Java Requires Chilkat v11.7.0+

Code Blocks and Code Spans in PDF to Markdown

See more PDF Text Extraction Examples

Demonstrates how monospaced text is converted by the "markdown" operation: a monospaced block becomes a fenced code block and a monospaced run inside a sentence becomes a code span. Set "code" to false to treat it as ordinary text. 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 code_block.pdf

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

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

        try {
            pdf.extractText("markdown", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("---- default (code: true) ----");
        System.out.println(jsonOut.stringOf("markdown"));

        json.updateBool("code", false);
        try {
            pdf.extractText("markdown", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("---- code: false ----");
        System.out.println(jsonOut.stringOf("markdown"));

        // Sample output:

        // ---- default (code: true) ----
        // <!-- page 1 -->
        //
        // # Extracting Text
        //
        // Load the PDF and call `ExtractText` with the operation and an options object. The result is returned as JSON:
        //
        // ```
        // new Pdf pdf;
        // success = pdf.LoadFile("report.pdf");
        // new JsonObject json;
        // new JsonObject jsonOut;
        // success = pdf.ExtractText("text",json,jsonOut);
        // println jsonOut.StringOf("text");
        // ```
        //
        // An empty options object extracts every page with the default clean-up. Set `pages` to limit the extraction.
        // ---- code: false ----
        // <!-- page 1 -->
        //
        // # Extracting Text
        //
        // Load the PDF and call ExtractText with the operation and an options object. The result is returned as JSON:
        //
        // new Pdf pdf; success = pdf.LoadFile("report.pdf"); new JsonObject json; new JsonObject jsonOut; success = pdf.ExtractText("text",json,jsonOut); println jsonOut.StringOf("text");
        //
        // An empty options object extracts every page with the default clean-up. Set pages to limit the extraction.
    }
}