Example usage for org.apache.hadoop.mapreduce Job setInputFormatClass

List of usage examples for org.apache.hadoop.mapreduce Job setInputFormatClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapreduce.*
  5. Job
  6. setInputFormatClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce Job setInputFormatClass.

Prototype

public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException

Source Link

Document

Set the InputFormat for the job.

Usage

From source file:com.fanlehai.hadoop.serialize.avro.MapReduceAvroWordCount.java

License:Apache License

public int run(String[] args) throws Exception {

    if (args.length != 2) {
        printUsage();//from  w w w.  j  a  v  a 2s  .c  o  m
    }

    FileSystem.get(new Configuration()).delete(new Path(args[1]), true);
    Job job = Job.getInstance(super.getConf(), "AvroWordCount");

    job.setJarByClass(MapReduceAvroWordCount.class);
    job.setJobName("AvroWordCount");

    // We call setOutputSchema first so we can override the configuration
    // parameters it sets
    AvroJob.setOutputKeySchema(job, Pair.getPairSchema(Schema.create(Type.STRING), Schema.create(Type.INT)));
    job.setOutputValueClass(NullWritable.class);

    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

    job.setInputFormatClass(TextInputFormat.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setSortComparatorClass(Text.Comparator.class);

    FileInputFormat.setInputPaths(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    return job.waitForCompletion(true) ? 1 : 0;
}

From source file:com.fanlehai.hadoop.serialize.avro.MapReduceColorCount.java

License:Apache License

public int run(String[] args) throws Exception {

    if (args.length != 2) {
        printUsage();/*from  w  w w.j  a  v  a 2 s  . c  om*/
    }

    FileSystem.get(new Configuration()).delete(new Path(args[1]), true);
    Job job = Job.getInstance(super.getConf(), "MapReduceAvroWordCount");

    job.setJarByClass(MapReduceColorCount.class);
    job.setJobName("Color Count");

    FileInputFormat.setInputPaths(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setInputFormatClass(AvroKeyInputFormat.class);
    job.setMapperClass(ColorCountMapper.class);
    AvroJob.setInputKeySchema(job, User.getClassSchema());
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputFormatClass(AvroKeyValueOutputFormat.class);
    job.setReducerClass(ColorCountReducer.class);
    AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING));
    AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT));

    return job.waitForCompletion(true) ? 1 : 0;
}

From source file:com.fanlehai.hadoop.serialize.json.multiline.ExampleJob.java

License:Apache License

/**
 * The MapReduce driver - setup and launch the job.
 *
 * @param args//ww w  .j a  v  a2s  .  c  o  m
 *            the command-line arguments
 * @return the process exit code
 * @throws Exception
 *             if something goes wrong
 */
@Override
public int run(String[] args) throws Exception {

    if (args.length != 2) {
        System.err.println("Usage: ExampleJob <in dir> <out dir>");
        ToolRunner.printGenericCommandUsage(System.err);
        System.exit(2);
    }

    String input = args[0];
    String output = args[1];

    Configuration conf = super.getConf();

    writeInput(conf, new Path(input));

    Job job = Job.getInstance(getConf(), "ExampleJob");
    job.setJarByClass(ExampleJob.class);
    job.setMapperClass(Map.class);

    job.setNumReduceTasks(0);

    Path outputPath = new Path(output);

    FileInputFormat.setInputPaths(job, input);
    FileOutputFormat.setOutputPath(job, outputPath);

    // use the JSON input format
    job.setInputFormatClass(MultiLineJsonInputFormat.class);

    // specify the JSON attribute name which is used to determine which
    // JSON elements are supplied to the mapper
    MultiLineJsonInputFormat.setInputJsonMember(job, "colorName");

    if (job.waitForCompletion(true)) {
        return 0;
    }
    return 1;
}

From source file:com.flipkart.fdp.migration.distcp.core.MirrorDistCPDriver.java

License:Apache License

private Job createJob(Configuration configuration) throws Exception {

    System.out.println("Initializing BlueShift v 2.0...");
    System.out.println("Configuration: " + dcmConfig.toString());

