.NET正则表达式的最佳用法

using System;
using System.Diagnostics;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      Stopwatch sw;
      string[] addresses = { "AAAAAAAAAAA@contoso.com",
                             "AAAAAAAAAAaaaaaaaaaa!@contoso.com" };
      // The following regular expression should not actually be used to
      // validate an email address.
      string pattern = @"^[0-9A-Z]([-.\w]*[0-9A-Z])*$";
      string input;

      foreach (var address in addresses) {
         string mailBox = address.Substring(0, address.IndexOf("@"));
         int index = 0;
         for (int ctr = mailBox.Length - 1; ctr >= 0; ctr--) {
            index++;

            input = mailBox.Substring(ctr, index);
            sw = Stopwatch.StartNew();
            Match m = Regex.Match(input, pattern, RegexOptions.IgnoreCase);
            sw.Stop();
            if (m.Success)
               Console.WriteLine("{0,2}. Matched '{1,25}' in {2}",
                                 index, m.Value, sw.Elapsed);
            else
               Console.WriteLine("{0,2}. Failed  '{1,25}' in {2}",
                                 index, input, sw.Elapsed);
         }
         Console.WriteLine();
      }
   }
}

// The example displays output similar to the following:
//     1. Matched '                        A' in 00:00:00.0007122
//     2. Matched '                       AA' in 00:00:00.0000282
//     3. Matched '                      AAA' in 00:00:00.0000042
//     4. Matched '                     AAAA' in 00:00:00.0000038
//     5. Matched '                    AAAAA' in 00:00:00.0000042
//     6. Matched '                   AAAAAA' in 00:00:00.0000042
//     7. Matched '                  AAAAAAA' in 00:00:00.0000042
//     8. Matched '                 AAAAAAAA' in 00:00:00.0000087
//     9. Matched '                AAAAAAAAA' in 00:00:00.0000045
//    10. Matched '               AAAAAAAAAA' in 00:00:00.0000045
//    11. Matched '              AAAAAAAAAAA' in 00:00:00.0000045
//
//     1. Failed  '                        !' in 00:00:00.0000447
//     2. Failed  '                       a!' in 00:00:00.0000071
//     3. Failed  '                      aa!' in 00:00:00.0000071
//     4. Failed  '                     aaa!' in 00:00:00.0000061
//     5. Failed  '                    aaaa!' in 00:00:00.0000081
//     6. Failed  '                   aaaaa!' in 00:00:00.0000126
//     7. Failed  '                  aaaaaa!' in 00:00:00.0000359
//     8. Failed  '                 aaaaaaa!' in 00:00:00.0000414
//     9. Failed  '                aaaaaaaa!' in 00:00:00.0000758
//    10. Failed  '               aaaaaaaaa!' in 00:00:00.0001462
//    11. Failed  '              aaaaaaaaaa!' in 00:00:00.0002885
//    12. Failed  '             Aaaaaaaaaaa!' in 00:00:00.0005780
//    13. Failed  '            AAaaaaaaaaaa!' in 00:00:00.0011628
//    14. Failed  '           AAAaaaaaaaaaa!' in 00:00:00.0022851
//    15. Failed  '          AAAAaaaaaaaaaa!' in 00:00:00.0045864
//    16. Failed  '         AAAAAaaaaaaaaaa!' in 00:00:00.0093168
//    17. Failed  '        AAAAAAaaaaaaaaaa!' in 00:00:00.0185993
//    18. Failed  '       AAAAAAAaaaaaaaaaa!' in 00:00:00.0366723
//    19. Failed  '      AAAAAAAAaaaaaaaaaa!' in 00:00:00.1370108
//    20. Failed  '     AAAAAAAAAaaaaaaaaaa!' in 00:00:00.1553966
//    21. Failed  '    AAAAAAAAAAaaaaaaaaaa!' in 00:00:00.3223372

public void OKButton_Click(object sender, EventArgs e)
{
   if (! String.IsNullOrEmpty(sourceCurrency.Text))
      if (RegexLib.IsValidCurrency(sourceCurrency.Text))
         PerformConversion();
      else
         status.Text = "The source currency value is invalid.";
}

