Lazarus Pascal

Convert a Text File from utf-8 to Windows-1252

Convert a text file from one character encoding to another. 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;

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

procedure RunDemo;
var
  success: Boolean;
  sb: TStringBuilder;

begin
  success := False;

  //  It's really simple:  Just load from one charset, save using another.

  sb := TStringBuilder.Create;

  //  In this case, my test file has some norwegian chars in the utf-8 encoding
  success := sb.LoadFile('qa_data/txt/norwegian_chars.txt','utf-8');

  //  We could just as well write over the file we just read in.
  //  (But I don't want to do that for my example..)
  success := sb.WriteFile('qa_output/norwegian_chars.txt','windows-1252',False);

  //  Note:  Windows-1252 is a 1-byte per char encoding, which means it's only capable of representing
  //  those chars in Western European languages.   See https://en.wikipedia.org/wiki/Windows-1252
  //  
  //  utf-8 is an encoding that can handle chars in any language, including Chinese, Korean, Japanese, Arabic, Hebrew, Greek, etc.
  //  If a text file contains chars in these other languages, obviously it cannot be converted to windows-1252 because
  //  there are only 256 chars that can possibly be represented in a 1-byte per char encoding.


  sb.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.