WireFeedInput


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.io;
18  
19  import com.sun.syndication.feed.WireFeed;
20  import com.sun.syndication.io.impl.FeedParsers;
21  import com.sun.syndication.io.impl.XmlFixerReader;
22  import org.jdom.Document;
23  import org.jdom.input.DOMBuilder;
24  import org.jdom.input.JDOMParseException;
25  import org.jdom.input.SAXBuilder;
26  import org.xml.sax.EntityResolver  ;
27  import org.xml.sax.InputSource  ;
28  
29  import java.io.*;
30  import java.util.List  ;
31  
32  /**
33   * Parses an XML document (File, InputStream, Reader, W3C SAX InputSource, W3C DOM Document or JDom DOcument)
34   * into an WireFeed (RSS/Atom).
35   * <p>
36   * It accepts all flavors of RSS (0.90, 0.91, 0.92, 0.93, 0.94, 1.0 and 2.0) and
37   * Atom 0.3 feeds. Parsers are plugable (they must implement the WireFeedParser interface).
38   * <p>
39   * The WireFeedInput useds liberal parsers.
40   * <p>
41   * @author Alejandro Abdelnur
42   *
43   */
44  public class WireFeedInput {
45      private static FeedParsers FEED_PARSERS = new FeedParsers();
46      private static final InputSource   EMPTY_INPUTSOURCE = new InputSource  (new ByteArrayInputStream(new byte[0]));
47      private static final EntityResolver   RESOLVER = new EmptyEntityResolver();
48  
49      private static class EmptyEntityResolver implements EntityResolver   {
50          public InputSource   resolveEntity(String   publicId, String   systemId) {
51              if(systemId != null && systemId.endsWith(".dtd")) return EMPTY_INPUTSOURCE;
52              return null;
53          }
54      }
55  
56      private boolean _validate;
57  
58      private boolean _xmlHealerOn;
59  
60      /**
61       * Returns the list of supported input feed types.
62       * <p>
63       * @see WireFeed for details on the format of these strings.
64       * <p>
65       * @return a list of String elements with the supported input feed types.
66       *
67       */
68      public static List   getSupportedFeedTypes() {
69          return FEED_PARSERS.getSupportedFeedTypes();
70      }
71  
72      /**
73       * Creates a WireFeedInput instance with input validation turned off.
74       * <p>
75       *
76       */
77      public WireFeedInput() {
78          this (false);
79      }
80  
81      /**
82       * Creates a WireFeedInput instance.
83       * <p>
84       * @param validate indicates if the input should be validated. NOT IMPLEMENTED YET (validation does not happen)
85       *
86       */
87      public WireFeedInput(boolean validate) {
88          _validate = false; // TODO FIX THIS THINGY
89          _xmlHealerOn = true;
90      }
91  
92      /**
93       * Enables XML healing in the WiredFeedInput instance.
94       * <p>
95       * Healing trims leading chars from the stream (empty spaces and comments) until the XML prolog.
96       * <p>
97       * Healing resolves HTML entities (from literal to code number) in the reader.
98       * <p>
99       * The healing is done only with the build(File) and build(Reader) signatures.
100      * <p>
101      * By default is TRUE.
102      * <p>
103      * @param heals TRUE enables stream healing, FALSE disables it.
104      *
105      */
106     public void setXmlHealerOn(boolean heals) {
107         _xmlHealerOn = heals;
108     }
109 
110     /**
111      * Indicates if the WiredFeedInput instance will XML heal (if necessary) the character stream.
112      * <p>
113      * Healing trims leading chars from the stream (empty spaces and comments) until the XML prolog.
114      * <p>
115      * Healing resolves HTML entities (from literal to code number) in the reader.
116      * <p>
117      * The healing is done only with the build(File) and build(Reader) signatures.
118      * <p>
119      * By default is TRUE.
120      * <p>
121      * @return TRUE if healing is enabled, FALSE if not.
122      *
123      */
124     public boolean getXmlHealerOn() {
125         return _xmlHealerOn;
126     }
127 
128     /**
129      * Builds an WireFeed (RSS or Atom) from a file.
130      * <p>
131      * NOTE: This method delages to the 'AsbtractFeed WireFeedInput#build(org.jdom.Document)'.
132      * <p>
133      * @param file file to read to create the WireFeed.
134      * @return the WireFeed read from the file.
135      * @throws FileNotFoundException thrown if the file could not be found.
136      * @throws IOException thrown if there is problem reading the file.
137      * @throws IllegalArgumentException thrown if feed type could not be understood by any of the underlying parsers.
