Package org.apache.lucene.index

Examples of org.apache.lucene.index.DocsEnum

503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
      Terms terms = fields.terms(fieldName);
      if (terms == null) {
        continue;
      }
      TermsEnum termsEnum = terms.iterator(null);
      DocsEnum docs = null;
      while(termsEnum.next() != null) {
        docs = _TestUtil.docs(random(), termsEnum, MultiFields.getLiveDocs(reader), docs, DocsEnum.FLAG_FREQS);
        while(docs.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
          totalTokenCount2 += docs.freq();
        }
      }
    }
    reader.close();
View Full Code Here
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
    int doc = -1;
    DirectoryReader reader = readerManager.acquire();
    try {
      final BytesRef catTerm = new BytesRef(categoryPath.toString(delimiter));
      TermsEnum termsEnum = null; // reuse
      DocsEnum docs = null; // reuse
      for (AtomicReaderContext ctx : reader.leaves()) {
        Terms terms = ctx.reader().terms(Consts.FULL);
        if (terms != null) {
          termsEnum = terms.iterator(termsEnum);
          if (termsEnum.seekExact(catTerm)) {
            // liveDocs=null because the taxonomy has no deletes
            docs = termsEnum.docs(null, docs, 0 /* freqs not required */);
            // if the term was found, we know it has exactly one document.
            doc = docs.nextDoc() + ctx.docBase;
            break;
          }
        }
      }
    } finally {
View Full Code Here
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
    boolean aborted = false;
    DirectoryReader reader = readerManager.acquire();
    try {
      TermsEnum termsEnum = null;
      DocsEnum docsEnum = null;
      for (AtomicReaderContext ctx : reader.leaves()) {
        Terms terms = ctx.reader().terms(Consts.FULL);
        if (terms != null) { // cannot really happen, but be on the safe side
          termsEnum = terms.iterator(termsEnum);
          while (termsEnum.next() != null) {
            if (!cache.isFull()) {
              BytesRef t = termsEnum.term();
              // Since we guarantee uniqueness of categories, each term has exactly
              // one document. Also, since we do not allow removing categories (and
              // hence documents), there are no deletions in the index. Therefore, it
              // is sufficient to call next(), and then doc(), exactly once with no
              // 'validation' checks.
              CategoryPath cp = new CategoryPath(t.utf8ToString(), delimiter);
              docsEnum = termsEnum.docs(null, docsEnum, DocsEnum.FLAG_NONE);
              boolean res = cache.put(cp, docsEnum.nextDoc() + ctx.docBase);
              assert !res : "entries should not have been evicted from the cache";
            } else {
              // the cache is full and the next put() will evict entries from it, therefore abort the iteration.
              aborted = true;
              break;
View Full Code Here
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
      final int size = r.numDocs();
      final OrdinalMap ordinalMap = map;
      ordinalMap.setSize(size);
      int base = 0;
      TermsEnum te = null;
      DocsEnum docs = null;
      for (final AtomicReaderContext ctx : r.leaves()) {
        final AtomicReader ar = ctx.reader();
        final Terms terms = ar.terms(Consts.FULL);
        te = terms.iterator(te);
        while (te.next() != null) {
          String value = te.term().utf8ToString();
          CategoryPath cp = new CategoryPath(value, delimiter);
          final int ordinal = addCategory(cp);
          docs = te.docs(null, docs, DocsEnum.FLAG_NONE);
          ordinalMap.addMapping(docs.nextDoc() + base, ordinal);
        }
        base += ar.maxDoc(); // no deletions, so we're ok
      }
      ordinalMap.addDone();
    } finally {
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
          valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
          t++;
        }

