• 汉字转拼音 输入汉字获取其拼音


    前不久看到有的朋友实现对商品名称拼音的录入,发现他的实现方式是手动输入的,—_—#、同志们,福利来了!

     本文刚发布时,只写了一个实现方式,使用的是微软的语言包,但是对多音字的效果不怎么理想,甚至个别字会出现很诡异的错误,因此,现在扩展另一个方法,手动实现。

       方式一、使用微软语言包
     微软为了开发者实现国际化语言的互转,提供了Microsoft Visual Studio International Pack,这个扩展包里面有中文、日文、韩文、英语等各国语言包,并提供方法实现互转、获取拼音、获取字数、甚至获取笔画数等等。

     [这种方式对多音字的效果不怎么理想,但是,这个方法比较简单,直接导入包就可以了,因此,对于那些只需要个别语句进行处理的或者不注重多音字的,可以使用这种方式,毕竟简便嘛。]

     在这里示例讲的是输入汉字,获取其拼音,获取拼音和获取拼音首字母实现效果分别如下:
    1.jpg   2.jpg

     首先,去微软官网下载Microsoft Visual Studio International Pack语言包,下载地址分别如下:
    Microsoft Visual Studio International Pack 1.0 SR1Microsoft Visual Studio International Feature Pack 2.0

     下载后分别是“vsintlpack1.zip”、“Vsintlpack2.msi”、双击“Vsintlpack2.msi”安装、路径随意、但是要记得、因为一会要引用的、
     安装“Vsintlpack2.msi”之后、解压“vsintlpack1.zip”、里面包含七个语言包、
     例如中文转拼音“CHSPinYinConv.msi”、简体繁体互转“CHTCHSConv.msi”等等。。

     在这里我们用到的是“CHSPinYinConv.msi”、双击安装成功后、打开Visual Studio、新建一个WinForm项目、窗体布局如上图所示、

    首先:添加刚刚安装的语言包引用:

    “D:\Program Files (x86)\Microsoft Visual Studio International Pack\Simplified Chinese Pin-Yin Conversion Library\ChnCharInfo.dll”

    默认是C盘、在这里我安装在D盘了,然后添加using引用:

    1 using Microsoft.International.Converters.PinYinConverter;//导入拼音相关


     创建获取拼音的方法:

     1 /// <summary> 
     2 /// 汉字转化为拼音
     3 /// </summary> 
     4 /// <param name="str">汉字</param> 
     5 /// <returns>全拼</returns> 
     6 public static string GetPinyin(string str)
     7 {
     8     string r = string.Empty;
     9     foreach (char obj in str)
    10     {
    11         try
    12         {
    13             ChineseChar chineseChar = new ChineseChar(obj);
    14             string t = chineseChar.Pinyins[0].ToString();
    15             r += t.Substring(0, t.Length - 1);
    16         }
    17         catch
    18         {
    19             r += obj.ToString();
    20         }
    21     }
    22     return r;
    23 }
    汉字转化为拼音

     创建获取汉字拼音首字母的方法:

     1 /// <summary> 
     2 /// 汉字转化为拼音首字母
     3 /// </summary> 
     4 /// <param name="str">汉字</param> 
     5 /// <returns>首字母</returns> 
     6 public static string GetFirstPinyin(string str)
     7 {
     8     string r = string.Empty;
     9     foreach (char obj in str)
    10     {
    11         try
    12         {
    13             ChineseChar chineseChar = new ChineseChar(obj);
    14             string t = chineseChar.Pinyins[0].ToString();
    15             r += t.Substring(0, 1);
    16         }
    17         catch
    18         {
    19             r += obj.ToString();
    20         }
    21     }
    22     return r;
    23 }
    汉字转化为拼音首字母

     然后在“转拼音”按钮的点击事件中调用上述方法:

    1 // 汉字转拼音
    2 private void btn_One_Click(object sender, EventArgs e)
    3 {
    4     string source = this.txt_ChineseCharacter_One.Text.Trim();  // 得到输入的源字符
    5     string result = GetPinyin(source);  // 调用方法,获取拼音
    6     this.txt_Pinyin_One.Text = result;
    7 }
    然后在“转拼音”按钮的点击事件中调用上述方法

     在“转首字母”按钮点击事件中调用上述方法:

