To wrap up this overview of how regular expressions are used in C# applications, the following is a set of useful expressions that have been used in other environments.[1]
[1] These expressions were taken from the Perl Cookbook by Tom Christiansen and Nathan Torkington (O'Reilly), and updated for the C# environment by Brad Merrill of Microsoft.
Matching roman numerals:
string p1 = "^m*(d?c{0,3}|c[dm])" + "(l?x{0,3}|x[lc])(v?i{0,3}|i[vx])$"; string t1 = "vii"; Match m1 = Regex.Match(t1, p1);
Swapping first two words:
string t2 = "the quick brown fox"; string p2 = @"(\S+)(\s+)(\S+)"; Regex x2 = new Regex(p2); string r2 = x2.Replace(t2, "$3$2$1", 1);
Matching "keyword = value" patterns:
string t3 = "myval = 3"; string p3 = @"(\w+)\s*=\s*(.*)\s*$"; Match m3 = Regex.Match(t3, p3);
Matching lines of at least 80 characters:
string t4 = "********************" + "******************************" + "******************************"; string p4 = ".{80,}"; Match m4 = Regex.Match(t4, p4);
Extracting date/time values (MM/DD/YY HH:MM:SS):
string t5 = "01/01/01 16:10:01"; string p5 = @"(\d+)/(\d+)/(\d+) (\d+):(\d+):(\d+)"; Match m5 = Regex.Match(t5, p5);
Changing directories (for Windows):
string t6 = @"C:\Documents and Settings\user1\Desktop\"; string r6 = Regex.Replace(t6, @"\\user1\\", @"\user2\");
Expanding (%nn) hex escapes:
string t7 = "%41"; // capital A string p7 = "%([0-9A-Fa-f][0-9A-Fa-f])"; // uses a MatchEvaluator delegate string r7 = Regex.Replace(t7, p7, HexConvert);
Deleting C comments (imperfectly):
string t8 = @" /* * this is an old cstyle comment block */ "; string p8 = @" /\* # match the opening delimiter .*? # match a minimal numer of characters \*/ # match the closing delimiter "; string r8 = Regex.Replace(t8, p8, "", RegexOptions.Singleline | RegexOptions.IgnorePatternWhitespace);
Removing leading and trailing whitespace:
string t9a = " leading"; string p9a = @"^\s+"; string r9a = Regex.Replace(t9a, p9a, ""); string t9b = "trailing "; string p9b = @"\s+$"; string r9b = Regex.Replace(t9b, p9b, "");
Turning "\" followed by "n" into a real newline:
string t10 = @"\ntest\n"; string r10 = Regex.Replace(t10, @"\\n", "\n");
Detecting IP addresses:
string t11 = "55.54.53.52"; string p11 = "^" + @"([01]?\d\d|2[0-4]\d|25[0-5])\." + @"([01]?\d\d|2[0-4]\d|25[0-5])\." + @"([01]?\d\d|2[0-4]\d|25[0-5])\." + @"([01]?\d\d|2[0-4]\d|25[0-5])" + "$"; Match m11 = Regex.Match(t11, p11);
Removing leading path from filename:
string t12 = @"c:\file.txt"; string p12 = @"^.*\\"; string r12 = Regex.Replace(t12, p12, "");
Joining lines in multiline strings:
string t13 = @"this is a split line"; string p13 = @"\s*\r?\n\s*"; string r13 = Regex.Replace(t13, p13, " ");
Extracting all numbers from a string:
string t14 = @" test 1 test 2.3 test 47 "; string p14 = @"(\d+\.?\d*|\.\d+)"; MatchCollection mc14 = Regex.Matches(t14, p14);
Finding all caps words:
string t15 = "This IS a Test OF ALL Caps"; string p15 = @"(\b[^\Wa-z0-9_]+\b)"; MatchCollection mc15 = Regex.Matches(t15, p15);
Finding all lowercase words:
string t16 = "This is A Test of lowercase"; string p16 = @"(\b[^\WA-Z0-9_]+\b)"; MatchCollection mc16 = Regex.Matches(t16, p16);
Finding all initial caps words:
string t17 = "This is A Test of Initial Caps"; string p17 = @"(\b[^\Wa-z0-9_][^\WA-Z0-9_]*\b)"; MatchCollection mc17 = Regex.Matches(t17, p17);
Finding links in simple HTML:
string t18 = @" <html> <a href=""http://windows.oreilly.com/news/first.htm"">first tag text</a> <a href=""http://windows.oreilly.com/news/next.htm"">next tag text</a> </html> "; string p18 = @"<A[^>]*?HREF\s*=\s*[""']?" + @"([^'"" >]+?)[ '""]?>"; MatchCollection mc18 = Regex.Matches(t18, p18, RegexOptions.IgnoreCase | RegexOptions.Singleline);
Finding middle initials:
string t19 = "Hanley A. Strappman"; string p19 = @"^\S+\s+(\S)\S*\s+\S"; Match m19 = Regex.Match(t19, p19);
Changing inch marks to quotation marks:
string t20 = @"2' 2"" "; string p20 = "\"([^\"]*)"; string r20 = Regex.Replace(t20, p20, "``$1''");