1. 程式人生 > >字串獲取字串的首字母

字串獲取字串的首字母

/**
 * 取得給定漢字串的首字母串,即聲母串
 * Title: ChineseCharToEn
 * @date 注:只支援GB2312字符集中的漢字
 */  
public final class ChineseCharToEn {  
    private final static int[] li_SecPosValue = { 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[] lc_FirstLetter = { "a", "b", "c", "d", "e",  
            "f", "g", "h", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s",  
            "t", "w", "x", "y", "z" };  
 
    /**
     * 取得給定漢字串的首字母串,即聲母串
     * @param str 給定漢字串
     * @return 聲母串
     */  
    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 + getFirstLetter(str.substring(i, i + 1));  
        }  
 
        return _str;  
    }  
 
    /**
     * 取得給定漢字的首字母,即聲母
     * @param chinese 給定的漢字
     * @return 給定漢字的聲母
     */  
    public static String getFirstLetter(String chinese) {
        if (chinese == null || chinese.trim().length() == 0) {  
            return "";  
        }  
        chinese = conversionStr(chinese, "GB2312", "ISO8859-1");  
 
        if (chinese.length() > 1) // 判斷是不是漢字  
        {  
            int li_SectorCode = (int) chinese.charAt(0); // 漢字區碼  
            int li_PositionCode = (int) chinese.charAt(1); // 漢字位碼
            li_SectorCode = li_SectorCode - 160;  
            li_PositionCode = li_PositionCode - 160;  
            int li_SecPosCode = li_SectorCode * 100 + li_PositionCode; // 漢字區位碼  
            if (li_SecPosCode > 1600 && li_SecPosCode < 5590) {  
                for (int i = 0; i < 23; i++) {  
                    if (li_SecPosCode >= li_SecPosValue[i]  
                            && li_SecPosCode < li_SecPosValue[i + 1]) {  
                        chinese = lc_FirstLetter[i];  
                        break;  
                    }  
                }  
            } else // 非漢字字元,如圖形符號或ASCII碼  
            {  
                chinese = conversionStr(chinese, "ISO8859-1", "GB2312");  
                chinese = chinese.substring(0, 1);  
            }  
        }  
 
        return chinese;  
    }  
 
    /**
     * 字串編碼轉換
     * @param str 要轉換編碼的字串
     * @param charsetName 原來的編碼
     * @param toCharsetName 轉換後的編碼
     * @return 經過編碼轉換後的字串
     */  
    private static String conversionStr(String str, String charsetName,String toCharsetName) {  
        try {  
            str = new String(str.getBytes(charsetName), toCharsetName);
        } catch (UnsupportedEncodingException ex) {  
            System.out.println("字串編碼轉換異常:" + ex.getMessage());  
        }  
        return str;  
    }  
 
    public static void main(String[] args) {  
        System.out.println("獲取拼音首字母:"+getAllFirstLetter("我愛中華人民共和國china"));  
    }  
 
}