Package com.browseengine.bobo.util

Examples of com.browseengine.bobo.util.BigSegmentedArray

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
      bits |= 0x00000001 << (i-1); 
    }
   
    final int finalBits = bits;
   
    final BigSegmentedArray orderArray = dataCache.orderArray;
   
    if (indexes.length == 0)
    {
      return EmptyDocIdSet.getInstance();
    }
    else
    {
      return new RandomAccessDocIdSet()
      {
        @Override
        public DocIdSetIterator iterator()
        {
          return new CompactMultiValueFacetDocIdSetIterator(dataCache,indexes,finalBits);
        }

            @Override
            final public boolean get(int docId)
            {
              return (orderArray.get(docId) & finalBits) != 0x0;
            }
      };
    }
  }
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
  /* (non-Javadoc)
   * @see com.browseengine.bobo.facets.FacetCountCollector#getCountDistribution()
   */
  public BigSegmentedArray getCountDistribution() {
    BigSegmentedArray dist = null;
    if(_latPredefinedRangeIndexes != null) {
      dist = new LazyBigIntArray(_latPredefinedRangeIndexes.length);
      int n = 0;
      int start;
      int end;
      for(int[] range: _latPredefinedRangeIndexes) {
        start = range[0];
        end = range[1];
        int sum = 0;
        for(int i = start; i < end; i++) {
          sum += _latCount[i];
        }
        dist.add(n++, sum);
      }
    }
    return dist;
  }
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
    public DocComparator getComparator(IndexReader reader, int docbase)
        throws IOException {
      if (!(reader instanceof BoboIndexReader)) throw new IllegalStateException("reader not instance of "+BoboIndexReader.class);
      BoboIndexReader boboReader = (BoboIndexReader)reader;
      final FacetDataCache dataCache = _facetHandler.getFacetData(boboReader);
      final BigSegmentedArray orderArray = dataCache.orderArray;
      return new DocComparator() {
       
        @Override
        public Comparable value(ScoreDoc doc) {
          int index = orderArray.get(doc.doc);
              return dataCache.valArray.get(index);
        }
       
        @Override
        public int compare(ScoreDoc doc1, ScoreDoc doc2) {
          return orderArray.get(doc1.doc) - orderArray.get(doc2.doc); 
        }
      };
    }
View Full Code Here
76
77
78
79
80
81
82
83
84
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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
  public void load(String fieldName,IndexReader reader,TermListFactory<T> listFactory) throws IOException
  {
    String field = fieldName.intern();
    int maxDoc = reader.maxDoc();

    BigSegmentedArray order = this.orderArray;
    if (order == null) // we want to reuse the memory
    {
      order = newInstance(_termCountSize, maxDoc);
    } else
    {
      order.ensureCapacity(maxDoc); // no need to fill to 0, we are reseting the
                                    // data anyway
    }
    this.orderArray = order;

    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();

    int length = maxDoc + 1;
    TermValueList<T> list = listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList();
    TermDocs termDocs = reader.termDocs();
    TermEnum termEnum = reader.terms(new Term(field, ""));
    int t = 0; // current term number

    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    int totalFreq = 0;
    // int df = 0;
    t++;
    try
    {
      do
      {
        Term term = termEnum.term();
        if (term == null || term.field() != field)
          break;

        if (t > order.maxValue())
        {
          throw new IOException("maximum number of value cannot exceed: "
              + order.maxValue());
        }
        // store term text
        // we expect that there is at most one term per document
        if (t >= length)
          throw new RuntimeException("there are more terms than "
              + "documents in field \"" + field
              + "\", but it's impossible to sort on " + "tokenized fields");
        list.add(term.text());
        termDocs.seek(termEnum);
        // freqList.add(termEnum.docFreq()); // doesn't take into account
        // deldocs
        int minID = -1;
        int maxID = -1;
        int df = 0;
        if (termDocs.next())
        {
          df++;
          int docid = termDocs.doc();
          order.add(docid, t);
          minID = docid;
          while (termDocs.next())
          {
            df++;
            docid = termDocs.doc();
            order.add(docid, t);
          }
          maxID = docid;
        }
        freqList.add(df);
        totalFreq += df;
        minIDList.add(minID);
        maxIDList.add(maxID);

        t++;
      } while (termEnum.next());
    } finally
    {
      termDocs.close();
      termEnum.close();
    }
    list.seal();

