http://www.sufeinet.com/plugin.php?id=keke_group

苏飞论坛

 找回密码
 马上注册

QQ登录

只需一步,快速开始

分布式系统框架(V2.0) 轻松承载百亿数据,千万流量!讨论专区 - 源码下载 - 官方教程

HttpHelper爬虫框架(V2.7-含.netcore) HttpHelper官方出品,爬虫框架讨论区 - 源码下载 - 在线测试和代码生成

HttpHelper爬虫类(V2.0) 开源的爬虫类,支持多种模式和属性 源码 - 代码生成器 - 讨论区 - 教程- 例子

查看: 25587|回复: 23
打印 上一主题 下一主题

[功能帮助类] C#将汉字转换成全拼的拼音EcanConvertToCh帮助类

[复制链接]
跳转到指定楼层
楼主
发表于 2013-3-28 10:09:18 | 只看该作者 回帖奖励 |倒序浏览 |阅读模式
      C#将汉字转换成全拼的拼音EcanConvertToCh帮助类
导读部分
-------------------------------------------------------------------------------------------------------------
C#基类库苏飞版--系列教程导航
http://www.sufeinet.com/thread-655-1-1.html

主要功能就是将汉字转换成全拼的拼音,只要你输入一个汉字就会相应的转成拼音
最新的EcanConvertToCh操作类
EcanConvertToCh.rar (3.04 KB, 下载次数: 922)
看下面代码吧
[C#] 纯文本查看 复制代码
/// <summary>
/// 编 码 人:苏飞
/// 联系方式:361983679  
/// 更新网站:[url=http://www.sufeinet.com/thread-655-1-1.html]http://www.sufeinet.com/thread-655-1-1.html[/url]
/// </summary>
using System.Text.RegularExpressions;

namespace DotNet.Utilities
{
    /// <summary>
    /// 汉字转拼音类
    /// </summary>
    public class EcanConvertToCh
    {
        //定义拼音区编码数组
        private static int[] getValue = 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
            };

        //定义拼音数组
        private static string[] getName = 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>
        /// 汉字转换成全拼的拼音
        /// </summary>
        /// <param name="Chstr">汉字字符串</param>
        /// <returns>转换后的拼音字符串</returns>
        public string convertCh(string Chstr)
        {
            Regex reg = new Regex("^[\u4e00-\u9fa5]$");//验证是否输入汉字
            byte[] arr = new byte[2];
            string pystr = "";
            int asc = 0, M1 = 0, M2 = 0;
            char[] mChar = Chstr.ToCharArray();//获取汉字对应的字符数组
            for (int j = 0; j < mChar.Length; j++)
            {
                //如果输入的是汉字
                if (reg.IsMatch(mChar[j].ToString()))
                {
                    arr = System.Text.Encoding.Default.GetBytes(mChar[j].ToString());
                    M1 = (short)(arr[0]);
                    M2 = (short)(arr[1]);
                    asc = M1 * 256 + M2 - 65536;
                    if (asc > 0 && asc < 160)
                    {
                        pystr += mChar[j];
                    }
                    else
                    {
                        switch (asc)
                        {
                            case -9254:
                                pystr += "Zhen"; break;
                            case -8985:
                                pystr += "Qian"; break;
                            case -5463:
                                pystr += "Jia"; break;
                            case -8274:
                                pystr += "Ge"; break;
                            case -5448:
                                pystr += "Ga"; break;
                            case -5447:
                                pystr += "La"; break;
                            case -4649:
                                pystr += "Chen"; break;
                            case -5436:
                                pystr += "Mao"; break;
                            case -5213:
                                pystr += "Mao"; break;
                            case -3597:
                                pystr += "Die"; break;
                            case -5659:
                                pystr += "Tian"; break;
                            default:
                                for (int i = (getValue.Length - 1); i >= 0; i--)
                                {
                                    if (getValue <= asc) //判断汉字的拼音区编码是否在指定范围内
                                    {
                                        pystr += getName;//如果不超出范围则获取对应的拼音
                                        break;
                                    }
                                }
                                break;
                        }
                    }
                }
                else//如果不是汉字
                {
                    pystr += mChar[j].ToString();//如果不是汉字则返回
                }
            }
            return pystr;//返回获取到的汉字拼音
        }
    }
}



1. 开通SVIP会员,免费下载本站所有源码,不限次数据,不限时间
2. 加官方QQ群,加官方微信群获取更多资源和帮助
3. 找站长苏飞做网站、商城、CRM、小程序、App、爬虫相关、项目外包等点这里
沙发
 楼主| 发表于 2013-3-28 10:10:03 | 只看该作者
亲测试好用大家可以下载试试
板凳
发表于 2013-9-22 13:59:27 | 只看该作者
多音字 有处理吗?
地板
发表于 2013-9-22 14:01:01 | 只看该作者
多音字有没有处理? 强烈支持楼主ing……
5
 楼主| 发表于 2013-9-22 14:13:56 | 只看该作者
xst 发表于 2013-9-22 14:01
多音字有没有处理? 强烈支持楼主ing……

没有
6
发表于 2013-9-23 17:23:32 | 只看该作者

那这个真的没多大用哦,中文汉语博大精深,特点之一就是多音字多
7
 楼主| 发表于 2013-9-23 18:10:43 | 只看该作者
ljx1 发表于 2013-9-23 17:23
那这个真的没多大用哦,中文汉语博大精深,特点之一就是多音字多

不能用就先不用,你如果要做一个简单的转化是没有问题的,如果要求比较精确,你可以自己写
8
发表于 2013-9-25 18:21:16 | 只看该作者
ljx1 发表于 2013-9-23 17:23
那这个真的没多大用哦,中文汉语博大精深,特点之一就是多音字多

我写了个能处理多音字的,回头发论坛
9
发表于 2014-1-21 09:56:24 | 只看该作者
不靠谱啊,刚才用那个在线的试了试  “淼”,它给我出来的是 Zuo,但是提取首字母又给我出的是 M      {:soso_e110:}
10
 楼主| 发表于 2014-1-21 10:26:51 | 只看该作者
flxgis 发表于 2014-1-21 09:56
不靠谱啊,刚才用那个在线的试了试  “淼”,它给我出来的是 Zuo,但是提取首字母又给我出的是 M       ...

这个过时了,只不是不会识别多音字,这个我已修复,下次更新会看到更新,你搜索一下,站里有人发过这个,也是修改过的,
您需要登录后才可以回帖 登录 | 马上注册

本版积分规则

QQ|手机版|小黑屋|手机版|联系我们|关于我们|广告合作|苏飞论坛 ( 豫ICP备18043678号-2)

GMT+8, 2024-11-21 22:36

© 2014-2021

快速回复 返回顶部 返回列表