中文转成拼音算法

 import org.omg.IOP.Encoding;


public class ConvertPY {
	/// 

    /// 包含字符 ASC 码的整形数组。
    /// 
    private static int[] pv = new int[] { -20319, -20317, -20304, -20295, -20292, -20283, -20265, -20257, -20242, -20230, -20051, -20036, -20032, -20026, -20002, -19990, -19986, -19982, -19976, -19805, -19784, -19775, -19774, -19763, -19756, -19751, -19746, -19741, -19739, -19728, -19725, -19715, -19540, -19531, -19525, -19515, -19500, -19484, -19479, -19467, -19289, -19288, -19281, -19275, -19270, -19263, -19261, -19249, -19243, -19242, -19238, -19235, -19227, -19224, -19218, -19212, -19038, -19023, -19018, -19006, -19003, -18996, -18977, -18961, -18952, -18783, -18774, -18773, -18763, -18756, -18741, -18735, -18731, -18722, -18710, -18697, -18696, -18526, -18518, -18501, -18490, -18478, -18463, -18448, -18447, -18446, -18239, -18237, -18231, -18220, -18211, -18201, -18184, -18183, -18181, -18012, -17997, -17988, -17970, -17964, -17961, -17950, -17947, -17931, -17928, -17922, -17759, -17752, -17733, -17730, -17721, -17703, -17701, -17697, -17692, -17683, -17676, -17496, -17487, -17482, -17468, -17454, -17433, -17427, -17417, -17202, -17185, -16983, -16970, -16942, -16915, -16733, -16708, -16706, -16689, -16664, -16657, -16647, -16474, -16470, -16465, -16459, -16452, -16448, -16433, -16429, -16427, -16423, -16419, -16412, -16407, -16403, -16401, -16393, -16220, -16216, -16212, -16205, -16202, -16187, -16180, -16171, -16169, -16158, -16155, -15959, -15958, -15944, -15933, -15920, -15915, -15903, -15889, -15878, -15707, -15701, -15681, -15667, -15661, -15659, -15652, -15640, -15631, -15625, -15454, -15448, -15436, -15435, -15419, -15416, -15408, -15394, -15385, -15377, -15375, -15369, -15363, -15362, -15183, -15180, -15165, -15158, -15153, -15150, -15149, -15144, -15143, -15141, -15140, -15139, -15128, -15121, -15119, -15117, -15110, -15109, -14941, -14937, -14933, -14930, -14929, -14928, -14926, -14922, -14921, -14914, -14908, -14902, -14894, -14889, -14882, -14873, -14871, -14857, -14678, -14674, -14670, -14668, -14663, -14654, -14645, -14630, -14594, -14429, -14407, -14399, -14384, -14379, -14368, -14355, -14353, -14345, -14170, -14159, -14151, -14149, -14145, -14140, -14137, -14135, -14125, -14123, -14122, -14112, -14109, -14099, -14097, -14094, -14092, -14090, -14087, -14083, -13917, -13914, -13910, -13907, -13906, -13905, -13896, -13894, -13878, -13870, -13859, -13847, -13831, -13658, -13611, -13601, -13406, -13404, -13400, -13398, -13395, -13391, -13387, -13383, -13367, -13359, -13356, -13343, -13340, -13329, -13326, -13318, -13147, -13138, -13120, -13107, -13096, -13095, -13091, -13076, -13068, -13063, -13060, -12888, -12875, -12871, -12860, -12858, -12852, -12849, -12838, -12831, -12829, -12812, -12802, -12607, -12597, -12594, -12585, -12556, -12359, -12346, -12320, -12300, -12120, -12099, -12089, -12074, -12067, -12058, -12039, -11867, -11861, -11847, -11831, -11798, -11781, -11604, -11589, -11536, -11358, -11340, -11339, -11324, -11303, -11097, -11077, -11067, -11055, -11052, -11045, -11041, -11038, -11024, -11020, -11019, -11018, -11014, -10838, -10832, -10815, -10800, -10790, -10780, -10764, -10587, -10544, -10533, -10519, -10331, -10329, -10328, -10322, -10315, -10309, -10307, -10296, -10281, -10274, -10270, -10262, -10260, -10256, -10254 };

