import java.util.regex.Matcher;
import java.util.regex.Pattern;

import net.sourceforge.pinyin4j.PinyinHelper;
import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;
import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;
 /***
 * 漢字工具類
 * @author csharper
 * @since 2014.12.26
 *
 */
public class ChineseCharacterUtil {
 /***
 * 將漢字轉(zhuǎn)成拼音(取首字母或全拼)
 * @param hanzi
 * @param full 是否全拼
 * @return
 */
 public static String convertHanzi2Pinyin(String hanzi,boolean full)
 {
 /***
 * ^[\u2E80-\u9FFF]+$ 匹配所有東亞區(qū)的語言 
 * ^[\u4E00-\u9FFF]+$ 匹配簡體和繁體 
 * ^[\u4E00-\u9FA5]+$ 匹配簡體
 */
 String regExp="^[\u4E00-\u9FFF]+$";
 StringBuffer sb=new StringBuffer();
 if(hanzi==null||"".equals(hanzi.trim()))
 {
 return "";
 }
 String pinyin="";
 for(int i=0;i<hanzi.length();i++)
 {
 char unit=hanzi.charAt(i);
 if(match(String.valueOf(unit),regExp))//是漢字，則轉(zhuǎn)拼音
 {
 pinyin=convertSingleHanzi2Pinyin(unit);
 if(full)
 {
  sb.append(pinyin);
 }
 else
 {
  sb.append(pinyin.charAt(0));
 }
 }
 else
 {
 sb.append(unit);
 }
 }
 return sb.toString();
 }
 /***
 * 將單個(gè)漢字轉(zhuǎn)成拼音
 * @param hanzi
 * @return
 */
 private static String convertSingleHanzi2Pinyin(char hanzi)
 {
 HanyuPinyinOutputFormat outputFormat = new HanyuPinyinOutputFormat();
 outputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
 String[] res;
 StringBuffer sb=new StringBuffer();
 try {
 res = PinyinHelper.toHanyuPinyinStringArray(hanzi,outputFormat);
 sb.append(res[0]);//對于多音字，只用第一個(gè)拼音
 } catch (Exception e) {
 e.printStackTrace();
 return "";
 }
 return sb.toString();
 }
 
 /***
 * @param str 源字符串
 * @param regex 正則表達(dá)式
 * @return 是否匹配
 */
 public static boolean match(String str,String regex)
 {
 Pattern pattern=Pattern.compile(regex);
 Matcher matcher=pattern.matcher(str);
 return matcher.find();
 }

 public static void main(String[] args) {
 System.out.println(convertHanzi2Pinyin("我是中國人123abc",true));
 }
}