using System;
using System.Text.RegularExpressions;

public class RegexLib
{
   public static bool IsValidCurrency(string currencyValue)
   {
      string pattern = @"\p{Sc}+\s*\d+";
      Regex currencyRegex = new Regex(pattern);
      return currencyRegex.IsMatch(currencyValue);
   }
}

using System;
using System.Text.RegularExpressions;

public class RegexLib
{
   public static bool IsValidCurrency(string currencyValue)
   {
      string pattern = @"\p{Sc}+\s*\d+";
      return Regex.IsMatch(currencyValue, pattern);
   }
}

using System;
using System.Diagnostics;
using System.IO;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      string pattern = @"\b(\w+((\r?\n)|,?\s))*\w+[.?:;!]";
      Stopwatch sw;
      Match match;
      int ctr;

      StreamReader inFile = new StreamReader(@".\Dreiser_TheFinancier.txt");
      string input = inFile.ReadToEnd();
      inFile.Close();

      // Read first ten sentences with interpreted regex.
      Console.WriteLine("10 Sentences with Interpreted Regex:");
      sw = Stopwatch.StartNew();
      Regex int10 = new Regex(pattern, RegexOptions.Singleline);
      match = int10.Match(input);
      for (ctr = 0; ctr <= 9; ctr++) {
         if (match.Success)
            // Do nothing with the match except get the next match.
            match = match.NextMatch();
         else
            break;
      }
      sw.Stop();
      Console.WriteLine("   {0} matches in {1}", ctr, sw.Elapsed);

      // Read first ten sentences with compiled regex.
      Console.WriteLine("10 Sentences with Compiled Regex:");
      sw = Stopwatch.StartNew();
      Regex comp10 = new Regex(pattern,
                   RegexOptions.Singleline | RegexOptions.Compiled);
      match = comp10.Match(input);
      for (ctr = 0; ctr <= 9; ctr++) {
         if (match.Success)
            // Do nothing with the match except get the next match.
            match = match.NextMatch();
         else
            break;
      }
      sw.Stop();
      Console.WriteLine("   {0} matches in {1}", ctr, sw.Elapsed);

      // Read all sentences with interpreted regex.
      Console.WriteLine("All Sentences with Interpreted Regex:");
      sw = Stopwatch.StartNew();
      Regex intAll = new Regex(pattern, RegexOptions.Singleline);
      match = intAll.Match(input);
      int matches = 0;
      while (match.Success) {
         matches++;
         // Do nothing with the match except get the next match.
         match = match.NextMatch();
      }
      sw.Stop();
      Console.WriteLine("   {0:N0} matches in {1}", matches, sw.Elapsed);

      // Read all sentences with compiled regex.
      Console.WriteLine("All Sentences with Compiled Regex:");
      sw = Stopwatch.StartNew();
      Regex compAll = new Regex(pattern,
                      RegexOptions.Singleline | RegexOptions.Compiled);
      match = compAll.Match(input);
      matches = 0;
      while (match.Success) {
         matches++;
         // Do nothing with the match except get the next match.
         match = match.NextMatch();
      }
      sw.Stop();
      Console.WriteLine("   {0:N0} matches in {1}", matches, sw.Elapsed);
   }
}
// The example displays the following output:
//       10 Sentences with Interpreted Regex:
//          10 matches in 00:00:00.0047491
//       10 Sentences with Compiled Regex:
//          10 matches in 00:00:00.0141872
//       All Sentences with Interpreted Regex:
//          13,443 matches in 00:00:01.1929928
//       All Sentences with Compiled Regex:
//          13,443 matches in 00:00:00.7635869
//
//       >compare1
//       10 Sentences with Interpreted Regex:
//          10 matches in 00:00:00.0046914
//       10 Sentences with Compiled Regex:
//          10 matches in 00:00:00.0143727
//       All Sentences with Interpreted Regex:
//          13,443 matches in 00:00:01.1514100
//       All Sentences with Compiled Regex:
//          13,443 matches in 00:00:00.7432921

