java汉字转拼音

//将汉字转换为全拼
public static String getPingYin(String src){

    char[] t1 = null;
    t1=src.toCharArray();
    String[] t2 = new String[t1.length];
    HanyuPinyinOutputFormat t3 = new HanyuPinyinOutputFormat();
    t3.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    t3.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    t3.setVCharType(HanyuPinyinVCharType.WITH_V);
    String t4="";
    int t0=t1.length;
    try {
      for (int i=0;i<t0;i++)
      {
      //判断是否为汉字字符
         if(java.lang.Character.toString(t1[i]).matches("[\\u4E00-\\u9FA5]+"))   
              {
              t2 = PinyinHelper.toHanyuPinyinStringArray(t1[i], t3);              
              t4+=t2[0];
              }
          else
              t4+=java.lang.Character.toString(t1[i]);
      }
//       System.out.println(t4);
      return t4;
    }
    catch (BadHanyuPinyinOutputFormatCombination e1) {
      e1.printStackTrace();
    }
    return t4;
}
//返回中文的首字母
public static String getPinYinHeadChar(String str) {

String convert = "";
for (int j = 0; j < str.length(); j++) {
      char word = str.charAt(j);
      String[] pinyinArray = PinyinHelper.toHanyuPinyinStringArray(word);
      if (pinyinArray != null) {
      convert += pinyinArray[0].charAt(0);
      }else {
      convert += word;
      }
}
return convert;
}
//将字符串转移为ASCII码
public static String getCnASCII(String cnStr)
{
StringBuffer   strBuf   =   new   StringBuffer();
byte[]   bGBK   =   cnStr.getBytes();
        for(int   i=0;i <bGBK.length;i++){
//              System.out.println(Integer.toHexString(bGBK[i]&0xff));
                strBuf.append(Integer.toHexString(bGBK[i]&0xff));
        }
        return strBuf.toString();
}
public static void main(String[] args) {

String cnStr = "中华人民共和国";
System.out.println(getPingYin(cnStr));
                System.out.println(getPinYinHeadChar(cnStr));
}

}

下面为结果:

zhonghuarenmingongheguo
zhrmghg 

先把字符串换成字符数组，然后一个个判断是否在汉字的unicode编码里。范围是\u4E00-\u9FA5 和
\uF900-\uFA2D  还有一种简单的方法是用正则表达式

System.out.println("欢迎光临www.xxx.net".replaceAll("[^\u4E00-\u9FA5]", ""));