1/*
2 * Copyright (C) 2009 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 *      http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17package com.android.internal.util;
18
19import android.text.TextUtils;
20import android.util.Log;
21
22import java.text.Collator;
23import java.util.ArrayList;
24import java.util.Locale;
25
26/**
27 * An object to convert Chinese character to its corresponding pinyin string.
28 * For characters with multiple possible pinyin string, only one is selected
29 * according to collator. Polyphone is not supported in this implementation.
30 * This class is implemented to achieve the best runtime performance and minimum
31 * runtime resources with tolerable sacrifice of accuracy. This implementation
32 * highly depends on zh_CN ICU collation data and must be always synchronized with
33 * ICU.
34 */
35public class HanziToPinyin {
36    private static final String TAG = "HanziToPinyin";
37
38    private static final char[] UNIHANS = {
39            '\u5416', '\u54ce', '\u5b89', '\u80ae', '\u51f9', '\u516b', '\u63b0', '\u6273',
40            '\u90a6', '\u52f9', '\u9642', '\u5954', '\u4f3b', '\u7680', '\u782d', '\u706c',
41            '\u618b', '\u6c43', '\u51ab', '\u7676', '\u5cec', '\u5693', '\u5072', '\u53c2',
42            '\u4ed3', '\u64a1', '\u518a', '\u5d7e', '\u564c', '\u6260', '\u62c6', '\u8fbf',
43            '\u4f25', '\u6284', '\u8f66', '\u62bb', '\u9637', '\u5403', '\u5145', '\u62bd',
44            '\u51fa', '\u640b', '\u5ddb', '\u5205', '\u5439', '\u65fe', '\u8e14', '\u5472',
45            '\u4ece', '\u51d1', '\u7c97', '\u6c46', '\u5d14', '\u90a8', '\u6413', '\u5491',
46            '\u5446', '\u4e39', '\u5f53', '\u5200', '\u6074', '\u6265', '\u706f', '\u4efe',
47            '\u55f2', '\u6541', '\u5201', '\u7239', '\u4e01', '\u4e1f', '\u4e1c', '\u543a',
48            '\u5262', '\u8011', '\u5796', '\u5428', '\u591a', '\u59b8', '\u5940', '\u97a5',
49            '\u800c', '\u53d1', '\u5e06', '\u531a', '\u98de', '\u5206', '\u4e30', '\u8985',
50            '\u4ecf', '\u57ba', '\u7d11', '\u592b', '\u7324', '\u65ee', '\u4f85', '\u5e72',
51            '\u5188', '\u768b', '\u6208', '\u7ed9', '\u6839', '\u63ef', '\u55bc', '\u55f0',
52            '\u5de5', '\u52fe', '\u4f30', '\u9e39', '\u4e56', '\u5173', '\u5149', '\u5f52',
53            '\u4e28', '\u8b34', '\u5459', '\u598e', '\u548d', '\u4f44', '\u592f', '\u8320',
54            '\u8bc3', '\u9ed2', '\u62eb', '\u4ea8', '\u53ff', '\u9f41', '\u4e4e', '\u82b1',
55            '\u6000', '\u6b22', '\u5ddf', '\u7070', '\u660f', '\u5419', '\u4e0c', '\u52a0',
56            '\u620b', '\u6c5f', '\u827d', '\u9636', '\u5dfe', '\u5755', '\u5182', '\u4e29',
57            '\u51e5', '\u59e2', '\u5658', '\u519b', '\u5494', '\u5f00', '\u938e', '\u5ffc',
58            '\u5c3b', '\u533c', '\u808e', '\u52a5', '\u7a7a', '\u62a0', '\u625d', '\u5938',
59            '\u84af', '\u5bbd', '\u5321', '\u4e8f', '\u5764', '\u6269', '\u62c9', '\u4f86',
60            '\u5170', '\u5577', '\u635e', '\u4ec2', '\u96f7', '\u8137', '\u68f1', '\u695e',
61            '\u550e', '\u4fe9', '\u5afe', '\u826f', '\u8e7d', '\u57d3', '\u53b8', '\u62ce',
