Search in sources :

Example 21 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestUnifiedHighlighterMTQ method testPositionSensitiveWithWildcardDoesNotHighlight.

public void testPositionSensitiveWithWildcardDoesNotHighlight() throws Exception {
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Document doc = new Document();
    doc.add(new Field("body", "iterate insect ipswitch illinois indirect", fieldType));
    doc.add(newTextField("id", "id", Field.Store.YES));
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
    int docID = searcher.search(new TermQuery(new Term("id", "id")), 1).scoreDocs[0].doc;
    PhraseQuery pq = new PhraseQuery.Builder().add(new Term("body", "consent")).add(new Term("body", "order")).build();
    BooleanQuery query = new BooleanQuery.Builder().add(new WildcardQuery(new Term("body", "enforc*")), BooleanClause.Occur.MUST).add(pq, BooleanClause.Occur.MUST).build();
    int[] docIds = new int[] { docID };
    String[] snippets = highlighter.highlightFields(new String[] { "body" }, query, docIds, new int[] { 2 }).get("body");
    assertEquals(1, snippets.length);
    assertEquals("iterate insect ipswitch illinois indirect", snippets[0]);
    ir.close();
}
Also used : IndexSearcher(org.apache.lucene.search.IndexSearcher) SpanTermQuery(org.apache.lucene.search.spans.SpanTermQuery) TermQuery(org.apache.lucene.search.TermQuery) BooleanQuery(org.apache.lucene.search.BooleanQuery) WildcardQuery(org.apache.lucene.search.WildcardQuery) PhraseQuery(org.apache.lucene.search.PhraseQuery) Term(org.apache.lucene.index.Term) Document(org.apache.lucene.document.Document) Field(org.apache.lucene.document.Field) IndexReader(org.apache.lucene.index.IndexReader) RandomIndexWriter(org.apache.lucene.index.RandomIndexWriter)

Example 22 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestQueryParser method testMultiWordSynonyms.

// TODO: Move to QueryParserTestBase once standard flexible parser gets this capability
public void testMultiWordSynonyms() throws Exception {
    QueryParser dumb = new QueryParser("field", new Analyzer1());
    dumb.setSplitOnWhitespace(false);
    TermQuery guinea = new TermQuery(new Term("field", "guinea"));
    TermQuery pig = new TermQuery(new Term("field", "pig"));
    TermQuery cavy = new TermQuery(new Term("field", "cavy"));
    // A multi-word synonym source will form a graph query for synonyms that formed the graph token stream
    BooleanQuery.Builder synonym = new BooleanQuery.Builder();
    synonym.add(guinea, BooleanClause.Occur.MUST);
    synonym.add(pig, BooleanClause.Occur.MUST);
    BooleanQuery guineaPig = synonym.build();
    PhraseQuery phraseGuineaPig = new PhraseQuery.Builder().add(new Term("field", "guinea")).add(new Term("field", "pig")).build();
    BooleanQuery graphQuery = new BooleanQuery.Builder().add(guineaPig, BooleanClause.Occur.SHOULD).add(cavy, BooleanClause.Occur.SHOULD).build();
    assertEquals(graphQuery, dumb.parse("guinea pig"));
    // With the phrase operator, a multi-word synonym source will form span near queries.
    SpanNearQuery spanGuineaPig = SpanNearQuery.newOrderedNearQuery("field").addClause(new SpanTermQuery(new Term("field", "guinea"))).addClause(new SpanTermQuery(new Term("field", "pig"))).setSlop(0).build();
    SpanTermQuery spanCavy = new SpanTermQuery(new Term("field", "cavy"));
    SpanOrQuery spanPhrase = new SpanOrQuery(new SpanQuery[] { spanGuineaPig, spanCavy });
    assertEquals(spanPhrase, dumb.parse("\"guinea pig\""));
    // custom behavior, the synonyms are expanded, unless you use quote operator
    QueryParser smart = new SmartQueryParser();
    smart.setSplitOnWhitespace(false);
    graphQuery = new BooleanQuery.Builder().add(guineaPig, BooleanClause.Occur.SHOULD).add(cavy, BooleanClause.Occur.SHOULD).build();
    assertEquals(graphQuery, smart.parse("guinea pig"));
    assertEquals(phraseGuineaPig, smart.parse("\"guinea pig\""));
}
Also used : SpanTermQuery(org.apache.lucene.search.spans.SpanTermQuery) TermQuery(org.apache.lucene.search.TermQuery) BooleanQuery(org.apache.lucene.search.BooleanQuery) PhraseQuery(org.apache.lucene.search.PhraseQuery) MultiPhraseQuery(org.apache.lucene.search.MultiPhraseQuery) Term(org.apache.lucene.index.Term) SpanOrQuery(org.apache.lucene.search.spans.SpanOrQuery) SpanTermQuery(org.apache.lucene.search.spans.SpanTermQuery) SpanNearQuery(org.apache.lucene.search.spans.SpanNearQuery)

