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
214
215
216
|
#!/usr/bin/env python
########################################################################
#
# Copyright (c) 2010 Jonas Jensen, Miklos Vajna
#
# Permission is hereby granted, free of charge, to any person
# obtaining a copy of this software and associated documentation
# files (the "Software"), to deal in the Software without
# restriction, including without limitation the rights to use,
# copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following
# conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.
#
########################################################################
import sys, re, subprocess, os, optparse, string
class Parser:
"""
This parser extracts comments from source files, tries to guess
their language and then prints out the german ones.
"""
def __init__(self):
self.strip = string.punctuation + " \n"
op = optparse.OptionParser()
op.set_usage("%prog [options] <rootdir>\n\n" +
"Searches for german comments in cxx/hxx source files inside a given root\n" +
"directory recursively.")
op.add_option("-f", "--filenames-only", action="store_true", dest="filenames_only", default=False,
help="Only print the filenames of files containing German comments")
op.add_option("-v", "--verbose", action="store_true", dest="verbose", default=False,
help="Turn on verbose mode (print progress to stderr)")
op.add_option("-l", "--line-numbers", action="store_true", dest="line_numbers", default=False,
help="Prints the filenames and line numbers only.")
op.add_option("-t", "--threshold", action="store", dest="THRESHOLD", default=0,
help="When used with '--line-numbers', only bothers outputting comment info if there are more than X number of flagged comments. Useful for weeding out false positives.")
self.options, args = op.parse_args()
try:
dir = args[0]
except IndexError:
dir = "."
self.check_source_files(dir)
def get_comments(self, filename):
"""
Extracts the source code comments.
"""
linenum = 0
if self.options.verbose:
sys.stderr.write("processing file '%s'...\n" % filename)
sock = open(filename)
# add an empty line to trigger the output of collected oneliner
# comment group
lines = sock.readlines() + ["\n"]
sock.close()
in_comment = False
buf = []
count = 1
for i in lines:
if "//" in i and not in_comment:
# if we find a new //-style comment, then we
# just append it to a previous one if: there is
# only whitespace before the // mark that is
# necessary to make comments longer, giving
# more reliable output
if not len(re.sub("(.*)//.*", r"\1", i).strip(self.strip)):
s = re.sub(".*// ?", "", i).strip(self.strip)
if len(s):
buf.append(s)
else:
# otherwise it's an independent //-style comment in the next line
yield (count, "\n ".join(buf))
buf = [re.sub(".*// ?", "", i.strip(self.strip))]
elif "//" not in i and not in_comment and len(buf) > 0:
# first normal line after a // block
yield (count, "\n ".join(buf))
buf = []
elif "/*" in i and "*/" not in i and not in_comment:
# start of a real multiline comment
in_comment = True
linenum = count
s = re.sub(".*/\*+", "", i.strip(self.strip))
if len(s):
buf.append(s.strip(self.strip))
elif in_comment and not "*/" in i:
# in multiline comment
s = re.sub("^( |\|)*\*?", "", i)
if len(s.strip(self.strip)):
buf.append(s.strip(self.strip))
elif "*/" in i and in_comment:
# end of multiline comment
in_comment = False
s = re.sub(r"\*+/.*", "", i.strip(self.strip))
if len(s):
buf.append(s)
yield (count, "\n ".join(buf))
buf = []
elif "/*" in i and "*/" in i:
# c-style oneliner comment
yield (count, re.sub(".*/\*(.*)\*/.*", r"\1", i).strip(self.strip))
count += 1
def get_lang(self, s):
""" the output is 'german' or 'english' or 'german or english'. when
unsure, just don't warn, there are strings where you just can't
teremine the results reliably, like '#110680#' """
cwd = os.getcwd()
# change to our directory
os.chdir(os.path.split(os.path.abspath(sys.argv[0]))[0])
sock = subprocess.Popen(["text_cat/text_cat", "-d", "text_cat/LM"], stdin=subprocess.PIPE, stdout=subprocess.PIPE)
sock.stdin.write(s)
sock.stdin.close()
lang = sock.stdout.read().strip()
sock.stdout.close()
os.chdir(cwd)
return lang
def is_german(self, s):
"""
determines if a string is german or not
"""
# for short strings we can't do reliable recognition, so skip
# short strings and less than 4 words
s = s.replace('\n', ' ')
if len(s) < 32 or len(s.split()) < 4:
return False
return "german" == self.get_lang(s)
def check_file(self, path):
"""
checks each comment in a file
"""
def tab_calc (string):
START = 40 #Default of 10 tabs
if len(string) >= START:
return 1, 0
diff = START - len(string)
if diff % 4 is not 0:
padding = 1
else:
padding = 0
return (diff/4)+padding
if self.options.line_numbers:
TABS = "\t"*10
path_linenums = []
for linenum, s in self.get_comments(path):
if self.is_german(s):
path_linenums.append(linenum)
valid = len(path_linenums) > int(self.options.THRESHOLD)
sys.stderr.write("%s ... %s positives -- %s\n" % (path, str(len(path_linenums)), str(valid)))
if valid:
if len(path) + (len(path_linenums)*4) > 75:
print "%s:\n" % path
while(path_linenums):
i = 0
numline = []
while i < 10:
try:
numline.append(path_linenums[0])
path_linenums.remove(path_linenums[0])
except IndexError:
i = 10
i+=1
numline = [str(i) for i in numline]
print "%s%s" %(TABS, ",".join(numline))
else:
path_linenums = [str(i) for i in path_linenums]
print "%s:%s%s" % (path,"\t"*tab_calc(path),",".join(path_linenums))
elif not self.options.filenames_only:
for linenum, s in self.get_comments(path):
if self.is_german(s):
print "%s:%s: %s" % (path, linenum, s)
else:
fnames = set([])
for linenum, s in self.get_comments(path):
if self.is_german(s):
# Make sure we print each filename only once
fnames.add(path)
# Print the filenames
for f in fnames:
print f
def check_source_files(self, dir):
"""
checks each _tracked_ file in a directory recursively
"""
sock = os.popen(r"git ls-files '%s' |egrep '\.(c|h)xx$'" % dir)
lines = sock.readlines()
sock.close()
for path in lines:
self.check_file(path.strip())
try:
Parser()
except KeyboardInterrupt:
print "Interrupted!"
sys.exit(0)
# vim:set shiftwidth=4 softtabstop=4 expandtab:
|