62            '\u6e9c', '\u9f99', '\u5a04', '\u565c', '\u5b6a', '\u62a1', '\u9831', '\u5988',
63            '\u57cb', '\u989f', '\u7264', '\u732b', '\u5445', '\u95e8', '\u6c13', '\u54aa',
64            '\u5b80', '\u55b5', '\u4e5c', '\u6c11', '\u540d', '\u8c2c', '\u6478', '\u725f',
65            '\u6bcd', '\u62cf', '\u8149', '\u56e1', '\u56d4', '\u5b6c', '\u8bb7', '\u5a1e',
66            '\u5ae9', '\u80fd', '\u92b0', '\u62c8', '\u5a18', '\u9e1f', '\u634f', '\u56dc',
67            '\u5b81', '\u599e', '\u519c', '\u7fba', '\u5974', '\u597b', '\u9ec1', '\u90cd',
68            '\u5662', '\u8bb4', '\u5991', '\u62cd', '\u7705', '\u6c78', '\u629b', '\u5478',
69            '\u55b7', '\u5309', '\u4e76', '\u7247', '\u527d', '\u6c15', '\u59d8', '\u4e52',
70            '\u948b', '\u5256', '\u4ec6', '\u4e03', '\u6390', '\u5343', '\u545b', '\u6084',
71            '\u5207', '\u4eb2', '\u9751', '\u5b86', '\u74d7', '\u533a', '\u5cd1', '\u7094',
72            '\u590b', '\u5465', '\u7a63', '\u835b', '\u60f9', '\u4eba', '\u6254', '\u65e5',
73            '\u620e', '\u53b9', '\u909a', '\u5827', '\u6875', '\u95f0', '\u633c', '\u4ee8',
74            '\u6be2', '\u4e09', '\u6852', '\u63bb', '\u8272', '\u68ee', '\u50e7', '\u6740',
75            '\u7b5b', '\u5c71', '\u4f24', '\u5f30', '\u5962', '\u7533', '\u5347', '\u5c38',
76            '\u53ce', '\u4e66', '\u5237', '\u8870', '\u95e9', '\u53cc', '\u8c01', '\u542e',
77            '\u8bf4', '\u53b6', '\u5fea', '\u51c1', '\u82cf', '\u72fb', '\u590a', '\u5b59',
78            '\u5506', '\u4ed6', '\u5b61', '\u574d', '\u6c64', '\u5932', '\u5fd1', '\u81af',
79            '\u5254', '\u5929', '\u65eb', '\u6017', '\u5385', '\u70b5', '\u5077', '\u51f8',
80            '\u6e4d', '\u63a8', '\u541e', '\u8bac', '\u52b8', '\u6b6a', '\u5f2f', '\u5c23',
81            '\u5371', '\u6637', '\u7fc1', '\u631d', '\u4e4c', '\u5915', '\u5477', '\u4ed9',
82            '\u4e61', '\u7071', '\u4e9b', '\u5fc3', '\u5174', '\u51f6', '\u4f11', '\u620c',
83            '\u5405', '\u75b6', '\u7025', '\u4e2b', '\u54bd', '\u592e', '\u5e7a', '\u503b',
84            '\u4e00', '\u4e5a', '\u5e94', '\u5537', '\u4f63', '\u4f18', '\u7ea1', '\u56e6',
85            '\u66f0', '\u8480', '\u5e00', '\u707d', '\u5142', '\u7242', '\u50ae', '\u556b',
86            '\u9c61', '\u600e', '\u66fd', '\u5412', '\u635a', '\u6cbe', '\u5f20', '\u4f4b',
87            '\u8707', '\u8d1e', '\u9eee', '\u4e4b', '\u4e2d', '\u5dde', '\u6731', '\u6293',
88            '\u62fd', '\u4e13', '\u5986', '\u96b9', '\u5b92', '\u5353', '\u4ed4', '\u5b97',
89            '\u90b9', '\u79df', '\u5297', '\u55fa', '\u5c0a', '\u6628',
90        };
91    private final static byte[][] PINYINS = {
92            {65, 00, 00, 00, 00, 00, }, {65, 73, 00, 00, 00, 00, },
93            {65, 78, 00, 00, 00, 00, }, {65, 78, 71, 00, 00, 00, },
94            {65, 79, 00, 00, 00, 00, }, {66, 65, 00, 00, 00, 00, },
95            {66, 65, 73, 00, 00, 00, }, {66, 65, 78, 00, 00, 00, },
96            {66, 65, 78, 71, 00, 00, }, {66, 65, 79, 00, 00, 00, },
97            {66, 69, 73, 00, 00, 00, }, {66, 69, 78, 00, 00, 00, },
