Package it.unimi.dsi.fastutil.ints

Examples of it.unimi.dsi.fastutil.ints.IntArrayList

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
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
        System.err.println( "Term frequency was " + f + " and position " + ( f - indexFrequency - 1 ) );
        throw e;
      }
    }
 
    IntArrayList l = new IntArrayList();
    ObjectArrayList<int[]> positions = new ObjectArrayList<int[]>();
   
    if ( ! jsapResult.getBoolean( "noSkip" ) ) {
      int start = 0, end = 0, result;
      try {
        for (i = 0; i < index.length; i++) {
         
          pl.expectedUpdates = numberOfTerms[ i ];
          pl.start("Verifying all skips in " + index[i] + "...");

          for (t = 0; t < numberOfTerms[ i ]; t++) {
            l.clear();
            positions.clear();
            IndexIterator documents = termLists ? indexReader[ i ].documents( terms[ i ].get( t ) ) : indexReader[ i ].documents( t );
            int d;
            while( ( d = documents.nextDocument() ) != -1 ) {
              l.add( d );
              if ( index[ i ].hasPositions ) positions.add( ArrayUtils.subarray( documents.positionArray(), 0, documents.count() ) );
            }
           
            for( start = 0; start < l.size(); start++ ) {
              for( end = start + 1; end < l.size(); end++ ) {
                IndexIterator indexIterator = termLists ? indexReader[ i ].documents( terms[ i ].get( t ) ) : indexReader[ i ].documents( t );
               
                result = indexIterator.skipTo( l.getInt( start ) );
                if ( indexIterator.document() != l.getInt( start ) || result != l.getInt( start ) ) throw new AssertionError( "Trying to skip to document " + l.getInt( start ) + " (term " + t + ") moved to " + indexIterator.document() + "(skipTo() returned " + result + ")" );
                result = indexIterator.skipTo( l.getInt( end ) );
                if ( indexIterator.document() != l.getInt( end ) || result != l.getInt( end ) ) throw new AssertionError( "Trying to skip to document " + l.getInt( end ) + " (term " + t + ") after a skip to " + start + " moved to " + indexIterator.document() + "(skipTo() returned " + result + ")" );
               
                if ( index[ i ].hasPositions ) {
                  // This catches wrong state reconstruction after skips.
                  indexIterator = termLists ? indexReader[ i ].documents( terms[ i ].get( t ) ) : indexReader[ i ].documents( t );
                  indexIterator.skipTo( l.getInt( start ) );
                  if ( indexIterator.document() != l.getInt( start ) ) throw new AssertionError(indexIterator.document() + " != " + l.getInt( start ) );
                  if ( indexIterator.count() != positions.get( start ).length ) throw new AssertionError(indexIterator.count() + " != " + positions.get( start ).length );
                  if ( ! Arrays.equals( positions.get( start ), ArrayUtils.subarray( indexIterator.positionArray(), 0, indexIterator.count() ) )
                     ) throw new AssertionError(Arrays.toString( positions.get( start ) ) + "!=" + Arrays.toString( ArrayUtils.subarray( indexIterator.positionArray(), 0, indexIterator.count() ) ) );
                  indexIterator.skipTo( l.getInt( end ) );
                  if ( indexIterator.document() != l.getInt( end )  ) throw new AssertionError(indexIterator.document() + " != " + l.getInt( end ) );
                  if ( indexIterator.count() != positions.get( end ).length ) throw new AssertionError(indexIterator.count() + " != " + positions.get( end ).length );
                  if ( ! Arrays.equals( positions.get( end ), ArrayUtils.subarray( indexIterator.positionArray(), 0, indexIterator.count() ) )
                     ) throw new AssertionError(Arrays.toString( positions.get( end ) ) + "!=" + Arrays.toString( ArrayUtils.subarray( indexIterator.positionArray(), 0, indexIterator.count() ) ) );
                }
               
              }
             
              IndexIterator indexIterator = termLists ? indexReader[ i ].documents( terms[ i ].get( t ) ) : indexReader[ i ].documents( t );
             
              result = indexIterator.skipTo( l.getInt( start ) );
              if ( indexIterator.document() != l.getInt( start ) || result != l.getInt( start ) ) throw new AssertionError("Trying to skip to document " + l.getInt( start ) + " (term " + t + ") moved to " + indexIterator.document() + "(skipTo() returned " + result + ")" );
              result = indexIterator.skipTo( Integer.MAX_VALUE );
              if ( indexIterator.hasNext() || result != Integer.MAX_VALUE ) throw new AssertionError("Trying to skip beyond end of list (term " + t + ") after a skip to " + start + " returned " + result + " (hasNext()=" + indexIterator.hasNext() + ")" );
             
