Examples of org.apache.lucene.search.Collector

org.apache.lucene.search.Collector
re scorer public void setScorer(Scorer scorer) { } // accept docs out of order (for a BitSet it doesn't matter) public boolean acceptsDocsOutOfOrder() { return true; } public void collect(int doc) { bits.set(doc + docBase); } public void setNextReader(IndexReader reader, int docBase) { this.docBase = docBase; } });
Not all collectors will need to rebase the docID. For example, a collector that simply counts the total number of hits would skip it.

NOTE: Prior to 2.9, Lucene silently filtered out hits with score <= 0. As of 2.9, the core Collectors no longer do that. It's very unusual to have such hits (a negative query boost, or function query returning negative custom scores, could cause it to happen). If you need that behavior, use {@link PositiveScoresOnlyCollector}.

NOTE: This API is experimental and might change in incompatible ways in the next release.
@since 2.9

    IndexSearcher searcher = new IndexSearcher(store, true);
    final float[] scores = new float[NUM_DOCS];
    float lastScore = 0.0f;
    
    // default similarity should put docs with shorter length first
    searcher.search(new TermQuery(new Term("field", "word")), new Collector() {
      private int docBase = 0;
      private Scorer scorer;
      
      @Override
      public final void collect(int doc) throws IOException {
        scores[doc + docBase] = scorer.score();
      }
      @Override
      public void setNextReader(IndexReader reader, int docBase) {
        this.docBase = docBase;
      }
      @Override
      public void setScorer(Scorer scorer) throws IOException {
        this.scorer = scorer;
      }
      @Override
      public boolean acceptsDocsOutOfOrder() {
        return true;
      }
    });
    searcher.close();
    
    lastScore = Float.MAX_VALUE;
    for (int i = 0; i < NUM_DOCS; i++) {
      String msg = "i=" + i + ", " + scores[i] + " <= " + lastScore;
      assertTrue(msg, scores[i] <= lastScore);
      //System.out.println(msg);
      lastScore = scores[i];
    }


    FieldNormModifier fnm = new FieldNormModifier(store, s);
    fnm.reSetNorms("field");
    
    // new norm (with default similarity) should put longer docs first
    searcher = new IndexSearcher(store, true);
    searcher.search(new TermQuery(new Term("field", "word")),  new Collector() {
      private int docBase = 0;
      private Scorer scorer;
      @Override
      public final void collect(int doc) throws IOException {
        scores[doc + docBase] = scorer.score();

View Full Code Here

    IndexSearcher searcher = new IndexSearcher(store, true);
    final float[] scores = new float[NUM_DOCS];
    float lastScore = 0.0f;
    
    // default similarity should return the same score for all documents for this query
    searcher.search(new TermQuery(new Term("untokfield", "20061212")), new Collector() {
      private int docBase = 0;
      private Scorer scorer;
      @Override
      public final void collect(int doc) throws IOException {
        scores[doc + docBase] = scorer.score();

View Full Code Here

      throw new IllegalArgumentException("query must not be null");
    
    IndexSearcher searcher = createSearcher();
    try {
      final float[] scores = new float[1]; // inits to 0.0f (no match)
      searcher.search(query, new Collector() {
        private Scorer scorer;


        @Override
        public void collect(int doc) throws IOException {
          scores[0] = scorer.score();

View Full Code Here

        filter = null;
      }


      // Verify docs are always collected in order:
      new DrillSideways(s, tr).search(ddq,
                           new Collector() {
                             int lastDocID;


                             @Override
                             public void setScorer(Scorer s) {
                             }

View Full Code Here


    BooleanQuery bq = new BooleanQuery();
    bq.add(joinQuery, BooleanClause.Occur.SHOULD);
    bq.add(new TermQuery(new Term("id", "3")), BooleanClause.Occur.SHOULD);


    indexSearcher.search(bq, new Collector() {
        boolean sawFive;
        @Override
        public void setNextReader(AtomicReaderContext context) {
        }
        @Override