98            {66, 69, 78, 71, 00, 00, }, {66, 73, 00, 00, 00, 00, },
99            {66, 73, 65, 78, 00, 00, }, {66, 73, 65, 79, 00, 00, },
100            {66, 73, 69, 00, 00, 00, }, {66, 73, 78, 00, 00, 00, },
101            {66, 73, 78, 71, 00, 00, }, {66, 79, 00, 00, 00, 00, },
102            {66, 85, 00, 00, 00, 00, }, {67, 65, 00, 00, 00, 00, },
103            {67, 65, 73, 00, 00, 00, }, {67, 65, 78, 00, 00, 00, },
104            {67, 65, 78, 71, 00, 00, }, {67, 65, 79, 00, 00, 00, },
105            {67, 69, 00, 00, 00, 00, }, {67, 69, 78, 00, 00, 00, },
106            {67, 69, 78, 71, 00, 00, }, {67, 72, 65, 00, 00, 00, },
107            {67, 72, 65, 73, 00, 00, }, {67, 72, 65, 78, 00, 00, },
108            {67, 72, 65, 78, 71, 00, }, {67, 72, 65, 79, 00, 00, },
109            {67, 72, 69, 00, 00, 00, }, {67, 72, 69, 78, 00, 00, },
110            {67, 72, 69, 78, 71, 00, }, {67, 72, 73, 00, 00, 00, },
111            {67, 72, 79, 78, 71, 00, }, {67, 72, 79, 85, 00, 00, },
112            {67, 72, 85, 00, 00, 00, }, {67, 72, 85, 65, 73, 00, },
113            {67, 72, 85, 65, 78, 00, }, {67, 72, 85, 65, 78, 71, },
114            {67, 72, 85, 73, 00, 00, }, {67, 72, 85, 78, 00, 00, },
115            {67, 72, 85, 79, 00, 00, }, {67, 73, 00, 00, 00, 00, },
116            {67, 79, 78, 71, 00, 00, }, {67, 79, 85, 00, 00, 00, },
117            {67, 85, 00, 00, 00, 00, }, {67, 85, 65, 78, 00, 00, },
118            {67, 85, 73, 00, 00, 00, }, {67, 85, 78, 00, 00, 00, },
119            {67, 85, 79, 00, 00, 00, }, {68, 65, 00, 00, 00, 00, },
120            {68, 65, 73, 00, 00, 00, }, {68, 65, 78, 00, 00, 00, },
121            {68, 65, 78, 71, 00, 00, }, {68, 65, 79, 00, 00, 00, },
122            {68, 69, 00, 00, 00, 00, }, {68, 69, 78, 00, 00, 00, },
123            {68, 69, 78, 71, 00, 00, }, {68, 73, 00, 00, 00, 00, },
124            {68, 73, 65, 00, 00, 00, }, {68, 73, 65, 78, 00, 00, },
125            {68, 73, 65, 79, 00, 00, }, {68, 73, 69, 00, 00, 00, },
126            {68, 73, 78, 71, 00, 00, }, {68, 73, 85, 00, 00, 00, },
127            {68, 79, 78, 71, 00, 00, }, {68, 79, 85, 00, 00, 00, },
128            {68, 85, 00, 00, 00, 00, }, {68, 85, 65, 78, 00, 00, },
129            {68, 85, 73, 00, 00, 00, }, {68, 85, 78, 00, 00, 00, },
130            {68, 85, 79, 00, 00, 00, }, {69, 00, 00, 00, 00, 00, },
131            {69, 78, 00, 00, 00, 00, }, {69, 78, 71, 00, 00, 00, },
132            {69, 82, 00, 00, 00, 00, }, {70, 65, 00, 00, 00, 00, },
133            {70, 65, 78, 00, 00, 00, }, {70, 65, 78, 71, 00, 00, },
134            {70, 69, 73, 00, 00, 00, }, {70, 69, 78, 00, 00, 00, },
135            {70, 69, 78, 71, 00, 00, }, {70, 73, 65, 79, 00, 00, },
136            {70, 79, 00, 00, 00, 00, }, {70, 85, 00, 00, 00, 00, },
137            {70, 79, 85, 00, 00, 00, }, {70, 85, 00, 00, 00, 00, },
138            {71, 85, 73, 00, 00, 00, }, {71, 65, 00, 00, 00, 00, },
139            {71, 65, 73, 00, 00, 00, }, {71, 65, 78, 00, 00, 00, },
140            {71, 65, 78, 71, 00, 00, }, {71, 65, 79, 00, 00, 00, },
