C#实现汉字转拼音或转拼音首字母的方法
程序员文章站
2023-12-13 12:20:10
本文实例讲述了c#实现汉字转拼音或转拼音首字母的方法。分享给大家供大家参考。具体实现方法如下:
///
/// 汉字转拼音或转拼...
本文实例讲述了c#实现汉字转拼音或转拼音首字母的方法。分享给大家供大家参考。具体实现方法如下:
/// <summary> /// 汉字转拼音或转拼音首字母 /// </summary> public class chinesetospell { 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[] pyname = new string[] { "a","ai","an","ang","ao","ba","bai","ban","bang","bao","bei","ben", "beng","bi","bian","biao","bie","bin","bing","bo","bu","ba","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" }; /// <summary> /// 把汉字转换成拼音(全拼) /// </summary> /// <param name="hzstring">汉字字符串</param> /// <returns>转换后的拼音(全拼)字符串</returns> public static string characterconvertstring(string hzstring) { // 匹配中文字符 regex regex = new regex("^[\u4e00-\u9fa5]$"); byte[] array = new byte[2]; string pystring = ""; int chrasc = 0; int i1 = 0; int i2 = 0; char[] nowchar = hzstring.tochararray(); for (int j = 0; j < nowchar.length; j++) { // 中文字符 if (regex.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) { pystring += nowchar[j]; } else { // 修正部分文字 if (chrasc == -9254) // 修正“圳”字 { pystring += "zhen"; } else { for (int i = (pyvalue.length - 1); i >= 0; i--) { if (pyvalue[i] <= chrasc) { pystring += pyname[i]; break; } } } } } // 非中文字符 else { pystring += nowchar[j].tostring(); } } return pystring; } /// <summary> /// 只转换每个汉字首字母(大写) /// </summary> /// <param name="strtext"></param> /// <returns></returns> public static string getchinesespell(string strtext) { int len = strtext.length; string mystr = ""; for (int i = 0; i < len; i++) { mystr += getspell(strtext.substring(i, 1)); } return mystr; } /// <summary> /// 获得第一个汉字的首字母(大写); /// </summary> /// <param name="cnchar"></param> /// <returns></returns> public static string getspell(string cnchar) { byte[] arrcn = encoding.default.getbytes(cnchar); 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 encoding.default.getstring(new byte[] { (byte)(65 + i) }); } } return "*"; } else return cnchar; } }
希望本文所述对大家的c#程序设计有所帮助。