android 汉字转拼音

---

前言

今天和大家分享一个从Android 7.0 系统源代码提取出来的汉字转成拼音实现方案，使用此方案必须要 android 7.0 以上系统。没啥复杂的逻辑 直接上代码，代码中注释详细说明。

---

代码如下（示例）：

import android.icu.text.Transliterator;
import android.text.TextUtils;
import android.util.Log;

import java.util.ArrayList;

public class HanZiToPinYin {
    private static final String TAG = "HanZiToPinYin";
    private static HanZiToPinYin instance;
    private Transliterator pinYinTrans;
    private Transliterator asciiTrans;

    public static class Token {
        /**
         * 每个源字符的目标字符串之间的分隔符
         */
        public static final String SEPARATOR = " ";

        /**
         * 拉丁语
         **/
        public static final int LATIN = 1;
        /**
         * 拼音
         **/
        public static final int PINYIN = 2;
        /**
         * 未知
         **/
        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 {
            pinYinTrans = Transliterator.getInstance("Han-Latin/Names; Latin-Ascii; Any-Upper");
            asciiTrans = Transliterator.getInstance("Latin-Ascii");
        } catch (IllegalArgumentException e) {
            Log.w(TAG, "Han-Latin/Names transliterator data is missing," + " HanZiToPinYin is disabled");
        }
    }

    public boolean hasChineseTransliterator() {
        return pinYinTrans != null;
    }

    public static HanZiToPinYin getInstance() {
        synchronized (HanZiToPinYin.class) {
            if (instance == null) {
                instance = new HanZiToPinYin();
            }
            return instance;
        }
    }


    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 = asciiTrans == null ? token.source : asciiTrans.transliterate(token.source);
            return;
        }

        token.type = Token.PINYIN;
        token.target = pinYinTrans.transliterate(token.source);
        if (TextUtils.isEmpty(token.target) || TextUtils.equals(token.source, token.target)) {
            token.type = Token.UNKNOWN;
            token.target = token.source;
        }
    }


    /**
     * 汉字转拼音
     *
     * @param input 输入源
     **/
    public String transliterate(final String input) {
        if (!hasChineseTransliterator() || TextUtils.isEmpty(input)) {
            return null;
        }
        return pinYinTrans.transliterate(input);
    }

    /**
     * 将输入转换为令牌数组。没有空格的 ASCII 或未知字符序列将被放入令牌中，一个带有拼音的汉字字符将被视为令牌。
     * 如果没有中文音译器或则 input为空，则返回空标记数组。
     *
     * @param input 输入源
     */
    public ArrayList<Token> getTokens(final String input) {
        ArrayList<Token> tokens = new ArrayList<>();
        if (!hasChineseTransliterator() || TextUtils.isEmpty(input)) {
            return tokens;
        }
        final int inputLength = input.length();
        final StringBuilder sb = new StringBuilder();
        int tokenType = Token.LATIN;
        Token token = new Token();

        // 遍历输入，创建新令牌时。令牌类型已更改 b。获取当前字符的拼音。C. 当前字符为空格。
        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);
    }

}

总结

这类并不支持多音字，所以如果一定要考虑多音字的问题，这个类就不适合了