summaryrefslogtreecommitdiff
path: root/engine/romaji.py
blob: 48167c626e98f4b73efd01793e5ea02313600563 (plain)
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
# vim:set et sts=4 sw=4:
# -*- coding: utf-8 -*-
#
# ibus-anthy - The Anthy engine for IBus
#
# Copyright (c) 2007-2008 Peng Huang <shawn.p.huang@gmail.com>
# Copyright (c) 2010-2013 Takao Fujiwara <takao.fujiwara1@gmail.com>
# Copyright (c) 2007-2013 Red Hat, Inc.
#
# 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 of the License, 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.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.

import sys

from tables import *
import segment

def romaji_correction_rule_get(k, d):
    return (u'ん', k[1:2]) if k[0:1] == u'n' and not k[1:2] in u"aiueony'" else d

class RomajiSegment(segment.Segment):
    _prefs = None
    _romaji_typing_rule_section = None
    _latin_with_shift = True
    _shift_mode = False

    def __init__(self, enchars=u'', jachars=u'', shift=False, unshift=False):
        if self._latin_with_shift:
            # If Shift key is pressed, Latin mode.
            # If Hiragana_Katakana key is pressed, Hiragana mode.
            if shift:
                self._shift_mode = True
            if unshift:
                self._shift_mode = False

        enchars_orig = enchars
        # Even if the chars are capital with CapsLock, Hiragana
        # should be converted. E.g. 'SA'
        enchars = enchars.lower()

        if not jachars and not shift:
            jachars = self.__get_romaji_typing_rule(enchars, None)
            if jachars == None:
                jachars = symbol_rule.get(enchars, u'')
        super(RomajiSegment, self).__init__(enchars_orig, jachars)

    @classmethod
    def INIT_ROMAJI_TYPING_RULE(cls, prefs):
        cls._prefs = prefs
        if prefs == None:
            cls._romaji_typing_rule_section = None
            return
        method = prefs.get_value('romaji_typing_rule', 'method')
        if method == None:
            method = 'default'
        cls._romaji_typing_rule_section = 'romaji_typing_rule/' + method
        if cls._romaji_typing_rule_section not in prefs.sections():
            cls._romaji_typing_rule_section = None

    @classmethod
    def SET_LATIN_WITH_SHIFT(cls, latin_with_shift):
        # Do not use IBus.Config in every conversion for the performance.
        cls._latin_with_shift = latin_with_shift

    def __get_romaji_typing_rule(self, enchars, retval=None):
        prefs = self._prefs
        value = None
        section = self._romaji_typing_rule_section
        if section != None:
            # Need to send Unicode to typing_to_config_key instead of UTF-8
            # not to separate U+A5
            gkey = prefs.typing_to_config_key(enchars)
            if gkey == '':
                return None
            if gkey in prefs.keys(section):
                value = prefs.unicode(prefs.str(
                    prefs.get_value(section, gkey)))
            else:
                prefs.set_no_key_warning(True)
                value = prefs.get_value_direct(section, gkey)
                prefs.set_no_key_warning(False)
                if value != None:
                    value = prefs.unicode(prefs.str(value))
            if value == '':
                value = None
            if value == None:
                value = retval 
        else:
            value = romaji_typing_rule_static.get(enchars, retval)
        return value

    def is_finished(self):
        return self._jachars != u''

    def append(self, enchar, shift=False, unshift=False):
        if self.is_finished():
            if enchar == u'' and enchar == u'\0':
                return []
            return [RomajiSegment(enchar)]

        text_orig = self._enchars + enchar
        text = text_orig.lower()

        if self._latin_with_shift:
            # If Shift key is pressed, Latin mode.
            # If Hiragana_Katakana key is pressed, Hiragana mode.
            if shift:
                self._shift_mode = True
            if unshift:
                self._shift_mode = False
            if self._shift_mode:
                self._enchars = text_orig
                return []

        if shift:
            self._enchars = text_orig
            return []

        jachars = self.__get_romaji_typing_rule(text, None)
        if jachars == None:
            jachars = symbol_rule.get(text, None)
        if jachars:
            self._enchars = text_orig
            self._jachars = jachars
            return []

        jachars, c = romaji_double_consonat_typing_rule.get(text, (None, None))
        if jachars:
            self._enchars = text_orig[0]
            self._jachars = jachars
            return [RomajiSegment(c)]

#        jachars, c = romaji_correction_rule.get(text, (None, None))
        jachars, c = romaji_correction_rule_get(text, (None, None))
        if jachars:
            self._enchars = text_orig[0]
            self._jachars = jachars
            return [RomajiSegment(c)]

        for i in range(-min(4, len(text)), 0):
            enchars = text[i:]

            jachars = self.__get_romaji_typing_rule(enchars, None)
            if jachars == None:
                jachars = symbol_rule.get(enchars, None)
            if jachars:
                jasegment = RomajiSegment(enchars, jachars)
                self._enchars = text_orig[: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_orig[:i]
                if c:
                    return [jasegment, RomajiSegment(c)]
                return [jasegment]

#            jachars, c = romaji_correction_rule.get(enchars, (None, None))
            jachars, c = romaji_correction_rule_get(enchars, (None, None))
            if jachars:
                jasegment = RomajiSegment(enchars[:-len(c)], jachars)
                self._enchars = text_orig[:i]
                if c:
                    return [jasegment, RomajiSegment(c)]
                return [jasegment]

        self._enchars = text_orig
        return []

    def prepend(self, enchar, shift=False, unshift=False):
        if enchar == u'' or enchar == u'\0':
            return []

        if self.is_finished():
            return [RomajiSegment(enchar)]

        text_orig  = enchar + self._enchars
        text  = text_orig.lower()

        if self._latin_with_shift:
            if shift:
                self._shift_mode = True
            if unshift:
                self._shift_mode = False
            if self._shift_mode:
                self._enchars = text_orig
                return []

        if shift:
            self._enchars = text_orig
            return []

        jachars = self.__get_romaji_typing_rule(text, None)
        if jachars == None:
            jachars = symbol_rule.get(text, None)
        if jachars:
            self._enchars = text_orig
            self._jachars = jachars
            return []

        jachars, c = romaji_double_consonat_typing_rule.get(text, (None, None))
        if jachars:
            self._enchars = c
            return [RomajiSegment(text_orig[0], jachars)]

#        jachars, c = romaji_correction_rule.get(text, (None, None))
        jachars, c = romaji_correction_rule_get(text, (None, None))
        if jachars:
            self._enchars = c
            return [RomajiSegment(text_orig[0], jachars)]

        for i in range(min(4, len(text)), 0, -1):
            enchars = text[:i]

            jachars = self.__get_romaji_typing_rule(enchars, None)
            if jachars == None:
                jachars = symbol_rule.get(enchars, None)
            if jachars:
                jasegment = RomajiSegment(enchars, jachars)
                self._enchars = text_orig[i:]
                return [jasegment]

            jachars, c = romaji_double_consonat_typing_rule.get(enchars, (None, None))
            if jachars:
                self._enchars = c + text_orig[i:]
                return [RomajiSegment(enchars[:-len(c)], jachars)]

#            jachars, c = romaji_correction_rule.get(enchars, (None, None))
            jachars, c = romaji_correction_rule_get(enchars, (None, None))
            if jachars:
                self._enchars = c + text_orig[i:]
                return [RomajiSegment(enchars[:-len(c)], jachars)]

        self._enchars = text_orig
        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 = self.__get_romaji_typing_rule(self._enchars, None)
            if jachars == None:
                jachars = symbol_rule.get(self._enchars, u'')
            self._jachars = jachars