using System;
using System.Reflection;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      RegexCompilationInfo SentencePattern =
                           new RegexCompilationInfo(@"\b(\w+((\r?\n)|,?\s))*\w+[.?:;!]",
                                                    RegexOptions.Multiline,
                                                    "SentencePattern",
                                                    "Utilities.RegularExpressions",
                                                    true);
      RegexCompilationInfo[] regexes = { SentencePattern };
      AssemblyName assemName = new AssemblyName("RegexLib, Version=1.0.0.1001, Culture=neutral, PublicKeyToken=null");
      Regex.CompileToAssembly(regexes, assemName);
   }
}

using System;
using System.IO;
using System.Text.RegularExpressions;
using Utilities.RegularExpressions;

public class Example
{
   public static void Main()
   {
      SentencePattern pattern = new SentencePattern();
      StreamReader inFile = new StreamReader(@".\Dreiser_TheFinancier.txt");
      string input = inFile.ReadToEnd();
      inFile.Close();

      MatchCollection matches = pattern.Matches(input);
      Console.WriteLine("Found {0:N0} sentences.", matches.Count);
   }
}
// The example displays the following output:
//      Found 13,443 sentences.

using System;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      string input = "This this word Sentence name Capital";
      string pattern = @"\b\p{Lu}\w*\b";
      foreach (Match match in Regex.Matches(input, pattern))
         Console.WriteLine(match.Value);

      Console.WriteLine();

      pattern = @"\b\p{Lu}(?>\w*)\b";
      foreach (Match match in Regex.Matches(input, pattern))
         Console.WriteLine(match.Value);
   }
}
// The example displays the following output:
//       This
//       Sentence
//       Capital
//
//       This
//       Sentence
//       Capital

using System;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      string pattern = @"^[0-9A-Z][-.\w]*(?<=[0-9A-Z])\$$";
      string[] partNos = { "A1C$", "A4", "A4$", "A1603D$", "A1603D#" };

      foreach (var input in partNos) {
         Match match = Regex.Match(input, pattern);
         if (match.Success)
            Console.WriteLine(match.Value);
         else
            Console.WriteLine("Match not found.");
      }
   }
}
// The example displays the following output:
//       A1C$
//       Match not found.
//       A4$
//       A1603D$
//       Match not found.

using System;
using System.Collections.Generic;
using System.IO;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      RegexUtilities util = new RegexUtilities();
      string title = "Doyle - The Hound of the Baskervilles.txt";
      try {
         var info = util.GetWordData(title);
         Console.WriteLine("Words:               {0:N0}", info.Item1);
         Console.WriteLine("Average Word Length: {0:N2} characters", info.Item2);
      }
      catch (IOException e) {
         Console.WriteLine("IOException reading file '{0}'", title);
         Console.WriteLine(e.Message);
      }
      catch (RegexMatchTimeoutException e) {
         Console.WriteLine("The operation timed out after {0:N0} milliseconds",
                           e.MatchTimeout.TotalMilliseconds);
      }
   }
}

public class RegexUtilities
{
   public Tuple<int, double> GetWordData(string filename)
   {
      const int MAX_TIMEOUT = 1000;   // Maximum timeout interval in milliseconds.
      const int INCREMENT = 350;      // Milliseconds increment of timeout.

      List<string> exclusions = new List<string>( new string[] { "a", "an", "the" });
      int[] wordLengths = new int[29];        // Allocate an array of more than ample size.
      string input = null;
      StreamReader sr = null;
      try {
         sr = new StreamReader(filename);
         input = sr.ReadToEnd();
      }
      catch (FileNotFoundException e) {
         string msg = String.Format("Unable to find the file '{0}'", filename);
         throw new IOException(msg, e);
      }
      catch (IOException e) {
         throw new IOException(e.Message, e);
      }
      finally {
         if (sr != null) sr.Close();
      }

