Package org.apache.lucene.util

Examples of org.apache.lucene.util.LongBitSet

144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
        valueCount++;
      }
     
      int docCount = 0;
      long ordCount = 0;
      LongBitSet seenOrds = new LongBitSet(valueCount);
      Iterator<Number> ordIterator = ords.iterator();
      for (Number v : docToOrdCount) {
        assert v != null;
        int count = v.intValue();
        assert count >= 0;
        docCount++;
        ordCount += count;
       
        long lastOrd = -1;
        for (int i = 0; i < count; i++) {
          Number o = ordIterator.next();
          assert o != null;
          long ord = o.longValue();
          assert ord >= 0 && ord < valueCount;
          assert ord > lastOrd : "ord=" + ord + ",lastOrd=" + lastOrd;
          seenOrds.set(ord);
          lastOrd = ord;
        }
      }
      assert ordIterator.hasNext() == false;
     
      assert docCount == maxDoc;
      assert seenOrds.cardinality() == valueCount;
      checkIterator(values.iterator(), valueCount, false);
      checkIterator(docToOrdCount.iterator(), maxDoc, false);
      checkIterator(ords.iterator(), ordCount, false);
      in.addSortedSetField(field, values, docToOrdCount, ords);
    }
View Full Code Here
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
    }
  }
 
  private static void checkSortedSetDocValues(String fieldName, AtomicReader reader, SortedSetDocValues dv, Bits docsWithField) {
    final long maxOrd = dv.getValueCount()-1;
    LongBitSet seenOrds = new LongBitSet(dv.getValueCount());
    long maxOrd2 = -1;
    for (int i = 0; i < reader.maxDoc(); i++) {
      dv.setDocument(i);
      long lastOrd = -1;
      long ord;
      if (docsWithField.get(i)) {
        int ordCount = 0;
        while ((ord = dv.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
          ordCount++;
          if (ord <= lastOrd) {
            throw new RuntimeException("ords out of order: " + ord + " <= " + lastOrd + " for doc: " + i);
          }
          if (ord < 0 || ord > maxOrd) {
            throw new RuntimeException("ord out of bounds: " + ord);
          }
          lastOrd = ord;
          maxOrd2 = Math.max(maxOrd2, ord);
          seenOrds.set(ord);
        }
        if (ordCount == 0) {
          throw new RuntimeException("dv for field: " + fieldName + " has no ordinals but is not marked missing for doc: " + i);
        }
      } else {
        long o = dv.nextOrd();
        if (o != SortedSetDocValues.NO_MORE_ORDS) {
          throw new RuntimeException("dv for field: " + fieldName + " is marked missing but has ord=" + o + " for doc: " + i);
        }
      }
    }
    if (maxOrd != maxOrd2) {
      throw new RuntimeException("dv for field: " + fieldName + " reports wrong maxOrd=" + maxOrd + " but this is not the case: " + maxOrd2);
    }
    if (seenOrds.cardinality() != dv.getValueCount()) {
      throw new RuntimeException("dv for field: " + fieldName + " has holes in its ords, valueCount=" + dv.getValueCount() + " but only used: " + seenOrds.cardinality());
    }
   
    BytesRef lastValue = null;
    BytesRef scratch = new BytesRef();
    for (long i = 0; i <= maxOrd; i++) {
View Full Code Here
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
    }
  }
 
