Pascal (Lazarus/Delphi)

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.

Pascal (Lazarus/Delphi)

program ChilkatDemo;

// Demonstrates using the Chilkat Pascal wrapper via the C bridge DLL.
// Builds as a console application under Lazarus (FPC) or Delphi.

{$IFDEF FPC}
  {$MODE DELPHI}
{$ENDIF}
{$APPTYPE CONSOLE}

uses
  {$IFDEF UNIX}
  cthreads,
  {$ENDIF}
  SysUtils,
  CkDllLoader,
  Chilkat.JsonObject,
  Chilkat.StringBuilder;

// ---------------------------------------------------------------------------

procedure RunDemo;
var
  success: Boolean;
  subject: string;
  pattern: string;
  sb: TStringBuilder;
  json: TJsonObject;
  timeoutMs: Integer;
  numMatches: Integer;
  cap: string;
  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 := TStringBuilder.Create;
  sb.Append(subject);

  json := TJsonObject.Create;
  json.EmitCompact := False;

  timeoutMs := 2000;
  numMatches := sb.RegexMatch(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.
      WriteLn(sb.LastErrorText);
      Exit;
    end;

  //  Examine the matches:
  WriteLn(json.Emit());

  //  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 := json.SizeOfArray('match');
  while i < matchCount do
    begin
      WriteLn('Match ' + i + 1 + ':');
      json.I := i;
      j := 0;
      numCaptureGroups := json.SizeOfArray('match[i].group');
      while j < numCaptureGroups do
        begin
          json.J := j;
          cap := json.StringOf('match[i].group[j].cap');
          WriteLn(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


  sb.Free;
  json.Free;

end;

// ---------------------------------------------------------------------------

begin

  try
    RunDemo;
  except
    on E: Exception do
      WriteLn('Unhandled exception: ', E.ClassName, ': ', E.Message);
  end;

  WriteLn;
  {$IFDEF MSWINDOWS}
  WriteLn('Press Enter to exit...');
  ReadLn;
  {$ENDIF}
end.