141            {71, 69, 00, 00, 00, 00, }, {71, 69, 73, 00, 00, 00, },
142            {71, 69, 78, 00, 00, 00, }, {71, 69, 78, 71, 00, 00, },
143            {74, 73, 69, 00, 00, 00, }, {71, 69, 00, 00, 00, 00, },
144            {71, 79, 78, 71, 00, 00, }, {71, 79, 85, 00, 00, 00, },
145            {71, 85, 00, 00, 00, 00, }, {71, 85, 65, 00, 00, 00, },
146            {71, 85, 65, 73, 00, 00, }, {71, 85, 65, 78, 00, 00, },
147            {71, 85, 65, 78, 71, 00, }, {71, 85, 73, 00, 00, 00, },
148            {71, 85, 78, 00, 00, 00, }, {71, 85, 65, 78, 00, 00, },
149            {71, 85, 79, 00, 00, 00, }, {72, 65, 00, 00, 00, 00, },
150            {72, 65, 73, 00, 00, 00, }, {72, 65, 78, 00, 00, 00, },
151            {72, 65, 78, 71, 00, 00, }, {72, 65, 79, 00, 00, 00, },
152            {72, 69, 00, 00, 00, 00, }, {72, 69, 73, 00, 00, 00, },
153            {72, 69, 78, 00, 00, 00, }, {72, 69, 78, 71, 00, 00, },
154            {72, 79, 78, 71, 00, 00, }, {72, 79, 85, 00, 00, 00, },
155            {72, 85, 00, 00, 00, 00, }, {72, 85, 65, 00, 00, 00, },
156            {72, 85, 65, 73, 00, 00, }, {72, 85, 65, 78, 00, 00, },
157            {72, 85, 65, 78, 71, 00, }, {72, 85, 73, 00, 00, 00, },
158            {72, 85, 78, 00, 00, 00, }, {72, 85, 79, 00, 00, 00, },
159            {74, 73, 00, 00, 00, 00, }, {74, 73, 65, 00, 00, 00, },
160            {74, 73, 65, 78, 00, 00, }, {74, 73, 65, 78, 71, 00, },
161            {74, 73, 65, 79, 00, 00, }, {74, 73, 69, 00, 00, 00, },
162            {74, 73, 78, 00, 00, 00, }, {74, 73, 78, 71, 00, 00, },
163            {74, 73, 79, 78, 71, 00, }, {74, 73, 85, 00, 00, 00, },
164            {74, 85, 00, 00, 00, 00, }, {74, 85, 65, 78, 00, 00, },
165            {74, 85, 69, 00, 00, 00, }, {74, 85, 78, 00, 00, 00, },
166            {75, 65, 00, 00, 00, 00, }, {75, 65, 73, 00, 00, 00, },
167            {75, 65, 78, 00, 00, 00, }, {75, 65, 78, 71, 00, 00, },
168            {75, 65, 79, 00, 00, 00, }, {75, 69, 00, 00, 00, 00, },
169            {75, 69, 78, 00, 00, 00, }, {75, 69, 78, 71, 00, 00, },
170            {75, 79, 78, 71, 00, 00, }, {75, 79, 85, 00, 00, 00, },
171            {75, 85, 00, 00, 00, 00, }, {75, 85, 65, 00, 00, 00, },
172            {75, 85, 65, 73, 00, 00, }, {75, 85, 65, 78, 00, 00, },
173            {75, 85, 65, 78, 71, 00, }, {75, 85, 73, 00, 00, 00, },
174            {75, 85, 78, 00, 00, 00, }, {75, 85, 79, 00, 00, 00, },
175            {76, 65, 00, 00, 00, 00, }, {76, 65, 73, 00, 00, 00, },
176            {76, 65, 78, 00, 00, 00, }, {76, 65, 78, 71, 00, 00, },
177            {76, 65, 79, 00, 00, 00, }, {76, 69, 00, 00, 00, 00, },
178            {76, 69, 73, 00, 00, 00, }, {76, 73, 00, 00, 00, 00, },
179            {76, 73, 78, 71, 00, 00, }, {76, 69, 78, 71, 00, 00, },
180            {76, 73, 00, 00, 00, 00, }, {76, 73, 65, 00, 00, 00, },
181            {76, 73, 65, 78, 00, 00, }, {76, 73, 65, 78, 71, 00, },
182            {76, 73, 65, 79, 00, 00, }, {76, 73, 69, 00, 00, 00, },
183            {76, 73, 78, 00, 00, 00, }, {76, 73, 78, 71, 00, 00, },
184            {76, 73, 85, 00, 00, 00, }, {76, 79, 78, 71, 00, 00, },
