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
|
#!/usr/bin/python
# mlpatch.py: Run with no arguments for usage
import sys, os
import sgmllib
from htmlentitydefs import entitydefs
import fileinput
from urllib2 import urlopen
CHUNKSIZE = 8 * 1024
class MyParser(sgmllib.SGMLParser):
def __init__(self):
self.baseclass = sgmllib.SGMLParser
self.baseclass.__init__(self)
self.entitydefs = entitydefs
self.entitydefs["nbsp"] = " "
self.inbody = False
self.complete_line = False
self.discard_gathered()
def discard_gathered(self):
self.gather_data = False
self.gathered_data = ""
def noop(self):
pass
def out(self, data):
sys.stdout.write(data)
def handle_starttag(self, tag, method, attrs):
if not self.inbody: return
self.baseclass.handle_starttag(self, tag, method, attrs)
def handle_endtag(self, tag, method):
if not self.inbody: return
self.baseclass.handle_endtag(self, tag, method)
def handle_data(self, data):
if not self.inbody: return
data = data.replace('\n','')
if len(data) == 0: return
if self.gather_data:
self.gathered_data += data
else:
if self.complete_line:
if data[0] in ('+', '-', ' ', '#') \
or data.startswith("Index:") \
or data.startswith("@@ ") \
or data.startswith("======"):
# Real new line
self.out('\n')
else:
# Presume that we are wrapped
self.out(' ')
self.complete_line = False
self.out(data)
def handle_charref(self, ref):
if not self.inbody: return
self.baseclass.handle_charref(self, ref)
def handle_entityref(self, ref):
if not self.inbody: return
self.baseclass.handle_entityref(self, ref)
def handle_comment(self, comment):
if comment == ' body="start" ':
self.inbody = True
elif comment == ' body="end" ':
self.inbody = False
def handle_decl(self, data):
if not self.inbody: return
print "DECL: " + data
def unknown_starttag(self, tag, attrs):
if not self.inbody: return
print "UNKTAG: %s %s" % (tag, attrs)
def unknown_endtag(self, tag):
if not self.inbody: return
print "UNKTAG: /%s" % (tag)
def do_br(self, attrs):
self.complete_line = True
def do_p(self, attrs):
if self.complete_line:
self.out('\n')
self.out(' ')
self.complete_line = True
def start_a(self, attrs):
self.gather_data = True
def end_a(self):
self.out(self.gathered_data.replace('_at_', '@'))
self.discard_gathered()
def close(self):
if self.complete_line:
self.out('\n')
self.baseclass.close(self)
def main():
if len(sys.argv) == 1:
sys.stderr.write(
"usage: mlpatch.py dev|users year month msgno > foobar.patch\n" +
"example: mlpatch.py dev 2005 01 0001 > issue-XXXX.patch\n" +
"""
Very annoyingly, the http://svn.haxx.se/ subversion mailing list archives
mangle inline patches, and provide no raw message download facility
(other than for an entire month's email as an mbox).
So, I wrote this script, to demangle them. It's not perfect, as it has to
guess about whitespace, but it does an acceptable job.\n""")
sys.exit(0)
elif len(sys.argv) != 5:
sys.stderr.write("error: mlpatch.py: Bad parameters - run with no "
+ "parameters for usage\n")
sys.exit(1)
else:
list, year, month, msgno = sys.argv[1:]
url = "http://svn.haxx.se/" \
+ "%(list)s/archive-%(year)s-%(month)s/%(msgno)s.shtml" % locals()
print "MsgUrl: " + url
msgfile = urlopen(url)
p = MyParser()
buffer = msgfile.read(CHUNKSIZE)
while buffer:
p.feed(buffer)
buffer = msgfile.read(CHUNKSIZE)
p.close()
msgfile.close()
if __name__ == '__main__':
main()
|
