1
# Copyright (C) 2006 Canonical
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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17
# TODO: Some kind of command-line display of revision properties:
18
# perhaps show them in log -v and allow them as options to the commit command.
20
"""Some functions to enable caching the conversion between unicode to utf8"""
23
# Map revisions from and to utf8 encoding
24
# Whenever we do an encode/decode operation, we save the result, so that
25
# we don't have to do it again.
26
_unicode_to_utf8_map = {}
27
_utf8_to_unicode_map = {}
30
def encode(unicode_str,
31
_uni_to_utf8=_unicode_to_utf8_map,
32
_utf8_to_uni=_utf8_to_unicode_map):
33
"""Take this unicode revision id, and get a unicode version"""
34
# If the key is in the cache try/KeyError is 50% faster than
35
# val = dict.get(key), if val is None:
36
# On jam's machine the difference is
39
# Since these are primarily used when iterating over a knit entry
40
# *most* of the time the key will already be in the cache, so use the
43
return _uni_to_utf8[unicode_str]
45
_uni_to_utf8[unicode_str] = utf8_str = unicode_str.encode('utf-8')
46
_utf8_to_uni[utf8_str] = unicode_str
51
_uni_to_utf8=_unicode_to_utf8_map,
52
_utf8_to_uni=_utf8_to_unicode_map):
53
"""Take a utf8 revision id, and decode it, but cache the result"""
55
return _utf8_to_uni[utf8_str]
57
_utf8_to_uni[utf8_str] = unicode_str = utf8_str.decode('utf-8')
58
_uni_to_utf8[unicode_str] = utf8_str
62
def get_cached_unicode(unicode_str):
63
"""Return a cached version of the unicode string.
65
This has a similar idea to that of intern() in that it tries
66
to return a singleton string. Only it works for unicode strings.
68
# This might return the same object, or it might return the cached one
69
# the decode() should just be a hash lookup, because the encode() side
70
# should add the entry to the maps
71
return decode(encode(unicode_str))
74
def clear_encoding_cache():
75
"""Clear the encoding and decoding caches"""
76
global _unicode_to_utf8_map, _utf8_to_unicode_map
77
_unicode_to_utf8_map.clear()
78
_utf8_to_unicode_map.clear()
added
removed
bzrlib/cache_utf8.py
