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
227
228
229
230
231
232
233
234
235
236
|
#!/usr/bin/env python
# -*- mode: python -*-
# $Id$
import sys
import string
from pcre import *
#
# First, the public part of the interface:
#
# pcre.error and re.error should be the same, since exceptions can be
# raised from either module.
# compilation flags
I = IGNORECASE
M = MULTILINE
S = DOTALL
X = VERBOSE
#
#
#
_cache = {}
_MAXCACHE = 20
def _cachecompile(pattern, flags=0):
key = (pattern, flags)
try:
return _cache[key]
except KeyError:
pass
value = compile(pattern, flags)
if len(_cache) >= _MAXCACHE:
_cache.clear()
_cache[key] = value
return value
def match(pattern, string, flags=0):
return _cachecompile(pattern, flags).match(string)
def search(pattern, string, flags=0):
return _cachecompile(pattern, flags).search(string)
def sub(pattern, repl, string, count=0):
if type(pattern) == type(''):
pattern = _cachecompile(pattern)
return pattern.sub(repl, string, count)
def subn(pattern, repl, string, count=0):
if type(pattern) == type(''):
pattern = _cachecompile(pattern)
return pattern.subn(repl, string, count)
def split(pattern, string, maxsplit=0):
if type(pattern) == type(''):
pattern = _cachecompile(pattern)
return pattern.split(string, maxsplit)
#
#
#
class RegexObject:
def __init__(self, pattern, flags, code, groupindex):
self.code = code
self.flags = flags
self.pattern = pattern
self.groupindex = groupindex
def search(self, string, pos=0):
regs = self.code.match(string, pos, 0)
if regs is None:
return None
self.num_regs=len(regs)
return MatchObject(self,
string,
pos,
regs)
def match(self, string, pos=0):
regs = self.code.match(string, pos, ANCHORED)
if regs is None:
return None
self.num_regs=len(regs)/2
return MatchObject(self,
string,
pos,
regs)
def sub(self, repl, string, count=0):
return self.subn(repl, string, count)[0]
def subn(self, repl, source, count=0):
if count < 0:
raise error, "negative substitution count"
if count == 0:
import sys
count = sys.maxint
if type(repl) == type(''):
if '\\' in repl:
repl = lambda m, r=repl: pcre_expand(m, r)
else:
repl = lambda m, r=repl: r
n = 0 # Number of matches
pos = 0 # Where to start searching
lastmatch = -1 # End of last match
results = [] # Substrings making up the result
end = len(source)
while n < count and pos <= end:
m = self.search(source, pos)
if not m:
break
i, j = m.span(0)
if i == j == lastmatch:
# Empty match adjacent to previous match
pos = pos + 1
results.append(source[lastmatch:pos])
continue
if pos < i:
results.append(source[pos:i])
results.append(repl(m))
pos = lastmatch = j
if i == j:
# Last match was empty; don't try here again
pos = pos + 1
results.append(source[lastmatch:pos])
n = n + 1
results.append(source[pos:])
return (string.join(results, ''), n)
def split(self, source, maxsplit=0):
if maxsplit < 0:
raise error, "negative split count"
if maxsplit == 0:
import sys
maxsplit = sys.maxint
n = 0
pos = 0
lastmatch = 0
results = []
end = len(source)
while n < maxsplit:
m = self.search(source, pos)
if not m:
break
i, j = m.span(0)
if i == j:
# Empty match
if pos >= end:
break
pos = pos+1
continue
results.append(source[lastmatch:i])
g = m.group()
if g:
results[len(results):] = list(g)
pos = lastmatch = j
results.append(source[lastmatch:])
return results
class MatchObject:
def __init__(self, re, string, pos, regs):
self.re = re
self.string = string
self.pos = pos
self.regs = regs
def start(self, g):
if type(g) == type(''):
try:
g = self.re.groupindex[g]
except (KeyError, TypeError):
raise IndexError, ('group "' + g + '" is undefined')
return self.regs[g][0]
def end(self, g):
if type(g) == type(''):
try:
g = self.re.groupindex[g]
except (KeyError, TypeError):
raise IndexError, ('group "' + g + '" is undefined')
return self.regs[g][1]
def span(self, g):
if type(g) == type(''):
try:
g = self.re.groupindex[g]
except (KeyError, TypeError):
raise IndexError, ('group "' + g + '" is undefined')
return self.regs[g]
def group(self, *groups):
if len(groups) == 0:
groups = range(1, self.re.num_regs)
use_all = 1
else:
use_all = 0
result = []
for g in groups:
if type(g) == type(''):
try:
g = self.re.groupindex[g]
except (KeyError, TypeError):
raise IndexError, ('group "' + g + '" is undefined')
if len(self.regs)<=g: raise IndexError, ('group "' + str(g) + '" is undefined')
elif (self.regs[g][0] == -1) or (self.regs[g][1] == -1):
result.append(None)
else:
result.append(self.string[self.regs[g][0]:self.regs[g][1]])
if use_all or len(result) > 1:
return tuple(result)
elif len(result) == 1:
return result[0]
else:
return ()
def escape(pattern):
result = []
alphanum=string.letters+'_'+string.digits
for char in pattern:
if char not in alphanum:
result.append('\\')
result.append(char)
return string.join(result, '')
def compile(pattern, flags=0):
groupindex={}
code=pcre_compile(pattern, flags, groupindex)
return RegexObject(pattern, flags, code, groupindex)
|
