lucenepdfdocument.java

非常有用的操作pdf文件的java源码

    /**
     * This will take a reference to a PDF document and create a lucene document.
     * 
     * @param file A reference to a PDF document.
     * @return The converted lucene document.
     * 
     * @throws IOException If there is an exception while converting the document.
     */
    public Document convertDocument( File file ) throws IOException
    {
        Document document = new Document();

        // Add the url as a field named "url".  Use an UnIndexed field, so
        // that the url is just stored with the document, but is not searchable.
        addUnindexedField( document, "path", file.getPath() );
        addUnindexedField( document, "url", file.getPath().replace(FILE_SEPARATOR, '/') );

        // Add the last modified date of the file a field named "modified".  Use a
        // Keyword field, so that it's searchable, but so that no attempt is made
        // to tokenize the field into words.
        addKeywordField( document, "modified", timeToString( file.lastModified() ) );

        String uid = file.getPath().replace(FILE_SEPARATOR,'\u0000')
                     + "\u0000" 
                     + timeToString( file.lastModified() );

        // Add the uid as a field, so that index can be incrementally maintained.
        // This field is not stored with document, it is indexed, but it is not
        // tokenized prior to indexing.
        addUnstoredKeywordField( document, "uid", uid );

        FileInputStream input = null;
        try
        {
            input = new FileInputStream( file );
            addContent( document, input, file.getPath() );
        }
        finally
        {
            if( input != null )
            {
                input.close();
            }
        }


        // return the document

        return document;
    }
    
    /**
     * Convert the document from a PDF to a lucene document.
     * 
     * @param url A url to a PDF document.
     * @return The PDF converted to a lucene document.
     * @throws IOException If there is an error while converting the document.
     */
    public Document convertDocument( URL url ) throws IOException
    {
        Document document = new Document();
        URLConnection connection = url.openConnection();
        connection.connect();
        // Add the url as a field named "url".  Use an UnIndexed field, so
        // that the url is just stored with the document, but is not searchable.
        addUnindexedField( document, "url", url.toExternalForm() );

        // Add the last modified date of the file a field named "modified".  Use a
        // Keyword field, so that it's searchable, but so that no attempt is made
        // to tokenize the field into words.
        addKeywordField( document, "modified", timeToString(connection.getLastModified() ) );

        String uid = url.toExternalForm().replace(FILE_SEPARATOR, '\u0000')
                     + "\u0000" 
                     + timeToString( connection.getLastModified() );

        // Add the uid as a field, so that index can be incrementally maintained.
        // This field is not stored with document, it is indexed, but it is not
        // tokenized prior to indexing.
        addUnstoredKeywordField( document, "uid", uid );

        InputStream input = null;
        try
        {
            input = connection.getInputStream();
            addContent( document, input,url.toExternalForm() );
        }
        finally
        {
            if( input != null )
            {
                input.close();
            }
        }

        // return the document
        return document;
    }
    
    /**
     * This will get a lucene document from a PDF file.
     *
     * @param is The stream to read the PDF from.
     *
     * @return The lucene document.
     *
     * @throws IOException If there is an error parsing or indexing the document.
     */
    public static Document getDocument( InputStream is ) throws IOException
    {
        LucenePDFDocument converter = new LucenePDFDocument();
        return converter.convertDocument( is );
    }

    /**
     * This will get a lucene document from a PDF file.
     *
     * @param file The file to get the document for.
     *
     * @return The lucene document.
     *
     * @throws IOException If there is an error parsing or indexing the document.
     */
    public static Document getDocument( File file ) throws IOException
    {
        LucenePDFDocument converter = new LucenePDFDocument();
        return converter.convertDocument( file );
    }

    /**
     * This will get a lucene document from a PDF file.
     *
     * @param url The file to get the document for.
     *
     * @return The lucene document.
     *
     * @throws IOException If there is an error parsing or indexing the document.
     */
    public static Document getDocument( URL url ) throws IOException
    {
        LucenePDFDocument converter = new LucenePDFDocument();
        return converter.convertDocument( url );
    }

    /**
     * This will add the contents to the lucene document.
     *
     * @param document The document to add the contents to.
     * @param is The stream to get the contents from.
     * @param documentLocation The location of the document, used just for debug messages.
     *
     * @throws IOException If there is an error parsing the document.
     */
    private void addContent( Document document, InputStream is, String documentLocation ) throws IOException
    {
        PDDocument pdfDocument = null;
        try
        {
            pdfDocument = PDDocument.load( is );

            if( pdfDocument.isEncrypted() )
            {
                //Just try using the default password and move on
                pdfDocument.decrypt( "" );
            }

            //create a writer where to append the text content.
            StringWriter writer = new StringWriter();
            if( stripper == null )
            {
                stripper = new PDFTextStripper();
            }
            else
            {
                stripper.resetEngine();
            }
            stripper.writeText( pdfDocument, writer );

            // Note: the buffer to string operation is costless;
            // the char array value of the writer buffer and the content string
            // is shared as long as the buffer content is not modified, which will
            // not occur here.
            String contents = writer.getBuffer().toString();

            StringReader reader = new StringReader( contents );

            // Add the tag-stripped contents as a Reader-valued Text field so it will
            // get tokenized and indexed.
            addTextField( document, "contents", reader );

            PDDocumentInformation info = pdfDocument.getDocumentInformation();
            if( info != null ) 
            {
                addTextField( document, "Author", info.getAuthor() );
                addTextField( document, "CreationDate", info.getCreationDate() );
                addTextField( document, "Creator", info.getCreator() );
                addTextField( document, "Keywords", info.getKeywords() );
                addTextField( document, "ModificationDate", info.getModificationDate() );
                addTextField( document, "Producer", info.getProducer() );
                addTextField( document, "Subject", info.getSubject() );
                addTextField( document, "Title", info.getTitle() );
                addTextField( document, "Trapped", info.getTrapped() );
            }
            int summarySize = Math.min( contents.length(), 500 );
            String summary = contents.substring( 0, summarySize );
            // Add the summary as an UnIndexed field, so that it is stored and returned
            // with hit documents for display.
            addUnindexedField( document, "summary", summary );
        }
        catch( CryptographyException e )
        {
            throw new IOException( "Error decrypting document(" + documentLocation + "): " + e );
        }
        catch( InvalidPasswordException e )
        {
            //they didn't suppply a password and the default of "" was wrong.
            throw new IOException( 
                "Error: The document(" + documentLocation + 
                ") is encrypted and will not be indexed." );
        }
        finally
        {
            if( pdfDocument != null )
            {
                pdfDocument.close();
            }
        }
    }

    /**
     * This will test creating a document.
     *
     * usage: java pdfparser.searchengine.lucene.LucenePDFDocument <pdf-document>
     *
     * @param args command line arguments.
     *
     * @throws IOException If there is an error.
     */
    public static void main( String[] args ) throws IOException
    {
        if( args.length != 1 )
        {
            String us = LucenePDFDocument.class.getName();
            System.err.println( "usage: java " + us + " <pdf-document>" );
            System.exit( 1 );
        }
        System.out.println( "Document=" + getDocument( new File( args[0] ) ) );
    }
}