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., 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"""
25
_utf8_encode = codecs.getencoder("utf-8")
26
_utf8_decode = codecs.getdecoder("utf-8")
28
# Map revisions from and to utf8 encoding
29
# Whenever we do an encode/decode operation, we save the result, so that
30
# we don't have to do it again.
31
_unicode_to_utf8_map = {}
32
_utf8_to_unicode_map = {}
35
def encode(unicode_str,
36
_uni_to_utf8=_unicode_to_utf8_map,
37
_utf8_to_uni=_utf8_to_unicode_map,
38
_utf8_encode=_utf8_encode):
39
"""Take this unicode revision id, and get a unicode version"""
40
# If the key is in the cache try/KeyError is 50% faster than
41
# val = dict.get(key), if val is None:
42
# On jam's machine the difference is
45
# Since these are primarily used when iterating over a knit entry
46
# *most* of the time the key will already be in the cache, so use the
49
return _uni_to_utf8[unicode_str]
51
_uni_to_utf8[unicode_str] = utf8_str = _utf8_encode(unicode_str)[0]
52
_utf8_to_uni[utf8_str] = unicode_str
57
_uni_to_utf8=_unicode_to_utf8_map,
58
_utf8_to_uni=_utf8_to_unicode_map,
59
_utf8_decode=_utf8_decode):
60
"""Take a utf8 revision id, and decode it, but cache the result"""
62
return _utf8_to_uni[utf8_str]
64
unicode_str = _utf8_decode(utf8_str)[0]
65
_utf8_to_uni[utf8_str] = unicode_str
66
_uni_to_utf8[unicode_str] = utf8_str
70
def get_cached_unicode(unicode_str):
71
"""Return a cached version of the unicode string.
73
This has a similar idea to that of intern() in that it tries
74
to return a singleton string. Only it works for unicode strings.
76
# This might return the same object, or it might return the cached one
77
# the decode() should just be a hash lookup, because the encode() side
78
# should add the entry to the maps
79
return decode(encode(unicode_str))
82
def get_cached_utf8(utf8_str):
83
"""Return a cached version of the utf-8 string.
85
Get a cached version of this string (similar to intern()).
86
At present, this will be decoded to ensure it is a utf-8 string. In the
87
future this might change to simply caching the string.
89
return encode(decode(utf8_str))
92
def get_cached_ascii(ascii_str,
93
_uni_to_utf8=_unicode_to_utf8_map,
94
_utf8_to_uni=_utf8_to_unicode_map):
95
"""This is a string which is identical in utf-8 and unicode."""
96
# We don't need to do any encoding, but we want _utf8_to_uni to return a
97
# real Unicode string. Unicode and plain strings of this type will have the
98
# same hash, so we can just use it as the key in _uni_to_utf8, but we need
99
# the return value to be different in _utf8_to_uni
100
ascii_str = _uni_to_utf8.setdefault(ascii_str, ascii_str)
101
_utf8_to_uni.setdefault(ascii_str, unicode(ascii_str))
105
def clear_encoding_cache():
106
"""Clear the encoding and decoding caches"""
107
_unicode_to_utf8_map.clear()
108
_utf8_to_unicode_map.clear()