Package org.apache.hcatalog.mapreduce.MultiOutputFormat

Examples of org.apache.hcatalog.mapreduce.MultiOutputFormat.JobConfigurer


    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(MultiOutputFormat.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);

    configurer.addOutputFormat("out1", TextOutputFormat.class, IntWritable.class, Text.class);
    configurer.addOutputFormat("out2", SequenceFileOutputFormat.class, Text.class,
      IntWritable.class);
    configurer.addOutputFormat("out3", NullOutputFormat.class, Text.class,
      IntWritable.class);
    Path outDir = new Path(workDir.getPath(), job.getJobName());
    FileOutputFormat.setOutputPath(configurer.getJob("out1"), new Path(outDir, "out1"));
    FileOutputFormat.setOutputPath(configurer.getJob("out2"), new Path(outDir, "out2"));

    configurer.configure();

    String fileContent = "Hello World Hello World World";
    String inputFile = createInputFile(fileContent);
    FileInputFormat.setInputPaths(job, new Path(inputFile));
View Full Code Here


    job.setMapperClass(MyMapper.class);
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(MultiOutputFormat.class);
    job.setNumReduceTasks(0);

    JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);

    for (int i = 0; i < tableNames.length; i++) {
      configurer.addOutputFormat(tableNames[i], HCatOutputFormat.class, BytesWritable.class,
        HCatRecord.class);
      HCatOutputFormat.setOutput(configurer.getJob(tableNames[i]), infoList.get(i));
      HCatOutputFormat.setSchema(configurer.getJob(tableNames[i]),
        schemaMap.get(tableNames[i]));
    }
    configurer.configure();

    Path filePath = createInputFile();
    FileInputFormat.addInputPath(job, filePath);
    Assert.assertTrue(job.waitForCompletion(true));
View Full Code Here

    job.setJarByClass(this.getClass());
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(MultiOutputFormat.class);
    job.setNumReduceTasks(0);

    JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);
    configurer.addOutputFormat("out1", TextOutputFormat.class, IntWritable.class, Text.class);
    configurer.addOutputFormat("out2", SequenceFileOutputFormat.class, Text.class,
      IntWritable.class);
    Path outDir = new Path(workDir.getPath(), job.getJobName());
    FileOutputFormat.setOutputPath(configurer.getJob("out1"), new Path(outDir, "out1"));
    FileOutputFormat.setOutputPath(configurer.getJob("out2"), new Path(outDir, "out2"));

    String fileContent = "Hello World";
    String inputFile = createInputFile(fileContent);
    FileInputFormat.setInputPaths(job, new Path(inputFile));

    //Test for merging of configs
    DistributedCache.addFileToClassPath(new Path(inputFile), job.getConfiguration(), fs);
    String dummyFile = createInputFile("dummy file");
    DistributedCache.addFileToClassPath(new Path(dummyFile), configurer.getJob("out1")
      .getConfiguration(), fs);
    // duplicate of the value. Merging should remove duplicates
    DistributedCache.addFileToClassPath(new Path(inputFile), configurer.getJob("out2")
      .getConfiguration(), fs);

    configurer.configure();

    // Verify if the configs are merged
    Path[] fileClassPaths = DistributedCache.getFileClassPaths(job.getConfiguration());
    List<Path> fileClassPathsList = Arrays.asList(fileClassPaths);
    Assert.assertTrue(fileClassPathsList.contains(new Path(inputFile)));
View Full Code Here

        job.setJarByClass(this.getClass());
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(MultiOutputFormat.class);
        job.setNumReduceTasks(0);

        JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);
        configurer.addOutputFormat("out1", TextOutputFormat.class, IntWritable.class, Text.class);
        configurer.addOutputFormat("out2", SequenceFileOutputFormat.class, Text.class,
            IntWritable.class);
        Path outDir = new Path(workDir.getPath(), job.getJobName());
        FileOutputFormat.setOutputPath(configurer.getJob("out1"), new Path(outDir, "out1"));
        FileOutputFormat.setOutputPath(configurer.getJob("out2"), new Path(outDir, "out2"));

