Package ivory.core

Examples of ivory.core.RetrievalEnvironment

68
69
70
71
72
73
74
75
76
77
78
    }
    LOG.info("Bigram segmentation = " + bigramSegment);

    // initialize environment to access index
    try {
      env = new RetrievalEnvironment(conf.get(Constants.IndexPath), fs);
      env.initialize(true);
    } catch (ConfigurationException e) {
      e.printStackTrace();
    }
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
    // initialize environment to access index
    // skip this if we only want to translate query (i.e., no retrieval)
    if (translateOnly == null) {   
      try {
        env = new RetrievalEnvironment(conf.get(Constants.IndexPath), fs);
        env.initialize(true);
      } catch (Exception e) {
        throw new RuntimeException(e);
      }
    }
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
109
110
      mCollectionDocCount = job.getInt("Ivory.CollectionDocumentCount", -1);

      try {
        if (job.get("mapred.job.tracker").equals("local")) {
          FileSystem fs = FileSystem.getLocal(job);
          RetrievalEnvironment re = new RetrievalEnvironment(job.get("Ivory.IndexPath"),
              fs);
          Path path = re.getDoclengthsData();
          sLogger.debug("Reading doclengths: " + path);
          mDocLengthTable = new DocLengthTable2B(path, fs);
        } else {
          Path[] localFiles = DistributedCache.getLocalCacheFiles(job);
          mDocLengthTable = new DocLengthTable2B(localFiles[0], FileSystem.getLocal(job));
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
    String indexPath = args[0];

    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(conf);

    RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);

    Path termsFilePath = new Path(env.getIndexTermsData());
    Path termIDsFilePath = new Path(env.getIndexTermIdsData());
    Path idToTermFilePath = new Path(env.getIndexTermIdMappingData());

    DefaultCachedFrequencySortedDictionary dictionary =
        new DefaultCachedFrequencySortedDictionary(termsFilePath, termIDsFilePath,
            idToTermFilePath, 100, fs);
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
    }   
  }
 
  protected void loadRetrievalEnv() throws ConfigurationException{
    try {
      env = new RetrievalEnvironment(indexPath, fs);
      env.initialize(true);
    } catch (IOException e) {
      throw new ConfigurationException("Failed to instantiate RetrievalEnvironment: "
          + e.getMessage());
    }
View Full Code Here
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
    String indexPath = args[0];

    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(conf);

    RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);

    Path termsFilePath = new Path(env.getIndexTermsData());
    Path termIDsFilePath = new Path(env.getIndexTermIdsData());
    Path idToTermFilePath = new Path(env.getIndexTermIdMappingData());

    DefaultFrequencySortedDictionary dictionary =
        new DefaultFrequencySortedDictionary(termsFilePath, termIDsFilePath, idToTermFilePath, fs);

    int nTerms = dictionary.size();
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
  public IntDocVectorsForwardIndex(String indexPath, FileSystem fs, boolean weighted)
      throws IOException {
    this.fs = Preconditions.checkNotNull(fs);
    this.conf = fs.getConf();

    RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);
    path = (weighted ? env.getWeightedIntDocVectorsDirectory() : env.getIntDocVectorsDirectory());

    String forwardIndexPath = (weighted ? env.getWeightedIntDocVectorsForwardIndex()
        : env.getIntDocVectorsForwardIndex());
    FSDataInputStream posInput = fs.open(new Path(forwardIndexPath));

    docnoOffset = posInput.readInt();
    collectionDocumentCount = posInput.readInt();
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
  public TermDocVectorsForwardIndex(String indexPath, FileSystem fs) throws IOException {
    Preconditions.checkNotNull(indexPath);
    this.fs = Preconditions.checkNotNull(fs);
    conf = fs.getConf();

    RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);
    path = env.getTermDocVectorsDirectory();

