Package org.apache.nutch.metadata

Examples of org.apache.nutch.metadata.Metadata

77
78
79
80
81
82
83
84
85
86
87
88
      assertEquals(expected[i], parts[i]);
    }
  }
 
  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());
View Full Code Here
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
        fetchDatum.getStatus() != CrawlDatum.STATUS_FETCH_SUCCESS) {
      return;
    }

    NutchDocument doc = new NutchDocument();
    final Metadata metadata = parseData.getContentMeta();

    // add segment, used to map from merged index back to segment files
    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
View Full Code Here
60
61
62
63
64
65
66
  private Metadata metadata;

  private MimeUtil mimeTypes;

  public Content() {
    metadata = new Metadata();
  }
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
    urlString = "file:" + sampleDir + fileSeparator + id3v2;
    protocol = new ProtocolFactory(conf).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum())
                      .getContent();
    parse = new ParseUtil(conf).parseByExtensionId("parse-mp3", content).get(urlString);
    Metadata metadata = parse.getData().getParseMeta();
    assertEquals("postgresql comment id3v2", metadata.get("COMM-Text"));
    assertEquals("postgresql composer id3v2", metadata.get("TCOM-Text"));
    assertEquals("02", metadata.get("TRCK-Text"));
    assertEquals("http://localhost/", metadata.get("WCOP-URL Link"));
    assertEquals("postgresql artist id3v2", metadata.get("TPE1-Text"));
    assertEquals("(28)", metadata.get("TCON-Text"));
    assertEquals("2004", metadata.get("TYER-Text"));
    assertEquals("postgresql title id3v2", metadata.get("TIT2-Text"));
    assertEquals("postgresql album id3v2", metadata.get("TALB-Text"));
    assertEquals("postgresql encoded by id3v2", metadata.get("TENC-Text"));

    assertEquals("postgresql title id3v2 - "
        + "postgresql album id3v2 - "
        + "postgresql artist id3v2", parse.getData().getTitle());
    assertEquals("http://localhost/", parse.getData().getOutlinks()[0].getToUrl());
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
    protocol = new ProtocolFactory(conf).getProtocol(urlString);
    content = protocol.getProtocolOutput(new Text(urlString), new CrawlDatum())
                      .getContent();
    parse = new ParseUtil(conf).parseByExtensionId("parse-mp3", content).get(urlString);

    Metadata metadata = parse.getData().getParseMeta();
    assertEquals("postgresql comment id3v1", metadata.get("COMM-Text"));
    assertEquals("postgresql artist id3v1", metadata.get("TPE1-Text"));
    assertEquals("(28)", metadata.get("TCON-Text"));
    assertEquals("2004", metadata.get("TYER-Text"));
    assertEquals("postgresql title id3v1", metadata.get("TIT2-Text"));
    assertEquals("postgresql album id3v1", metadata.get("TALB-Text"));

    assertEquals("postgresql title id3v1 - "
        + "postgresql album id3v1 - "
        + "postgresql artist id3v1", parse.getData().getTitle());
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
  private Document createLuceneDoc(NutchDocument doc) {
    final Document out = new Document();

    out.setBoost(doc.getScore());

    final Metadata documentMeta = doc.getDocumentMeta();
    for (final Entry<String, List<String>> entry : doc) {
      final String fieldName = entry.getKey();

      Field.Store store = fieldStore.get(fieldName);
      Field.Index index = fieldIndex.get(fieldName);
      Field.TermVector vector = fieldVector.get(fieldName);

      // default values
      if (store == null) {
        store = Field.Store.NO;
      }

      if (index == null) {
        index = Field.Index.NO;
      }

      if (vector == null) {
        vector = Field.TermVector.NO;
      }

      // read document-level field information
      final String[] fieldMetas =
        documentMeta.getValues(LuceneConstants.FIELD_PREFIX + fieldName);
      if (fieldMetas.length != 0) {
        for (final String val : fieldMetas) {
          if (LuceneConstants.STORE_YES.equals(val)) {
            store = Field.Store.YES;
          } else if (LuceneConstants.STORE_NO.equals(val)) {
View Full Code Here
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
   * */
  @Deprecated
  public static void add(NutchDocument doc, Field f) {
    final String fieldName = f.name();
    final String key = LuceneConstants.FIELD_PREFIX + fieldName;
    final Metadata documentMeta = doc.getDocumentMeta();
    if (f.isStored()) {
      documentMeta.add(key, LuceneConstants.STORE_YES);
    } else if (f.isCompressed()) {
      documentMeta.add(key, LuceneConstants.STORE_COMPRESS);
    } else {
      documentMeta.add(key, LuceneConstants.STORE_NO);
    }

