zoukankan      html  css  js  c++  java
  • 汉字转拼音的代码——(C#版)

    汉字转拼音

      1 using System;
      2 using System.Collections.Generic;
      3 using System.Text;
      4 using System.Text.RegularExpressions;
      5 
      6 namespace CommonLibrary
      7 {
      8     /// <summary>
      9     /// 汉字转拼音类(支持全拼,首拼)
     10     /// </summary>
     11     public class ChineseToPinyinHelper
     12     {
     13         private static int[] pyValue = new int[]
     14                 {
     15                 -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,-20242,-20230,-20051,-20036,
     16                 -20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,-19775,-19774,-19763,
     17                 -19756,-19751,-19746,-19741,-19739,-19728,-19725,-19715,-19540,-19531,-19525,-19515,
     18                 -19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263,-19261,-19249,
     19                 -19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,
     20                 -19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,
     21                 -18731,-18722,-18710,-18697,-18696,-18526,-18518,-18501,-18490,-18478,-18463,-18448,
     22                 -18447,-18446,-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183, -18181,-18012,
     23                 -17997,-17988,-17970,-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,
     24                 -17733,-17730,-17721,-17703,-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,
     25                 -17468,-17454,-17433,-17427,-17417,-17202,-17185,-16983,-16970,-16942,-16915,-16733,
     26                 -16708,-16706,-16689,-16664,-16657,-16647,-16474,-16470,-16465,-16459,-16452,-16448,
     27                 -16433,-16429,-16427,-16423,-16419,-16412,-16407,-16403,-16401,-16393,-16220,-16216,
     28                 -16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,-16155,-15959,-15958,-15944,
     29                 -15933,-15920,-15915,-15903,-15889,-15878,-15707,-15701,-15681,-15667,-15661,-15659,
     30                 -15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,-15408,-15394,
     31                 -15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,-15150,
     32                 -15149,-15144,-15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,
     33                 -14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,
     34                 -14894,-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668,-14663,-14654,
     35                 -14645,-14630,-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345,
     36                 -14170,-14159,-14151,-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,
     37                 -14109,-14099,-14097,-14094,-14092,-14090,-14087,-14083,-13917,-13914,-13910,-13907,
     38                 -13906,-13905,-13896,-13894,-13878,-13870,-13859,-13847,-13831,-13658,-13611,-13601,
     39                 -13406,-13404,-13400,-13398,-13395,-13391,-13387,-13383,-13367,-13359,-13356,-13343,
     40                 -13340,-13329,-13326,-13318,-13147,-13138,-13120,-13107,-13096,-13095,-13091,-13076,
     41                 -13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,-12852,-12849,-12838,-12831,
     42                 -12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,-12346,-12320,-12300,
     43                 -12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,-11831,-11798,
     44                 -11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,-11067,
     45                 -11055,-11052,-11045,-11041,-11038,-11024,-11020,-11019,-11018,-11014,-10838,-10832,
     46                 -10815,-10800,-10790,-10780,-10764,-10587,-10544,-10533,-10519,-10331,-10329,-10328,
     47                 -10322,-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254
     48                 };
     49 
     50         private static string[] pyName = new string[]
     51                 {
     52                 "A","Ai","An","Ang","Ao","Ba","Bai","Ban","Bang","Bao","Bei","Ben",
     53                 "Beng","Bi","Bian","Biao","Bie","Bin","Bing","Bo","Bu","Ba","Cai","Can",