        String fileContent = "Hello World";
        String inputFile = createInputFile(fileContent);
        FileInputFormat.setInputPaths(job, new Path(inputFile));

        //Test for merging of configs
        DistributedCache.addFileToClassPath(new Path(inputFile), job.getConfiguration(), fs);
        String dummyFile = createInputFile("dummy file");
        DistributedCache.addFileToClassPath(new Path(dummyFile), configurer.getJob("out1")
            .getConfiguration(), fs);
        // duplicate of the value. Merging should remove duplicates
        DistributedCache.addFileToClassPath(new Path(inputFile), configurer.getJob("out2")
            .getConfiguration(), fs);

        configurer.configure();

        // Verify if the configs are merged
        Path[] fileClassPaths = DistributedCache.getFileClassPaths(job.getConfiguration());
        Assert.assertArrayEquals(new Path[]{new Path(inputFile), new Path(dummyFile)},
            fileClassPaths);
View Full Code Here

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(MultiOutputFormat.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);

        configurer.addOutputFormat("out1", TextOutputFormat.class, IntWritable.class, Text.class);
        configurer.addOutputFormat("out2", SequenceFileOutputFormat.class, Text.class,
            IntWritable.class);
        configurer.addOutputFormat("out3", NullOutputFormat.class, Text.class,
            IntWritable.class);
        Path outDir = new Path(workDir.getPath(), job.getJobName());
        FileOutputFormat.setOutputPath(configurer.getJob("out1"), new Path(outDir, "out1"));
        FileOutputFormat.setOutputPath(configurer.getJob("out2"), new Path(outDir, "out2"));

        configurer.configure();

        String fileContent = "Hello World Hello World World";
        String inputFile = createInputFile(fileContent);
        FileInputFormat.setInputPaths(job, new Path(inputFile));
View Full Code Here

        job.setMapperClass(MyMapper.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(MultiOutputFormat.class);
        job.setNumReduceTasks(0);

        JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);

        for (int i = 0; i < tableNames.length; i++) {
            configurer.addOutputFormat(tableNames[i], HCatOutputFormat.class, BytesWritable.class,
                HCatRecord.class);
            HCatOutputFormat.setOutput(configurer.getJob(tableNames[i]), infoList.get(i));
            HCatOutputFormat.setSchema(configurer.getJob(tableNames[i]),
                schemaMap.get(tableNames[i]));
        }
        configurer.configure();

        Path filePath = createInputFile();
        FileInputFormat.addInputPath(job, filePath);
        Assert.assertTrue(job.waitForCompletion(true));
View Full Code Here

    job.setJarByClass(this.getClass());
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(MultiOutputFormat.class);
    job.setNumReduceTasks(0);

    JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);
    configurer.addOutputFormat("out1", TextOutputFormat.class, IntWritable.class, Text.class);
    configurer.addOutputFormat("out2", SequenceFileOutputFormat.class, Text.class,
      IntWritable.class);
    Path outDir = new Path(workDir.getPath(), job.getJobName());
    FileOutputFormat.setOutputPath(configurer.getJob("out1"), new Path(outDir, "out1"));
    FileOutputFormat.setOutputPath(configurer.getJob("out2"), new Path(outDir, "out2"));

    String fileContent = "Hello World";
    String inputFile = createInputFile(fileContent);
    FileInputFormat.setInputPaths(job, new Path(inputFile));

    //Test for merging of configs
    DistributedCache.addFileToClassPath(new Path(inputFile), job.getConfiguration(), fs);
    String dummyFile = createInputFile("dummy file");
    DistributedCache.addFileToClassPath(new Path(dummyFile), configurer.getJob("out1")
      .getConfiguration(), fs);
    // duplicate of the value. Merging should remove duplicates
    DistributedCache.addFileToClassPath(new Path(inputFile), configurer.getJob("out2")
      .getConfiguration(), fs);

    configurer.configure();

