C#中实现输入汉字获取其拼音（汉字转拼音）的2种方法

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：

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 sr1、microsoft 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：

/// <summary>
/// 汉字转化为拼音
/// </summary>
/// <param name="str">汉字</param>
/// <returns>全拼</returns>
public static string getpinyin(string str)
{
    string r = string.empty;
    foreach (char obj in str)
    {
        try
        {
            chinesechar chinesechar = new chinesechar(obj);
            string t = chinesechar.pinyins[0].tostring();
            r += t.substring(0, t.length - 1);
        }
        catch
        {
            r += obj.tostring();
        }
    }
    return r;
}

创建获取汉字拼音首字母的方法：

/// <summary>
/// 汉字转化为拼音首字母
/// </summary>
/// <param name="str">汉字</param>
/// <returns>首字母</returns>
public static string getfirstpinyin(string str)
{
    string r = string.empty;
    foreach (char obj in str)
    {
        try
        {
            chinesechar chinesechar = new chinesechar(obj);
            string t = chinesechar.pinyins[0].tostring();
            r += t.substring(0, 1);
        }
        catch
        {
            r += obj.tostring();
        }
    }
    return r;
}

然后在“转拼音”按钮的点击事件中调用上述方法：

// 汉字转拼音
private void btn_one_click(object sender, eventargs e)
{
    string source = this.txt_chinesecharacter_one.text.trim();  // 得到输入的源字符
    string result = getpinyin(source);  // 调用方法，获取拼音
    this.txt_pinyin_one.text = result;
}

在“转首字母”按钮点击事件中调用上述方法：

// 转首字母
private void btn_two_click(object sender, eventargs e)
{
    string source = this.txt_chinesecharacter_one.text.trim();  // 得到输入的源字符
    string result = getfirstpinyin(source);  // 调用方法，获取拼音
    this.txt_pinyin_one.text = result;
}

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：

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：

// 汉字转拼音
private void btn_one_click(object sender, eventargs e)
{
    string source = this.txt_chinesecharacter_one.text.trim();  // 得到输入的源字符

    string result = string.empty;   // 转拼音的结果
    string temp = string.empty; // 下面foreach用到的临时变量
    foreach (char item in source)   // 遍历每个源字符
    {
        temp = getpinyin(item.tostring());  // 将每个字符转拼音
        // 处理：获取首字母大写、其余字母小写
        result += (string.format("{0}{1} ", temp.substring(0, 1).toupper(), temp.substring(1).tolower()));
    }

    //string result = getpinyin(source);  // 调用方法，获取拼音
    this.txt_pinyin_one.text = result;
}

　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：

//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
    };

然后定义拼音数组：

//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"
   };

然后定义转换字符串的方法：

/// <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 strconverttopinyin(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[i] <= asc) //判断汉字的拼音区编码是否在指定范围内
                                    {
                                        pystr += getname[i];//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
        }

　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。