    /// 

    /// 包含汉字拼音的字符串数组。
    /// 
    private static String[] ps = new String[] { "a", "ai", "an", "ang", "ao", "ba", "bai", "ban", "bang", "bao", "bei", "ben", "beng", "bi", "bian", "biao", "bie", "bin", "bing", "bo", "bu", "ca", "cai", "can", "cang", "cao", "ce", "ceng", "cha", "chai", "chan", "chang", "chao", "che", "chen", "cheng", "chi", "chong", "chou", "chu", "chuai", "chuan", "chuang", "chui", "chun", "chuo", "ci", "cong", "cou", "cu", "cuan", "cui", "cun", "cuo", "da", "dai", "dan", "dang", "dao", "de", "deng", "di", "dian", "diao", "die", "ding", "diu", "dong", "dou", "du", "duan", "dui", "dun", "duo", "e", "en", "er", "fa", "fan", "fang", "fei", "fen", "feng", "fo", "fou", "fu", "ga", "gai", "gan", "gang", "gao", "ge", "gei", "gen", "geng", "gong", "gou", "gu", "gua", "guai", "guan", "guang", "gui", "gun", "guo", "ha", "hai", "han", "hang", "hao", "he", "hei", "hen", "heng", "hong", "hou", "hu", "hua", "huai", "huan", "huang", "hui", "hun", "huo", "ji", "jia", "jian", "jiang", "jiao", "jie", "jin", "jing", "jiong", "jiu", "ju", "juan", "jue", "jun", "ka", "kai", "kan", "kang", "kao", "ke", "ken", "keng", "kong", "kou", "ku", "kua", "kuai", "kuan", "kuang", "kui", "kun", "kuo", "la", "lai", "lan", "lang", "lao", "le", "lei", "leng", "li", "lia", "lian", "liang", "liao", "lie", "lin", "ling", "liu", "long", "lou", "lu", "lv", "luan", "lue", "lun", "luo", "ma", "mai", "man", "mang", "mao", "me", "mei", "men", "meng", "mi", "mian", "miao", "mie", "min", "ming", "miu", "mo", "mou", "mu", "na", "nai", "nan", "nang", "nao", "ne", "nei", "nen", "neng", "ni", "nian", "niang", "niao", "nie", "nin", "ning", "niu", "nong", "nu", "nv", "nuan", "nue", "nuo", "o", "ou", "pa", "pai", "pan", "pang", "pao", "pei", "pen", "peng", "pi", "pian", "piao", "pie", "pin", "ping", "po", "pu", "qi", "qia", "qian", "qiang", "qiao", "qie", "qin", "qing", "qiong", "qiu", "qu", "quan", "que", "qun", "ran", "rang", "rao", "re", "ren", "reng", "ri", "rong", "rou", "ru", "ruan", "rui", "run", "ruo", "sa", "sai", "san", "sang", "sao", "se", "sen", "seng", "sha", "shai", "shan", "shang", "shao", "she", "shen", "sheng", "shi", "shou", "shu", "shua", "shuai", "shuan", "shuang", "shui", "shun", "shuo", "si", "song", "sou", "su", "suan", "sui", "sun", "suo", "ta", "tai", "tan", "tang", "tao", "te", "teng", "ti", "tian", "tiao", "tie", "ting", "tong", "tou", "tu", "tuan", "tui", "tun", "tuo", "wa", "wai", "wan", "wang", "wei", "wen", "weng", "wo", "wu", "xi", "xia", "xian", "xiang", "xiao", "xie", "xin", "xing", "xiong", "xiu", "xu", "xuan", "xue", "xun", "ya", "yan", "yang", "yao", "ye", "yi", "yin", "ying", "yo", "yong", "you", "yu", "yuan", "yue", "yun", "za", "zai", "zan", "zang", "zao", "ze", "zei", "zen", "zeng", "zha", "zhai", "zhan", "zhang", "zhao", "zhe", "zhen", "zheng", "zhi", "zhong", "zhou", "zhu", "zhua", "zhuai", "zhuan", "zhuang", "zhui", "zhun", "zhuo", "zi", "zong", "zou", "zu", "zuan", "zui", "zun", "zuo" };

    /// 

    /// 包含要排除处理的字符的字符串数组。
    /// 
    private static String[] bd = new String[] { "，", "。", "“", "”", "‘", "’", "￥", "＄", "（", "「", "『", "）", "」", "』", "［", "〖", "【", "］", "〗", "】", "—", "…", "《", "＜", "》", "＞" };