    // Verify if the configs are merged
    Path[] fileClassPaths = DistributedCache.getFileClassPaths(job.getConfiguration());
    List<Path> fileClassPathsList = Arrays.asList(fileClassPaths);
    Assert.assertTrue(fileClassPathsList.contains(new Path(inputFile)));
View Full Code Here

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(MultiOutputFormat.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);

    configurer.addOutputFormat("out1", TextOutputFormat.class, IntWritable.class, Text.class);
    configurer.addOutputFormat("out2", SequenceFileOutputFormat.class, Text.class,
      IntWritable.class);
    configurer.addOutputFormat("out3", NullOutputFormat.class, Text.class,
      IntWritable.class);
    Path outDir = new Path(workDir.getPath(), job.getJobName());
    FileOutputFormat.setOutputPath(configurer.getJob("out1"), new Path(outDir, "out1"));
    FileOutputFormat.setOutputPath(configurer.getJob("out2"), new Path(outDir, "out2"));

    configurer.configure();

    String fileContent = "Hello World Hello World World";
    String inputFile = createInputFile(fileContent);
    FileInputFormat.setInputPaths(job, new Path(inputFile));
View Full Code Here

    job.setMapperClass(MyMapper.class);
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(MultiOutputFormat.class);
    job.setNumReduceTasks(0);

    JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);

    for (int i = 0; i < tableNames.length; i++) {
      configurer.addOutputFormat(tableNames[i], HCatOutputFormat.class, BytesWritable.class,
        HCatRecord.class);
      HCatOutputFormat.setOutput(configurer.getJob(tableNames[i]), infoList.get(i));
      HCatOutputFormat.setSchema(configurer.getJob(tableNames[i]),
        schemaMap.get(tableNames[i]));
    }
    configurer.configure();

    Path filePath = createInputFile();
    FileInputFormat.addInputPath(job, filePath);
    Assert.assertTrue(job.waitForCompletion(true));
View Full Code Here

        job.setJarByClass(this.getClass());
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(MultiOutputFormat.class);
        job.setNumReduceTasks(0);

        JobConfigurer configurer = MultiOutputFormat.createConfigurer(job);
        configurer.addOutputFormat("out1", TextOutputFormat.class, IntWritable.class, Text.class);
        configurer.addOutputFormat("out2", SequenceFileOutputFormat.class, Text.class,
            IntWritable.class);
        Path outDir = new Path(workDir.getPath(), job.getJobName());
        FileOutputFormat.setOutputPath(configurer.getJob("out1"), new Path(outDir, "out1"));
        FileOutputFormat.setOutputPath(configurer.getJob("out2"), new Path(outDir, "out2"));

        String fileContent = "Hello World";
        String inputFile = createInputFile(fileContent);
        FileInputFormat.setInputPaths(job, new Path(inputFile));

        //Test for merging of configs
        DistributedCache.addFileToClassPath(new Path(inputFile), job.getConfiguration(), fs);
        String dummyFile = createInputFile("dummy file");
        DistributedCache.addFileToClassPath(new Path(dummyFile), configurer.getJob("out1")
            .getConfiguration(), fs);
        // duplicate of the value. Merging should remove duplicates
        DistributedCache.addFileToClassPath(new Path(inputFile), configurer.getJob("out2")
            .getConfiguration(), fs);

        configurer.configure();

        // Verify if the configs are merged
        Path[] fileClassPaths = DistributedCache.getFileClassPaths(job.getConfiguration());
        List<Path> fileClassPathsList = Arrays.asList(fileClassPaths);
        Assert.assertTrue(fileClassPathsList.contains(new Path(inputFile)));
View Full Code Here

TOP

Related Classes of org.apache.hcatalog.mapreduce.MultiOutputFormat.JobConfigurer

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.