    1 // 转首字母
    2 private void btn_Two_Click(object sender, EventArgs e)
    3 {
    4     string source = this.txt_ChineseCharacter_One.Text.Trim();  // 得到输入的源字符
    5     string result = GetFirstPinyin(source);  // 调用方法,获取拼音
    6     this.txt_Pinyin_One.Text = result;
    7 }
    在“转首字母”按钮点击事件中调用上述方法:


     到此,已经完成了80%,运行程序,你会发现,当点击“转拼音”的时候,结果是这样子的:
    3.jpg
    并不是我开始说的那种“Gu Ying”的效果啊、这是因为我在获取拼音的时候简单的处理了一下:

     1 // 汉字转拼音
     2 private void btn_One_Click(object sender, EventArgs e)
     3 {
     4     string source = this.txt_ChineseCharacter_One.Text.Trim();  // 得到输入的源字符
     5 
     6     string result = string.Empty;   // 转拼音的结果
     7     string temp = string.Empty; // 下面foreach用到的临时变量
     8     foreach (char item in source)   // 遍历每个源字符
     9     {
    10         temp = GetPinyin(item.ToString());  // 将每个字符转拼音
    11         // 处理:获取首字母大写、其余字母小写
    12         result += (String.Format("{0}{1} ", temp.Substring(0, 1).ToUpper(), temp.Substring(1).ToLower()));
    13     }
    14 
    15     //string result = GetPinyin(source);  // 调用方法,获取拼音
    16     this.txt_Pinyin_One.Text = result;
    17 }
    处理拼音结果


     OK、到此、这个功能已经实现完成了,还有其余的语言包功能,和此类似,大家可以百度“Microsoft Visual Studio International Pack使用”、各种语言之间的互转及功能示例就出来了。

    方式二、手动编码实现

     这种方式其实也不困难,说白了就是根据Unicode编码值,定义对应的拼音数组或集合,然后实现此效果。

    首先定义拼音区编码数组:

     1 //定义拼音区编码数组
     2 private static int[] getValue = new int[]
     3     {
     4         -20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,-20242,-20230,-20051,-20036,
     5         -20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,-19775,-19774,-19763,
     6         -19756,-19751,-19746,-19741,-19739,-19728,-19725,-19715,-19540,-19531,-19525,-19515,
     7         -19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263,-19261,-19249,
     8         -19243,-19242,-19238,-19235,-19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,
     9         -19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,
    10         -18731,-18722,-18710,-18697,-18696,-18526,-18518,-18501,-18490,-18478,-18463,-18448,
    11         -18447,-18446,-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183, -18181,-18012,
    12         -17997,-17988,-17970,-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,
    13         -17733,-17730,-17721,-17703,-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,
    14         -17468,-17454,-17433,-17427,-17417,-17202,-17185,-16983,-16970,-16942,-16915,-16733,
    15         -16708,-16706,-16689,-16664,-16657,-16647,-16474,-16470,-16465,-16459,-16452,-16448,
    16         -16433,-16429,-16427,-16423,-16419,-16412,-16407,-16403,-16401,-16393,-16220,-16216,
    17         -16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,-16155,-15959,-15958,-15944,
    18         -15933,-15920,-15915,-15903,-15889,-15878,-15707,-15701,-15681,-15667,-15661,-15659,
    19         -15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,-15408,-15394,
    20         -15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,-15150,
    21         -15149,-15144,-15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,
    22         -14941,-14937,-14933,-14930,-14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,
    23         -14894,-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668,-14663,-14654,
    24         -14645,-14630,-14594,-14429,-14407,-14399,-14384,-14379,-14368,-14355,-14353,-14345,
    25         -14170,-14159,-14151,-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,
    26         -14109,-14099,-14097,-14094,-14092,-14090,-14087,-14083,-13917,-13914,-13910,-13907,
    27         -13906,-13905,-13896,-13894,-13878,-13870,-13859,-13847,-13831,-13658,-13611,-13601,
    28         -13406,-13404,-13400,-13398,-13395,-13391,-13387,-13383,-13367,-13359,-13356,-13343,
    29         -13340,-13329,-13326,-13318,-13147,-13138,-13120,-13107,-13096,-13095,-13091,-13076,
    30         -13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,-12852,-12849,-12838,-12831,
    31         -12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,-12359,-12346,-12320,-12300,
    32         -12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,-11831,-11798,
    33         -11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,-11067,
    34         -11055,-11052,-11045,-11041,-11038,-11024,-11020,-11019,-11018,-11014,-10838,-10832,
    35         -10815,-10800,-10790,-10780,-10764,-10587,-10544,-10533,-10519,-10331,-10329,-10328,
    36         -10322,-10315,-10309,-10307,-10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254
    37     };
    定义拼音区编码数组

