Package org.terrier.compression

Examples of org.terrier.compression.BitIn

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
    for(int i=0;i<fieldCount+3;i++)
      documentTerms[i] = new int[df];
    final TIntArrayList blockids = new TIntArrayList(df); //ideally we'd have TF here

    try{
      final BitIn file = this.file[pointer.getFileNumber()].readReset(startOffset, startBitOffset);
 
      if (loadTagInformation) { //if there are tag information to process
        //documentTerms[2] = new int[df];
        documentTerms[0][0] = file.readGamma() - 1;       
        documentTerms[1][0] = file.readUnary();
        for(int fi=0;fi < fieldCount;fi++)
          documentTerms[2+fi][0] = file.readUnary() -1;
        int blockfreq = documentTerms[2+fieldCount][0] = file.readUnary() - DocumentBlockCountDelta;
        int tmpBlocks[] = new int[blockfreq];
        int previousBlockId = -1;
        for(int j=0;j<blockfreq;j++)
        {
          tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
        }
        blockids.add(tmpBlocks);
       
        for (int i = 1; i < df; i++) {         
          documentTerms[0][i]  = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i]  = file.readUnary();
          for(int fi=0;fi < fieldCount;fi++)
            documentTerms[2+fi][0] = file.readUnary() -1;
          blockfreq = documentTerms[2+fieldCount][i] = file.readUnary() - DocumentBlockCountDelta;
          tmpBlocks = new int[blockfreq];
          previousBlockId = -1;
          for(int j=0;j<blockfreq;j++)
          {
            tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
          }
          blockids.add(tmpBlocks);
        }
      } else { //no tag information to process         
       
        documentTerms[0][0] = file.readGamma() - 1;
        documentTerms[1][0] = file.readUnary();
       
        int blockfreq = documentTerms[2][0] = file.readUnary() - DocumentBlockCountDelta;
        int tmpBlocks[] = new int[blockfreq];
        int previousBlockId = -1;
        for(int j=0;j<blockfreq;j++)
        {
          tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
        }
        blockids.add(tmpBlocks);
       
        for (int i = 1; i < df; i++) {         
          documentTerms[0][i]  = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i]  = file.readUnary();

          blockfreq = documentTerms[2][i] = file.readUnary() - DocumentBlockCountDelta;
          tmpBlocks = new int[blockfreq];
          previousBlockId = -1;
          for(int j=0;j<blockfreq;j++)
          {
            tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
          }
          blockids.add(tmpBlocks);
        }
      }
      documentTerms[documentTerms.length-1] = blockids.toNativeArray();
View Full Code Here
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
    if (pointer==null)
      return null;
    final boolean loadTagInformation = FieldScore.USE_FIELD_INFORMATION;
    final int count = pointer.getNumberOfEntries();
    try{
      final BitIn file = this.file[pointer.getFileNumber()].readReset(pointer.getOffset(), pointer.getOffsetBits());
      int[][] documentTerms = null;
      if (loadTagInformation) { //if there are tag information to process     
        documentTerms = new int[2+fieldCount][count];
        documentTerms[0][0] = file.readGamma() - 1;
        documentTerms[1][0] = file.readUnary();
        for (int f = 0; f < fieldCount; f++) {
          documentTerms[2+f][0] = file.readUnary() - 1;
        }
       
        for (int i = 1; i < count; i++) {         
          documentTerms[0][i] = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i] = file.readUnary();
          for (int f = 0; f < fieldCount; f++) {
            documentTerms[2+f][i] = file.readUnary() - 1;
          }
        }       
      } else { //no tag information to process         
        documentTerms = new int[2][count];
        //new   
        documentTerms[0][0] = file.readGamma() - 1;
        documentTerms[1][0] = file.readUnary();
        for(int i = 1; i < count; i++){              
          documentTerms[0][i] = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i] = file.readUnary();
        }
      }
      file.close();
      return documentTerms;
    } catch (IOException ioe) {
      logger.error("Problem reading inverted index", ioe);
      return null;
    }
View Full Code Here
164
165
166
167
168
169
170
171
172
173
174
  /**
   * {@inheritDoc}
   */
  public IterablePosting getPostings(BitIndexPointer pointer) throws IOException
  {
    final BitIn _file = this.file[pointer.getFileNumber()].readReset(pointer.getOffset(), pointer.getOffsetBits());
    IterablePosting rtr = null;
   
    DocumentIndex fixedDi = pointer instanceof DocumentIndexEntry
      ? new DocidSpecificDocumentIndex(index.getDocumentIndex(), (DocumentIndexEntry)pointer)
      : null;
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
    throw new UnsupportedOperationException("InvIndex.print() is missing. Use IndexUtil instead.");
  }
 
