Package org.apache.nutch.storage

Examples of org.apache.nutch.storage.WebPage

145
146
147
148
149
150
151
152
153
154
155
156
157
      fail(e.toString());
    }
  }

  private WebPage getPage(String text) {
    WebPage page = new WebPage();
    page.setBaseUrl(BASE);
    page.setContent(ByteBuffer.wrap(text.getBytes()));
    page.setContentType(new Utf8("text/html"));
    page
        .putToHeaders(EncodingDetector.CONTENT_TYPE_UTF8, new Utf8("text/html"));
    return page;
  }
View Full Code Here
40
41
42
43
44
45
46
47
48
49
    String class1 = "NonExistingFilter";
    String class2 = "org.apache.nutch.indexer.basic.BasicIndexingFilter";
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1 + " " + class2);

    IndexingFilters filters = new IndexingFilters(conf);
    WebPage page = new WebPage();
    page.setText(new Utf8("text"));
    page.setTitle(new Utf8("title"));
    filters.filter(new NutchDocument(),"http://www.example.com/",page);
  }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
    Configuration conf = NutchConfiguration.create();
    conf.addResource("nutch-default.xml");
    conf.addResource("crawl-tests.xml");

    IndexingFilters filters = new IndexingFilters(conf);
    WebPage page = new WebPage();
    page.setText(new Utf8("text"));
    page.setTitle(new Utf8("title"));
    NutchDocument doc = filters.filter(null,"http://www.example.com/",page);

    assertNull(doc);
  }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
    String class1 = "org.apache.nutch.indexer.basic.BasicIndexingFilter";
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1);

    IndexingFilters filters1 = new IndexingFilters(conf);
    WebPage page = new WebPage();
    page.setText(new Utf8("text"));
    page.setTitle(new Utf8("title"));
    NutchDocument fdoc1 = filters1.filter(new NutchDocument(),"http://www.example.com/",page);

    // add another index filter
    String class2 = "org.apache.nutch.indexer.metadata.MetadataIndexer";
    // set content metadata
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
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
94
95
96
97
    //Metadata metadata = new Metadata();
    EncodingDetector detector;
    // Content content;
    String encoding;

    WebPage page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));

    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    encoding = detector.guessEncoding(page, "windows-1252");
    // no information is available, so it should return default encoding
    assertEquals("windows-1252", encoding.toLowerCase());

    page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));
    page.putToHeaders(EncodingDetector.CONTENT_TYPE_UTF8, new Utf8("text/plain; charset=UTF-16"));
   
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    encoding = detector.guessEncoding(page, "windows-1252");
    assertEquals("utf-16", encoding.toLowerCase());

    page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));
   
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    detector.addClue("windows-1254", "sniffed");
    encoding = detector.guessEncoding(page, "windows-1252");
    assertEquals("windows-1254", encoding.toLowerCase());

    // enable autodetection
    conf.setInt(EncodingDetector.MIN_CONFIDENCE_KEY, 50);
    page = new WebPage();
    page.setBaseUrl(new Utf8("http://www.example.com/"));
    page.setContentType(new Utf8("text/plain"));
    page.setContent(ByteBuffer.wrap(contentInOctets));
    page.putToMetadata(new Utf8(Response.CONTENT_TYPE), ByteBuffer.wrap("text/plain; charset=UTF-16".getBytes()));
   
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(page, true);
    detector.addClue("utf-32", "sniffed");
    encoding = detector.guessEncoding(page, "windows-1252");
View Full Code Here
166
167
168
169
170
171
172
173
174
175
176
    int numReduceTasks = 100;
   
    int partitionFromRef = refPartitioner.getPartition("http://www.example.org/", numReduceTasks);
    //init selector entry (score shouldn't matter)
    SelectorEntry selectorEntry = new SelectorEntry("http://www.example.org/", 1337);
    WebPage page = new WebPage();
    int partitionFromSig = sigPartitioner.getPartition(selectorEntry, page, numReduceTasks);
   
    assertEquals("partitions should be same",
        partitionFromRef, partitionFromSig);
   
View Full Code Here
197
198
199
200
201
202
203
204
205
206
207
   
    int numReduceTasks = 100;
   
    int partitionFromRef = refPartitioner.getPartition("http://www.example.org/", numReduceTasks);
    IntWritable intWritable = new IntWritable(1337); //doesn't matter
    WebPage page = new WebPage();
    String key = TableUtil.reverseUrl("http://www.example.org/");
    FetchEntry fetchEntry = new FetchEntry(conf, key, page);
    int partitionFromSig = sigPartitioner.getPartition(intWritable, fetchEntry, numReduceTasks);
   
    assertEquals("partitions should be same",
View Full Code Here
292
293
294
295
296
297
298
299
300
301
302
   * @param score
   * @return Constructed object
   */
  private URLWebPage createURLWebPage(final String url,
      final int fetchInterval, final float score) {
    WebPage page = new WebPage();
    page.setFetchInterval(fetchInterval);
    page.setScore(score);
    page.setStatus(CrawlStatus.STATUS_UNFETCHED);
    return new URLWebPage(url, page);
  }
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
    }

    Result<String, WebPage> results = store.execute(query);
    while (results.next()) {
      try {
        WebPage page = results.get();
        String url = results.getKey();

        if (page == null)
          continue;

        if (requiredMark != null && requiredMark.checkMark(page) == null)
          continue;

        l.add(new URLWebPage(TableUtil.unreverseUrl(url), (WebPage)page.clone()));
      } catch (Exception e) {
        e.printStackTrace();
      }
    }
    return l;
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
117
118
119
  private List<String> readDb() throws Exception {
    List<URLWebPage> pages = CrawlTestUtil.readContents(webPageStore, null, fields);
    ArrayList<String> read = new ArrayList<String>();
    for (URLWebPage up : pages) {
      WebPage page = up.getDatum();
      String representation = up.getUrl();
      representation += "\tnutch.score=" + (int)page.getScore();
      ByteBuffer bb = page.getFromMetadata(new Utf8("custom.attribute"));
      if (bb != null) {
        representation += "\tcustom.attribute=" + ByteUtils.toString(bb.array());
      }
      read.add(representation);
    }
View Full Code Here
TOP

Related Classes of org.apache.nutch.storage.WebPage

  • org.apache.gora.persistency.impl.StateManagerImpl
  • org.apache.nutch.analysis.lang.TestHTMLLanguageParser
  • org.apache.nutch.api.DbReader$DbIterator
  • org.apache.nutch.crawl.DbUpdateReducer
  • org.apache.nutch.crawl.InjectorJob$UrlMapper
  • org.apache.nutch.crawl.TestGenerator
  • org.apache.nutch.crawl.TestInjector
  • org.apache.nutch.crawl.TestURLPartitioner
  • org.apache.nutch.crawl.WebTableReader
  • org.apache.nutch.fetcher.FetcherReducer$FetcherThread
    • 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.