    然后定义拼音数组:

     1 //定义拼音数组
     2 private static string[] getName = new string[]
     3     {
     4         "A","Ai","An","Ang","Ao","Ba","Bai","Ban","Bang","Bao","Bei","Ben",
     5         "Beng","Bi","Bian","Biao","Bie","Bin","Bing","Bo","Bu","Ba","Cai","Can",
     6         "Cang","Cao","Ce","Ceng","Cha","Chai","Chan","Chang","Chao","Che","Chen","Cheng",
     7         "Chi","Chong","Chou","Chu","Chuai","Chuan","Chuang","Chui","Chun","Chuo","Ci","Cong",
     8         "Cou","Cu","Cuan","Cui","Cun","Cuo","Da","Dai","Dan","Dang","Dao","De",
     9         "Deng","Di","Dian","Diao","Die","Ding","Diu","Dong","Dou","Du","Duan","Dui",
    10         "Dun","Duo","E","En","Er","Fa","Fan","Fang","Fei","Fen","Feng","Fo",
    11         "Fou","Fu","Ga","Gai","Gan","Gang","Gao","Ge","Gei","Gen","Geng","Gong",
    12         "Gou","Gu","Gua","Guai","Guan","Guang","Gui","Gun","Guo","Ha","Hai","Han",
    13         "Hang","Hao","He","Hei","Hen","Heng","Hong","Hou","Hu","Hua","Huai","Huan",
    14         "Huang","Hui","Hun","Huo","Ji","Jia","Jian","Jiang","Jiao","Jie","Jin","Jing",
    15         "Jiong","Jiu","Ju","Juan","Jue","Jun","Ka","Kai","Kan","Kang","Kao","Ke",
    16         "Ken","Keng","Kong","Kou","Ku","Kua","Kuai","Kuan","Kuang","Kui","Kun","Kuo",
    17         "La","Lai","Lan","Lang","Lao","Le","Lei","Leng","Li","Lia","Lian","Liang",
    18         "Liao","Lie","Lin","Ling","Liu","Long","Lou","Lu","Lv","Luan","Lue","Lun",
    19         "Luo","Ma","Mai","Man","Mang","Mao","Me","Mei","Men","Meng","Mi","Mian",
    20         "Miao","Mie","Min","Ming","Miu","Mo","Mou","Mu","Na","Nai","Nan","Nang",
    21         "Nao","Ne","Nei","Nen","Neng","Ni","Nian","Niang","Niao","Nie","Nin","Ning",
    22         "Niu","Nong","Nu","Nv","Nuan","Nue","Nuo","O","Ou","Pa","Pai","Pan",
    23         "Pang","Pao","Pei","Pen","Peng","Pi","Pian","Piao","Pie","Pin","Ping","Po",
    24         "Pu","Qi","Qia","Qian","Qiang","Qiao","Qie","Qin","Qing","Qiong","Qiu","Qu",
    25         "Quan","Que","Qun","Ran","Rang","Rao","Re","Ren","Reng","Ri","Rong","Rou",
    26         "Ru","Ruan","Rui","Run","Ruo","Sa","Sai","San","Sang","Sao","Se","Sen",
    27         "Seng","Sha","Shai","Shan","Shang","Shao","She","Shen","Sheng","Shi","Shou","Shu",
    28         "Shua","Shuai","Shuan","Shuang","Shui","Shun","Shuo","Si","Song","Sou","Su","Suan",
    29         "Sui","Sun","Suo","Ta","Tai","Tan","Tang","Tao","Te","Teng","Ti","Tian",
    30         "Tiao","Tie","Ting","Tong","Tou","Tu","Tuan","Tui","Tun","Tuo","Wa","Wai",
    31         "Wan","Wang","Wei","Wen","Weng","Wo","Wu","Xi","Xia","Xian","Xiang","Xiao",
    32         "Xie","Xin","Xing","Xiong","Xiu","Xu","Xuan","Xue","Xun","Ya","Yan","Yang",
    33         "Yao","Ye","Yi","Yin","Ying","Yo","Yong","You","Yu","Yuan","Yue","Yun",
    34         "Za", "Zai","Zan","Zang","Zao","Ze","Zei","Zen","Zeng","Zha","Zhai","Zhan",
    35         "Zhang","Zhao","Zhe","Zhen","Zheng","Zhi","Zhong","Zhou","Zhu","Zhua","Zhuai","Zhuan",
    36         "Zhuang","Zhui","Zhun","Zhuo","Zi","Zong","Zou","Zu","Zuan","Zui","Zun","Zuo"
    37    };
    定义拼音数组

