| 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 Afrikaans language.
23
24 For more information, see U{http://en.wikipedia.org/wiki/Afrikaans_language}
25 """
26
27 import re
28
29 from translate.lang import common
30
31 articlere = re.compile(r"'n\b")
32
33
35 """This class represents Afrikaans."""
36
37 punctuation = u"".join([common.Common.commonpunc, common.Common.quotes,
38 common.Common.miscpunc])
39 sentenceend = u".!?…"
40 sentencere = re.compile(r"""(?s) #make . also match newlines
41 .*? #anything, but match non-greedy
42 [%s] #the puntuation for sentence ending
43 \s+ #the spacing after the puntuation
44 (?='n\s[A-Z]|[^'a-z\d]|'[^n])
45 #lookahead that next part starts with caps or 'n followed by caps
46 """ % sentenceend, re.VERBOSE)
47
49 """Modify this for the indefinite article ('n)."""
50 match = articlere.search(text, 0, 20)
51 if match:
52 #construct a list of non-apostrophe punctuation:
53 nonapos = u"".join(cls.punctuation.split(u"'"))
54 stripped = text.lstrip().lstrip(nonapos)
55 match = articlere.match(stripped)
56 if match:
57 return common.Common.capsstart(stripped[match.end():])
58 return common.Common.capsstart(text)
59 capsstart = classmethod(capsstart)
60
61 cyr2lat = {
62 u"А": "A", u"а": "a",
63 u"Б": "B", u"б": "b",
64 u"В": "W", u"в": "w", # Different if at the end of a syllable see rule 2.
65 u"Г": "G", u"г": "g", # see rule 3 and 4
66 u"Д": "D", u"д": "d",
67 u"ДЖ": "Dj", u"дж": "dj",
68 u"Е": "Je", u"е": "je", # Sometimes e need to check when/why see rule 5.
69 u"Ё": "Jo", u"ё": "jo", # see rule 6
70 u"ЕЙ": "Ei", u"ей": "ei",
71 u"Ж": "Zj", u"ж": "zj",
72 u"З": "Z", u"з": "z",
73 u"И": "I", u"и": "i",
74 u"Й": "J", u"й": "j", # see rule 9 and 10
75 u"К": "K", u"к": "k", # see note 11
76 u"Л": "L", u"л": "l",
77 u"М": "M", u"м": "m",
78 u"Н": "N", u"н": "n",
79 u"О": "O", u"о": "o",
80 u"П": "P", u"п": "p",
81 u"Р": "R", u"р": "r",
82 u"С": "S", u"с": "s", # see note 12
83 u"Т": "T", u"т": "t",
84 u"У": "Oe", u"у": "oe",
85 u"Ф": "F", u"ф": "f",
86 u"Х": "Ch", u"х": "ch", # see rule 12
87 u"Ц": "Ts", u"ц": "ts",
88 u"Ч": "Tj", u"ч": "tj",
89 u"Ш": "Sj", u"ш": "sj",
90 u"Щ": "Sjtsj", u"щ": "sjtsj",
91 u"Ы": "I", u"ы": "i", # see note 13
92 u"Ъ": "", u"ъ": "", # See note 14
93 u"Ь": "", u"ь": "", # this letter is not in the AWS we assume it is left out as in the previous letter
94 u"Э": "E", u"э": "e",
95 u"Ю": "Joe", u"ю": "joe",
96 u"Я": "Ja", u"я": "ja",
97 }
98 """Mapping of Cyrillic to Latin letters for transliteration in Afrikaans"""
99
100 cyr_vowels = u"аеёиоуыэюя"
101
102
109
| Home | Trees | Indices | Help |
|
|---|
| Generated by Epydoc 3.0.1 on Tue Apr 12 18:12:07 2011 | http://epydoc.sourceforge.net |