138      * @throws FeedException if the feed could not be parsed
139      *
140      */
141     public WireFeed build(File file) throws FileNotFoundException,IOException,IllegalArgumentException  ,FeedException {
142         WireFeed feed;
143         Reader reader = new FileReader(file);
144         if (_xmlHealerOn) {
145             reader = new XmlFixerReader(reader);
146         }
147         feed = build(reader);
148         reader.close();
149         return feed;
150     }
151 
152     /**
153      * Builds an WireFeed (RSS or Atom) from an Reader.
154      * <p>
155      * NOTE: This method delages to the 'AsbtractFeed WireFeedInput#build(org.jdom.Document)'.
156      * <p>
157      * @param reader Reader to read to create the WireFeed.
158      * @return the WireFeed read from the Reader.
159      * @throws IllegalArgumentException thrown if feed type could not be understood by any of the underlying parsers.
160      * @throws FeedException if the feed could not be parsed
161      *
162      */
163     public WireFeed build(Reader reader) throws IllegalArgumentException  ,FeedException {
164         SAXBuilder saxBuilder = new SAXBuilder(_validate);
165         saxBuilder.setEntityResolver(RESOLVER);
166         try {
167             if (_xmlHealerOn) {
168                 reader = new XmlFixerReader(reader);
169             }
170             Document document = saxBuilder.build(reader);
171             return build(document);
172         }
173         catch (JDOMParseException ex) {
174             throw new ParsingFeedException("Invalid XML: " + ex.getMessage(), ex);
175         }
176         catch (Exception   ex) {
177             throw new ParsingFeedException("Invalid XML",ex);
178         }
179     }
180 
181     /**
182      * Builds an WireFeed (RSS or Atom) from an W3C SAX InputSource.
183      * <p>
184      * NOTE: This method delages to the 'AsbtractFeed WireFeedInput#build(org.jdom.Document)'.
185      * <p>
186      * @param is W3C SAX InputSource to read to create the WireFeed.
187      * @return the WireFeed read from the W3C SAX InputSource.
188      * @throws IllegalArgumentException thrown if feed type could not be understood by any of the underlying parsers.
189      * @throws FeedException if the feed could not be parsed
190      *
191      */
192     public WireFeed build(InputSource   is) throws IllegalArgumentException  ,FeedException {
193         SAXBuilder saxBuilder = new SAXBuilder(_validate);
194         saxBuilder.setEntityResolver(RESOLVER);
195         try {
196             Document document = saxBuilder.build(is);
197             return build(document);
198         }
199         catch (JDOMParseException ex) {
200             throw new ParsingFeedException("Invalid XML: " + ex.getMessage(), ex);
201         }
202         catch (Exception   ex) {
203             throw new ParsingFeedException("Invalid XML",ex);
204         }
205     }
206 
207     /**
208      * Builds an WireFeed (RSS or Atom) from an W3C DOM document.
209      * <p>
210      * NOTE: This method delages to the 'AsbtractFeed WireFeedInput#build(org.jdom.Document)'.
211      * <p>
212      * @param document W3C DOM document to read to create the WireFeed.
213      * @return the WireFeed read from the W3C DOM document.
214      * @throws IllegalArgumentException thrown if feed type could not be understood by any of the underlying parsers.
215      * @throws FeedException if the feed could not be parsed
216      *
217      */
218     public WireFeed build(org.w3c.dom.Document   document) throws IllegalArgumentException  ,FeedException {
219         DOMBuilder domBuilder = new DOMBuilder();
220         try {
221             Document jdomDoc = domBuilder.build(document);
222             return build(jdomDoc);
223         }
224         catch (Exception   ex) {
225             throw new ParsingFeedException("Invalid XML",ex);
226         }
227     }
228 
229     /**
230      * Builds an WireFeed (RSS or Atom) from an JDOM document.
231      * <p>
232      * NOTE: All other build methods delegate to this method.
233      * <p>
234      * @param document JDOM document to read to create the WireFeed.
235      * @return the WireFeed read from the JDOM document.
236      * @throws IllegalArgumentException thrown if feed type could not be understood by any of the underlying parsers.
237      * @throws FeedException if the feed could not be parsed
238      *
239      */
240     public WireFeed build(Document document) throws IllegalArgumentException  ,FeedException {
241         WireFeedParser parser = FEED_PARSERS.getParserFor(document);
242         if (parser==null) {
243             throw new IllegalArgumentException  ("Invalid document");
244         }
245         return parser.parse(document, _validate);
246     }
247 
248 }
249
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags