Examples of TextInputFormat

Examples of org.apache.hadoop.mapreduce.lib.input.TextInputFormat

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
124
125
126
127
128
129
  @Override
  protected boolean runJob(Job job) throws IOException, InterruptedException {
    Configuration conf = job.getConfiguration();
   
    // retrieve the splits
    TextInputFormat input = new TextInputFormat();
    List<InputSplit> splits = input.getSplits(job);
   
    int nbSplits = splits.size();
    log.debug("Nb splits : " + nbSplits);

    InputSplit[] sorted = new InputSplit[nbSplits];
    splits.toArray(sorted);
    Builder.sortSplits(sorted);

    int numTrees = Builder.getNbTrees(conf); // total number of trees

    TaskAttemptContext task = new TaskAttemptContext(conf, new TaskAttemptID());

    firstOutput = new MockContext(new Step1Mapper(), conf, task.getTaskAttemptID(), numTrees);

    firstIds = new int[nbSplits];
    sizes = new int[nbSplits];
   
    // to compute firstIds, process the splits in file order
    long slowest = 0; // duration of slowest map
    int firstId = 0;
    for (int p = 0; p < nbSplits; p++) {
      InputSplit split = splits.get(p);
      int hp = ArrayUtils.indexOf(sorted, split); // hadoop's partition
     
      RecordReader<LongWritable, Text> reader = input.createRecordReader(split, task);
      reader.initialize(split, task);
     
      Step1Mapper mapper = new MockStep1Mapper(getTreeBuilder(), dataset, getSeed(),
          hp, nbSplits, numTrees);
View Full Code Here

Examples of org.apache.hadoop.mapreduce.lib.input.TextInputFormat

210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
  protected void secondStep(Configuration conf, Path forestPath, PredictionCallback callback)
      throws IOException, InterruptedException {
    JobContext jobContext = new JobContext(conf, new JobID());
   
    // retrieve the splits
    TextInputFormat input = new TextInputFormat();
    List<InputSplit> splits = input.getSplits(jobContext);
   
    int nbSplits = splits.size();
    log.debug("Nb splits : " + nbSplits);

    InputSplit[] sorted = new InputSplit[nbSplits];
    splits.toArray(sorted);
    Builder.sortSplits(sorted);

    int numTrees = Builder.getNbTrees(conf); // total number of trees

    // compute the expected number of outputs
    int total = 0;
    for (int p = 0; p < nbSplits; p++) {
      total += Step2Mapper.nbConcerned(nbSplits, numTrees, p);
    }

    TaskAttemptContext task = new TaskAttemptContext(conf, new TaskAttemptID());

    secondOutput = new MockContext(new Step2Mapper(), conf, task.getTaskAttemptID(), numTrees);
    long slowest = 0; // duration of slowest map

    for (int partition = 0; partition < nbSplits; partition++) {
     
      InputSplit split = sorted[partition];
      RecordReader<LongWritable, Text> reader = input.createRecordReader(split, task);

      // load the output of the 1st step
      int nbConcerned = Step2Mapper.nbConcerned(nbSplits, numTrees, partition);
      TreeID[] fsKeys = new TreeID[nbConcerned];
      Node[] fsTrees = new Node[nbConcerned];
View Full Code Here

Examples of org.apache.hadoop.mapreduce.lib.input.TextInputFormat

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
    FileInputFormat.setInputPaths(job, dataPath);

    setMaxSplitSize(job.getConfiguration(), dataPath, numMaps);

    // retrieve the splits
    TextInputFormat input = new TextInputFormat();
    List<InputSplit> splits = input.getSplits(job);
    assertEquals(numMaps, splits.size());

    InputSplit[] sorted = new InputSplit[numMaps];
    splits.toArray(sorted);
    Builder.sortSplits(sorted);

    context = new Step0Context(new Step0Mapper(), job.getConfiguration(),
        new TaskAttemptID(), numMaps);

    for (int p = 0; p < numMaps; p++) {
      InputSplit split = sorted[p];

      RecordReader<LongWritable, Text> reader = input.createRecordReader(split,
          context);
      reader.initialize(split, context);

      Step0Mapper mapper = new Step0Mapper();
      mapper.configure(p);
View Full Code Here

Examples of org.apache.hadoop.mapreduce.lib.input.TextInputFormat

172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
    FileInputFormat.setInputPaths(job, dataPath);

    setMaxSplitSize(job.getConfiguration(), dataPath, numMaps);

    // retrieve the splits
    TextInputFormat input = new TextInputFormat();
    List<InputSplit> splits = input.getSplits(job);
    assertEquals(numMaps, splits.size());

    InputSplit[] sorted = new InputSplit[numMaps];
    splits.toArray(sorted);
    Builder.sortSplits(sorted);

    List<Integer> keys = new ArrayList<Integer>();
    List<Step0Output> values = new ArrayList<Step0Output>();

    int[] expectedIds = new int[numMaps];

    TaskAttemptContext context = new TaskAttemptContext(job.getConfiguration(),
        new TaskAttemptID());

    for (int p = 0; p < numMaps; p++) {
      InputSplit split = sorted[p];
      RecordReader<LongWritable, Text> reader = input.createRecordReader(split,
          context);
      reader.initialize(split, context);

      Long firstKey = null;
      int size = 0;
View Full Code Here

Examples of org.apache.hadoop.mapreduce.lib.input.TextInputFormat

331
332
333
334
335
336
337
338
339
            } else {
                result = new PigAvroInputFormat(
                        inputAvroSchema, ignoreBadFiles, schemaToMergedSchemaMap);
            }
        } else {
            result = new TextInputFormat();
        }
        return result;
    }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.