  private static void checkSortedSetDocValues(String fieldName, AtomicReader reader, SortedSetDocValues dv, Bits docsWithField) {
    final long maxOrd = dv.getValueCount()-1;
    LongBitSet seenOrds = new LongBitSet(dv.getValueCount());
    long maxOrd2 = -1;
    for (int i = 0; i < reader.maxDoc(); i++) {
      dv.setDocument(i);
      long lastOrd = -1;
      long ord;
      if (docsWithField.get(i)) {
        int ordCount = 0;
        while ((ord = dv.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
          if (ord <= lastOrd) {
            throw new RuntimeException("ords out of order: " + ord + " <= " + lastOrd + " for doc: " + i);
          }
          if (ord < 0 || ord > maxOrd) {
            throw new RuntimeException("ord out of bounds: " + ord);
          }
          if (dv instanceof RandomAccessOrds) {
            long ord2 = ((RandomAccessOrds)dv).ordAt(ordCount);
            if (ord != ord2) {
              throw new RuntimeException("ordAt(" + ordCount + ") inconsistent, expected=" + ord + ",got=" + ord2 + " for doc: " + i);
            }
          }
          lastOrd = ord;
          maxOrd2 = Math.max(maxOrd2, ord);
          seenOrds.set(ord);
          ordCount++;
        }
        if (ordCount == 0) {
          throw new RuntimeException("dv for field: " + fieldName + " has no ordinals but is not marked missing for doc: " + i);
        }
        if (dv instanceof RandomAccessOrds) {
          long ordCount2 = ((RandomAccessOrds)dv).cardinality();
          if (ordCount != ordCount2) {
            throw new RuntimeException("cardinality inconsistent, expected=" + ordCount + ",got=" + ordCount2 + " for doc: " + i);
          }
        }
      } else {
        long o = dv.nextOrd();
        if (o != SortedSetDocValues.NO_MORE_ORDS) {
          throw new RuntimeException("dv for field: " + fieldName + " is marked missing but has ord=" + o + " for doc: " + i);
        }
        if (dv instanceof RandomAccessOrds) {
          long ordCount2 = ((RandomAccessOrds)dv).cardinality();
          if (ordCount2 != 0) {
            throw new RuntimeException("dv for field: " + fieldName + " is marked missing but has cardinality " + ordCount2 + " for doc: " + i);
          }
        }
      }
    }
    if (maxOrd != maxOrd2) {
      throw new RuntimeException("dv for field: " + fieldName + " reports wrong maxOrd=" + maxOrd + " but this is not the case: " + maxOrd2);
    }
    if (seenOrds.cardinality() != dv.getValueCount()) {
      throw new RuntimeException("dv for field: " + fieldName + " has holes in its ords, valueCount=" + dv.getValueCount() + " but only used: " + seenOrds.cardinality());
    }
   
    BytesRef lastValue = null;
    for (long i = 0; i <= maxOrd; i++) {
      final BytesRef term = dv.lookupOrd(i);
View Full Code Here
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
        valueCount++;
      }
     
      int docCount = 0;
      long ordCount = 0;
      LongBitSet seenOrds = new LongBitSet(valueCount);
      Iterator<Number> ordIterator = ords.iterator();
      for (Number v : docToOrdCount) {
        assert v != null;
        int count = v.intValue();
        assert count >= 0;
        docCount++;
        ordCount += count;
       
        long lastOrd = -1;
        for (int i = 0; i < count; i++) {
          Number o = ordIterator.next();
          assert o != null;
          long ord = o.longValue();
          assert ord >= 0 && ord < valueCount;
          assert ord > lastOrd : "ord=" + ord + ",lastOrd=" + lastOrd;
          seenOrds.set(ord);
          lastOrd = ord;
        }
      }
      assert ordIterator.hasNext() == false;
     
      assert docCount == maxDoc;
      assert seenOrds.cardinality() == valueCount;
      checkIterator(values.iterator(), valueCount, false);
      checkIterator(docToOrdCount.iterator(), maxDoc, false);
      checkIterator(ords.iterator(), ordCount, false);
      in.addSortedSetField(field, values, docToOrdCount, ords);
    }
View Full Code Here
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
      SortedDocValues dv = dvs[sub];
      Bits liveDocs = reader.getLiveDocs();
      if (liveDocs == null) {
        liveTerms[sub] = dv.termsEnum();
      } else {
        LongBitSet bitset = new LongBitSet(dv.getValueCount());
        for (int i = 0; i < reader.maxDoc(); i++) {
          if (liveDocs.get(i)) {
            int ord = dv.getOrd(i);
            if (ord >= 0) {
              bitset.set(ord);
            }
          }
        }
        liveTerms[sub] = new BitsFilteredTermsEnum(dv.termsEnum(), bitset);
      }
View Full Code Here
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
      SortedSetDocValues dv = dvs[sub];
      Bits liveDocs = reader.getLiveDocs();
      if (liveDocs == null) {
        liveTerms[sub] = dv.termsEnum();
      } else {
        LongBitSet bitset = new LongBitSet(dv.getValueCount());
        for (int i = 0; i < reader.maxDoc(); i++) {
          if (liveDocs.get(i)) {
            dv.setDocument(i);
            long ord;
            while ((ord = dv.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
              bitset.set(ord);
            }
          }
        }
        liveTerms[sub] = new BitsFilteredTermsEnum(dv.termsEnum(), bitset);
      }
View Full Code Here
85
86
87
88
89
90
91
92
93
94
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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
     */
    @Override
    public DocIdSet getDocIdSet(AtomicReaderContext context, final Bits acceptDocs) throws IOException {
      final SortedDocValues fcsi = FieldCache.DEFAULT.getTermsIndex(context.reader(), query.field);
      // Cannot use FixedBitSet because we require long index (ord):
      final LongBitSet termSet = new LongBitSet(fcsi.getValueCount());
      TermsEnum termsEnum = query.getTermsEnum(new Terms() {
       
