Show text locations from a PDF file

pom.xml

<?xml version="1.0" encoding="UTF-8"?>

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>com.pdfcompose.app</groupId>
  <artifactId>parse-app</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>parse-app</name>
  <url>https://pdfcompose.com</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
  </properties>

  <dependencies>
    <dependency>
      <groupId>org.apache.pdfbox</groupId>
      <artifactId>pdfbox</artifactId>
      <version>2.0.29</version>
    </dependency>
  </dependencies>

  <build>
    <pluginManagement>
      <plugins>
        <plugin>
          <artifactId>maven-clean-plugin</artifactId>
          <version>3.1.0</version>
        </plugin>
        <plugin>
          <artifactId>maven-assembly-plugin</artifactId>
          <configuration>
            <descriptorRefs>
              <descriptorRef>jar-with-dependencies</descriptorRef>
            </descriptorRefs>
            <archive>
              <manifest>
                <mainClass>com.pdfcompose.app.sample</mainClass>
              </manifest>
            </archive>
          </configuration>
          <executions>
            <execution>
              <id>make-my-jar-with-dependencies</id>
              <phase>package</phase>
              <goals>
                <goal>single</goal>
              </goals>
            </execution>
          </executions>
        </plugin>
        <plugin>
          <artifactId>maven-resources-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-compiler-plugin</artifactId>
          <version>3.8.0</version>
        </plugin>
        <plugin>
          <artifactId>maven-surefire-plugin</artifactId>
          <version>2.22.1</version>
        </plugin>
        <plugin>
          <artifactId>maven-jar-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-install-plugin</artifactId>
          <version>2.5.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-deploy-plugin</artifactId>
          <version>2.8.2</version>
        </plugin>
      </plugins>
    </pluginManagement>
  </build>
</project>

ShowTextLocation.java

import java.io.File;
import java.io.ByteArrayOutputStream;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.awt.Color;
import java.awt.Shape;
import javax.imageio.ImageIO;
import java.util.List;
import java.awt.BasicStroke;
import java.awt.geom.AffineTransform;
import java.awt.image.BufferedImage;
import java.awt.geom.Rectangle2D;
import java.awt.Graphics2D;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.common.PDRectangle;
import org.apache.pdfbox.pdmodel.interactive.pagenavigation.PDThreadBead;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.pdmodel.font.PDFont;
import org.apache.pdfbox.pdmodel.font.PDType3Font;
import org.apache.fontbox.util.BoundingBox;
import org.apache.pdfbox.text.TextPosition;

public class ShowTextLocation extends PDFTextStripper
{
    private AffineTransform flipAT;
    private AffineTransform rotateAT;
    private AffineTransform transAT;
    private final String filename;
    static final int SCALE = 4;
    private Graphics2D g2d;

    public ShowTextLocation(PDDocument document, String filename) throws java.io.IOException
    {
	this.document = document;
	this.filename = filename;
    }

    @Override
    protected void writeString(String string, List<TextPosition> textPositions) throws java.io.IOException
    {
	for (TextPosition text : textPositions) {
	    // glyph space -> user space
	    // note: text.getTextMatrix() is *not* the Text Matrix, it's the Text Rendering Matrix
	    AffineTransform at = text.getTextMatrix().createAffineTransform();

	    // in red:
	    // show rectangles with the "height" (not a real height, but used for text extraction 
	    // heuristics, it is 1/2 of the bounding box height and starts at y=0)
	    Rectangle2D.Float rect = new Rectangle2D.Float(0, 0, 
							   text.getWidthDirAdj() / text.getTextMatrix().getScalingFactorX(),
							   text.getHeightDir() / text.getTextMatrix().getScalingFactorY());
	    Shape s = at.createTransformedShape(rect);
	    s = flipAT.createTransformedShape(s);
	    s = rotateAT.createTransformedShape(s);
	    g2d.setColor(Color.red);
	    g2d.draw(s);

	    // in blue:
	    // show rectangle with the real vertical bounds, based on the font bounding box y values
	    // usually, the height is identical to what you see when marking text in Adobe Reader
	    PDFont font = text.getFont();
	    BoundingBox bbox = font.getBoundingBox();

