中文汉字转换成拼音首字拼音全拼

最新推荐文章于 2022-04-22 10:44:41 发布

原创最新推荐文章于 2022-04-22 10:44:41 发布 · 8.7k 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#string #byte #encoding #dao #bing #sun

C# 专栏收录该内容

47 篇文章

订阅专栏

本文介绍了一个C#类，用于获取汉字的拼音及其首字母。通过编码转换和对照表，该类能准确地实现汉字到拼音的转换，并进一步提取拼音的首字母。

1./// <summary> 2. /// 获取汉字的首字母和全拼 3. /// </summary> 4. public class ChineseCode 5. { 6. protected string _CnTxt; 7. protected string _EnTxt; 8. 9. /// <summary> 10. /// 要获取字母的汉字 11. /// </summary> 12. public string CnTxt 13. { 14. get { return _CnTxt; } 15. set { _CnTxt = value; } 16. } 17. /// <summary> 18. /// 汉字的首字母 19. /// </summary> 20. public string EnTxt 21. { 22. get { return _EnTxt; } 23. set { _EnTxt = value; } 24. } 25. /// <summary> 26. /// 构造方法 27. /// </summary> 28. public ChineseCode() 29. { 30. 31. } 32. /// <summary> 33. /// 构造方法，获取汉字首字母拼音 34. /// </summary> 35. /// <param name="txt"></param> 36. public ChineseCode(string txt) 37. { 38. _CnTxt = txt; 39. _EnTxt = IndexCode(_CnTxt); 40. } 41. /// <summary> 42. /// 获取汉字的首字母 43. /// </summary> 44. /// <param name="IndexTxt">汉字</param> 45. /// <returns>汉字的首字母</returns> 46. public String IndexCode(String IndexTxt) 47. { 48. String _Temp = null; 49. for (int i = 0; i < IndexTxt.Length; i++) 50. _Temp = _Temp + GetOneIndex(IndexTxt.Substring(i, 1)); 51. return _Temp; 52. } 53. 54. /// <summary> 55. /// 单个汉字 56. /// </summary> 57. /// <param name="OneIndexTxt">汉字</param> 58. /// <returns>首拼</returns> 59. private String GetOneIndex(String OneIndexTxt) 60. { 61. if (Convert.ToChar(OneIndexTxt) >= 0 && Convert.ToChar(OneIndexTxt) < 256) 62. return OneIndexTxt; 63. else 64. { 65. Encoding gb2312 = Encoding.GetEncoding("gb2312"); 66. byte[] unicodeBytes = Encoding.Unicode.GetBytes(OneIndexTxt); 67. byte[] gb2312Bytes = Encoding.Convert(Encoding.Unicode, gb2312, unicodeBytes); 68. return GetX(Convert.ToInt32( 69. String.Format("{0:D2}", Convert.ToInt16(gb2312Bytes[0]) - 160) 70. + String.Format("{0:D2}", Convert.ToInt16(gb2312Bytes[1]) - 160) 71. )); 72. } 73. } 74. /// <summary> 75. /// 根据区位得到首字母 76. /// </summary> 77. /// <param name="GBCode">区位</param> 78. /// <returns></returns> 79. private String GetX(int GBCode) 80. { 81. if (GBCode >= 1601 && GBCode < 1637) return "a"; 82. if (GBCode >= 1637 && GBCode < 1833) return "b"; 83. if (GBCode >= 1833 && GBCode < 2078) return "c"; 84. if (GBCode >= 2078 && GBCode < 2274) return "d"; 85. if (GBCode >= 2274 && GBCode < 2302) return "e"; 86. if (GBCode >= 