Java Requires Chilkat v11.7.0+

Search for Text in a PDF

See more PDF Text Extraction Examples

Demonstrates the "search" operation, which finds every occurrence of a string in a PDF and returns each match with its page number and the text around it. Matching ignores case unless caseSensitive is true. 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 three-page PDF used in this example is available at search_context.pdf

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

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

    //  The string to find.
    json.UpdateString("query","chilkat");

    //  The number of characters returned before and after each match.  The default is 40.
    json.UpdateInt("context",30);

    success = pdf.ExtractText("search",json,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    //  "count" is the number of matches.  Each match has the page, the matched text as it appears
    //  in the PDF, and the text before and after it.
    System.out.println("Matches: " + jsonOut.IntOf("count"));

    int i = 0;
    int count_i = jsonOut.SizeOfArray("matches");
    while (i < count_i) {
        jsonOut.put_I(i);
        System.out.println("page " + jsonOut.IntOf("matches[i].page") + ": ..." + jsonOut.stringOf("matches[i].before") + "[" + jsonOut.stringOf("matches[i].text")
             + "]" + jsonOut.stringOf("matches[i].after") + "...");
        i = i+1;
        }

    //  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
    json.UpdateBool("caseSensitive",true);
    json.UpdateString("query","Chilkat");
    success = pdf.ExtractText("search",json,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    System.out.println("Case-sensitive matches for Chilkat: " + jsonOut.IntOf("count"));

    //  Sample output:

    //  Matches: 5
    //  page 1: ...[Chilkat] River Field Notes The Chilkat...
    //  page 1: ...Chilkat River Field Notes The [Chilkat] River runs for about fifty mi...
    //  page 2: ...DAY ONE: UPPER [CHILKAT] FLATS Clear and cold, minus e...
    //  page 2: ...he river is sometimes spelled [chilkat] in older records, and the val...
    //  page 3: ...y because the fish run on the [Chilkat] was thinning. Two tagged bird...
    //  Case-sensitive matches for Chilkat: 3
  }
}