185            {76, 79, 85, 00, 00, 00, }, {76, 85, 00, 00, 00, 00, },
186            {76, 85, 65, 78, 00, 00, }, {76, 85, 78, 00, 00, 00, },
187            {76, 85, 79, 00, 00, 00, }, {77, 65, 00, 00, 00, 00, },
188            {77, 65, 73, 00, 00, 00, }, {77, 65, 78, 00, 00, 00, },
189            {77, 65, 78, 71, 00, 00, }, {77, 65, 79, 00, 00, 00, },
190            {77, 69, 73, 00, 00, 00, }, {77, 69, 78, 00, 00, 00, },
191            {77, 69, 78, 71, 00, 00, }, {77, 73, 00, 00, 00, 00, },
192            {77, 73, 65, 78, 00, 00, }, {77, 73, 65, 79, 00, 00, },
193            {77, 73, 69, 00, 00, 00, }, {77, 73, 78, 00, 00, 00, },
194            {77, 73, 78, 71, 00, 00, }, {77, 73, 85, 00, 00, 00, },
195            {77, 79, 00, 00, 00, 00, }, {77, 79, 85, 00, 00, 00, },
196            {77, 85, 00, 00, 00, 00, }, {78, 65, 00, 00, 00, 00, },
197            {78, 65, 73, 00, 00, 00, }, {78, 65, 78, 00, 00, 00, },
198            {78, 65, 78, 71, 00, 00, }, {78, 65, 79, 00, 00, 00, },
199            {78, 69, 00, 00, 00, 00, }, {78, 69, 73, 00, 00, 00, },
200            {78, 69, 78, 00, 00, 00, }, {78, 69, 78, 71, 00, 00, },
201            {78, 73, 00, 00, 00, 00, }, {78, 73, 65, 78, 00, 00, },
202            {78, 73, 65, 78, 71, 00, }, {78, 73, 65, 79, 00, 00, },
203            {78, 73, 69, 00, 00, 00, }, {78, 73, 78, 00, 00, 00, },
204            {78, 73, 78, 71, 00, 00, }, {78, 73, 85, 00, 00, 00, },
205            {78, 79, 78, 71, 00, 00, }, {78, 79, 85, 00, 00, 00, },
206            {78, 85, 00, 00, 00, 00, }, {78, 85, 65, 78, 00, 00, },
207            {78, 85, 78, 00, 00, 00, }, {78, 85, 79, 00, 00, 00, },
208            {79, 00, 00, 00, 00, 00, }, {79, 85, 00, 00, 00, 00, },
209            {80, 65, 00, 00, 00, 00, }, {80, 65, 73, 00, 00, 00, },
210            {80, 65, 78, 00, 00, 00, }, {80, 65, 78, 71, 00, 00, },
211            {80, 65, 79, 00, 00, 00, }, {80, 69, 73, 00, 00, 00, },
212            {80, 69, 78, 00, 00, 00, }, {80, 69, 78, 71, 00, 00, },
213            {80, 73, 00, 00, 00, 00, }, {80, 73, 65, 78, 00, 00, },
214            {80, 73, 65, 79, 00, 00, }, {80, 73, 69, 00, 00, 00, },
215            {80, 73, 78, 00, 00, 00, }, {80, 73, 78, 71, 00, 00, },
216            {80, 79, 00, 00, 00, 00, }, {80, 79, 85, 00, 00, 00, },
217            {80, 85, 00, 00, 00, 00, }, {81, 73, 00, 00, 00, 00, },
218            {81, 73, 65, 00, 00, 00, }, {81, 73, 65, 78, 00, 00, },
219            {81, 73, 65, 78, 71, 00, }, {81, 73, 65, 79, 00, 00, },
220            {81, 73, 69, 00, 00, 00, }, {81, 73, 78, 00, 00, 00, },
221            {81, 73, 78, 71, 00, 00, }, {81, 73, 79, 78, 71, 00, },
222            {81, 73, 85, 00, 00, 00, }, {81, 85, 00, 00, 00, 00, },
223            {81, 85, 65, 78, 00, 00, }, {81, 85, 69, 00, 00, 00, },
224            {81, 85, 78, 00, 00, 00, }, {82, 65, 78, 00, 00, 00, },
225            {82, 65, 78, 71, 00, 00, }, {82, 65, 79, 00, 00, 00, },
226            {82, 69, 00, 00, 00, 00, }, {82, 69, 78, 00, 00, 00, },
227            {82, 69, 78, 71, 00, 00, }, {82, 73, 00, 00, 00, 00, },
228            {82, 79, 78, 71, 00, 00, }, {82, 79, 85, 00, 00, 00, },
