[转]在C#中将汉字转换成拼音

最新推荐文章于 2022-07-19 09:27:47 发布

转载最新推荐文章于 2022-07-19 09:27:47 发布 · 453 阅读

0 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/chaosimple/archive/2012/11/02/2751101.html

本文详细介绍了如何使用 C# 实现汉字转拼音的功能，包括编码解析、字典匹配等关键步骤，以及如何在实际场景中应用此功能。

   1:  public static class ChineseToPinYin

   2:          {

   3:              private static readonly Dictionary<int, string> CodeCollections = new Dictionary<int, string> {

   4:   { -20319, "a" }, { -20317, "ai" }, { -20304, "an" }, { -20295, "ang" }, { -20292, "ao" }, { -20283, "ba" }, { -20265, "bai" },

   5:  { -20257, "ban" }, { -20242, "bang" }, { -20230, "bao" }, { -20051, "bei" }, { -20036, "ben" }, { -20032, "beng" }, { -20026, "bi" }

   6:  , { -20002, "bian" }, { -19990, "biao" }, { -19986, "bie" }, { -19982, "bin" }, { -19976, "bing" }, { -19805, "bo" },

   7:  { -19784, "bu" }, { -19775, "ca" }, { -19774, "cai" }, { -19763, "can" }, { -19756, "cang" }, { -19751, "cao" }, { -19746, "ce" },

   8:   { -19741, "ceng" }, { -19739, "cha" }, { -19728, "chai" }, { -19725, "chan" }, { -19715, "chang" }, { -19540, "chao" },

   9:  { -19531, "che" }, { -19525, "chen" }, { -19515, "cheng" }, { -19500, "chi" }, { -19484, "chong" }, { -19479, "chou" },

  10:  { -19467, "chu" }, { -19289, "chuai" }, { -19288, "chuan" }, { -19281, "chuang" }, { -19275, "chui" }, { -19270, "chun" },

  11:   { -19263, "chuo" }, { -19261, "ci" }, { -19249, "cong" }, { -19243, "cou" }, { -19242, "cu" }, { -19238, "cuan" },

  12:  { -19235, "cui" }, { -19227, "cun" }, { -19224, "cuo" }, { -19218, "da" }, { -19212, "dai" }, { -19038, "dan" }, { -19023, "dang" },

  13:   { -19018, "dao" }, { -19006, "de" }, { -19003, "deng" }, { -18996, "di" }, { -18977, "dian" }, { -18961, "diao" }, { -18952, "die" }

  14:  , { -18783, "ding" }, { -18774, "diu" }, { -18773, "dong" }, { -18763, "dou" }, { -18756, "du" }, { -18741, "duan" },

  15:  { -18735, "dui" }, { -18731, "dun" }, { -18722, "duo" }, { -18710, "e" }, { -18697, "en" }, { -18696, "er" }, { -18526, "fa" },

  16:   { -18518, "fan" }, { -18501, "fang" }, { -18490, "fei" }, { -18478, "fen" }, { -18463, "feng" }, { -18448, "fo" }, { -18447, "fou" }

  17:  , { -18446, "fu" }, { -18239, "ga" }, { -18237, "gai" }, { -18231, "gan" }, { -18220, "gang" }, { -18211, "gao" }, { -18201, "ge" },

  18:   { -18184, "gei" }, { -18183, "gen" }, { -18181, "geng" }, { -18012, "gong" }, { -17997, "gou" }, { -17988, "gu" }, { -17970, "gua" }

  19:  , { -17964, "guai" }, { -17961, "guan" }, { -17950, "guang" }, { -17947, "gui" }, { -17931, "gun" }, { -17928, "guo" },

  20:  { -17922, "ha" }, { -17759, "hai" }, { -17752, "han" }, { -17733, "hang" }, { -17730, "hao" }, { -17721, "he" }, { -17703, "hei" },

  21:   { -17701, "hen" }, { -17697, "heng" }, { -17692, "hong" }, { -17683, "hou" }, { -17676, "hu" }, { -17496, "hua" },

  22:  { -17487, "huai" }, { -17482, "huan" }, { -17468, "huang" }, { -17454, "hui" }, { -17433, "hun" }, { -17427, "huo" },

  23:  { -17417, "ji" }, { -17202, "jia" }, { -17185, "jian" }, { -16983, "jiang" }, { -16970, "jiao" }, { -16942, "jie" },

  24:  { -16915, "jin" }, { -16733, "jing" }, { -16708, "jiong" }, { -16706, "jiu" }, { -16689, "ju" }, { -16664, "juan" },

  25:  { -16657, "jue" }, { -16647, "jun" }, { -16474, "ka" }, { -16470, "kai" }, { -16465, "kan" }, { -16459, "kang" }, { -16452, "kao" },

  26:   { -16448, "ke" }, { -16433, "ken" }, { -16429, "keng" }, { -16427, "kong" }, { -16423, "kou" }, { -16419, "ku" }, { -16412, "kua" }

