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
217
218
219
220
221
222
223
224
225
226
|
# emacs: -*- mode: python; py-indent-offset: 4; indent-tabs-mode: t -*-
# vi: set ft=python sts=4 ts=4 sw=4 noet :
# This file is part of Fail2Ban.
#
# Fail2Ban is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# Fail2Ban is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Fail2Ban; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
__author__ = "Cyril Jaquier"
__copyright__ = "Copyright (c) 2004 Cyril Jaquier"
__license__ = "GPL"
import re, sre_constants, sys
##
# Regular expression class.
#
# This class represents a regular expression with its compiled version.
class Regex:
##
# Constructor.
#
# Creates a new object. This method can throw RegexException in order to
# avoid construction of invalid object.
# @param value the regular expression
def __init__(self, regex):
self._matchCache = None
# Perform shortcuts expansions.
# Replace "<HOST>" with default regular expression for host.
regex = regex.replace("<HOST>", "(?:::f{4,6}:)?(?P<host>[\w\-.^_]*\w)")
# Replace "<SKIPLINES>" with regular expression for multiple lines.
regexSplit = regex.split("<SKIPLINES>")
regex = regexSplit[0]
for n, regexLine in enumerate(regexSplit[1:]):
regex += "\n(?P<skiplines%i>(?:(.*\n)*?))" % n + regexLine
if regex.lstrip() == '':
raise RegexException("Cannot add empty regex")
try:
self._regexObj = re.compile(regex, re.MULTILINE)
self._regex = regex
except sre_constants.error:
raise RegexException("Unable to compile regular expression '%s'" %
regex)
def __str__(self):
return "%s(%r)" % (self.__class__.__name__, self._regex)
##
# Gets the regular expression.
#
# The effective regular expression used is returned.
# @return the regular expression
def getRegex(self):
return self._regex
##
# Searches the regular expression.
#
# Sets an internal cache (match object) in order to avoid searching for
# the pattern again. This method must be called before calling any other
# method of this object.
# @param a list of tupples. The tupples are ( prematch, datematch, postdatematch )
def search(self, tupleLines):
self._matchCache = self._regexObj.search(
"\n".join("".join(value[::2]) for value in tupleLines) + "\n")
if self.hasMatched():
# Find start of the first line where the match was found
try:
self._matchLineStart = self._matchCache.string.rindex(
"\n", 0, self._matchCache.start() +1 ) + 1
except ValueError:
self._matchLineStart = 0
# Find end of the last line where the match was found
try:
self._matchLineEnd = self._matchCache.string.index(
"\n", self._matchCache.end() - 1) + 1
except ValueError:
self._matchLineEnd = len(self._matchCache.string)
lineCount1 = self._matchCache.string.count(
"\n", 0, self._matchLineStart)
lineCount2 = self._matchCache.string.count(
"\n", 0, self._matchLineEnd)
self._matchedTupleLines = tupleLines[lineCount1:lineCount2]
self._unmatchedTupleLines = tupleLines[:lineCount1]
n = 0
for skippedLine in self.getSkippedLines():
for m, matchedTupleLine in enumerate(
self._matchedTupleLines[n:]):
if "".join(matchedTupleLine[::2]) == skippedLine:
self._unmatchedTupleLines.append(
self._matchedTupleLines.pop(n+m))
n += m
break
self._unmatchedTupleLines.extend(tupleLines[lineCount2:])
# Checks if the previous call to search() matched.
#
# @return True if a match was found, False otherwise
def hasMatched(self):
if self._matchCache:
return True
else:
return False
##
# Returns skipped lines.
#
# This returns skipped lines captured by the <SKIPLINES> tag.
# @return list of skipped lines
def getSkippedLines(self):
if not self._matchCache:
return []
skippedLines = ""
n = 0
while True:
try:
if self._matchCache.group("skiplines%i" % n) is not None:
skippedLines += self._matchCache.group("skiplines%i" % n)
n += 1
except IndexError:
break
# KeyError is because of PyPy issue1665 affecting pypy <= 2.2.1
except KeyError:
if 'PyPy' not in sys.version: # pragma: no cover - not sure this is even reachable
raise
break
return skippedLines.splitlines(False)
##
# Returns unmatched lines.
#
# This returns unmatched lines including captured by the <SKIPLINES> tag.
# @return list of unmatched lines
def getUnmatchedTupleLines(self):
if not self.hasMatched():
return []
else:
return self._unmatchedTupleLines
def getUnmatchedLines(self):
if not self.hasMatched():
return []
else:
return ["".join(line) for line in self._unmatchedTupleLines]
##
# Returns matched lines.
#
# This returns matched lines by excluding those captured
# by the <SKIPLINES> tag.
# @return list of matched lines
def getMatchedTupleLines(self):
if not self.hasMatched():
return []
else:
return self._matchedTupleLines
def getMatchedLines(self):
if not self.hasMatched():
return []
else:
return ["".join(line) for line in self._matchedTupleLines]
##
# Exception dedicated to the class Regex.
class RegexException(Exception):
pass
##
# Regular expression class.
#
# This class represents a regular expression with its compiled version.
class FailRegex(Regex):
##
# Constructor.
#
# Creates a new object. This method can throw RegexException in order to
# avoid construction of invalid object.
# @param value the regular expression
def __init__(self, regex):
# Initializes the parent.
Regex.__init__(self, regex)
# Check for group "host"
if "host" not in self._regexObj.groupindex:
raise RegexException("No 'host' group in '%s'" % self._regex)
##
# Returns the matched host.
#
# This corresponds to the pattern matched by the named group "host".
# @return the matched host
def getHost(self):
host = self._matchCache.group("host")
if host is None:
# Gets a few information.
s = self._matchCache.string
r = self._matchCache.re
raise RegexException("No 'host' found in '%s' using '%s'" % (s, r))
return str(host)
|
