C# 透過 正則表達式(正規表示式) 計算 中英數字的實際寬度(中文算2個字)進行字串切割/分割/分段 (子字串)

資料來源: https://blog.typeart.cc/JavaScript%E8%A8%88%E7%AE%97%E5%90%AB%E4%B8%AD%E8%8B%B1%E6%96%87%E5%AD%97%E7%9A%84%E5%AD%97%E4%B8%B2%E9%95%B7%E5%BA%A6/

https://www.cnblogs.com/PatrickChen/archive/2008/10/17/1313250.html

Code

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Text.RegularExpressions;
using System.Threading.Tasks;

namespace ConsoleApplication1
{
    class Program
    {
        static void pause()
        {
            Console.WriteLine("\nPress any key to terminate...");
            Console.ReadKey();
        }

        static int Wlen(String str)
        {
            string result = Regex.Replace(str, "[^\x00-\xff]", "xx");
            //x00~xff: ASCII code(0~255)
            //^: 正則取反向
            //所以只要非英數和英數標點符號 都從一個字變成兩個字
            return result.Length;
        }
        static string Wsubstring(string data,int start,int len)
        {
            string strResult = data;

            double m = start;
            double n = Math.Floor((float)len / 2); //函式會回傳小於等於所給數字的最大整數。
            if ((Wlen(data)-m-len)<=0)
            {
                try
                {
                    strResult = data.Substring((int)m);
                }
                catch
                {
                    strResult = "";
                }              
            }
            else
            {
                for (int i = (int)n; i < data.Length; i++)
                {
                    try
                    {
                        if (Wlen(data.Substring((int)m, i)) >= len)
                        {
                            strResult = data.Substring((int)m, (int)i);
                            break;
                        }
                    }
                    catch
                    {
                        strResult = data.Substring((int)m);
                    }

                }
            }
            return strResult;
        }
        static void Main(string[] args)
        {
            Console.WriteLine("jash中英文處理");
            Console.WriteLine("jash中英文處理".Length);
            Console.WriteLine(Wlen("jash中英文處理"));
            Console.WriteLine("0,5->" + Wsubstring("jash中英文處理", 0, 5));
            Console.WriteLine("0,6->" + Wsubstring("jash中英文處理", 0, 6));
            Console.WriteLine("0,7->" + Wsubstring("jash中英文處理", 0, 7));
            Console.WriteLine("0,8->" + Wsubstring("jash中英文處理", 0, 8));
            Console.WriteLine("");
            Console.WriteLine("1,5->" + Wsubstring("jash中英文處理", 1, 5));
            Console.WriteLine("1,6->" + Wsubstring("jash中英文處理", 1, 6));
            Console.WriteLine("1,7->" + Wsubstring("jash中英文處理", 1, 7));
            Console.WriteLine("1,8->" + Wsubstring("jash中英文處理", 1, 8));
            Console.WriteLine("");
            Console.WriteLine("2,5->" + Wsubstring("jash中英文處理", 2, 5));
            Console.WriteLine("2,6->" + Wsubstring("jash中英文處理", 2, 6));
            Console.WriteLine("2,7->" + Wsubstring("jash中英文處理", 2, 7));
            Console.WriteLine("2,8->" + Wsubstring("jash中英文處理", 2, 8));
            Console.WriteLine("");
            Console.WriteLine("3,5->" + Wsubstring("jash中英文處理", 3, 5));
            Console.WriteLine("3,6->" + Wsubstring("jash中英文處理", 3, 6));
            Console.WriteLine("3,7->" + Wsubstring("jash中英文處理", 3, 7));
            Console.WriteLine("3,8->" + Wsubstring("jash中英文處理", 3, 8));
            Console.WriteLine("");
            Console.WriteLine("4,5->" + Wsubstring("jash中英文處理", 4, 5));
            Console.WriteLine("4,6->" + Wsubstring("jash中英文處理", 4, 6));
            Console.WriteLine("4,7->" + Wsubstring("jash中英文處理", 4, 7));
            Console.WriteLine("4,8->" + Wsubstring("jash中英文處理", 4, 8));
            Console.WriteLine("");
            Console.WriteLine("5,5->" + Wsubstring("jash中英文處理", 5, 5));
            Console.WriteLine("5,6->" + Wsubstring("jash中英文處理", 5, 6));
            Console.WriteLine("5,7->" + Wsubstring("jash中英文處理", 5, 7));
            Console.WriteLine("5,8->" + Wsubstring("jash中英文處理", 5, 8));
            pause();

            /*Ans:
            jash中英文處理
            9
            14
            0,5->jash中
            0,6->jash中
            0,7->jash中英
            0,8->jash中英

            1,5->ash中
            1,6->ash中英
            1,7->ash中英
            1,8->ash中英文

            2,5->sh中英
            2,6->sh中英
            2,7->sh中英文
            2,8->sh中英文

            3,5->h中英
            3,6->h中英文
            3,7->h中英文
            3,8->h中英文處

            4,5->中英文
            4,6->中英文
            4,7->中英文處
            4,8->中英文處

            5,5->英文處
            5,6->英文處
            5,7->英文處理
            5,8->英文處理
            Press any key to terminate...
            */
        }
    }
}

PS.正規表示式/ 正規表達式教學

. 點，匹配任何字符
^ 開始錨，匹配字符串的開頭
$ 結束錨，匹配字符串的結尾
* 星號，匹配零個或多個（貪婪）
+ 加號，匹配一個或多個（貪婪）
？ 問題，匹配零或一（非貪婪）
[abc] 字符類，如果{‘a’，’b’，’c’}中的一個匹配則匹配
[^abc] 反相的類，如果不是{‘a’，’b’，’c’}中的一個，則匹配。注意：此功能當前在某些字符範圍內無效！
[a-zA-Z] 字符範圍，範圍的字符集{a-z | A-Z}
\s 空格，\t \f \r \n \v和空格
\S 非空白
\w 字母數字，[a-zA-Z0-9_]
\W 非字母數字
\d 位數字，[0-9]
\D 非數字

. Dot, matches any character
^ Start anchor, matches beginning of string
$ End anchor, matches end of string
* Asterisk, match zero or more (greedy)
+ Plus, match one or more (greedy)
? Question, match zero or one (non-greedy)
[abc] Character class, match if one of {‘a’, ‘b’, ‘c’}
[^abc] Inverted class, match if NOT one of {‘a’, ‘b’, ‘c’} NOTE: This feature is currently broken for some usage of character ranges!
[a-zA-Z] Character ranges, the character set of the ranges { a-z | A-Z }
\s Whitespace, \t \f \r \n \v and spaces
\S Non-whitespace
\w Alphanumeric, [a-zA-Z0-9_]
\W Non-alphanumeric
\d Digits, [0-9]
\D Non-digits