	    // advance width, bbox height (glyph space)
	    float xadvance = font.getWidth(text.getCharacterCodes()[0]); // todo: should iterate all chars
	    rect = new Rectangle2D.Float(0, bbox.getLowerLeftY(), xadvance, bbox.getHeight());
            
	    if (font instanceof PDType3Font) {
		// bbox and font matrix are unscaled
		at.concatenate(font.getFontMatrix().createAffineTransform());
	    } else {
		// bbox and font matrix are already scaled to 1000
		at.scale(1/1000f, 1/1000f);
	    }
	    s = at.createTransformedShape(rect);
	    s = flipAT.createTransformedShape(s);
	    s = rotateAT.createTransformedShape(s);

	    g2d.setColor(Color.blue);
	    g2d.draw(s);
	    Rectangle2D bounds = s.getBounds2D();
	    System.out.printf("[%s] (%f, %f, %f %f)\n", text.toString(),
			      bounds.getX(), bounds.getY(), bounds.getWidth(), bounds.getHeight());
	}
    }

    private void stripPage(int page) throws java.io.IOException
    {
	PDFRenderer pdfRenderer = new PDFRenderer(document);
	BufferedImage image = pdfRenderer.renderImage(page, SCALE);
	PDPage pdPage = document.getPage(page);
	PDRectangle cropBox = pdPage.getCropBox();

	// flip y-axis
	flipAT = new AffineTransform();
	flipAT.translate(0, pdPage.getBBox().getHeight());
	flipAT.scale(1, -1);

	// page may be rotated
	rotateAT = new AffineTransform();
	int rotation = pdPage.getRotation();
	if (rotation != 0)
	    {
		PDRectangle mediaBox = pdPage.getMediaBox();
		switch (rotation)
		    {
		    case 90:
			rotateAT.translate(mediaBox.getHeight(), 0);
			break;
		    case 270:
			rotateAT.translate(0, mediaBox.getWidth());
			break;
		    case 180:
			rotateAT.translate(mediaBox.getWidth(), mediaBox.getHeight());
			break;
		    default:
			break;
		    }
		rotateAT.rotate(Math.toRadians(rotation));
	    }

	// cropbox
	transAT = AffineTransform.getTranslateInstance(-cropBox.getLowerLeftX(), cropBox.getLowerLeftY());

	g2d = image.createGraphics();
	g2d.setStroke(new BasicStroke(0.1f));
	g2d.scale(SCALE, SCALE);

	setStartPage(page + 1);
	setEndPage(page + 1);

	Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
	writeText(document, dummy);
        
	// beads in green
	g2d.setStroke(new BasicStroke(0.4f));
	List<PDThreadBead> pageArticles = pdPage.getThreadBeads();
	for (PDThreadBead bead : pageArticles)
	    {
		if (bead == null)
		    {
			continue;
		    }
		PDRectangle r = bead.getRectangle();
		Shape s = r.toGeneralPath().createTransformedShape(transAT);
		s = flipAT.createTransformedShape(s);
		s = rotateAT.createTransformedShape(s);
		g2d.setColor(Color.green);
		g2d.draw(s);
	    }

	g2d.dispose();

	String imageFilename = filename;
	int pt = imageFilename.lastIndexOf('.');
	imageFilename = imageFilename.substring(0, pt) + "-marked-" + (page + 1) + ".png";
	ImageIO.write(image, "png", new File(imageFilename));
    }

    public static void main(String[] args) throws Exception
    {
	if (args.length != 1) {
	    System.err.println("usage: java ShowTextLocation pdf-file");
	    System.exit(1);
	}
	PDDocument document = null;
	try {
	    document = PDDocument.load(new File(args[0]));
	    ShowTextLocation stripper = new ShowTextLocation(document, args[0]);
	    stripper.setSortByPosition(true);
	    for (int page = 0; page < document.getNumberOfPages(); ++page) {
		stripper.stripPage(page);
	    }
	} finally {
	    if (document != null) document.close();
	}
    }
}