        @Override
        public Comparator<BytesRef> getComparator() {
          return BytesRef.getUTF8SortedAsUnicodeComparator();
        }
       
        @Override
        public TermsEnum iterator(TermsEnum reuse) {
          return fcsi.termsEnum();
        }

        @Override
        public long getSumTotalTermFreq() {
          return -1;
        }

        @Override
        public long getSumDocFreq() {
          return -1;
        }

        @Override
        public int getDocCount() {
          return -1;
        }

        @Override
        public long size() {
          return -1;
        }

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

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

        @Override
        public boolean hasPositions() {
          return false;
        }
       
        @Override
        public boolean hasPayloads() {
          return false;
        }
      });
     
      assert termsEnum != null;
      if (termsEnum.next() != null) {
        // fill into a bitset
        do {
          long ord = termsEnum.ord();
          if (ord >= 0) {
            termSet.set(ord);
          }
        } while (termsEnum.next() != null);
      } else {
        return null;
      }
     
      return new FieldCacheDocIdSet(context.reader().maxDoc(), acceptDocs) {
        @Override
        protected final boolean matchDoc(int doc) throws ArrayIndexOutOfBoundsException {
          int ord = fcsi.getOrd(doc);
          if (ord == -1) {
            return false;
          }
          return termSet.get(ord);
        }
      };
    }
View Full Code Here
85
86
87
88
89
90
91
92
93
94
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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
     */
    @Override
    public DocIdSet getDocIdSet(AtomicReaderContext context, final Bits acceptDocs) throws IOException {
      final SortedSetDocValues docTermOrds = FieldCache.DEFAULT.getDocTermOrds(context.reader(), query.field);
      // Cannot use FixedBitSet because we require long index (ord):
      final LongBitSet termSet = new LongBitSet(docTermOrds.getValueCount());
      TermsEnum termsEnum = query.getTermsEnum(new Terms() {
       
        @Override
        public Comparator<BytesRef> getComparator() {
          return BytesRef.getUTF8SortedAsUnicodeComparator();
        }
       
        @Override
        public TermsEnum iterator(TermsEnum reuse) {
          return docTermOrds.termsEnum();
        }

        @Override
        public long getSumTotalTermFreq() {
          return -1;
        }

        @Override
        public long getSumDocFreq() {
          return -1;
        }

        @Override
        public int getDocCount() {
          return -1;
        }

        @Override
        public long size() {
          return -1;
        }

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

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

        @Override
        public boolean hasPositions() {
          return false;
        }
       
        @Override
        public boolean hasPayloads() {
          return false;
        }
      });
     
      assert termsEnum != null;
      if (termsEnum.next() != null) {
        // fill into a bitset
        do {
          termSet.set(termsEnum.ord());
        } while (termsEnum.next() != null);
      } else {
        return null;
      }
     
      return new FieldCacheDocIdSet(context.reader().maxDoc(), acceptDocs) {
        @Override
        protected final boolean matchDoc(int doc) throws ArrayIndexOutOfBoundsException {
          docTermOrds.setDocument(doc);
          long ord;
          // TODO: we could track max bit set and early terminate (since they come in sorted order)
          while ((ord = docTermOrds.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
            if (termSet.get(ord)) {
              return true;
            }
          }
          return false;
        }
View Full Code Here
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
    }
  }
 