2302 && GBCode < 2433) return "f"; 87. if (GBCode >= 2433 && GBCode < 2594) return "g"; 88. if (GBCode >= 2594 && GBCode < 2787) return "h"; 89. if (GBCode >= 2787 && GBCode < 3106) return "j"; 90. if (GBCode >= 3106 && GBCode < 3212) return "k"; 91. if (GBCode >= 3212 && GBCode < 3472) return "l"; 92. if (GBCode >= 3472 && GBCode < 3635) return "m"; 93. if (GBCode >= 3635 && GBCode < 3722) return "n"; 94. if (GBCode >= 3722 && GBCode < 3730) return "o"; 95. if (GBCode >= 3730 && GBCode < 3858) return "p"; 96. if (GBCode >= 3858 && GBCode < 4027) return "q"; 97. if (GBCode >= 4027 && GBCode < 4086) return "r"; 98. if (GBCode >= 4086 && GBCode < 4390) return "s"; 99. if (GBCode >= 4390 && GBCode < 4558) return "t"; 100. if (GBCode >= 4558 && GBCode < 4684) return "w"; 101. if (GBCode >= 4684 && GBCode < 4925) return "x"; 102. if (GBCode >= 4925 && GBCode < 5249) return "y"; 103. if (GBCode >= 5249 && GBCode <= 5589) return "z"; 104. if (GBCode >= 5601 && GBCode <= 8794) 105. { 106. String CodeData = "cjwgnspgcenegypbtwxzdxykygtpjnmjqmbsgzscyjsyyfpggbzgydywjkgaljswkbjqhyjwpdzlsgmr" 107. + "ybywwccgznkydgttngjeyekzydcjnmcylqlypyqbqrpzslwbdgkjfyxjwcltbncxjjjjcxdtqsqzycdxxhgckbphffss" 108. + "pybgmxjbbyglbhlssmzmpjhsojnghdzcdklgjhsgqzhxqgkezzwymcscjnyetxadzpmdssmzjjqjyzcjjfwqjbdzbjgd" 109. + "nzcbwhgxhqkmwfbpbqdtjjzkqhylcgxfptyjyyzpsjlfchmqshgmmxsxjpkdcmbbqbefsjwhwwgckpylqbgldlcctnma" 110. + "eddksjngkcsgxlhzaybdbtsdkdylhgymylcxpycjndqjwxqxfyyfjlejbzrwccqhqcsbzkymgplbmcrqcflnymyqmsqt" 111. + "rbcjthztqfrxchxmcjcjlxqgjmshzkbswxemdlckfsydsglycjjssjnqbjctyhbftdcyjdgwyghqfrxwckqkxebpdjpx" 112. + "jqsrmebwgjlbjslyysmdxlclqkxlhtjrjjmbjhxhwywcbhtrxxglhjhfbmgykldyxzpplggpmtcbbajjzyljtyanjgbj" 113. + "flqgdzyqcaxbkclecjsznslyzhlxlzcghbxzhznytdsbcjkdlzayffydlabbgqszkggldndnyskjshdlxxbcghxyggdj" 114. + "mmzngmmccgwzszxsjbznmlzdthcqydbdllscddnlkjyhjsycjlkohqasdhnhcsgaehdaashtcplcpqybsdmpjlpcjaql" 115. + "cdhjjasprchngjnlhlyyqyhwzpnccgwwmzffjqqqqxxaclbhkdjxdgmmydjxzllsygxgkjrywzwyclzmcsjzldbndcfc" 116. + "xyhlschycjqppqagmnyxpfrkssbjlyxyjjglnscmhcwwmnzjjlhmhchsyppttxrycsxbyhcsmxjsxnbwgpxxtaybgajc" 117. + "xlypdccwqocwkccsbnhcpdyznbcyytyckskybsqkkytqqxfcwchcwkelcqbsqyjqcclmthsywhmktlkjlychwheqjhtj" 118. + "hppqpqscfymmcmgbmhglgsllysdllljpchmjhwljcyhzjxhdxjlhxrswlwzjcbxmhzqxsdzpmgfcsglsdymjshxpjxom" 119. + "yqknmyblrthbcftpmgyxlchlhlzylxgsssscclsldclepbhshxyyfhbmgdfycnjqwlqhjjcywjztejjdhfblqxtqkwhd" 