Example usage for org.apache.lucene.search BooleanQuery BooleanQuery

List of usage examples for org.apache.lucene.search BooleanQuery BooleanQuery

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.*
  5. BooleanQuery
  6. BooleanQuery

Introduction

In this page you can find the example usage for org.apache.lucene.search BooleanQuery BooleanQuery.

Prototype

BooleanQuery

Source Link

Usage

From source file:edu.uic.cs.t_verifier.index.synonym.WordNetSynonymEngine.java

License:Apache License

public String[] getSynonyms(String word) throws IOException {
    // List<String> synList = new ArrayList<String>();
    Set<String> synList = new TreeSet<String>();

    AllDocCollector collector = new AllDocCollector(); // #A

    String stemmedWord = stemmer.stem(word);
    // System.out.print("\n>>>>> " + word + " " + stemmedWord);

    Query originalWordQuery = new TermQuery(new Term("word", word));
    Query stemmedWordQuery = new TermQuery(new Term("word", stemmedWord));
    BooleanQuery query = new BooleanQuery();
    query.add(originalWordQuery, Occur.SHOULD);
    query.add(stemmedWordQuery, Occur.SHOULD);

    searcher.search(query, collector);/* w  w  w .j av  a  2s .c o  m*/

    for (ScoreDoc hit : collector.getHits()) { // #B
        Document doc = searcher.doc(hit.doc);

        String[] values = doc.getValues("syn");

        for (String syn : values) { // #C
            synList.add(syn);
        }
    }

    return synList.toArray(new String[0]);
}

From source file:edu.unika.aifb.graphindex.searcher.entity.EntitySearcher.java

License:Open Source License

public Collection<String> searchConceptWithClause(IndexSearcher searcher, Query clause) {
    Collection<String> result = new HashSet<String>();
    try {/*from  w  ww  .ja  v a  2 s . c  o m*/
        Hits hits = searcher.search(clause);
        /********* add fuzzy query funtion here **************/
        if (hits == null || hits.length() == 0) {
            Set<Term> terms = new HashSet<Term>();
            clause.extractTerms(terms);
            //if clause query is a term query
            if (terms.size() != 0) {
                BooleanQuery query = new BooleanQuery();
                for (Term term : terms) {
                    query.add(new FuzzyQuery(term, 0.8f, 1), Occur.MUST);
                }
                hits = searcher.search(query);
                log.debug(query + " " + hits);
            }
        }
        /************************************************/

        for (int i = 0; i < hits.length(); i++) {
            Document doc = hits.doc(i);
            float score = hits.score(i);
            if (score >= SCHEMA_THRESHOLD) {
                String type = doc.get(Constant.TYPE_FIELD);
                if (type == null) {
                    System.err.println("type is null!");
                    continue;
                }

                if (type.equals(TypeUtil.CONCEPT)) {
                    result.add(doc.get(Constant.URI_FIELD));
                }
            }
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
    return result;
}

From source file:edu.unika.aifb.graphindex.searcher.entity.EntitySearcher.java

License:Open Source License

public Collection<String> searchAttributesWithClause(IndexSearcher searcher, Query clause) {
    Collection<String> result = new HashSet<String>();
    try {//  w w w  . j  av a2 s  .c  o  m
        Hits hits = searcher.search(clause);
        /********* add fuzzy query funtion here **************/
        if (hits == null || hits.length() == 0) {
            Set<Term> terms = new HashSet<Term>();
            clause.extractTerms(terms);
            //if clause query is a term query
            if (terms.size() != 0) {
                BooleanQuery query = new BooleanQuery();
                for (Term term : terms) {
                    query.add(new FuzzyQuery(term, 0.8f, 1), Occur.MUST);
                }
                hits = searcher.search(query);
                log.debug(query + " " + hits);
            }
        }
        /************************************************/

        for (int i = 0; i < hits.length(); i++) {
            Document doc = hits.doc(i);
            float score = hits.score(i);
            if (score >= SCHEMA_THRESHOLD) {
                String type = doc.get(Constant.TYPE_FIELD);
                if (type == null) {
                    System.err.println("type is null!");
                    continue;
                }

                if (type.equals(TypeUtil.ATTRIBUTE)) {
                    result.add(doc.get(Constant.URI_FIELD));
                }
            }
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
    return result;
}