  27:  , { -16407, "kuai" }, { -16403, "kuan" }, { -16401, "kuang" }, { -16393, "kui" }, { -16220, "kun" }, { -16216, "kuo" },

  28:  { -16212, "la" }, { -16205, "lai" }, { -16202, "lan" }, { -16187, "lang" }, { -16180, "lao" }, { -16171, "le" }, { -16169, "lei" },

  29:  { -16158, "leng" }, { -16155, "li" }, { -15959, "lia" }, { -15958, "lian" }, { -15944, "liang" }, { -15933, "liao" },

  30:  { -15920, "lie" }, { -15915, "lin" }, { -15903, "ling" }, { -15889, "liu" }, { -15878, "long" }, { -15707, "lou" }, { -15701, "lu" },

  31:   { -15681, "lv" }, { -15667, "luan" }, { -15661, "lue" }, { -15659, "lun" }, { -15652, "luo" }, { -15640, "ma" }, { -15631, "mai" },

  32:   { -15625, "man" }, { -15454, "mang" }, { -15448, "mao" }, { -15436, "me" }, { -15435, "mei" }, { -15419, "men" },

  33:  { -15416, "meng" }, { -15408, "mi" }, { -15394, "mian" }, { -15385, "miao" }, { -15377, "mie" }, { -15375, "min" },

  34:  { -15369, "ming" }, { -15363, "miu" }, { -15362, "mo" }, { -15183, "mou" }, { -15180, "mu" }, { -15165, "na" }, { -15158, "nai" },

  35:  { -15153, "nan" }, { -15150, "nang" }, { -15149, "nao" }, { -15144, "ne" }, { -15143, "nei" }, { -15141, "nen" }, { -15140, "neng" }

  36:  , { -15139, "ni" }, { -15128, "nian" }, { -15121, "niang" }, { -15119, "niao" }, { -15117, "nie" }, { -15110, "nin" },

  37:  { -15109, "ning" }, { -14941, "niu" }, { -14937, "nong" }, { -14933, "nu" }, { -14930, "nv" }, { -14929, "nuan" }, { -14928, "nue" }

  38:  , { -14926, "nuo" }, { -14922, "o" }, { -14921, "ou" }, { -14914, "pa" }, { -14908, "pai" }, { -14902, "pan" }, { -14894, "pang" },

  39:   { -14889, "pao" }, { -14882, "pei" }, { -14873, "pen" }, { -14871, "peng" }, { -14857, "pi" }, { -14678, "pian" },

  40:  { -14674, "piao" }, { -14670, "pie" }, { -14668, "pin" }, { -14663, "ping" }, { -14654, "po" }, { -14645, "pu" }, { -14630, "qi" },

  41:   { -14594, "qia" }, { -14429, "qian" }, { -14407, "qiang" }, { -14399, "qiao" }, { -14384, "qie" }, { -14379, "qin" },

  42:   { -14368, "qing" }, { -14355, "qiong" }, { -14353, "qiu" }, { -14345, "qu" }, { -14170, "quan" }, { -14159, "que" },

  43:  { -14151, "qun" }, { -14149, "ran" }, { -14145, "rang" }, { -14140, "rao" }, { -14137, "re" }, { -14135, "ren" }, { -14125, "reng" }

  44:  , { -14123, "ri" }, { -14122, "rong" }, { -14112, "rou" }, { -14109, "ru" }, { -14099, "ruan" }, { -14097, "rui" }, { -14094, "run" }

  45:  , { -14092, "ruo" }, { -14090, "sa" }, { -14087, "sai" }, { -14083, "san" }, { -13917, "sang" }, { -13914, "sao" }, { -13910, "se" }

  46:  , { -13907, "sen" }, { -13906, "seng" }, { -13905, "sha" }, { -13896, "shai" }, { -13894, "shan" }, { -13878, "shang" },

  47:  { -13870, "shao" }, { -13859, "she" }, { -13847, "shen" }, { -13831, "sheng" }, { -13658, "shi" }, { -13611, "shou" },

  48:   { -13601, "shu" }, { -13406, "shua" }, { -13404, "shuai" }, { -13400, "shuan" }, { -13398, "shuang" }, { -13395, "shui" },

  49:   { -13391, "shun" }, { -13387, "shuo" }, { -13383, "si" }, { -13367, "song" }, { -13359, "sou" }, { -13356, "su" },

  50:  { -13343, "suan" }, { -13340, "sui" }, { -13329, "sun" }, { -13326, "suo" }, { -13318, "ta" }, { -13147, "tai" }, { -13138, "tan" },

  51:   { -13120, "tang" }, { -13107, "tao" }, { -13096, "te" }, { -13095, "teng" }, { -13091, "ti" }, { -13076, "tian" },

  52:  { -13068, "tiao" }, { -13063, "tie" }, { -13060, "ting" }, { -12888, "tong" }, { -12875, "tou" }, { -12871, "tu" },