    然后定义转换字符串的方法:

     1         /// <summary>汉字转换成全拼的拼音</summary>
     2         /// <param name="Chstr">汉字字符串</param>
     3         /// <returns>转换后的拼音字符串</returns> 
     4         public string StrConvertToPinyin(string Chstr)
     5         {
     6             Regex reg = new Regex("^[\u4e00-\u9fa5]$");//验证是否输入汉字
     7             byte[] arr = new byte[2];
     8             string pystr = "";
     9             int asc = 0, M1 = 0, M2 = 0;
    10             char[] mChar = Chstr.ToCharArray();//获取汉字对应的字符数组
    11             for (int j = 0; j < mChar.Length; j++)
    12             {
    13                 //如果输入的是汉字
    14                 if (reg.IsMatch(mChar[j].ToString()))
    15                 {
    16                     arr = System.Text.Encoding.Default.GetBytes(mChar[j].ToString());
    17                     M1 = (short)(arr[0]);
    18                     M2 = (short)(arr[1]);
    19                     asc = M1 * 256 + M2 - 65536;
    20                     if (asc > 0 && asc < 160)
    21                     {
    22                         pystr += mChar[j];
    23                     }
    24                     else
    25                     {
    26                         switch (asc)
    27                         {
    28                             case -9254:
    29                                 pystr += "Zhen"; break;
    30                             case -8985:
    31                                 pystr += "Qian"; break;
    32                             case -5463:
    33                                 pystr += "Jia"; break;
    34                             case -8274:
    35                                 pystr += "Ge"; break;
    36                             case -5448:
    37                                 pystr += "Ga"; break;
    38                             case -5447:
    39                                 pystr += "La"; break;
    40                             case -4649:
    41                                 pystr += "Chen"; break;
    42                             case -5436:
    43                                 pystr += "Mao"; break;
    44                             case -5213:
    45                                 pystr += "Mao"; break;
    46                             case -3597:
    47                                 pystr += "Die"; break;
    48                             case -5659:
    49                                 pystr += "Tian"; break;
    50                             default:
    51                                 for (int i = (getValue.Length - 1); i >= 0; i--)
    52                                 {
    53                                     if (getValue[i] <= asc) //判断汉字的拼音区编码是否在指定范围内
    54                                     {
    55                                         pystr += getName[i];//如果不超出范围则获取对应的拼音
    56                                         break;
    57                                     }
    58                                 }
    59                                 break;
    60                         }
    61                     }
    62                 }
    63                 else    //如果不是汉字
    64                 {
    65                     pystr += mChar[j].ToString();//如果不是汉字则返回
    66                 }
    67             }
    68             return pystr;//返回获取到的汉字拼音
    69         }
    汉字转换成全拼的拼音

     这种方法虽然也会对多音字的识别也不是很理想,但是这种方式毕竟是手动实现的,可以手动控制,比如,“家长”,我们想得到的结果是“Jia Zhang”,但是生成的结果却是“Jia Chang”、

     对于这种包含多音字的词组,我们可以另行控制,比如,定义一个多音字数组和其对应的不同词组组合,在我们进行转换拼音的时候,判断,如果是多音字,那么在其词组中找到对应的拼音即可。

     类似于我们做Web开发时的关键字过滤。

    【来自:LonelyShadow http://www.cnblogs.com/LonelyShadow

    【来自:张董'Blogs:http://www.cnblogs.com/LonelyShadow,转载请注明出处。】

    亲们。码字不容易,觉得不错的话记得点赞哦。。

  • 相关阅读:
    Python 3.6安装yaml时报"AttributeError: module 'pip' has no attribute 'main'"和“Non-zero exit code”错误
    Python 3.6版本中实现 HTMLTestRunner输出时”fp=file(filename,'wb')“报错
    LoadRunner录制脚本时没有响应——无法启动浏览器问题总结
    python中print不换行
    python中for循环的三种遍历方式
    python enumerate用法
    Python中添加中文注释报错SyntaxError: Non-UTF-8 code starting with 'xc1'
    pycharm 2017最新激活码
    设计模式之禅2之六大原则
    hibernate错误整理
  • 原文地址:https://www.cnblogs.com/geeksss/p/3543798.html
Copyright © 2020-2023  润新知