    Job job = Job.getInstance(configuration, "BlueShift v 2.0 - " + dcmConfig.getBatchName());

    job.setJarByClass(MirrorDistCPDriver.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    job.setMapperClass(MirrorMapper.class);
    job.setReducerClass(MirrorReducer.class);

    job.setInputFormatClass(MirrorFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    FileOutputFormat.setOutputPath(job, stateManager.getReportPath());

    job.setNumReduceTasks(configuration.getInt("mapreduce.reduce.tasks", 1));

    System.out.println("Job Initialization Complete, The status of the Mirror job will be written to: "
            + stateManager.getReportPath());
    return job;/*from  w ww. j a  va  2 s  .  c o  m*/
}

From source file:com.github.libsml.commons.util.HadoopUtils.java

License:Apache License

/**
 * Create a map-only Hadoop Job out of the passed in parameters.  Does not set the
 * Job name./*from w  w  w .j ava 2 s.c  om*/
 *
 * @see #getCustomJobName(String, JobContext, Class, Class)
 */
public static Job prepareJob(Path inputPath, Path outputPath, Class<? extends InputFormat> inputFormat,
        Class<? extends Mapper> mapper, Class<? extends Writable> mapperKey,
        Class<? extends Writable> mapperValue, Class<? extends OutputFormat> outputFormat, Configuration conf)
        throws IOException {

    //    Job job = new Job(new Configuration(conf));
    Job job = Job.getInstance(conf);
    Configuration jobConf = job.getConfiguration();

    if (mapper.equals(Mapper.class)) {
        throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer");
    }
    job.setJarByClass(mapper);

    job.setInputFormatClass(inputFormat);
    jobConf.set("mapred.input.dir", inputPath.toString());

    job.setMapperClass(mapper);
    job.setMapOutputKeyClass(mapperKey);
    job.setMapOutputValueClass(mapperValue);
    job.setOutputKeyClass(mapperKey);
    job.setOutputValueClass(mapperValue);
    jobConf.setBoolean("mapred.compress.map.output", true);
    job.setNumReduceTasks(0);

    job.setOutputFormatClass(outputFormat);
    jobConf.set("mapred.output.dir", outputPath.toString());

    return job;
}

From source file:com.github.libsml.commons.util.HadoopUtils.java

License:Apache License

/**
 *
 * @param inputPaths//w  w  w . j  a v  a  2  s.  co m
 * @param outputPath
 * @param inputFormat
 * @param inputKey
 * @param inputValue
 * @param mapper
 * @param mapperKey
 * @param mapperValue
 * @param combiner
 * @param reducer
 * @param outputKey
 * @param outputValue
 * @param outputFormat
 * @param conf
 * @param overwrite
 * @param isCompress
 * @return
 * @throws IOException
 */
public static Job prepareAvroJob(String inputPaths, String outputPath, Class<? extends InputFormat> inputFormat,
        Object inputKey, Object inputValue, Class<? extends Mapper> mapper, Object mapperKey,
        Object mapperValue, Class<? extends Reducer> combiner, Class<? extends Reducer> reducer,
        Object outputKey, Object outputValue, Class<? extends OutputFormat> outputFormat, Configuration conf,
        boolean overwrite, boolean isCompress) throws IOException {

    Job job = Job.getInstance(conf);
    Configuration jobConf = job.getConfiguration();
    if (inputKey instanceof Schema) {

        if (inputValue instanceof Schema) {
            inputFormat = inputFormat == null ? AvroKeyValueInputFormat.class : inputFormat;
        }
        inputFormat = inputFormat == null ? AvroKeyInputFormat.class : inputFormat;

    }
    if (inputFormat != null) {
        job.setInputFormatClass(inputFormat);
    }

    if (inputKey instanceof Schema) {
        AvroJob.setInputKeySchema(job, (Schema) inputKey);
    }

    if (inputValue instanceof Schema) {
        AvroJob.setInputValueSchema(job, (Schema) inputValue);
    }

    if (outputKey instanceof Schema) {

        if (outputValue instanceof Schema) {
            outputFormat = outputFormat == null ? AvroKeyValueOutputFormat.class : outputFormat;
        }
        outputFormat = outputFormat == null ? AvroKeyOutputFormat.class : outputFormat;