Example 23 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class ThreadedIndexingAndSearchingTestCase method smokeTestSearcher.

protected void smokeTestSearcher(IndexSearcher s) throws Exception {
    runQuery(s, new TermQuery(new Term("body", "united")));
    runQuery(s, new TermQuery(new Term("titleTokenized", "states")));
    PhraseQuery pq = new PhraseQuery("body", "united", "states");
    runQuery(s, pq);
}
Also used : TermQuery(org.apache.lucene.search.TermQuery) PhraseQuery(org.apache.lucene.search.PhraseQuery)

Example 24 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestBasics method testPhrase.

public void testPhrase() throws Exception {
    PhraseQuery query = new PhraseQuery("field", "seventy", "seven");
    checkHits(query, new int[] { 77, 177, 277, 377, 477, 577, 677, 777, 877, 977, 1077, 1177, 1277, 1377, 1477, 1577, 1677, 1777, 1877, 1977 });
}
Also used : PhraseQuery(org.apache.lucene.search.PhraseQuery)

Example 25 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class WeightedSpanTermExtractor method extract.

/**
   * Fills a <code>Map</code> with {@link WeightedSpanTerm}s using the terms from the supplied <code>Query</code>.
   * 
   * @param query
   *          Query to extract Terms from
   * @param terms
   *          Map to place created WeightedSpanTerms in
   * @throws IOException If there is a low-level I/O error
   */
protected void extract(Query query, float boost, Map<String, WeightedSpanTerm> terms) throws IOException {
    if (query instanceof BoostQuery) {
        BoostQuery boostQuery = (BoostQuery) query;
        extract(boostQuery.getQuery(), boost * boostQuery.getBoost(), terms);
    } else if (query instanceof BooleanQuery) {
        for (BooleanClause clause : (BooleanQuery) query) {
            if (!clause.isProhibited()) {
                extract(clause.getQuery(), boost, terms);
            }
        }
    } else if (query instanceof PhraseQuery) {
        PhraseQuery phraseQuery = ((PhraseQuery) query);
        Term[] phraseQueryTerms = phraseQuery.getTerms();
        if (phraseQueryTerms.length == 1) {
            extractWeightedSpanTerms(terms, new SpanTermQuery(phraseQueryTerms[0]), boost);
        } else {
            SpanQuery[] clauses = new SpanQuery[phraseQueryTerms.length];
            for (int i = 0; i < phraseQueryTerms.length; i++) {
                clauses[i] = new SpanTermQuery(phraseQueryTerms[i]);
            }
            // sum position increments beyond 1
            int positionGaps = 0;
            int[] positions = phraseQuery.getPositions();
            if (positions.length >= 2) {
                // positions are in increasing order.   max(0,...) is just a safeguard.
                positionGaps = Math.max(0, positions[positions.length - 1] - positions[0] - positions.length + 1);
            }
            //if original slop is 0 then require inOrder
            boolean inorder = (phraseQuery.getSlop() == 0);
            SpanNearQuery sp = new SpanNearQuery(clauses, phraseQuery.getSlop() + positionGaps, inorder);
            extractWeightedSpanTerms(terms, sp, boost);
        }
    } else if (query instanceof TermQuery || query instanceof SynonymQuery) {
        extractWeightedTerms(terms, query, boost);
    } else if (query instanceof SpanQuery) {
        extractWeightedSpanTerms(terms, (SpanQuery) query, boost);
    } else if (query instanceof ConstantScoreQuery) {
        final Query q = ((ConstantScoreQuery) query).getQuery();
        if (q != null) {
            extract(q, boost, terms);
        }
    } else if (query instanceof CommonTermsQuery) {
        // specialized since rewriting would change the result query 
        // this query is TermContext sensitive.
        extractWeightedTerms(terms, query, boost);
    } else if (query instanceof DisjunctionMaxQuery) {
        for (Query clause : ((DisjunctionMaxQuery) query)) {
            extract(clause, boost, terms);
        }
    } else if (query instanceof ToParentBlockJoinQuery) {
        extract(((ToParentBlockJoinQuery) query).getChildQuery(), boost, terms);
    } else if (query instanceof ToChildBlockJoinQuery) {
        extract(((ToChildBlockJoinQuery) query).getParentQuery(), boost, terms);
    } else if (query instanceof MultiPhraseQuery) {
        final MultiPhraseQuery mpq = (MultiPhraseQuery) query;
        final Term[][] termArrays = mpq.getTermArrays();
        final int[] positions = mpq.getPositions();
        if (positions.length > 0) {
            int maxPosition = positions[positions.length - 1];
            for (int i = 0; i < positions.length - 1; ++i) {
                if (positions[i] > maxPosition) {
                    maxPosition = positions[i];
                }
            }
            @SuppressWarnings({ "unchecked", "rawtypes" }) final List<SpanQuery>[] disjunctLists = new List[maxPosition + 1];
            int distinctPositions = 0;
            for (int i = 0; i < termArrays.length; ++i) {
                final Term[] termArray = termArrays[i];
                List<SpanQuery> disjuncts = disjunctLists[positions[i]];
                if (disjuncts == null) {
