public LucenePDFDocument() 
{

}

Constructor.

 public Document convertDocument(InputStream is) throws IOException 
{
        Document document = new Document();
        addContent( document, is, "< inputstream >" );
        return document;
}

Convert the PDF stream to a lucene 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;
}

This will take a reference to a PDF document and create a lucene 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;
}

Convert the document from a PDF to a lucene document.

 public Resolution getDateTimeResolution() 
{
        return dateTimeResolution;
}

Get the Lucene data time resolution.

 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.

 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.

 public static Document getDocument(URL url) throws IOException 
{
        LucenePDFDocument converter = new LucenePDFDocument();
        return converter.convertDocument( url );
}

This will get a lucene document from a PDF file.

 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] ) ) );
}

This will test creating a document. usage: java pdfparser.searchengine.lucene.LucenePDFDocument <pdf-document>

 public  void setDateTimeResolution(Resolution resolution) 
{
        dateTimeResolution = resolution;
}

Set the Lucene data time resolution.

 public  void setTextStripper(PDFTextStripper aStripper) 
{
        stripper = aStripper;
}

Set the text stripper that will be used during extraction.