1
# Copyright (C) 2006 Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
17
"""Lazily compiled regex objects.
19
This module defines a class which creates proxy objects for regex
20
compilation. This allows overriding re.compile() to return lazily compiled
23
We do this rather than just providing a new interface so that it will also
24
be used by existing Python modules that create regexs.
29
from bzrlib import errors
32
class LazyRegex(object):
33
"""A proxy around a real regex, which won't be compiled until accessed."""
36
# These are the parameters on a real _sre.SRE_Pattern object, which we
37
# will map to local members so that we don't have the proxy overhead.
38
_regex_attributes_to_copy = [
39
'__copy__', '__deepcopy__', 'findall', 'finditer', 'match',
40
'scanner', 'search', 'split', 'sub', 'subn'
43
# We use slots to keep the overhead low. But we need a slot entry for
44
# all of the attributes we will copy
45
__slots__ = ['_real_regex', '_regex_args', '_regex_kwargs',
46
] + _regex_attributes_to_copy
48
def __init__(self, args=(), kwargs={}):
49
"""Create a new proxy object, passing in the args to pass to re.compile
51
:param args: The `*args` to pass to re.compile
52
:param kwargs: The `**kwargs` to pass to re.compile
54
self._real_regex = None
55
self._regex_args = args
56
self._regex_kwargs = kwargs
58
def _compile_and_collapse(self):
59
"""Actually compile the requested regex"""
60
self._real_regex = self._real_re_compile(*self._regex_args,
62
for attr in self._regex_attributes_to_copy:
63
setattr(self, attr, getattr(self._real_regex, attr))
65
def _real_re_compile(self, *args, **kwargs):
66
"""Thunk over to the original re.compile"""
68
return _real_re_compile(*args, **kwargs)
70
# raise InvalidPattern instead of re.error as this gives a
71
# cleaner message to the user.
72
raise errors.InvalidPattern('"' + args[0] + '" ' +str(e))
74
def __getattr__(self, attr):
75
"""Return a member from the proxied regex object.
77
If the regex hasn't been compiled yet, compile it
79
if self._real_regex is None:
80
self._compile_and_collapse()
81
# Once we have compiled, the only time we should come here
82
# is actually if the attribute is missing.
83
return getattr(self._real_regex, attr)
86
def lazy_compile(*args, **kwargs):
87
"""Create a proxy object which will compile the regex on demand.
89
:return: a LazyRegex proxy object.
91
return LazyRegex(args, kwargs)
94
def install_lazy_compile():
95
"""Make lazy_compile the default compile mode for regex compilation.
97
This overrides re.compile with lazy_compile. To restore the original
98
functionality, call reset_compile().
100
re.compile = lazy_compile
104
"""Restore the original function to re.compile().
106
It is safe to call reset_compile() multiple times, it will always
107
restore re.compile() to the value that existed at import time.
108
Though the first call will reset back to the original (it doesn't
111
re.compile = _real_re_compile
114
_real_re_compile = re.compile
115
if _real_re_compile is lazy_compile:
116
raise AssertionError(
117
"re.compile has already been overridden as lazy_compile, but this would" \
118
" cause infinite recursion")