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 from translate.lang import common 28 import re 2931 """This class represents Chinese.""" 32 code = "zh" 33 fullname = "Chinese" 34 nplurals = 1 35 pluralequation = "0" 36 37 listseperator = u"、" 38 39 sentenceend = u"。!?…" 40 41 # Compared to common.py, we make the space after the sentence ending 42 # optional and don't demand an uppercase letter to follow. 43 sentencere = re.compile(r"""(?s) #make . also match newlines 44 .*? #any text, but match non-greedy 45 [%s] #the puntuation for sentence ending 46 \s* #the optional space after the puntuation 47 """ % sentenceend, re.VERBOSE) 48 49 # The following transformation rules should be mostly useful for all types 50 # of Chinese. The comma (,) is not handled here, since it maps to two 51 # different characters, depending on context. 52 # If comma is used as seperation of sentence, then it is converted to a 53 # fullwidth comma (","). If comma is used as seperation of list items like 54 # "apple, orange, grape, .....", "、" is used. 55 puncdict = { 56 u". ": u"。", 57 u"; ": u";", 58 u": ": u":", 59 u"! ": u"!", 60 u"? ": u"?", 61 u".\n": u"。\n", 62 u";\n": u";\n", 63 u":\n": u":\n", 64 u"!\n": u"!\n", 65 u"?\n": u"?", 66 u"% ": u"%", 67 u" (": u"(", 68 u") ": u")", 69 } 70 71 ignoretests = ["startcaps", "simplecaps"]72
Trees | Indices | Help |
|
---|
Generated by Epydoc 3.0.1 on Wed Mar 26 12:49:42 2008 | http://epydoc.sourceforge.net |