|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
1 |
# Copyright (C) 2006 Canonical
|
2 |
#
|
|
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.
|
|
7 |
#
|
|
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.
|
|
12 |
#
|
|
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
|
|
16 |
||
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.
|
|
19 |
||
20 |
"""Some functions to enable caching the conversion between unicode to utf8"""
|
|
21 |
||
22 |
||
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 = {} |
|
28 |
||
29 |
||
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"""
|
|
|
1934.1.11
by John Arbash Meinel
Document why we use try/except rather than if None |
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
|
|
37 |
# try/KeyError: 900ms
|
|
38 |
# if None: 1250ms
|
|
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
|
|
41 |
# fast path
|
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
42 |
try: |
43 |
return _uni_to_utf8[unicode_str] |
|
44 |
except KeyError: |
|
45 |
_uni_to_utf8[unicode_str] = utf8_str = unicode_str.encode('utf-8') |
|
46 |
_utf8_to_uni[utf8_str] = unicode_str |
|
47 |
return utf8_str |
|
48 |
||
49 |
||
50 |
def decode(utf8_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"""
|
|
54 |
try: |
|
55 |
return _utf8_to_uni[utf8_str] |
|
56 |
except KeyError: |
|
57 |
_utf8_to_uni[utf8_str] = unicode_str = utf8_str.decode('utf-8') |
|
58 |
_uni_to_utf8[unicode_str] = utf8_str |
|
59 |
return unicode_str |
|
60 |
||
61 |
||
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
62 |
def get_cached_unicode(unicode_str): |
63 |
"""Return a cached version of the unicode string.
|
|
64 |
||
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.
|
|
67 |
"""
|
|
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)) |
|
72 |
||
73 |
||
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
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() |
|
79 |