Package org.apache.hadoop.mapred

Examples of org.apache.hadoop.mapred.RecordReader

514
515
516
517
518
519
520
521
522
523
524
525
526
527
    InputSplit[] splits = inputFormat.getSplits(jonconf, splitNumber);
    assertEquals("splits length should be " + splitNumber, splits.length, splitNumber);
    int readCount = 0;
    for (int i = 0; i < splits.length; i++) {
      int previousReadCount = readCount;
      RecordReader rr = inputFormat.getRecordReader(splits[i], jonconf, Reporter.NULL);
      Object key = rr.createKey();
      Object value = rr.createValue();
      while (rr.next(key, value)) {
        readCount++;
      }
      System.out.println("The " + i + "th split read "
          + (readCount - previousReadCount));
    }
View Full Code Here
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
        //LOG.info("splitting: got =        " + splits.length);

        // check each split
        BitSet bits = new BitSet(length);
        for (int j = 0; j < splits.length; j++) {
          RecordReader reader =
            format.getRecordReader(fs, splits[j], job, reporter);
          try {
            int count = 0;
            while (reader.next(key, value)) {
              // if (bits.get(key.get())) {
              // LOG.info("splits["+j+"]="+splits[j]+" : " + key.get());
              // LOG.info("@"+reader.getPos());
              // }
              assertFalse("Key in multiple partitions.", bits.get(key.getData()));
              bits.set(key.getData());
              count++;
            }
            //LOG.info("splits["+j+"]="+splits[j]+" count=" + count);
          } finally {
            reader.close();
          }
        }
        assertEquals("Some keys in no partition.", length, bits.cardinality());
      }
View Full Code Here
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
    AutoInputFormat autoInputFormat = new AutoInputFormat();
    for (FileStatus fileStatus : files) {
      FileSplit split = new FileSplit(fileStatus.getPath(), 0,
        fileStatus.getLen() * fileStatus.getBlockSize(),
        (String[]) null);
      RecordReader recReader = null;
      try {
        recReader = autoInputFormat.getRecordReader(split, job, Reporter.NULL);
        Object key = recReader.createKey();
        Object value = recReader.createValue();
        while (recReader.next(key, value)) {
          if (key instanceof Writable) {
            TypedBytesWritableOutput.get(dout).write((Writable) key);
          } else {
            TypedBytesOutput.get(dout).write(key);
          }
          if (value instanceof Writable) {
            TypedBytesWritableOutput.get(dout).write((Writable) value);
          } else {
            TypedBytesOutput.get(dout).write(value);
          }
        }
      } finally {
        if (recReader != null) {
          recReader.close();
        }
      }
    }
    dout.flush();
    return 0;
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
    Reporter reporter) throws IOException {
    FileSplit fileSplit = (FileSplit) split;
    FileSystem fs = FileSystem.get(job);
    FSDataInputStream is = fs.open(fileSplit.getPath());
    byte[] header = new byte[3];
    RecordReader reader = null;
    try {
      is.readFully(header);
    } catch (EOFException eof) {
      reader = textInputFormat.getRecordReader(split, job, reporter);
    } finally {
View Full Code Here
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
    AutoInputFormat autoInputFormat = new AutoInputFormat();
    for (FileStatus fileStatus : files) {
      FileSplit split = new FileSplit(fileStatus.getPath(), 0,
        fileStatus.getLen() * fileStatus.getBlockSize(),
        (String[]) null);
      RecordReader recReader = null;
      try {
        recReader = autoInputFormat.getRecordReader(split, job, Reporter.NULL);
        Object key = recReader.createKey();
        Object value = recReader.createValue();
        while (recReader.next(key, value)) {
          if (key instanceof Writable) {
            TypedBytesWritableOutput.get(dout).write((Writable) key);
          } else {
            TypedBytesOutput.get(dout).write(key);
          }
          if (value instanceof Writable) {
            TypedBytesWritableOutput.get(dout).write((Writable) value);
          } else {
            TypedBytesOutput.get(dout).write(value);
          }
        }
      } finally {
        if (recReader != null) {
          recReader.close();
        }
      }
    }
    dout.flush();
    return 0;
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
    }