120. + "chqxagtlxljxmsljhdzkzjecxjcjnmbbjcsfywkbjzghysdcpqyrsljpclpwxsdwejbjcbcnaytmgmbapclyqbclzxcb" 121. + "nmsggfnzjjbzsfqyndxhpcqkzczwalsbccjxpozgwkybsgxfcfcdkhjbstlqfsgdslqwzkxtmhsbgzhjcrglyjbpmljs" 122. + "xlcjqqhzmjczydjwbmjklddpmjegxyhylxhlqyqhkycwcjmyhxnatjhyccxzpcqlbzwwwtwbqcmlbmynjcccxbbsnzzl" 123. + "jpljxyztzlgcldcklyrzzgqtgjhhgjljaxfgfjzslcfdqzlclgjdjcsnclljpjqdcclcjxmyzftsxgcgsbrzxjqqcczh" 124. + "gyjdjqqlzxjyldlbcyamcstylbdjbyregklzdzhldszchznwczcllwjqjjjkdgjcolbbzppglghtgzcygezmycnqcycy" 125. + "hbhgxkamtxyxnbskyzzgjzlqjdfcjxdygjqjjpmgwgjjjpkjsbgbmmcjssclpqpdxcdyykypcjddyygywchjrtgcnyql" 126. + "dkljczzgzccjgdyksgpzmdlcphnjafyzdjcnmwescsglbtzcgmsdllyxqsxsbljsbbsgghfjlwpmzjnlyywdqshzxtyy" 127. + "whmcyhywdbxbtlmswyyfsbjcbdxxlhjhfpsxzqhfzmqcztqcxzxrdkdjhnnyzqqfnqdmmgnydxmjgdhcdycbffallztd" 128. + "ltfkmxqzdngeqdbdczjdxbzgsqqddjcmbkxffxmkdmcsychzcmljdjynhprsjmkmpcklgdbqtfzswtfgglyplljzhgjj" 129. + "gypzltcsmcnbtjbhfkdhbyzgkpbbymtdlsxsbnpdkleycjnycdykzddhqgsdzsctarlltkzlgecllkjljjaqnbdggghf" 130. + "jtzqjsecshalqfmmgjnlyjbbtmlycxdcjpldlpcqdhsycbzsckbzmsljflhrbjsnbrgjhxpdgdjybzgdlgcsezgxlblg" 131. + "yxtwmabchecmwyjyzlljjshlgndjlslygkdzpzxjyyzlpcxszfgwyydlyhcljscmbjhblyjlycblydpdqysxktbytdkd" 132. + "xjypcnrjmfdjgklccjbctbjddbblblcdqrppxjcglzcshltoljnmdddlngkaqakgjgyhheznmshrphqqjchgmfprxcjg" 133. + "dychghlyrzqlcngjnzsqdkqjymszswlcfqjqxgbggxmdjwlmcrnfkkfsyyljbmqammmycctbshcptxxzzsmphfshmclm" 134. + "ldjfyqxsdyjdjjzzhqpdszglssjbckbxyqzjsgpsxjzqznqtbdkwxjkhhgflbcsmdldgdzdblzkycqnncsybzbfglzzx" 135. + "swmsccmqnjqsbdqsjtxxmbldxcclzshzcxrqjgjylxzfjphymzqqydfqjjlcznzjcdgzygcdxmzysctlkphtxhtlbjxj" 136. + "lxscdqccbbqjfqzfsltjbtkqbsxjjljchczdbzjdczjccprnlqcgpfczlclcxzdmxmphgsgzgszzqjxlwtjpfsyaslcj" 137. + "btckwcwmytcsjjljcqlwzmalbxyfbpnlschtgjwejjxxglljstgshjqlzfkcgnndszfdeqfhbsaqdgylbxmmygszldyd" 138. + "jmjjrgbjgkgdhgkblgkbdmbylxwcxyttybkmrjjzxqjbhlmhmjjzmqasldcyxyqdlqcafywyxqhz"; 139. 140. String _gbcode = GBCode.ToString(); 141. int pos = (Convert.ToInt16(_gbcode.Substring(0, 2)) - 56) * 94 + Convert.ToInt16(_gbcode.Substring(_gbcode.Length - 2, 2)); 142. return CodeData.Substring(pos - 1, 1); 143. } 144. return " "; 145. } 146. //获取汉字的首字母和全拼 147. 