(Delphi DLL) Regular Expression with Capture Groups

See more Regular Expressions Examples

Note: Chilkat uses PCRE2. See PCRE2 Regular Expressions
Also see: PCRE2 Performance

Demonstrates the following PCRE2 regular expression:

See the sample code below.

Name:\s+(\w+)\s+(\w+),\s+Email:\s+(\S+)

And apply it to this string:

Name: John Smith, Email: john.smith@example.com

Regex Components Explained

Part	Meaning	Matched Text
"Name:"	Matches the literal text "Name:"	"Name:"
"\s+"	Matches one or more whitespace characters (spaces, tabs, etc.)	(space)
"(\w+)"	Capture Group 1: One or more word characters ("a-zA-Z0-9_")	"John"
"\s+"	More whitespace	(space)
"(\w+)"	Capture Group 2: Another word (the last name)	"Smith"
","	A literal comma	","
"\s+"	Whitespace again	(space)
"Email:"	Matches the literal "Email:"	"Email:"
"\s+"	Whitespace	(space)
"(\S+)"	Capture Group 3: One or more non-whitespace characters	"john.smith@example.com"

Matches for Your Example String

String:

"Name: John Smith, Email: john.smith@example.com"

Regex Match Groups:

Group	Captured Value
Group 1	"John"
Group 2	"Smith"
Group 3	"john.smith@example.com"

Notes on Character Classes

\w matches [a-zA-Z0-9_] — so it doesn’t include punctuation like a period.
\S matches any non-whitespace character, so it’s good for capturing an email.

Note: This example requires Chilkat v11.1.0 or greater.

For more information, see https://www.chilkatsoft.com/chilkat_pcre2.asp

Chilkat for Delphi Downloads

Chilkat non-ActiveX DLL for Delphi

Chilkat ActiveX DLL for Delphi

* The examples here use the non-ActiveX DLL.

uses
    Winapi.Windows, Winapi.Messages, System.SysUtils, System.Variants, System.Classes, Vcl.Graphics,
    Vcl.Controls, Vcl.Forms, Vcl.Dialogs, Vcl.StdCtrls, JsonObject, StringBuilder;

...

procedure TForm1.Button1Click(Sender: TObject);
var
success: Boolean;
subject: PWideChar;
pattern: PWideChar;
sb: HCkStringBuilder;
json: HCkJsonObject;
timeoutMs: Integer;
numMatches: Integer;
cap: PWideChar;
i: Integer;
matchCount: Integer;
j: Integer;
numCaptureGroups: Integer;

begin
success := False;

subject := 'Name: John Smith, Email: john.smith@example.com';
pattern := 'Name:\\s+(\\w+)\\s+(\\w+),\\s+Email:\\s+(\\S+)';

sb := CkStringBuilder_Create();
CkStringBuilder_Append(sb,subject);

json := CkJsonObject_Create();
CkJsonObject_putEmitCompact(json,False);

timeoutMs := 2000;
numMatches := CkStringBuilder_RegexMatch(sb,pattern,json,timeoutMs);
if (numMatches < 0) then
  begin
    // Probably an error in the regular expression.
    // Suggestion: Use AI to help create and/or diagnose regular expressions.
    Memo1.Lines.Add(CkStringBuilder__lastErrorText(sb));
    Exit;
  end;

// Examine the matches:
Memo1.Lines.Add(CkJsonObject__emit(json));

// This is the JSON with the match information.
// See the JSON parsing code below to get the matched capture group values.

// Important:  Capture group 0 always contains the entire match — that is, the portion of the input string that matches the full regular expression.

// {
//   "match": [
//     {
//       "group": [
//         {
//           "cap": "Name: John Smith, Email: john.smith@example.com",
//           "idx": 0,
//           "len": 47
//         },
//         {
//           "cap": "John",
//           "idx": 6,
//           "len": 4
//         },
//         {
//           "cap": "Smith",
//           "idx": 11,
//           "len": 5
//         },
//         {
//           "cap": "john.smith@example.com",
//           "idx": 25,
//           "len": 22
//         }
//       ]
//     }
//   ]
// }

i := 0;
matchCount := CkJsonObject_SizeOfArray(json,'match');
while i < matchCount do
  begin
    Memo1.Lines.Add('Match ' + IntToStr(i + 1) + ':');
    CkJsonObject_putI(json,i);
    j := 0;
    numCaptureGroups := CkJsonObject_SizeOfArray(json,'match[i].group');
    while j < numCaptureGroups do
      begin
        CkJsonObject_putJ(json,j);
        cap := CkJsonObject__stringOf(json,'match[i].group[j].cap');
        Memo1.Lines.Add(IntToStr(j) + ': ' + cap);
        j := j + 1;
      end;

    i := i + 1;
  end;

// Capture group 0 always contains the entire match — that is, the portion of the input string that matches the full regular expression.

// Output

// Match 1:
// 0: Name: John Smith, Email: john.smith@example.com
// 1: John
// 2: Smith
// 3: john.smith@example.com

CkStringBuilder_Dispose(sb);
CkJsonObject_Dispose(json);

end;