                    disjuncts = (disjunctLists[positions[i]] = new ArrayList<>(termArray.length));
                    ++distinctPositions;
                }
                for (Term aTermArray : termArray) {
                    disjuncts.add(new SpanTermQuery(aTermArray));
                }
            }
            int positionGaps = 0;
            int position = 0;
            final SpanQuery[] clauses = new SpanQuery[distinctPositions];
            for (List<SpanQuery> disjuncts : disjunctLists) {
                if (disjuncts != null) {
                    clauses[position++] = new SpanOrQuery(disjuncts.toArray(new SpanQuery[disjuncts.size()]));
                } else {
                    ++positionGaps;
                }
            }
            if (clauses.length == 1) {
                extractWeightedSpanTerms(terms, clauses[0], boost);
            } else {
                final int slop = mpq.getSlop();
                final boolean inorder = (slop == 0);
                SpanNearQuery sp = new SpanNearQuery(clauses, slop + positionGaps, inorder);
                extractWeightedSpanTerms(terms, sp, boost);
            }
        }
    } else if (query instanceof MatchAllDocsQuery) {
    //nothing
    } else if (query instanceof CustomScoreQuery) {
        extract(((CustomScoreQuery) query).getSubQuery(), boost, terms);
    } else if (isQueryUnsupported(query.getClass())) {
    // nothing
    } else {
        if (query instanceof MultiTermQuery && (!expandMultiTermQuery || !fieldNameComparator(((MultiTermQuery) query).getField()))) {
            return;
        }
        Query origQuery = query;
        final IndexReader reader = getLeafContext().reader();
        Query rewritten;
        if (query instanceof MultiTermQuery) {
            rewritten = MultiTermQuery.SCORING_BOOLEAN_REWRITE.rewrite(reader, (MultiTermQuery) query);
        } else {
            rewritten = origQuery.rewrite(reader);
        }
        if (rewritten != origQuery) {
            // only rewrite once and then flatten again - the rewritten query could have a special treatment
            // if this method is overwritten in a subclass or above in the next recursion
            extract(rewritten, boost, terms);
        } else {
            extractUnknownQuery(query, terms);
        }
    }
}
Also used : BooleanQuery(org.apache.lucene.search.BooleanQuery) Query(org.apache.lucene.search.Query) CommonTermsQuery(org.apache.lucene.queries.CommonTermsQuery) PhraseQuery(org.apache.lucene.search.PhraseQuery) MultiTermQuery(org.apache.lucene.search.MultiTermQuery) ToChildBlockJoinQuery(org.apache.lucene.search.join.ToChildBlockJoinQuery) SpanFirstQuery(org.apache.lucene.search.spans.SpanFirstQuery) MatchAllDocsQuery(org.apache.lucene.search.MatchAllDocsQuery) DisjunctionMaxQuery(org.apache.lucene.search.DisjunctionMaxQuery) FieldMaskingSpanQuery(org.apache.lucene.search.spans.FieldMaskingSpanQuery) SpanTermQuery(org.apache.lucene.search.spans.SpanTermQuery) SpanNotQuery(org.apache.lucene.search.spans.SpanNotQuery) CustomScoreQuery(org.apache.lucene.queries.CustomScoreQuery) ConstantScoreQuery(org.apache.lucene.search.ConstantScoreQuery) MultiPhraseQuery(org.apache.lucene.search.MultiPhraseQuery) SpanQuery(org.apache.lucene.search.spans.SpanQuery) SpanNearQuery(org.apache.lucene.search.spans.SpanNearQuery) TermQuery(org.apache.lucene.search.TermQuery) SynonymQuery(org.apache.lucene.search.SynonymQuery) BooleanQuery(org.apache.lucene.search.BooleanQuery) ToParentBlockJoinQuery(org.apache.lucene.search.join.ToParentBlockJoinQuery) BoostQuery(org.apache.lucene.search.BoostQuery) SpanOrQuery(org.apache.lucene.search.spans.SpanOrQuery) SynonymQuery(org.apache.lucene.search.SynonymQuery) MultiPhraseQuery(org.apache.lucene.search.MultiPhraseQuery) BoostQuery(org.apache.lucene.search.BoostQuery) CommonTermsQuery(org.apache.lucene.queries.CommonTermsQuery) SpanTermQuery(org.apache.lucene.search.spans.SpanTermQuery) CustomScoreQuery(org.apache.lucene.queries.CustomScoreQuery) ConstantScoreQuery(org.apache.lucene.search.ConstantScoreQuery) List(java.util.List) ArrayList(java.util.ArrayList) MultiTermQuery(org.apache.lucene.search.MultiTermQuery) SpanTermQuery(org.apache.lucene.search.spans.SpanTermQuery) TermQuery(org.apache.lucene.search.TermQuery) PhraseQuery(org.apache.lucene.search.PhraseQuery) MultiPhraseQuery(org.apache.lucene.search.MultiPhraseQuery) MultiTermQuery(org.apache.lucene.search.MultiTermQuery) DisjunctionMaxQuery(org.apache.lucene.search.DisjunctionMaxQuery) Term(org.apache.lucene.index.Term) SpanOrQuery(org.apache.lucene.search.spans.SpanOrQuery) MatchAllDocsQuery(org.apache.lucene.search.MatchAllDocsQuery) ToChildBlockJoinQuery(org.apache.lucene.search.join.ToChildBlockJoinQuery) FieldMaskingSpanQuery(org.apache.lucene.search.spans.FieldMaskingSpanQuery) SpanQuery(org.apache.lucene.search.spans.SpanQuery) BooleanClause(org.apache.lucene.search.BooleanClause) ToParentBlockJoinQuery(org.apache.lucene.search.join.ToParentBlockJoinQuery) IndexReader(org.apache.lucene.index.IndexReader) SpanNearQuery(org.apache.lucene.search.spans.SpanNearQuery)

