Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.Parse

91
92
93
94
95
96
97
98
99
      List<Outlink> list = Arrays.asList(old);
      outlinks.addAll(list);
      ParseStatus status = parse.getParseStatus();
      String text = parse.getText();
      Outlink[] newlinks = outlinks.toArray(new Outlink[outlinks.size()]);
      return new Parse(text, title, newlinks, status);
    }
    return parse;
  }
View Full Code Here
175
176
177
178
179
180
181
182
183
      title = script.substring(0, idx);
    } else {
      idx = Math.min(MAX_TITLE_LEN, script.length());
      title = script.substring(0, idx);
    }
    Parse parse =
      new Parse(script, title, outlinks, ParseStatusUtils.STATUS_SUCCESS);
    return parse;
  }
View Full Code Here
330
331
332
333
334
335
336
337
338
339
340
341
342
    try {
      protocol = ProtocolFactory.getProtocol(url);
      Content content = protocol.getProtocolOutput(url).getContent();
      String contentType = content.getContentType();
      Parser parser = ParserFactory.getParser(contentType, url);
      Parse parse = parser.getParse(content);
      System.out.println("text:" + parse.getText());
      return parse.getText();

    } catch (ProtocolNotFound e) {
      e.printStackTrace();
    } catch (ProtocolException e) {
      e.printStackTrace();
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
58
      /* loop through the test documents and validate result */
      for (int t = 0; t < docs.length; t++) {

        Content content = getContent(docs[t]);
        Parser parser = ParserFactory.getParser("text/html", URL);
        Parse parse = parser.getParse(content);

        assertEquals(metalanguages[t], (String) parse.getData().get(
            HTMLLanguageParser.META_LANG_NAME));

      }
    } catch (Exception e) {
      e.printStackTrace(System.out);
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
  private boolean multiValued = false;

  public ParseResult filter(Content content, ParseResult parseResult, HTMLMetaTags metaTags, DocumentFragment doc) {
    this.doc = doc;

    Parse parse = parseResult.get(content.getUrl());

    for (int i = 0 ; headings != null && i < headings.length ; i++ ) {
      List<String> discoveredHeadings = getElement(headings[i]);

      if (discoveredHeadings.size() > 0) {
        for (String heading : discoveredHeadings) {
          if (heading != null) {
            heading.trim();

            if (heading.length() > 0) {
              parse.getData().getParseMeta().add(headings[i], heading);
            }
          }
        }
      }
    }
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
    try {
      String urlString = "file:" + sampleDir + fileSeparator + fileName;    
      Protocol protocol = new ProtocolFactory(conf).getProtocol(urlString);
      Content content = protocol.getProtocolOutput(new Text(urlString),
          new CrawlDatum()).getContent();
      Parse parse = new ParseUtil(conf).parse(content).get(content.getUrl());
      metadata = parse.getData().getParseMeta();
    } catch (Exception e) {
      e.printStackTrace();
      fail(e.toString());
    }
    return metadata;
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
    NutchDocument doc = new NutchDocument();
    Text urlText = new Text(url);

    Inlinks inlinks = null;
    Parse parse = parseResult.get(urlText);
    try {
      doc = indexers.filter(doc, parse, urlText, datum, inlinks);
    } catch (IndexingException e) {
      e.printStackTrace();
    }
View Full Code Here
259
260
261
262
263
264
265
266
267
268
269
    doc.add("segment", metadata.get(Nutch.SEGMENT_NAME_KEY));

    // add digest, used by dedup
    doc.add("digest", metadata.get(Nutch.SIGNATURE_KEY));

    final Parse parse = new ParseImpl(parseText, parseData);
    try {
      // extract information from dbDatum and pass it to
      // fetchDatum so that indexing filters can use it
      final Text url = (Text) dbDatum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY);
      if (url != null) {
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
  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).get(content.getUrl());

      String text = parse.getText().replaceAll("[ \t\r\n]+", " ").trim();
      assertTrue(sampleTexts[i].equals(text));
    }
  }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
  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 UTF8(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
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.