Package it.unimi.dsi.fastutil.ints

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

40
41
42
43
44
45
46
  }

  @Override
  protected List<?> buildPrimitiveList(int capacity) {
    _type = Integer.class;
    return capacity > 0 ? new IntArrayList(capacity) : new IntArrayList();
  }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
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
    BufferedLoader weightLoader = getBufferedLoader(maxdoc, null);

    @SuppressWarnings("unchecked")
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();
    OpenBitSet bitset = new OpenBitSet(maxdoc + 1);
    int negativeValueCount = getNegativeValueCount(reader, field);
    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    t++;

    _overflow = false;

    String pre = null;

    int df = 0;
    int minID = -1;
    int maxID = -1;
    int docID = -1;
    int valId = 0;

    Terms terms = reader.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator(null);
      BytesRef text;
      while ((text = termsEnum.next()) != null) {
        String strText = text.utf8ToString();
        String val = null;
        int weight = 0;
        String[] split = strText.split("\u0000");
        if (split.length > 1) {
          val = split[0];
          weight = Integer.parseInt(split[split.length - 1]);
        } else {
          continue;
        }

        if (pre == null || !val.equals(pre)) {
          if (pre != null) {
            freqList.add(df);
            minIDList.add(minID);
            maxIDList.add(maxID);
          }
          list.add(val);
          df = 0;
          minID = -1;
          maxID = -1;
          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);
              }
              bitset.fastSet(docID);
            }
            if (docID > maxID) maxID = docID;
          }
        }
        pre = val;
      }
      if (pre != null) {
        freqList.add(df);
        minIDList.add(minID);
        maxIDList.add(maxID);
      }
    }

    list.seal();

    try {
      _nestedArray.load(maxdoc + 1, loader);
      _weightArray.load(maxdoc + 1, weightLoader);
    } 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();

    int doc = 0;
    while (doc <= maxdoc && !_nestedArray.contains(doc, 0, true)) {
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
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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
      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;
    @SuppressWarnings("unchecked")
    TermValueList<T> list = listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList();

    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    int totalFreq = 0;
    t++;
    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) {
View Full Code Here
211
212
213
214
215
216
217
218
219
220
221
222
223
224
    }
    this.freqs[0] = maxDoc + 1 - totalFreq;
  }

  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
233
234
235
236
237
238
239
240
241
242
243
244
245
246
   * @param vals
   * @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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
    }

  }

  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
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
      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();
    int negativeValueCount = getNegativeValueCount(reader, field);
   
    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;
        int valId = (t - 1 < negativeValueCount) ? (negativeValueCount - t + 1) : t;
        if (termDocs.next()) {
          df++;
          int docid = termDocs.doc();
          order.add(docid, valId);
          minID = docid;
          while (termDocs.next()) {
            df++;
            docid = termDocs.doc();
            order.add(docid, valId);
          }
          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) {
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
203
204
205
    }
    this.freqs[0] = maxDoc + 1 - totalFreq;
  }

  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
215
216
217
218
219
220
221
222
223
224
225
226
227
228
   * @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
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
    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
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.