Example usage for org.apache.hadoop.mapreduce.lib.output TextOutputFormat TextOutputFormat

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce.lib.output TextOutputFormat TextOutputFormat.

Prototype

TextOutputFormat

Source Link

Usage

From source file:org.apache.flink.test.hadoopcompatibility.mapreduce.WordCountMapreduceITCase.java

License:Apache License

private void internalRun(boolean isTestDeprecatedAPI) throws Exception {
    final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

    DataSet<Tuple2<LongWritable, Text>> input;
    if (isTestDeprecatedAPI) {
        input = env.createInput(// w w  w.  j a  v  a  2 s.co  m
                HadoopInputs.readHadoopFile(new TextInputFormat(), LongWritable.class, Text.class, textPath));
    } else {
        input = env
                .createInput(readHadoopFile(new TextInputFormat(), LongWritable.class, Text.class, textPath));
    }

    DataSet<String> text = input.map(new MapFunction<Tuple2<LongWritable, Text>, String>() {
        @Override
        public String map(Tuple2<LongWritable, Text> value) throws Exception {
            return value.f1.toString();
        }
    });

    DataSet<Tuple2<String, Integer>> counts =
            // split up the lines in pairs (2-tuples) containing: (word,1)
            text.flatMap(new Tokenizer())
                    // group by the tuple field "0" and sum up tuple field "1"
                    .groupBy(0).sum(1);

    DataSet<Tuple2<Text, LongWritable>> words = counts
            .map(new MapFunction<Tuple2<String, Integer>, Tuple2<Text, LongWritable>>() {

                @Override
                public Tuple2<Text, LongWritable> map(Tuple2<String, Integer> value) throws Exception {
                    return new Tuple2<Text, LongWritable>(new Text(value.f0), new LongWritable(value.f1));
                }
            });

    // Set up Hadoop Output Format
    Job job = Job.getInstance();
    HadoopOutputFormat<Text, LongWritable> hadoopOutputFormat = new HadoopOutputFormat<Text, LongWritable>(
            new TextOutputFormat<Text, LongWritable>(), job);
    job.getConfiguration().set("mapred.textoutputformat.separator", " ");
    TextOutputFormat.setOutputPath(job, new Path(resultPath));

    // Output & Execute
    words.output(hadoopOutputFormat);
    env.execute("Hadoop Compat WordCount");
}

---

From source file:org.apache.pig.piggybank.storage.FixedWidthStorer.java

License:Apache License

@Override
public OutputFormat getOutputFormat() throws IOException {
    // Key is unused, Text is where the data is stored in
    return new TextOutputFormat<LongWritable, Text>();
}

---

From source file:pignlproc.storage.AbstractNTriplesStorer.java

License:Apache License

@SuppressWarnings("rawtypes")
@Override/*from  w ww  . j  a va 2 s.  c om*/
public OutputFormat getOutputFormat() {
    return new TextOutputFormat<WritableComparable, Text>();
}

---

• «
• 1
• 2
• »