Aggregations

PhraseQuery (org.apache.lucene.search.PhraseQuery)97 Term (org.apache.lucene.index.Term)51 TermQuery (org.apache.lucene.search.TermQuery)39 BooleanQuery (org.apache.lucene.search.BooleanQuery)36 MultiPhraseQuery (org.apache.lucene.search.MultiPhraseQuery)36 Document (org.apache.lucene.document.Document)34 Query (org.apache.lucene.search.Query)26 Directory (org.apache.lucene.store.Directory)26 MockAnalyzer (org.apache.lucene.analysis.MockAnalyzer)25 IndexSearcher (org.apache.lucene.search.IndexSearcher)22 IndexReader (org.apache.lucene.index.IndexReader)20 Field (org.apache.lucene.document.Field)17 TextField (org.apache.lucene.document.TextField)16 SpanTermQuery (org.apache.lucene.search.spans.SpanTermQuery)16 TokenStream (org.apache.lucene.analysis.TokenStream)15 TopDocs (org.apache.lucene.search.TopDocs)14 IndexWriter (org.apache.lucene.index.IndexWriter)13 BoostQuery (org.apache.lucene.search.BoostQuery)13 ArrayList (java.util.ArrayList)10 CannedTokenStream (org.apache.lucene.analysis.CannedTokenStream)10