pdftextstripper.java

非常有用的操作pdf文件的java源码

/**
 * Copyright (c) 2003-2005, 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.util;

import java.io.IOException;
import java.io.StringWriter;
import java.io.Writer;

import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.Vector;

import org.pdfbox.cos.COSDocument;
import org.pdfbox.cos.COSStream;

import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdmodel.PDPage;

import org.pdfbox.pdmodel.common.PDRectangle;
import org.pdfbox.pdmodel.common.PDStream;

import org.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem;
import org.pdfbox.pdmodel.interactive.pagenavigation.PDThreadBead;

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


/**
 * This class will take a pdf document and strip out all of the text and ignore the
 * formatting and such.
 *
 * @author <a href="mailto:[e-mail]">Ben Litchfield</a>
 * @version $Revision: 1.69 $
 */
public class PDFTextStripper extends PDFStreamEngine
{   
    private int currentPageNo = 0;
    private int startPage = 1;
    private int endPage = Integer.MAX_VALUE;
    private PDOutlineItem startBookmark = null;
    private int startBookmarkPageNumber = -1;
    private PDOutlineItem endBookmark = null;
    private int endBookmarkPageNumber = -1;
    private PDDocument document;
    private boolean suppressDuplicateOverlappingText = true;
    private boolean shouldSeparateByBeads = true;
    private boolean sortByPosition = false;
    
    private List pageArticles = null;
    /**
     * The charactersByArticle is used to extract text by article divisions.  For example
     * a PDF that has two columns like a newspaper, we want to extract the first column and
     * then the second column.  In this example the PDF would have 2 beads(or articles), one for
     * each column.  The size of the charactersByArticle would be 5, because not all text on the 
     * screen will fall into one of the articles.  The five divisions are shown below
     * 
     * Text before first article
     * first article text
     * text between first article and second article
     * second article text
     * text after second article
     * 
     * Most PDFs won't have any beads, so charactersByArticle will contain a single entry.
     */
    protected Vector charactersByArticle = new Vector();
    
    private Map characterListMapping = new HashMap();
    
    private String lineSeparator = System.getProperty("line.separator");
    private String pageSeparator = System.getProperty("line.separator");
    private String wordSeparator = " ";
    
    /**
     * The stream to write the output to.
     */
    protected Writer output;
    
    /**
     * Instantiate a new PDFTextStripper object.  This object will load properties from
     * Resources/PDFTextStripper.properties.
     * @throws IOException If there is an error loading the properties.
     */
    public PDFTextStripper() throws IOException
    {
        super( ResourceLoader.loadProperties( "Resources/PDFTextStripper.properties" ) );
    }
    
    /**
     * Instantiate a new PDFTextStripper object.  Loading all of the operator mappings
     * from the properties object that is passed in.
     * 
     * @param props The properties containing the mapping of operators to PDFOperator 
     * classes.
     * 
     * @throws IOException If there is an error reading the properties.
     */
    public PDFTextStripper( Properties props ) throws IOException
    {
        super( props );
    }

    /**
     * This will return the text of a document.  See writeText. <br />
     * NOTE: The document must not be encrypted when coming into this method.
     *
     * @param doc The document to get the text from.
     *
     * @return The text of the PDF document.
     *
     * @throws IOException if the doc state is invalid or it is encrypted.
     */
    public String getText( PDDocument doc ) throws IOException
    {
        StringWriter outputStream = new StringWriter();
        writeText( doc, outputStream );
        return outputStream.toString();
    }

    /**
     * @deprecated
     * @see PDFTextStripper#getText( PDDocument )
     * @param doc The document to extract the text from.
     * @return The document text.
     * @throws IOException If there is an error extracting the text.
     */
    public String getText( COSDocument doc ) throws IOException
    {
        return getText( new PDDocument( doc ) );
    }

    /**
     * @deprecated
     * @see PDFTextStripper#writeText( PDDocument, Writer )
     * @param doc The document to extract the text.
     * @param outputStream The stream to write the text to.
     * @throws IOException If there is an error extracting the text.
     */
    public void writeText( COSDocument doc, Writer outputStream ) throws IOException
    {
        writeText( new PDDocument( doc ), outputStream );
    }