      int timeoutInterval = INCREMENT;
      bool init = false;
      Regex rgx = null;
      Match m = null;
      int indexPos = 0;
      do {
         try {
            if (! init) {
               rgx = new Regex(@"\b\w+\b", RegexOptions.None,
                               TimeSpan.FromMilliseconds(timeoutInterval));
               m = rgx.Match(input, indexPos);
               init = true;
            }
            else {
               m = m.NextMatch();
            }
            if (m.Success) {
               if ( !exclusions.Contains(m.Value.ToLower()))
                  wordLengths[m.Value.Length]++;

               indexPos += m.Length + 1;
            }
         }
         catch (RegexMatchTimeoutException e) {
            if (e.MatchTimeout.TotalMilliseconds < MAX_TIMEOUT) {
               timeoutInterval += INCREMENT;
               init = false;
            }
            else {
               // Rethrow the exception.
               throw;
            }
         }
      } while (m.Success);

      // If regex completed successfully, calculate number of words and average length.
      int nWords = 0;
      long totalLength = 0;

      for (int ctr = wordLengths.GetLowerBound(0); ctr <= wordLengths.GetUpperBound(0); ctr++) {
         nWords += wordLengths[ctr];
         totalLength += ctr * wordLengths[ctr];
      }
      return new Tuple<int, double>(nWords, totalLength/nWords);
   }
}

using System;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      string input = "This is one sentence. This is another.";
      string pattern = @"\b(\w+[;,]?\s?)+[.?!]";

      foreach (Match match in Regex.Matches(input, pattern)) {
         Console.WriteLine("Match: '{0}' at index {1}.",
                           match.Value, match.Index);
         int grpCtr = 0;
         foreach (Group grp in match.Groups) {
            Console.WriteLine("   Group {0}: '{1}' at index {2}.",
                              grpCtr, grp.Value, grp.Index);
            int capCtr = 0;
            foreach (Capture cap in grp.Captures) {
               Console.WriteLine("      Capture {0}: '{1}' at {2}.",
                                 capCtr, cap.Value, cap.Index);
               capCtr++;
            }
            grpCtr++;
         }
         Console.WriteLine();
      }
   }
}
// The example displays the following output:
//       Match: 'This is one sentence.' at index 0.
//          Group 0: 'This is one sentence.' at index 0.
//             Capture 0: 'This is one sentence.' at 0.
//          Group 1: 'sentence' at index 12.
//             Capture 0: 'This ' at 0.
//             Capture 1: 'is ' at 5.
//             Capture 2: 'one ' at 8.
//             Capture 3: 'sentence' at 12.
//
//       Match: 'This is another.' at index 22.
//          Group 0: 'This is another.' at index 22.
//             Capture 0: 'This is another.' at 22.
//          Group 1: 'another' at index 30.
//             Capture 0: 'This ' at 22.
//             Capture 1: 'is ' at 27.
//             Capture 2: 'another' at 30.

using System;
using System.Text.RegularExpressions;

public class Example
{
   public static void Main()
   {
      string input = "This is one sentence. This is another.";
      string pattern = @"\b(?:\w+[;,]?\s?)+[.?!]";

      foreach (Match match in Regex.Matches(input, pattern)) {
         Console.WriteLine("Match: '{0}' at index {1}.",
                           match.Value, match.Index);
         int grpCtr = 0;
         foreach (Group grp in match.Groups) {
            Console.WriteLine("   Group {0}: '{1}' at index {2}.",
                              grpCtr, grp.Value, grp.Index);
            int capCtr = 0;
            foreach (Capture cap in grp.Captures) {
               Console.WriteLine("      Capture {0}: '{1}' at {2}.",
                                 capCtr, cap.Value, cap.Index);
               capCtr++;
            }
            grpCtr++;
         }
         Console.WriteLine();
      }
   }
}
// The example displays the following output:
//       Match: 'This is one sentence.' at index 0.
//          Group 0: 'This is one sentence.' at index 0.
//             Capture 0: 'This is one sentence.' at 0.
//
//       Match: 'This is another.' at index 22.
//          Group 0: 'This is another.' at index 22.
//             Capture 0: 'This is another.' at 22.