1*cdf0e10cSrcweir /************************************************************************* 2*cdf0e10cSrcweir * 3*cdf0e10cSrcweir * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4*cdf0e10cSrcweir * 5*cdf0e10cSrcweir * Copyright 2000, 2010 Oracle and/or its affiliates. 6*cdf0e10cSrcweir * 7*cdf0e10cSrcweir * OpenOffice.org - a multi-platform office productivity suite 8*cdf0e10cSrcweir * 9*cdf0e10cSrcweir * This file is part of OpenOffice.org. 10*cdf0e10cSrcweir * 11*cdf0e10cSrcweir * OpenOffice.org is free software: you can redistribute it and/or modify 12*cdf0e10cSrcweir * it under the terms of the GNU Lesser General Public License version 3 13*cdf0e10cSrcweir * only, as published by the Free Software Foundation. 14*cdf0e10cSrcweir * 15*cdf0e10cSrcweir * OpenOffice.org is distributed in the hope that it will be useful, 16*cdf0e10cSrcweir * but WITHOUT ANY WARRANTY; without even the implied warranty of 17*cdf0e10cSrcweir * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 18*cdf0e10cSrcweir * GNU Lesser General Public License version 3 for more details 19*cdf0e10cSrcweir * (a copy is included in the LICENSE file that accompanied this code). 20*cdf0e10cSrcweir * 21*cdf0e10cSrcweir * You should have received a copy of the GNU Lesser General Public License 22*cdf0e10cSrcweir * version 3 along with OpenOffice.org. If not, see 23*cdf0e10cSrcweir * <http://www.openoffice.org/license.html> 24*cdf0e10cSrcweir * for a copy of the LGPLv3 License. 25*cdf0e10cSrcweir * 26*cdf0e10cSrcweir ************************************************************************/ 27*cdf0e10cSrcweir 28*cdf0e10cSrcweir package com.sun.star.help; 29*cdf0e10cSrcweir 30*cdf0e10cSrcweir import java.io.File; 31*cdf0e10cSrcweir import java.io.Reader; 32*cdf0e10cSrcweir import java.io.FileInputStream; 33*cdf0e10cSrcweir import java.io.InputStreamReader; 34*cdf0e10cSrcweir //import java.io.FileReader; 35*cdf0e10cSrcweir import java.io.StringReader; 36*cdf0e10cSrcweir 37*cdf0e10cSrcweir import org.apache.lucene.document.Document; 38*cdf0e10cSrcweir import org.apache.lucene.document.Field; 39*cdf0e10cSrcweir 40*cdf0e10cSrcweir /** Lucene Document for help files */ 41*cdf0e10cSrcweir public class HelpFileDocument 42*cdf0e10cSrcweir { 43*cdf0e10cSrcweir /** Creates reader for UTF-8 files 44*cdf0e10cSrcweir */ 45*cdf0e10cSrcweir private static Reader getReaderForFile( File aFile ) 46*cdf0e10cSrcweir throws java.io.FileNotFoundException, java.io.UnsupportedEncodingException { 47*cdf0e10cSrcweir Reader aReader; 48*cdf0e10cSrcweir if( aFile != null ) { 49*cdf0e10cSrcweir FileInputStream fis = new FileInputStream( aFile ); 50*cdf0e10cSrcweir aReader = new InputStreamReader( fis, "UTF-8" ); 51*cdf0e10cSrcweir } 52*cdf0e10cSrcweir else { 53*cdf0e10cSrcweir aReader = new StringReader( "" ); 54*cdf0e10cSrcweir } 55*cdf0e10cSrcweir return aReader; 56*cdf0e10cSrcweir } 57*cdf0e10cSrcweir 58*cdf0e10cSrcweir /** Makes a document for a File. 59*cdf0e10cSrcweir */ 60*cdf0e10cSrcweir public static Document Document( String aModule, File aCaptionFile, File aContentFile ) 61*cdf0e10cSrcweir throws java.io.FileNotFoundException, java.io.UnsupportedEncodingException { 62*cdf0e10cSrcweir Document doc = new Document(); 63*cdf0e10cSrcweir 64*cdf0e10cSrcweir // Add the path of the file as a field named "path". Use a field that is 65*cdf0e10cSrcweir // indexed (i.e. searchable), but don't tokenize the field into words. 66*cdf0e10cSrcweir File aFile = aCaptionFile != null ? aCaptionFile : aContentFile; 67*cdf0e10cSrcweir if( aFile != null ) 68*cdf0e10cSrcweir { 69*cdf0e10cSrcweir String aPath = "#HLP#" + aModule + "/" + aFile.getName(); 70*cdf0e10cSrcweir doc.add(new Field("path", aPath, Field.Store.YES, Field.Index.UN_TOKENIZED)); 71*cdf0e10cSrcweir } 72*cdf0e10cSrcweir 73*cdf0e10cSrcweir // Add the caption of the file to a field named "caption". Specify a Reader, 74*cdf0e10cSrcweir // so that the text of the file is tokenized and indexed, but not stored. 75*cdf0e10cSrcweir doc.add( new Field( "caption", getReaderForFile( aCaptionFile ) ) ); 76*cdf0e10cSrcweir 77*cdf0e10cSrcweir // Add the contents of the file to a field named "content". Specify a Reader, 78*cdf0e10cSrcweir // so that the text of the file is tokenized and indexed, but not stored. 79*cdf0e10cSrcweir doc.add( new Field( "content", getReaderForFile( aContentFile ) ) ); 80*cdf0e10cSrcweir 81*cdf0e10cSrcweir // return the document 82*cdf0e10cSrcweir return doc; 83*cdf0e10cSrcweir } 84*cdf0e10cSrcweir 85*cdf0e10cSrcweir private HelpFileDocument() {} 86*cdf0e10cSrcweir } 87