Package ivory.core.data.index

Examples of ivory.core.data.index.PostingsReader

395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
    // Now merge and test.
    Posting p = new Posting();

    PostingsListDocSortedPositional merged;
    PostingsReader mergedReader;

    merged = PostingsListDocSortedPositional.create(PostingsListDocSortedPositional.merge(
        postings1b, postings2b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(5, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(11, p.getDocno());
    assertEquals(4, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(19, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(25, p.getDocno());
    assertEquals(2, p.getTf());

    merged = PostingsListDocSortedPositional.create(PostingsListDocSortedPositional.merge(
        postings2b, postings1b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(5, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(11, p.getDocno());
    assertEquals(4, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(19, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(25, p.getDocno());
    assertEquals(2, p.getTf());
  }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
        out = fs.create(new Path(outputPath + "/" + i));
      }

      try {
        PostingsList pl = env.getPostingsList(env.getTermFromId(i));
        PostingsReader reader = pl.getPostingsReader();
        Signature filter = null;

        //Decide which filter to use based on the configuration parameters
        int df = pl.getDf();
        if (df <= bloomConfig.getIdentityHashThreshold()) {
          filter = new BloomFilterHash(df * bloomConfig.getBitsPerElement(),
                                       bloomConfig.getHashCount());
        } else {
          filter = new BloomFilterIdentityHash(bloomConfig.getDocumentCount());
        }

        while (reader.nextPosting(posting)) {
          filter.add(newDocids[posting.getDocno()]);
        }

        out.writeInt(i);
        out.writeInt(df);
View Full Code Here
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
    assertEquals(3, postings2.getDf());
    assertEquals(8, postings2.getCf());

    Posting posting = new Posting();

    PostingsReader reader = postings2.getPostingsReader();

    int arr[] = null;

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(13, posting.getDocno());
    assertEquals(5, posting.getTf());
    assertEquals(1, arr[0]);
    assertEquals(4, arr[1]);
    assertEquals(5, arr[2]);
    assertEquals(10, arr[3]);
    assertEquals(23, arr[4]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(14, posting.getDocno());
    assertEquals(2, posting.getTf());
    assertEquals(2, arr[0]);
    assertEquals(23, arr[1]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(24, posting.getDocno());
    assertEquals(1, posting.getTf());
    assertEquals(1, arr[0]);
  }
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
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
185
186
187
188
189
190
191
192
193
194
    assertEquals(3, postings2.getDf());
    assertEquals(8, postings2.getCf());

    Posting posting = new Posting();

    PostingsReader reader = postings2.getPostingsReader();

    int arr[] = null;

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(13, posting.getDocno());
    assertEquals(5, posting.getTf());
    assertEquals(1, arr[0]);
    assertEquals(4, arr[1]);
    assertEquals(5, arr[2]);
    assertEquals(10, arr[3]);
    assertEquals(23, arr[4]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(14, posting.getDocno());
    assertEquals(2, posting.getTf());
    assertEquals(2, arr[0]);
    assertEquals(23, arr[1]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(24, posting.getDocno());
    assertEquals(1, posting.getTf());
    assertEquals(1, arr[0]);

    // Set new tf and cf.
    postings2.setDf(6);
    postings2.setCf(16);

    // Verify tf and cf.
    assertEquals(6, postings2.getDf());
    assertEquals(16, postings2.getCf());

    reader = postings2.getPostingsReader();
    arr = null;

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(13, posting.getDocno());
    assertEquals(5, posting.getTf());
    assertEquals(1, arr[0]);
    assertEquals(4, arr[1]);
    assertEquals(5, arr[2]);
    assertEquals(10, arr[3]);
    assertEquals(23, arr[4]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(14, posting.getDocno());
    assertEquals(2, posting.getTf());
    assertEquals(2, arr[0]);
    assertEquals(23, arr[1]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(24, posting.getDocno());
    assertEquals(1, posting.getTf());
    assertEquals(1, arr[0]);

    PostingsListDocSortedPositionalPForDelta postings3 =
        PostingsListDocSortedPositionalPForDelta.create(postings2.serialize());
    postings3.setCollectionDocumentCount(20);

    // Verify tf and cf.
    assertEquals(6, postings2.getDf());
    assertEquals(16, postings2.getCf());

    reader = postings2.getPostingsReader();
    arr = null;

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(13, posting.getDocno());
    assertEquals(5, posting.getTf());
    assertEquals(1, arr[0]);
    assertEquals(4, arr[1]);
    assertEquals(5, arr[2]);
    assertEquals(10, arr[3]);
    assertEquals(23, arr[4]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(14, posting.getDocno());
    assertEquals(2, posting.getTf());
    assertEquals(2, arr[0]);
    assertEquals(23, arr[1]);

    reader.nextPosting(posting);
    arr = reader.getPositions();
    assertEquals(24, posting.getDocno());
    assertEquals(1, posting.getTf());
    assertEquals(1, arr[0]);
  }
View Full Code Here
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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
    // Now merge and test.
    Posting p = new Posting();