        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);
        if (docsEnum != null) {
          while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
            df++;

            if (!loader.add(docID, valId)) {
              logOverflow(fieldName);
            } else {
              weightLoader.add(docID, weight);
            }

            if (docID < minID) minID = docID;
            bitset.fastSet(docID);
            while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
              docID = docsEnum.docID();
              df++;
              if (!loader.add(docID, valId)) {
                logOverflow(fieldName);
              } else {
                weightLoader.add(docID, weight);
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
            + "documents in field \"" + field + "\", but it's impossible to sort on "
            + "tokenized fields");
        String strText = text.utf8ToString();
        list.add(strText);
        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);
        int minID = -1;
        int maxID = -1;
        int docID;
        int df = 0;
        int valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
        while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
          df++;
          order.add(docID, valId);
          minID = docID;
          while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
            docID = docsEnum.docID();
            df++;
            order.add(docID, valId);
          }
          maxID = docID;
        }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
      while ((text = termsEnum.next()) != null) {
        String strText = text.utf8ToString();
        list.add(strText);

        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);
        int df = 0;
        int minID = -1;
        int maxID = -1;
        int docID = -1;
        int valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
        while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
          df++;
          if (!loader.add(docID, valId)) logOverflow(fieldName);
          minID = docID;
          bitset.fastSet(docID);
          while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
            docID = docsEnum.docID();
            df++;
            if (!loader.add(docID, valId)) logOverflow(fieldName);
            bitset.fastSet(docID);
          }
          maxID = docID;
View Full Code Here
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
      while ((text = termsEnum.next()) != null) {
        String strText = text.utf8ToString();
        list.add(strText);

        Term term = new Term(field, strText);
        DocsEnum docsEnum = reader.termDocsEnum(term);

        int df = 0;
        int minID = -1;
        int maxID = -1;
        int docID = -1;
        while ((docID = docsEnum.nextDoc()) != DocsEnum.NO_MORE_DOCS) {
          df++;
          if (!_nestedArray.addData(docID, t)) logOverflow(fieldName);
          minID = docID;
          bitset.fastSet(docID);
          int valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
          while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
            docID = docsEnum.docID();
            df++;
            if (!_nestedArray.addData(docID, valId)) logOverflow(fieldName);
            bitset.fastSet(docID);
          }
          maxID = docID;
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
118
119
          float numDocs = ir.maxDoc();
          if (numDocs < numAgeGroups) numAgeGroups = ir.maxDoc();
          float ageTotals[] = new float[numAgeGroups];
          TermsEnum te = MultiFields.getTerms(ir, field).iterator(null);
          while (te.next() != null) {
            DocsEnum td = te.docs(null, null, 0);
            td.nextDoc();
            float firstDocId = td.docID();
            int ageBracket = (int) ((firstDocId / numDocs) * numAgeGroups);
            ageTotals[ageBracket]++;
          }
          float total = 0.0f;
          float max = 0.0f;
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
      doc(token("aaa", node(1,0)), token("bbb", node(1,0,1,0))),
      doc(token("aaa", node(5,3,6,3)), token("bbb", node(5,3,6,3,7)))
    );

    final AtomicReader aReader = SlowCompositeReaderWrapper.wrap(reader);
    final DocsEnum docsEnum = aReader.termDocsEnum(new Term(DEFAULT_TEST_FIELD, "aaa"));
    assertTrue(docsEnum instanceof Siren10DocsEnum);
    final Siren10DocsNodesAndPositionsEnum e = ((Siren10DocsEnum) docsEnum).getDocsNodesAndPositionsEnum();
    assertEquals(-1, e.doc());
    assertEquals(0, e.nodeFreqInDoc());
    assertTrue(e.nextDocument());
View Full Code Here
TOP

Related Classes of org.apache.lucene.index.DocsEnum

  • com.basho.yokozuna.handler.EntropyData
  • com.browseengine.bobo.facets.data.FacetDataCache
  • com.browseengine.bobo.facets.data.MultiValueFacetDataCache
  • com.browseengine.bobo.facets.data.MultiValueWithWeightFacetDataCache
  • com.browseengine.bobo.facets.filter.AdaptiveFacetFilter$TermListRandomAccessDocIdSet$TermDocIdSet
  • com.browseengine.bobo.facets.impl.CompactMultiValueFacetHandler
  • com.pearson.entech.elasticsearch.search.facet.approx.termlist.TermListFacetExecutor$PostExecutor
  • org.apache.blur.lucene.search.PrimeDocCache
  • org.apache.blur.lucene.warmup.IndexTracer
  • org.apache.blur.utils.BlurUtil
    • 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.