1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
|
# vim:set et sts=4 sw=4:
# -*- coding: utf-8 -*-
#
# ibus-anthy - The Anthy engine for IBus
#
# Copyright (c) 2007-2008 Huang Peng <shawn.p.huang@gmail.com>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
from ibus import unichar_half_to_full
from tables import *
import segment
class RomajiSegment(segment.Segment):
def __init__(self, enchars=u"", jachars=u""):
if not jachars:
jachars = romaji_typing_rule.get(enchars, None)
if jachars == None:
jachars = symbol_rule.get(enchars, u"")
super(RomajiSegment, self).__init__(enchars, jachars)
def is_finished(self):
return self._jachars != u""
def append(self, enchar):
if self.is_finished():
if enchar == u"" and enchar == u"\0":
return []
return [RomajiSegment(enchar)]
text = self._enchars + enchar
jachars = romaji_typing_rule.get(text, None)
if jachars == None:
jachars = symbol_rule.get(text, None)
if jachars:
self._enchars = text
self._jachars = jachars
return []
jachars, c = romaji_double_consonat_typing_rule.get(text, (None, None))
if jachars:
self._enchars = text[0]
self._jachars = jachars
return [RomajiSegment(c)]
jachars, c = romaji_correction_rule.get(text, (None, None))
if jachars:
self._enchars = text[0]
self._jachars = jachars
return [RomajiSegment(c)]
for i in range(-min(4, len(text)), 0):
enchars = text[i:]
jachars = romaji_typing_rule.get(enchars, None)
if jachars == None:
jachars = symbol_rule.get(enchars, None)
if jachars:
jasegment = RomajiSegment(enchars, jachars)
self._enchars = text[:i]
return [jasegment]
jachars, c = romaji_double_consonat_typing_rule.get(enchars, (None, None))
if jachars:
jasegment = RomajiSegment(enchars[:-len(c)], jachars)
self._enchars = text[:i]
if c:
return [jasegment, RomajiSegment(c)]
return [jasegment]
jachars, c = romaji_correction_rule.get(enchars, (None, None))
if jachars:
jasegment = RomajiSegment(enchars[:-len(c)], jachars)
self._enchars = text[:i]
if c:
return [jasegment, RomajiSegment(c)]
return [jasegment]
self._enchars = text
return []
def prepend(self, enchar):
if enchar == u"" or enchar == u"\0":
return []
if self.is_finished():
return [RomajiSegment(enchar)]
text = enchar + self._enchars
jachars = romaji_typing_rule.get(text, None)
if jachars == None:
jachars = symbol_rule.get(text, None)
if jachars:
self._enchars = text
self._jachars = jachars
return []
jachars, c = romaji_double_consonat_typing_rule.get(text, (None, None))
if jachars:
self._enchars = c
return [RomajiSegment(text[0], jachars)]
jachars, c = romaji_correction_rule.get(text, (None, None))
if jachars:
self._enchars = c
return [RomajiSegment(text[0], jachars)]
for i in range(min(4, len(text)), 0, -1):
enchars = text[:i]
jachars = romaji_typing_rule.get(enchars, None)
if jachars == None:
jachars = symbol_rule.get(enchars, None)
if jachars:
jasegment = RomajiSegment(enchars, jachars)
self._enchars = text[i:]
return [jasegment]
jachars, c = romaji_double_consonat_typing_rule.get(enchars, (None, None))
if jachars:
self._enchars = c + text[i:]
return [RomajiSegment(enchars[:-len(c)], jachars)]
jachars, c = romaji_correction_rule.get(enchars, (None, None))
if jachars:
self._enchars = c + text[i:]
return [RomajiSegment(enchars[:-len(c)], jachars)]
self._enchars = text
return []
def pop(self, index=-1):
if index == -1:
index = len(self._enchars) - 1
if index < 0 or index >= len(self._enchars):
raise IndexError("Out of bound")
if self.is_finished():
self._enchars = u""
self._jachars = u""
else:
enchars = list(self._enchars)
del enchars[index]
self._enchars = u"".join(enchars)
jachars = romaji_typing_rule.get(self._enchars, None)
if jachars == None:
jachars = symbol_rule.get(self._enchars, u"")
self._jachars = jachars
|
