Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseImpl

121
122
123
124
125
126
127
128
129
130
131
    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
      final Text url = (Text) dbDatum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY);
      if (url != null) {
View Full Code Here
100
101
102
103
104
105
106
    final ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                                              resultTitle, outlinks,
                                              content.getMetadata());

    if (LOG.isTraceEnabled()) { LOG.trace("Zip file parsed sucessfully !!"); }
    return ParseResult.createParseResult(content.getUrl(), new ParseImpl(resultText, parseData));
  }
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
          Integer.toString(metaTags.getRefreshTime()) });
    }
    ParseData parseData = new ParseData(status, title, outlinks, content
        .getMetadata(), nutchMetadata);
    ParseResult parseResult = ParseResult.createParseResult(content
        .getUrl(), new ParseImpl(text, parseData));

    // run filters on parse
    ParseResult filteredParse = this.htmlParseFilters.filter(content,
        parseResult, metaTags, root);
    if (metaTags.getNoCache()) { // not okay to cache
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
    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 {
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
    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){
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
222
223
224
225
226
227
228
229
230
231
232
            catch (Exception e) {
              if (LOG.isWarnEnabled()) {
                LOG.warn("Couldn't pass score, url " + key + " (" + e + ")");
              }
            }
            output.collect(url, new NutchWritable(new ParseImpl(new ParseText(
              parse.getText()), parse.getData(), parse.isCanonical())));
          }
        }
      }
      catch (IOException e) {
View Full Code Here
258
259
260
261
262
263
264
265
266
267
268
    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
      final Text url = (Text) dbDatum.getMetaData().get(Nutch.WRITABLE_REPR_URL_KEY);
      if (url != null) {
View Full Code Here
196
197
198
199
200
201
202
        // }

        ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                contentTitle.toString(), outlinks, content.getMetadata());
        parseData.setConf(this.conf);
        return new ParseImpl(indexText.toString(), parseData);
    }
View Full Code Here
TOP

Related Classes of org.apache.nutch.parse.ParseImpl

  • org.apache.nutch.crawl.TextProfileSignature
  • org.apache.nutch.indexer.anchor.TestAnchorIndexingFilter
  • org.apache.nutch.indexer.basic.TestBasicIndexingFilter
  • org.apache.nutch.indexer.field.BasicFields$Extractor
  • org.apache.nutch.indexer.IndexerMapReduce
  • org.apache.nutch.indexer.more.TestMoreIndexingFilter
  • org.apache.nutch.indexer.staticfield.TestStaticFieldIndexerTest
  • org.apache.nutch.indexer.TestIndexingFilters
  • org.apache.nutch.parse.ext.ExtParser
  • org.apache.nutch.parse.ext.WaxExtParser
    • 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.