath(args[0])
if not new_file:
new_file = args[0]
else:
orig = args[0]
compression = file_extension(orig)
if not new_file:
new_file = options.package + "_" + options.upstream_version + ".orig.tar." + compression
new_file = os.path.realpath(os.path.join(dirname(orig), new_file))
print(orig, new_file)
filter_tar(orig, new_file, options.filter, options.topdir)
if __name__ == '__main__':
main()
|
