Package org.semanticdesktop.aperture.extractor

Examples of org.semanticdesktop.aperture.extractor.ExtractorException

111
112
113
114
115
116
117
118
119
120
121
        if (charset == null) {
            try {
                encoding = CharsetRecognizer.detect(input, "html", null);
            } catch (IOException e) {
                LOG.error("Charset detection problem: " + e.getMessage());
                throw new ExtractorException("Charset detection problem: " + e.getMessage());
            }
        }
        Document doc = htmlParser.getDOM(input, encoding);
        htmlExtractor.extract(id.toString(), doc, null, result);
    }
View Full Code Here
110
111
112
113
114
115
116
117
118
119
            copyAddress(getRecipients(message, RecipientType.BCC), NMO.bcc, result);
           
            MailUtil.getDates(message, result);
           
        } catch (MessagingException e) {
            throw new ExtractorException(e);
        } catch (IOException e) {
            throw new ExtractorException(e);
        }
    }
View Full Code Here
310
311
312
313
314
315
316
317
318
319
320
        // parse the HTML and extract full-text and metadata
        HtmlTextExtractUtil extractor;
        try {
            extractor = new HtmlTextExtractUtil();
        } catch (InitializationException e) {
            throw new ExtractorException("Could not initialize HtmlExtractor: " + e.getMessage());
        }
        InputStream stream = new ByteArrayInputStream(string.getBytes());
        RDFContainerFactory containerFactory = new RDFContainerFactoryImpl();
        URI id = rdf.getDescribedUri();
        RDFContainer result = containerFactory.getRDFContainer(id);
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
      ID3Wrapper wrapper = new ID3Wrapper(id3v1,id3v2);
      addId3Fields(wrapper,result);
      result.add(RDF.type, NID3.ID3Audio);
     
    } catch (UnsupportedTagException e) {
      throw new ExtractorException(e);
    } catch (InvalidDataException e) {
      throw new ExtractorException(e);
    } catch (IOException e) {
      throw new ExtractorException(e);
    }
  }
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
            }
            try {
                encoding = CharsetRecognizer.detect(input, "html", "UTF-8");
            } catch (IOException e) {
                LOG.error("Charset detection problem: " + e.getMessage());
                throw new ExtractorException("Charset detection problem: "
                    + e.getMessage());
            }
        }
        else {
            encoding = charset.name();
View Full Code Here
138
139
140
141
142
143
144
145
146
147
148
149
            LOG.debug(rdf);
            StringReader reader = new StringReader(rdf);
            result.getModel().readFrom(reader, this.syntax);
            reader.close();
        } catch (TransformerException e) {
            throw new ExtractorException(e.getMessage(), e);
        } catch (ModelRuntimeException e) {
            throw new ExtractorException(e.getMessage(), e);
        } catch (IOException e) {
            throw new ExtractorException(e.getMessage(), e);
        }
    }
View Full Code Here
TOP

Related Classes of org.semanticdesktop.aperture.extractor.ExtractorException

  • org.apache.stanbol.enhancer.engines.metaxa.core.html.HtmlTextExtractUtil
  • org.apache.stanbol.enhancer.engines.metaxa.core.html.IksHtmlExtractor
  • org.apache.stanbol.enhancer.engines.metaxa.core.html.XsltExtractor
  • org.apache.stanbol.enhancer.engines.metaxa.core.mail.simple.SimpleMailExtractor
  • org.apache.stanbol.enhancer.engines.metaxa.core.mp3.MP3FileExtractor
    • 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.