对于中文文本的排序,我想将汉字转换为拼音,正确分离每个汉字并将连续的字符组合在一起.
通过提供执行此操作的逻辑或源代码,您能帮助我完成此任务吗?
如果有任何开源或lib已经存在,请告诉我.
JUS*_*ION 12
简短的回答:你没有.
答案很长:汉字拼音没有一对一的映射.只是一些简单的例子:
等等.我有一本关于这个主题的初学者书,里面有207个例子.我强调这是一本初学者的书,并不完整.每个人都有一两页使用和条件的例子,您可以根据这些例子选择合适的发音.它不是易于编程的东西(如果有的话).
这甚至没有解决你想要处理的其他问题:将字符分成分组的单词.一句话的概念在中文中有点滑.(有两个术语对应,大致相当于中文中的"单词",例如:字和词.第一个是字符,第二个字符组合在一起构成一个概念.(我经常被中国人问到有多少当他们真正意为"人物"时,我可以阅读"单词".)虽然在某些情况下区别很明显(例如,"乌鸦"一词是"乌鸦" - 两个字必须在一起才能恰当地表达这个想法将它翻译为"黑鸦"是不正确的,在其他人中它不是那么清楚."你好"是什么意思?它是一个词意义,惯用,"你好"?还是两个词翻译字面意思是"你好"?所涉及的每个角色都是独立的或与其他词汇分组,但它们在一起意味着与其个人意义完全不同的东西.鉴于此,你是如何准确地将汉语拼音音译分组的(一开始很难做到这一点!)进入"言语"?
CoreFoundation提供了一些转换方法:
CFMutableStringRef string = CFStringCreateMutableCopy(NULL, 0, CFSTR("??"));
CFStringTransform(string, NULL, kCFStringTransformMandarinLatin, NO);
CFStringTransform(string, NULL, kCFStringTransformStripDiacritics, NO);
NSLog(@"%@", string);
Run Code Online (Sandbox Code Playgroud)
输出是
zhong wen
Run Code Online (Sandbox Code Playgroud)
虽然@JUST 我的正确意见的答案解决了将字符转换为拼音的一些困难,但这并不是一个不可能解决的问题。
我写了一个库(pinyinify),它以不错的准确度解决了这个任务。即使字符和拼音之间没有一一对应的关系,我的图书馆通常也可以决定哪个发音是正确的。例如, ”?????” 正确转换为 "w? shòubùli?o le",有两种不同的 ? 发音。
我解决这个问题的方法很简单:
下面用C#编写的代码可以帮助您简单地将GB2312编码中包含的中文单词(仅常用简体中文单词的2312个)转换为拼音。例如转换“\xe4\xbb\x8a\xe5\xa4\xa9\xe5 \xa4\xa9\xe6\xb0\x94\xe4\xb8\x8d\xe9\x94\x99" 到 "JinTianTianQiBuCuo"。
\n\n有时一个中文单词并不是一一对应于拼音的,这取决于我们谈论的上下文。就像“\xe8\x87\xaa\xe8\xa1\x8c\xe8\”中的“\xe8\xa1\x8c” xbd\xa6"(自行车)发音为“Xing”,但在“\xe9\x93\xb6\xe8\xa1\x8c”(银行)中发音为“Hang”。所以如果你对此有疑问,你可能会找到更多复杂的解决方案来处理这个问题。
\n\n抱歉我的英语不好。我希望这能给你一点帮助。
\n\npublic class ChineseToPinYin\n {\n private static int[] pyValue = new int[]\n {\n -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,-20242,-20230,-20051,-20036,\n -20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,-19775,-19774,-19763,\n -19756,-19751,-19746,-19741,-19739,-19728,-19725,-19715,-19540,-19531,-19525,-19515,\n -19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263,-19261,-19249,\n -19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,\n -19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,\n -18731,-18722,-18710,-18697,-18696,-18526,-18518,-18501,-18490,-18478,-18463,-18448,\n -18447,-18446,-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183, -18181,-18012,\n -17997,-17988,-17970,-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,\n -17733,-17730,-17721,-17703,-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,\n -17468,-17454,-17433,-17427,-17417,-17202,-17185,-16983,-16970,-16942,-16915,-16733,\n -16708,-16706,-16689,-16664,-16657,-16647,-16474,-16470,-16465,-16459,-16452,-16448,\n -16433,-16429,-16427,-16423,-16419,-16412,-16407,-16403,-16401,-16393,-16220,-16216,\n -16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,-16155,-15959,-15958,-15944,\n -15933,-15920,-15915,-15903,-15889,-15878,-15707,-15701,-15681,-15667,-15661,-15659,\n -15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,-15408,-15394,\n -15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,-15150,\n -15149,-15144,-15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,\n -14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,\n -14894,-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668,-14663,-14654,\n -14645,-14630,-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345,\n -14170,-14159,-14151,-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,\n -14109,-14099,-14097,-14094,-14092,-14090,-14087,-14083,-13917,-13914,-13910,-13907,\n -13906,-13905,-13896,-13894,-13878,-13870,-13859,-13847,-13831,-13658,-13611,-13601,\n -13406,-13404,-13400,-13398,-13395,-13391,-13387,-13383,-13367,-13359,-13356,-13343,\n -13340,-13329,-13326,-13318,-13147,-13138,-13120,-13107,-13096,-13095,-13091,-13076,\n -13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,-12852,-12849,-12838,-12831,\n -12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,-12346,-12320,-12300,\n -12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,-11831,-11798,\n -11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,-11067,\n -11055,-11052,-11045,-11041,-11038,-11024,-11020,-11019,-11018,-11014,-10838,-10832,\n -10815,-10800,-10790,-10780,-10764,-10587,-10544,-10533,-10519,-10331,-10329,-10328,\n -10322,-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254\n };\n\n private static string[] pyName = new string[]\n{\n"A","Ai","An","Ang","Ao","Ba","Bai","Ban","Bang","Bao","Bei","Ben",\n"Beng","Bi","Bian","Biao","Bie","Bin","Bing","Bo","Bu","Ba","Cai","Can",\n"Cang","Cao","Ce","Ceng","Cha","Chai","Chan","Chang","Chao","Che","Chen","Cheng",\n"Chi","Chong","Chou","Chu","Chuai","Chuan","Chuang","Chui","Chun","Chuo","Ci","Cong",\n"Cou","Cu","Cuan","Cui","Cun","Cuo","Da","Dai","Dan","Dang","Dao","De",\n"Deng","Di","Dian","Diao","Die","Ding","Diu","Dong","Dou","Du","Duan","Dui",\n"Dun","Duo","E","En","Er","Fa","Fan","Fang","Fei","Fen","Feng","Fo",\n"Fou","Fu","Ga","Gai","Gan","Gang","Gao","Ge","Gei","Gen","Geng","Gong",\n"Gou","Gu","Gua","Guai","Guan","Guang","Gui","Gun","Guo","Ha","Hai","Han",\n"Hang","Hao","He","Hei","Hen","Heng","Hong","Hou","Hu","Hua","Huai","Huan",\n"Huang","Hui","Hun","Huo","Ji","Jia","Jian","Jiang","Jiao","Jie","Jin","Jing",\n"Jiong","Jiu","Ju","Juan","Jue","Jun","Ka","Kai","Kan","Kang","Kao","Ke",\n"Ken","Keng","Kong","Kou","Ku","Kua","Kuai","Kuan","Kuang","Kui","Kun","Kuo",\n"La","Lai","Lan","Lang","Lao","Le","Lei","Leng","Li","Lia","Lian","Liang",\n"Liao","Lie","Lin","Ling","Liu","Long","Lou","Lu","Lv","Luan","Lue","Lun",\n"Luo","Ma","Mai","Man","Mang","Mao","Me","Mei","Men","Meng","Mi","Mian",\n"Miao","Mie","Min","Ming","Miu","Mo","Mou","Mu","Na","Nai","Nan","Nang",\n"Nao","Ne","Nei","Nen","Neng","Ni","Nian","Niang","Niao","Nie","Nin","Ning",\n"Niu","Nong","Nu","Nv","Nuan","Nue","Nuo","O","Ou","Pa","Pai","Pan",\n"Pang","Pao","Pei","Pen","Peng","Pi","Pian","Piao","Pie","Pin","Ping","Po",\n"Pu","Qi","Qia","Qian","Qiang","Qiao","Qie","Qin","Qing","Qiong","Qiu","Qu",\n"Quan","Que","Qun","Ran","Rang","Rao","Re","Ren","Reng","Ri","Rong","Rou",\n"Ru","Ruan","Rui","Run","Ruo","Sa","Sai","San","Sang","Sao","Se","Sen",\n"Seng","Sha","Shai","Shan","Shang","Shao","She","Shen","Sheng","Shi","Shou","Shu",\n"Shua","Shuai","Shuan","Shuang","Shui","Shun","Shuo","Si","Song","Sou","Su","Suan",\n"Sui","Sun","Suo","Ta","Tai","Tan","Tang","Tao","Te","Teng","Ti","Tian",\n"Tiao","Tie","Ting","Tong","Tou","Tu","Tuan","Tui","Tun","Tuo","Wa","Wai",\n"Wan","Wang","Wei","Wen","Weng","Wo","Wu","Xi","Xia","Xian","Xiang","Xiao",\n"Xie","Xin","Xing","Xiong","Xiu","Xu","Xuan","Xue","Xun","Ya","Yan","Yang",\n"Yao","Ye","Yi","Yin","Ying","Yo","Yong","You","Yu","Yuan","Yue","Yun",\n"Za", "Zai","Zan","Zang","Zao","Ze","Zei","Zen","Zeng","Zha","Zhai","Zhan",\n"Zhang","Zhao","Zhe","Zhen","Zheng","Zhi","Zhong","Zhou","Zhu","Zhua","Zhuai","Zhuan",\n"Zhuang","Zhui","Zhun","Zhuo","Zi","Zong","Zou","Zu","Zuan","Zui","Zun","Zuo"\n};\n\n /// <summary>\n /// \xe6\x8a\x8a\xe6\xb1\x89\xe5\xad\x97\xe8\xbd\xac\xe6\x8d\xa2\xe6\x88\x90\xe6\x8b\xbc\xe9\x9f\xb3(\xe5\x85\xa8\xe6\x8b\xbc)\n /// </summary>\n /// <param name="hzString">\xe6\xb1\x89\xe5\xad\x97\xe5\xad\x97\xe7\xac\xa6\xe4\xb8\xb2</param>\n /// <returns>\xe8\xbd\xac\xe6\x8d\xa2\xe5\x90\x8e\xe7\x9a\x84\xe6\x8b\xbc\xe9\x9f\xb3(\xe5\x85\xa8\xe6\x8b\xbc)\xe5\xad\x97\xe7\xac\xa6\xe4\xb8\xb2</returns>\n public static string Convert(string hzString)\n {\n // \xe5\x8c\xb9\xe9\x85\x8d\xe4\xb8\xad\xe6\x96\x87\xe5\xad\x97\xe7\xac\xa6\n Regex regex = new Regex("^[\\u4e00-\\u9fa5]$");\n byte[] array = new byte[2];\n string pyString = "";\n int chrAsc = 0;\n int i1 = 0;\n int i2 = 0;\n char[] noWChar = hzString.ToCharArray();\n\n for (int j = 0; j < noWChar.Length; j++)\n {\n // \xe4\xb8\xad\xe6\x96\x87\xe5\xad\x97\xe7\xac\xa6\n if (regex.IsMatch(noWChar[j].ToString()))\n {\n array = System.Text.Encoding.Default.GetBytes(noWChar[j].ToString());\n i1 = (short)(array[0]);\n i2 = (short)(array[1]);\n chrAsc = i1 * 256 + i2 - 65536;\n if (chrAsc > 0 && chrAsc < 160)\n {\n pyString += noWChar[j];\n }\n else\n {\n // \xe4\xbf\xae\xe6\xad\xa3\xe9\x83\xa8\xe5\x88\x86\xe6\x96\x87\xe5\xad\x97\n if (chrAsc == -9254) // \xe4\xbf\xae\xe6\xad\xa3\xe2\x80\x9c\xe5\x9c\xb3\xe2\x80\x9d\xe5\xad\x97\n pyString += "Zhen";\n else\n {\n for (int i = (pyValue.Length - 1); i >= 0; i--)\n {\n if (pyValue[i] <= chrAsc)\n {\n pyString += pyName[i];\n break;\n }\n }\n }\n }\n }\n // \xe9\x9d\x9e\xe4\xb8\xad\xe6\x96\x87\xe5\xad\x97\xe7\xac\xa6\n else\n {\n pyString += noWChar[j].ToString();\n }\n }\n return pyString;\n }\n}\nRun Code Online (Sandbox Code Playgroud)\n