    /// 

    /// 将指定中文字符串转换为拼音形式。
    /// 
    /// 要转换的中文字符串。
    /// 连接拼音之间的分隔符。
    /// 指定是否将首字母大写。
    /// 包含中文字符串的拼音的字符串。
    public static String Convert(String chs, String separator, boolean initialCap)
    {
        if (chs == null || chs.length() == 0) return "";
        if (separator == null || separator.length() == 0) separator = "";

        byte[] array = new byte[2];
        String returnstr = "";
        int chrasc = 0;
        int i1 = 0;
        int i2 = 0;
        boolean b = false;
        char[] nowchar = chs.toCharArray();

      //  CultureInfo ci = Thread.currentThread().CurrentCulture;
        //TextInfo ti = ci.TextInfo;
        		//	ThreadGroup ci=Thread.currentThread().getThreadGroup();
        			           

        for (int j = 0; j < nowchar.length; j++)
        {
            array = chs.getBytes();
            String s = (new Character(nowchar[j])).toString(); ;

            if (array.length == 1)
            {
                b = true;
                returnstr += s;
            }
            else
            {
                if (s == "？")
                {
                    if (returnstr == "" || b == true) returnstr += s;
                    else returnstr += separator + s;

                    continue;
                }

                i1 = (short)(array[0]);
                i2 = (short)(array[1]);

                chrasc = i1 * 256 + i2 - 65536;

                for (int i = (pv.length - 1); i >= 0; i--)
                {
                    if (pv[i] <= chrasc)
                    {
                        s = ps[i];

                      //  if (initialCap == true) s = ti.ToTitleCase(s);

                        if (returnstr == "" || b == true) returnstr += s;
                        else returnstr += separator + s;

                        break;
                    }
                }

                b = false;
            }
        }

        returnstr = returnstr.replace( separator," ");
        return returnstr;
    }

    /// 

    /// 将指定中文字符串转换为拼音形式。
    /// 
    /// 要转换的中文字符串。
    /// 连接拼音之间的分隔符。
    /// 包含中文字符串的拼音的字符串。
    public static String Convert(String chs, String separator)
    {
        return Convert(chs, separator, false);
    }

    /**/
    /// 

    /// 将指定中文字符串转换为拼音形式。
    /// 
    /// 要转换的中文字符串。
    /// 指定是否将首字母大写。
    /// 包含中文字符串的拼音的字符串。
    public static String Convert(String chs, boolean initialCap)
    {
        return Convert(chs, "", initialCap);
    }

    /// 

    /// 将指定中文字符串转换为拼音形式。
    /// 
    /// 要转换的中文字符串。
    /// 包含中文字符串的拼音的字符串。
    public static String Convert(String chs)
    {
        return Convert(chs, "");
    }

    /// 

    /// 获取简体中文字符串拼音首字母
    /// 
    /// 简体中文字符串
    /// 拼音首字母
    static public String GetSpells(String input)
    {
        int len = input.length();
        String reVal = "";
        for (int i = 0; i < len; i++)
        {
            reVal += GetSpell(input.substring(i, 1));
        }
        return reVal;
    }

    /// 

    /// 获取一个简体中文字的拼音首字母
    /// 
    /// 一个简体中文字
    /// 拼音首字母
    static public String GetSpell(String cn)
    {
        byte[] arrCN = cn.getBytes();
        if (arrCN.length > 1)
        {
            int area = (short)arrCN[0];
            int pos = (short)arrCN[1];
            int code = (area << 8) + pos;
            int[] areacode = { 45217, 45253, 45761, 46318, 46826, 47010, 47297, 47614, 48119, 48119, 49062, 49324, 49896, 50371, 50614, 50622, 50906, 51387, 51446, 52218, 52698, 52698, 52698, 52980, 53689, 54481 };
            for (int i = 0; i < 26; i++)
            {
                int max = 55290;
                if (i != 25) max = areacode[i + 1];
                if (areacode[i] <= code && code < max)
                {
                    return new String(new byte[] { (byte)(65 + i) });
                }
            }
            return "?";
        }
        else return cn;
    }
    
    public static void main(String[] args) {
    	 System.out.println(ConvertPY.Convert("这的的话的是","-",true));
	}
}

 
	public class GetCh2Spell {
	    public static int compare(String str1, String str2)
	     {
	         int result = 0;
	         String m_s1 = null;
	         String m_s2 = null;
	         try
	         {
	             m_s1 = new String(str1.getBytes(_FromEncode_), _ToEncode_);
	             m_s2 = new String(str2.getBytes(_FromEncode_), _ToEncode_);
	         }
	         catch(Exception e)
	         {
	             return str1.compareTo(str2);
	         }
	         result = chineseCompareTo(m_s1, m_s2);
	         return result;
	     }

