Package org.apache.hadoop.mapred.lib

Examples of org.apache.hadoop.mapred.lib.CombineTextInputFormat

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
110
111
112
113
114
    final int numFiles = 10;

    createFiles(length, numFiles, random);

    // create a combined split for the files
    CombineTextInputFormat format = new CombineTextInputFormat();
    LongWritable key = new LongWritable();
    Text value = new Text();
    for (int i = 0; i < 3; i++) {
      int numSplits = random.nextInt(length/20)+1;
      LOG.info("splitting: requesting = " + numSplits);
      InputSplit[] splits = format.getSplits(job, numSplits);
      LOG.info("splitting: got =        " + splits.length);

      // we should have a single split as the length is comfortably smaller than
      // the block size
      assertEquals("We got more than one splits!", 1, splits.length);
      InputSplit split = splits[0];
      assertEquals("It should be CombineFileSplit",
        CombineFileSplit.class, split.getClass());

      // check the split
      BitSet bits = new BitSet(length);
      LOG.debug("split= " + split);
      RecordReader<LongWritable, Text> reader =
        format.getRecordReader(split, job, voidReporter);
      try {
        int count = 0;
        while (reader.next(key, value)) {
          int v = Integer.parseInt(value.toString());
          LOG.debug("read " + v);
View Full Code Here
216
217
218
219
220
221
222
223
224
225
226
227
    writeFile(localFs, new Path(workDir, "part1.txt.gz"), gzip,
              "the quick\nbrown\nfox jumped\nover\n the lazy\n dog\n");
    writeFile(localFs, new Path(workDir, "part2.txt.gz"), gzip,
              "this is a test\nof gzip\n");
    FileInputFormat.setInputPaths(job, workDir);
    CombineTextInputFormat format = new CombineTextInputFormat();
    InputSplit[] splits = format.getSplits(job, 100);
    assertEquals("compressed splits == 1", 1, splits.length);
    List<Text> results = readSplit(format, splits[0], job);
    assertEquals("splits[0] length", 8, results.size());

    final String[] firstList =
View Full Code Here
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
110
111
112
113
114
    final int numFiles = 10;

    createFiles(length, numFiles, random);

    // create a combined split for the files
    CombineTextInputFormat format = new CombineTextInputFormat();
    LongWritable key = new LongWritable();
    Text value = new Text();
    for (int i = 0; i < 3; i++) {
      int numSplits = random.nextInt(length/20)+1;
      LOG.info("splitting: requesting = " + numSplits);
      InputSplit[] splits = format.getSplits(job, numSplits);
      LOG.info("splitting: got =        " + splits.length);

      // we should have a single split as the length is comfortably smaller than
      // the block size
      assertEquals("We got more than one splits!", 1, splits.length);
      InputSplit split = splits[0];
      assertEquals("It should be CombineFileSplit",
        CombineFileSplit.class, split.getClass());

      // check the split
      BitSet bits = new BitSet(length);
      LOG.debug("split= " + split);
      RecordReader<LongWritable, Text> reader =
        format.getRecordReader(split, job, voidReporter);
      try {
        int count = 0;
        while (reader.next(key, value)) {
          int v = Integer.parseInt(value.toString());
          LOG.debug("read " + v);
View Full Code Here
216
217
218
219
220
221
222
223
224
225
226
227
    writeFile(localFs, new Path(workDir, "part1.txt.gz"), gzip,
              "the quick\nbrown\nfox jumped\nover\n the lazy\n dog\n");
    writeFile(localFs, new Path(workDir, "part2.txt.gz"), gzip,
              "this is a test\nof gzip\n");
    FileInputFormat.setInputPaths(job, workDir);
    CombineTextInputFormat format = new CombineTextInputFormat();
    InputSplit[] splits = format.getSplits(job, 100);
    assertEquals("compressed splits == 1", 1, splits.length);
    List<Text> results = readSplit(format, splits[0], job);
    assertEquals("splits[0] length", 8, results.size());

    final String[] firstList =
View Full Code Here
TOP

Related Classes of org.apache.hadoop.mapred.lib.CombineTextInputFormat

  • org.apache.hadoop.mapred.TestCombineTextInputFormat
  • org.apache.hadoop.mapred.TextInputFormat
    • 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.