This repository has been archived by the owner on Nov 8, 2023. It is now read-only.
/
PhoneticStringUtils.cpp
319 lines (290 loc) · 10.1 KB
/
PhoneticStringUtils.cpp
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
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
/*
* Copyright (C) 2009 The Android Open Source Project
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include <stdio.h>
#include <stdlib.h>
#include "PhoneticStringUtils.h"
#include <utils/Unicode.h>
// We'd like 0 length string last of sorted list. So when input string is NULL
// or 0 length string, we use these instead.
#define CODEPOINT_FOR_NULL_STR 0xFFFD
#define STR_FOR_NULL_STR "\xEF\xBF\xBD"
// We assume that users will not notice strings not sorted properly when the
// first 128 characters are the same.
#define MAX_CODEPOINTS 128
namespace android {
// Get hiragana from halfwidth katakana.
static int GetHiraganaFromHalfwidthKatakana(char32_t codepoint,
char32_t next_codepoint,
bool *next_is_consumed) {
if (codepoint < 0xFF66 || 0xFF9F < codepoint) {
return codepoint;
}
switch (codepoint) {
case 0xFF66: // wo
return 0x3092;
case 0xFF67: // xa
return 0x3041;
case 0xFF68: // xi
return 0x3043;
case 0xFF69: // xu
return 0x3045;
case 0xFF6A: // xe
return 0x3047;
case 0xFF6B: // xo
return 0x3049;
case 0xFF6C: // xya
return 0x3083;
case 0xFF6D: // xyu
return 0x3085;
case 0xFF6E: // xyo
return 0x3087;
case 0xFF6F: // xtsu
return 0x3063;
case 0xFF70: // -
return 0x30FC;
case 0xFF9C: // wa
return 0x308F;
case 0xFF9D: // n
return 0x3093;
break;
default: {
if (0xFF71 <= codepoint && codepoint <= 0xFF75) {
// a, i, u, e, o
if (codepoint == 0xFF73 && next_codepoint == 0xFF9E) {
if (next_is_consumed != NULL) {
*next_is_consumed = true;
}
return 0x3094; // vu
} else {
return 0x3042 + (codepoint - 0xFF71) * 2;
}
} else if (0xFF76 <= codepoint && codepoint <= 0xFF81) {
// ka - chi
if (next_codepoint == 0xFF9E) {
// "dakuten" (voiced mark)
if (next_is_consumed != NULL) {
*next_is_consumed = true;
}
return 0x304B + (codepoint - 0xFF76) * 2 + 1;
} else {
return 0x304B + (codepoint - 0xFF76) * 2;
}
} else if (0xFF82 <= codepoint && codepoint <= 0xFF84) {
// tsu, te, to (skip xtsu)
if (next_codepoint == 0xFF9E) {
// "dakuten" (voiced mark)
if (next_is_consumed != NULL) {
*next_is_consumed = true;
}
return 0x3064 + (codepoint - 0xFF82) * 2 + 1;
} else {
return 0x3064 + (codepoint - 0xFF82) * 2;
}
} else if (0xFF85 <= codepoint && codepoint <= 0xFF89) {
// na, ni, nu, ne, no
return 0x306A + (codepoint - 0xFF85);
} else if (0xFF8A <= codepoint && codepoint <= 0xFF8E) {
// ha, hi, hu, he, ho
if (next_codepoint == 0xFF9E) {
// "dakuten" (voiced mark)
if (next_is_consumed != NULL) {
*next_is_consumed = true;
}
return 0x306F + (codepoint - 0xFF8A) * 3 + 1;
} else if (next_codepoint == 0xFF9F) {
// "han-dakuten" (half voiced mark)
if (next_is_consumed != NULL) {
*next_is_consumed = true;
}
return 0x306F + (codepoint - 0xFF8A) * 3 + 2;
} else {
return 0x306F + (codepoint - 0xFF8A) * 3;
}
} else if (0xFF8F <= codepoint && codepoint <= 0xFF93) {
// ma, mi, mu, me, mo
return 0x307E + (codepoint - 0xFF8F);
} else if (0xFF94 <= codepoint && codepoint <= 0xFF96) {
// ya, yu, yo
return 0x3084 + (codepoint - 0xFF94) * 2;
} else if (0xFF97 <= codepoint && codepoint <= 0xFF9B) {
// ra, ri, ru, re, ro
return 0x3089 + (codepoint - 0xFF97);
}
// Note: 0xFF9C, 0xFF9D are handled above
} // end of default
}
return codepoint;
}
// Assuming input is hiragana, convert the hiragana to "normalized" hiragana.
static int GetNormalizedHiragana(int codepoint) {
if (codepoint < 0x3040 || 0x309F < codepoint) {
return codepoint;
}
// TODO: should care (semi-)voiced mark (0x3099, 0x309A).
// Trivial kana conversions.
