Lazarus Pascal Requires Chilkat v11.7.0+

Extract PDF Text to a StringBuilder and Save to a File

See more PDF Text Extraction Examples

Demonstrates ExtractTextSb, which writes the extracted text to a StringBuilder instead of returning it as a JSON string. Use it for large documents. The JSON output still receives the quality report. 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.StringBuilder,
  Chilkat.Pdf,
  Chilkat.JsonObject;

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

procedure RunDemo;
var
  success: Boolean;
  pdf: TPdf;
  json: TJsonObject;
  sbText: TStringBuilder;
  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 long_report.pdf

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

  WriteLn('Number of pages: ' + pdf.NumPages);

  //  ExtractTextSb takes the same operation and options as ExtractText, but the text
  //  goes to a StringBuilder.  This avoids building a very large JSON string for
  //  documents with many pages.
  json := TJsonObject.Create;
  sbText := TStringBuilder.Create;
  jsonOut := TJsonObject.Create;

  success := pdf.ExtractTextSb('text',json,sbText,jsonOut);
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;

  WriteLn('Extracted ' + sbText.Length + ' characters.');

  //  Save the text to a file.
  success := sbText.WriteFile('qa_output/long_report.txt','utf-8',False);
  if (success = False) then
    begin
      WriteLn(sbText.LastErrorText);
      Exit;
    end;

  //  The JSON output does not contain the text, but it still has the quality report.
  WriteLn('Quality: ' + jsonOut.StringOf('quality.rating'));
  WriteLn('Pages with no text (need OCR): [' + jsonOut.StringOf('quality.pagesNeedingOcr') + ']');

  //  Sample output:

  //  Number of pages: 3
  //  Extracted 4522 characters.
  //  Quality: good
  //  Pages with no text (need OCR): []


  pdf.Free;
  json.Free;
  sbText.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.