Android™ 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. 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 long_report.pdf

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

    Log.i(TAG, "Number of pages: " + String.valueOf(pdf.get_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.
    CkJsonObject json = new CkJsonObject();
    CkStringBuilder sbText = new CkStringBuilder();
    CkJsonObject jsonOut = new CkJsonObject();

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

    Log.i(TAG, "Extracted " + String.valueOf(sbText.get_Length()) + " characters.");

    //  Save the text to a file.
    success = sbText.WriteFile("qa_output/long_report.txt","utf-8",false);
    if (success == false) {
        Log.i(TAG, sbText.lastErrorText());
        return;
        }

    //  The JSON output does not contain the text, but it still has the quality report.
    Log.i(TAG, "Quality: " + jsonOut.stringOf("quality.rating"));
    Log.i(TAG, "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): []

  }

  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."
  }
}