CookBook
/*
* This is a conversion of some of the regular expressions listed in
* the Perl CookBook.
* compile this sample with the command line:
* csc /debug /r:System.Text.RegularExpressions.dll cookbook.cs
* This has been tested with Beta1 of the Framework SDK.
*/
using System.Text.RegularExpressions;
using System;
class Test
{
static void Main()
{
// Roman Numbers
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);
Console.WriteLine("Match=[" + m1 + "]");
// Swap 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$1", 1);
Console.WriteLine("Result=[" + r2 + "]");
// Keyword = Value
string t3 = "myval = 3";
string p3 = @"(\w+)\s*=\s*(.*)\s*$";
Match m3 = Regex.Match(t3, p3);
Console.WriteLine("Group1=[" + m1.Group(1) + "]");
Console.WriteLine("Group2=[" + m1.Group(2) + "]");
// Line of at least 80 chars
string t4 = "********************"
+ "******************************"
+ "******************************";
string p4 = ".{80,}";
Match m4 = Regex.Match(t4, p4);
Console.WriteLine("if line >= 80 is = " + m1.Success + "]");
// 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);
Console.WriteLine("M5=" + m5);
for (int i = 1; i <= 6; i++)
Console.WriteLine("Group" + i + "=[" + m5.Group(i) + "]");
// 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";
string p7 = "%([0-9A-Fa-f][0-9A-Fa-f])";
string r7 = Regex.Replace(t7, p7, HexConvert);
Console.WriteLine("R7=" + r7);
// deleting C comments (imperfectly)
string t8 = @"
/*
* this is an old cstyle comment block
*/
foo();
";
string p8 = @"
/\* # match the opening delimiter
.*? # match a minimal numer of chracters
\*/ # match the closing delimiter
";
string r8 = Regex.Replace(t8, p8, "", "xs");
Console.WriteLine("r8="+r8);
// Removing leading and trailing whitespace
string t9a = " leading";
string p9a = @"^\s+";
string r9a = Regex.Replace(t9a, p9a, "");
Console.WriteLine("r9b=" + r9a);
string t9b = "trailing ";
string p9b = @"\s+$";
string r9b = Regex.Replace(t9b, p9b, "");
Console.WriteLine("r9b=" + r9b);
// turning \ followed by n into a real newline
string t10 = @"\ntest\n";
string r10 = Regex.Replace(t10, @"\\n", "\n");
Console.WriteLine("r10=" + r10);
// IP address
string t11 = "55.54.53.52";
string p11 = "^" +
@"([01]?\d\d|2[0-4]\d|25[0-5])\." +
@"([01]?\d\d|2[0-4]\d|25[0-5])\." +
@"([01]?\d\d|2[0-4]\d|25[0-5])\." +
@"([01]?\d\d|2[0-4]\d|25[0-5])" +
"$";
Match m11 = Regex.Match(t11, p11);
Console.WriteLine("M11=" + m11);
Console.WriteLine("Group1=" + m11.Group(1));
Console.WriteLine("Group2=" + m11.Group(2));
Console.WriteLine("Group3=" + m11.Group(3));
Console.WriteLine("Group4=" + m11.Group(4));
// removing leading path from filename
string t12 = @"c:\file.txt";
string p12 = @"^.*\\";
string r12 = Regex.Replace(t12, p12, "");
Console.WriteLine("r12=" + r12);
// joining lines in multiline strings
string t13 = @"this is
a split line";
string p13 = @"\s*\r?\n\s*";
string r13 = Regex.Replace(t13, p13, " ");
Console.WriteLine("r13=" + r13);
// 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);
foreach (Match m in mc14)
Console.WriteLine("Match=" + m);
// 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);
foreach (Match m in mc15)
Console.WriteLine("Match=" + m);
// find all lowercase words
string t16 = "This is A Test of lowercase";
string p16 = @"(\b[^\WA-Z0-9_]+\b)";
MatchCollection mc16 = Regex.Matches(t16, p16);
foreach (Match m in mc16)
Console.WriteLine("Match=" + m);
// find all initial caps
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);
foreach (Match m in mc17)
Console.WriteLine("Match=" + m);
// find links in simple html
string t18 = @"
";
string p18 = @"
MatchCollection mc18 = Regex.Matches(t18, p18, "si");
foreach (Match m in mc18)
{
Console.WriteLine("Match=" + m);
Console.WriteLine("Group1=" + m.Group(1));
}
// finding middle initial
string t19 = "Hanley A. Strappman";
string p19 = @"^\S+\s+(\S)\S*\s+\S";
Match m19 = Regex.Match(t19, p19);
Console.WriteLine("Initial=" + m19.Group(1));
// changing inch marks to quotes
string t20 = @"2' 2"" ";
string p20 = "\"([^\"]*)";
string r20 = Regex.Replace(t20, p20, "``$1''");
Console.WriteLine("Result=" + r20);
}
static int[] hexval = new int[128];
static Test()
{
InitHex();
}
static void InitHex()
{
hexval['0'] = 0;
hexval['1'] = 1;
hexval['2'] = 2;
hexval['3'] = 3;
hexval['4'] = 4;
hexval['5'] = 5;
hexval['6'] = 6;
hexval['7'] = 7;
hexval['8'] = 8;
hexval['9'] = 9;
hexval['A'] = 10;
hexval['B'] = 11;
hexval['C'] = 12;
hexval['D'] = 13;
hexval['E'] = 14;
hexval['F'] = 15;
hexval['a'] = 10;
hexval['b'] = 11;
hexval['c'] = 12;
hexval['d'] = 13;
hexval['e'] = 14;
hexval['f'] = 15;
}
static MatchEvaluator HexConvert = new MatchEvaluator(Hex);
static string Hex(Match m)
{
string s = m.Group(1).ToString();
int i0 = hexval[s[0]];
int i1 = hexval[s[1]];
string r = new string((char)((i0 << 4) | i1),1);
return r;
}
}
