Package org.apache.stanbol.enhancer.engines.htmlextractor.impl

Examples of org.apache.stanbol.enhancer.engines.htmlextractor.impl.HtmlExtractor

99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
     * @throws ExtractorException if there is an error during extraction
     * @throws IOException if there is an error when reading the document
     */
    @Test
    public void testMFExtraction() throws Exception {
        HtmlExtractor extractor = new HtmlExtractor(registry, parser);
        MGraph model = new SimpleMGraph();
        String testFile = "test-MF.html";

        // extract text from RDFa annotated html
        InputStream in = getResourceAsStream(testFile);
        assertNotNull("failed to load resource " + testFile, in);

        extractor.extract("file://" + testFile,in,null, "text/html", model);

        // show triples
        int tripleCounter = model.size();
        LOG.debug("Microformat triples: {}",tripleCounter);
        printTriples(model);
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
     *
     * @throws Exception
     */
    @Test
    public void testMicrodataExtraction() throws Exception {
      HtmlExtractor extractor = new HtmlExtractor(registry, parser);
      MGraph model = new SimpleMGraph();
      String testFile = "test-microdata.html";

      // extract text from RDFa annotated html
      InputStream in = getResourceAsStream(testFile);
      assertNotNull("failed to load resource " + testFile, in);

      extractor.extract("file://" + testFile,in,null, "text/html", model);

      // show triples
      int tripleCounter = model.size();
      LOG.debug("Microdata triples: {}",tripleCounter);
      printTriples(model);
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
     *
     * @throws Exception
     */
    @Test
    public void testRootExtraction() throws Exception {
        HtmlExtractor extractor = new HtmlExtractor(registry, parser);
        MGraph model = new SimpleMGraph();
        String testFile = "test-MultiRoot.html";

        // extract text from RDFa annotated html
        InputStream in = getResourceAsStream(testFile);
        assertNotNull("failed to load resource " + testFile, in);

        extractor.extract("file://" + testFile,in,null, "text/html", model);

        // show triples
        int tripleCounter = model.size();
        LOG.debug("Triples: {}",tripleCounter);
        printTriples(model);
View Full Code Here
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
        return CANNOT_ENHANCE;
    }
   
    @Override
    public void computeEnhancements(ContentItem ci) throws EngineException {
        HtmlExtractor extractor = new HtmlExtractor(htmlExtractorRegistry, htmlParser);
        MGraph model = new SimpleMGraph();
        ci.getLock().readLock().lock();
        try {
            extractor.extract(ci.getUri().getUnicodeString(), ci.getStream(),null, ci.getMimeType(), model);
        } catch (ExtractorException e) {
            throw new EngineException("Error while processing ContentItem "
                    + ci.getUri()+" with HtmlExtractor",e);
        } finally {
            ci.getLock().readLock().unlock();
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
     * @throws ExtractorException if there is an error during extraction
     * @throws IOException if there is an error when reading the document
     */
    @Test
    public void testRdfaExtraction() throws Exception {
        HtmlExtractor extractor = new HtmlExtractor(registry, parser);
        MGraph model = new SimpleMGraph();
        String testFile = "test-rdfa.html";
        // extract text from RDFa annotated html
        InputStream in = getResourceAsStream(testFile);
        assertNotNull("failed to load resource " + testFile, in);

        extractor.extract("file://" + testFile,in,null, "text/html", model);

        // show triples
        int tripleCounter = model.size();
        LOG.debug("RDFa triples: {}",tripleCounter);
        printTriples(model);
View Full Code Here
TOP

Related Classes of org.apache.stanbol.enhancer.engines.htmlextractor.impl.HtmlExtractor

  • org.apache.clerezza.rdf.core.impl.SimpleMGraph
  • org.apache.clerezza.rdf.core.MGraph
  • org.apache.clerezza.rdf.core.UriRef
  • org.apache.stanbol.enhancer.engines.htmlextractor.HtmlExtractorEngine
  • org.apache.stanbol.enhancer.engines.htmlextractor.TestHtmlExtractor
  • java.io.InputStream
  • java.io.File
  • java.io.FileInputStream
  • org.w3c.dom.Document
  • java.nio.charset.Charset
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.