Package org.apache.nutch.indexer

Examples of org.apache.nutch.indexer.NutchDocument

42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
    Configuration conf = NutchConfiguration.create();
    conf.setBoolean("anchorIndexingFilter.deduplicate", true);
    AnchorIndexingFilter filter = new AnchorIndexingFilter();
    filter.setConf(conf);
    assertNotNull(filter);
    NutchDocument doc = new NutchDocument();
    ParseImpl parse = new ParseImpl("foo bar", new ParseData());
    Inlinks inlinks = new Inlinks();
    inlinks.add(new Inlink("http://test1.com/", "text1"));
    inlinks.add(new Inlink("http://test2.com/", "text2"));
    inlinks.add(new Inlink("http://test3.com/", "text2"));
    try {
      filter.filter(doc, parse, new Text("http://nutch.apache.org/index.html"), new CrawlDatum(), inlinks);
    } catch(Exception e){
      e.printStackTrace();
      fail(e.getMessage());
    }
    assertNotNull(doc);
    assertTrue("test if there is an anchor at all", doc.getFieldNames().contains("anchor"));
    assertEquals("test dedup, we expect 2", 2, doc.getField("anchor").getValues().size());
  }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
    Configuration conf = NutchConfiguration.create();
    conf.setBoolean("moreIndexingFilter.indexMimeTypeParts", false);
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    assertNotNull(filter);
    NutchDocument doc = new NutchDocument();
    ParseImpl parse = new ParseImpl("foo bar", new ParseData());
   
    try{
        filter.filter(doc, parse, new Text("http://nutch.apache.org/index.html"), new CrawlDatum(), new Inlinks());
    }
    catch(Exception e){
        e.printStackTrace();
        fail(e.getMessage());
    }
    assertNotNull(doc);
    assertTrue(doc.getFieldNames().contains("type"));
    assertEquals(1, doc.getField("type").getValues().size());
    assertEquals("text/html", doc.getFieldValue("type"));   
  }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_DISPOSITION, "filename=filename.ext");
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);

    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
      new ParseStatus(), "title", new Outlink[0], metadata)), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());

    assertEquals("content-disposition not detected", "filename.ext", doc.getFieldValue("title"));
  }
View Full Code Here
95
96
97
98
99
100
101
102
103
104
  private void assertContentType(Configuration conf, String source, String expected) throws IndexingException {
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_TYPE, source);
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
        new ParseStatus(), "title", new Outlink[0], metadata)), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());
    assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
  }
View Full Code Here
41
42
43
44
45
46
47
48
    this.action = action;
  }

  public void readFields(DataInput in) throws IOException {
    action = in.readByte();
    NutchDocument doc = new NutchDocument();
    doc.readFields(in);
  }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
     Configuration conf = NutchConfiguration.create();
     conf.setBoolean("moreIndexingFilter.indexMimeTypeParts", false);
     MoreIndexingFilter filter = new MoreIndexingFilter();
     filter.setConf(conf);
     assertNotNull(filter);
     NutchDocument doc = new NutchDocument();
     try{
       filter.filter(doc, "http://nutch.apache.org/index.html", new WebPage());
     }
     catch(Exception e){
       e.printStackTrace();
       fail(e.getMessage());
     }
     assertNotNull(doc);
     assertTrue(doc.getFieldNames().contains("type"));
     assertEquals(1, doc.getFieldValues("type").size());
     assertEquals("text/html", doc.getFieldValue("type"));    
  }
View Full Code Here
78
79
80
81
82
83
84
85
    WebPage page = new WebPage();
    String url = "http://www.example.com/";
    page.setContent(ByteBuffer.wrap("text".getBytes()));
    page.setTitle(new Utf8("title"));
    page.putToHeaders(EncodingDetector.CONTENT_TYPE_UTF8, new Utf8(source));
    NutchDocument doc = filter.filter(new NutchDocument(), url, page);
    assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
  }
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
  public void testDeduplicateAnchor() throws Exception {
    Configuration conf = NutchConfiguration.create();
    conf.setBoolean("anchorIndexingFilter.deduplicate", true);
    AnchorIndexingFilter filter = new AnchorIndexingFilter();
    filter.setConf(conf);
    NutchDocument doc = new NutchDocument();
    WebPage page = new WebPage();
    page.putToInlinks(new Utf8("http://example1.com/"), new Utf8("cool site"));
    page.putToInlinks(new Utf8("http://example2.com/"), new Utf8("cool site"));
    page.putToInlinks(new Utf8("http://example3.com/"), new Utf8("fun site"));
    filter.filter(doc, "http://myurldoesnotmatter.com/", page);
   
