1   /*
    2    * Licensed to the Apache Software Foundation (ASF) under one or more
    3    * contributor license agreements.  See the NOTICE file distributed with
    4    * this work for additional information regarding copyright ownership.
    5    * The ASF licenses this file to You under the Apache License, Version 2.0
    6    * (the "License"); you may not use this file except in compliance with
    7    * the License.  You may obtain a copy of the License at
    8    *
    9    *      http://www.apache.org/licenses/LICENSE-2.0
   10    *
   11    * Unless required by applicable law or agreed to in writing, software
   12    * distributed under the License is distributed on an "AS IS" BASIS,
   13    * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   14    * See the License for the specific language governing permissions and
   15    * limitations under the License.
   16    */
   17   package org.apache.pdfbox.ant;
   18   
   19   import java.io.File;
   20   
   21   import java.util.ArrayList;
   22   import java.util.Iterator;
   23   import java.util.List;
   24   
   25   import org.apache.tools.ant.DirectoryScanner;
   26   import org.apache.tools.ant.Task;
   27   
   28   import org.apache.tools.ant.types.FileSet;
   29   
   30   /**
   31    * This is an ant task that will allow pdf documents to be converted using an
   32    * and task.
   33    *
   34    * @author <a href="ben@benlitchfield.com">Ben Litchfield</a>
   35    * @version $Revision: 1.8 $
   36    */
   37   public class PDFToTextTask extends Task
   38   {
   39       private List fileSets = new ArrayList();
   40   
   41       /**
   42        * Adds a set of files (nested fileset attribute).
   43        *
   44        * @param set Another fileset to add.
   45        */
   46       public void addFileset( FileSet set )
   47       {
   48           fileSets.add( set );
   49       }
   50   
   51       /**
   52        * This will perform the execution.
   53        */
   54       public void execute()
   55       {
   56           log( "PDFToTextTask executing" );
   57           Iterator fileSetIter = fileSets.iterator();
   58           while( fileSetIter.hasNext() )
   59           {
   60               FileSet next = (FileSet)fileSetIter.next();
   61               DirectoryScanner dirScanner = next.getDirectoryScanner( getProject() );
   62               dirScanner.scan();
   63               String[] files = dirScanner.getIncludedFiles();
   64               for( int i=0; i<files.length; i++ )
   65               {
   66                   File f = new File( dirScanner.getBasedir(), files[i] );
   67                   log( "processing: " + f.getAbsolutePath() );
   68                   String pdfFile = f.getAbsolutePath();
   69                   if( pdfFile.toUpperCase().endsWith( ".PDF" ) )
   70                   {
   71                       String textFile = pdfFile.substring( 0, pdfFile.length() -3 );
   72                       textFile = textFile + "txt";
   73                       try
   74                       {
   75                           org.apache.pdfbox.ExtractText.main( new String[] { pdfFile, textFile } );
   76                       }
   77                       catch( Exception e )
   78                       {
   79                           log( "Error processing " + pdfFile + e.getMessage() );
   80                       }
   81                   }
   82               }
   83   
   84           }
   85       }
   86   }