用户注册



邮箱：

密码：

用户登录


邮箱：

密码：
记住登录一个月忘记密码？

发表随想


还能输入：200字
云代码 - c#代码库

用C#实现汉字转化为拼音

2012-09-03 作者： 神马举报

[c#]代码库

using System;
using System.Collections.Generic;
using System.Text;
using System.Text.RegularExpressions;

namespace test
{
/// 用C#实现汉字转化为拼音
/// 实现的原理就是先将汉字转化成为内码，然后通过内码和拼音的对照来查找。
public class SplitWord
{
	/// <summary>
	///将所有的汉字转换成为拼音（小写）
	///作者：
	///完成于：
	/// </summary>
	static Regex MyRegex = new Regex ( "^[一-龥]$" ); //汉字的正则表达式“[一-龥]”指所有的汉字，从“一”到“龥”（念yu）的汉字，基本上涵盖了所有的汉字

	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[] pystr = new string[] {"a","ai","an","ang","ao","ba","bai","ban","bang","bao","bei","ben","beng","bi","bian","biao",
	        "bie","bin","bing","bo","bu","ca","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>
	/// 转化汉字的全部拼音
	/// </summary>
	/// <param name="chrstr"></param>
	/// <returns></returns>
	public static string ConvertAllSpell ( string chrstr )
	{
		Regex MyRegex = new Regex ( "^[一-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 < nowchar.Length; j++ )
		{
			if ( MyRegex.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 )
				{
					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();
			}
		}
		return returnstr;
	}
	//ChineseToPY
	/**/
	/// <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;
	}
	public static string ConvertFirstSpell ( string chrstr )
	{
		Regex MyRegex = new Regex ( "^[一-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 < 1; j++ )
		{
			if ( MyRegex.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 )
				{
					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();
			}
		}
		return returnstr;
	}
}
}


网友评论    (发表评论)

共2 条评论 1/1页

发表评论：

评论须知：

  • 1、评论每次加2分，每天上限为30；
  • 2、请文明用语，共同创建干净的技术交流环境；
  • 3、若被发现提交非法信息，评论将会被删除，并且给予扣分处理，严重者给予封号处理；
  • 4、请勿发布广告信息或其他无关评论，否则将会删除评论并扣分，严重者给予封号处理。


扫码下载

加载中，请稍后...

输入口令后可复制整站源码

加载中，请稍后...