org.apache.pdfbox.examples.util.PrintTextLocations Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of pdfbox-examples Show documentation

The Apache PDFBox library is an open source Java tool for working with PDF documents. This artefact contains examples on how the library can be used.

There is a newer version: 3.0.3

Show newest version

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.pdfbox.examples.util;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.List;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;

/**
 * This is an example on how to get some x/y coordinates of text.
 *
 * @author Ben Litchfield
 */
public class PrintTextLocations extends PDFTextStripper
{
    /**
     * Instantiate a new PDFTextStripper object.
     *
     * @throws IOException If there is an error loading the properties.
     */
    public PrintTextLocations() throws IOException
    {
    }

    /**
     * This will print the documents data.
     *
     * @param args The command line arguments.
     *
     * @throws IOException If there is an error parsing the document.
     */
    public static void main( String[] args ) throws IOException
    {
        if( args.length != 1 )
        {
            usage();
        }
        else
        {
            PDDocument document = null;
            try
            {
                document = PDDocument.load( new File(args[0]) );

                PDFTextStripper stripper = new PrintTextLocations();
                stripper.setSortByPosition( true );
                stripper.setStartPage( 0 );
                stripper.setEndPage( document.getNumberOfPages() );

                Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
                stripper.writeText(document, dummy);
            }
            finally
            {
                if( document != null )
                {
                    document.close();
                }
            }
        }
    }

    /**
     * Override the default functionality of PDFTextStripper.
     */
    @Override
    protected void writeString(String string, List textPositions) throws IOException
    {
        for (TextPosition text : textPositions)
        {
            System.out.println( "String[" + text.getXDirAdj() + "," +
                    text.getYDirAdj() + " fs=" + text.getFontSize() + " xscale=" +
                    text.getXScale() + " height=" + text.getHeightDir() + " space=" +
                    text.getWidthOfSpace() + " width=" +
                    text.getWidthDirAdj() + "]" + text.getUnicode() );
        }
    }
    
    /**
     * This will print the usage for this document.
     */
    private static void usage()
    {
        System.err.println( "Usage: java " + PrintTextLocations.class.getName() + " " );
    }
}