Package edu.umd.cloud9.collection.clue

Examples of edu.umd.cloud9.collection.clue.ClueWarcForwardIndex

658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
  public DocnoMapping getDocnoMapping() throws IOException {
    return loadDocnoMapping(indexPath, fs);
  }

  public static DocnoMapping loadDocnoMapping(String indexPath, FileSystem fs) throws IOException {
    DocnoMapping mDocMapping = null;
    // load the docid to docno mappings
    try {
      LOG.info("Loading DocnoMapping file...");
      RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);

      String className = env.readDocnoMappingClass();
      LOG.info(" - Class name: " + className);
      mDocMapping = (DocnoMapping) Class.forName(className).newInstance();

      Path mappingFile = env.getDocnoMappingData();
      LOG.info(" - File name: " + mappingFile);
      mDocMapping.loadMapping(mappingFile, fs);
      LOG.info("Done!");
    } catch (Exception e) {
      throw new IOException("Error initializing DocnoMapping!");
    }
    return mDocMapping;
View Full Code Here
359
360
361
362
363
364
365
366
367
368
369
    if (list.getLength() > 0) {  conf.set(Constants.StemmedStopwordListQ, list.item(0).getTextContent());  } 
  }

  static float eval(QueryEngine qe, Configuration conf, String setting){
    Qrels qrels = new Qrels(conf.get(Constants.QrelsPath));
    DocnoMapping mapping = qe.getDocnoMapping();
    float apSum = 0, p10Sum = 0;
    Map<String, Accumulator[]> results = qe.getResults();
    for (String qid : results.keySet()) {
      float ap = (float) RankedListEvaluator.computeAP(results.get(qid), mapping,
          qrels.getReldocsForQid(qid));
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
      return -1;
    }

    RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);
    Path mappingFile = env.getDocnoMappingData();
    new ClueWarcDocnoMappingBuilder().build(new Path(collection), mappingFile, conf);

    conf.set(Constants.CollectionName, "ClueWeb:English:Segment" + segment);
    conf.set(Constants.CollectionPath, collection);
    conf.set(Constants.IndexPath, indexPath);
    conf.set(Constants.InputFormat, SequenceFileInputFormat.class.getCanonicalName());
View Full Code Here
41
42
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
      String inputFile = conf.get("InputFile");
      String outputFile = conf.get("OutputFile");

      ClueWarcForwardIndex[] indexes = new ClueWarcForwardIndex[10];

      indexes[0] = new ClueWarcForwardIndex();
      indexes[0].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.01.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[1] = new ClueWarcForwardIndex();
      indexes[1].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.02.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[2] = new ClueWarcForwardIndex();
      indexes[2].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.03.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[3] = new ClueWarcForwardIndex();
      indexes[3].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.04.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[4] = new ClueWarcForwardIndex();
      indexes[4].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.05.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[5] = new ClueWarcForwardIndex();
      indexes[5].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.06.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[6] = new ClueWarcForwardIndex();
      indexes[6].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.07.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[7] = new ClueWarcForwardIndex();
      indexes[7].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.08.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[8] = new ClueWarcForwardIndex();
      indexes[8].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.09.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[9] = new ClueWarcForwardIndex();
      indexes[9].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.10.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      FileSystem fs = FileSystem.get(conf);
View Full Code Here
40
41
42
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
      String inputFile = conf.get("InputFile");
      String outputFile = conf.get("OutputFile");
      String findexFile = conf.get("ForwardIndexFile");
      String docnoMapping = conf.get("DocnoMappingFile");

      ClueWarcForwardIndex findex = new ClueWarcForwardIndex();
      findex.loadIndex(new Path(findexFile), new Path(docnoMapping), FileSystem.get(conf));

      FileSystem fs = FileSystem.get(conf);

      sLogger.info("reading " + inputFile);

      FSLineReader reader = new FSLineReader(new Path(inputFile), fs);
      FSDataOutputStream writer = fs.create(new Path(outputFile), true);

      Text line = new Text();
      while (reader.readLine(line) > 0) {
        String[] arr = line.toString().split("\\s+");

        String docid = arr[2];
        int rank = Integer.parseInt(arr[3]);

        long start = System.currentTimeMillis();
        String url = findex.getDocument(docid).getHeaderMetadataItem("WARC-Target-URI");
        long duration = System.currentTimeMillis() - start;

        reporter.incrCounter(MyCounter.Count, 1);
        reporter.incrCounter(MyCounter.Time, duration);
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
        "-collection=" + collectionPathRepacked,
        "-index=" + index };

    IntegrationUtils.exec(Joiner.on(" ").join(args));

