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 * Concrete implementation of {@link org.apache.any23.extractor.Extractor.ContentExtractor}
32 * able to perform the extraction on <a href="http://www.w3.org/TR/REC-rdf-syntax/">RDF/XML</a>
33 * documents.
34 */
35 public class RDFXMLExtractor extends BaseRDFExtractor {
36
37 public final static ExtractorFactory<RDFXMLExtractor> factory =
38 SimpleExtractorFactory.create(
39 "rdf-xml",
40 null,
41 Arrays.asList(
42 "application/rdf+xml",
43 "text/rdf",
44 "text/rdf+xml",
45 "application/rdf"
46 // "application/xml;q=0.2",
47 // "text/xml;q=0.2"
48 ),
49 "example-rdfxml.rdf",
50 RDFXMLExtractor.class
51 );
52
53 /**
54 * Constructor, allows to specify the validation and error handling policies.
55 *
56 * @param verifyDataType if <code>true</code> the data types will be verified,
57 * if <code>false</code> will be ignored.
58 * @param stopAtFirstError if <code>true</code> the parser will stop at first parsing error,
59 * if <code>false</code> will ignore non blocking errors.
60 */
61 public RDFXMLExtractor(boolean verifyDataType, boolean stopAtFirstError) {
62 super(verifyDataType, stopAtFirstError);
63 }
64
65 /**
66 * Default constructor, with no verification of data types and not stop at first error.
67 */
68 public RDFXMLExtractor() {
69 this(true, true);
70 }
71
72 public ExtractorDescription getDescription() {
73 return factory;
74 }
75
76 @Override
77 protected RDFParser getParser(ExtractionContext extractionContext, ExtractionResult extractionResult) {
78 return RDFParserFactory.getInstance().getRDFXMLParser(
79 isVerifyDataType(), isStopAtFirstError(), extractionContext, extractionResult
80 );
81 }
82
83 }