View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    *
9    *  http://www.apache.org/licenses/LICENSE-2.0
10   *
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  
18  package org.apache.any23.extractor;
19  
20  import org.apache.any23.mime.MIMEType;
21  
22  import java.util.ArrayList;
23  import java.util.Collection;
24  import java.util.Iterator;
25  
26  /**
27   * It simple models a group of {@link ExtractorFactory} providing simple accessing methods.
28   */
29  public class ExtractorGroup implements Iterable<ExtractorFactory<?>> {
30  
31      private final Collection<ExtractorFactory<?>> factories;
32  
33      public ExtractorGroup(Collection<ExtractorFactory<?>> factories) {
34          this.factories = factories;
35      }
36  
37      public boolean isEmpty() {
38          return factories.isEmpty();
39      }
40  
41      public int getNumOfExtractors() {
42          return factories.size();
43      }
44  
45      /**
46       * Returns a {@link ExtractorGroup} with a set of {@link Extractor} able to process the provided mime type.
47       * 
48       * @param mimeType
49       *            to perform the selection.
50       * 
51       * @return an {@link ExtractorGroup} able to process the provided mime type.
52       */
53      public ExtractorGroup filterByMIMEType(MIMEType mimeType) {
54          // @@@ wildcards, q values
55          Collection<ExtractorFactory<?>> matching = new ArrayList<>();
56          for (ExtractorFactory<?> factory : factories) {
57              if (supportsAllContentTypes(factory) || supports(factory, mimeType)) {
58                  matching.add(factory);
59              }
60          }
61          return new ExtractorGroup(matching);
62      }
63  
64      @Override
65      public Iterator<ExtractorFactory<?>> iterator() {
66          return factories.iterator();
67      }
68  
69      /**
70       * @return <code>true</code> if all the {@link Extractor} contained in the group supports all the content types.
71       */
72      public boolean allExtractorsSupportAllContentTypes() {
73          for (ExtractorFactory<?> factory : factories) {
74              if (!supportsAllContentTypes(factory))
75                  return false;
76          }
77          return true;
78      }
79  
80      private boolean supportsAllContentTypes(ExtractorFactory<?> factory) {
81          return factory.getSupportedMIMETypes().contains("*/*");
82      }
83  
84      private boolean supports(ExtractorFactory<?> factory, MIMEType mimeType) {
85          for (MIMEType supported : factory.getSupportedMIMETypes()) {
86              if (supported.isAnyMajorType())
87                  return true;
88              if (supported.isAnySubtype() && supported.getMajorType().equals(mimeType.getMajorType()))
89                  return true;
90              if (supported.getFullType().equals(mimeType.getFullType()))
91                  return true;
92          }
93          return false;
94      }
95  
96  }