    }
    if (outputFormat != null) {
        job.setOutputFormatClass(outputFormat);
    }

    if (outputKey instanceof Schema) {
        AvroJob.setOutputKeySchema(job, (Schema) outputKey);
    } else if (outputKey instanceof Class) {
        job.setOutputKeyClass((Class) outputKey);
    }

    if (outputValue instanceof Schema) {
        AvroJob.setOutputValueSchema(job, (Schema) outputValue);
    } else if (outputValue instanceof Class) {
        job.setOutputValueClass((Class) outputValue);
    }

    if (reducer == null) {
        job.setNumReduceTasks(0);

        if (mapperKey instanceof Schema) {
            AvroJob.setMapOutputKeySchema(job, (Schema) mapperKey);
        } else if (mapperKey instanceof Class) {
            job.setOutputKeyClass((Class) mapperKey);
        }

        if (mapperValue instanceof Schema) {
            AvroJob.setOutputValueSchema(job, (Schema) mapperValue);
        } else if (mapperKey instanceof Class) {
            job.setOutputValueClass((Class) mapperValue);
        }
        job.setJarByClass(mapper);

    } else if (reducer.equals(Reducer.class)) {
        if (mapper.equals(Mapper.class)) {
            throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer");
        }
        job.setJarByClass(mapper);

    } else {
        job.setJarByClass(reducer);

    }

    FileInputFormat.setInputPaths(job, inputPaths);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    if (isCompress) {
        FileOutputFormat.setCompressOutput(job, true);
        FileOutputFormat.setOutputCompressorClass(job, DeflateCodec.class);
    }

    job.setMapperClass(mapper);
    if (mapperKey instanceof Schema) {
        AvroJob.setMapOutputKeySchema(job, (Schema) mapperKey);
    } else if (mapperKey instanceof Class) {
        job.setMapOutputKeyClass((Class) mapperKey);
    }

    if (mapperValue instanceof Schema) {
        AvroJob.setMapOutputValueSchema(job, (Schema) mapperValue);
    } else if (mapperKey instanceof Class) {
        job.setMapOutputValueClass((Class) mapperValue);
    }

    if (reducer != null) {
        job.setReducerClass(reducer);
    }
    if (combiner != null) {
        job.setCombinerClass(combiner);
    }

    if (overwrite) {
        HadoopUtils.delete(jobConf, new Path(outputPath));
    }

    return job;

}

From source file:com.github.libsml.commons.util.HadoopUtils.java

License:Apache License

public static Job prepareAvroJob(String inputPaths, Path outputPath, Schema inputKeySchema,
        Class<? extends Mapper> mapper, Class<? extends Writable> mapperKey,
        Class<? extends Writable> mapperValue, Class<? extends Reducer> combiner,
        Class<? extends Reducer> reducer, Schema outputKeySchema, Class<? extends Writable> outputValue,
        Configuration conf, boolean overwrite) throws IOException {
    Job job = Job.getInstance(conf);
    Configuration jobConf = job.getConfiguration();

    if (reducer.equals(Reducer.class)) {
        if (mapper.equals(Mapper.class)) {
            throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer");
        }//from w w w .j  a  v  a  2 s . c  o  m
        job.setJarByClass(mapper);
    } else {
        job.setJarByClass(reducer);
    }

    FileInputFormat.setInputPaths(job, inputPaths);
    FileOutputFormat.setOutputPath(job, outputPath);

    FileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, DeflateCodec.class);

    job.setInputFormatClass(AvroKeyInputFormat.class);
    AvroJob.setInputKeySchema(job, inputKeySchema);
    job.setMapperClass(mapper);
    if (mapperKey != null) {
        job.setMapOutputKeyClass(mapperKey);
    }
    if (mapperValue != null) {
        job.setMapOutputValueClass(mapperValue);
    }
    if (combiner != null) {
        job.setCombinerClass(combiner);
    }

    job.setOutputFormatClass(AvroKeyOutputFormat.class);
    job.setReducerClass(reducer);
    AvroJob.setOutputKeySchema(job, outputKeySchema);
    job.setOutputValueClass(outputValue);

    if (overwrite) {
        HadoopUtils.delete(jobConf, outputPath);
    }

    return job;