    this.valArray = list;
    this.freqs = freqList.toIntArray();
    this.minIDs = minIDList.toIntArray();
    this.maxIDs = maxIDList.toIntArray();

    int doc = 0;
    while (doc <= maxDoc && order.get(doc) != 0)
    {
      ++doc;
    }
    if (doc <= maxDoc)
    {
      this.minIDs[0] = doc;
      // Try to get the max
      doc = maxDoc;
      while (doc > 0 && order.get(doc) != 0)
      {
        --doc;
      }
      if (doc > 0)
      {
View Full Code Here
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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
      throws IOException {
    String field = fieldName.intern();
    int maxDoc = reader.maxDoc();

    int dictValueCount = getDictValueCount(reader, fieldName);
    BigSegmentedArray order = newInstance(dictValueCount, maxDoc);
    this.orderArray = order;

    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();

    int length = maxDoc + 1;
    @SuppressWarnings("unchecked")
    TermValueList<T> list = listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList();
    int negativeValueCount = getNegativeValueCount(reader, field);

    int t = 1; // valid term id starts from 1
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    int totalFreq = 0;
    Terms terms = reader.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator(null);
      BytesRef text;
      while ((text = termsEnum.next()) != null) {
        // store term text
        // we expect that there is at most one term per document
        if (t >= length) throw new RuntimeException("there are more terms than "
            + "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);
        // freqList.add(termEnum.docFreq()); // doesn't take into account
        // deldocs
        int minID = -1;
        int maxID = -1;
        int docID = -1;
        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;
        }
        freqList.add(df);
        totalFreq += df;
        minIDList.add(minID);
        maxIDList.add(maxID);
        t++;
      }
    }

    list.seal();
    this.valArray = list;
    this.freqs = freqList.toIntArray();
    this.minIDs = minIDList.toIntArray();
    this.maxIDs = maxIDList.toIntArray();

    int doc = 0;
    while (doc < maxDoc && order.get(doc) != 0) {
      ++doc;
    }
    if (doc < maxDoc) {
      this.minIDs[0] = doc;
      // Try to get the max
      doc = maxDoc - 1;
      while (doc >= 0 && order.get(doc) != 0) {
        --doc;
      }
      this.maxIDs[0] = doc;
    }
    this.freqs[0] = maxDoc - totalFreq;
View Full Code Here
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
    public DocComparator getComparator(AtomicReader reader, int docbase) throws IOException {
      if (!(reader instanceof BoboSegmentReader)) throw new IllegalStateException(
          "reader not instance of " + BoboSegmentReader.class);
      BoboSegmentReader boboReader = (BoboSegmentReader) reader;
      final FacetDataCache<?> dataCache = _facetHandler.getFacetData(boboReader);
      final BigSegmentedArray orderArray = dataCache.orderArray;
      return new DocComparator() {
        @Override
        public Comparable<?> value(ScoreDoc doc) {
          int index = orderArray.get(doc.doc);
          return dataCache.valArray.getComparableValue(index);
        }

        @Override
        public int compare(ScoreDoc doc1, ScoreDoc doc2) {
          return orderArray.get(doc1.doc) - orderArray.get(doc2.doc);
        }
      };
    }
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
   * (non-Javadoc)
   * @see com.browseengine.bobo.facets.FacetCountCollector#getCountDistribution()
   */
  @Override
  public BigSegmentedArray getCountDistribution() {
    BigSegmentedArray dist = null;
    if (_latPredefinedRangeIndexes != null) {
      dist = new LazyBigIntArray(_latPredefinedRangeIndexes.length);
      int n = 0;
      int start;
      int end;
      for (int[] range : _latPredefinedRangeIndexes) {
        start = range[0];
        end = range[1];
        int sum = 0;
        for (int i = start; i < end; i++) {
          sum += _latCount[i];
        }
        dist.add(n++, sum);
      }
    }
    return dist;
  }
View Full Code Here
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
  /**
   * @return Count distribution for all the user specified range values
   */
  @Override
  public BigSegmentedArray getCountDistribution() {
    BigSegmentedArray dist = null;
    if (_predefinedRanges != null) {
      dist = new LazyBigIntArray(_predefinedRanges.size());
      int distIdx = 0;
      for (int i = 0; i < _count.size(); i++) {
        int count = _count.get(i);
        dist.add(distIdx++, count);
      }
    }
    return dist;
  }
View Full Code Here
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
      if (startIdx < 0) startIdx = -(startIdx + 1);

      int endIdx = _valArray.indexOf(_end);
      if (endIdx < 0) endIdx = -(endIdx + 1);

