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
|
#!/usr/bin/python
from optparse import OptionParser
import os
import re
import sys
import datetime
report = {}
wordscore = {}
filescore = {}
filelist = list()
skipped = 0
opened = 0
datasize = 0
progresstext = ""
def sortscore(score, reverse=False):
sortedscore = sorted(score.items(), key=lambda score: score[1], reverse=reverse)
returnscore = []
for s in sortedscore:
if s[1] > 0:
returnscore.append(s)
return returnscore
def printscore(report):
for i in report:
print i[0] + ':' + str(i[1])
def wholeword(word, string):
re.purge()
matches = []
regexU = r'([A-Z]|[^a-zA-Z]|\b)(' + re.escape(word.lower()) + r')([A-Z]|[^a-zA-Z]|\b)'
regexL = r'([a-z]|[^a-zA-Z]|\b)(' + re.escape(word.upper()) + r')([a-z]|[^a-zA-Z]|\b)'
mU = re.search(regexU, string)
if "groups" in dir(mU):
matches.append(mU.groups())
re.purge()
mL = re.search(regexL, string)
if "groups" in dir(mL):
matches.append(mL.groups())
return matches
def skipfile(filename,skippedexts):
if not isinstance(skippedexts, list):
return False
for skip in skippedexts:
if filename.endswith(skip):
return True
return False
def scoretext(wordlist, text, maxwholewordlen = -1):
score = {}
for word in wordlist:
if int(len(word)) > int(maxwholewordlen):
score[word] = text.lower().count(word.lower())
else:
score[word] = len(wholeword(word,text))
return score
parser = OptionParser()
parser.add_option("-f", "--file", dest="suspiciousfilename", help="specify file to scan", action="append")
parser.add_option("-w", "--wordlist", dest="wordlistfilename", help="file containing all of the words to look for")
parser.add_option("-s", "--skip", dest="skipfileextensions", help="file extensions to skip", action="append")
parser.add_option("-v", "--verbose", dest="verbose", help="print verberose information", default=False, action="store_true")
parser.add_option("-r", "--report", dest="printreport", default="w", help="print score")
parser.add_option("--show-wordlist", dest="show_wordlist", default=False, help="print list of words to detect", action="store_true")
parser.add_option("-c", "--display-counts", dest="display_counts", default=False, help="Show the num ber of files processed", action="store_true")
parser.add_option("-p", "--display_progress", dest="display_progress", default=False, help="show percentage complete", action="store_true")
parser.add_option("-l", "--max-wholeword-length", dest="maxwholewordlength", type="int", default=-1, help="maximun length of a word allowed to only find matches on whole word")
parser.add_option("-o", "--summary-file", dest="summaryfile", help="name of the file to store the summary in")
parser.add_option("-x", "--display-summary", dest="displaysummary", default=False, help="Display a summary from the summary file", action="store_true")
(options, args) = parser.parse_args()
if options.wordlistfilename:
wordlist = list(set(open(options.wordlistfilename).read().lower().strip().split('\n')))
if options.show_wordlist: print wordlist; exit()
for a in args:
#filelist.append(a)
for (path, dirs, files) in os.walk(a):
if 'CVS' in dirs:
dirs.remove('CVS')
if '.git' in dirs:
dirs.remove('.git')
if '.bzr' in dirs:
dirs.remove('.bzr')
if '.hg' in dirs:
dirs.remove('.hg')
if '.svn' in dirs:
dirs.remove('.svn')
for file in files:
filelist.append(path + '/' + file)
if options.suspiciousfilename:
filelist += options.suspiciousfilename
if options.summaryfile:
summaryfile = open(summaryfile, 'w')
start = datetime.datetime.now()
for file in filelist:
if skipfile(file, options.skipfileextensions):
skipped += 1
continue
try:
f = open(file)
except:
print "failed to open: " + file
continue
opened +=1
now = datetime.datetime.now()
estimate = (((now - start) / (opened + skipped)) * len(filelist))
if options.display_progress:
print '\r' + " " * len(progresstext) + '\r',
progresstext = str(((opened + skipped)*1.0/len(filelist))*100)[:5] + '% '+ " time left:" + str(estimate).split('.')[0] + ' ' + file + '\r'
print progresstext,
sys.stdout.flush()
filecontents = f.read()
datasize += len(filecontents)
filenamescore = scoretext(wordlist, file, options.maxwholewordlength)
filecontentsscore = scoretext(wordlist, filecontents, options.maxwholewordlength)
report[file] = {}
for k in filecontentsscore.keys():
report[file][k] = filenamescore[k] + filecontentsscore[k]
def scorewords(report):
for file in report.keys():
for word in report[file].keys():
if not word in wordscore:
wordscore[word] = 0
if not file in filescore:
filescore[file] = 0
wordscore[word] += report[file][word]
return wordscore
def scorefile(report):
for file in report.keys():
for word in report[file].keys():
if not word in wordscore:
wordscore[word] = 0
if not file in filescore:
filescore[file] = 0
filescore[file] += report[file][word]
return filescore
def summary(report):
filescore = scorefile(report)
text = ""
for file in sortscore(filescore):
text += file[0] + '(' + str(file[1]) + '):'
for word in report[file[0]].keys():
if report[file[0]][word] > 0:
text += word + '(' + str(report[file[0]][word]) + ');'
text += '\n'
return text
if options.printreport:
if options.printreport == "f":
printscore(sortscore(scorefile(report)))
elif options.printreport == "wf" or options.printreport == "fw":
print summary(report)
else:
printscore(sortscore(scorewords(report)))
if options.display_counts:
print "total files:" + str(len(filelist)) ,
print "suspicious files:" + str(len(sortscore(filescore))) ,
print "skipped files:" + str(skipped) ,
print "searched:" + str(datasize) + 'B',
print "time:" + str(datetime.datetime.now() - start).split('.')[0]
def test():
print wholeword("ear","bearth")
print wholeword("ear","BearTH")
print wholeword("ear","bEARth")
print wholeword("ear","ear_")
print wholeword("ear","ear()")
print wholeword("ear","ear.")
print wholeword("ear","ear:")
print wholeword("ear","ear\n\r")
print wholeword("ear","myEAR() MYear: myEAR()")
#test()
|
