Package ivory.core.data.index

Examples of ivory.core.data.index.TermPositions

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
      bitsOut = new BitOutputStream(bytesOut);

      Iterator<Map.Entry<Integer, int[]>> it = termPositionsMap.entrySet().iterator();
      Map.Entry<Integer, int[]> posting = it.next();
      int[] positions = posting.getValue();
      TermPositions tp = new TermPositions();
      // Write out the first termid.
      int lastTerm = posting.getKey().intValue();
      bitsOut.writeBinary(32, lastTerm);
      // Write out the tf value.
      bitsOut.writeGamma((short) positions.length);
      tp.set(positions, (short) positions.length);
      // Write out the positions.
      writePositions(bitsOut, tp);

      int curTerm;
      while (it.hasNext()) {
        posting = it.next();
        curTerm = posting.getKey().intValue();
        positions = posting.getValue();
        int tgap = curTerm - lastTerm;
        if (tgap <= 0) {
          throw new RuntimeException("Error: encountered invalid t-gap. termid=" + curTerm);
        }
        // Write out the gap.
        bitsOut.writeGamma(tgap);
        tp.set(positions, (short) positions.length);
        // Write out the tf value.
        bitsOut.writeGamma((short) positions.length);
        // Write out the positions.
        writePositions(bitsOut, tp);
        lastTerm = curTerm;
View Full Code Here
188
189
190
191
192
193
194
195
196
197
198
199
200
    StringBuffer s = new StringBuffer("[");
    try {
      Reader r = this.getReader();
      while (r.hasMoreTerms()) {
        int id = r.nextTerm();
        TermPositions pos = new TermPositions();
        r.getPositions(pos);
        s.append("(" + id + ", " + pos.getTf() + ", " + pos + ")");
      }
      s.append("]");
    } catch (Exception e) {
      e.printStackTrace();
    }
View Full Code Here
205
206
207
208
209
210
211
212
213
214
215
216
217
    StringBuffer s = new StringBuffer("");
    try {
      Reader r = this.getReader();
      while (r.hasMoreTerms()) {
        int id = r.nextTerm();
        TermPositions pos = new TermPositions();
        r.getPositions(pos);
        s.append(String.format("(%d, %d, %s)", map.getTerm(id), pos.getTf(), pos));
      }
      s.append("]");
    } catch (Exception e) {
      e.printStackTrace();
    }
View Full Code Here
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
        }

        numPostings = 0;
        Iterator<TermPositions> iter = values.iterator();
        while (iter.hasNext()) {
          TermPositions positions = iter.next();
          numPostings += positions.getPositions()[0];
        }

        postings.setNumberOfPostings(numPostings);
        return;
      }

      Iterator<TermPositions> iter = values.iterator();
      TermPositions positions = iter.next();
      postings.add(pair.getRightElement(), positions.getTf(), positions);

      if (iter.hasNext()) {
        throw new RuntimeException(
            String.format("Error: values with the same (term, docno): docno=%d, term=%d",
                pair.getRightElement(), curTerm));
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
        }

        numPostings = 0;
        Iterator<TermPositions> iter = values.iterator();
        while (iter.hasNext()) {
          TermPositions positions = iter.next();
          numPostings += positions.getPositions()[0];
        }

        postings.setNumberOfPostings(numPostings);
        return;
      }

      Iterator<TermPositions> iter = values.iterator();
      TermPositions positions = iter.next();
      postings.add(pair.getRightElement(), positions.getTf(), positions);

      if (iter.hasNext()) {
        throw new RuntimeException(
            String.format("Error: values with the same (term, docno): docno=%d, term=%d",
                pair.getRightElement(), curTerm));
View Full Code Here
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
      bitsOut = new BitOutputStream(bytesOut);