      BigSegmentedArray baseCounts = _baseCollector.getCountDistribution();
      if (_start instanceof Long) {
        long start = _start.longValue();
        long unit = _unit.longValue();
        TermLongList valArray = (TermLongList) _valArray;
        for (int i = startIdx; i < endIdx; i++) {
          long val = valArray.getPrimitiveValue(i);
          int idx = (int) ((val - start) / unit);
          if (idx >= 0 && idx < _count.size()) {
            _count.add(idx, _count.get(idx) + baseCounts.get(i));
          }
        }
      } else if (_start instanceof Integer) {
        int start = _start.intValue();
        int unit = _unit.intValue();
        TermIntList valArray = (TermIntList) _valArray;
        for (int i = startIdx; i < endIdx; i++) {
          int val = valArray.getPrimitiveValue(i);
          int idx = ((val - start) / unit);
          if (idx >= 0 && idx < _count.size()) {
            _count.add(idx, _count.get(idx) + baseCounts.get(i));
          }
        }
      } else {
        double start = _start.doubleValue();
        double unit = _unit.doubleValue();
        for (int i = startIdx; i < endIdx; i++) {
          Number val = (Number) _valArray.getRawValue(i);
          int idx = (int) ((val.doubleValue() - start) / unit);
          if (idx >= 0 && idx < _count.size()) {
            _count.add(idx, _count.get(idx) + baseCounts.get(i));
          }
        }
      }
    }
View Full Code Here
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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
      throws IOException {
    String field = fieldName.intern();
    int maxDoc = reader.maxDoc();

    int dictValueCount = getDictValueCount(reader, fieldName);
    BigSegmentedArray order = newInstance(dictValueCount, maxDoc);
    this.orderArray = order;

    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();

    int length = maxDoc + 1;
    @SuppressWarnings("unchecked")
    TermValueList<T> list = listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList();
    int negativeValueCount = getNegativeValueCount(reader, field);

    int t = 1; // valid term id starts from 1
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    int totalFreq = 0;
    Terms terms = reader.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator(null);
      BytesRef text;
      while ((text = termsEnum.next()) != null) {
        // store term text
        // we expect that there is at most one term per document
        if (t >= length) throw new RuntimeException("there are more terms than "
            + "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);
        // freqList.add(termEnum.docFreq()); // doesn't take into account
        // deldocs
        int minID = -1;
        int maxID = -1;
        int docID = -1;
        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;
        }
        freqList.add(df);
        totalFreq += df;
        minIDList.add(minID);
        maxIDList.add(maxID);
        t++;
      }
    }

    list.seal();
    this.valArray = list;
    this.freqs = freqList.toIntArray();
    this.minIDs = minIDList.toIntArray();
    this.maxIDs = maxIDList.toIntArray();

    int doc = 0;
    while (doc < maxDoc && order.get(doc) != 0) {
      ++doc;
    }
    if (doc < maxDoc) {
      this.minIDs[0] = doc;
      // Try to get the max
      doc = maxDoc - 1;
      while (doc >= 0 && order.get(doc) != 0) {
        --doc;
      }
      this.maxIDs[0] = doc;
    }
    this.freqs[0] = reader.numDocs() - totalFreq;
View Full Code Here
TOP

Related Classes of com.browseengine.bobo.util.BigSegmentedArray

  • com.browseengine.bobo.facets.data.FacetDataCache
  • com.browseengine.bobo.facets.data.FacetDataCache$FacetDocComparatorSource
  • com.browseengine.bobo.facets.filter.CompactMultiValueFacetFilter
  • com.browseengine.bobo.facets.impl.BucketFacetCountCollector
  • com.browseengine.bobo.facets.impl.GeoFacetCountCollector
  • com.browseengine.bobo.facets.impl.GeoFacetHandler$GeoFacetData
  • com.browseengine.bobo.facets.impl.GeoSimpleFacetCountCollector
  • com.browseengine.bobo.facets.impl.HistogramFacetHandler$HistogramCollector
  • com.browseengine.bobo.facets.impl.RangeFacetCountCollector
  • com.browseengine.bobo.facets.impl.SpatialFacetHandler
    • 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.