View Full Code Here

        }


        // Need to know all documents that have matches. TopDocs doesn't give me that and then I'd be also testing TopDocsCollector...
        final FixedBitSet actualResult = new FixedBitSet(indexSearcher.getIndexReader().maxDoc());
        final TopScoreDocCollector topScoreDocCollector = TopScoreDocCollector.create(10, false);
        indexSearcher.search(joinQuery, new Collector() {


          int docBase;


          @Override
          public void collect(int doc) throws IOException {

View Full Code Here

        toField = "from";
        queryVals = context.toHitsToJoinScore;
      }
      final Map<BytesRef, JoinScore> joinValueToJoinScores = new HashMap<>();
      if (multipleValuesPerDocument) {
        fromSearcher.search(new TermQuery(new Term("value", uniqueRandomValue)), new Collector() {


          private Scorer scorer;
          private SortedSetDocValues docTermOrds;


          @Override
          public void collect(int doc) throws IOException {
            docTermOrds.setDocument(doc);
            long ord;
            while ((ord = docTermOrds.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
              final BytesRef joinValue = docTermOrds.lookupOrd(ord);
              JoinScore joinScore = joinValueToJoinScores.get(joinValue);
              if (joinScore == null) {
                joinValueToJoinScores.put(BytesRef.deepCopyOf(joinValue), joinScore = new JoinScore());
              }
              joinScore.addScore(scorer.score());
            }
          }


          @Override
          public void setNextReader(AtomicReaderContext context) throws IOException {
            docTermOrds = FieldCache.DEFAULT.getDocTermOrds(context.reader(), fromField);
          }


          @Override
          public void setScorer(Scorer scorer) {
            this.scorer = scorer;
          }


          @Override
          public boolean acceptsDocsOutOfOrder() {
            return false;
          }
        });
      } else {
        fromSearcher.search(new TermQuery(new Term("value", uniqueRandomValue)), new Collector() {


          private Scorer scorer;
          private BinaryDocValues terms;
          private Bits docsWithField;


          @Override
          public void collect(int doc) throws IOException {
            final BytesRef joinValue = terms.get(doc);
            if (joinValue.length == 0 && !docsWithField.get(doc)) {
              return;
            }


            JoinScore joinScore = joinValueToJoinScores.get(joinValue);
            if (joinScore == null) {
              joinValueToJoinScores.put(BytesRef.deepCopyOf(joinValue), joinScore = new JoinScore());
            }
            joinScore.addScore(scorer.score());
          }


          @Override
          public void setNextReader(AtomicReaderContext context) throws IOException {
            terms = FieldCache.DEFAULT.getTerms(context.reader(), fromField, true);
            docsWithField = FieldCache.DEFAULT.getDocsWithField(context.reader(), fromField);
          }


          @Override
          public void setScorer(Scorer scorer) {
            this.scorer = scorer;
          }


          @Override
          public boolean acceptsDocsOutOfOrder() {
            return false;
          }
        });
      }


      final Map<Integer, JoinScore> docToJoinScore = new HashMap<>();
      if (multipleValuesPerDocument) {
        if (scoreDocsInOrder) {
          AtomicReader slowCompositeReader = SlowCompositeReaderWrapper.wrap(toSearcher.getIndexReader());
          Terms terms = slowCompositeReader.terms(toField);
          if (terms != null) {
            DocsEnum docsEnum = null;
            TermsEnum termsEnum = null;
            SortedSet<BytesRef> joinValues = new TreeSet<>(BytesRef.getUTF8SortedAsUnicodeComparator());
            joinValues.addAll(joinValueToJoinScores.keySet());
            for (BytesRef joinValue : joinValues) {
              termsEnum = terms.iterator(termsEnum);
              if (termsEnum.seekExact(joinValue)) {
                docsEnum = termsEnum.docs(slowCompositeReader.getLiveDocs(), docsEnum, DocsEnum.FLAG_NONE);
                JoinScore joinScore = joinValueToJoinScores.get(joinValue);