// e.g. xa => a
switch (codepoint) {
case 0x3041:
case 0x3043:
case 0x3045:
case 0x3047:
case 0x3049:
case 0x3063:
case 0x3083:
case 0x3085:
case 0x3087:
case 0x308E: // xwa
return codepoint + 1;
case 0x3095: // xka
return 0x304B;
case 0x3096: // xke
return 0x3051;
case 0x31F0: // xku
return 0x304F;
case 0x31F1: // xsi
return 0x3057;
case 0x31F2: // xsu
return 0x3059;
case 0x31F3: // xto
return 0x3068;
case 0x31F4: // xnu
return 0x306C;
case 0x31F5: // xha
return 0x306F;
case 0x31F6: // xhi
return 0x3072;
case 0x31F7: // xhu
return 0x3075;
case 0x31F8: // xhe
return 0x3078;
case 0x31F9: // xho
return 0x307B;
case 0x31FA: // xmu
return 0x3080;
case 0x31FB: // xra
case 0x31FC: // xri
case 0x31FD: // xru
case 0x31FE: // xre
case 0x31FF: // xro
// ra: 0x3089
return 0x3089 + (codepoint - 0x31FB);
default:
return codepoint;
}
}
static int GetNormalizedKana(char32_t codepoint,
char32_t next_codepoint,
bool *next_is_consumed) {
// First, convert fullwidth katakana and halfwidth katakana to hiragana.
if (0x30A1 <= codepoint && codepoint <= 0x30F6) {
// Make fullwidth katakana same as hiragana.
// 96 == 0x30A1 - 0x3041c
codepoint = codepoint - 96;
} else if (codepoint == 0x309F) {
// Digraph YORI; Yo
codepoint = 0x3088;
} else if (codepoint == 0x30FF) {
// Digraph KOTO; Ko
codepoint = 0x3053;
} else {
codepoint = GetHiraganaFromHalfwidthKatakana(
codepoint, next_codepoint, next_is_consumed);
}
// Normalize Hiragana.
return GetNormalizedHiragana(codepoint);
}
int GetNormalizedCodePoint(char32_t codepoint,
char32_t next_codepoint,
bool *next_is_consumed) {
if (next_is_consumed != NULL) {
*next_is_consumed = false;
}
if (codepoint <= 0x0020 || codepoint == 0x3000) {
// Whitespaces. Keep it as is.
return codepoint;
} else if ((0x0021 <= codepoint && codepoint <= 0x007E) ||
(0xFF01 <= codepoint && codepoint <= 0xFF5E)) {
// Ascii and fullwidth ascii. Keep it as is
return codepoint;
} else if (codepoint == 0x02DC || codepoint == 0x223C) {
// tilde
return 0xFF5E;
} else if (codepoint <= 0x3040 ||
(0x3100 <= codepoint && codepoint < 0xFF00) ||
codepoint == CODEPOINT_FOR_NULL_STR) {
// Keep it as is.
return codepoint;
}
// Below is Kana-related handling.
return GetNormalizedKana(codepoint, next_codepoint, next_is_consumed);
}
static bool GetExpectedString(
const char *src, char **dst, size_t *dst_len,
int (*get_codepoint_function)(char32_t, char32_t, bool*)) {
if (dst == NULL || dst_len == NULL) {
return false;
}
if (src == NULL || *src == '\0') {
src = STR_FOR_NULL_STR;
}
char32_t codepoints[MAX_CODEPOINTS]; // if array size is changed the for loop needs to be changed
ssize_t src_len = utf8_length(src);
if (src_len <= 0) {
return false;
}
bool next_is_consumed;
size_t j = 0;
for (size_t i = 0; i < (size_t)src_len && j < MAX_CODEPOINTS;) {
int32_t ret = utf32_from_utf8_at(src, src_len, i, &i);
if (ret < 0) {
// failed to parse UTF-8
return false;
}
ret = get_codepoint_function(
static_cast<char32_t>(ret),
i + 1 < (size_t)src_len ? src[i + 1] : 0,
&next_is_consumed);
if (ret > 0) {
codepoints[j] = static_cast<char32_t>(ret);
j++;
}
if (next_is_consumed) {
i++;
}
}
size_t length = j;
if (length == 0) {
// If all of codepoints are invalid, we place the string at the end of
// the list.
codepoints[0] = 0x10000 + CODEPOINT_FOR_NULL_STR;
length = 1;
}
ssize_t new_len = utf32_to_utf8_length(codepoints, length);
if (new_len < 0) {
return false;
}
*dst = static_cast<char *>(malloc(new_len + 1));
if (*dst == NULL) {
return false;
}
utf32_to_utf8(codepoints, length, *dst);
*dst_len = new_len;
return true;
}
bool GetNormalizedString(const char *src, char **dst, size_t *len) {
return GetExpectedString(src, dst, len, GetNormalizedCodePoint);
}
} // namespace android