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
28   * simple accessing methods.
29   */
30  public class ExtractorGroup implements Iterable<ExtractorFactory<?>> {
31  
32      private final Collection<ExtractorFactory<?>> factories;
33  
34      public ExtractorGroup(Collection<ExtractorFactory<?>> factories) {
35          this.factories = factories;
36      }
37  
38      public boolean isEmpty() {
39          return factories.isEmpty();
40      }
41  
42      public int getNumOfExtractors() {
43          return factories.size();
44      }
45  
46      /**
47       * Returns a {@link ExtractorGroup} with a set of {@link Extractor} able to
48       * process the provided mime type.
49       * 
50       * @param mimeType to perform the selection.
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
71       * supports all the content types.
72       */
73      public boolean allExtractorsSupportAllContentTypes() {
74          for (ExtractorFactory<?> factory : factories) {
75              if (!supportsAllContentTypes(factory))
76                  return false;
77          }
78          return true;
79      }
80  
81      private boolean supportsAllContentTypes(ExtractorFactory<?> factory) {
82          return factory.getSupportedMIMETypes().contains("*/*");
83      }
84  
85      private boolean supports(ExtractorFactory<?> factory, MIMEType mimeType) {
86          for (MIMEType supported : factory.getSupportedMIMETypes()) {
87              if (supported.isAnyMajorType())
88                  return true;
89              if (supported.isAnySubtype() && supported.getMajorType().equals(mimeType.getMajorType()))
90                  return true;
91              if (supported.getFullType().equals(mimeType.getFullType()))
92                  return true;
93          }
94          return false;
95      }
96  
97  }