Java Requires Chilkat v11.7.0+

Clipped, Off-Page and White-on-White Text in PDF Extraction

See more PDF Text Extraction Examples

Demonstrates the "clippedText", "offPageText" and "obscuredText" filters. Text that a reader never sees - hidden by a clipping path, outside the crop box, or drawn in the same color as the box beneath it - is excluded by default, and the quality report notes what was skipped. Each kind can be included. Chilkat2 Java

import com.chilkatsoft.chilkat2.ChilkatException;
import com.chilkatsoft.chilkat2.JsonObject;
import com.chilkatsoft.chilkat2.Pdf;

public class ChilkatExample {

    public static void main(String[] args) {
        // 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 hidden_text.pdf

        Pdf pdf = new Pdf();
        try {
            pdf.loadFile("qa_data/pdf/hidden_text.pdf");
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        JsonObject json = new JsonObject();
        JsonObject jsonOut = new JsonObject();

        // The page has a visible paragraph plus three hidden lines: one drawn outside its clipping
        // rectangle, one below the crop box, and one in white on a white box.
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("---- default ----");
        System.out.println(jsonOut.stringOf("text"));

        // The quality report says what was left out.
        int i = 0;
        int count_i = jsonOut.sizeOfArray("quality.pages[0].issues");
        while (i < count_i) {
            jsonOut.setI(i);
            System.out.println("issue: " + jsonOut.stringOf("quality.pages[0].issues[i].code"));
            i = i + 1;
        }

        // Include everything.
        json.updateString("clippedText", "include");
        json.updateString("offPageText", "include");
        json.updateString("obscuredText", "include");
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("---- clippedText, offPageText, obscuredText: include ----");
        System.out.println(jsonOut.stringOf("text"));

        // Sample output:

        // ---- default ----
        // Visible Text
        //
        // This paragraph is visible. The page also carries three kinds of text a reader never sees.
        //
        // End of the visible text.
        // issue: obscuredTextSkipped
        // issue: clippedTextSkipped
        // ---- clippedText, offPageText, obscuredText: include ----
        // Visible Text
        //
        // This paragraph is visible. The page also carries three kinds of text a reader never sees.
        //
        // CLIPPED: this line is drawn outside its clipping rectangle.
        //
        // OBSCURED: this line is white on a white box.
        //
        // End of the visible text.
        //
        // OFFPAGE: this line sits below the crop box.
    }
}