Java 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. Java

import com.chilkatsoft.*;

public class ChilkatExample {

  static {
    try {
        System.loadLibrary("chilkat");
    } catch (UnsatisfiedLinkError e) {
      System.err.println("Native code library failed to load.\n" + e);
      System.exit(1);
    }
  }

  public static void main(String argv[])
  {
    boolean 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

    CkPdf pdf = new CkPdf();
    success = pdf.LoadFile("qa_data/pdf/two_column_article.pdf");
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    CkJsonObject json = new CkJsonObject();
    CkJsonObject jsonOut = new CkJsonObject();

    //  With the default options the columns are detected, and the text of the left column
    //  comes before the text of the right column.
    success = pdf.ExtractText("text",json,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    System.out.println("Columns detected: " + jsonOut.IntOf("quality.pages[0].columns"));
    System.out.println("Reading order: " + jsonOut.stringOf("quality.pages[0].readingOrderSource"));
    System.out.println(jsonOut.stringOf("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.
    json.UpdateString("columns","none");
    json.UpdateString("layout","lines");
    success = pdf.ExtractText("text",json,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    System.out.println("---- columns: none ----");
    System.out.println(jsonOut.stringOf("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
    //  ...
  }
}