148. /// <summary> 149. /// 获取汉字的全拼音 150. /// </summary> 151. /// <param name="x">传汉字的字符串</param> 152. /// <returns>汉字的字符串的拼音</returns> 153. public string GetSpell(string x) 154. { 155. int[] iA = new int[] 156. { 157. -20319 ,-20317 ,-20304 ,-20295 ,-20292 ,-20283 ,-20265 ,-20257 ,-20242 ,-20230 158. ,-20051 ,-20036 ,-20032 ,-20026 ,-20002 ,-19990 ,-19986 ,-19982 ,-19976 ,-19805 159. ,-19784 ,-19775 ,-19774 ,-19763 ,-19756 ,-19751 ,-19746 ,-19741 ,-19739 ,-19728 160. ,-19725 ,-19715 ,-19540 ,-19531 ,-19525 ,-19515 ,-19500 ,-19484 ,-19479 ,-19467 161. ,-19289 ,-19288 ,-19281 ,-19275 ,-19270 ,-19263 ,-19261 ,-19249 ,-19243 ,-19242 162. ,-19238 ,-19235 ,-19227 ,-19224 ,-19218 ,-19212 ,-19038 ,-19023 ,-19018 ,-19006 163. ,-19003 ,-18996 ,-18977 ,-18961 ,-18952 ,-18783 ,-18774 ,-18773 ,-18763 ,-18756 164. ,-18741 ,-18735 ,-18731 ,-18722 ,-18710 ,-18697 ,-18696 ,-18526 ,-18518 ,-18501 165. ,-18490 ,-18478 ,-18463 ,-18448 ,-18447 ,-18446 ,-18239 ,-18237 ,-18231 ,-18220 166. ,-18211 ,-18201 ,-18184 ,-18183 ,-18181 ,-18012 ,-17997 ,-17988 ,-17970 ,-17964 167. ,-17961 ,-17950 ,-17947 ,-17931 ,-17928 ,-17922 ,-17759 ,-17752 ,-17733 ,-17730 168. ,-17721 ,-17703 ,-17701 ,-17697 ,-17692 ,-17683 ,-17676 ,-17496 ,-17487 ,-17482 169. ,-17468 ,-17454 ,-17433 ,-17427 ,-17417 ,-17202 ,-17185 ,-16983 ,-16970 ,-16942 170. ,-16915 ,-16733 ,-16708 ,-16706 ,-16689 ,-16664 ,-16657 ,-16647 ,-16474 ,-16470 171. ,-16465 ,-16459 ,-16452 ,-16448 ,-16433 ,-16429 ,-16427 ,-16423 ,-16419 ,-16412 172. ,-16407 ,-16403 ,-16401 ,-16393 ,-16220 ,-16216 ,-16212 ,-16205 ,-16202 ,-16187 173. ,-16180 ,-16171 ,-16169 ,-16158 ,-16155 ,-15959 ,-15958 ,-15944 ,-15933 ,-15920 174. ,-15915 ,-15903 ,-15889 ,-15878 ,-15707 ,-15701 ,-15681 ,-15667 ,-15661 ,-15659 175. ,-15652 ,-15640 ,-15631 ,-15625 ,-15454 ,-15448 ,-15436 ,-15435 ,-15419 ,-15416 176. ,-15408 ,-15394 ,-15385 ,-15377 ,-15375 ,-15369 ,-15363 ,-15362 ,-15183 ,-15180 177. ,-15165 ,-15158 ,-15153 ,-15150 ,-15149 ,-15144 ,-15143 ,-15141 ,-15140 ,-15139 178. ,-15128 ,-15121 ,-15119 ,-15117 ,-15110 ,-15109 ,-14941 ,-14937 ,-14933 ,-14930 179. ,-14929 ,-14928 ,-14926 ,-14922 ,-14921 ,-14914 ,-14908 ,-14902 ,-14894 ,-14889 180. ,-14882 ,-14873 ,-14871 ,-14857 ,-14678 ,-14674 ,-14670 ,-14668 ,-14663 ,-14654 181. ,-14645 ,-14630 ,-14594 ,-14429 ,-14407 ,-14399 ,-14384 ,-14379 ,-14368 ,-14355 182. ,-14353 ,-14345 ,-14170 ,-14159 ,-14151 ,-14149 ,-14145 ,-14140 ,-14137 ,-14135 183. ,-14125 ,-14123 ,-14122 ,-14112 ,-14109 ,-14099 ,-14097 ,-14094 ,-14092 ,-14090 184. ,-14087 ,-14083 ,-13917 ,-13914 ,-13910 ,-13907 ,-13906 ,-13905 ,-13896 ,-13894 185. ,-13878 ,-13870 ,-13859 ,-13847 ,-13831 ,-13658 ,-13611 ,-13601 ,-13406 ,-13404 186. ,-13400 ,-13398 ,-13395 ,-13391 ,-13387 ,-13383 ,-13367 ,-13359 ,-13356 ,-13343 187. ,-13340 ,-13329 ,-13326 ,-13318 ,-13147 ,-13138 ,-13120 ,-13107 ,-13096 ,-13095 188. ,-13091 ,-13076 ,-13068 ,-13063 ,-13060 ,-12888 ,-12875 ,-12871 ,-12860 ,-12858 189. ,-12852 ,-12849 ,-12838 ,-12831 ,-12829 ,-12812 ,-12802 ,-12607 ,-12597 ,-12594 190. ,-12585 ,-12556 ,-12359 ,-12346 ,-12320 ,-12300 ,-12120 ,-12099 ,-12089 ,-12074 191. ,-12067 ,-12058 ,-12039 ,-11867 ,-11861 ,-11847 ,-11831 ,-11798 ,-11781 ,-11604 192. ,-11589 ,-11536 ,-11358 ,-11340 ,-11339 ,-11324 ,-11303 ,-11097 ,-11077 ,-11067 193. ,-11055 ,-11052 ,-11045 ,-11041 ,-11038 ,-11024 ,-11020 ,-11019 ,-11018 ,-11014 194. ,-10838 ,-10832 ,-10815 ,-10800 ,-10790 ,-10780 ,-10764 ,-10587 ,-10544 ,-10533 195. ,-10519 ,-10331 ,-10329 ,-10328 ,-10322 ,-10315 ,-10309 ,-10307 ,-10296 ,-10281 196. ,-10274 ,-10270 ,-10262 ,-10260 ,-10256 ,-10254 197. }; 198. string[] sA = new string[] 199. { 200. "a","ai","an","ang","ao" 201. 202. ,"ba","bai","ban","bang","bao","bei","ben","beng","bi","bian","biao","bie","bin" 203. ,"bing","bo","bu" 204. 205. ,"ca","cai","can","cang","cao","ce","ceng","cha","chai","chan","chang","chao","che" 206. ,"chen","cheng","chi","chong","chou","chu","chuai","chuan","chuang","chui","chun" 207. ,"chuo","ci","cong","cou","cu","cuan","cui","cun","cuo" 208. 209. ,"da","dai","dan","dang","dao","de","deng","di","dian","diao","die","ding","diu" 210. ,"dong","dou","du","duan","dui","dun","duo" 211. 212. ,"e","en","er" 213. 214. ,"fa","fan","fang","fei","fen","feng","fo","fou","fu" 215. 216. ,"ga","gai","gan","gang","gao","ge","gei","gen","geng","gong","gou","gu","gua","guai" 217. ,"guan","guang","gui","gun","guo" 218. 219. ,"ha","hai","han","hang","hao","he","hei","hen","heng","hong","hou","hu","hua","huai" 220. ,"huan","huang","hui","hun","huo" 221. 222. ,"ji","jia","jian","jiang","jiao","jie","jin","jing","jiong","jiu","ju","juan","jue" 223. ,"jun" 224. 225. ,"ka","kai","kan","kang","kao","ke","ken","keng","kong","kou","ku","kua","kuai","kuan" 226. ,"kuang","kui","kun","kuo" 227. 228. ,"la","lai","lan","lang","lao","le","lei","leng","li","lia","lian","liang","liao","lie" 229. ,"lin","ling","liu","long","lou","lu","lv","luan","lue","lun","luo" 230. 231. ,"ma","mai","man","mang","mao","me","mei","men","meng","mi","mian","miao","mie","min" 232. ,"ming","miu","mo","mou","mu" 233. 234. ,"na","nai","nan","nang","nao","ne","nei","nen","neng","ni","nian","niang","niao","nie" 235. ,"nin","ning","niu","nong","nu","nv","nuan","nue","nuo" 236. 237. ,"o","ou" 238. 