This project has retired. For details please refer to its Attic page.
RepositoryScanner xref
View Javadoc
1   package org.apache.archiva.repository.scanner;
2   
3   /*
4    * Licensed to the Apache Software Foundation (ASF) under one
5    * or more contributor license agreements.  See the NOTICE file
6    * distributed with this work for additional information
7    * regarding copyright ownership.  The ASF licenses this file
8    * to you under the Apache License, Version 2.0 (the
9    * "License"); you may not use this file except in compliance
10   * with the License.  You may obtain a copy of the License at
11   *
12   *  http://www.apache.org/licenses/LICENSE-2.0
13   *
14   * Unless required by applicable law or agreed to in writing,
15   * software distributed under the License is distributed on an
16   * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
17   * KIND, either express or implied.  See the License for the
18   * specific language governing permissions and limitations
19   * under the License.
20   */
21  
22  import org.apache.archiva.consumers.InvalidRepositoryContentConsumer;
23  import org.apache.archiva.consumers.KnownRepositoryContentConsumer;
24  import org.apache.archiva.repository.ManagedRepository;
25  
26  import java.util.List;
27  import java.util.Set;
28  
29  import static org.apache.archiva.indexer.ArchivaIndexManager.DEFAULT_INDEX_PATH;
30  import static org.apache.archiva.indexer.ArchivaIndexManager.DEFAULT_PACKED_INDEX_PATH;
31  
32  /**
33   * RepositoryScanner
34   *
35   *
36   */
37  public interface RepositoryScanner
38  {
39      /**
40       * The value to pass to {@link #scan(ManagedRepository, long)} to have the scan
41       * operate in a fresh fashion, with no check on changes based on timestamp.
42       */
43      long FRESH_SCAN = 0;
44  
45      /**
46       * <p>
47       * Typical Ignorable Content patterns.
48       * </p>
49       * <p><strong>
50       * NOTE: Do not use for normal webapp or task driven repository scanning.
51       * </strong></p>     
52       * <p>
53       * These patterns are only valid for archiva-cli and archiva-converter use.
54       * </p>
55       */
56      static final String[] IGNORABLE_CONTENT =
57          { "bin/**", "reports/**", DEFAULT_PACKED_INDEX_PATH, ".reports/**", ".maven/**", "**/.svn/**", "**/*snapshot-version",
58              "*/website/**", "*/licences/**", "**/.htaccess", "**/*.html", "**/*.txt", "**/README*", "**/CHANGELOG*",
59              "**/KEYS*", DEFAULT_INDEX_PATH };
60  
61      /**
62       * Scan the repository for content changes.
63       * <p>
64       * Internally, this will use the as-configured known and invalid consumer lists.
65       *
66       * @param repository   the repository to change.
67       * @param changesSince the timestamp to use as a threshold on what is considered new or changed.
68       *                     (To have all content be taken into consideration regardless of timestamp,
69       *                     use the {@link #FRESH_SCAN} constant)
70       * @return the statistics for this scan.
71       * @throws RepositoryScannerException if there was a fundamental problem with getting the discoverer started.
72       */
73      RepositoryScanStatistics scan( ManagedRepository repository, long changesSince )
74          throws RepositoryScannerException;
75  
76      /**
77       * Scan the repository for content changes.
78       * <p>
79       * Internally, this will use the as-configured known and invalid consumer lists.
80       *
81       * @param repository              the repository to change.
82       * @param knownContentConsumers   the list of consumers that follow the {@link KnownRepositoryContentConsumer}
83       *                                interface that should be used for this scan.
84       * @param invalidContentConsumers the list of consumers that follow the {@link InvalidRepositoryContentConsumer}
85       *                                interface that should be used for this scan.
86       * @param ignoredContentPatterns  list of patterns that should be ignored and not sent to any consumer.
87       * @param changesSince            the timestamp to use as a threshold on what is considered new or changed.
88       *                                (To have all content be taken into consideration regardless of timestamp,
89       *                                use the {@link #FRESH_SCAN} constant)
90       * @return the statistics for this scan.
91       * @throws RepositoryScannerException if there was a fundamental problem with getting the discoverer started.
92       */
93      RepositoryScanStatistics scan( ManagedRepository repository,
94                                     List<KnownRepositoryContentConsumer> knownContentConsumers,
95                                     List<InvalidRepositoryContentConsumer> invalidContentConsumers,
96                                     List<String> ignoredContentPatterns, long changesSince )
97          throws RepositoryScannerException;
98  
99      Set<RepositoryScannerInstance> getInProgressScans();
100 }