From source file:edu.unika.aifb.graphindex.searcher.entity.EntitySearcher.java

License:Open Source License

private void searchEntitiesByAttributeVauleCompounds(IndexSearcher searcher,
        Map<String, Collection<String>> queries, Map<String, Collection<String>> attributes,
        Collection<String> concepts, Collection<KeywordElement> entities, int cutOff) {
    BooleanQuery entityQuery = new BooleanQuery();
    try {/*from   w  ww  . j  a v a  2s  . co m*/
        StandardAnalyzer analyzer = new StandardAnalyzer();
        for (String keywordForAttribute : queries.keySet()) {
            BooleanQuery attributeQuery = new BooleanQuery();
            Collection<String> attributeElements = attributes.get(keywordForAttribute);
            if (attributeElements != null && attributeElements.size() != 0)
                for (String attribute : attributeElements) {
                    QueryParser parser = new QueryParser(attribute, analyzer);
                    BooleanQuery bq = new BooleanQuery();
                    for (String value : queries.get(keywordForAttribute)) {
                        Query q = parser.parse(value);
                        if (q instanceof BooleanQuery) {
                            BooleanQuery bquery = (BooleanQuery) q;
                            for (BooleanClause clause : bquery.getClauses()) {
                                clause.setOccur(Occur.MUST);
                            }
                        }
                        bq.add(q, BooleanClause.Occur.MUST);
                    }
                    attributeQuery.add(bq, BooleanClause.Occur.SHOULD);
                }
            entityQuery.add(attributeQuery, BooleanClause.Occur.MUST);
        }
        if (concepts != null && concepts.size() != 0) {
            BooleanQuery typeQuery = new BooleanQuery();
            for (String type : concepts) {
                TermQuery tq = new TermQuery(new Term(Constant.CONCEPT_FIELD, type));
                typeQuery.add(tq, BooleanClause.Occur.MUST);
            }
            entityQuery.add(typeQuery, BooleanClause.Occur.MUST);
        }

        searchEntitiesWithClause(searcher, entityQuery, entities, cutOff);
    } catch (ParseException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}

From source file:edu.unika.aifb.graphindex.searcher.keyword.KeywordQueryParser.java

License:Open Source License

public Query parse(String query, String[] fields) throws ParseException {
    BooleanQuery bQuery = new BooleanQuery();
    for (int i = 0; i < fields.length; i++) {
        QueryParser qp = new QueryParser(fields[i], getAnalyzer());
        qp.setDefaultOperator(QueryParser.AND_OPERATOR);
        Query q = qp.parse(query);
        bQuery.add(q, Occur.SHOULD);//from  ww w.  j  av a 2 s.c  om
    }
    return bQuery;
}

From source file:edu.unika.aifb.graphindex.searcher.keyword.KeywordQueryParser.java

License:Open Source License

public Query parse(String query) throws ParseException {
    BooleanQuery bQuery = new BooleanQuery();
    for (int i = 0; i < fields.length; i++) {
        QueryParser qp = new QueryParser(fields[i], getAnalyzer());
        qp.setDefaultOperator(QueryParser.AND_OPERATOR);
        Query q = qp.parse(query);
        bQuery.add(q, Occur.SHOULD);/*from   ww  w  . j av a  2  s  . c om*/
    }
    return bQuery;
}

