Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.Parse

40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
  public ParseResult filter(Content content, ParseResult parseResult, HTMLMetaTags metaTags, DocumentFragment doc) {
    this.doc = doc;

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

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

      if (heading != null) {
        parse.getData().getParseMeta().set(headings[i], heading.trim());
      }
    }

    return parseResult;
  }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
 
  @Test
  public void testRelTagParser() throws ProtocolException, ParseException, IOException {
  conf = NutchConfiguration.create();
  conf.set("file.content.limit", "-1");
  Parse parse;
  String urlString = "file:" + sampleDir + fileSeparator + sampleFile;

  File file = new File(sampleDir + fileSeparator + sampleFile);
  byte[] bytes = new byte[(int) file.length()];
  DataInputStream in = new DataInputStream(new FileInputStream(file));
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
  protected void tearDown() {
  } 
 
  public Outlink[] getOutlinks(String[] sampleFiles) throws ProtocolException, ParseException, IOException {
  String urlString;
  Parse parse;
 
  urlString = "file:" + sampleDir + fileSeparator + sampleFiles;
  File file = new File(urlString);
  byte[] bytes = new byte[(int) file.length()];
  DataInputStream dip = new DataInputStream(new FileInputStream(file));
  dip.readFully(bytes);
  dip.close();
   
  WebPage page = new WebPage();
  page.setBaseUrl(new Utf8(urlString));
  page.setContent(ByteBuffer.wrap(bytes));
  MimeUtil mutil = new MimeUtil(conf);
  String mime = mutil.getMimeType(file);
  page.setContentType(new Utf8(mime));
 
  parse = new ParseUtil(conf).parse(urlString, page);
  return parse.getOutlinks();
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
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, IOException {

  String urlString;
  Parse parse;
  Configuration conf = NutchConfiguration.create();
  MimeUtil mimeutil = new MimeUtil(conf);

  urlString = "file:" + sampleDir + fileSeparator + rtfFile;

  File file = new File(sampleDir + fileSeparator + rtfFile);
  byte[] bytes = new byte[(int) file.length()];
  DataInputStream in = new DataInputStream(new FileInputStream(file));
  in.readFully(bytes);
  in.close();

  WebPage page = new WebPage();
  page.setBaseUrl(new Utf8(urlString));
  page.setContent(ByteBuffer.wrap(bytes));
  String mtype = mimeutil.getMimeType(file);
  page.setContentType(new Utf8(mtype));

  parse = new ParseUtil(conf).parse(urlString, page);

  String title = parse.getTitle();
  String text = parse.getText();
  assertEquals("test rft document", title);
  //assertEquals("The quick brown fox jumps over the lazy dog", text.trim());

 
  // HOW DO WE GET THE PARSE METADATA?
View Full Code Here
90
91
92
93
94
95
96
97
98
      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
174
175
176
177
178
179
180
181
182
      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
219
220
221
222
223
224
225
226
227
228
229
      status.setMinorCode(ParseStatusCodes.SUCCESS_REDIRECT);
      status.addToArgs(new Utf8(metaTags.getRefreshHref().toString()));
      status.addToArgs(new Utf8(Integer.toString(metaTags.getRefreshTime())));
    }

    Parse parse = new Parse(text, title, outlinks, status);
    parse = htmlParseFilters.filter(url, page, parse, metaTags, root);

    if (metaTags.getNoCache()) {             // not okay to cache
      page.putToMetadata(new Utf8(Nutch.CACHING_FORBIDDEN_KEY),
          ByteBuffer.wrap(Bytes.toBytes(cachingPolicy)));
View Full Code Here
324
325
326
327
328
329
330
331
332
333
334
    parser.setConf(conf);
    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8(url));
    page.setContent(ByteBuffer.wrap(bytes));
    page.setContentType(new Utf8("text/html"));
    Parse parse = parser.getParse(url, page);
    System.out.println("title: "+parse.getTitle());
    System.out.println("text: "+parse.getText());
    System.out.println("outlinks: " + Arrays.toString(parse.getOutlinks()));

  }
View Full Code Here
184
185
186
187
188
189
190
191
192
193
194
      status.setMinorCode(ParseStatusCodes.SUCCESS_REDIRECT);
      status.addToArgs(new Utf8(metaTags.getRefreshHref().toString()));
      status.addToArgs(new Utf8(Integer.toString(metaTags.getRefreshTime())));
    }

    Parse parse = new Parse(text, title, outlinks, status);
    parse = htmlParseFilters.filter(url, page, parse, metaTags, root);

    if (metaTags.getNoCache()) { // not okay to cache
      page.putToMetadata(new Utf8(Nutch.CACHING_FORBIDDEN_KEY), ByteBuffer.wrap(Bytes
          .toBytes(cachingPolicy)));
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
256
    MimeUtil mimeutil = new MimeUtil(conf);
    String mtype = mimeutil.getMimeType(file);
    page.setContentType(new Utf8(mtype));
    // Parse parse = parser.getParse(url, page);

    Parse parse = new ParseUtil(conf).parse(url, page);

    System.out.println("content type: " + mtype);
    System.out.println("title: " + parse.getTitle());
    System.out.println("text: " + parse.getText());
    System.out.println("outlinks: " + Arrays.toString(parse.getOutlinks()));
  }
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.