}

From source file:com.github.libsml.commons.util.HadoopUtils.java

License:Apache License

public static Job prepareAvroJob(String inputPaths, Path outputPath, Schema inputKeySchema,
        Class<? extends Mapper> mapper, Class<? extends Writable> mapperKey,
        Class<? extends Writable> mapperValue, Class<? extends Reducer> combiner,
        Class<? extends Reducer> reducer, Class<? extends Writable> outputKey,
        Class<? extends Writable> outputValue, Configuration conf, boolean overwrite) throws IOException {
    Job job = Job.getInstance(conf);
    Configuration jobConf = job.getConfiguration();

    if (reducer.equals(Reducer.class)) {
        if (mapper.equals(Mapper.class)) {
            throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer");
        }/*from  ww  w  . j a v  a2  s.c  om*/
        job.setJarByClass(mapper);
    } else {
        job.setJarByClass(reducer);
    }

    FileInputFormat.setInputPaths(job, inputPaths);
    FileOutputFormat.setOutputPath(job, outputPath);

    //        FileOutputFormat.setCompressOutput(job, true);
    //        FileOutputFormat.setOutputCompressorClass(job, DeflateCodec.class);

    job.setInputFormatClass(AvroKeyInputFormat.class);
    AvroJob.setInputKeySchema(job, inputKeySchema);
    job.setMapperClass(mapper);
    if (mapperKey != null) {
        job.setMapOutputKeyClass(mapperKey);
    }
    if (mapperValue != null) {
        job.setMapOutputValueClass(mapperValue);
    }
    if (combiner != null) {
        job.setCombinerClass(combiner);
    }

    job.setReducerClass(reducer);
    job.setOutputKeyClass(outputKey);
    job.setOutputValueClass(outputValue);

    if (overwrite) {
        HadoopUtils.delete(jobConf, outputPath);
    }

    return job;

}

From source file:com.github.libsml.commons.util.HadoopUtils.java

License:Apache License

public static Job prepareJob(String inputPath, String outputPath, Class<? extends InputFormat> inputFormat,
        Class<? extends Mapper> mapper, Class<? extends Writable> mapperKey,
        Class<? extends Writable> mapperValue, Class<? extends Reducer> reducer,
        Class<? extends Writable> reducerKey, Class<? extends Writable> reducerValue,
        Class<? extends OutputFormat> outputFormat, Configuration conf) throws IOException {

    //    Job job = new Job(new Configuration(conf));
    Job job = Job.getInstance(conf);
    Configuration jobConf = job.getConfiguration();

    if (reducer.equals(Reducer.class)) {
        if (mapper.equals(Mapper.class)) {
            throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer");
        }//from ww  w.  j  av  a  2  s.  c o m
        job.setJarByClass(mapper);
    } else {
        job.setJarByClass(reducer);
    }

    job.setInputFormatClass(inputFormat);
    jobConf.set("mapred.input.dir", inputPath);

    job.setMapperClass(mapper);
    if (mapperKey != null) {
        job.setMapOutputKeyClass(mapperKey);
    }
    if (mapperValue != null) {
        job.setMapOutputValueClass(mapperValue);
    }

    jobConf.setBoolean("mapred.compress.map.output", true);

    job.setReducerClass(reducer);
    job.setOutputKeyClass(reducerKey);
    job.setOutputValueClass(reducerValue);

    job.setOutputFormatClass(outputFormat);
    jobConf.set("mapred.output.dir", outputPath);

    return job;
}

From source file:com.github.sakserv.minicluster.mapreduce.Driver.java

License:Apache License

public static void main(String[] args) throws Exception {

    if (args.length != 2) {
        System.out.println("usage: [input] [output]");
        System.exit(-1);//from   w w  w. j  a v  a2 s . c o m
    }

    if (null == configuration) {
        configuration = new Configuration();
    }

    Job job = Job.getInstance(configuration);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setMapperClass(WordMapper.class);
    job.setReducerClass(SumReducer.class);

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    FileInputFormat.setInputPaths(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setJarByClass(Driver.class);

    job.waitForCompletion(true);

}