Android™ Requires Chilkat v11.7.0+

Extract a PDF Table with Merged Cells

See more PDF Text Extraction Examples

Demonstrates how merged cells are reported by the "tables" operation: a header cell that spans several columns has colSpan greater than 1, and a row label that spans several rows has rowSpan greater than 1. Also shows the minRows and minColumns options. Android™

// Important: Don't forget to include the call to System.loadLibrary
// as shown at the bottom of this code sample.
package com.test;

import android.app.Activity;
import com.chilkatsoft.*;

import android.widget.TextView;
import android.os.Bundle;

public class SimpleActivity extends Activity {

  private static final String TAG = "Chilkat";

  // Called when the activity is first created.
  @Override
  public void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);

    boolean 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 spans_table.pdf

    CkPdf pdf = new CkPdf();
    success = pdf.LoadFile("qa_data/pdf/spans_table.pdf");
    if (success == false) {
        Log.i(TAG, pdf.lastErrorText());
        return;
        }

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

    //  Grids smaller than minRows x minColumns are not reported as tables.  The defaults are 2 and 2.
    //  Setting them higher skips small boxes that are not really tables.
    json.UpdateInt("minRows",3);
    json.UpdateInt("minColumns",3);

    success = pdf.ExtractText("tables",json,jsonOut);
    if (success == false) {
        Log.i(TAG, pdf.lastErrorText());
        return;
        }

    Log.i(TAG, "Tables found: " + String.valueOf(jsonOut.IntOf("count")));
    Log.i(TAG, String.valueOf(jsonOut.IntOf("tables[0].rows")) + " rows x " + String.valueOf(jsonOut.IntOf("tables[0].columns")) + " columns");

    //  A merged cell is reported once, at its top-left position, with its spans.
    //  The positions it covers have no cell of their own.
    int rowSpan;
    int colSpan;
    int j = 0;
    int count_j = jsonOut.SizeOfArray("tables[0].cells");
    while (j < count_j) {
        jsonOut.put_J(j);
        rowSpan = jsonOut.IntOf("tables[0].cells[j].rowSpan");
        colSpan = jsonOut.IntOf("tables[0].cells[j].colSpan");
        if ((rowSpan > 1) or (colSpan > 1)) {
            Log.i(TAG, "row " + String.valueOf(jsonOut.IntOf("tables[0].cells[j].row")) + ", col " + String.valueOf(jsonOut.IntOf("tables[0].cells[j].col")) + ": \""
                 + jsonOut.stringOf("tables[0].cells[j].text") + "\" spans " + String.valueOf(rowSpan) + " row(s) and " + String.valueOf(colSpan) + " column(s)");
            }

        j = j + 1;
        }

    //  Sample output:

    //  Tables found: 1
    //  6 rows x 6 columns
    //  row 0, col 0: "Area" spans 2 row(s) and 1 column(s)
    //  row 0, col 1: "City" spans 2 row(s) and 1 column(s)
    //  row 0, col 2: "First Half" spans 1 row(s) and 2 column(s)
    //  row 0, col 4: "Second Half" spans 1 row(s) and 2 column(s)
    //  row 2, col 0: "East" spans 2 row(s) and 1 column(s)
    //  row 4, col 0: "West" spans 2 row(s) and 1 column(s)

  }

  static {
      System.loadLibrary("chilkat");

      // Note: If the incorrect library name is passed to System.loadLibrary,
      // then you will see the following error message at application startup:
      //"The application <your-application-name> has stopped unexpectedly. Please try again."
  }
}