questions.directcontent.InterpretOCR.java Source code

Introduction

Here is the source code for questions.directcontent.InterpretOCR.java

Source

/*
 * This example was written by Bruno Lowagie, author of the book
 * 'iText in Action' by Manning Publications (ISBN: 1932394796).
 * You can use this example as inspiration for your own applications.
 * The following license applies:
 * http://www.1t3xt.com/about/copyright/index.php?page=MIT
 */

package questions.directcontent;

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.StringTokenizer;

import com.lowagie.text.Document;
import com.lowagie.text.DocumentException;
import com.lowagie.text.Element;
import com.lowagie.text.PageSize;
import com.lowagie.text.pdf.BaseFont;
import com.lowagie.text.pdf.PdfContentByte;
import com.lowagie.text.pdf.PdfWriter;

public class InterpretOCR {

    public static final String RESOURCE = "resources/questions/txt/ocr.txt";
    public static final String RESULT = "results/questions/directcontent/rendered_ocr.pdf";

    public static void main(String[] args) throws IOException, DocumentException {
        Document document = new Document(PageSize.LETTER);
        PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(RESULT));
        document.open();
        PdfContentByte cb = writer.getDirectContent();
        BaseFont font = BaseFont.createFont(BaseFont.TIMES_ROMAN, BaseFont.WINANSI, BaseFont.NOT_EMBEDDED);
        cb.beginText();
        cb.setFontAndSize(font, 12);
        String line;
        String word;
        @SuppressWarnings("unused")
        float llx, lly, urx, ury;
        StringTokenizer tokenizer;
        BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(RESOURCE)));
        while ((line = reader.readLine()) != null) {
            tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                tokenizer.nextToken();
                word = tokenizer.nextToken();
                llx = Float.parseFloat(tokenizer.nextToken() + "f") / 10;
                lly = document.top() - Float.parseFloat(tokenizer.nextToken() + "f") / 10;
                urx = Float.parseFloat(tokenizer.nextToken() + "f") / 10;
                ury = document.top() - Float.parseFloat(tokenizer.nextToken() + "f") / 10;
                cb.showTextAligned(Element.ALIGN_LEFT, word, (llx + urx) / 2, lly, 0);
            }
        }
        cb.endText();
        document.close();
    }
}