Package org.apache.nutch.indexer

Examples of org.apache.nutch.indexer.NutchDocument

62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
  public void testEmptyIndexStatic() throws Exception {

    assertNotNull(filter);
    filter.setConf(conf);

    NutchDocument doc = new NutchDocument();

    try {
      filter.filter(doc, parse, url, crawlDatum, inlinks);
    } catch (Exception e) {
      e.printStackTrace();
      fail(e.getMessage());
    }

    assertNotNull(doc);
    assertTrue("tests if no field is set for empty index.static", doc.getFieldNames().isEmpty());
  }
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
    conf.set("index.static",
        "field1:val1, field2    :      val2 val3     , field3, field4 :val4 , ");
    assertNotNull(filter);
    filter.setConf(conf);

    NutchDocument doc = new NutchDocument();

    try {
      filter.filter(doc, parse, url, crawlDatum, inlinks);
    } catch (Exception e) {
      e.printStackTrace();
      fail(e.getMessage());
    }

    assertNotNull(doc);
    assertFalse("test if doc is not empty", doc.getFieldNames().isEmpty());
    assertEquals("test if doc has 3 fields", 3, doc.getFieldNames().size());
    assertTrue("test if doc has field1", doc.getField("field1").getValues()
        .contains("val1"));
    assertTrue("test if doc has field2", doc.getField("field2").getValues()
        .contains("val2"));
    assertTrue("test if doc has field4", doc.getField("field4").getValues()
        .contains("val4"));
  }
View Full Code Here
56
57
58
59
60
61
62
63
64
65
  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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
      LOG.info("contentType: " + contentType);
    }

    ParseResult parseResult = new ParseUtil(conf).parse(content);
   
    NutchDocument doc = new NutchDocument();
    Text urlText = new Text(url);

    Inlinks inlinks = null;
    Parse parse = parseResult.get(urlText);
    try {
      indexers.filter(doc, parse, urlText, datum, inlinks);
    } catch (IndexingException e) {
      e.printStackTrace();
    }

    for (String fname : doc.getFieldNames()) {
      List<Object> values = doc.getField(fname).getValues();
      if (values != null) {
        for (Object value : values) {
          String str = value.toString();
          int minText = Math.min(100, str.length());
          System.out.println(fname + " :\t" + str.substring(0, minText));
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
  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
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
73
74
  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 site field", doc.getFieldNames().contains("site"));
  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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
  Configuration conf = NutchConfiguration.create();
  conf.setInt("indexer.max.title.length", 10);
  BasicIndexingFilter filter = new BasicIndexingFilter();
  filter.setConf(conf);
  assertNotNull(filter);
  NutchDocument doc = new NutchDocument();
  WebPage page = new WebPage();
  page.putToInlinks(new Utf8("http://exceedmaximumtitleurl.org/"), new Utf8("exceeding title site"));
  page.setTitle(new Utf8("This title exceeds maximum characters"));
  try {
    filter.filter(doc, "http://www.apache.org/", page);
  } catch (Exception e) {
    e.printStackTrace();
    fail(e.getMessage());
  }
  assertNotNull(doc);
  assertEquals("assert title field only has 10 characters", 10, doc.getFieldValue("title").length());
  }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
  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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
      LOG.info("contentType: " + contentType);
    }

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

    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();
    }

    if (doc == null) {
      System.out.println("Document discarded by indexing filter");
      return 0;
    }
   
    for (String fname : doc.getFieldNames()) {
      List<Object> values = doc.getField(fname).getValues();
      if (values != null) {
        for (Object value : values) {
          String str = value.toString();
          int minText = Math.min(100, str.length());
          System.out.println(fname + " :\t" + str.substring(0, minText));
View Full Code Here
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
    BasicIndexingFilter filter = new BasicIndexingFilter();
    filter.setConf(conf);
    assertNotNull(filter);

    NutchDocument doc = new NutchDocument();

    String title = "The Foo Page";
    Outlink[] outlinks = new Outlink[] { new Outlink("http://foo.com/", "Foo") };
    Metadata metaData = new Metadata();
    metaData.add("Language", "en/us");
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title, outlinks, metaData);
    ParseImpl parse = new ParseImpl("this is a sample foo bar page. hope you enjoy it.", parseData);

    CrawlDatum crawlDatum = new CrawlDatum();
    crawlDatum.setFetchTime(100L);

    Inlinks inlinks = new Inlinks();

    try {
      filter.filter(doc, parse, new Text("http://nutch.apache.org/index.html"), crawlDatum, inlinks);
    } catch(Exception e){
      e.printStackTrace();
      fail(e.getMessage());
    }
    assertNotNull(doc);
    assertEquals("test title, expect \"The Foo Pa\"", "The Foo Pa", doc.getField("title").getValues().get(0));
    assertEquals("test domain, expect \"apache.org\"", "apache.org", doc.getField("domain").getValues().get(0));
    assertEquals("test host, expect \"nutch.apache.org\"", "nutch.apache.org", doc.getField("host").getValues().get(0));
    assertEquals("test url, expect \"http://nutch.apache.org/index.html\"", "http://nutch.apache.org/index.html",
      doc.getField("url").getValues().get(0));
    assertEquals("test content", "this is a sample foo", doc.getField("content").getValues().get(0));
    assertEquals("test fetch time", new Date(100L), (Date)doc.getField("tstamp").getValues().get(0));
  }
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.