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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294
|
#!/usr/bin/env python
# -*- mode: python -*-
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
L = LOCALE
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)
def escape(pattern):
"Escape all non-alphanumeric characters in pattern."
result = []
alphanum=string.letters+'_'+string.digits
for char in pattern:
if char not in alphanum:
if char=='\000': result.append('\\000')
else: result.append('\\'+char)
else: result.append(char)
return string.join(result, '')
def compile(pattern, flags=0):
"Compile a regular expression pattern, returning a RegexObject."
groupindex={}
code=pcre_compile(pattern, flags, groupindex)
return RegexObject(pattern, flags, code, groupindex)
#
# Class definitions
#
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, endpos=None):
"""Scan through string looking for a match to the pattern, returning
a MatchObject instance, or None if no match was found."""
if endpos is None or endpos>len(string):
endpos=len(string)
if endpos<pos: endpos=pos
regs = self.code.match(string, pos, endpos, 0)
if regs is None:
return None
self._num_regs=len(regs)
return MatchObject(self,
string,
pos, endpos,
regs)
def match(self, string, pos=0, endpos=None):
"""Try to apply the pattern at the start of the string, returning
a MatchObject instance, or None if no match was found."""
if endpos is None or endpos>len(string):
endpos=len(string)
if endpos<pos: endpos=pos
regs = self.code.match(string, pos, endpos, ANCHORED)
if regs is None:
return None
self._num_regs=len(regs)
return MatchObject(self,
string,
pos, endpos,
regs)
def sub(self, repl, string, count=0):
"""Return the string obtained by replacing the leftmost
non-overlapping occurrences of the pattern in string by the
replacement repl"""
return self.subn(repl, string, count)[0]
def subn(self, repl, source, count=0):
"""Return a 2-tuple containing (new_string, number).
new_string is the string obtained by replacing the leftmost
non-overlapping occurrences of the pattern in the source
string by the replacement repl. number is the number of
substitutions that were made."""
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):
"""Split the \var{source} string by the occurrences of the pattern,
returning a list containing the resulting substrings."""
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.groups()
if g:
if type(g)==type( "" ): g = [g]
results[len(results):] = list(g)
pos = lastmatch = j
n = n + 1
results.append(source[lastmatch:])
return results
# The following 3 functions were contributed by Mike Fletcher, and
# allow pickling and unpickling of RegexObject instances.
def __getinitargs__(self):
return (None,None,None,None) # any 4 elements, to work around
# problems with the
# pickle/cPickle modules not yet
# ignoring the __init__ function
def __getstate__(self):
return self.pattern, self.flags, self.groupindex
def __setstate__(self, statetuple):
self.pattern = statetuple[0]
self.flags = statetuple[1]
self.groupindex = statetuple[2]
self.code = apply(pcre_compile, statetuple)
class MatchObject:
def __init__(self, re, string, pos, endpos, regs):
self.re = re
self.string = string
self.pos = pos
self.endpos = endpos
self.regs = regs
def start(self, g = 0):
"Return the start of the substring matched by group 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 = 0):
"Return the end of the substring matched by group 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 = 0):
"""Return a tuple containing the start,end of the substring
matched by group 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 groups(self):
"Return a tuple containing all subgroups of the match object"
result = []
for g in range(1, self.re._num_regs):
if (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]])
return tuple(result)
def group(self, *groups):
"Return one or more groups of the match."
if len(groups) == 0:
groups = (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 len(result) > 1:
return tuple(result)
elif len(result) == 1:
return result[0]
else:
return ()
|