From source file:edu.unika.aifb.graphindex.searcher.keyword.KeywordSearcher.java

License:Open Source License

private void searchEntitiesByAttributesAndValues(SortedSet<KeywordSegment> segements,
        Map<String, Collection<KeywordElement>> attributes,
        Map<KeywordElement, KeywordSegment> entities2Segement,
        Map<KeywordSegment, Collection<KeywordElement>> segments2Entities,
        Map<String, Collection<KeywordElement>> keywords2Entities) throws IOException {

    StandardAnalyzer analyzer = new StandardAnalyzer();

    Set<KeywordSegment> segementsWithResults = new HashSet<KeywordSegment>();
    for (String keywordForAttribute : attributes.keySet()) {
        for (KeywordElement attribute : attributes.get(keywordForAttribute)) {
            QueryParser parser = new QueryParser(Constant.CONTENT_FIELD, analyzer);
            parser.setDefaultOperator(QueryParser.AND_OPERATOR);

            for (KeywordSegment segement : segements) {
                try {
                    BooleanQuery q = new BooleanQuery();
                    Query valueQuery = parser.parse(segement.getQuery());
                    Query attributeQuery = new TermQuery(
                            new Term(Constant.ATTRIBUTE_FIELD, attribute.getUri()));
                    q.add(valueQuery, Occur.MUST);
                    q.add(attributeQuery, Occur.MUST);
                    boolean hasResults = searchEntitiesWithClause(q, segement, keywordForAttribute,
                            entities2Segement, segments2Entities, keywords2Entities);

                    if (hasResults)
                        segementsWithResults.add(segement);
                } catch (ParseException e) {
                    e.printStackTrace();
                    continue;
                }/*from  w  ww  .  ja  v  a 2s . c o m*/
            }
        }
    }
}

From source file:edu.virginia.cs.searcher.PostSearcher.java

/**
 * The main search function./* w ww  .j  ava2s . c o m*/
 *
 * @param searchQuery Set this object's attributes as needed.
 * @return
 */
private SearchResult search(SearchQuery searchQuery) {
    searchQuery.numResults(numOfResults);
    BooleanQuery combinedQuery = new BooleanQuery();
    for (String field : searchQuery.fields()) {
        QueryParser parser = new QueryParser(Version.LUCENE_46, field, analyzer);
        try {
            Query textQuery = parser.parse(parser.escape(searchQuery.queryText()));
            combinedQuery.add(textQuery, BooleanClause.Occur.MUST);
        } catch (ParseException exception) {
            exception.printStackTrace();
        }
    }
    return runSearch(combinedQuery, searchQuery);
}

From source file:engine.easy.search.RelevanceFeedBackUtil.java

License:Apache License

/**
 * Computes a term frequency map for the specific terms at the specified location.
 * Builds a Boolean OR query out of the "most frequent" terms in the index
 * and returns it. "Most Frequent" is defined as the terms whose frequencies
 * are greater than or equal to the topTermCutoff * the frequency of the top
 * term, where the topTermCutoff is number between 0 and 1.
 * /*ww  w.  j a v  a 2 s. com*/
 * @param ramdir the directory where the index is created.
 * @return a Boolean OR query.
 * @throws Exception if one is thrown.
 */
private static Query computeTopTermQuery(List<String> termlist, Map<String, Integer> frequencyMap, int numOf)
        throws Exception {

    // sort the term map by frequency descending
    Collections.sort(termlist, new ReverseComparator(new ByValueComparator<String, Integer>(frequencyMap)));

    // retrieve the top terms based on topTermCutoff
    List<String> topTerms = new ArrayList<String>();
    float topFreq = -1.0F;
    for (String term : termlist) {
        if (topFreq < 0.0F) {
            // first term, capture the value
            topFreq = (float) frequencyMap.get(term);
            topTerms.add(term);
        } else {
            // not the first term, compute the ratio and discard if below
            // topTermCutoff score
            float ratio = (float) ((float) frequencyMap.get(term) / topFreq);
            if (ratio >= AppConstants.TOP_TERM_CUT_OFF_FREQ) {
                topTerms.add(term);
            } else {
                break;
            }
        }
    }
    //
    //      //Top results
    //      List<String> topArray = null;
    //      if (topTerms.size() > numOf) {
    //         topArray = new ArrayList<String>(numOf);
    //
    //         for (int position=0; position < numOf; position++) {
    //            topArray.add(topTerms.get(position));
    //         }
    //      }
    //      else {
    //         topArray = topTerms;
    //      }

    StringBuilder termBuf = new StringBuilder();
    BooleanQuery q = new BooleanQuery();
    for (String topTerm : topTerms) {
        termBuf.append(topTerm).append("(").append(frequencyMap.get(topTerm)).append(");");
        q.add(new TermQuery(new Term("CONTENT", topTerm)), Occur.SHOULD);
    }
    System.out.println(">>> top terms: " + termBuf.toString());
    System.out.println(">>> query: " + q.toString());
    return q;
}

From source file:es.pode.indexador.negocio.servicios.busqueda.SrvBuscadorServiceImpl.java

License:Open Source License

/**
 * @see es.pode.indexador.negocio.servicios.busqueda.SrvBuscadorServiceBase#handleSolicitudDocsCountArbolCurricular(ParamDocsCountVO)
 * //from w w  w  .  j  a v  a 2  s  .c  o  m
 * @param ParamDocsCountVO VO que alberga los parametros que acepta una solicitud de numero de documentos para el nodo de un arbol curricular.
 * @return ResultadosCountVO VO que alberga el resultado de la solicitud de la suma de documentos para un nodo de arbol curricular.
 */
protected ResultadosCountVO handleSolicitudDocsCount(ParamDocsCountVO paramBusq) throws Exception {
    //      logger.debug("SrvBuscadorServiceImpl - handleSolicitudDocsCount: AreaCurricular=" + array2String(paramBusq.getAreaCurricular())+ ", Tesauros="+array2String(paramBusq.getTesauros()));
    //      return NumTermsArbol.obtenerNumeroNodos(paramBusq.getAreaCurricular(),getIndexPathByLanguage(paramBusq.getIdiomaBusqueda()),(paramBusq.getAreaCurricular()!=null && paramBusq.getAreaCurricular().length > 0)?"areaCurricular":"tesauro");
    Directory directorioIndiceSimple = this.getIndexByLanguage(paramBusq.getIdiomaBusqueda());
    IndexSearcher searcher = new IndexSearcher(directorioIndiceSimple);
    ResultadosCountVO resultado = new ResultadosCountVO();
    searcher.setSimilarity(new DefaultSimilarity());
    int suma = 0;
    if (paramBusq.getAreaCurricular() != null && paramBusq.getAreaCurricular().length > 0) {
        resultado.setConteo(new Integer[paramBusq.getAreaCurricular().length]);
        for (int i = 0; i < paramBusq.getAreaCurricular().length; i++) {
            BooleanQuery andQuery = new BooleanQuery();
            andQuery.add(
                    getTermQuery(props.getProperty(CAMPO_AREA_CURRICULAR), paramBusq.getAreaCurricular()[i]),
                    BooleanClause.Occur.MUST);
            andQuery.add(getTermQuery(props.getProperty(CAMPO_ARBOL_CURRICULAR_VIGENTE),
                    paramBusq.getArbolCurricularVigente()), BooleanClause.Occur.MUST);
            Hits hits = searcher.search(andQuery);
            resultado.getConteo()[i] = new Integer(hits.length());
            suma = suma + resultado.getConteo()[i].intValue();
        }
        resultado.setDocumentosCount(new Integer(suma));
    } else {
        resultado = NumTermsArbol.obtenerNumeroNodos(paramBusq.getTesauros(),
                getIndexPathByLanguage(paramBusq.getIdiomaBusqueda()), "tesauro");
    }
    return resultado;
}