229            {82, 85, 00, 00, 00, 00, }, {82, 85, 65, 78, 00, 00, },
230            {82, 85, 73, 00, 00, 00, }, {82, 85, 78, 00, 00, 00, },
231            {82, 85, 79, 00, 00, 00, }, {83, 65, 00, 00, 00, 00, },
232            {83, 65, 73, 00, 00, 00, }, {83, 65, 78, 00, 00, 00, },
233            {83, 65, 78, 71, 00, 00, }, {83, 65, 79, 00, 00, 00, },
234            {83, 69, 00, 00, 00, 00, }, {83, 69, 78, 00, 00, 00, },
235            {83, 69, 78, 71, 00, 00, }, {83, 72, 65, 00, 00, 00, },
236            {83, 72, 65, 73, 00, 00, }, {83, 72, 65, 78, 00, 00, },
237            {83, 72, 65, 78, 71, 00, }, {83, 72, 65, 79, 00, 00, },
238            {83, 72, 69, 00, 00, 00, }, {83, 72, 69, 78, 00, 00, },
239            {83, 72, 69, 78, 71, 00, }, {83, 72, 73, 00, 00, 00, },
240            {83, 72, 79, 85, 00, 00, }, {83, 72, 85, 00, 00, 00, },
241            {83, 72, 85, 65, 00, 00, }, {83, 72, 85, 65, 73, 00, },
242            {83, 72, 85, 65, 78, 00, }, {83, 72, 85, 65, 78, 71, },
243            {83, 72, 85, 73, 00, 00, }, {83, 72, 85, 78, 00, 00, },
244            {83, 72, 85, 79, 00, 00, }, {83, 73, 00, 00, 00, 00, },
245            {83, 79, 78, 71, 00, 00, }, {83, 79, 85, 00, 00, 00, },
246            {83, 85, 00, 00, 00, 00, }, {83, 85, 65, 78, 00, 00, },
247            {83, 85, 73, 00, 00, 00, }, {83, 85, 78, 00, 00, 00, },
248            {83, 85, 79, 00, 00, 00, }, {84, 65, 00, 00, 00, 00, },
249            {84, 65, 73, 00, 00, 00, }, {84, 65, 78, 00, 00, 00, },
250            {84, 65, 78, 71, 00, 00, }, {84, 65, 79, 00, 00, 00, },
251            {84, 69, 00, 00, 00, 00, }, {84, 69, 78, 71, 00, 00, },
252            {84, 73, 00, 00, 00, 00, }, {84, 73, 65, 78, 00, 00, },
253            {84, 73, 65, 79, 00, 00, }, {84, 73, 69, 00, 00, 00, },
254            {84, 73, 78, 71, 00, 00, }, {84, 79, 78, 71, 00, 00, },
255            {84, 79, 85, 00, 00, 00, }, {84, 85, 00, 00, 00, 00, },
256            {84, 85, 65, 78, 00, 00, }, {84, 85, 73, 00, 00, 00, },
257            {84, 85, 78, 00, 00, 00, }, {84, 85, 79, 00, 00, 00, },
258            {87, 65, 00, 00, 00, 00, }, {87, 65, 73, 00, 00, 00, },
259            {87, 65, 78, 00, 00, 00, }, {87, 65, 78, 71, 00, 00, },
260            {87, 69, 73, 00, 00, 00, }, {87, 69, 78, 00, 00, 00, },
261            {87, 69, 78, 71, 00, 00, }, {87, 79, 00, 00, 00, 00, },
262            {87, 85, 00, 00, 00, 00, }, {88, 73, 00, 00, 00, 00, },
263            {88, 73, 65, 00, 00, 00, }, {88, 73, 65, 78, 00, 00, },
264            {88, 73, 65, 78, 71, 00, }, {88, 73, 65, 79, 00, 00, },
265            {88, 73, 69, 00, 00, 00, }, {88, 73, 78, 00, 00, 00, },
266            {88, 73, 78, 71, 00, 00, }, {88, 73, 79, 78, 71, 00, },
267            {88, 73, 85, 00, 00, 00, }, {88, 85, 00, 00, 00, 00, },
268            {88, 85, 65, 78, 00, 00, }, {88, 85, 69, 00, 00, 00, },
269            {88, 85, 78, 00, 00, 00, }, {89, 65, 00, 00, 00, 00, },
270            {89, 65, 78, 00, 00, 00, }, {89, 65, 78, 71, 00, 00, },
271            {89, 65, 79, 00, 00, 00, }, {89, 69, 00, 00, 00, 00, },
272            {89, 73, 00, 00, 00, 00, }, {89, 73, 78, 00, 00, 00, },