     54                 "Cang","Cao","Ce","Ceng","Cha","Chai","Chan","Chang","Chao","Che","Chen","Cheng",
     55                 "Chi","Chong","Chou","Chu","Chuai","Chuan","Chuang","Chui","Chun","Chuo","Ci","Cong",
     56                 "Cou","Cu","Cuan","Cui","Cun","Cuo","Da","Dai","Dan","Dang","Dao","De",
     57                 "Deng","Di","Dian","Diao","Die","Ding","Diu","Dong","Dou","Du","Duan","Dui",
     58                 "Dun","Duo","E","En","Er","Fa","Fan","Fang","Fei","Fen","Feng","Fo",
     59                 "Fou","Fu","Ga","Gai","Gan","Gang","Gao","Ge","Gei","Gen","Geng","Gong",
     60                 "Gou","Gu","Gua","Guai","Guan","Guang","Gui","Gun","Guo","Ha","Hai","Han",
     61                 "Hang","Hao","He","Hei","Hen","Heng","Hong","Hou","Hu","Hua","Huai","Huan",
     62                 "Huang","Hui","Hun","Huo","Ji","Jia","Jian","Jiang","Jiao","Jie","Jin","Jing",
     63                 "Jiong","Jiu","Ju","Juan","Jue","Jun","Ka","Kai","Kan","Kang","Kao","Ke",
     64                 "Ken","Keng","Kong","Kou","Ku","Kua","Kuai","Kuan","Kuang","Kui","Kun","Kuo",
     65                 "La","Lai","Lan","Lang","Lao","Le","Lei","Leng","Li","Lia","Lian","Liang",
     66                 "Liao","Lie","Lin","Ling","Liu","Long","Lou","Lu","Lv","Luan","Lue","Lun",
     67                 "Luo","Ma","Mai","Man","Mang","Mao","Me","Mei","Men","Meng","Mi","Mian",
     68                 "Miao","Mie","Min","Ming","Miu","Mo","Mou","Mu","Na","Nai","Nan","Nang",
     69                 "Nao","Ne","Nei","Nen","Neng","Ni","Nian","Niang","Niao","Nie","Nin","Ning",
     70                 "Niu","Nong","Nu","Nv","Nuan","Nue","Nuo","O","Ou","Pa","Pai","Pan",
     71                 "Pang","Pao","Pei","Pen","Peng","Pi","Pian","Piao","Pie","Pin","Ping","Po",
     72                 "Pu","Qi","Qia","Qian","Qiang","Qiao","Qie","Qin","Qing","Qiong","Qiu","Qu",
     73                 "Quan","Que","Qun","Ran","Rang","Rao","Re","Ren","Reng","Ri","Rong","Rou",
     74                 "Ru","Ruan","Rui","Run","Ruo","Sa","Sai","San","Sang","Sao","Se","Sen",
     75                 "Seng","Sha","Shai","Shan","Shang","Shao","She","Shen","Sheng","Shi","Shou","Shu",
     76                 "Shua","Shuai","Shuan","Shuang","Shui","Shun","Shuo","Si","Song","Sou","Su","Suan",
     77                 "Sui","Sun","Suo","Ta","Tai","Tan","Tang","Tao","Te","Teng","Ti","Tian",
     78                 "Tiao","Tie","Ting","Tong","Tou","Tu","Tuan","Tui","Tun","Tuo","Wa","Wai",
     79                 "Wan","Wang","Wei","Wen","Weng","Wo","Wu","Xi","Xia","Xian","Xiang","Xiao",
     80                 "Xie","Xin","Xing","Xiong","Xiu","Xu","Xuan","Xue","Xun","Ya","Yan","Yang",
     81                 "Yao","Ye","Yi","Yin","Ying","Yo","Yong","You","Yu","Yuan","Yue","Yun",
     82                 "Za", "Zai","Zan","Zang","Zao","Ze","Zei","Zen","Zeng","Zha","Zhai","Zhan",
     83                 "Zhang","Zhao","Zhe","Zhen","Zheng","Zhi","Zhong","Zhou","Zhu","Zhua","Zhuai","Zhuan",
     84                 "Zhuang","Zhui","Zhun","Zhuo","Zi","Zong","Zou","Zu","Zuan","Zui","Zun","Zuo"
     85                 };
     86 
     87         /// <summary>
     88         /// 把汉字转换成拼音(全拼)
     89         /// </summary>
     90         /// <param name="zhString">汉字字符串</param>
     91         /// <returns>转换后的拼音(全拼)字符串</returns>
     92         public static string ConvertToQP(string zhString)
     93         {
     94             // 匹配中文字符
     95             Regex regex = new Regex("^[u4e00-u9fa5]$");
     96             byte[] array = new byte[2];
     97             string pyString = "";
     98             int chrAsc = 0;
     99             int i1 = 0;
    100             int i2 = 0;
    101             char[] noWChar = zhString.ToCharArray();
    102 
    103             for (int j = 0; j < noWChar.Length; j++)
    104             {
    105                 // 中文字符
    106                 if (regex.IsMatch(noWChar[j].ToString()))
    107                 {
    108                     array = System.Text.Encoding.Default.GetBytes(noWChar[j].ToString());
