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
|
# Copyright (C) 2006, 2008 Canonical Ltd
# This program 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.
#
# This program 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 this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
"""Tools for converting globs to regular expressions.
This module provides functions for converting shell-like globs to regular
expressions.
"""
import re
from bzrlib.trace import (
warning
)
class Replacer(object):
"""Do a multiple-pattern substitution.
The patterns and substitutions are combined into one, so the result of
one replacement is never substituted again. Add the patterns and
replacements via the add method and then call the object. The patterns
must not contain capturing groups.
"""
_expand = re.compile(ur'\\&')
def __init__(self, source=None):
self._pat = None
if source:
self._pats = list(source._pats)
self._funs = list(source._funs)
else:
self._pats = []
self._funs = []
def add(self, pat, fun):
r"""Add a pattern and replacement.
The pattern must not contain capturing groups.
The replacement might be either a string template in which \& will be
replaced with the match, or a function that will get the matching text
as argument. It does not get match object, because capturing is
forbidden anyway.
"""
self._pat = None
self._pats.append(pat)
self._funs.append(fun)
def add_replacer(self, replacer):
r"""Add all patterns from another replacer.
All patterns and replacements from replacer are appended to the ones
already defined.
"""
self._pat = None
self._pats.extend(replacer._pats)
self._funs.extend(replacer._funs)
def __call__(self, text):
if not self._pat:
self._pat = re.compile(
u'|'.join([u'(%s)' % p for p in self._pats]),
re.UNICODE)
return self._pat.sub(self._do_sub, text)
def _do_sub(self, m):
fun = self._funs[m.lastindex - 1]
if hasattr(fun, '__call__'):
return fun(m.group(0))
else:
return self._expand.sub(m.group(0), fun)
_sub_named = Replacer()
_sub_named.add(ur'\[:digit:\]', ur'\d')
_sub_named.add(ur'\[:space:\]', ur'\s')
_sub_named.add(ur'\[:alnum:\]', ur'\w')
_sub_named.add(ur'\[:ascii:\]', ur'\0-\x7f')
_sub_named.add(ur'\[:blank:\]', ur' \t')
_sub_named.add(ur'\[:cntrl:\]', ur'\0-\x1f\x7f-\x9f')
def _sub_group(m):
if m[1] in (u'!', u'^'):
return u'[^' + _sub_named(m[2:-1]) + u']'
return u'[' + _sub_named(m[1:-1]) + u']'
def _invalid_regex(repl):
def _(m):
warning(u"'%s' not allowed within a regular expression. "
"Replacing with '%s'" % (m, repl))
return repl
return _
def _trailing_backslashes_regex(m):
"""Check trailing backslashes.
Does a head count on trailing backslashes to ensure there isn't an odd
one on the end that would escape the brackets we wrap the RE in.
"""
if (len(m) % 2) != 0:
warning(u"Regular expressions cannot end with an odd number of '\\'. "
"Dropping the final '\\'.")
return m[:-1]
return m
_sub_re = Replacer()
_sub_re.add(u'^RE:', u'')
_sub_re.add(u'\((?!\?)', u'(?:')
_sub_re.add(u'\(\?P<.*>', _invalid_regex(u'(?:'))
_sub_re.add(u'\(\?P=[^)]*\)', _invalid_regex(u''))
_sub_re.add(ur'\\+$', _trailing_backslashes_regex)
_sub_fullpath = Replacer()
_sub_fullpath.add(ur'^RE:.*', _sub_re) # RE:<anything> is a regex
_sub_fullpath.add(ur'\[\^?\]?(?:[^][]|\[:[^]]+:\])+\]', _sub_group) # char group
_sub_fullpath.add(ur'(?:(?<=/)|^)(?:\.?/)+', u'') # canonicalize path
_sub_fullpath.add(ur'\\.', ur'\&') # keep anything backslashed
_sub_fullpath.add(ur'[(){}|^$+.]', ur'\\&') # escape specials
_sub_fullpath.add(ur'(?:(?<=/)|^)\*\*+/', ur'(?:.*/)?') # **/ after ^ or /
_sub_fullpath.add(ur'\*+', ur'[^/]*') # * elsewhere
_sub_fullpath.add(ur'\?', ur'[^/]') # ? everywhere
_sub_basename = Replacer()
_sub_basename.add(ur'\[\^?\]?(?:[^][]|\[:[^]]+:\])+\]', _sub_group) # char group
_sub_basename.add(ur'\\.', ur'\&') # keep anything backslashed
_sub_basename.add(ur'[(){}|^$+.]', ur'\\&') # escape specials
_sub_basename.add(ur'\*+', ur'.*') # * everywhere
_sub_basename.add(ur'\?', ur'.') # ? everywhere
def _sub_extension(pattern):
return _sub_basename(pattern[2:])
class Globster(object):
"""A simple wrapper for a set of glob patterns.
