C#----汉字转拼音

上一篇博客中介绍的是动态加载EasyUI控件显示到前台，里面包括按钮控件，而且每一个设备有可能有不同的命令和参数，不过总共可以显示的有八种不同的按钮，公用的，那如何实现不同的参数按钮点击的时候能够去加载相同的JS,而不用每次都去获取一个新的ID，于是就想到了一个办法，根据从数据库中获取的命令的数据，将汉字转化成拼音，这样就可以实现上面的结果。

代码如下：

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Threading.Tasks;
using System.Text.RegularExpressions;

namespace CssimpBLL.DoorAlarmCommonBLL
{
    ''' <summary>'''
    ''' 实现汉字转化为拼音'''
    ''' <remarks>实现的原理就是先将汉字转化成为内码，然后通过内码和拼音的对照来查找</remarks>'''
    ''' </summary>'''
    public class ChineseToSpellBLL
    {
        private static Regex MyRegex = new Regex("^[一-龥]$"); //汉字的正则表达式.eg: if(MyRegex.IsMatch(chrstr.ToString()))
        private static int[] pyvalue = 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};
        private static string[] pystr = 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"};

        #region ConvertToAllSpell 将汉字转化为全拼
        ''' <summary>'''
        ''' 将汉字转化为全拼'''
        ''' </summary>'''
        ''' <param name="strChinese"></param>'''
        ''' <returns></returns>'''
        public static string ConvertToAllSpell(string strChinese)
        {
            Regex MyRegex = new Regex("^[一-龥]$");
            byte[] array = new byte[2];
            string returnstr = "";
            int chrasc = 0;
            int i1 = 0;
            int i2 = 0;
            char[] nowchar = strChinese.ToCharArray();
            for (int j = 0; j < nowchar.Length; j++)
            {
                if (MyRegex.IsMatch(nowchar[j].ToString()))
                {
                    array = System.Text.Encoding.Default.GetBytes(nowchar[j].ToString());
                    i1 = (short)(array[0]);
                    i2 = (short)(array[1]);
                    chrasc = i1 * 256 + i2 - 65536;
                    if (chrasc > 0 && chrasc < 160)
                    {
                        returnstr += nowchar[j];
                    }
                    else
                    {
                        for (int i = (pyvalue.Length - 1); i >= 0; i--)
                        {
                            if (pyvalue[i] <= chrasc)
                            {
                                returnstr += pystr[i];
                                break;
                            }
                        }
                    }
                }
                else
                {
                    returnstr += nowchar[j].ToString();
                }
            }
            return returnstr;
        }
        #endregion

        #region ConvertToFirstSpell 将汉字转化为拼音首字母（大写）
        ''' <summary>'''
        ''' 将汉字转化为拼音首字母（大写）'''
        ''' </summary>'''
        ''' <param name="strChinese"></param>'''
        ''' <returns></returns>'''
        public static string ConvertToFirstSpell(string strChinese)
        {
            int len = strChinese.Length;
            string myStr = "";
            for (int i = 0; i < len; i++)
            {
                myStr += GetFirstSpell(strChinese.Substring(i, 1));
            }
            return myStr;
        }
        #endregion

        #region GetFirstSpell 获取第一个汉字的首字母（大写）
        ''' <summary>'''
        ''' 获取第一个汉字的首字母（大写）'''
        ''' </summary>'''
        ''' <param name="charChinese"></param>'''
        ''' <returns></returns>'''
        public static string GetFirstSpell(string charChinese)
        {
            byte[] arrCN = Encoding.Default.GetBytes(charChinese);
            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)
                    {
                        byte[] bytes = new byte[] { (byte)(65 + i) };
                        return Encoding.Default.GetString(bytes, 0, bytes.Length);
                    }
                }
                return "*";
            }
            else return charChinese;
        }
        #endregion

        #region ConvertFirstSpell 获取第一个汉字的拼音
        ''' <summary>'''
        ''' 获取第一个汉字的拼音'''
        ''' </summary>'''
        ''' <param name="charChinese"></param>'''
        ''' <returns></returns>'''
        public static string ConvertFirstSpell(string charChinese)
        {
            Regex MyRegex = new Regex("^[一-龥]$");
            byte[] array = new byte[2];
            string returnstr = "";
            int chrasc = 0;
            int i1 = 0;
            int i2 = 0;
            char[] nowchar = charChinese.ToCharArray();
            for (int j = 0; j < 1; j++)
            {
                if (MyRegex.IsMatch(nowchar[j].ToString()))
                {
                    array = System.Text.Encoding.Default.GetBytes(nowchar[j].ToString());
                    i1 = (short)(array[0]);
                    i2 = (short)(array[1]);
                    chrasc = i1 * 256 + i2 - 65536;
                    if (chrasc > 0 && chrasc < 160)
                    {
                        returnstr += nowchar[j];
                    }
                    else
                    {
                        for (int i = (pyvalue.Length - 1); i >= 0; i--)
                        {
                            if (pyvalue[i] <= chrasc)
                            {
                                returnstr += pystr[i];
                                break;
                            }
                        }
                    }
                }
                else
                {
                    returnstr += nowchar[j].ToString();
                }
            }
            return returnstr;
        }
        #endregion
    }
}

在上面的代码中有一个地方一开始很好奇，‘^[一-龥]$’ ，括号里面有这样一段代码，然后在百度上查了查，这是一个正则表达式，里面从前面的一到小短线后面的龥之间的任意字符。一是ASC码最小的汉字，是19968，龥的ASC码是40869，这其间包括了绝大多数常用和不怎么常用的简繁体字，并不是所有的，不过一般的文章而言足够用来查找文章中的任意汉字了，也有人用﨩，这个ASC码更大一些64041，不过大的这些也没啥意义，都是基本完全不会在正常文章中出现的字。