1
# Copyright (C) 2006 Canonical Ltd
1
# Copyright (C) 2006, 2008 Canonical Ltd
3
3
# This program is free software; you can redistribute it and/or modify
4
4
# it under the terms of the GNU General Public License as published by
13
13
# You should have received a copy of the GNU General Public License
14
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
17
17
"""Tools for converting globs to regular expressions.
53
53
The pattern must not contain capturing groups.
54
54
The replacement might be either a string template in which \& will be
55
replaced with the match, or a function that will get the matching text
56
as argument. It does not get match object, because capturing is
55
replaced with the match, or a function that will get the matching text
56
as argument. It does not get match object, because capturing is
161
161
Patterns are translated to regular expressions to expidite matching.
163
The regular expressions for multiple patterns are aggregated into
164
a super-regex containing groups of up to 99 patterns.
163
The regular expressions for multiple patterns are aggregated into
164
a super-regex containing groups of up to 99 patterns.
165
165
The 99 limitation is due to the grouping limit of the Python re module.
166
166
The resulting super-regex and associated patterns are stored as a list of
167
167
(regex,[patterns]) in _regex_patterns.
169
169
For performance reasons the patterns are categorised as extension patterns
170
170
(those that match against a file extension), basename patterns
171
171
(those that match against the basename of the filename),
172
172
and fullpath patterns (those that match against the full path).
173
The translations used for extensions and basenames are relatively simpler
173
The translations used for extensions and basenames are relatively simpler
174
174
and therefore faster to perform than the fullpath patterns.
176
Also, the extension patterns are more likely to find a match and
176
Also, the extension patterns are more likely to find a match and
177
177
so are matched first, then the basename patterns, then the fullpath
192
192
base_patterns.append(pat)
193
193
self._add_patterns(ext_patterns,_sub_extension,
194
194
prefix=r'(?:.*/)?(?!.*/)(?:.*\.)')
195
self._add_patterns(base_patterns,_sub_basename,
195
self._add_patterns(base_patterns,_sub_basename,
196
196
prefix=r'(?:.*/)?(?!.*/)')
197
self._add_patterns(path_patterns,_sub_fullpath)
197
self._add_patterns(path_patterns,_sub_fullpath)
199
199
def _add_patterns(self, patterns, translator, prefix=''):
201
201
grouped_rules = ['(%s)' % translator(pat) for pat in patterns[:99]]
202
202
joined_rule = '%s(?:%s)$' % (prefix, '|'.join(grouped_rules))
203
self._regex_patterns.append((re.compile(joined_rule, re.UNICODE),
203
self._regex_patterns.append((re.compile(joined_rule, re.UNICODE),
205
205
patterns = patterns[99:]
207
207
def match(self, filename):
208
208
"""Searches for a pattern that matches the given filename.
210
210
:return A matching pattern or None if there is no matching pattern.
212
212
for regex, patterns in self._regex_patterns:
215
215
return patterns[match.lastindex -1]
219
class _OrderedGlobster(Globster):
220
"""A Globster that keeps pattern order."""
222
def __init__(self, patterns):
225
:param patterns: sequence of glob patterns
227
# Note: This could be smarter by running like sequences together
228
self._regex_patterns = []
230
pat = normalize_pattern(pat)
231
if pat.startswith(u'RE:') or u'/' in pat:
232
self._add_patterns([pat], _sub_fullpath)
233
elif pat.startswith(u'*.'):
234
self._add_patterns([pat], _sub_extension,
235
prefix=r'(?:.*/)?(?!.*/)(?:.*\.)')
237
self._add_patterns([pat], _sub_basename,
238
prefix=r'(?:.*/)?(?!.*/)')
241
_slashes = re.compile(r'[\\/]+')
219
242
def normalize_pattern(pattern):
220
243
"""Converts backslashes in path patterns to forward slashes.
222
245
Doesn't normalize regular expressions - they may contain escapes.
224
248
if not pattern.startswith('RE:'):
225
pattern = pattern.replace('\\','/')
226
return pattern.rstrip('/')
249
pattern = _slashes.sub('/', pattern)
251
pattern = pattern.rstrip('/')