    ClueWarcForwardIndex findex = new ClueWarcForwardIndex();
    findex.loadIndex(new Path(index), new Path(mappingFile), fs);

    assertTrue(findex.getDocument(14069750).getContent()
        .contains("Vizergy: How Design and SEO work together"));
    assertTrue(findex.getDocument("clueweb09-en0008-76-19728").getContent()
        .contains("Jostens - Homeschool Yearbooks"));
    assertEquals(1, findex.getFirstDocno());
    assertEquals(50220423, findex.getLastDocno());
  }
View Full Code Here
41
42
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
      String inputFile = conf.get("InputFile");
      String outputFile = conf.get("OutputFile");

      ClueWarcForwardIndex[] indexes = new ClueWarcForwardIndex[10];

      indexes[0] = new ClueWarcForwardIndex();
      indexes[0].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.01.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[1] = new ClueWarcForwardIndex();
      indexes[1].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.02.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[2] = new ClueWarcForwardIndex();
      indexes[2].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.03.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[3] = new ClueWarcForwardIndex();
      indexes[3].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.04.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[4] = new ClueWarcForwardIndex();
      indexes[4].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.05.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[5] = new ClueWarcForwardIndex();
      indexes[5].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.06.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[6] = new ClueWarcForwardIndex();
      indexes[6].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.07.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[7] = new ClueWarcForwardIndex();
      indexes[7].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.08.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[8] = new ClueWarcForwardIndex();
      indexes[8].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.09.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      indexes[9] = new ClueWarcForwardIndex();
      indexes[9].loadIndex(new Path("/shared/ClueWeb09/collection.compressed.block/findex.en.10.dat"),
               new Path("/shared/ClueWeb09/docno-mapping.dat"), FileSystem.get(conf));

      FileSystem fs = FileSystem.get(conf);
View Full Code Here
40
41
42
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
      String inputFile = conf.get("InputFile");
      String outputFile = conf.get("OutputFile");
      String findexFile = conf.get("ForwardIndexFile");
      String docnoMapping = conf.get("DocnoMappingFile");

      ClueWarcForwardIndex findex = new ClueWarcForwardIndex();
      findex.loadIndex(new Path(findexFile), new Path(docnoMapping), FileSystem.get(conf));

      FileSystem fs = FileSystem.get(conf);

      sLogger.info("reading " + inputFile);

      LineReader reader = new LineReader(fs.open(new Path(inputFile)));
      FSDataOutputStream writer = fs.create(new Path(outputFile), true);

      Text line = new Text();
      while (reader.readLine(line) > 0) {
        String[] arr = line.toString().split("\\s+");

        String docid = arr[2];
        int rank = Integer.parseInt(arr[3]);

        long start = System.currentTimeMillis();
        String url = findex.getDocument(docid).getHeaderMetadataItem("WARC-Target-URI");
        long duration = System.currentTimeMillis() - start;

        reporter.incrCounter(MyCounter.Count, 1);
        reporter.incrCounter(MyCounter.Time, duration);
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
    if (!fs.exists(p)) {
      sLogger.info("docno-mapping.dat doesn't exist, creating...");
      String[] arr = new String[] { collection, mappingDir.toString(), mappingFile.toString(),
          new Integer(numMappers).toString() };
      NumberTextDocuments tool = new NumberTextDocuments();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(mappingDir, true);
    }

    // Now we're ready to start the preprocessing pipeline... set
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
    // (sequentially-number integer). If it doesn't exist create it.
    Path mappingFile = env.getDocnoMappingData();
    if (!fs.exists(mappingFile)) {
      sLogger.info(mappingFile + " doesn't exist, creating...");
      String[] arr = new String[] { collection, indexPath + "/medline-docid-tmp",  mappingFile.toString(), new Integer(numMappers).toString() };
      NumberMedlineCitations tool = new NumberMedlineCitations();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(new Path(indexPath + "/medline-docid-tmp"), true);
    }

    // Now we're ready to start the preprocessing pipeline... set
View Full Code Here
TOP

Related Classes of edu.umd.cloud9.collection.clue.ClueWarcForwardIndex

  • bak.pcj.IntIterator
  • edu.umd.cloud9.example.bfs.BfsNodeTest
  • edu.umd.cloud9.example.pagerank.PageRankNodeTest
  • edu.umd.cloud9.io.array.ArrayListOfIntsWritable
  • edu.umd.cloud9.io.fastutil.Int2FloatOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.Int2IntOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.String2FloatOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.String2IntOpenHashMapWritableTest
  • edu.umd.cloud9.io.map.HMapIDW
  • edu.umd.cloud9.io.map.HMapIDWTest
    • 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.