  53:  { -12860, "tuan" }, { -12858, "tui" }, { -12852, "tun" }, { -12849, "tuo" }, { -12838, "wa" }, { -12831, "wai" }, { -12829, "wan" }

  54:  , { -12812, "wang" }, { -12802, "wei" }, { -12607, "wen" }, { -12597, "weng" }, { -12594, "wo" }, { -12585, "wu" }, { -12556, "xi" }

  55:  , { -12359, "xia" }, { -12346, "xian" }, { -12320, "xiang" }, { -12300, "xiao" }, { -12120, "xie" }, { -12099, "xin" },

  56:  { -12089, "xing" }, { -12074, "xiong" }, { -12067, "xiu" }, { -12058, "xu" }, { -12039, "xuan" }, { -11867, "xue" },

  57:  { -11861, "xun" }, { -11847, "ya" }, { -11831, "yan" }, { -11798, "yang" }, { -11781, "yao" }, { -11604, "ye" }, { -11589, "yi" },

  58:   { -11536, "yin" }, { -11358, "ying" }, { -11340, "yo" }, { -11339, "yong" }, { -11324, "you" }, { -11303, "yu" },

  59:  { -11097, "yuan" }, { -11077, "yue" }, { -11067, "yun" }, { -11055, "za" }, { -11052, "zai" }, { -11045, "zan" },

  60:   { -11041, "zang" }, { -11038, "zao" }, { -11024, "ze" }, { -11020, "zei" }, { -11019, "zen" }, { -11018, "zeng" },

  61:  { -11014, "zha" }, { -10838, "zhai" }, { -10832, "zhan" }, { -10815, "zhang" }, { -10800, "zhao" }, { -10790, "zhe" },

  62:  { -10780, "zhen" }, { -10764, "zheng" }, { -10587, "zhi" }, { -10544, "zhong" }, { -10533, "zhou" }, { -10519, "zhu" },

  63:  { -10331, "zhua" }, { -10329, "zhuai" }, { -10328, "zhuan" }, { -10322, "zhuang" }, { -10315, "zhui" }, { -10309, "zhun" },

  64:  { -10307, "zhuo" }, { -10296, "zi" }, { -10281, "zong" }, { -10274, "zou" }, { -10270, "zu" }, { -10262, "zuan" }, { -10260, "zui" }

  65:  , { -10256, "zun" }, { -10254, "zuo" } };

  66:              ///   <summary>

  67:              ///   汉字转拼音

  68:              ///   </summary>

  69:              ///   <param   name="txt"> 需要转换的汉字 </param>

  70:              ///   <returns> 返回汉字对应的拼音 </returns>

  71:              public static string ToPinYin(string txt)

  72:              {

  73:                  txt = txt.Trim();

  74:                  byte[] arr = new byte[2];   //每个汉字为2字节

  75:                  StringBuilder result = new StringBuilder();//使用StringBuilder优化字符串连接

  76:                  int charCode = 0;

  77:                  int arr1 = 0;

  78:                  int arr2 = 0;

  79:                  char[] arrChar = txt.ToCharArray();

  80:                  for (int j = 0; j < arrChar.Length; j++)   //遍历输入的字符

  81:                  {

  82:                      arr = System.Text.Encoding.Default.GetBytes(arrChar[j].ToString());//根据系统默认编码得到字节码

  83:                      if (arr.Length == 1)//如果只有1字节说明该字符不是汉字，结束本次循环

  84:                      {

  85:                          result.Append(arrChar[j].ToString());

  86:                          continue;

87:

  88:                      }

  89:                      arr1 = (short)(arr[0]);   //取字节1

  90:                      arr2 = (short)(arr[1]);   //取字节2

  91:                      charCode = arr1 * 256 + arr2 - 65536;//计算汉字的编码

92:

  93:                       if (charCode > -10254 || charCode < -20319)  //如果不在汉字编码范围内则不改变

  94:                      {

  95:                          result.Append(arrChar[j]);

  96:                      }

  97:                      else

  98:                      {

  99:                          //根据汉字编码范围查找对应的拼音并保存到结果中

 100:                          //由于charCode的键不一定存在，所以要找比他更小的键上一个键

 101:                          if (!CodeCollections.ContainsKey(charCode))

 102:                          {

 103:                              for (int i = charCode; i <= 0; --i)

 104:                              {

 105:                                  if (CodeCollections.ContainsKey(i))

 106:                                  {

 107:                                      result.Append(" " + CodeCollections[i] + " ");

 108:                                      break;

 109:                                  }

 110:                              }

 111:                          }

 112:                          else

 113:                          {

 114:                              result.Append(" " + CodeCollections[charCode] + " ");

 115:                          }

 116:                      }

 117:                  }

 118:                  return result.ToString();

 119:              }

 120:          }

原文地址：

http://www.cnblogs.com/lilin123/archive/2012/11/01/2749169.html

转载于:https://www.cnblogs.com/chaosimple/archive/2012/11/02/2751101.html