             
            }
View Full Code Here
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
      if ( word.length() == 0 ) continue;
      if ( !termProcessor.processTerm( word ) ) {
        pos++;
        continue;
      }
      IntArrayList positions = terms.get( word );
      if ( positions == null ) terms.put( word.copy(), positions = new IntArrayList() );
      positions.add( pos++ );
    }

    for ( MutableString term : terms.keySet() ) {
      ObjectArrayList<int[]> list = termMap.get( term );
      IntArrayList positions = terms.get( term );
      if ( list == null ) termMap.put( term, list = new ObjectArrayList<int[]>() );

      int[] t = new int[ positions.size() + 1 ];
      t[ 0 ] = documentIndex;
      System.arraycopy( positions.elements(), 0, t, 1, positions.size() );
      list.add( t );
    }

    return pos;
  }
View Full Code Here
301
302
303
304
305
306
307
308
309
310
311
      case TEXT:
        termMap[ i ] = new Object2ObjectOpenHashMap<MutableString, ObjectArrayList<int[]>>();
        break;
      case DATE:
      case INT:
        payloadPointers[ i ] = new IntArrayList();
        payloadContent[ i ] = new ObjectArrayList<Object>();
      }
    }

    int documentIndex = 0;
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
   
  }

  public static int[] convertIndexes(FacetDataCache dataCache,String[] vals)
    {
      IntList list = new IntArrayList();
      for (String val : vals)
      {
        int[] range = parse(dataCache,val);
        if ( range!=null)
        {
          for (int i=range[0];i<=range[1];++i)
          {
            list.add(i);
          }
        }
      }
      return list.toIntArray();
    }
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
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
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
    BigIntArray order = new BigIntArray(maxDoc);

    TermValueList mterms = _termListFactory == null ? new TermStringList() : _termListFactory.createTermList();
   
    IntArrayList minIDList=new IntArrayList();
      IntArrayList maxIDList=new IntArrayList();
      IntArrayList freqList = new IntArrayList();
     
    TermDocs termDocs = null;
    TermEnum termEnum = null;
    int t = 0; // current term number
    mterms.add(null);
    minIDList.add(-1);
      maxIDList.add(-1);
      freqList.add(0);
    t++;
    try {
      termDocs = reader.termDocs();
      termEnum = reader.terms(new Term(_indexFieldName, ""));
      do {
        if (termEnum == null)
          break;
        Term term = termEnum.term();
        if (term == null || !_indexFieldName.equals(term.field()))
          break;

        // store term text
        // we expect that there is at most one term per document
        if (t > MAX_VAL_COUNT) {
          throw new IOException("maximum number of value cannot exceed: "
              + MAX_VAL_COUNT);
        }
        String val = term.text();
        mterms.add(val);
        int bit = (0x00000001 << (t-1));
        termDocs.seek(termEnum);
        //freqList.add(termEnum.docFreq());  // removed because the df doesn't take into account the num of deletedDocs
        int df = 0;
        int minID=-1;
            int maxID=-1;
            if(termDocs.next())
            {
              df++;
                  int docid = termDocs.doc();
                  order.add(docid, order.get(docid) | bit);
                  minID = docid;
                  while (termDocs.next())
              {
                    df++;
                    docid = termDocs.doc();
                    order.add(docid, order.get(docid) | bit);
              }
          maxID = docid;
            }
              freqList.add(df);
        minIDList.add(minID);
            maxIDList.add(maxID);
        t++;
      } while (termEnum.next());
    } finally {
      try {
        if (termDocs != null) {
          termDocs.close();
        }
      } finally {
        if (termEnum != null) {
          termEnum.close();
        }
      }
    }
   
    mterms.seal();

    return new FacetDataCache(order,mterms,freqList.toIntArray(),minIDList.toIntArray(),maxIDList.toIntArray(),TermCountSize.large);
  }
View Full Code Here
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
      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 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);
        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();
  }
View Full Code Here
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
    this.maxIDs = maxIDList.toIntArray();
  }
 
  private static int[] convertString(FacetDataCache dataCache,String[] vals)
  {
      IntList list = new IntArrayList(vals.length);
      for (int i=0;i<vals.length;++i)
      {
        int index = dataCache.valArray.indexOf(vals[i]);
        if (index>=0)
        {
          list.add(index);
        }
      }
      return list.toIntArray();
  }
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
   * @return the array of order indices of the values.
   */
  public static <T> int[] convert(FacetDataCache<T> dataCache,T[] vals)
  {
    if (vals!=null && (vals instanceof String[])) return convertString(dataCache, (String[])vals);
    IntList list = new IntArrayList(vals.length);
    for (int i=0;i<vals.length;++i)
    {
      int index = dataCache.valArray.indexOfWithType(vals[i]);
      if (index>=0)
      {
        list.add(index);
      }
    }
    return list.toIntArray();
  }
View Full Code Here
72
73
74
75
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
    BufferedLoader loader = getBufferedLoader(maxdoc, workArea);