    PostingsListDocSortedPositionalPForDelta merged;
    PostingsReader mergedReader;

    merged = PostingsListDocSortedPositionalPForDelta.create(PostingsListDocSortedPositionalPForDelta.merge(
        postings1b, postings2b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(7, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(11, p.getDocno());
    assertEquals(4, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(14, p.getDocno());
    assertEquals(2, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(19, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(24, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(25, p.getDocno());
    assertEquals(2, p.getTf());

    merged = PostingsListDocSortedPositionalPForDelta.create(PostingsListDocSortedPositionalPForDelta.merge(
        postings2b, postings1b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(7, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(11, p.getDocno());
    assertEquals(4, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(14, p.getDocno());
    assertEquals(2, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(19, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(24, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(25, p.getDocno());
    assertEquals(2, p.getTf());
  }
View Full Code Here
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
    // Now merge and test.
    Posting p = new Posting();

    PostingsListDocSortedPositionalPForDelta merged;
    PostingsReader mergedReader;

    merged = PostingsListDocSortedPositionalPForDelta.create(PostingsListDocSortedPositionalPForDelta.merge(
        postings1b, postings2b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(2, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());

    merged = PostingsListDocSortedPositionalPForDelta.create(PostingsListDocSortedPositionalPForDelta.merge(
        postings2b, postings1b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(2, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());
  }
View Full Code Here
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
    // Now merge and test.
    Posting p = new Posting();

    PostingsListDocSortedPositionalPForDelta merged;
    PostingsReader mergedReader;

    merged = PostingsListDocSortedPositionalPForDelta.create(PostingsListDocSortedPositionalPForDelta.merge(
        postings1b, postings2b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(5, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(11, p.getDocno());
    assertEquals(4, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(19, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(25, p.getDocno());
    assertEquals(2, p.getTf());

    merged = PostingsListDocSortedPositionalPForDelta.create(PostingsListDocSortedPositionalPForDelta.merge(
        postings2b, postings1b, 30).serialize());

    merged.setCollectionDocumentCount(30);
    mergedReader = merged.getPostingsReader();

    assertEquals(5, merged.getNumberOfPostings());
    mergedReader.nextPosting(p);
    assertEquals(2, p.getDocno());
    assertEquals(3, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(11, p.getDocno());
    assertEquals(4, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(13, p.getDocno());
    assertEquals(5, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(19, p.getDocno());
    assertEquals(1, p.getTf());

    mergedReader.nextPosting(p);
    assertEquals(25, p.getDocno());
    assertEquals(2, p.getTf());
  }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
    for(int qid: queries.keySet()) {
      for(int termid: queries.get(qid)) {
        if(!termidHistory.contains(termid)) {
          termidHistory.add(termid);
          PostingsList pl = env.getPostingsList(env.getTermFromId(termid));
          PostingsReader reader = pl.getPostingsReader();

          positions.clear();
          positionsMap.clear();
          int[] data = new int[pl.getDf()];
          int index = 0;
          while (reader.nextPosting(posting)) {
            data[index] = newDocids[posting.getDocno()];
            positionsMap.put(data[index], new TermPositions(reader.getPositions(), reader.getTf()));
            docLengths.put(data[index], env.getDocumentLength(posting.getDocno()));
            index++;
          }
          Arrays.sort(data);
View Full Code Here
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
        OutputCollector<IntWritable, HMapIFW> output, Reporter reporter) throws IOException {

      sLogger.debug(mCollectionDocCount);
      postings.setCollectionDocumentCount(mCollectionDocCount);

      PostingsReader reader1 = postings.getPostingsReader();

      if (reader1.getNumberOfPostings() > dfCut)
        return;

      // set per postings list
      mModel.setDF(reader1.getNumberOfPostings());

      // performing PCP
      while (reader1.nextPosting(e1)) {

        // Here's a hidden dependency: How we do the blocking depends on
        // how the postings are sorted. If the postings are sorted in
        // ascending docno, then we can break out of the loop after
        // we've gone past the block bounds (as in code below).
        // Otherwise (say, if postings are sorted by tf), we have to go
        // through all postings.
        // -- Jimmy, 2008/09/03
        //

        if (e1.getDocno() < mBlockStart)
          continue;
        if (e1.getDocno() >= mBlockEnd)
          break;

        HMapIFW map = new HMapIFW();

        sLogger.debug(key + ": " + e1);

        PostingsReader reader2 = postings.getPostingsReader();

        while (reader2.nextPosting(e2)) {

          sLogger.debug(key + ": " + e1 + ", " + e2);

          if (e1.getDocno() == e2.getDocno())
            continue;
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
      // The current concept.
      String concept = vocab[conceptID].getKey();

      // Get df and cf information for the concept.
      PostingsReader reader = env.getPostingsReader(new Expression(concept));
      if (reader == null) {
        continue;
      }
      PostingsList list = reader.getPostingsList();
      int df = list.getDf();
      long cf = list.getCf();
      env.clearPostingsReaderCache();

      // Construct concept evidence.
View Full Code Here
TOP

Related Classes of ivory.core.data.index.PostingsReader

  • ivory.bloomir.data.CompressedPostingsIO
  • ivory.bloomir.data.SignatureIO
  • ivory.core.data.index.PostingsListDocSortedPositionalPForDeltaTest
  • ivory.core.data.index.PostingsListDocSortedPositionalTest
  • ivory.core.RetrievalEnvironment
  • ivory.ffg.preprocessing.GenerateCompressedPositionalPostings
  • ivory.pwsim.PCP$MyMapper
  • ivory.smrf.model.expander.UnigramLatentConceptExpander
    • 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.