      Iterator<Map.Entry<Integer, int[]>> it = termPositionsMap.entrySet().iterator();
      Map.Entry<Integer, int[]> posting = it.next();
      int[] positions = posting.getValue();
      TermPositions tp = new TermPositions();
      // Write out the first termid.
      int lastTerm = posting.getKey().intValue();
      bitsOut.writeBinary(32, lastTerm);
      // Write out the tf value.
      bitsOut.writeGamma((short) positions.length);
      tp.set(positions, (short) positions.length);
      // Write out the positions.
      writePositions(bitsOut, tp);

      int curTerm;
      while (it.hasNext()) {
        posting = it.next();
        curTerm = posting.getKey().intValue();
        positions = posting.getValue();
        int tgap = curTerm - lastTerm;
        if (tgap <= 0) {
          throw new RuntimeException("Error: encountered invalid t-gap. termid=" + curTerm);
        }
        // Write out the gap.
        bitsOut.writeGamma(tgap);
        tp.set(positions, (short) positions.length);
        // Write out the tf value.
        bitsOut.writeGamma((short) positions.length);
        // Write out the positions.
        writePositions(bitsOut, tp);
        lastTerm = curTerm;
View Full Code Here
188
189
190
191
192
193
194
195
196
197
198
199
200
    StringBuffer s = new StringBuffer("[");
    try {
      Reader r = this.getReader();
      while (r.hasMoreTerms()) {
        int id = r.nextTerm();
        TermPositions pos = new TermPositions();
        r.getPositions(pos);
        s.append("(" + id + ", " + pos.getTf() + ", " + pos + ")");
      }
      s.append("]");
    } catch (Exception e) {
      e.printStackTrace();
    }
View Full Code Here
205
206
207
208
209
210
211
212
213
214
215
216
217
    StringBuffer s = new StringBuffer("");
    try {
      Reader r = this.getReader();
      while (r.hasMoreTerms()) {
        int id = r.nextTerm();
        TermPositions pos = new TermPositions();
        r.getPositions(pos);
        s.append(String.format("(%d, %d, %s)", map.getTerm(id), pos.getTf(), pos));
      }
      s.append("]");
    } catch (Exception e) {
      e.printStackTrace();
    }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
    assertEquals(17, tp.getEncodedSize());
  }

  @Test
  public void testSerial2() throws IOException {
    TermPositions tp = new TermPositions();
    int[] pos = { 1, 4, 5, 10, 23, 324 };

    // If the int array is longer than tf, ignore the extra ints.
    tp.set(pos, (short) 5);

    assertEquals(5, tp.getTf());

    byte[] bytes = tp.serialize();
    TermPositions tp2 = TermPositions.create(bytes);

    assertEquals(5, tp2.getTf());
    int[] pos2 = tp2.getPositions();

    assertEquals(1, pos2[0]);
    assertEquals(4, pos2[1]);
    assertEquals(5, pos2[2]);
    assertEquals(10, pos2[3]);
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
  @Test
  public void testSerial3() throws IOException {
    // Check large term positions for possible overflow. This would show up
    // if we were using shorts somewhere in the code for term positions.
    TermPositions tp = new TermPositions();
    int[] pos = { 1, 4, 5311782, 5311783, 98921257 };
    tp.set(pos, (short) 5);

    assertEquals(5, tp.getTf());

    byte[] bytes = tp.serialize();
    TermPositions tp2 = TermPositions.create(bytes);

    assertEquals(5, tp2.getTf());
    int[] pos2 = tp2.getPositions();

    assertEquals(1, pos2[0]);
    assertEquals(4, pos2[1]);
    assertEquals(5311782, pos2[2]);
    assertEquals(5311783, pos2[3]);
View Full Code Here
TOP

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

  • ivory.core.compression.BitInputStream
  • ivory.core.compression.BitOutputStream
  • ivory.core.data.document.LazyIntDocVector
  • ivory.core.data.document.LazyTermDocVector
  • ivory.core.data.index.TermPositionsTest
  • ivory.core.index.BuildIPInvertedIndexDocSorted$MyReducer
  • ivory.core.index.BuildLPInvertedIndexDocSorted$MyMapper
  • ivory.ffg.data.CompressedPositionalPostingsTest
  • ivory.ffg.data.DocumentVectorUtility
  • ivory.ffg.preprocessing.GenerateCompressedPositionalPostings
    • 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.