HTMLParser


1   /*
2    * Copyright  1999-2004 The Apache Software Foundation
3    *
4    *  Licensed under the Apache License, Version 2.0 (the "License");
5    *  you may not use this file except in compliance with the License.
6    *  You may obtain a copy of the License at
7    *
8    *      http://www.apache.org/licenses/LICENSE-2.0
9    *
10   *  Unless required by applicable law or agreed to in writing, software
11   *  distributed under the License is distributed on an "AS IS" BASIS,
12   *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   *  See the License for the specific language governing permissions and
14   *  limitations under the License.
15   *
16   */
17  
18  /* $Id: HTMLParser.java 42598 2004-03-01 16:18:28Z gregor $  */
19  
20  package org.apache.lenya.lucene.parser;
21  
22  import java.io.File  ;
23  import java.io.IOException  ;
24  import java.io.Reader  ;
25  import java.net.URI  ;
26  
27  public interface HTMLParser {
28      void parse(File   file) throws ParseException;
29  
30      void parse(URI   uri) throws ParseException;
31  
32      /**
33       * Returns the title of the HTML document.
34       */
35      String   getTitle() throws IOException  ;
36  
37      /**
38       * Returns keywords
39       */
40      String   getKeywords() throws IOException  ;
41  
42      /**
43       * Returns a reader that reads the contents of the HTML document.
44       */
45      Reader   getReader() throws IOException  ;
46  }
47

A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame

Popular Tags