Package org.apache.hadoop.mapred

Examples of org.apache.hadoop.mapred.TextInputFormat

128
129
130
131
132
133
134
135
136
137
138
    this.split = new FileSplit( new Path( file ), offset, length, defaultConf);

    this.hasMore = true;
    this.jobConf = defaultConf;
    //this.split = split;
    this.input_format = new TextInputFormat();

    try {
      this.reader = input_format.getRecordReader(this.split, this.jobConf, voidReporter);
    } catch (IOException e) {
      // TODO Auto-generated catch block
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
    // ---- set where we'll read the input files from -------------
    FileInputFormat.setInputPaths(job, input_path);

    // try splitting the file in a variety of sizes
    TextInputFormat format = new TextInputFormat();
    format.configure(job);

    int numSplits = 1;

    InputSplit[] splits = null;

    try {
      splits = format.getSplits(job, numSplits);
    } catch (IOException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
    final int numFiles = 10;

    createFiles(length, numFiles, random);

    // create a combined split for the files
    TextInputFormat wrappedFormat = new TextInputFormat();
    wrappedFormat.configure(job);
    TezGroupedSplitsInputFormat<LongWritable , Text> format =
        new TezGroupedSplitsInputFormat<LongWritable, Text>();
    format.setConf(job);
    format.setDesiredNumberOfSplits(1);
    format.setInputFormat(wrappedFormat);
View Full Code Here
234
235
236
237
238
239
240
241
242
243
244
245
    writeFile(localFs, new Path(workDir, "part2.txt.gz"), gzip,
              "is\ngzip\n");
    writeFile(localFs, new Path(workDir, "part3.txt.gz"), gzip,
        "one\nmore\nsplit\n");
    FileInputFormat.setInputPaths(job, workDir);
    TextInputFormat wrappedFormat = new TextInputFormat();
    wrappedFormat.configure(job);
    TezGroupedSplitsInputFormat<LongWritable , Text> format =
        new TezGroupedSplitsInputFormat<LongWritable, Text>();
    format.setConf(job);
    format.setInputFormat(wrappedFormat);
   
View Full Code Here
147
148
149
150
151
152
153
  TextInputFormat format;
  JobConf job;

  public Base64TextInputFormat() {
    format = new TextInputFormat();
  }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
  public RecordReader<LongWritable, Text> getRecordReader(
      InputSplit split, JobConf job, Reporter reporter) throws IOException {
    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
          .handleRecordReaderCreationException(e, job);
    }
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
    if (targetPaths.size() == 0) {
      return new InputSplit[0];
    }

    // The input should be in TextInputFormat.
    TextInputFormat inputFormat = new TextInputFormat();
    JobConf newjob = new JobConf(job);
    newjob.setInputFormat(TextInputFormat.class);
    inputFormat.configure(newjob);

    List<InputSplit> result = new ArrayList<InputSplit>();

    // ceil(numSplits / numPaths), so we can get at least numSplits splits.
    int numPaths = targetPaths.size();
    int numSubSplits = (numSplits + numPaths - 1) / numPaths;

    // For each path, do getSplits().
    for (int i = 0; i < numPaths; ++i) {
      Path targetPath = targetPaths.get(i);
      Path symlinkPath = symlinkPaths.get(i);

      FileInputFormat.setInputPaths(newjob, targetPath);

      InputSplit[] iss = inputFormat.getSplits(newjob, numSubSplits);
      for (InputSplit is : iss) {
        result.add(new SymlinkTextInputSplit(symlinkPath, (FileSplit)is));
      }
    }
    return result.toArray(new InputSplit[result.size()]);
View Full Code Here
95
96
97
98
99
100
101
102
103
  public RecordReader<LongWritable, Text> getRecordReader(
      InputSplit split, JobConf job, Reporter reporter) throws IOException {
    InputSplit targetSplit = ((SymlinkTextInputSplit)split).getTargetSplit();

    // The target data is in TextInputFormat.
    TextInputFormat inputFormat = new TextInputFormat();
    inputFormat.configure(job);
    return inputFormat.getRecordReader(targetSplit, job, reporter);
  }
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
    if (targetPaths.size() == 0) {
      return new InputSplit[0];
    }

    // The input should be in TextInputFormat.
    TextInputFormat inputFormat = new TextInputFormat();
    JobConf newjob = new JobConf(job);
    newjob.setInputFormat(TextInputFormat.class);
    inputFormat.configure(newjob);

    List<InputSplit> result = new ArrayList<InputSplit>();

    // ceil(numSplits / numPaths), so we can get at least numSplits splits.
    int numPaths = targetPaths.size();
    int numSubSplits = (numSplits + numPaths - 1) / numPaths;

    // For each path, do getSplits().
    for (int i = 0; i < numPaths; ++i) {
      Path targetPath = targetPaths.get(i);
      Path symlinkPath = symlinkPaths.get(i);

      FileInputFormat.setInputPaths(newjob, targetPath);

      InputSplit[] iss = inputFormat.getSplits(newjob, numSubSplits);
      for (InputSplit is : iss) {
        result.add(new SymlinkTextInputSplit(symlinkPath, (FileSplit)is));
      }
    }
    return result.toArray(new InputSplit[result.size()]);
View Full Code Here
47
48
49
50
51
52
53
  private static class TextRecordReaderWrapper
    extends org.apache.hadoop.mapred.lib.CombineFileRecordReaderWrapper<LongWritable,Text> {
    // this constructor signature is required by CombineFileRecordReader
    public TextRecordReaderWrapper(CombineFileSplit split, Configuration conf,
      Reporter reporter, Integer idx) throws IOException {
      super(new TextInputFormat(), split, conf, reporter, idx);
    }
View Full Code Here
TOP

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

  • com.cloudera.iterativereduce.io.TextRecordParser
  • com.cloudera.iterativereduce.irunit.IRUnitDriver
  • com.m6d.filecrush.crush.KeyValuePreservingTextInputFormat
  • eu.stratosphere.hadoopcompatibility.example.WordCount
  • eu.stratosphere.hadoopcompatibility.example.WordCountWithHadoopOutputFormat
  • org.apache.drill.exec.store.text.DrillTextRecordReader
  • org.apache.flink.hadoopcompatibility.mapred.example.HadoopMapredCompatWordCount
  • org.apache.flink.hadoopcompatibility.mapred.record.example.WordCount
  • org.apache.flink.hadoopcompatibility.mapred.record.example.WordCountWithOutputFormat
  • org.apache.hadoop.fs.FSDataInputStream
    • 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.