Examples with HadoopOutputFormat org.apache.flink.api.java.hadoop.mapred.HadoopOutputFormat used on opensource projects

Example 1 with HadoopOutputFormat

use of org.apache.flink.api.java.hadoop.mapred.HadoopOutputFormat in project flink by apache.

the class WordCountMapredITCase method internalRun.

private void internalRun(boolean isTestDeprecatedAPI) throws Exception {
    final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    DataSet<Tuple2<LongWritable, Text>> input;
    if (isTestDeprecatedAPI) {
        input = env.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()).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
    HadoopOutputFormat<Text, LongWritable> hadoopOutputFormat = new HadoopOutputFormat<Text, LongWritable>(new TextOutputFormat<Text, LongWritable>(), new JobConf());
    hadoopOutputFormat.getJobConf().set("mapred.textoutputformat.separator", " ");
    TextOutputFormat.setOutputPath(hadoopOutputFormat.getJobConf(), new Path(resultPath));
    // Output & Execute
    words.output(hadoopOutputFormat);
    env.execute("Hadoop Compat WordCount");
}

Example 2 with HadoopOutputFormat

use of org.apache.flink.api.java.hadoop.mapred.HadoopOutputFormat in project flink by apache.

the class HadoopMapredCompatWordCount method main.

public static void main(String[] args) throws Exception {
    if (args.length < 2) {
        System.err.println("Usage: WordCount <input path> <result path>");
        return;
    }
    final String inputPath = args[0];
    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);
    DataSet<Tuple2<Text, LongWritable>> words = text.flatMap(new HadoopMapFunction<LongWritable, Text, Text, LongWritable>(new Tokenizer())).groupBy(0).reduceGroup(new HadoopReduceCombineFunction<Text, LongWritable, Text, LongWritable>(new Counter(), new Counter()));
    // Set up Hadoop Output Format
    HadoopOutputFormat<Text, LongWritable> hadoopOutputFormat = new HadoopOutputFormat<Text, LongWritable>(new TextOutputFormat<Text, LongWritable>(), new JobConf());
    hadoopOutputFormat.getJobConf().set("mapred.textoutputformat.separator", " ");
    TextOutputFormat.setOutputPath(hadoopOutputFormat.getJobConf(), new Path(outputPath));
    // Output & Execute
    words.output(hadoopOutputFormat).setParallelism(1);
    env.execute("Hadoop Compat WordCount");
}

Example 3 with HadoopOutputFormat

use of org.apache.flink.api.java.hadoop.mapred.HadoopOutputFormat in project flink by apache.

the class WordCountMapredITCase method internalRun.

private void internalRun() throws Exception {
    final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    DataSet<Tuple2<LongWritable, Text>> input;
    input = env.createInput(HadoopInputs.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()).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
    HadoopOutputFormat<Text, LongWritable> hadoopOutputFormat = new HadoopOutputFormat<Text, LongWritable>(new TextOutputFormat<Text, LongWritable>(), new JobConf());
    hadoopOutputFormat.getJobConf().set("mapred.textoutputformat.separator", " ");
    TextOutputFormat.setOutputPath(hadoopOutputFormat.getJobConf(), new Path(resultPath));
    // Output & Execute
    words.output(hadoopOutputFormat);
    env.execute("Hadoop Compat WordCount");
}