Package edu.umd.cloud9.io

Examples of edu.umd.cloud9.io.FSLineReader

191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
          "-output_path=" + indexRootPath + "/wiki-docid-tmp",
          "-output_file=" + mappingFile.toString(),
          "-wiki_language=" + collectionLang };
      LOG.info("Running BuildWikipediaDocnoMapping with args " + Arrays.toString(arr));

      BuildWikipediaDocnoMapping tool = new BuildWikipediaDocnoMapping();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(new Path(indexRootPath + "/wiki-docid-tmp"), true);
    } else {
      LOG.info("Docno mapping already exists at: " + mappingFile);
    }

    // Repack Wikipedia into sequential compressed block
    if (!fs.exists(new Path(seqCollection + "/part-00000"))) {
      LOG.info(seqCollection + " doesn't exist, creating...");
      String[] arr = new String[] { "-input=" + rawCollection,
          "-output=" + seqCollection,
          "-mapping_file=" + mappingFile.toString(),
          "-compression_type=block",
          "-wiki_language=" + collectionLang };
      LOG.info("Running RepackWikipedia with args " + Arrays.toString(arr));

      RepackWikipedia tool = new RepackWikipedia();
      tool.setConf(conf);
      tool.run(arr);
    } else {
      LOG.info("Repacked collection already exists at: " + seqCollection);     
    }

    conf.set(Constants.CollectionName, "Wikipedia-"+collectionLang);
View Full Code Here
199
200
201
202
203
204
205
206
207
208
209
210
211
        "-mapping_file=" + mappingFile.toString(),
        "-compression_type=block",
        "-wiki_language=" + collectionLang };
    LOG.info("Running RepackWikipedia with args " + Arrays.toString(arr));

    RepackWikipedia tool = new RepackWikipedia();
    tool.setConf(conf);
    tool.run(arr);

    conf.set(Constants.CollectionName, "Wikipedia-"+collectionLang);
    conf.setInt(Constants.NumMapTasks, numMappers);
    conf.setInt(Constants.NumReduceTasks, numReducers);
    conf.set(Constants.CollectionPath, seqCollection);
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
    // Repack Wikipedia into sequential compressed block
    p = new Path(seqCollection);
    if (!fs.exists(p)) {
      LOG.info(seqCollection + " doesn't exist, creating...");
      String[] arr = new String[] { rawCollection, seqCollection, mappingFile.toString(), "block"};
      RepackWikipedia tool = new RepackWikipedia();
      tool.setConf(conf);
      tool.run(arr);
    }

    conf.set("Ivory.CollectionName", "Wikipedia-"+collectionLang);
    conf.setInt("Ivory.NumMapTasks", numMappers);
    conf.setInt("Ivory.NumReduceTasks", numReducers);
View Full Code Here
210
211
212
213
214
215
216
217
218
219
220
221
222
          "-mapping_file=" + mappingFile.toString(),
          "-compression_type=block",
          "-wiki_language=" + collectionLang };
      LOG.info("Running RepackWikipedia with args " + Arrays.toString(arr));

      RepackWikipedia tool = new RepackWikipedia();
      tool.setConf(conf);
      tool.run(arr);
    } else {
      LOG.info("Repacked collection already exists at: " + seqCollection);     
    }

    conf.set(Constants.CollectionName, "Wikipedia-"+collectionLang);
View Full Code Here
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
        if (fileStats[i].getPath().getName().startsWith("_")) {
          continue;
        }

        LOG.info("processing " + fileStats[i].getPath());
        FSLineReader reader = new FSLineReader(fileStats[i].getPath(), fs);

        Text line = new Text();
        while (reader.readLine(line) > 0) {
          String[] arr = line.toString().split("\\t+", 2);

          int docno = Integer.parseInt(arr[0]);
          int len = Integer.parseInt(arr[1]);

          // Note that because of speculative execution there may be
          // multiple copies of doclength data. Therefore, we can't
          // just count number of doclengths read. Instead, keep track
          // of largest docno encountered.
          if (docno < docnoOffset) {
            throw new RuntimeException(
                "Error: docno " + docno + " < docnoOffset " + docnoOffset + "!");
          }

          doclengths[docno - docnoOffset] = len;

          if (docno > maxDocno) {
            maxDocno = docno;
          }
          if (docno < minDocno) {
            minDocno = docno;
          }
        }
        reader.close();
        context.getCounter(DocLengths.Files).increment(1);
      }

      LOG.info("min docno: " + minDocno);
      LOG.info("max docno: " + maxDocno);
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
      }

      if(localFiles!=null && localFiles.length > 0){
        samplesMap = new HMapIIW();
        try {
          FSLineReader reader = new FSLineReader(localFiles[0], FileSystem.getLocal(job));
          Text t = new Text();
          while(reader.readLine(t)!=0){
            int docno = Integer.parseInt(t.toString());
            samplesMap.put(docno, 1);
          }
          reader.close();
        } catch (IOException e1) {
        }
        sLogger.info(samplesMap);
      }
    }
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
      // if cache is non-empty, a docnos file has been entered
      if(localFiles != null){
        sLogger.setLevel(Level.INFO);
        samplesMap = new HMapII();
        try {
          FSLineReader reader = new FSLineReader(localFiles[0], FileSystem.getLocal(conf));
          Text t = new Text();
          while(reader.readLine(t)!=0){
            int docno = Integer.parseInt(t.toString());
            samplesMap.put(docno, 1);
          }
          reader.close();
        } catch (IOException e1) {
        }
        sLogger.info(samplesMap);
      }
    }
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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
      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();
        ClueWarcRecord doc = null;

        for (int i = 0; i < 10; i++) {
          doc = indexes[i].getDocument(docid);
          if (doc != null)
            break;
        }
        String url = doc.getHeaderMetadataItem("WARC-Target-URI");
        long duration = System.currentTimeMillis() - start;

        reporter.incrCounter(MyCounter.Count, 1);
        reporter.incrCounter(MyCounter.Time, duration);

        if (rank == 1 || rank % 100 == 0)
          sLogger.info(line + " " + url + " (" + duration + "ms)");
        writer.write(new String(line + " " + url + "\n").getBytes());
      }

      reader.close();
      writer.close();

    }
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
      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);

        if (rank == 1 || rank % 100 == 0)
          sLogger.info(line + " " + url + " (" + duration + "ms)");
        writer.write(new String(line + " " + url + "\n").getBytes());
      }

      reader.close();
      writer.close();

    }
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
     
      if(localFiles.length > 1){
        dotProductThresholds = new float[D];
        int i = 0;
        try {
          FSLineReader reader = new FSLineReader(localFiles[1], FileSystem.getLocal(job));
          Text t = new Text();
          while(reader.readLine(t)!=0){
            float val = Float.parseFloat(t.toString());
            sLogger.debug(i + " --> "+val);
            dotProductThresholds[i] = val;
          }
          reader.close();
        } catch (IOException e1) {
        }
        sLogger.info("Dot product thresholds read");
      }else{
        sLogger.info("Dot product thresholds file not specified in option Ivory.DotProdThreshFile");
View Full Code Here
TOP

Related Classes of edu.umd.cloud9.io.FSLineReader

  • 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.