    AutoInputFormat format = new AutoInputFormat();
    InputSplit[] splits = format.getSplits(job, SPLITS_COUNT);
    for (InputSplit split : splits) {
      RecordReader reader = format.getRecordReader(split, job, Reporter.NULL);
      Object key = reader.createKey();
      Object value = reader.createValue();
      try {
        while (reader.next(key, value)) {
          if (key instanceof LongWritable) {
            assertEquals("Wrong value class.", Text.class, value.getClass());
            assertTrue("Invalid value", Integer.parseInt(((Text) value)
              .toString()) % 10 == 0);
          } else {
            assertEquals("Wrong key class.", IntWritable.class, key.getClass());
            assertEquals("Wrong value class.", LongWritable.class, value
              .getClass());
            assertTrue("Invalid key.", ((IntWritable) key).get() % 11 == 0);
            assertTrue("Invalid value.", ((LongWritable) value).get() % 12 == 0);
          }
        }
      } finally {
        reader.close();
      }
    }
  }
View Full Code Here
239
240
241
242
243
244
245
246
247
248
249
    pushProjectionsAndFilters(job, inputFormatClass, hsplit.getPath()
      .toString(), hsplit.getPath().toUri().getPath(), nonNative);

    InputFormat inputFormat = getInputFormatFromCache(inputFormatClass, job);
    RecordReader innerReader = null;
    try {
      innerReader = inputFormat.getRecordReader(inputSplit, job, reporter);
    } catch (Exception e) {
      innerReader = HiveIOExceptionHandlerUtil
          .handleRecordReaderCreationException(e, job);
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
    InputSplit targetSplit = ((SymlinkTextInputSplit)split).getTargetSplit();

    // The target data is in TextInputFormat.
    TextInputFormat inputFormat = new TextInputFormat();
    inputFormat.configure(job);
    RecordReader innerReader = null;
    try {
      innerReader = inputFormat.getRecordReader(targetSplit, job,
          reporter);
    } catch (Exception e) {
      innerReader = HiveIOExceptionHandlerUtil
View Full Code Here
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
    InputSplit[] splits = inputFormat.getSplits(jonconf, splitNumber);
    assertEquals("splits length should be " + splitNumber, splits.length, splitNumber);
    int readCount = 0;
    for (int i = 0; i < splits.length; i++) {
      int previousReadCount = readCount;
      RecordReader rr = inputFormat.getRecordReader(splits[i], jonconf, Reporter.NULL);
      Object key = rr.createKey();
      Object value = rr.createValue();
      while (rr.next(key, value)) {
        readCount++;
      }
      rr.close();
      System.out.println("The " + i + "th split read "
          + (readCount - previousReadCount));
    }
    assertEquals("readCount should be equal to writeCount", writeCount,
                 readCount);
View Full Code Here
83
84
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
    }

    AutoInputFormat format = new AutoInputFormat();
    InputSplit[] splits = format.getSplits(job, SPLITS_COUNT);
    for (InputSplit split : splits) {
      RecordReader reader = format.getRecordReader(split, job, Reporter.NULL);
      Object key = reader.createKey();
      Object value = reader.createValue();
      try {
        while (reader.next(key, value)) {
          if (key instanceof LongWritable) {
            assertEquals("Wrong value class.", Text.class, value.getClass());
            assertTrue("Invalid value", Integer.parseInt(((Text) value)
              .toString()) % 10 == 0);
          } else {
            assertEquals("Wrong key class.", IntWritable.class, key.getClass());
            assertEquals("Wrong value class.", LongWritable.class, value
              .getClass());
            assertTrue("Invalid key.", ((IntWritable) key).get() % 11 == 0);
            assertTrue("Invalid value.", ((LongWritable) value).get() % 12 == 0);
          }
        }
      } finally {
        reader.close();
      }
    }
  }
View Full Code Here
TOP

Related Classes of org.apache.hadoop.mapred.RecordReader

  • cascading.flow.tez.stream.element.TezSourceStage
  • org.apache.hadoop.hive.ql.io.HiveInputFormat
  • org.apache.hadoop.hive.ql.io.SymlinkTextInputFormat
  • org.apache.hadoop.hive.ql.io.TestRCFile
  • org.apache.hadoop.record.test.TestWritable
  • org.apache.hadoop.record.TestRecordWritable
  • org.apache.hadoop.streaming.AutoInputFormat
  • org.apache.hadoop.streaming.DumpTypedBytes
  • org.apache.hadoop.streaming.TestAutoInputFormat
  • org.apache.tez.mapreduce.processor.map.MapProcessor
    • 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.