    if (f.isIndexed()) {
      if (f.isTokenized()) {
        documentMeta.add(key, LuceneConstants.INDEX_TOKENIZED);
      } else if (f.getOmitNorms()) {
        documentMeta.add(key, LuceneConstants.INDEX_NO_NORMS);
      } else {
        documentMeta.add(key, LuceneConstants.INDEX_UNTOKENIZED);
      }
    } else {
      documentMeta.add(key, LuceneConstants.INDEX_NO);
    }

    if (f.isStoreOffsetWithTermVector() && f.isStorePositionWithTermVector()) {
      documentMeta.add(key, LuceneConstants.VECTOR_POS_OFFSET);
    } else if (f.isStoreOffsetWithTermVector()) {
      documentMeta.add(key, LuceneConstants.VECTOR_OFFSET);
    } else if (f.isStorePositionWithTermVector()) {
      documentMeta.add(key, LuceneConstants.VECTOR_POS);
    } else if (f.isTermVectorStored()) {
      documentMeta.add(key, LuceneConstants.VECTOR_YES);
    } else {
      documentMeta.add(key, LuceneConstants.VECTOR_NO);
    }
  }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
  }

  /** Unit tests for getContentType(String, String, byte[]) method. */
  public void testGetContentType() throws Exception {
    Content c = null;
    Metadata p = new Metadata();

    c = new Content("http://www.foo.com/",
                    "http://www.foo.com/",
                    "".getBytes("UTF8"),
                    "text/html; charset=UTF-8", p, conf);
View Full Code Here
146
147
148
149
150
151
152
153
154
155
156
157
158
      Text key = new Text();
      ParseData value = new ParseData();
      if(!reader.next(key, value)) break READ_PARSE_DATA;
      // make sure they all contain "nutch.segment.name" and "nutch.content.digest"
      // keys in parse metadata
      Metadata contentMeta = value.getContentMeta();
      if (contentMeta.get(Nutch.SEGMENT_NAME_KEY) != null
            && contentMeta.get(Nutch.SIGNATURE_KEY) != null) {
        handledurls.add(key.toString());
      }
    } while(true);
   
    Collections.sort(handledurls);
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
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 testGuessing() {
    // first disable auto detection
    conf.setInt(EncodingDetector.MIN_CONFIDENCE_KEY, -1);

    Metadata metadata = new Metadata();
    EncodingDetector detector;
    Content content;
    String encoding;

    content = new Content("http://www.example.com", "http://www.example.com/",
        contentInOctets, "text/plain", metadata, conf);
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(content, true);
    encoding = detector.guessEncoding(content, "windows-1252");
    // no information is available, so it should return default encoding
    assertEquals("windows-1252", encoding.toLowerCase());

    metadata.clear();
    metadata.set(Response.CONTENT_TYPE, "text/plain; charset=UTF-16");
    content = new Content("http://www.example.com", "http://www.example.com/",
        contentInOctets, "text/plain", metadata, conf);
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(content, true);
    encoding = detector.guessEncoding(content, "windows-1252");
    assertEquals("utf-16", encoding.toLowerCase());

    metadata.clear();
    content = new Content("http://www.example.com", "http://www.example.com/",
        contentInOctets, "text/plain", metadata, conf);
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(content, true);
    detector.addClue("windows-1254", "sniffed");
    encoding = detector.guessEncoding(content, "windows-1252");
    assertEquals("windows-1254", encoding.toLowerCase());

    // enable autodetection
    conf.setInt(EncodingDetector.MIN_CONFIDENCE_KEY, 50);
    metadata.clear();
    metadata.set(Response.CONTENT_TYPE, "text/plain; charset=UTF-16");
    content = new Content("http://www.example.com", "http://www.example.com/",
        contentInOctets, "text/plain", metadata, conf);
    detector = new EncodingDetector(conf);
    detector.autoDetectClues(content, true);
    detector.addClue("utf-32", "sniffed");
View Full Code Here
TOP

Related Classes of org.apache.nutch.metadata.Metadata

  • com.atlantbh.nutch.filter.index.omit.OmitIndexingFilter
  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilter
  • com.atlantbh.nutch.filter.xpath.XPathHtmlParserFilterTest
  • com.atlantbh.nutch.filter.xpath.XPathIndexingFilter
  • com.atlantbh.nutch.filter.xpath.XPathIndexingFilterTest
  • com.atlantbh.nutch.index.alternativedataflow.flow.CsvDataFlow
  • com.flaptor.hounder.crawler.Nutch9Fetcher$NutchSegment$SegmentIterator
  • org.apache.nutch.analysis.lang.TestHTMLLanguageParser
  • org.apache.nutch.fetcher.Fetcher$FetcherThread
  • org.apache.nutch.fetcher.Fetcher2$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.