    /**
     * This will take a PDDocument and write the text of that document to the print writer.
     *
     * @param doc The document to get the data from.
     * @param outputStream The location to put the text.
     *
     * @throws IOException If the doc is in an invalid state.
     */
    public void writeText( PDDocument doc, Writer outputStream ) throws IOException
    {
        resetEngine();

        currentPageNo = 0;
        document = doc;
        output = outputStream;
        startDocument(document);

        if( document.isEncrypted() )
        {
            // We are expecting non-encrypted documents here, but it is common
            // for users to pass in a document that is encrypted with an empty
            // password (such a document appears to not be encrypted by
            // someone viewing the document, thus the confusion).  We will
            // attempt to decrypt with the empty password to handle this case.
            //
            try
            {
                document.decrypt("");
            }
            catch (CryptographyException e)
            {
                throw new IOException("Error decrypting document, details: " + e.getMessage());
            }
            catch (InvalidPasswordException e)
            {
                throw new IOException("Error: document is encrypted");
            }
        }

        processPages( document.getDocumentCatalog().getAllPages() );
        endDocument(document);
    }

    /**
     * This will process all of the pages and the text that is in them.
     *
     * @param pages The pages object in the document.
     *
     * @throws IOException If there is an error parsing the text.
     */
    protected void processPages( List pages ) throws IOException
    {
        if( startBookmark != null )
        {
            startBookmarkPageNumber = getPageNumber( startBookmark, pages );
        }
        
        if( endBookmark != null )
        {
            endBookmarkPageNumber = getPageNumber( endBookmark, pages );
        }
        
        if( startBookmarkPageNumber == -1 && startBookmark != null &&
            endBookmarkPageNumber == -1 && endBookmark != null &&
            startBookmark.getCOSObject() == endBookmark.getCOSObject() )
        {
            //this is a special case where both the start and end bookmark
            //are the same but point to nothing.  In this case
            //we will not extract any text.
            startBookmarkPageNumber = 0;
            endBookmarkPageNumber = 0;
        }
        

        Iterator pageIter = pages.iterator();
        while( pageIter.hasNext() )
        {
            PDPage nextPage = (PDPage)pageIter.next();
            PDStream contentStream = nextPage.getContents();
            if( contentStream != null )
            {
                COSStream contents = contentStream.getStream();
                processPage( nextPage, contents );
            }
        }
    }
    
    private int getPageNumber( PDOutlineItem bookmark, List allPages ) throws IOException 
    {
        int pageNumber = -1;
        PDPage page = bookmark.findDestinationPage( document );
        if( page != null )
        {
            pageNumber = allPages.indexOf( page )+1;//use one based indexing
        }
        return pageNumber;
    }
    
    /**
     * This method is available for subclasses of this class.  It will be called before processing
     * of the document start.
     * 
     * @param pdf The PDF document that is being processed.
     * @throws IOException If an IO error occurs.
     */
    protected void startDocument(PDDocument pdf) throws IOException 
    {
        // no default implementation, but available for subclasses    
    }
    
    /**
     * This method is available for subclasses of this class.  It will be called after processing
     * of the document finishes.
     * 
     * @param pdf The PDF document that is being processed.
     * @throws IOException If an IO error occurs.
     */
    protected void endDocument(PDDocument pdf ) throws IOException 
    {
        // no default implementation, but available for subclasses
    }

    /**
     * This will process the contents of a page.
     *
     * @param page The page to process.
     * @param content The contents of the page.
     *
     * @throws IOException If there is an error processing the page.
     */
    protected void processPage( PDPage page, COSStream content ) throws IOException
    {
        currentPageNo++;
        if( currentPageNo >= startPage && currentPageNo <= endPage &&
            (startBookmarkPageNumber == -1 || currentPageNo >= startBookmarkPageNumber ) && 
            (endBookmarkPageNumber == -1 || currentPageNo <= endBookmarkPageNumber ))
        {
            startPage( page );
            pageArticles = page.getThreadBeads();
            int numberOfArticleSections = 1 + pageArticles.size() * 2;
            if( !shouldSeparateByBeads )
            {