org.apache.pdfbox.examples.util.PDFHighlighter 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.regex.Matcher;
import java.util.regex.Pattern;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.text.PDFTextStripper;


/**
 * Highlighting of words in a PDF document with an XML file.
 *
 * @author slagraulet ([email protected])
 * @author Ben Litchfield
 *
 * @see 
 *      Adobe Highlight File Format
 */
public class PDFHighlighter extends PDFTextStripper
{
    private Writer highlighterOutput = null;

    private String[] searchedWords;
    private ByteArrayOutputStream textOS = null;
    private Writer textWriter = null;
    private static final String ENCODING = "UTF-16";

    /**
     * Default constructor.
     *
     * @throws IOException If there is an error constructing this class.
     */
    public PDFHighlighter() throws IOException
    {
        super();
        super.setLineSeparator( "" );
        super.setWordSeparator( "" );
        super.setShouldSeparateByBeads( false );
        super.setSuppressDuplicateOverlappingText( false );
    }

    /**
     * Generate an XML highlight string based on the PDF.
     *
     * @param pdDocument The PDF to find words in.
     * @param highlightWord The word to search for.
     * @param xmlOutput The resulting output xml file.
     *
     * @throws IOException If there is an error reading from the PDF, or writing to the XML.
     */
    public void generateXMLHighlight(PDDocument pdDocument, String highlightWord, Writer xmlOutput ) throws IOException
    {
        generateXMLHighlight( pdDocument, new String[] { highlightWord }, xmlOutput );
    }

    /**
     * Generate an XML highlight string based on the PDF.
     *
     * @param pdDocument The PDF to find words in.
     * @param sWords The words to search for.
     * @param xmlOutput The resulting output xml file.
     *
     * @throws IOException If there is an error reading from the PDF, or writing to the XML.
     */
    public void generateXMLHighlight(PDDocument pdDocument, String[] sWords, Writer xmlOutput ) throws IOException
    {
        highlighterOutput = xmlOutput;
        searchedWords = sWords;
        highlighterOutput.write("\n\n\n");
        textOS = new ByteArrayOutputStream();
        textWriter = new OutputStreamWriter( textOS, ENCODING);
        writeText(pdDocument, textWriter);
        highlighterOutput.write("\n\n");
        highlighterOutput.flush();
    }

    /**
     * {@inheritDoc}
     */
    @Override
    protected void endPage( PDPage pdPage ) throws IOException
    {
        textWriter.flush();

        String page = new String( textOS.toByteArray(), ENCODING );
        textOS.reset();

        // Traitement des listes à puces (caractères spéciaux)
        if (page.indexOf('a') != -1)
        {
            page = page.replaceAll("a[0-9]{1,3}", ".");
        }
        for (String searchedWord : searchedWords)
        {
            Pattern pattern = Pattern.compile(searchedWord, Pattern.CASE_INSENSITIVE);
            Matcher matcher = pattern.matcher(page);
            while( matcher.find() )
            {
                int begin = matcher.start();
                int end = matcher.end();
                highlighterOutput.write("    \n");
            }
        }
    }

    /**
     * Command line application.
     *
     * @param args The command line arguments to the application.
     *
     * @throws IOException If there is an error generating the highlight file.
     */
    public static void main(String[] args) throws IOException
    {
        PDFHighlighter xmlExtractor = new PDFHighlighter();
        PDDocument doc = null;
        try
        {
            if( args.length < 2 )
            {
                usage();
            }
            String[] highlightStrings = new String[ args.length - 1];
            System.arraycopy( args, 1, highlightStrings, 0, highlightStrings.length );
            doc = PDDocument.load( new File(args[0]) );

            xmlExtractor.generateXMLHighlight(
                doc,
                highlightStrings,
                new OutputStreamWriter( System.out ) );
        }
        finally
        {
            if( doc != null )
            {
                doc.close();
            }
        }
    }

    private static void usage()
    {
        System.err.println( "usage: java " + PDFHighlighter.class.getName() + "  word1 word2 word3 ..." );
        System.exit( 1 );
    }
}