C#使用正則表達式實現(xiàn)漢字轉(zhuǎn)拼音

更新時間：2024年01月04日 09:07:52 作者：wenchm

這篇文章主要為大家詳細介紹了C#如何使用正則表達式實現(xiàn)漢字轉(zhuǎn)拼音的功能,文中的示例代碼講解詳細,感興趣的小伙伴可以跟隨小編一起學(xué)習(xí)一下

一、正則表達式基礎(chǔ)

在C#中使用正則表達式，首先要創(chuàng)建正則表達式對象，正則表達式對象的構(gòu)造方法中接收一個正則表達式字符串，對象創(chuàng)建后，可以調(diào)用對象的IsMatch方法，對該方法中的字符串進行驗證，如果驗證成功將返回true，如果不成功則返回false。

調(diào)用字符串對象的ToCharArray方法，可以根據(jù)當(dāng)前的字符串對象中的字符內(nèi)容，產(chǎn)生一個新的字符數(shù)組。字符串對象的ToCharArray方法：

//使用正則表達式
Regex reg =new Regex("^[\u4e00-\u9fa5]$"); //創(chuàng)建正則表達式對象
bool P_bl=reg.IsMatch("中");//調(diào)用IsMatch方法判斷字符串中的字符是否為漢字
//字符串轉(zhuǎn)字符數(shù)組
string str ="abc";
char[]mChar =str.ToCharArray();

正則表達式經(jīng)常用于數(shù)字或字符串等信息的驗證及截取。

適當(dāng)?shù)厥褂谜齽t表達式，可以讓字符串的處理變得更輕松。

二、實例

使用正則表達式，可以方便地操作字符串，對字符串進行驗證或提取。在本實例中，使用正則表達式驗證字符串中的每一個字符是否為漢字，如果為漢字則查找漢字的拼音。

1.程序入口Form1.cs

//漢字轉(zhuǎn)拼音
namespace _038
{
    public partial class Form1 : Form
    {
        private TextBox? textBox1;
        private TextBox? textBox2;
 
        public Form1()
        {
            InitializeComponent();
            Load += Form1_Load;
        }
 
        private void Form1_Load(object? sender, EventArgs e)
        {
            // 
            // textBox1
            // 
            textBox1 = new TextBox
            {
                Location = new Point(12, 20),
                Name = "textBox1",
                Size = new Size(310, 23),
                TabIndex = 0
            };
            textBox1.TextChanged += TextBox1_TextChanged;
            // 
            // textBox2
            // 
            textBox2 = new TextBox
            {
                Location = new Point(12, 49),
                Name = "textBox2",
                Size = new Size(310, 23),
                TabIndex = 1
            };
            // 
            // Form1
            // 
            AutoScaleDimensions = new SizeF(7F, 17F);
            AutoScaleMode = AutoScaleMode.Font;
            ClientSize = new Size(334, 91);
            Controls.Add(textBox2);
            Controls.Add(textBox1);
            Name = "Form1";
            StartPosition = FormStartPosition.CenterScreen;
            Text = "漢字轉(zhuǎn)拼音";
           
        }
        /// <summary>
        /// 調(diào)用拼音類的GetABC方法得到拼音字符串
        /// </summary>
        private void TextBox1_TextChanged(object? sender, EventArgs e)
        {
            textBox2!.Text = PinYin.GetABC(textBox1!.Text);
        }
    }
}

2.類庫PinYin.cs

using System.Text;
using System.Text.RegularExpressions;
 
namespace _038
{
    internal partial class PinYin
    {
        /// <summary>
        /// 定義拼音區(qū)編碼數(shù)組
        /// </summary>
        private static readonly int[] getValue =
                [
                -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
                ];
 
        /// <summary>
        /// 定義拼音數(shù)組
        /// </summary>
        private static readonly string[] getStr =
                [
                "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>
        /// 將漢字轉(zhuǎn)換拼音的方法
        /// </summary>
        /// <param name="str">漢字字符串</param>
        /// <returns>拼音字符串</returns>
        public static string GetABC(string str)
        {
            Regex reg = new("^[\u4e00-\u9fa5]$");  //驗證輸入是否為漢字
            byte[] arr = new byte[2];              //定義字節(jié)數(shù)組
            string pystr = "";                     //定義字符串變量用于返回拼音
            char[] mChar = str.ToCharArray();      //獲取漢字對應(yīng)的字符數(shù)組
            return GetStr(mChar, pystr, reg, arr); //返回獲取到的漢字拼音
        }
 
        private static string GetStr(char[] mChar, string pystr, Regex reg, byte[] arr)
        {
            ArgumentNullException.ThrowIfNull(arr); //null檢查
 
            for (int j = 0; j < mChar.Length; j++)
            {
                if (reg.IsMatch(mChar[j].ToString()))//如果輸入的是漢字
                {
                    arr = Encoding.Default.GetBytes(mChar[j].ToString());
                    int M1 = arr[0];
                    int M2 = arr[1];
                    int 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)//判斷漢字的拼音區(qū)編碼是否在指定范圍內(nèi)
                                    {
                                        pystr += getStr[i];//如果不超出范圍則獲取對應(yīng)的拼音
                                        break;
                                    }
                                }
                                break;
                        }
                    }
                }
                else//如果不是漢字
                {
                    pystr += mChar[j].ToString();         //如果不是漢字則返回
                }
            }
            return pystr;
        }
 
        //[GeneratedRegex("^[\u4e00-\u9fa5]$")]
        //private static partial Regex MyRegex();
    }
}

三、生成效果

四、實例中的知識點

1.Regex

2.ToCharArray()

3.Regex.IsMatch 方法

（1）定義

命名空間：

System.Text.RegularExpressions

程序集：

System.Text.RegularExpressions.dll

指示正則表達式在輸入字符串中是否找到匹配項。

（2）重載

（3）IsMatch(String)

指示 Regex 構(gòu)造函數(shù)中指定的正則表達式在指定的輸入字符串中是否找到了匹配項。

public bool IsMatch (string input);

參數(shù)input String 要搜索匹配項的字符串。

返回Boolean

如果正則表達式找到匹配項，則為 true；否則為 false。

例外ArgumentNullException

input 為 null。

RegexMatchTimeoutException

發(fā)生超時。有關(guān)超時的詳細信息，請參閱“備注”部分。

// 正則表達式實例
using System.Text.RegularExpressions;
 
namespace ConsoleApp3
{
    public partial class Example
    {
        public static void Main()
        {
            string[] partNumbers = { "1298-673-4192", "A08Z-931-468A",
                              "_A90-123-129X", "12345-KKA-1230",
                              "0919-2893-1256" };
            Regex rgx = MyRegex();
            foreach (string partNumber in partNumbers)
                Console.WriteLine("{0} {1} a valid part number.",
                                  partNumber,
                                  rgx.IsMatch(partNumber) ? "is" : "is not");
        }
 
        [GeneratedRegex(@"^[a-zA-Z0-9]\d{2}[a-zA-Z0-9](-\d{3}){2}[A-Za-z0-9]$")]
        private static partial Regex MyRegex();
    }
}
// The example displays the following output:
// 1298-673-4192 is a valid part number.
// A08Z-931-468A is a valid part number.
// _A90-123-129X is not a valid part number.
// 12345-KKA-1230 is not a valid part number.
// 0919-2893-1256 is not a valid part number.

（4）正則表達式模式為：