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.rdf;
19  
20  import org.apache.any23.extractor.ExtractionContext;
21  import org.apache.any23.extractor.ExtractionResult;
22  import org.apache.any23.extractor.ExtractorDescription;
23  import org.apache.any23.extractor.ExtractorFactory;
24  import org.apache.any23.extractor.SimpleExtractorFactory;
25  import org.openrdf.rio.RDFParser;
26  import org.openrdf.rio.helpers.RDFParserBase;
27  
28  import java.util.Arrays;
29  
30  /**
31   *
32   * Concrete implementation of {@link org.apache.any23.extractor.Extractor.ContentExtractor} able to perform the
33   * extraction on <a href="http://www.w3.org/TeamSubmission/turtle/">Turtle</a> documents.
34   *
35   */
36  public class TurtleExtractor extends BaseRDFExtractor {
37  
38      public static final ExtractorFactory<TurtleExtractor> factory =
39              SimpleExtractorFactory.create(
40                      "rdf-turtle",
41                      null,
42                      Arrays.asList(
43                              "text/rdf+n3",
44                              "text/n3",
45                              "application/n3",
46                              "application/x-turtle",
47                              "application/turtle",
48                              "text/turtle"
49                      ),
50                      "example-turtle.ttl",
51                      TurtleExtractor.class
52              );
53  
54      /**
55       * Constructor, allows to specify the validation and error handling policies.
56       *
57       * @param verifyDataType   if <code>true</code> the data types will be verified,
58       *                         if <code>false</code> will be ignored.
59       * @param stopAtFirstError if <code>true</code> the parser will stop at first parsing error,
60       *                         if <code>false</code> will ignore non blocking errors.
61       */
62      public TurtleExtractor(boolean verifyDataType, boolean stopAtFirstError) {
63          super(verifyDataType, stopAtFirstError);
64      }
65  
66      /**
67       * Default constructor, with no verification of data types and no stop at first error.
68       */
69      public TurtleExtractor() {
70          this(false, false);
71      }
72  
73      public ExtractorDescription getDescription() {
74          return factory;
75      }
76  
77      @Override
78      protected RDFParser getParser(ExtractionContext extractionContext, ExtractionResult extractionResult) {
79          return RDFParserFactory.getInstance().getTurtleParserInstance(
80                  isVerifyDataType(), isStopAtFirstError(), extractionContext, extractionResult
81          );
82      }
83  
84  }