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
# 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
from __future__ import absolute_import
22
"""Some functions to enable caching the conversion between unicode to utf8"""
27
_utf8_encode = codecs.utf_8_encode
28
_utf8_decode = codecs.utf_8_decode
29
def _utf8_decode_with_None(bytestring, _utf8_decode=_utf8_decode):
30
"""wrap _utf8_decode to support None->None for optional strings.
32
Also, only return the Unicode portion, since we don't care about the second
35
if bytestring is None:
38
return _utf8_decode(bytestring)[0]
40
# Map revisions from and to utf8 encoding
41
# Whenever we do an encode/decode operation, we save the result, so that
42
# we don't have to do it again.
43
_unicode_to_utf8_map = {}
44
_utf8_to_unicode_map = {}
47
def encode(unicode_str,
48
_uni_to_utf8=_unicode_to_utf8_map,
49
_utf8_to_uni=_utf8_to_unicode_map,
50
_utf8_encode=_utf8_encode):
51
"""Take this unicode revision id, and get a unicode version"""
52
# If the key is in the cache try/KeyError is 50% faster than
53
# val = dict.get(key), if val is None:
54
# On jam's machine the difference is
57
# Since these are primarily used when iterating over a knit entry
58
# *most* of the time the key will already be in the cache, so use the
61
return _uni_to_utf8[unicode_str]
63
_uni_to_utf8[unicode_str] = utf8_str = _utf8_encode(unicode_str)[0]
64
_utf8_to_uni[utf8_str] = unicode_str
69
_uni_to_utf8=_unicode_to_utf8_map,
70
_utf8_to_uni=_utf8_to_unicode_map,
71
_utf8_decode=_utf8_decode):
72
"""Take a utf8 revision id, and decode it, but cache the result"""
74
return _utf8_to_uni[utf8_str]
76
unicode_str = _utf8_decode(utf8_str)[0]
77
_utf8_to_uni[utf8_str] = unicode_str
78
_uni_to_utf8[unicode_str] = utf8_str
82
def get_cached_unicode(unicode_str):
83
"""Return a cached version of the unicode string.
85
This has a similar idea to that of intern() in that it tries
86
to return a singleton string. Only it works for unicode strings.
88
# This might return the same object, or it might return the cached one
89
# the decode() should just be a hash lookup, because the encode() side
90
# should add the entry to the maps
91
return decode(encode(unicode_str))
94
def get_cached_utf8(utf8_str):
95
"""Return a cached version of the utf-8 string.
97
Get a cached version of this string (similar to intern()).
98
At present, this will be decoded to ensure it is a utf-8 string. In the
99
future this might change to simply caching the string.
101
return encode(decode(utf8_str))
104
def get_cached_ascii(ascii_str,
105
_uni_to_utf8=_unicode_to_utf8_map,
106
_utf8_to_uni=_utf8_to_unicode_map):
107
"""This is a string which is identical in utf-8 and unicode."""
108
# We don't need to do any encoding, but we want _utf8_to_uni to return a
109
# real Unicode string. Unicode and plain strings of this type will have the
110
# same hash, so we can just use it as the key in _uni_to_utf8, but we need
111
# the return value to be different in _utf8_to_uni
112
ascii_str = _uni_to_utf8.setdefault(ascii_str, ascii_str)
113
_utf8_to_uni.setdefault(ascii_str, unicode(ascii_str))
117
def clear_encoding_cache():
118
"""Clear the encoding and decoding caches"""
119
_unicode_to_utf8_map.clear()
120
_utf8_to_unicode_map.clear()