Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.Parse

60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    for (int i=0; i<sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      Configuration conf = NutchConfiguration.create();
      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
      parse = new ParseUtil(conf).parseByExtensionId("parse-pdf", content);

      int index = parse.getText().indexOf(expectedText);
      assertTrue(index > 0);
    }
  }
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
          try {
            Metadata metadata = new Metadata();
            metadata.set(Response.CONTENT_LENGTH, Long.toString(entry.getSize()));
            metadata.set(Response.CONTENT_TYPE, contentType);
            Content content = new Content(newurl, base, b, contentType, metadata, this.conf);
            Parse parse = new ParseUtil(this.conf).parse(content);
            ParseData theParseData = parse.getData();
            Outlink[] theOutlinks = theParseData.getOutlinks();
           
            for(int count = 0; count < theOutlinks.length; count++) {
              outLinksList.add(new Outlink(theOutlinks[count].getToUrl(), theOutlinks[count].getAnchor(), this.conf));
            }
           
            resultText += entry.getName() + " " + parse.getText() + " ";
          } catch (ParseException e) {
            if (LOG.isInfoEnabled()) {
              LOG.info("fetch okay, but can't parse " + fname + ", reason: " + e.getMessage());
            }
          }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
  private MetadataCollector metadataCollector;
  private Configuration conf;

  public Parse getParse(Content content) {

    Parse parse = null;
    byte[] raw = content.getContent();
    File tmp = null;
   
    try {
      tmp = File.createTempFile("nutch", ".mp3");
View Full Code Here
216
217
218
219
220
221
222
223
224
    Configuration conf = NutchConfiguration.create();
    RSSParser parser = new RSSParser();
    parser.setConf(conf);
    Protocol protocol = new ProtocolFactory(conf).getProtocol(url);
    Content content = protocol.getProtocolOutput(new Text(url), new CrawlDatum()).getContent();
    Parse parse = parser.getParse(content);
    System.out.println("data: "+ parse.getData());
    System.out.println("text: "+parse.getText());
  }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
      parse = new ParseUtil(conf).parseByExtensionId("parse-zip",content);
      assertTrue(parse.getText().equals(expectedText));
    }
  }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
  public void testIt() throws ProtocolException, ParseException {

    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    ParseUtil parser = new ParseUtil(conf);
    ProtocolFactory factory = new ProtocolFactory(conf);
    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = factory.getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString),
                                           new CrawlDatum()).getContent();
      parse = parser.parseByExtensionId("parse-msexcel", content);

      assertTrue(parse.getText().equals(expectedText));
    }
  }
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
     */
    public void testIt() throws ProtocolException, ParseException {
        String urlString;
        Protocol protocol;
        Content content;
        Parse parse;

        Configuration conf = NutchConfiguration.create();
        for (int i = 0; i < sampleFiles.length; i++) {
            urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

            protocol = new ProtocolFactory(conf).getProtocol(urlString);
            content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
            parse = new ParseUtil(conf).parseByExtensionId("parse-rss", content);

            //check that there are 3 outlinks:
            //http://test.channel.com
            //http://www-scf.usc.edu/~mattmann/
            //http://www.nutch.org

            ParseData theParseData = parse.getData();

            Outlink[] theOutlinks = theParseData.getOutlinks();

            assertTrue("There aren't 3 outlinks read!", theOutlinks.length == 3);

View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
  public void testIt() throws ProtocolException, ParseException {

    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    urlString = "file:" + sampleDir + fileSeparator + rtfFile;
    protocol = new ProtocolFactory(conf).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum())
                      .getContent();
    parse = new ParseUtil(conf).parseByExtensionId("parse-rtf", content);
    String text = parse.getText();
    assertEquals("The quick brown fox jumps over the lazy dog", text.trim());

    String title = parse.getData().getTitle();
    Metadata meta = parse.getData().getParseMeta();
    assertEquals("test rft document", title);
    assertEquals("tests", meta.get(DublinCore.SUBJECT));


View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;
    Configuration conf = NutchConfiguration.create();

    for (int i = 0; i < sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();

      parse = new ParseUtil(conf).parse(content);

      String text = parse.getText().replaceAll("[ \t\r\n]+", " ").trim();
      assertTrue(sampleTexts[i].equals(text));
    }
  }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
  public void testIt() throws ProtocolException, ParseException {
    String urlString;
    Protocol protocol;
    Content content;
    Parse parse;

    Configuration conf = NutchConfiguration.create();
    for (int i=0; i<sampleFiles.length; i++) {
      urlString = "file:" + sampleDir + fileSeparator + sampleFiles[i];

      protocol = new ProtocolFactory(conf).getProtocol(urlString);
      content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum()).getContent();
      parse = new ParseUtil(conf).parseByExtensionId("parse-msword", content);

      assertTrue(parse.getText().startsWith(expectedText));
    }
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.parse.Parse

  • com.atlantbh.nutch.filter.index.omit.OmitIndexingFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.AlternativeDataFlowIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.flow.CsvDataFlowTest
  • org.apache.nutch.analysis.lang.HTMLLanguageParser
  • org.apache.nutch.analysis.lang.LanguageIdentifier
  • org.apache.nutch.analysis.lang.TestHTMLLanguageParser
  • org.apache.nutch.indexer.field.BasicFields$Extractor
  • org.apache.nutch.indexer.IndexerMapReduce
    • 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.