273            {89, 73, 78, 71, 00, 00, }, {89, 79, 00, 00, 00, 00, },
274            {89, 79, 78, 71, 00, 00, }, {89, 79, 85, 00, 00, 00, },
275            {89, 85, 00, 00, 00, 00, }, {89, 85, 65, 78, 00, 00, },
276            {89, 85, 69, 00, 00, 00, }, {89, 85, 78, 00, 00, 00, },
277            {90, 65, 00, 00, 00, 00, }, {90, 65, 73, 00, 00, 00, },
278            {90, 65, 78, 00, 00, 00, }, {90, 65, 78, 71, 00, 00, },
279            {90, 65, 79, 00, 00, 00, }, {90, 69, 00, 00, 00, 00, },
280            {90, 69, 73, 00, 00, 00, }, {90, 69, 78, 00, 00, 00, },
281            {90, 69, 78, 71, 00, 00, }, {90, 72, 65, 00, 00, 00, },
282            {90, 72, 65, 73, 00, 00, }, {90, 72, 65, 78, 00, 00, },
283            {90, 72, 65, 78, 71, 00, }, {90, 72, 65, 79, 00, 00, },
284            {90, 72, 69, 00, 00, 00, }, {90, 72, 69, 78, 00, 00, },
285            {90, 72, 69, 78, 71, 00, }, {90, 72, 73, 00, 00, 00, },
286            {90, 72, 79, 78, 71, 00, }, {90, 72, 79, 85, 00, 00, },
287            {90, 72, 85, 00, 00, 00, }, {90, 72, 85, 65, 00, 00, },
288            {90, 72, 85, 65, 73, 00, }, {90, 72, 85, 65, 78, 00, },
289            {90, 72, 85, 65, 78, 71, }, {90, 72, 85, 73, 00, 00, },
290            {90, 72, 85, 78, 00, 00, }, {90, 72, 85, 79, 00, 00, },
291            {90, 73, 00, 00, 00, 00, }, {90, 79, 78, 71, 00, 00, },
292            {90, 79, 85, 00, 00, 00, }, {90, 85, 00, 00, 00, 00, },
293            {90, 85, 65, 78, 00, 00, }, {90, 85, 73, 00, 00, 00, },
294            {90, 85, 78, 00, 00, 00, }, {90, 85, 79, 00, 00, 00, },
295
296        };
297
298    /** First and last Chinese character with known Pinyin according to zh collation */
299    private static final String FIRST_PINYIN_UNIHAN =  "\u5416";
300    private static final String LAST_PINYIN_UNIHAN =  "\u5497";
301    /** The first Chinese character in Unicode block */
302    private static final char FIRST_UNIHAN = '\u3400';
303    private static final Collator COLLATOR = Collator.getInstance(Locale.CHINA);
304
305    private static HanziToPinyin sInstance;
306    private final boolean mHasChinaCollator;
307
308    public static class Token {
309        /**
310         * Separator between target string for each source char
311         */
312        public static final String SEPARATOR = " ";
313
314        public static final int LATIN = 1;
315        public static final int PINYIN = 2;
316        public static final int UNKNOWN = 3;
317
318        public Token() {
319        }
320
321        public Token(int type, String source, String target) {
322            this.type = type;
323            this.source = source;
324            this.target = target;
325        }
326        /**
327         * Type of this token, ASCII, PINYIN or UNKNOWN.
328         */
329        public int type;
330        /**
331         * Original string before translation.
332         */
333        public String source;
334        /**
335         * Translated string of source. For Han, target is corresponding Pinyin.
336         * Otherwise target is original string in source.
