java 获取中文字符的首字母

原理: GB2312编码中的中文是按照拼音排序的

注意: 一些生僻的字无法获得正确的首字母，原因是这些字都是后加入的。

import java.io.UnsupportedEncodingException;  
  
/** 
 * 取得给定汉字串的首字母串,即声母串 
 * 
 * 注：只支持GB2312字符集中的汉字 
 */  
class ChineseInital {  
    private final static int[] areaCode = { 1601, 1637, 1833, 2078, 2274,  
            2302, 2433, 2594, 2787, 3106, 3212, 3472, 3635, 3722, 3730, 3858,  
            4027, 4086, 4390, 4558, 4684, 4925, 5249, 5590 };  
    private final static String[] letters = { "a", "b", "c", "d", "e",  
            "f", "g", "h", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s",  
            "t", "w", "x", "y", "z" };  
  
    /** 
     * 取得给定汉字串的首字母串
     * @param str 给定汉字串 
     * @return 所有字符的首字母
     */  
    public static String getAllFirstLetter(String str) {  
        if (str == null || str.trim().length() == 0) {  
            return "";  
        }  
  
        String _str = "";  
        for (int i = 0; i < str.length(); i++) {  
            _str = _str + this.getFirstLetter(str.substring(i, i + 1));  
        }  
  
        return _str;  
    }  
  
    /** 
     * 取得给定汉字的首字母,即声母 
     * @param chinese 给定的汉字 
     * @return 给定汉字的声母 
     */  
    public static String getFirstLetter(String chinese) {  
        if (chinese == null || chinese.trim().length() == 0) {  
            return "";  
        }  
        chinese = this.conversionStr(chinese, "GB2312", "ISO8859-1");  
  
        if (chinese.length() > 1) // 判断是不是汉字  
        {  
            int li_SectorCode = (int) chinese.charAt(0); // 汉字区码  
            int li_PositionCode = (int) chinese.charAt(1); // 汉字位码  
            li_SectorCode = li_SectorCode - 160;  
            li_PositionCode = li_PositionCode - 160;  
            int li_SecPosCode = li_SectorCode * 100 + li_PositionCode; // 汉字区位码  
            if (li_SecPosCode > 1600 && li_SecPosCode < 5590) {  
                for (int i = 0; i < 23; i++) {  
                    if (li_SecPosCode >= areaCode[i]  
                            && li_SecPosCode < areaCode[i + 1]) {  
                        chinese = letters[i];  
                        break;  
                    }  
                }  
            } else // 非汉字字符,如图形符号或ASCII码  
            {  
                chinese = this.conversionStr(chinese, "ISO8859-1", "GB2312");  
                chinese = chinese.substring(0, 1);  
            }  
        }  
  
        return chinese;  
    }  
  
    /** 
     * 字符串编码转换 
     * @param str 要转换编码的字符串 
     * @param charsetName 原来的编码 
     * @param toCharsetName 转换后的编码 
     * @return 经过编码转换后的字符串 
     */  
    private static String conversionStr(String str, String charsetName,String toCharsetName) {  
        try {  
            str = new String(str.getBytes(charsetName), toCharsetName);  
        } catch (UnsupportedEncodingException ex) {  
            System.out.println("字符串编码转换异常：" + ex.getMessage());  
        }  
        return str;  
    }  
  
}  

 

调用：

String s = ChineseInital.getAllFirstLetter("中华人民共和国");
System.out.println(s); // => "zhrmghg"

 

(整理于网络)