	     public static int getCharCode(String s)
	     {
	         if(s == null && s.equals(""))
	             return -1;
	         byte b[] = s.getBytes();
	         int value = 0;
	         for(int i = 0; i < b.length && i <= 2; i++)
	             value = value * 100 + b[i];

	         return value;
	     }

	     public static int chineseCompareTo(String s1, String s2)
	     {
	         int len1 = s1.length();
	         int len2 = s2.length();
	         int n = Math.min(len1, len2);
	         for(int i = 0; i < n; i++)
	         {
	             int s1_code = getCharCode(s1.charAt(i) + "");
	             int s2_code = getCharCode(s2.charAt(i) + "");
	             if(s1_code * s2_code < 0)
	                 return Math.min(s1_code, s2_code);
	             if(s1_code != s2_code)
	                 return s1_code - s2_code;
	         }

	         return len1 - len2;
	     }

	     public static String getBeginCharacter(String res)
	     {
	         String a = res;
	         String result = "";
	         for(int i = 0; i < a.length(); i++)
	         {
	             String current = a.substring(i, i + 1);
	             if(compare(current, "\u554A") < 0)
	                 result = result + current;
	             else
	             if(compare(current, "\u554A") >= 0 && compare(current, "\u5EA7") <= 0)
	                 if(compare(current, "\u531D") >= 0)
	                     result = result + "z";
	                 else
	                 if(compare(current, "\u538B") >= 0)
	                     result = result + "y";
	                 else
	                 if(compare(current, "\u6614") >= 0)
	                     result = result + "x";
	                 else
	                 if(compare(current, "\u6316") >= 0)
	                     result = result + "w";
	                 else
	                 if(compare(current, "\u584C") >= 0)
	                     result = result + "t";
	                 else
	                 if(compare(current, "\u6492") >= 0)
	                     result = result + "s";
	                 else
	                 if(compare(current, "\u7136") >= 0)
	                     result = result + "r";
	                 else
	                 if(compare(current, "\u671F") >= 0)
	                     result = result + "q";
	                 else
	                 if(compare(current, "\u556A") >= 0)
	                     result = result + "p";
	                 else
	                 if(compare(current, "\u54E6") >= 0)
	                     result = result + "o";
	                 else
	                 if(compare(current, "\u62FF") >= 0)
	                     result = result + "n";
	                 else
	                 if(compare(current, "\u5988") >= 0)
	                     result = result + "m";
	                 else
	                 if(compare(current, "\u5783") >= 0)
	                     result = result + "l";
	                 else
	                 if(compare(current, "\u5580") >= 0)
	                     result = result + "k";
	                 else
	                 if(compare(current, "\u51FB") > 0)
	                     result = result + "j";
	                 else
	                 if(compare(current, "\u54C8") >= 0)
	                     result = result + "h";
	                 else
	                 if(compare(current, "\u5676") >= 0)
	                     result = result + "g";
	                 else
	                 if(compare(current, "\u53D1") >= 0)
	                     result = result + "f";
	                 else
	                 if(compare(current, "\u86FE") >= 0)
	                     result = result + "e";
	                 else
	                 if(compare(current, "\u642D") >= 0)
	                     result = result + "d";
	                 else
	                 if(compare(current, "\u64E6") >= 0)
	                     result = result + "c";
	                 else
	                 if(compare(current, "\u82AD") >= 0)
	                     result = result + "b";
	                 else
	                 if(compare(current, "\u554A") >= 0)
	                     result = result + "a";
	         }

	         return result;
	     }

	     public static String getFirstStr(String str)
	     {
	         char a = str.charAt(0);
	         char aa[] = {
	             a
	         };
	         String sss = new String(aa);
	         if(Character.isDigit(aa[0]))
	             sss = "data";
	         else
	         if(a >= 'a' && a <= 'z' || a >= 'A' && a <= 'Z')
	             sss = "character";
	         else
	             sss = getBeginCharacter(sss);
	         return sss;
	     }

	     private static String _FromEncode_ = "GBK";
	     private static String _ToEncode_ = "GBK";

  public static void main(String[] args) {
		System.out.println( GetCh2Spell.chineseCompareTo("的风格的话","的后果的后果"));
		System.out.println( GetCh2Spell.getFirstStr("sdfsdfds"));
	 
	  
	}

}