Delphi DLL Requires Chilkat v11.7.0+

Extract Text from a Two-Column PDF

See more PDF Text Extraction Examples

Demonstrates how multi-column pages are read. By default the columns are detected and each column is read top to bottom before the next ("columns": "auto"); "columns": "none" reads the full page width line by line, which interleaves the columns. The quality report tells how many columns were found. Delphi DLL

var
success: Boolean;
pdf: HCkPdf;
json: HCkJsonObject;
jsonOut: HCkJsonObject;

begin
success := False;

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

//  The two-column PDF used in this example is available at two_column_article.pdf

pdf := CkPdf_Create();
success := CkPdf_LoadFile(pdf,'qa_data/pdf/two_column_article.pdf');
if (success = False) then
  begin
    Memo1.Lines.Add(CkPdf__lastErrorText(pdf));
    Exit;
  end;

json := CkJsonObject_Create();
jsonOut := CkJsonObject_Create();

//  With the default options the columns are detected, and the text of the left column
//  comes before the text of the right column.
success := CkPdf_ExtractText(pdf,'text',json,jsonOut);
if (success = False) then
  begin
    Memo1.Lines.Add(CkPdf__lastErrorText(pdf));
    Exit;
  end;

Memo1.Lines.Add('Columns detected: ' + IntToStr(CkJsonObject_IntOf(jsonOut,'quality.pages[0].columns')));
Memo1.Lines.Add('Reading order: ' + CkJsonObject__stringOf(jsonOut,'quality.pages[0].readingOrderSource'));
Memo1.Lines.Add(CkJsonObject__stringOf(jsonOut,'text'));

//  "none" switches column detection off: the page is read across its full width, line by line,
//  so each output line holds a line of the left column followed by a line of the right column.
//  This is rarely wanted, but it shows what the detection does.
CkJsonObject_UpdateString(json,'columns','none');
CkJsonObject_UpdateString(json,'layout','lines');
success := CkPdf_ExtractText(pdf,'text',json,jsonOut);
if (success = False) then
  begin
    Memo1.Lines.Add(CkPdf__lastErrorText(pdf));
    Exit;
  end;

Memo1.Lines.Add('---- columns: none ----');
Memo1.Lines.Add(CkJsonObject__stringOf(jsonOut,'text'));

//  Sample output (abbreviated):

//  Columns detected: 2
//  Reading order: visual
//  The Harbor Lighthouse, Season Two
//  
//  The harbor lighthouse was built in 1874 to mark the entrance to the inner channel. It operated continuously until 1968, ...
//  
//  The restoration society took ownership in 2021 with three goals: ...
//  ...
//  The lantern room frame was stripped, primed and repainted in the original dark green. ...
//  ...
//  ---- columns: none ----
//  The Harbor Lighthouse, Season Two
//  The harbor lighthouse was built in 1874 to The lantern room frame was stripped, primed
//  mark the entrance to the inner channel. It and repainted in the original dark green. New
//  ...

CkPdf_Dispose(pdf);
CkJsonObject_Dispose(json);
CkJsonObject_Dispose(jsonOut);