    FSDataInputStream posInput = fs.open(new Path(env.getTermDocVectorsForwardIndex()));

    docnoOffset = posInput.readInt();
    collectionDocumentCount = posInput.readInt();

    positions = new long[collectionDocumentCount];
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
  public IntPostingsForwardIndex(String indexPath, FileSystem fs) throws IOException {
    this.fs = fs;
    this.conf = fs.getConf();
    postingsType = ivory.core.data.index.PostingsListDocSortedPositional.class.getCanonicalName();
    RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);
    postingsPath = env.getPostingsDirectory();

    FSDataInputStream posInput = fs.open(new Path(env
        .getPostingsIndexData()));

    int l = posInput.readInt();
    positions = new long[l];
    for (int i = 0; i < l; i++) {
View Full Code Here
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
303
304
305
306
307
308
309
310
311
312
313
314
315
316
    int blockSize = getConf().getInt("Ivory.BlockSize", -1);
    int topN = getConf().getInt("Ivory.TopN", -1);

    FileSystem fs = FileSystem.get(getConf());

    RetrievalEnvironment re = new RetrievalEnvironment(indexPath, fs);

    String collectionName = re.readCollectionName();
    int numDocs = re.readCollectionDocumentCount();
    Path docLengthPath = re.getDoclengthsData();
    String scoringModel = getConf().get("Ivory.ScoringModel");

    sLogger.info("Characteristics of the collection:");
    sLogger.info(" - CollectionName: " + collectionName);
    sLogger.info(" - IndexPath: " + indexPath);
    sLogger.info("Characteristics of the job:");
    sLogger.info(" - NumMapTasks: " + mapTasks);
    sLogger.info(" - NumReduceTasks: " + reduceTasks);
    sLogger.info(" - DfCut: " + getConf().getInt("Ivory.DfCut", 0));
    sLogger.info(" - BlockSize: " + blockSize);
    sLogger.info(" - ScoringModel: " + scoringModel);
    sLogger.info(" - topN: " + topN);
    sLogger.info(" - OutputPath: " + outputPath);

    getConf().setInt("Ivory.CollectionDocumentCount", numDocs);

    if (fs.exists(new Path(outputPath))) {
      System.out.println("PCP output path already exists!");
      return 0;
    }

    int numBlocks = numDocs / blockSize + 1;

    for (int i = 0; i < numBlocks; i++) {
      int start = blockSize * i;
      int end = i == numBlocks - 1 ? numDocs : blockSize * (i + 1);

      JobConf conf = new JobConf(getConf(), PCP.class);
      DistributedCache.addCacheFile(docLengthPath.toUri(), conf);

      sLogger.info("block " + i + ": " + start + "-" + end);

      conf.setInt("Ivory.BlockStart", start);
      conf.setInt("Ivory.BlockEnd", end);

      conf.setJobName("PCP:" + collectionName + "-dfCut=" + dfCut
          + (topN > 0 ? "-topN" + topN : "-all") + ":Block #" + i);

      conf.setNumMapTasks(mapTasks);
      conf.setNumReduceTasks(reduceTasks);

      String currentOutputPath = outputPath + "/block" + i;

      FileInputFormat.setInputPaths(conf, new Path(re.getPostingsDirectory()));
      FileOutputFormat.setOutputPath(conf, new Path(currentOutputPath));

      conf.setInputFormat(SequenceFileInputFormat.class);
      conf.setOutputKeyClass(IntWritable.class);
      conf.setOutputValueClass(HMapIFW.class);
View Full Code Here
TOP

Related Classes of ivory.core.RetrievalEnvironment

  • edu.umd.cloud9.collection.DocnoMapping
  • ivory.app.PreprocessClueWebEnglish
  • ivory.app.PreprocessClueWebEnglishMultipleSegments
  • ivory.app.PreprocessCollection
  • ivory.app.PreprocessMedline
  • ivory.app.PreprocessTextCollection
  • ivory.app.PreprocessTrecForeign
  • ivory.app.PreprocessWikipedia
  • ivory.bloomir.preprocessing.GenerateBloomFilters
  • ivory.bloomir.preprocessing.GenerateCompressedPostings
    • 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.