Package org.apache.hadoop.mapred

Examples of org.apache.hadoop.mapred.TextInputFormat$LineRecordReader$TextStuffer

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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
      Collections.sort(columnIds);
      numCols = columnIds.size();
    }
    targetRecordCount = context.getConfig().getInt(ExecConstants.TEXT_LINE_READER_BATCH_SIZE);

    TextInputFormat inputFormat = new TextInputFormat();
    JobConf job = new JobConf();
    job.setInt("io.file.buffer.size", context.getConfig().getInt(ExecConstants.TEXT_LINE_READER_BUFFER_SIZE));
    job.setInputFormat(inputFormat.getClass());
    try {
      reader = inputFormat.getRecordReader(split, job, Reporter.NULL);
      key = reader.createKey();
      value = reader.createValue();
    } catch (IOException e) {
      throw new RuntimeException(e);
    }
View Full Code Here
39
40
41
42
43
44
45
46
public class KeyValuePreservingTextInputFormat extends FileInputFormat<Text, Text> {

  private TextInputFormat delegate;

  public void configure(JobConf conf) {
    delegate = new TextInputFormat();
    delegate.configure(conf);
  }
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
    int numSubTasks   = (args.length > 0 ? Integer.parseInt(args[0]) : 1);
    String dataInput = (args.length > 1 ? args[1] : "");
    String output    = (args.length > 2 ? args[2] : "");
   
   
    HadoopDataSource source = new HadoopDataSource(new TextInputFormat(), new JobConf(), "Input Lines");
    TextInputFormat.addInputPath(source.getJobConf(), new Path(dataInput));
   
    // Example with Wrapper Converter
    HadoopDataSource<LongWritable,Text> sourceHadoopType = new HadoopDataSource<LongWritable, Text>(
        new TextInputFormat(), new JobConf(), "Input Lines", new WritableWrapperConverter<LongWritable, Text>());
    TextInputFormat.addInputPath(source.getJobConf(), new Path(dataInput));
   
    MapOperator mapper = MapOperator.builder(new TokenizeLine())
      .input(source)
      .name("Tokenize Lines")
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    final String outputPath = args[1];
   
    final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
   
    // Set up the Hadoop Input Format
    HadoopInputFormat<LongWritable, Text> hadoopInputFormat = new HadoopInputFormat<LongWritable, Text>(new TextInputFormat(), LongWritable.class, Text.class, new JobConf());
    TextInputFormat.addInputPath(hadoopInputFormat.getJobConf(), new Path(inputPath));
   
    // Create a Flink job with it
    DataSet<Tuple2<LongWritable, Text>> text = env.createInput(hadoopInputFormat);
   
View Full Code Here
125
126
127
128
129
130
131
132
133
134
135
    int numSubTasks   = (args.length > 0 ? Integer.parseInt(args[0]) : 1);
    String dataInput = (args.length > 1 ? args[1] : "");
    String output    = (args.length > 2 ? args[2] : "");

    HadoopDataSource<LongWritable, Text> source = new HadoopDataSource<LongWritable, Text>(
        new TextInputFormat(), new JobConf(), "Input Lines");
    TextInputFormat.addInputPath(source.getJobConf(), new Path(dataInput));


    MapOperator mapper = MapOperator.builder(new TokenizeLine())
        .input(source)
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
    // ---- 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
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
    // ---- 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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
    // ---- 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
TOP

Related Classes of org.apache.hadoop.mapred.TextInputFormat$LineRecordReader$TextStuffer

  • 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.