网上没有找到什么可行的汉字转拼音的代码。我所说的可行是指任意汉字都能转换正确。
前段时间需要将地名转换成为汉语拼音。网上找了一个类，并且更改了一些特定的字符，勉强可用。
以下是本人更改后的地名汉字转拼音的C#源码，如有错漏，欢迎指正：
/// <summary> /// 地名汉字转拼音类 /// </summary> public class Hz2Py { 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 Convert(string hzString) { // 匹配中文字符 Regex regex = new Regex("^[\u4e00-\u9fa5]$"); byte[] array = new byte[2]; string pyString = ""; switch (hzString) { case "重庆": return "chongqing"; case "闵行": return "minhang"; case "番禺": return "panyu"; default: break; } 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())) { switch (noWChar[j].ToString()) { #region 地名生僻字 case "郏": pyString += "Jia"; break; case "杞": pyString += "Qi"; break; case "嵩": pyString += "Song"; break; case "偃": pyString += "Yan"; break; case "栾": pyString += "Luan"; break; case "睢": pyString += "Sui"; break; case "柘": pyString += "Zhen"; break; case "陟": pyString += "Zhi"; break; case "濮": pyString += "Pu"; break; case "漯": pyString += "Ta"; break; case "颍": pyString += "Ying"; break; case "渑": pyString += "Sheng"; break; case "溧": pyString += "Li"; break; case "泗": pyString += "Si"; break; case "邗": pyString += "Han"; break; case "邳": pyString += "Pi"; break; case "盱": pyString += "Xu"; break; case "眙": pyString += "Yi"; break; case "陂": pyString += "Bei"; break; case "浠": pyString += "Xi"; break; case "蕲": pyString += "Qi"; break; case "秭": pyString += "Zi"; break; case "鄞": pyString += "Yin"; break; case "暨": pyString += "Ji"; break; case "嵊": pyString += "Sheng"; break; case "缙": pyString += "Jin"; break; case "衢": pyString += "Qu"; break; case "蚌": pyString += "Beng"; break; case "砀": pyString += "Dang"; break; case "亳": pyString += "Bo"; break; case "歙": pyString += "Xi"; break; case "濉": pyString += "Sui"; break; case "闵": pyString += "Min"; break; case "坻": pyString += "Di"; break; case "潼": pyString += "Tong"; break; case "璧": pyString += "Bi"; break; case "綦": pyString += "Qi"; break; case "讷": pyString += "Ne"; break; case "桦": pyString += "Hua"; break; case "蛟": pyString += "Jiao"; break; case "珲": pyString += "Hun"; break; case "洮": pyString += "Tao"; break; case "赉": pyString += "Lai"; break; case "岫": pyString += "Xiu"; break; case "磴": pyString += "Deng"; break; case "佘": pyString += "She"; break; case "陉": pyString += "Xing"; break; case "藁": pyString += "Gao"; break; case "涞": pyString += "Lai"; break; case "蠡": pyString += "Li"; break; case "涿": pyString += "Zhuo"; break; case "骅": pyString += "Hua"; break; case "妃": pyString += "Fei"; break; case "隰": pyString += "Xi"; break; case "猗": pyString += "Yi"; break; case "稷": pyString += "Ji"; break; case "绛": pyString += "Jiang"; break; case "岢": pyString += "Ke"; break; case "岚": pyString += "Lan"; break; case "泾": pyString += "Jing"; break; case "麟": pyString += "Lin"; break; case "岐": pyString += "Qi"; break; case "崂": pyString += "Lao"; break; case "朐": pyString += "Qu"; break; case "兖": pyString += "Yan"; break; case "汶": pyString += "Wen"; break; case "沭": pyString += "Shu"; break; case "郯": pyString += "Tan"; break; case "鄄": pyString += "Juan"; break; case "郓": pyString += "Yun"; break; case "棣": pyString += "Di"; break; case "峄": pyString += "Yi"; break; case "滕": pyString += "Teng"; break; case "莒": pyString += "Ju"; break; case "茌": pyString += "Chi"; break; case "莘": pyString += "Shen"; break; case "坂": pyString += "Ban"; break; case "鄯": pyString += "Shan"; break; case "耆": pyString += "Qi"; break; case "伽": pyString += "Qie"; break; case "尕": pyString += "Ga"; break; case "湟": pyString += "Huang"; break; case "晏": pyString += "Yan"; break; case "岷": pyString += "Min"; break; case "崆": pyString += "Kong"; break; case "峒": pyString += "Tong"; break; case "宕": pyString += "Dang"; break; case "荥": pyString += "Xing"; break; case "鄢": pyString += "Yan"; break; case "碚": pyString += "Bei"; break; case "芮": pyString += "Rui"; break; case "潢": pyString += "Huang"; break; case "淅": pyString += "Xi"; break; case "淇": pyString += "Qi"; break; case "岱": pyString += "Dai"; break; case "枞": pyString += "Zong"; break; case "黟": pyString += "Yi"; break; case "旌": pyString += "Jing"; break; case "诏": pyString += "Zhao"; break; case "瓯": pyString += "Ou"; break; case "鄱": pyString += "Po"; break; case "婺": pyString += "Wu"; break; case "弋": pyString += "Yi"; break; case "浏": pyString += "Liu"; break; case "攸": pyString += "You"; break; case "醴": pyString += "Ling"; break; case "耒": pyString += "Lei"; break; case "澧": pyString += "Li"; break; case "沅": pyString += "Yuan"; break; case "汨": pyString += "Mi"; break; case "芷": pyString += "Zhi"; break; case "溆": pyString += "Xu"; break; case "泸": pyString += "Lu"; break; case "湄": pyString += "Mei"; break; case "梓": pyString += "Zi"; break; case "岑": pyString += "Cen"; break; case "榕": pyString += "Rong"; break; case "阡": pyString += "Qian"; break; case "谟": pyString += "Mo"; break; case "驿": pyString += "Yi"; break; case "郫": pyString += "Pi"; break; case "邛": pyString += "Qiong"; break; case "崃": pyString += "Lai"; break; case "阆": pyString += "lang"; break; case "蓥": pyString += "Ying"; break; case "蔺": pyString += "Lin"; break; case "珙": pyString += "Gong"; break; case "筠": pyString += "Jun"; break; case "犍": pyString += "Qian"; break; case "沐": pyString += "Mu"; break; case "孚": pyString += "Fu"; break; case "邡": pyString += "Fang"; break; case "禺": pyString += "Yu"; break; case "硇": pyString += "Nao"; break; case "莞": pyString += "Guan"; break; case "蒗": pyString += "Lang"; break; case "畹": pyString += "Wan"; break; case "町": pyString += "Ding"; break; case "勐": pyString += "Meng"; break; case "邕": pyString += "Yong"; break; case "儋": pyString += "Dan"; break; case "涠": pyString += "Wei"; break; #endregion default: 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; } } } } break; } } // 非中文字符 else { pyString += noWChar[j].ToString(); } } return pyString.ToLower(); } }