    TermEnum tenum = null;
    TermDocs tdoc = null;
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>)new TermStringList() : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();

    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    t++;
   
    _overflow = false;
    try
    {
      tdoc = reader.termDocs();
      tenum = reader.terms(new Term(fieldName, ""));
      if (tenum != null)
      {
        do
        {
          Term term = tenum.term();
          if (term == null || !fieldName.equals(term.field()))
            break;

          String val = term.text();

          if (val != null)
          {
            list.add(val);

            tdoc.seek(tenum);
            //freqList.add(tenum.docFreq()); // removed because the df doesn't take into account the num of deletedDocs
            int df = 0;
            int minID = -1;
            int maxID = -1;
            if(tdoc.next())
            {
              df++;
              int docid = tdoc.doc();
              if(!loader.add(docid, t)) logOverflow(fieldName);
              minID = docid;
              while(tdoc.next())
              {
                df++;
                docid = tdoc.doc();
                if(!loader.add(docid, t)) logOverflow(fieldName);
              }
              maxID = docid;
            }
            freqList.add(df);
            minIDList.add(minID);
            maxIDList.add(maxID);
          }

          t++;
        }
        while (tenum.next());
      }
    }
    finally
    {
      try
      {
        if (tdoc != null)
        {
          tdoc.close();
        }
      }
      finally
      {
        if (tenum != null)
        {
          tenum.close();
        }
      }
    }

    list.seal();

    try
    {
      _nestedArray.load(maxdoc, loader);
    }
    catch (IOException e)
    {
      throw e;
    }
    catch (Exception e)
    {
      throw new RuntimeException("failed to load due to " + e.toString(), e);
    }
   
    this.valArray = list;
    this.freqs = freqList.toIntArray();
    this.minIDs = minIDList.toIntArray();
    this.maxIDs = maxIDList.toIntArray();
  }
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
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
    }
   
    TermEnum tenum = null;
    TermDocs tdoc = null;
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>)new TermStringList() : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();

    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    t++;

    _overflow = false;
    try
    {
      tdoc = reader.termDocs();
      tenum = reader.terms(new Term(fieldName, ""));
      if (tenum != null)
      {
        do
        {
          Term term = tenum.term();
          if(term == null || !fieldName.equals(term.field()))
            break;
         
          String val = term.text();
         
          if (val != null)
          {
            list.add(val);
           
            tdoc.seek(tenum);
            //freqList.add(tenum.docFreq()); // removed because the df doesn't take into account the num of deletedDocs
            int df = 0;
            int minID = -1;
            int maxID = -1;
            if(tdoc.next())
            {
              df++;
              int docid = tdoc.doc();
              if (!_nestedArray.addData(docid, t)) logOverflow(fieldName);
              minID = docid;
              while(tdoc.next())
              {
                df++;
                docid = tdoc.doc();
                if(!_nestedArray.addData(docid, t)) logOverflow(fieldName);
              }
              maxID = docid;
            }
            freqList.add(df);
            minIDList.add(minID);
            maxIDList.add(maxID);
          }
         
          t++;
        }
        while (tenum.next());
      }
    }
    finally
    {
      try
      {
        if (tdoc != null)
        {
          tdoc.close();
        }
      }
      finally
      {
        if (tenum != null)
        {
          tenum.close();
        }
      }
    }
   
    list.seal();
   
    this.valArray = list;
    this.freqs = freqList.toIntArray();
    this.minIDs = minIDList.toIntArray();
    this.maxIDs = maxIDList.toIntArray();
  }
View Full Code Here
TOP

Related Classes of it.unimi.dsi.fastutil.ints.IntArrayList

  • com.browseengine.bobo.facets.data.FacetDataCache
  • com.browseengine.bobo.facets.data.MultiValueFacetDataCache
  • com.browseengine.bobo.facets.data.MultiValueWithWeightFacetDataCache
  • com.browseengine.bobo.facets.data.TermIntList
  • com.browseengine.bobo.facets.filter.FacetRangeFilter
  • com.browseengine.bobo.facets.impl.CompactMultiValueFacetHandler
  • com.facebook.presto.operator.ChannelHash
  • com.facebook.presto.operator.GroupByHash$ChannelBuilder
  • com.facebook.presto.operator.index.UnloadedIndexKeyRecordSet
  • com.facebook.presto.operator.JoinHash
    • 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.