View Javadoc

1   /*
2    * Copyright 2004 Sun Microsystems, Inc.
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  package com.sun.syndication.fetcher.impl;
18  
19  import java.net.URLConnection;
20  import java.util.regex.Matcher;
21  import java.util.regex.Pattern;
22  
23  /***
24   * Utility class to help deal with HTTP responses
25   *
26   */
27  public class ResponseHandler {
28  	public static final String defaultCharacterEncoding = "ISO-8859-1";
29  	
30  	private final static Pattern characterEncodingPattern = Pattern.compile("charset=([.[^; ]]*)");
31  	
32  	public static String getCharacterEncoding(URLConnection connection) {
33  		return getCharacterEncoding(connection.getContentType());
34  	}
35  	
36  	/***
37  	 * 
38  	 * <p>Gets the character encoding of a response. (Note that this is different to
39  	 * the content-encoding)</p>
40  	 * 
41  	 * @param contentTypeHeader the value of the content-type HTTP header eg: text/html; charset=ISO-8859-4
42  	 * @return the character encoding, eg: ISO-8859-4
43  	 */
44  	public static String getCharacterEncoding(String contentTypeHeader) {
45  		if (contentTypeHeader == null) {
46  			return defaultCharacterEncoding;
47  		}
48  		
49  		Matcher m = characterEncodingPattern.matcher(contentTypeHeader);
50  		//if (!m.matches()) {
51  		if (!m.find()) {
52  			return defaultCharacterEncoding;
53  		} else {
54  			return m.group(1);
55  		}
56  	}
57  }