Provides the capability to search the patterns to find a match for
a given filename (including the full path).
Patterns are translated to regular expressions to expidite matching.
The regular expressions for multiple patterns are aggregated into
a super-regex containing groups of up to 99 patterns.
The 99 limitation is due to the grouping limit of the Python re module.
The resulting super-regex and associated patterns are stored as a list of
(regex,[patterns]) in _regex_patterns.
For performance reasons the patterns are categorised as extension patterns
(those that match against a file extension), basename patterns
(those that match against the basename of the filename),
and fullpath patterns (those that match against the full path).
The translations used for extensions and basenames are relatively simpler
and therefore faster to perform than the fullpath patterns.
Also, the extension patterns are more likely to find a match and
so are matched first, then the basename patterns, then the fullpath
patterns.
"""
def __init__(self, patterns):
self._regex_patterns = []
path_patterns = []
base_patterns = []
ext_patterns = []
for pat in patterns:
pat = normalize_pattern(pat)
if pat.startswith(u'RE:') or u'/' in pat:
path_patterns.append(pat)
elif pat.startswith(u'*.'):
ext_patterns.append(pat)
else:
base_patterns.append(pat)
self._add_patterns(ext_patterns,_sub_extension,
prefix=r'(?:.*/)?(?!.*/)(?:.*\.)')
self._add_patterns(base_patterns,_sub_basename,
prefix=r'(?:.*/)?(?!.*/)')
self._add_patterns(path_patterns,_sub_fullpath)
def _add_patterns(self, patterns, translator, prefix=''):
while patterns:
grouped_rules = ['(%s)' % translator(pat) for pat in patterns[:99]]
joined_rule = '%s(?:%s)$' % (prefix, '|'.join(grouped_rules))
self._regex_patterns.append((re.compile(joined_rule, re.UNICODE),
patterns[:99]))
patterns = patterns[99:]
def match(self, filename):
"""Searches for a pattern that matches the given filename.
:return A matching pattern or None if there is no matching pattern.
"""
for regex, patterns in self._regex_patterns:
match = regex.match(filename)
if match:
return patterns[match.lastindex -1]
return None
class _OrderedGlobster(Globster):
"""A Globster that keeps pattern order."""
def __init__(self, patterns):
"""Constructor.
:param patterns: sequence of glob patterns
"""
# Note: This could be smarter by running like sequences together
self._regex_patterns = []
for pat in patterns:
pat = normalize_pattern(pat)
if pat.startswith(u'RE:') or u'/' in pat:
self._add_patterns([pat], _sub_fullpath)
elif pat.startswith(u'*.'):
self._add_patterns([pat], _sub_extension,
prefix=r'(?:.*/)?(?!.*/)(?:.*\.)')
else:
self._add_patterns([pat], _sub_basename,
prefix=r'(?:.*/)?(?!.*/)')
_slashes = re.compile(r'[\\/]+')
def normalize_pattern(pattern):
"""Converts backslashes in path patterns to forward slashes.
Doesn't normalize regular expressions - they may contain escapes.
"""
if not pattern.startswith('RE:'):
pattern = _slashes.sub('/', pattern)
if len(pattern) > 1:
pattern = pattern.rstrip('/')
return pattern
|