239. ,"pa","pai","pan","pang","pao","pei","pen","peng","pi","pian","piao","pie","pin","ping" 240. ,"po","pu" 241. 242. ,"qi","qia","qian","qiang","qiao","qie","qin","qing","qiong","qiu","qu","quan","que" 243. ,"qun" 244. 245. ,"ran","rang","rao","re","ren","reng","ri","rong","rou","ru","ruan","rui","run","ruo" 246. 247. ,"sa","sai","san","sang","sao","se","sen","seng","sha","shai","shan","shang","shao","she" 248. ,"shen","sheng","shi","shou","shu","shua","shuai","shuan","shuang","shui","shun","shuo","si" 249. ,"song","sou","su","suan","sui","sun","suo" 250. 251. ,"ta","tai","tan","tang","tao","te","teng","ti","tian","tiao","tie","ting","tong","tou","tu" 252. ,"tuan","tui","tun","tuo" 253. 254. ,"wa","wai","wan","wang","wei","wen","weng","wo","wu" 255. 256. ,"xi","xia","xian","xiang","xiao","xie","xin","xing","xiong","xiu","xu","xuan","xue","xun" 257. 258. ,"ya","yan","yang","yao","ye","yi","yin","ying","yo","yong","you","yu","yuan","yue","yun" 259. 260. ,"za","zai","zan","zang","zao","ze","zei","zen","zeng","zha","zhai","zhan","zhang","zhao" 261. ,"zhe","zhen","zheng","zhi","zhong","zhou","zhu","zhua","zhuai","zhuan","zhuang","zhui" 262. ,"zhun","zhuo","zi","zong","zou","zu","zuan","zui","zun","zuo" 263. }; 264. byte[] B = new byte[2]; 265. string s = ""; 266. char[] c = x.ToCharArray(); 267. for (int j = 0; j < c.Length; j++) 268. { 269. B = System.Text.Encoding.Default.GetBytes(c[j].ToString()); 270. if ((int)(B[0]) <= 160 && (int)(B[0]) >= 0) 271. { 272. s += c[j]; 273. } 274. else 275. { 276. for (int i = (iA.Length - 1); i >= 0; i--) 277. { 278. if (iA[i] <= (int)(B[0]) * 256 + (int)(B[1]) - 65536) 279. { 280. s += sA[i]; 281. break; 282. } 283. } 284. } 285. } 286. return s; 287. } 288. }

/// <summary> /// 静态方法，获取一个字符的汉字拼音的首字母 /// </summary> /// <param name="cnChar"> /// 需要计算拼音首字母的串 /// </param> public static System.String getSpell(System.String cnChar) { System.Byte[] arrCN = System.Text.Encoding.Default.GetBytes(cnChar); if (arrCN.Length > 1) { System.Int32 area = (System.Int16)arrCN[0]; System.Int32 pos = (System.Int16)arrCN[1]; System.Int32 code = (area << 8) + pos; System.Int32[] 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 (System.Int32 i = 0; i < 26; i++) { System.Int32 max = 55290; if (i != 25) { max = areacode[i + 1]; } if (areacode[i] <= code && code < max) { return System.Text.Encoding.Default.GetString(new System.Byte[] { (System.Byte)(65 + i) }); } } return "*"; } else { return cnChar; } }

soruce http://paulfzm.javaeye.com/blog/394886