    assertTrue("test if there is an anchor at all", doc.getFieldNames().contains("anchor"));
   
    assertEquals("test dedup, we expect 2", 2, doc.getFieldValues("anchor").size());
  }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
  public void testRelTagFields() throws Exception {
    Configuration conf = NutchConfiguration.create();
    RelTagIndexingFilter filter = new RelTagIndexingFilter();
    filter.setConf(conf);
    assertNotNull(filter);
    NutchDocument doc = new NutchDocument();
    WebPage page = new WebPage();
    byte[] bytes = new byte[10];
    ByteBuffer bbuf = ByteBuffer.wrap(bytes);
    page.putToMetadata(new Utf8(RelTagParser.REL_TAG), bbuf);
    try {
      filter.filter(doc, "http://nutch.apache.org/", page);
    } catch (Exception e) {
      e.printStackTrace();
      fail(e.getMessage());
    }
    assertNotNull(doc);
    assertTrue("check for 'tag' field", doc.getFieldNames().contains("tag"));
  }
View Full Code Here
44
45
46
47
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
  public void testBasicFields() throws Exception {
  Configuration conf = NutchConfiguration.create();
  BasicIndexingFilter filter = new BasicIndexingFilter();
  filter.setConf(conf);
  assertNotNull(filter);
  NutchDocument doc = new NutchDocument();
  WebPage page = new WebPage();
  page.putToInlinks(new Utf8("http://nutch.apache.org/"), new Utf8("Welcome to Nutch"));
  page.setTitle(new Utf8("Welcome to Nutch"));
    page.setReprUrl(new Utf8("http://www.urldoesnotmatter.org"));
    byte[] bytes = new byte[10];
    ByteBuffer bbuf = ByteBuffer.wrap(bytes);
    page.putToMetadata(Nutch.CACHING_FORBIDDEN_KEY_UTF8, bbuf);
    page.setFetchTime(System.currentTimeMillis());
  try {
    filter.filter(doc, "http://www.apache.org/", page);
  } catch(Exception e) {
    e.printStackTrace();
    fail(e.getMessage());
  }
  assertNotNull(doc);
  assertTrue("check for host field ", doc.getFieldNames().contains("host"));
  assertTrue("check for url field", doc.getFieldNames().contains("url"));
  assertTrue("check for orig field", doc.getFieldNames().contains("orig"));
  assertTrue("check for content field", doc.getFieldNames().contains("content"));
  assertTrue("check for title field", doc.getFieldNames().contains("title"));
  assertTrue("check for cache field", doc.getFieldNames().contains("cache"));
  assertTrue("check for tstamp field", doc.getFieldNames().contains("tstamp"));
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.indexer.NutchDocument

  • com.atlantbh.nutch.filter.index.omit.OmitIndexingFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.AlternativeDataFlowIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.flow.CsvDataFlowTest
  • org.apache.nutch.indexer.anchor.TestAnchorIndexingFilter
  • org.apache.nutch.indexer.basic.TestBasicIndexingFilter
  • org.apache.nutch.indexer.IndexingFiltersChecker
  • org.apache.nutch.indexer.more.TestMoreIndexingFilter
  • org.apache.nutch.indexer.NutchIndexAction
  • org.apache.nutch.indexer.staticfield.TestStaticFieldIndexerTest
    • 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.