1 | |
|
2 | |
|
3 | |
|
4 | |
|
5 | |
|
6 | |
|
7 | |
|
8 | |
|
9 | |
|
10 | |
|
11 | |
|
12 | |
|
13 | |
|
14 | |
|
15 | |
|
16 | |
|
17 | |
|
18 | |
package org.apache.any23.extractor.rdfa; |
19 | |
|
20 | |
import org.apache.any23.configuration.DefaultConfiguration; |
21 | |
import org.apache.any23.extractor.ExtractionContext; |
22 | |
import org.apache.any23.extractor.ExtractionException; |
23 | |
import org.apache.any23.extractor.ExtractionParameters; |
24 | |
import org.apache.any23.extractor.ExtractionResult; |
25 | |
import org.apache.any23.extractor.ExtractorDescription; |
26 | |
import org.apache.any23.extractor.ExtractorFactory; |
27 | |
import org.apache.any23.extractor.SimpleExtractorFactory; |
28 | |
import org.apache.any23.extractor.rdf.RDFParserFactory; |
29 | |
import org.apache.any23.extractor.Extractor.TagSoupDOMExtractor; |
30 | |
import org.openrdf.rio.RDFHandlerException; |
31 | |
import org.openrdf.rio.RDFParseException; |
32 | |
import org.openrdf.rio.RDFParser; |
33 | |
import org.w3c.dom.Document; |
34 | |
|
35 | |
import java.io.IOException; |
36 | |
import java.io.InputStream; |
37 | |
import java.io.StringReader; |
38 | |
import java.io.StringWriter; |
39 | |
import java.util.Arrays; |
40 | |
|
41 | |
|
42 | |
|
43 | |
|
44 | |
|
45 | |
|
46 | |
|
47 | |
|
48 | |
|
49 | |
|
50 | 0 | public class RDFaExtractor implements TagSoupDOMExtractor { |
51 | |
|
52 | |
public final static String NAME = "html-rdfa"; |
53 | |
|
54 | 0 | public final static String xsltFilename = |
55 | |
DefaultConfiguration.singleton().getPropertyOrFail("any23.rdfa.extractor.xslt"); |
56 | |
|
57 | 0 | private static XSLTStylesheet xslt = null; |
58 | |
|
59 | 0 | public final static ExtractorFactory<RDFaExtractor> factory = |
60 | |
SimpleExtractorFactory.create( |
61 | |
NAME, |
62 | |
null, |
63 | |
Arrays.asList("text/html;q=0.3", "application/xhtml+xml;q=0.3"), |
64 | |
null, |
65 | |
RDFaExtractor.class |
66 | |
); |
67 | |
|
68 | |
|
69 | |
|
70 | |
|
71 | |
|
72 | |
|
73 | |
|
74 | |
public static synchronized XSLTStylesheet getXSLT() { |
75 | |
|
76 | |
|
77 | 0 | if (xslt == null) { |
78 | 0 | InputStream in = RDFaExtractor.class.getResourceAsStream(xsltFilename); |
79 | 0 | if (in == null) { |
80 | 0 | throw new RuntimeException("Couldn't load '" + xsltFilename + |
81 | |
"', maybe the file is not bundled in the jar?"); |
82 | |
} |
83 | 0 | xslt = new XSLTStylesheet(in); |
84 | |
} |
85 | 0 | return xslt; |
86 | |
} |
87 | |
|
88 | |
private boolean verifyDataType; |
89 | |
|
90 | |
private boolean stopAtFirstError; |
91 | |
|
92 | |
|
93 | |
|
94 | |
|
95 | |
|
96 | |
|
97 | |
|
98 | |
|
99 | |
|
100 | 0 | public RDFaExtractor(boolean verifyDataType, boolean stopAtFirstError) { |
101 | 0 | this.verifyDataType = verifyDataType; |
102 | 0 | this.stopAtFirstError = stopAtFirstError; |
103 | 0 | } |
104 | |
|
105 | |
|
106 | |
|
107 | |
|
108 | |
public RDFaExtractor() { |
109 | 0 | this(false, false); |
110 | 0 | } |
111 | |
|
112 | |
public boolean isVerifyDataType() { |
113 | 0 | return verifyDataType; |
114 | |
} |
115 | |
|
116 | |
public void setVerifyDataType(boolean verifyDataType) { |
117 | 0 | this.verifyDataType = verifyDataType; |
118 | 0 | } |
119 | |
|
120 | |
public boolean isStopAtFirstError() { |
121 | 0 | return stopAtFirstError; |
122 | |
} |
123 | |
|
124 | |
public void setStopAtFirstError(boolean stopAtFirstError) { |
125 | 0 | this.stopAtFirstError = stopAtFirstError; |
126 | 0 | } |
127 | |
|
128 | |
public void run( |
129 | |
ExtractionParameters extractionParameters, |
130 | |
ExtractionContext extractionContext, |
131 | |
Document in, |
132 | |
ExtractionResult out |
133 | |
) throws IOException, ExtractionException { |
134 | |
|
135 | 0 | StringWriter buffer = new StringWriter(); |
136 | |
try { |
137 | 0 | getXSLT().applyTo(in, buffer); |
138 | 0 | } catch (XSLTStylesheetException xslte) { |
139 | 0 | throw new ExtractionException("An error occurred during the XSLT application.", xslte); |
140 | 0 | } |
141 | |
|
142 | |
try { |
143 | 0 | RDFParser parser |
144 | |
= RDFParserFactory.getInstance().getRDFXMLParser( |
145 | |
verifyDataType, stopAtFirstError, extractionContext, out |
146 | |
); |
147 | 0 | parser.parse( |
148 | |
new StringReader(buffer.getBuffer().toString()), |
149 | |
extractionContext.getDocumentURI().stringValue() |
150 | |
); |
151 | 0 | } catch (RDFHandlerException ex) { |
152 | 0 | throw new IllegalStateException( |
153 | |
"Should not happen, RDFHandlerAdapter does not throw RDFHandlerException", ex |
154 | |
); |
155 | 0 | } catch (RDFParseException ex) { |
156 | 0 | throw new ExtractionException( |
157 | |
"Invalid RDF/XML produced by RDFa transform.", ex, out |
158 | |
); |
159 | 0 | } |
160 | 0 | } |
161 | |
|
162 | |
private String getDocType(Document in) { |
163 | 0 | return in.getDoctype().getPublicId(); |
164 | |
} |
165 | |
|
166 | |
|
167 | |
|
168 | |
|
169 | |
public ExtractorDescription getDescription() { |
170 | 0 | return factory; |
171 | |
} |
172 | |
|
173 | |
} |