Android开发笔记（八十三）多语言支持

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

import java.util.ArrayList;

import libcore.icu.Transliterator;

public class HanziToPinyin {
    private static final String TAG = "HanziToPinyin";

    private static HanziToPinyin sInstance;
    private Transliterator mPinyinTransliterator;
    private Transliterator mAsciiTransliterator;

    public static class Token {
        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;
        }

        public int type;
        public String source;
        public String target;
    }

    private HanziToPinyin() {
        try {
        	mPinyinTransliterator = new Transliterator("Han-Latin/Names; Latin-Ascii; Any-Upper");
        	mAsciiTransliterator = new Transliterator("Latin-Ascii");
        } catch (RuntimeException 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);
    }

    public ArrayList<Token> getTokens(final String input) {
        ArrayList<Token> tokens = new ArrayList<Token>();
        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();

        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);
    }
}

package libcore.icu;
/**
 * Exposes icu4c's Transliterator.
 */
public final class Transliterator {
  private long peer;
  /**
   * Creates a new Transliterator for the given id.
   */
  public Transliterator(String id) {
    peer = create(id);
  }
  @Override protected synchronized void finalize() throws Throwable {
    try {
      destroy(peer);
      peer = 0;
    } finally {
      super.finalize();
    }
  }
  /**
   * Returns the ids of all known transliterators.
   */
  public static native String[] getAvailableIDs();
  /**
   * Transliterates the specified string.
   */
  public String transliterate(String s) {
    return transliterate(peer, s);
  }
  private static native long create(String id);
  private static native void destroy(long peer);
  private static native String transliterate(long peer, String s);
}

String pinyin = HanziToPinyin.getInstance().transliterate("我爱你中国");

import java.util.HashSet;
import java.util.Locale;
import java.util.Set;

import net.sourceforge.pinyin4j.PinyinHelper;
import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType;
import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;
import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;
import net.sourceforge.pinyin4j.format.HanyuPinyinVCharType;
import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination;

public class pinyin4j {

	public static String makeStringByStringSet(Set<String> stringSet) {
		StringBuilder str = new StringBuilder();
		int i = 0;
		for (String s : stringSet) {
			if (i == stringSet.size() - 1) {
				str.append(s);
			} else {
				str.append(s + ",");
			}
			i++;
		}
		return str.toString().toLowerCase(Locale.getDefault());
	}

	public static Set<String> getPinyin(String src) {
		if (src != null && !src.trim().equalsIgnoreCase("")) {
			char[] srcChar;
			srcChar = src.toCharArray();
			// 汉语拼音格式输出类
			HanyuPinyinOutputFormat hanYuPinOutputFormat = new HanyuPinyinOutputFormat();

			// 输出设置，大小写，音标方式等
			hanYuPinOutputFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
			hanYuPinOutputFormat.setToneType(HanyuPinyinToneType.WITH_TONE_MARK);
			hanYuPinOutputFormat.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);

			String[][] temp = new String[src.length()][];
			for (int i = 0; i < srcChar.length; i++) {
				char c = srcChar[i];
				// 是中文或者a-z或者A-Z转换拼音(我的需求，是保留中文或者a-z或者A-Z)
				if (String.valueOf(c).matches("[\\u4E00-\\u9FA5]+")) {
					try {
						temp[i] = PinyinHelper.toHanyuPinyinStringArray(
								srcChar[i], hanYuPinOutputFormat);
					} catch (BadHanyuPinyinOutputFormatCombination e) {
						e.printStackTrace();
					}
				} else if (((int) c >= 65 && (int) c <= 90)
						|| ((int) c >= 97 && (int) c <= 122)) {
					temp[i] = new String[] { String.valueOf(srcChar[i]) };
				} else {
					temp[i] = new String[] { "" };
				}
			}
			String[] pingyinArray = Exchange(temp);
			Set<String> pinyinSet = new HashSet<String>();
			for (int i = 0; i < pingyinArray.length; i++) {
				pinyinSet.add(pingyinArray[i]);
			}
			return pinyinSet;
		}
		return null;
	}

	public static String[] Exchange(String[][] strJaggedArray) {
		String[][] temp = DoExchange(strJaggedArray);
		return temp[0];
	}

	private static String[][] DoExchange(String[][] strJaggedArray) {
		int len = strJaggedArray.length;
		if (len >= 2) {
			int len1 = strJaggedArray[0].length;
			int len2 = strJaggedArray[1].length;
			int newlen = len1 * len2;
			String[] temp = new String[newlen];
			int Index = 0;
			for (int i = 0; i < len1; i++) {
				for (int j = 0; j < len2; j++) {
					temp[Index] = strJaggedArray[0][i] + strJaggedArray[1][j];
					Index++;
				}
			}
			String[][] newArray = new String[len - 1][];
			for (int i = 2; i < len; i++) {
				newArray[i - 1] = strJaggedArray[i];
			}
			newArray[0] = temp;
			return DoExchange(newArray);
		} else {
			return strJaggedArray;
		}
	}
	
	public static String getPinyinFull(String hanzi) {
		return makeStringByStringSet(getPinyin(hanzi));
	}

}