337         */
338        public String target;
339    }
340
341    protected HanziToPinyin(boolean hasChinaCollator) {
342        mHasChinaCollator = hasChinaCollator;
343    }
344
345    public static HanziToPinyin getInstance() {
346        synchronized(HanziToPinyin.class) {
347            if (sInstance != null) {
348                return sInstance;
349            }
350            // Check if zh_CN collation data is available
351            final Locale locale[] = Collator.getAvailableLocales();
352            for (int i = 0; i < locale.length; i++) {
353                if (locale[i].equals(Locale.CHINA)) {
354                    sInstance = new HanziToPinyin(true);
355                    return sInstance;
356                }
357            }
358            Log.w(TAG, "There is no Chinese collator, HanziToPinyin is disabled");
359            sInstance = new HanziToPinyin(false);
360            return sInstance;
361        }
362    }
363
364    private Token getToken(char character) {
365        Token token = new Token();
366        final String letter = Character.toString(character);
367        token.source = letter;
368        int offset = -1;
369        int cmp;
370        if (character < 256) {
371            token.type = Token.LATIN;
372            token.target = letter;
373            return token;
374        } else if (character < FIRST_UNIHAN) {
375            token.type = Token.UNKNOWN;
376            token.target = letter;
377            return token;
378        } else {
379            cmp = COLLATOR.compare(letter, FIRST_PINYIN_UNIHAN);
380            if (cmp < 0) {
381                token.type = Token.UNKNOWN;
382                token.target = letter;
383                return token;
384            } else if (cmp == 0) {
385                token.type = Token.PINYIN;
386                offset = 0;
387            } else {
388                cmp = COLLATOR.compare(letter, LAST_PINYIN_UNIHAN);
389                if (cmp > 0) {
390                    token.type = Token.UNKNOWN;
391                    token.target = letter;
392                    return token;
393                } else if (cmp == 0) {
394                    token.type = Token.PINYIN;
395                    offset = UNIHANS.length - 1;
396                }
397            }
398        }
399
400        token.type = Token.PINYIN;
401        if (offset < 0) {
402            int begin = 0;
403            int end = UNIHANS.length - 1;
404            while (begin <= end) {
405                offset = (begin + end) / 2;
406                final String unihan = Character.toString(UNIHANS[offset]);
407                cmp = COLLATOR.compare(letter, unihan);
408                if (cmp == 0) {
409                    break;
410                } else if (cmp > 0) {
411                    begin = offset + 1;
412                } else {
413                    end = offset - 1;
414                }
415            }
416        }
417        if (cmp < 0) {
418            offset--;
419        }
420        StringBuilder pinyin = new StringBuilder();
421        for (int j = 0; j < PINYINS[offset].length && PINYINS[offset][j] != 0; j++) {
422            pinyin.append((char)PINYINS[offset][j]);
423        }
424        token.target = pinyin.toString();
425        return token;
426    }
427
428    /**
429     * Convert the input to a array of tokens. The sequence of ASCII or Unknown
430     * characters without space will be put into a Token, One Hanzi character
431     * which has pinyin will be treated as a Token.
432     * If these is no China collator, the empty token array is returned.
433     */
434    public ArrayList<Token> get(final String input) {
435        ArrayList<Token> tokens = new ArrayList<Token>();
436        if (!mHasChinaCollator || TextUtils.isEmpty(input)) {
437            // return empty tokens.
438            return tokens;
439        }
440        final int inputLength = input.length();
441        final StringBuilder sb = new StringBuilder();
442        int tokenType = Token.LATIN;
443        // Go through the input, create a new token when
444        // a. Token type changed
445        // b. Get the Pinyin of current charater.
446        // c. current character is space.
447        for (int i = 0; i < inputLength; i++) {
448            final char character = input.charAt(i);
449            if (character == ' ') {
450                if (sb.length() > 0) {
451                    addToken(sb, tokens, tokenType);
452                }
453            } else if (character < 256) {
454                if (tokenType != Token.LATIN && sb.length() > 0) {
455                    addToken(sb, tokens, tokenType);
456                }
457                tokenType = Token.LATIN;
458                sb.append(character);
459            } else if (character < FIRST_UNIHAN) {
460                if (tokenType != Token.UNKNOWN && sb.length() > 0) {
461                    addToken(sb, tokens, tokenType);
462                }
463                tokenType = Token.UNKNOWN;
464                sb.append(character);
465            } else {
466                Token t = getToken(character);
467                if (t.type == Token.PINYIN) {
468                    if (sb.length() > 0) {
469                        addToken(sb, tokens, tokenType);
470                    }
471                    tokens.add(t);
472                    tokenType = Token.PINYIN;
473                } else {
474                    if (tokenType != t.type && sb.length() > 0) {
475                        addToken(sb, tokens, tokenType);
476                    }
477                    tokenType = t.type;
478                    sb.append(character);
479                }
480            }
481        }
482        if (sb.length() > 0) {
483            addToken(sb, tokens, tokenType);
484        }
485        return tokens;
486    }
487
488    private void addToken(final StringBuilder sb, final ArrayList<Token> tokens,
489            final int tokenType) {
490        String str = sb.toString();
491        tokens.add(new Token(tokenType, str, str));
492        sb.setLength(0);
493    }
494
495}
496