C#教程

关注公众号 jb51net

关闭
首页 > 软件编程 > C#教程 > C#汉字转拼音

C#使用正则表达式实现汉字转拼音

作者:wenchm

这篇文章主要为大家详细介绍了C#如何使用正则表达式实现汉字转拼音的功能,文中的示例代码讲解详细,感兴趣的小伙伴可以跟随小编一起学习一下

一、正则表达式基础 

在C#中使用正则表达式,首先要创建正则表达式对象,正则表达式对象的构造方法中接收一个正则表达式字符串,对象创建后,可以调用对象的IsMatch方法,对该方法中的字符串进行验证,如果验证成功将返回true,如果不成功则返回false。

调用字符串对象的ToCharArray方法,可以根据当前的字符串对象中的字符内容,产生一个新的字符数组。字符串对象的ToCharArray方法:

//使用正则表达式
Regex reg =new Regex("^[\u4e00-\u9fa5]$"); //创建正则表达式对象
bool P_bl=reg.IsMatch("中");//调用IsMatch方法判断字符串中的字符是否为汉字
//字符串转字符数组
string str ="abc";
char[]mChar =str.ToCharArray();

正则表达式经常用于数字或字符串等信息的验证及截取。

适当地使用正则表达式,可以让字符串的处理变得更轻松。

二、实例

使用正则表达式,可以方便地操作字符串,对字符串进行验证或提取。在本实例中,使用正则表达式验证字符串中的每一个字符是否为汉字,如果为汉字则查找汉字的拼音。

1.程序入口Form1.cs

//汉字转拼音
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 = "汉字转拼音";
           
        }
        /// <summary>
        /// 调用拼音类的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.类库PinYin.cs

using System.Text;
using System.Text.RegularExpressions;
 
namespace _038
{
    internal partial class PinYin
    {
        /// <summary>
        /// 定义拼音区编码数组
        /// </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>
        /// 定义拼音数组
        /// </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>
        /// 将汉字转换拼音的方法
        /// </summary>
        /// <param name="str">汉字字符串</param>
        /// <returns>拼音字符串</returns>
        public static string GetABC(string str)
        {
            Regex reg = new("^[\u4e00-\u9fa5]$");  //验证输入是否为汉字
            byte[] arr = new byte[2];              //定义字节数组
            string pystr = "";                     //定义字符串变量用于返回拼音
            char[] mChar = str.ToCharArray();      //获取汉字对应的字符数组
            return GetStr(mChar, pystr, reg, arr); //返回获取到的汉字拼音
        }
 
        private static string GetStr(char[] mChar, string pystr, Regex reg, byte[] arr)
        {
            ArgumentNullException.ThrowIfNull(arr); //null检查
 
            for (int j = 0; j < mChar.Length; j++)
            {
                if (reg.IsMatch(mChar[j].ToString()))//如果输入的是汉字
                {
                    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)//判断汉字的拼音区编码是否在指定范围内
                                    {
                                        pystr += getStr[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;
        }
 
        //[GeneratedRegex("^[\u4e00-\u9fa5]$")]
        //private static partial Regex MyRegex();
    }
}

三、生成效果

四、实例中的知识点 

1.Regex

2.ToCharArray()

3.Regex.IsMatch 方法

(1)定义

命名空间:

System.Text.RegularExpressions

程序集:

System.Text.RegularExpressions.dll

指示正则表达式在输入字符串中是否找到匹配项。

(2)重载

(3)IsMatch(String)

指示 Regex 构造函数中指定的正则表达式在指定的输入字符串中是否找到了匹配项。

public bool IsMatch (string input);

参数input    String    要搜索匹配项的字符串。

返回Boolean    

如果正则表达式找到匹配项,则为 true;否则为 false。

例外ArgumentNullException    

input 为 null。

RegexMatchTimeoutException

发生超时。 有关超时的详细信息,请参阅“备注”部分。

// 正则表达式实例
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) 正则表达式模式为:

^[a-zA-Z0-9]\d{2}[a-zA-Z0-9](-\d{3}){2}[A-Za-z0-9]$

(5)解释正则表达式模式

(6)正则表达式语言

- .NET | Microsoft Learn  https://learn.microsoft.com/zh-cn/dotnet/standard/base-types/regular-expression-language-quick-reference

(7)GetBytes()

详见本文作者的其它文章,C#中汉字转区位码

到此这篇关于C#使用正则表达式实现汉字转拼音的文章就介绍到这了,更多相关C#汉字转拼音内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家!

您可能感兴趣的文章:
阅读全文