Package org.apache.nutch.indexer

Examples of org.apache.nutch.indexer.NutchSimilarity

73
74
75
76
77
78
79
80
81
  }

  private void init(IndexReader reader, Configuration conf) throws IOException {
    this.reader = reader;
    this.luceneSearcher = new org.apache.lucene.search.IndexSearcher(reader);
    this.luceneSearcher.setSimilarity(new NutchSimilarity());
    this.optimizer = new LuceneQueryOptimizer(conf);
    this.queryFilters = new QueryFilters(conf);
  }
View Full Code Here
226
227
228
229
230
231
232
233
234
        .getInt("indexer.maxMergeDocs", Integer.MAX_VALUE));
    writer.setTermIndexInterval(job.getInt("indexer.termIndexInterval", 128));
    writer.setMaxFieldLength(job.getInt("indexer.max.tokens", 10000));
    writer.setInfoStream(LogUtil.getDebugStream(Indexer.LOG));
    writer.setUseCompoundFile(false);
    writer.setSimilarity(new NutchSimilarity());

    processOptions(job);
  }
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
        Integer.MAX_VALUE));
      writer.setTermIndexInterval(job.getInt("indexer.termIndexInterval", 128));
      writer.setMaxFieldLength(job.getInt("indexer.max.tokens", 10000));
      writer.setInfoStream(LogUtil.getInfoStream(LOG));
      writer.setUseCompoundFile(false);
      writer.setSimilarity(new NutchSimilarity());

      return new RecordWriter<WritableComparable, LuceneDocumentWrapper>() {
        boolean closed;

        public void write(WritableComparable key, LuceneDocumentWrapper value)
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
          extractorBean.readQueries(args[2]);
                           
          Directory idx = FSDirectory.getDirectory(args[1], false);
          org.apache.lucene.search.Searcher searcher = new IndexSearcher(idx);
          org.apache.lucene.index.IndexReader reader=IndexReader.open(idx);
          searcher.setSimilarity(new NutchSimilarity()); // line ignored; ranking is hard coded in lucene                 
         
            BufferedReader in = new BufferedReader(new FileReader(args[0]));
            String str;
            String splitStr[]=null;
            String qid=null;      
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
        Integer.MAX_VALUE));
      writer.setTermIndexInterval(job.getInt("indexer.termIndexInterval", 128));
      writer.setMaxFieldLength(job.getInt("indexer.max.tokens", 10000));
      writer.setInfoStream(LogUtil.getInfoStream(LOG));
      writer.setUseCompoundFile(false);
      writer.setSimilarity(new NutchSimilarity());

      return new RecordWriter<WritableComparable, LuceneDocumentWrapper>() {
        boolean closed;

        public void write(WritableComparable key, LuceneDocumentWrapper value)
View Full Code Here
221
222
223
224
225
226
227
228
229
        .getInt("indexer.maxMergeDocs", Integer.MAX_VALUE));
    writer.setTermIndexInterval(job.getInt("indexer.termIndexInterval", 128));
    writer.setMaxFieldLength(job.getInt("indexer.max.tokens", 10000));
    writer.setInfoStream(LogUtil.getDebugStream(Indexer.LOG));
    writer.setUseCompoundFile(false);
    writer.setSimilarity(new NutchSimilarity());

    processOptions(job);
  }
View Full Code Here
72
73
74
75
76
77
78
79
80
  }

  private void init(IndexReader reader, Configuration conf) throws IOException {
    this.reader = reader;
    this.luceneSearcher = new org.apache.lucene.search.IndexSearcher(reader);
    this.luceneSearcher.setSimilarity(new NutchSimilarity());
    this.optimizer = new LuceneQueryOptimizer(conf);
    this.queryFilters = new QueryFilters(conf);
  }
View Full Code Here
129
130
131
132
133
134
135
136
137
138
139
        Integer.MAX_VALUE));
      writer.setTermIndexInterval(job.getInt("indexer.termIndexInterval", 128));
      writer.setMaxFieldLength(job.getInt("indexer.max.tokens", 10000));
      writer.setInfoStream(LogUtil.getInfoStream(LOG));
      writer.setUseCompoundFile(false);
      writer.setSimilarity(new NutchSimilarity());

      return new RecordWriter<WritableComparable, LuceneDocumentWrapper>() {
        boolean closed;

        public void write(WritableComparable key, LuceneDocumentWrapper value)
View Full Code Here
223
224
225
226
227
228
229
230
231
        .getInt("indexer.maxMergeDocs", Integer.MAX_VALUE));
    writer.setTermIndexInterval(job.getInt("indexer.termIndexInterval", 128));
    writer.setMaxFieldLength(job.getInt("indexer.max.tokens", 10000));
    writer.setInfoStream(LogUtil.getDebugStream(Indexer.LOG));
    writer.setUseCompoundFile(false);
    writer.setSimilarity(new NutchSimilarity());

    processOptions(job);
  }
View Full Code Here
TOP

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

  • org.apache.nutch.indexer.field.FieldIndexer$OutputFormat
  • org.apache.nutch.indexer.lucene.LuceneWriter
  • org.apache.nutch.searcher.IndexSearcher
  • org.archive.nutch.trec.TRECFeaturesExtractor
    • 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.