Package org.apache.lucene.search.similar

Examples of org.apache.lucene.search.similar.MoreLikeThis

255
256
257
258
259
260
261
262
263
264
265
      if( fields.length < 1 ) {
        throw new SolrException( SolrException.ErrorCode.BAD_REQUEST,
            "MoreLikeThis requires at least one similarity field: "+MoreLikeThisParams.SIMILARITY_FIELDS );
      }
     
      this.mlt = new MoreLikeThis( reader ); // TODO -- after LUCENE-896, we can use , searcher.getSimilarity() );
      mlt.setFieldNames(fields);
      mlt.setAnalyzer( searcher.getSchema().getAnalyzer() );
     
      // configurable params
      mlt.setMinTermFreq(       params.getInt(MoreLikeThisParams.MIN_TERM_FREQ,         MoreLikeThis.DEFAULT_MIN_TERM_FREQ));
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
        this.analyzer=analyzer;
    }
   
    public Query rewrite(IndexReader reader) throws IOException
    {
        MoreLikeThis mlt=new MoreLikeThis(reader);
       
        mlt.setFieldNames(moreLikeFields);
        mlt.setAnalyzer(analyzer);
        mlt.setMinTermFreq(minTermFrequency);
        mlt.setMaxQueryTerms(maxQueryTerms);
        BooleanQuery bq= (BooleanQuery) mlt.like(new ByteArrayInputStream(likeText.getBytes()));       
        BooleanClause[] clauses = bq.getClauses();
        //make at least half the terms match
        bq.setMinimumNumberShouldMatch((int)(clauses.length*percentTermsToMatch));
        return bq;
    }
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
        this.analyzer=analyzer;
    }
   
    public Query rewrite(IndexReader reader) throws IOException
    {
        MoreLikeThis mlt=new MoreLikeThis(reader);
       
        mlt.setFieldNames(moreLikeFields);
        mlt.setAnalyzer(analyzer);
        mlt.setMinTermFreq(minTermFrequency);
        if(minDocFreq>=0)
        {
          mlt.setMinDocFreq(minDocFreq);
        }       
        mlt.setMaxQueryTerms(maxQueryTerms);
        mlt.setStopWords(stopWords);
        BooleanQuery bq= (BooleanQuery) mlt.like(new ByteArrayInputStream(likeText.getBytes()));       
        BooleanClause[] clauses = bq.getClauses();
        //make at least half the terms match
        bq.setMinimumNumberShouldMatch((int)(clauses.length*percentTermsToMatch));
        return bq;
    }
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
        this.analyzer=analyzer;
    }
   
    public Query rewrite(IndexReader reader) throws IOException
    {
        MoreLikeThis mlt=new MoreLikeThis(reader);
       
        mlt.setFieldNames(moreLikeFields);
        mlt.setAnalyzer(analyzer);
        mlt.setMinTermFreq(minTermFrequency);
        mlt.setMaxQueryTerms(maxQueryTerms);
        mlt.setStopWords(stopWords);
        BooleanQuery bq= (BooleanQuery) mlt.like(new ByteArrayInputStream(likeText.getBytes()));       
        BooleanClause[] clauses = bq.getClauses();
        //make at least half the terms match
        bq.setMinimumNumberShouldMatch((int)(clauses.length*percentTermsToMatch));
        return bq;
    }
View Full Code Here
474
475
476
477
478
479
480
481
482
483
484
485
486
        //val filter = new FieldCacheTermsFilter(DBpediaResourceField.CONTEXT.toString,allowedUris)
        TermsFilter filter = new org.apache.lucene.search.TermsFilter();
        for (DBpediaResource u:  allowedUris) {
            filter.addTerm(new Term(DBpediaResourceField.URI.toString(),u.uri()) );
        }
        MoreLikeThis mlt = new MoreLikeThis(reader);
        String[] fields = {DBpediaResourceField.CONTEXT.toString()};
        mlt.setFieldNames(fields);
        mlt.setAnalyzer(this.mDefaultAnalyzer);
        InputStream inputStream = new ByteArrayInputStream(text.text().getBytes("UTF-8"));
        Query query = mlt.like(inputStream);
        return query;
    }
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
    }
   
    @Override
    public Query rewrite(IndexReader reader) throws IOException
    {
        MoreLikeThis mlt=new MoreLikeThis(reader);
       
        mlt.setFieldNames(moreLikeFields);
        mlt.setAnalyzer(analyzer);
        mlt.setMinTermFreq(minTermFrequency);
        if(minDocFreq>=0)
        {
          mlt.setMinDocFreq(minDocFreq);
        }       
        mlt.setMaxQueryTerms(maxQueryTerms);
        mlt.setStopWords(stopWords);
        BooleanQuery bq= (BooleanQuery) mlt.like(new ByteArrayInputStream(likeText.getBytes()));       
        BooleanClause[] clauses = bq.getClauses();
        //make at least half the terms match
        bq.setMinimumNumberShouldMatch((int)(clauses.length*percentTermsToMatch));
        return bq;
    }
View Full Code Here
TOP

Related Classes of org.apache.lucene.search.similar.MoreLikeThis

  • com.tamingtext.classifier.mlt.MoreLikeThisCategorizer
  • com.tamingtext.classifier.mlt.MoreLikeThisQueryTest
  • org.apache.lucene.analysis.Token
  • org.apache.lucene.analysis.tokenattributes.CharTermAttribute
  • org.apache.lucene.analysis.tokenattributes.TermAttribute
  • org.apache.lucene.analysis.TokenStream
  • org.apache.lucene.document.Document
  • org.apache.lucene.index.IndexReader
  • org.apache.lucene.index.Term
  • org.apache.lucene.index.TermFreqVector
    • 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.