看源码时发现, 在联系人存储的代码下, 有一个汉字转拼音的工具类 HanziToPinyin;
使用了全球化支持库 icu4j
导入依赖文件:
|
1 |
implementation 'com.ibm.icu:icu4j:60.2' |
使用方法:
|
1 2 |
hanziToPinyin = HanziToPinyin.getInstance(); String pinyin = hanziToPinyin.transliterate("汉语拼音"); |
HanziToPinyin 源码
|
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 |
/* * Copyright (C) 2011 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. */ package com.android.providers.contacts; import android.icu.text.Transliterator; import android.text.TextUtils; import android.util.Log; import java.util.ArrayList; import java.util.Locale; /** * An object to convert Chinese character to its corresponding pinyin string. * For characters with multiple possible pinyin string, only one is selected * according to ICU Transliterator class. Polyphone is not supported in this * implementation. */ public class HanziToPinyin { private static final String TAG = "HanziToPinyin"; private static HanziToPinyin sInstance; private Transliterator mPinyinTransliterator; private Transliterator mAsciiTransliterator; public static class Token { /** * Separator between target string for each source char */ public static final String SEPARATOR = " "; public static final int LATIN = 1; public static final int PINYIN = 2; public static final int UNKNOWN = 3; public Token() { } public Token(int type, String source, String target) { this.type = type; this.source = source; this.target = target; } /** * Type of this token, ASCII, PINYIN or UNKNOWN. */ public int type; /** * Original string before translation. */ public String source; /** * Translated string of source. For Han, target is corresponding Pinyin. Otherwise target is * original string in source. */ public String target; } private HanziToPinyin() { try { mPinyinTransliterator = Transliterator.getInstance( "Han-Latin/Names; Latin-Ascii; Any-Upper"); mAsciiTransliterator = Transliterator.getInstance("Latin-Ascii"); } catch (IllegalArgumentException e) { Log.w(TAG, "Han-Latin/Names transliterator data is missing," + " HanziToPinyin is disabled"); } } public boolean hasChineseTransliterator() { return mPinyinTransliterator != null; } public static HanziToPinyin getInstance() { synchronized (HanziToPinyin.class) { if (sInstance == null) { sInstance = new HanziToPinyin(); } return sInstance; } } private void tokenize(char character, Token token) { token.source = Character.toString(character); // ASCII if (character < 128) { token.type = Token.LATIN; token.target = token.source; return; } // Extended Latin. Transcode these to ASCII equivalents if (character < 0x250 || (0x1e00 <= character && character < 0x1eff)) { token.type = Token.LATIN; token.target = mAsciiTransliterator == null ? token.source : mAsciiTransliterator.transliterate(token.source); return; } token.type = Token.PINYIN; token.target = mPinyinTransliterator.transliterate(token.source); if (TextUtils.isEmpty(token.target) || TextUtils.equals(token.source, token.target)) { token.type = Token.UNKNOWN; token.target = token.source; } } public String transliterate(final String input) { if (!hasChineseTransliterator() || TextUtils.isEmpty(input)) { return null; } return mPinyinTransliterator.transliterate(input); } /** * Convert the input to a array of tokens. The sequence of ASCII or Unknown characters without * space will be put into a Token, One Hanzi character which has pinyin will be treated as a * Token. If there is no Chinese transliterator, the empty token array is returned. */ public ArrayList<Token> getTokens(final String input) { ArrayList<Token> tokens = new ArrayList<Token>(); if (!hasChineseTransliterator() || TextUtils.isEmpty(input)) { // return empty tokens. return tokens; } final int inputLength = input.length(); final StringBuilder sb = new StringBuilder(); int tokenType = Token.LATIN; Token token = new Token(); // Go through the input, create a new token when // a. Token type changed // b. Get the Pinyin of current charater. // c. current character is space. for (int i = 0; i < inputLength; i++) { final char character = input.charAt(i); if (Character.isSpaceChar(character)) { if (sb.length() > 0) { addToken(sb, tokens, tokenType); } } else { tokenize(character, token); if (token.type == Token.PINYIN) { if (sb.length() > 0) { addToken(sb, tokens, tokenType); } tokens.add(token); token = new Token(); } else { if (tokenType != token.type && sb.length() > 0) { addToken(sb, tokens, tokenType); } sb.append(token.target); } tokenType = token.type; } } if (sb.length() > 0) { addToken(sb, tokens, tokenType); } return tokens; } private void addToken( final StringBuilder sb, final ArrayList<Token> tokens, final int tokenType) { String str = sb.toString(); tokens.add(new Token(tokenType, str, str)); sb.setLength(0); } } |
0 Comments