| Home | Trees | Indices | Help |
|
|---|
|
|
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3 #
4 # Copyright 2007 Zuza Software Foundation
5 #
6 # This file is part of translate.
7 #
8 # translate is free software; you can redistribute it and/or modify
9 # it under the terms of the GNU General Public License as published by
10 # the Free Software Foundation; either version 2 of the License, or
11 # (at your option) any later version.
12 #
13 # translate is distributed in the hope that it will be useful,
14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 # GNU General Public License for more details.
17 #
18 # You should have received a copy of the GNU General Public License
19 # along with translate; if not, write to the Free Software
20 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
21
22 """This module represents Chinese language. (Both tradisional and simplified)
23
24 For more information, see U{http://en.wikipedia.org/wiki/Chinese_language}
25 """
26
27 import re
28
29 from translate.lang import common
30
31
33 """This class represents Chinese."""
34
35 listseperator = u"、"
36
37 sentenceend = u"。!?…"
38
39 # Compared to common.py, we make the space after the sentence ending
40 # optional and don't demand an uppercase letter to follow.
41 sentencere = re.compile(r"""(?s) # make . also match newlines
42 .*? # any text, but match non-greedy
43 [%s] # the puntuation for sentence ending
44 \s* # the optional space after the puntuation
45 """ % sentenceend, re.VERBOSE)
46
47 # The following transformation rules should be mostly useful for all types
48 # of Chinese. The comma (,) is not handled here, since it maps to two
49 # different characters, depending on context.
50 # If comma is used as seperation of sentence, it should be converted to a
51 # fullwidth comma (","). If comma is used as seperation of list items
52 # like "apple, orange, grape, .....", "、" is used.
53 puncdict = {
54 u". ": u"。",
55 u"; ": u";",
56 u": ": u":",
57 u"! ": u"!",
58 u"? ": u"?",
59 u".\n": u"。\n",
60 u";\n": u";\n",
61 u":\n": u":\n",
62 u"!\n": u"!\n",
63 u"?\n": u"?",
64 u"% ": u"%",
65 }
66
69 length_difference = classmethod(length_difference)
70
71 ignoretests = ["startcaps", "simplecaps"]
72
| Home | Trees | Indices | Help |
|
|---|
| Generated by Epydoc 3.0.1 on Tue Apr 12 18:12:04 2011 | http://epydoc.sourceforge.net |