                for (int doc = docsEnum.nextDoc(); doc != DocIdSetIterator.NO_MORE_DOCS; doc = docsEnum.nextDoc()) {
                  // First encountered join value determines the score.
                  // Something to keep in mind for many-to-many relations.
                  if (!docToJoinScore.containsKey(doc)) {
                    docToJoinScore.put(doc, joinScore);
                  }
                }
              }
            }
          }
        } else {
          toSearcher.search(new MatchAllDocsQuery(), new Collector() {


            private SortedSetDocValues docTermOrds;
            private int docBase;


            @Override
            public void collect(int doc) throws IOException {
              docTermOrds.setDocument(doc);
              long ord;
              while ((ord = docTermOrds.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
                final BytesRef joinValue = docTermOrds.lookupOrd(ord);
                JoinScore joinScore = joinValueToJoinScores.get(joinValue);
                if (joinScore == null) {
                  continue;
                }
                Integer basedDoc = docBase + doc;
                // First encountered join value determines the score.
                // Something to keep in mind for many-to-many relations.
                if (!docToJoinScore.containsKey(basedDoc)) {
                  docToJoinScore.put(basedDoc, joinScore);
                }
              }
            }


            @Override
            public void setNextReader(AtomicReaderContext context) throws IOException {
              docBase = context.docBase;
              docTermOrds = FieldCache.DEFAULT.getDocTermOrds(context.reader(), toField);
            }


            @Override
            public boolean acceptsDocsOutOfOrder() {return false;}
            @Override
            public void setScorer(Scorer scorer) {}
          });
        }
      } else {
        toSearcher.search(new MatchAllDocsQuery(), new Collector() {


          private BinaryDocValues terms;
          private int docBase;


          @Override

View Full Code Here

      final IndexSearcher indexSearcher = newSearcher(indexReader);
      final Query phraseQuery = new SpanNearQuery(new SpanQuery[] {
          new SpanTermQuery(new Term(FIELD, "fox")),
          new SpanTermQuery(new Term(FIELD, "jumped")) }, 0, true);
      final FixedBitSet bitset = new FixedBitSet(indexReader.maxDoc());
      indexSearcher.search(phraseQuery, new Collector() {
        private int baseDoc;


        @Override
        public boolean acceptsDocsOutOfOrder() {
          return true;

View Full Code Here

      throw new IllegalArgumentException("query must not be null");
    
    IndexSearcher searcher = createSearcher();
    try {
      final float[] scores = new float[1]; // inits to 0.0f (no match)
      searcher.search(query, new Collector() {
        private Scorer scorer;


        @Override
        public void collect(int doc) throws IOException {
          scores[0] = scorer.score();

View Full Code Here

   * 
   *  This simulates the streaming search use case, where all hits are supposed to
   *  be processed, regardless of their relevance.
   */
  public static void doStreamingSearch(final Searcher searcher, Query query) throws IOException {
    Collector streamingHitCollector = new Collector() {
      private Scorer scorer;
      private int docBase;
      
      // simply print docId and score of every matching document
      @Override

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.search.Collector

com.gentics.cr.lucene.indexaccessor.WarmingIndexAccessor$SearcherWarmer

com.senseidb.search.node.impl.DefaultJsonQueryBuilderFactory

com.senseidb.svc.impl.CoreSenseiServiceImpl

com.twitter.elephantbird.mapreduce.input.LuceneIndexCollectAllRecordReader

er.lucenceadaptor.example.DirectAction

org.apache.blur.lucene.search.IterablePaging$PagingIterator

org.apache.blur.lucene.search.PrimeDocCache

org.apache.lucene.benchmark.byTask.tasks.ReadTask

org.apache.lucene.benchmark.byTask.tasks.SearchWithCollectorTask

org.apache.lucene.demo.SearchFiles

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.