Lazarus Pascal Requires Chilkat v11.7.0+

Rejoin Words Hyphenated at Line Ends

See more PDF Text Extraction Examples

Demonstrates the "dehyphenate" clean-up option (true by default). A word broken at the end of a line ("docu-" / "ment") is rejoined, while a hyphen that belongs to the word ("self-service") is kept. Set the option to false to keep the lines exactly as printed. Lazarus Pascal

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.Pdf,
  Chilkat.JsonObject;

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

procedure RunDemo;
var
  success: Boolean;
  pdf: TPdf;
  json: TJsonObject;
  jsonOut: TJsonObject;

begin
  success := False;

  //  This example requires the Chilkat API to have been previously unlocked.
  //  See Global Unlock Sample for sample code.

  //  The PDF used in this example is available at hyphenated.pdf

  pdf := TPdf.Create;
  success := pdf.LoadFile('qa_data/pdf/hyphenated.pdf');
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;

  json := TJsonObject.Create;
  jsonOut := TJsonObject.Create;

  //  The paragraph breaks "document", "self-service", "underlying" and "re-issued" at line ends.
  //  The default rejoins them.  "self-service" keeps its hyphen because the word appears with it,
  //  unbroken, elsewhere on the page; "re-issued" appears nowhere else, so it becomes "reissued".
  success := pdf.ExtractText('text',json,jsonOut);
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;
  WriteLn('---- default (dehyphenate: true) ----');
  WriteLn(jsonOut.StringOf('text'));

  json.UpdateBool('dehyphenate',False);
  success := pdf.ExtractText('text',json,jsonOut);
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;
  WriteLn('---- dehyphenate: false ----');
  WriteLn(jsonOut.StringOf('text'));

  //  Sample output:

  //  ---- default (dehyphenate: true) ----
  //  Self-Service Kiosk Notes
  //  
  //  The new self-service kiosk in the lobby prints a visitor badge from the document number on the reservation. Staff should direct first-time visitors to the self-service kiosk rather than the desk, and should keep the paper tray topped up. The underlying software restarts itself overnight; a badge that fails to print is reissued at the desk on request.
  //  ---- dehyphenate: false ----
  //  Self-Service Kiosk Notes
  //  
  //  The new self-service kiosk in the lobby prints a visitor badge from the docu- ment number on the reservation. Staff should direct first-time visitors to the self- service kiosk rather than the desk, and should keep the paper tray topped up. The under- lying software restarts itself overnight; a badge that fails to print is re- issued at the desk on request.


  pdf.Free;
  json.Free;
  jsonOut.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.