Use C # to realize Chinese characters to pinyin

xiaoxiao2021-03-31 207

Using

System;

Using

System.collections.Generic;

Using

System.Text;

Using

System.Text.RegularExpress;

Namespace

Splitword

...

{/ ** //// Use C # to transform the Chinese characters to pinyin /// The principle of implementation is to convert Chinese characters into internal code, and then look up through the internal code and pinyin.

Public class chs2py ... {/ ** // ** / / ** // ** / ////// ** / / ** ////

/// Transfer Chinese characters into pinyin / // author: /// completed by: /// static regex myRegex = new regex ( "^ [a - 龥] $"); // regular expression characters .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, -189996, -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, -1 7752, -17733, -17730, -17721, -177703, -17701, -17697, -17692, -17683, -17676, -17496, -17487, -17482, -17468, -17454, -17433, -17427, -17417, -17202, -17185, -16983, -16970, -16942, -16915, -16733, -16708, -16706, -16689, -16664, -1647, -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, -15144, -15143, -15141, -15140, -15139, -15128, -15121, -15119, -15117, -15110, -15109, -14941, -14937, - 14933, -14930, -14929, -14922, -14926, -14922, -14921, -14914, -14908, -14902, -14894, -14889, -148882, -14873, -14871, -14857, -14678, -14674, -14670, -14668, -14663, -14654, -14645, -14630, -14594, -14429, -14407, -14399, -14384, -14379, -14368, -14355, -14353, -14345 -14170, -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 -13604, -13400, -13398, -13395, -13391, -13387, -13383, -13367, -133359, -13356, -13343, -13340, -13329, -13326, -133326, 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, -1108, -10832, -10815, -10800, -10790, -10780, -10764, -10587, -10544, -10533, -10519, -10331, -10329 , -10328, -10309, -10307, -10296, -10281, -10274, -10270, -10262, -10260, -10256, -10254}; private stric string [] pystr = new string [] {"A", "AI", "AN", "ANG", "Ao", "BA", "Bai", "Ban", "Bang", "Bao", "BEI", "Ben", "Beng", "Bi", "Bian", "BIAO", "Bie", "BIN", "Bo", "BU", "CA", "CAI", "CAN "" CANG "," CAO "," CE "," CENG "," CHA "," 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 "," DAO "," DE "," DENG ", "DI", "Dian", "DIAO", "DIE", "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", "GU", "Gua", "Guai "," Guan "," Guang "," GUI "," GUN "," Guo "," HAN "," HAI "," HAN "," Hao "," HE "," HEI ", "Hen", "HENG", "HONG", "Hou", "Hu", "Hua", "Huai", "HUAN", "Hui", "Hun", "Huo", "Ji" "JIA", "Jian", "JIANG", "JIAO", "Jie", "JING", "Jiong", "JIU", "JU", "Juan", "Jue", "Jun", "KA", "Kai", "KAN", "Kang", "Kao", "KE", "KEN", "KENG", "KOON", "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", "NAO", "NAO", "NE "," Nei "," Nen "," NENG "," Ni "," Nian "," NIANG "," NIAO "," NIE "," NIN "," NIAO "," NIU "," Nong ", "Nu", "NV", "NUAN", "NUE", "Nu", "O", "Ou", "PA", "PAI", "PAN", "PAO", "PEI "" Pen "," Peng "," Pi "," Pian "," PIAO "," PIE "," PIN "," Ping "," Po "," PU "," Qi "," QIA ", "Qian", "Qiang", "QIAO", "QIE", "QING", "Qiong", "Qiu", "QUAN", "QUE", "Qun", "RAN" "," Rang "," Rao "," RE "," REN "," Ro "," Rou "," Ru "," Ruan "," RUI "," Run ", "Ruo", "SA", "SAI", "SAN", "SANG", "SAO", "SE", "SEN", "SENG", "SHA", "SHAN", "Shang "," SHAO "," SHE "," SHENG "," Shi "," Shou "," SHUAN "," Shuang "," Shui ", "SHUN", "SHUO", "Si", "Song", "Sou", "SU",

"suan", "sui", "su", "su", "ta", "tai", "tan", "tao", "te", "ten", "ti", "tian" "," TIAO "," Tie "," Tong "," Tou "," TU "," TUAN "," TUI "," Tun "," Tuo "," WA "," WAI ", "Wan", "WANG", "WEI", "Wen", "WENG", "Wo", "WU", "Xi", "XIA", "XIAN", "XIAO", "XIE "," xin "," xing "," xiong "," xiu "," xu "," xuan "," xun "," ya "," yan "," yang "," yao ", "Ye", "yi", "yin", "ying", "yo", "yon", "yu", "yuan", "yun", "za", "zai "," ZAN "," Zang "," ZAO "," Ze "," Zei "," ZENG "," ZHA "," ZHAI "," ZHAN "," ZHAO ", "ZHE", "Zhen", "zheng", "zhu", "zhua", "zhuai", "zhua", "zhuang", "zhu" "," zhuo "," zi "," zong "," zou "," zu "," zuan "," zui "," zun ",

"Zuo"}; / ** ////

/// Transform Chinese characters //// /// /// public static string control (string chrstr) ... {regex myregex = new regex ("^ [1 - 龥] $"); Byte [] array = new byte [2]; string returnstr = "" ; Int CHRASC = 0; INT I1 = 0; INT I2 = 0; char [] nowchar = chrstr.tochararray (); for (int J = 0; j 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 ();}} returnstr;}} Return Returnstr;

转载请注明原文地址:https://www.9cbs.com/read-130876.html

9cbs

New Post(0)