lucenepdfdocument.java

非常有用的操作pdf文件的java源码

/**
 * Copyright (c) 2003-2006, www.pdfbox.org
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice,
 *    this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright notice,
 *    this list of conditions and the following disclaimer in the documentation
 *    and/or other materials provided with the distribution.
 * 3. Neither the name of pdfbox; nor the names of its
 *    contributors may be used to endorse or promote products derived from this
 *    software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY
 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
 * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * http://www.pdfbox.org
 *
 */
package org.pdfbox.searchengine.lucene;

import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.io.StringWriter;
import java.util.Calendar;

import java.net.URL;
import java.net.URLConnection;

import java.util.Date;

import org.apache.lucene.document.DateTools;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;

import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdmodel.PDDocumentInformation;

import org.pdfbox.exceptions.CryptographyException;
import org.pdfbox.exceptions.InvalidPasswordException;

import org.pdfbox.util.PDFTextStripper;

/**
 * This class is used to create a document for the lucene search engine.
 * This should easily plug into the IndexHTML or IndexFiles that comes with
 * the lucene project.  This class will populate the following fields.
 * <table>
 *      <tr>
 *          <th>Lucene Field Name</th>
 *          <th>Description</th>
 *      </tr>
 *      <tr>
 *          <td>path</td>
 *          <td>File system path if loaded from a file</td>
 *      </tr>
 *      <tr>
 *          <td>url</td>
 *          <td>URL to PDF document</td>
 *      </tr>
 *      <tr>
 *          <td>contents</td>
 *          <td>Entire contents of PDF document, indexed but not stored</td>
 *      </tr>
 *      <tr>
 *          <td>summary</td>
 *          <td>First 500 characters of content</td>
 *      </tr>
 *      <tr>
 *          <td>modified</td>
 *          <td>The modified date/time according to the url or path</td>
 *      </tr>
 *      <tr>
 *          <td>uid</td>
 *          <td>A unique identifier for the Lucene document.</td>
 *      </tr>
 *      <tr>
 *          <td>CreationDate</td>
 *          <td>From PDF meta-data if available</td>
 *      </tr>
 *      <tr>
 *          <td>Creator</td>
 *          <td>From PDF meta-data if available</td>
 *      </tr>
 *      <tr>
 *          <td>Keywords</td>
 *          <td>From PDF meta-data if available</td>
 *      </tr>
 *      <tr>
 *          <td>ModificationDate</td>
 *          <td>From PDF meta-data if available</td>
 *      </tr>
 *      <tr>
 *          <td>Producer</td>
 *          <td>From PDF meta-data if available</td>
 *      </tr>
 *      <tr>
 *          <td>Subject</td>
 *          <td>From PDF meta-data if available</td>
 *      </tr>
 *      <tr>
 *          <td>Trapped</td>
 *          <td>From PDF meta-data if available</td>
 *      </tr>
 * </table>
 *
 * @author <a href="mailto:[e-mail]">Ben Litchfield</a>
 * @version $Revision: 1.22 $
 */
public final class LucenePDFDocument
{
    private static final char FILE_SEPARATOR = System.getProperty("file.separator").charAt(0);

    // given caveat of increased search times when using
    //MICROSECOND, only use SECOND by default
    private DateTools.Resolution dateTimeResolution = DateTools.Resolution.SECOND;
    
    private PDFTextStripper stripper = null;
    
    /**
     * Constructor.
     */
    public LucenePDFDocument()
    {
    }
    
    /**
     * Set the text stripper that will be used during extraction.
     * 
     * @param aStripper The new pdf text stripper.
     */
    public void setTextStripper( PDFTextStripper aStripper )
    {
        stripper = aStripper;
    }
    
    /**
     * Get the Lucene data time resolution.
     * 
     * @return current date/time resolution
     */
    public DateTools.Resolution getDateTimeResolution()
    {
        return dateTimeResolution;
    }
    
    /**
     * Set the Lucene data time resolution.
     * 
     * @param resolution set new date/time resolution
     */
    public void setDateTimeResolution( DateTools.Resolution resolution )
    {
        dateTimeResolution = resolution;
    }
    
    //
    // compatibility methods for lucene-1.9+
    //
    private String timeToString( long time )
    {
        return DateTools.timeToString( time, dateTimeResolution );
    }
    
    private void addKeywordField( Document document, String name, String value )
    {
        if ( value != null ) 
        {
            document.add( new Field( name, value, Field.Store.YES, Field.Index.UN_TOKENIZED ) );
        }
    }
    
    private void addTextField( Document document, String name, Reader value )
    {
        if ( value != null ) 
        {
            document.add( new Field( name, value ) );
        }
    }
    
    private void addTextField( Document document, String name, String value )
    {
        if ( value != null ) 
        {
            document.add( new Field( name, value, Field.Store.YES, Field.Index.TOKENIZED ) );
        }
    }
    
    private void addTextField( Document document, String name, Date value )
    {
        if ( value != null ) 
        {
            addTextField( document, name, DateTools.dateToString( value, dateTimeResolution ) );
        }
    }
    
    private void addTextField( Document document, String name, Calendar value )
    {
        if ( value != null ) 
        {
            addTextField( document, name, value.getTime() );
        }
    }
    
    private static void addUnindexedField( Document document, String name, String value )
    {
        if ( value != null ) 
        {
            document.add( new Field( name, value, Field.Store.YES, Field.Index.NO ) );
        }
    }
    
    private void addUnstoredKeywordField( Document document, String name, String value )
    {
        if ( value != null ) 
        {
            document.add( new Field( name, value, Field.Store.NO, Field.Index.UN_TOKENIZED ) );
        }
    }
    
    /**
     * Convert the PDF stream to a lucene document.
     * 
     * @param is The input stream.
     * @return The input stream converted to a lucene document.
     * @throws IOException If there is an error converting the PDF.
     */
    public Document convertDocument( InputStream is ) throws IOException
    {
        Document document = new Document();
        addContent( document, is, "<inputstream>" );
        return document;
        
    }