  @Override
  public IterablePosting getPostings(BitIndexPointer pointer) throws IOException {
    final BitIn _file = this.file[pointer.getFileNumber()].readReset(pointer.getOffset(), pointer.getOffsetBits());
    IterablePosting rtr = null;
    try{
      rtr = (fieldCount > 0)
        ? postingConstructor.newInstance(_file, pointer.getNumberOfEntries(), doi, fieldCount)
        : postingConstructor.newInstance(_file, pointer.getNumberOfEntries(), doi);
View Full Code Here
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
    if (pointer==null)
      return null;
    final boolean loadTagInformation = FieldScore.USE_FIELD_INFORMATION;
    final int count = pointer.getNumberOfEntries();
    try{
      final BitIn file = this.file[pointer.getFileNumber()].readReset(pointer.getOffset(), pointer.getOffsetBits());
      int[][] documentTerms = null;
      if (loadTagInformation) { //if there are tag information to process     
        documentTerms = new int[2+fieldCount][count];
        documentTerms[0][0] = file.readGamma() - 1;
        documentTerms[1][0] = file.readUnary();
        for (int f = 0; f < fieldCount; f++) {
          documentTerms[2+f][0] = file.readUnary() - 1;
        }       

        for (int i = 1; i < count; i++) {         
          documentTerms[0][i]  = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i]  = file.readUnary();
          for (int f = 0; f < fieldCount; f++) {
            documentTerms[2+f][i] = file.readUnary() - 1;
          }
        }       
      } else { //no tag information to process         
        documentTerms = new int[2][count];
        //new   
        documentTerms[0][0] = file.readGamma() - 1;
        documentTerms[1][0] = file.readUnary();
        for(int i = 1; i < count; i++){              
          documentTerms[0][i] = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i] = file.readUnary();
        }
      }
      file.close();
      return documentTerms;
    } catch (IOException ioe) {
      logger.error("Problem reading inverted index", ioe);
      return null;
    }
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
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
    for(int i=0;i<fieldCount+3;i++)
      documentTerms[i] = new int[df];
    final TIntArrayList blockids = new TIntArrayList(df); //ideally we'd have TF here

    try{
      final BitIn file = this.file[pointer.getFileNumber()].readReset(startOffset, startBitOffset);
 
      if (loadTagInformation) { //if there are tag information to process
        //documentTerms[2] = new int[df];
        documentTerms[0][0] = file.readGamma() - 1;       
        documentTerms[1][0] = file.readUnary();
        for(int fi=0;fi < fieldCount;fi++)
          documentTerms[2+fi][0] = file.readUnary() -1;
        int blockfreq = documentTerms[2+fieldCount][0] = file.readUnary() - DocumentBlockCountDelta;
        int tmpBlocks[] = new int[blockfreq];
        int previousBlockId = -1;
        for(int j=0;j<blockfreq;j++)
        {
          tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
        }
        blockids.add(tmpBlocks);
       
        for (int i = 1; i < df; i++) {         
          documentTerms[0][i]  = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i]  = file.readUnary();
          for(int fi=0;fi < fieldCount;fi++)
            documentTerms[2+fi][0] = file.readUnary() -1;
          blockfreq = documentTerms[2+fieldCount][i] = file.readUnary() - DocumentBlockCountDelta;
          tmpBlocks = new int[blockfreq];
          previousBlockId = -1;
          for(int j=0;j<blockfreq;j++)
          {
            tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
          }
          blockids.add(tmpBlocks);
        }
      } else { //no tag information to process         
       
        documentTerms[0][0] = file.readGamma() - 1;
        documentTerms[1][0] = file.readUnary();
       
        int blockfreq = documentTerms[2][0] = file.readUnary() - DocumentBlockCountDelta;
        int tmpBlocks[] = new int[blockfreq];
        int previousBlockId = -1;
        for(int j=0;j<blockfreq;j++)
        {
          tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
        }
        blockids.add(tmpBlocks);
       
        for (int i = 1; i < df; i++) {         
          documentTerms[0][i]  = file.readGamma() + documentTerms[0][i - 1];
          documentTerms[1][i]  = file.readUnary();

          blockfreq = documentTerms[2][i] = file.readUnary() - DocumentBlockCountDelta;
          tmpBlocks = new int[blockfreq];
          previousBlockId = -1;
          for(int j=0;j<blockfreq;j++)
          {
            tmpBlocks[j] = previousBlockId = file.readGamma() + previousBlockId;
          }
          blockids.add(tmpBlocks);
        }
      }
      documentTerms[documentTerms.length-1] = blockids.toNativeArray();
View Full Code Here
TOP

Related Classes of org.terrier.compression.BitIn

  • org.terrier.structures.BitPostingIndex
  • org.terrier.structures.BlockDirectIndex
  • org.terrier.structures.BlockInvertedIndex
  • org.terrier.structures.DirectIndex
  • org.terrier.structures.InvertedIndex
    • 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.