Package org.apache.lucene.search.similar

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

73
74
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
    if (nGramSize > 1) { //<co id="mlt.ngramsetup"/>
      analyzer = new ShingleAnalyzerWrapper(analyzer, nGramSize,
              nGramSize);
    }
   
    MoreLikeThis moreLikeThis  = new MoreLikeThis(indexReader); //<co id="mlt.configure"/>
    moreLikeThis.setAnalyzer(analyzer);
    moreLikeThis.setFieldNames(new String[] {
      "content"
    });
   
/*<calloutlist>
<callout arearefs="mlt.indexsetup">Open Index</callout>
<callout arearefs="mlt.analyzersetup">Setup Analyzer</callout>
<callout arearefs="mlt.ngramsetup">Setup NGrams</callout>
<callout arearefs="mlt.configure">Create <classname>MoreLikeThis</classname></callout>
</calloutlist>*/
    //<end id="lucene.examples.mlt.setup"/>
   
    // for testing against the same corpus
    moreLikeThis.setMinTermFreq(1);
    moreLikeThis.setMinDocFreq(1);
   
    //<start id="lucene.examples.mlt.query"/>
    Reader reader = new FileReader(inputPath); //<co id="mlt.query"/>
    Query query = moreLikeThis.like(reader);

    TopDocs results
      = indexSearcher.search(query, maxResults); //<co id="mlt.search"/>
   
    HashMap<String, CategoryHits> categoryHash
View Full Code Here
257
258
259
260
261
262
263
264
265
266
267
      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
75
76
77
78
79
80
81
82
83
  int maxResults = 10;
 
  public MoreLikeThisCategorizer(IndexReader indexReader, String categoryFieldName) throws IOException {
    this.indexReader   = indexReader;
    this.indexSearcher = new IndexSearcher(indexReader);
    this.moreLikeThis  = new MoreLikeThis(indexReader);
    this.categoryFieldName = categoryFieldName;
    loadCategoriesFromIndex();
  }
View Full Code Here
257
258
259
260
261
262
263
264
265
266
267
      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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
    this.fieldName = fieldName;
  }
 
  @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 StringReader(likeText), fieldName);
    BooleanClause[] clauses = bq.getClauses();
    // make at least half the terms match
    bq.setMinimumNumberShouldMatch((int) (clauses.length * percentTermsToMatch));
    return bq;
  }
View Full Code Here
246
247
248
249
250
251
252
253
254
255
256
      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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
        this.moreLikeFields = moreLikeFields;
        this.analyzer = analyzer;
    }

    @Override public Query rewrite(IndexReader reader) throws IOException {
        MoreLikeThis mlt = new MoreLikeThis(reader, similarity == null ? new DefaultSimilarity() : similarity);

        mlt.setFieldNames(moreLikeFields);
        mlt.setAnalyzer(analyzer);
        mlt.setMinTermFreq(minTermFrequency);
        mlt.setMinDocFreq(minDocFreq);
        mlt.setMaxDocFreq(maxDocFreq);
        mlt.setMaxQueryTerms(maxQueryTerms);
        mlt.setMinWordLen(minWordLen);
        mlt.setMaxWordLen(maxWordLen);
        mlt.setStopWords(stopWords);
        mlt.setBoost(boostTerms);
        mlt.setBoostFactor(boostTermsFactor);
        BooleanQuery bq = (BooleanQuery) mlt.like(new FastStringReader(likeText));
        BooleanClause[] clauses = bq.getClauses();

        bq.setMinimumNumberShouldMatch((int) (clauses.length * percentTermsToMatch));
        return bq;
    }
View Full Code Here
246
247
248
249
250
251
252
253
254
255
256
      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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
        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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
        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
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.