    109                     i1 = (short)(array[0]);
    110                     i2 = (short)(array[1]);
    111                     chrAsc = i1 * 256 + i2 - 65536;
    112                     if (chrAsc > 0 && chrAsc < 160)
    113                     {
    114                         pyString += noWChar[j];
    115                     }
    116                     else
    117                     {
    118                         // 修正部分文字
    119                         if (chrAsc == -9254)  // 修正“圳”字
    120                             pyString += "Zhen";
    121                         else
    122                         {
    123                             for (int i = (pyValue.Length - 1); i >= 0; i--)
    124                             {
    125                                 if (pyValue[i] <= chrAsc)
    126                                 {
    127                                     pyString += pyName[i];
    128                                     break;
    129                                 }
    130                             }
    131                         }
    132                     }
    133                 }
    134                 // 非中文字符
    135                 else
    136                 {
    137                     pyString += noWChar[j].ToString();
    138                 }
    139             }
    140             return pyString;
    141         }
    142 
    143         /// <summary>
    144         /// 把汉字转换成拼音(首拼)
    145         /// </summary>
    146         /// <param name="zhString">汉字字符串</param>
    147         /// <returns>转换后的拼音(首拼)字符串</returns>
    148         public static string ConvertToSP(string zhString)
    149         {
    150             char[] noWChar = zhString.ToCharArray();
    151             StringBuilder sb = new StringBuilder();
    152             for (int j = 0; j < noWChar.Length; j++)
    153             {
    154                 sb.Append(GetCharSpellCode(noWChar[j].ToString()));
    155             }
    156             return sb.ToString().ToUpper();
    157         }
    158 
    159         /// <summary>  
    160         /// 获取单个汉字的首拼音  
    161         /// </summary>  
    162         /// <param name="myChar">需要转换的字符</param>  
    163         /// <returns>转换结果</returns>  
    164         private static string GetCharSpellCode(string myChar)
    165         {
    166             byte[] arrCN = System.Text.Encoding.Default.GetBytes(myChar);
    167             if (arrCN.Length > 1)
    168             {
    169                 int area = (short)arrCN[0];
    170                 int pos = (short)arrCN[1];
    171                 int code = (area << 8) + pos;
    172                 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 };
    173                 for (int i = 0; i < 26; i++)
    174                 {
    175                     int max = 55290;
    176                     if (i != 25) max = areacode[i + 1];
    177                     if (areacode[i] <= code && code < max)
    178                     {
    179                         return System.Text.Encoding.Default.GetString(new byte[] { (byte)(65 + i) });
    180                     }
    181                 }
    182                 return "_";
    183             }
    184             else return myChar;
    185         }
    186 
    187     }
    188 }

    使用方式:

    string spname = ChineseToPinyinHelper.ConvertToSP("姓名"); //获取名字首拼
    string qpname = ChineseToPinyinHelper.ConvertToQP("姓名"); //获取名字全拼

    结果:spname是XM,qpname是XingMing。

    如果要转换字母大小写可用:ToUpper()转大写,ToLower()转小写。

    例如有个字符串string   testStr=“AbcDefg”;

    (1)转换为大写:string UpTestStr=testStr.ToUpper();

    转换后UpTestStr结果为:ABCDEFG

    (2)转换为小写:string LowTestStr=testStr.ToLower();

    转换后LowTestStr结果为:abcdefg

  • 相关阅读:
    phpstorm常用快捷键
    tp3.2.3运用phpexcel将excel文件导入mysql数据库
    TP3.2加载外部PHPexcel类,实现导入和导出
    Navicat常用快捷键
    thnkphp框架面试问题
    PHPSQL注入
    PHP4个载入语句的区别
    goflyway简单使用
    ubuntu16.04 HyperLedger Fabric 1.2.0 开发环境搭建
    DApp demo之pet-shop
  • 原文地址:https://www.cnblogs.com/kk138/p/13533602.html
Copyright © 2011-2022 走看看