  private static void checkSortedSetDocValues(String fieldName, AtomicReader reader, SortedSetDocValues dv, Bits docsWithField) {
    final long maxOrd = dv.getValueCount()-1;
    LongBitSet seenOrds = new LongBitSet(dv.getValueCount());
    long maxOrd2 = -1;
    for (int i = 0; i < reader.maxDoc(); i++) {
      dv.setDocument(i);
      long lastOrd = -1;
      long ord;
      if (docsWithField.get(i)) {
        int ordCount = 0;
        while ((ord = dv.nextOrd()) != SortedSetDocValues.NO_MORE_ORDS) {
          if (ord <= lastOrd) {
            throw new RuntimeException("ords out of order: " + ord + " <= " + lastOrd + " for doc: " + i);
          }
          if (ord < 0 || ord > maxOrd) {
            throw new RuntimeException("ord out of bounds: " + ord);
          }
          if (dv instanceof RandomAccessOrds) {
            long ord2 = ((RandomAccessOrds)dv).ordAt(ordCount);
            if (ord != ord2) {
              throw new RuntimeException("ordAt(" + ordCount + ") inconsistent, expected=" + ord + ",got=" + ord2 + " for doc: " + i);
            }
          }
          lastOrd = ord;
          maxOrd2 = Math.max(maxOrd2, ord);
          seenOrds.set(ord);
          ordCount++;
        }
        if (ordCount == 0) {
          throw new RuntimeException("dv for field: " + fieldName + " has no ordinals but is not marked missing for doc: " + i);
        }
        if (dv instanceof RandomAccessOrds) {
          long ordCount2 = ((RandomAccessOrds)dv).cardinality();
          if (ordCount != ordCount2) {
            throw new RuntimeException("cardinality inconsistent, expected=" + ordCount + ",got=" + ordCount2 + " for doc: " + i);
          }
        }
      } else {
        long o = dv.nextOrd();
        if (o != SortedSetDocValues.NO_MORE_ORDS) {
          throw new RuntimeException("dv for field: " + fieldName + " is marked missing but has ord=" + o + " for doc: " + i);
        }
        if (dv instanceof RandomAccessOrds) {
          long ordCount2 = ((RandomAccessOrds)dv).cardinality();
          if (ordCount2 != 0) {
            throw new RuntimeException("dv for field: " + fieldName + " is marked missing but has cardinality " + ordCount2 + " for doc: " + i);
          }
        }
      }
    }
    if (maxOrd != maxOrd2) {
      throw new RuntimeException("dv for field: " + fieldName + " reports wrong maxOrd=" + maxOrd + " but this is not the case: " + maxOrd2);
    }
    if (seenOrds.cardinality() != dv.getValueCount()) {
      throw new RuntimeException("dv for field: " + fieldName + " has holes in its ords, valueCount=" + dv.getValueCount() + " but only used: " + seenOrds.cardinality());
    }
   
    BytesRef lastValue = null;
    BytesRef scratch = new BytesRef();
    for (long i = 0; i <= maxOrd; i++) {
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
        valueCount++;
      }
     
      int docCount = 0;
      long ordCount = 0;
      LongBitSet seenOrds = new LongBitSet(valueCount);
      Iterator<Number> ordIterator = ords.iterator();
      for (Number v : docToOrdCount) {
        assert v != null;
        int count = v.intValue();
        assert count >= 0;
        docCount++;
        ordCount += count;
       
        long lastOrd = -1;
        for (int i = 0; i < count; i++) {
          Number o = ordIterator.next();
          assert o != null;
          long ord = o.longValue();
          assert ord >= 0 && ord < valueCount;
          assert ord > lastOrd : "ord=" + ord + ",lastOrd=" + lastOrd;
          seenOrds.set(ord);
          lastOrd = ord;
        }
      }
      assert ordIterator.hasNext() == false;
     
      assert docCount == maxDoc;
      assert seenOrds.cardinality() == valueCount;
      checkIterator(values.iterator(), valueCount, false);
      checkIterator(docToOrdCount.iterator(), maxDoc, false);
      checkIterator(ords.iterator(), ordCount, false);
      in.addSortedSetField(field, values, docToOrdCount, ords);
    }
View Full Code Here
TOP

Related Classes of org.apache.lucene.util.LongBitSet

  • org.apache.lucene.codecs.asserting.AssertingDocValuesFormat$AssertingDocValuesConsumer
  • org.apache.lucene.codecs.DocValuesConsumer
  • org.apache.lucene.index.CheckIndex
  • org.apache.lucene.search.DocTermOrdsRewriteMethod$MultiTermQueryDocTermOrdsWrapperFilter
  • org.apache.lucene.search.FieldCacheRewriteMethod$MultiTermQueryFieldCacheWrapperFilter
  • org.elasticsearch.index.search.child.ChildrenConstantScoreQuery$ParentOrdCollector
  • org.elasticsearch.index.search.child.ChildrenConstantScoreQuery$ParentWeight
  • org.elasticsearch.index.search.child.ParentConstantScoreQuery$ParentOrdsCollector
    • 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.