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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Codetags finder
~~~~~~~~~~~~~~~
Find code tags in specified files and/or directories
and create a report in HTML format.
:copyright: Copyright 2006-2010 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys, os, re
import getopt
from os.path import join, abspath, isdir, isfile
TAGS = set(('XXX', 'TODO', 'FIXME', 'HACK'))
tag_re = re.compile(
r'(?P<tag>\b' + r'\b|\b'.join(TAGS) + r'\b)\s*'
r'(?: \( (?P<who> .*? ) \) )?'
r'\s*:?\s* (?P<what> .*? ) \s* $',
re.X)
binary_re = re.compile('[\x00-\x06\x0E-\x1F]')
def escape_html(text):
return text.replace('&', '&'). \
replace('<', '<'). \
replace('>', '>'). \
replace('"', '"')
def process_file(store, filename):
try:
f = open(filename, 'r')
except (IOError, OSError):
return False
llmatch = 0
try:
for lno, line in enumerate(f):
# just some random heuristics to filter out binary files
if lno < 100 and binary_re.search(line):
return False
m = tag_re.search(line)
if m:
store.setdefault(filename, []).append({
'lno': lno+1,
'tag': m.group('tag'),
'who': m.group('who') or '',
'what': escape_html(m.group('what')),
})
# 'what' cannot start at column 0
llmatch = m.start('what')
elif llmatch:
# continuation lines
# XXX: this is Python centric, doesn't work for
# JavaScript, for example.
if line[:llmatch].replace('#', '').isspace():
cont = line[llmatch:].strip()
if cont:
store[filename][-1]['what'] += ' ' + escape_html(cont)
continue
llmatch = 0
return True
finally:
f.close()
def main():
try:
gopts, args = getopt.getopt(sys.argv[1:], "vo:i:")
except getopt.GetoptError:
print ("Usage: %s [-v] [-i ignoredir]* [-o reportfile.html] "
"path ..." % sys.argv[0])
return 2
opts = {}
for opt, val in gopts:
if opt == '-i':
val = abspath(val)
opts.setdefault(opt, []).append(val)
if not args:
args = ['.']
if '-o' in opts:
output = abspath(opts['-o'][-1])
else:
output = abspath('tags.html')
verbose = '-v' in opts
store = {}
gnum = 0
num = 0
for path in args:
print "Searching for code tags in %s, please wait." % path
if isfile(path):
gnum += 1
if process_file(store, path):
if verbose:
print path + ": found %d tags" % \
(path in store and len(store[path]) or 0)
num += 1
else:
if verbose:
print path + ": binary or not readable"
continue
elif not isdir(path):
continue
for root, dirs, files in os.walk(path):
if '-i' in opts and abspath(root) in opts['-i']:
del dirs[:]
continue
if '.svn' in dirs:
dirs.remove('.svn')
for fn in files:
gnum += 1
if gnum % 50 == 0 and not verbose:
sys.stdout.write('.')
sys.stdout.flush()
fn = join(root, fn)
if fn.endswith('.pyc') or fn.endswith('.pyo'):
continue
elif '-i' in opts and abspath(fn) in opts['-i']:
continue
elif abspath(fn) == output:
continue
if fn[:2] == './': fn = fn[2:]
if process_file(store, fn):
if verbose:
print fn + ": found %d tags" % \
(fn in store and len(store[fn]) or 0)
num += 1
else:
if verbose:
print fn + ": binary or not readable"
print
print "Processed %d of %d files. Found %d tags in %d files." % (
num, gnum, sum(len(fitem) for fitem in store.itervalues()), len(store))
if not store:
return 0
HTML = '''\
<html>
<head>
<title>Code tags report</title>
<style type="text/css">
body { font-family: Trebuchet MS,Verdana,sans-serif;
width: 80%%; margin-left: auto; margin-right: auto; }
table { width: 100%%; border-spacing: 0;
border: 1px solid #CCC; }
th { font-weight: bold; background-color: #DDD }
td { padding: 2px 5px 2px 5px;
vertical-align: top; }
.tr0 { background-color: #EEEEEE; }
.tr1 { background-color: #F6F6F6; }
.tag { text-align: center; font-weight: bold; }
.tr0 .tag { background-color: #FFEEEE; }
.tr1 .tag { background-color: #FFDDDD; }
.head { padding-top: 10px; font-size: 100%%; font-weight: bold }
.XXX { color: #500; }
.FIXME { color: red; }
.TODO { color: #880; }
</style>
</head>
<body>
<h1>Code tags report for %s</h1>
<table>
<tr><th>Line</th><th>Tag</th><th>Who</th><th>Description</th></tr>
%s
</table>
</body>
</html>
'''
TABLE = '\n<tr><td class="head" colspan="4">File: %s</td>\n'
TR = ('<tr class="tr%d"><td class="lno">%%(lno)d</td>'
'<td class="tag %%(tag)s">%%(tag)s</td>'
'<td class="who">%%(who)s</td><td class="what">%%(what)s</td></tr>')
f = file(output, 'w')
table = '\n'.join(TABLE % fname +
'\n'.join(TR % (no % 2,) % entry
for no, entry in enumerate(store[fname]))
for fname in sorted(store))
f.write(HTML % (', '.join(map(abspath, args)), table))
f.close()
print "Report written to %s." % output
return 0
if __name__ == '__main__':
sys.exit(main())
|
