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

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

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

Introduction

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

Prototype

public void setOutputFormatClass(Class<? extends OutputFormat> cls) throws IllegalStateException

Source Link

Document

Set the OutputFormat for the job.

Usage

From source file:com.cloudera.test.UseHCat.java

License:Apache License

public int run(String[] args) throws Exception {
    Configuration conf = getConf();
    args = new GenericOptionsParser(conf, args).getRemainingArgs();

    // Get the input and output table names as arguments
    String inputTableName = args[0];
    String outputTableName = args[1];
    // Assume the default database
    String dbName = null;//w w w .  ja va2s.  c om

    Job job = new Job(conf, "UseHCat");
    HCatInputFormat.setInput(job, dbName, inputTableName);
    job.setJarByClass(UseHCat.class);
    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

    // An HCatalog record as input
    job.setInputFormatClass(HCatInputFormat.class);

    // Mapper emits a string as key and an integer as value
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    // Ignore the key for the reducer output; emitting an HCatalog record as value
    job.setOutputKeyClass(WritableComparable.class);
    job.setOutputValueClass(DefaultHCatRecord.class);
    job.setOutputFormatClass(HCatOutputFormat.class);

    HCatOutputFormat.setOutput(job, OutputJobInfo.create(dbName, outputTableName, null));
    HCatSchema s = HCatOutputFormat.getTableSchema(job);
    System.err.println("INFO: output schema explicitly set for writing:" + s);
    HCatOutputFormat.setSchema(job, s);
    return (job.waitForCompletion(true) ? 0 : 1);
}

From source file:com.cloudy.mapred.base.JobUtil.java

License:Apache License

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));
    Configuration jobConf = job.getConfiguration();

    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);

    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.cloudy.mapred.base.JobUtil.java

License:Apache License

/**
 * Create a map and reduce Hadoop job.  Does not set the name on the job.
 * @param inputPath The input {@link org.apache.hadoop.fs.Path}
 * @param outputPath The output {@link org.apache.hadoop.fs.Path}
 * @param inputFormat The {@link org.apache.hadoop.mapreduce.InputFormat}
 * @param mapper The {@link org.apache.hadoop.mapreduce.Mapper} class to use
 * @param mapperKey The {@link org.apache.hadoop.io.Writable} key class.  If the Mapper is a no-op,
 *                  this value may be null
 * @param mapperValue The {@link org.apache.hadoop.io.Writable} value class.  If the Mapper is a no-op,
 *                    this value may be null
 * @param reducer The {@link org.apache.hadoop.mapreduce.Reducer} to use
 * @param reducerKey The reducer key class.
 * @param reducerValue The reducer value class.
 * @param outputFormat The {@link org.apache.hadoop.mapreduce.OutputFormat}.
 * @param conf The {@link org.apache.hadoop.conf.Configuration} to use.
 * @return The {@link org.apache.hadoop.mapreduce.Job}.
 * @throws IOException if there is a problem with the IO.
 *
 * @see #getCustomJobName(String, org.apache.hadoop.mapreduce.JobContext, Class, Class)
 * @see #prepareJob(org.apache.hadoop.fs.Path, org.apache.hadoop.fs.Path, Class, Class, Class, Class, Class,
 * org.apache.hadoop.conf.Configuration)
 *//*  w w  w  .  j  a  va  2s .  co  m*/
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 Reducer> reducer,
        Class<? extends Writable> reducerKey, Class<? extends Writable> reducerValue,
        Class<? extends OutputFormat> outputFormat, Configuration conf) throws IOException {

    Job job = new Job(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");
        }
        job.setJarByClass(mapper);
    } else {
        job.setJarByClass(reducer);
    }

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

    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.toString());

    return job;
}

From source file:com.cmcc.hy.bigdata.weijifen.jobs.hubei.score.ScoreInfoDayJob.java

License:Open Source License

@Override
public int run(String[] args) throws Exception {
    // TODO Auto-generated method stub

    Configuration conf = ConfigurationUtil.loginAuthentication(args, SEPCIFIC_CONFIG_NAME, getConf());

    // ?()/*from  w ww  . j  a  va2s .  c om*/
    String statDate = DateUtil.getFilterDate(args);
    if (statDate == null) {
        System.exit(1);
    }

    conf.set(STAT_DAY, statDate);

    // ?job
    Job job = Job.getInstance(conf, JOB_NAME + ":" + statDate);
    job.setJarByClass(ScoreInfoDayJob.class);
    String scoreInfoInput = conf.get(SCORE_INFO_INPUT_PATH);
    Path scoreInfoPath = new Path(scoreInfoInput);

    String acctPhoneMapInfoInput = conf.get(ACCT_PHONE_MAP_INPUT_PATH);
    Path accPhoneMapInfoPath = new Path(acctPhoneMapInfoInput);

    // ?
    if (FileSystemUtil.exists(scoreInfoPath)) {
        MultipleInputs.addInputPath(job, scoreInfoPath, SequenceFileInputFormat.class,
                ScoreInfoDayMapper.class);
        logger.info("SocreInfoPath is " + scoreInfoInput);
    } else {
        logger.error("Path [{}] not exist!", scoreInfoInput);
    }

    // ??
    //        if (FileSystemUtil.exists(accPhoneMapInfoPath)) {
    //            MultipleInputs.addInputPath(job, accPhoneMapInfoPath, TextInputFormat.class,
    //                    AcctPhoneMapper.class);
    //            logger.info("AccPhoneMapInfoPath is " + acctPhoneMapInfoInput);
    //        } else {
    //            logger.error("Path [{}] not exist!", acctPhoneMapInfoInput);
    //        }
    // job
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(ScoreInfo.class);
    job.setNumReduceTasks(conf.getInt(REDUCE_NUMBER, 40));
    job.setOutputFormatClass(NullOutputFormat.class);

    //        TableMapReduceUtil.initTableReducerJob(HBaseTableSchema.USER_INFO_TABLE2,
    //                ScoreInfoDayReducer.class, job);

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

From source file:com.conversantmedia.mapreduce.example.WordCount.java

License:Apache License

public static void main(String[] args) {

    try {//from w w  w  . j  av  a2s.  co  m
        Job job = Job.getInstance(new Configuration(), "WordCount v2");

        job.setInputFormatClass(FileInputFormat.class);
        job.setOutputFormatClass(FileOutputFormat.class);

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        job.setCombinerClass(WordCountReducer.class);

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

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

        job.waitForCompletion(true);

    } catch (IOException | ClassNotFoundException | InterruptedException e) {
        e.printStackTrace();
    }
}

From source file:com.conversantmedia.mapreduce.tool.annotation.handler.FileOutputAnnotationHandler.java

License:Apache License

protected void configureOutputs(Job job, FileOutput fileOutput) throws IllegalAccessException,
        InvocationTargetException, NoSuchMethodException, ToolException, IllegalArgumentException, IOException {
    job.setOutputFormatClass(fileOutput.value());
    // The property used for retrieving the path
    Object path = this.evaluateExpression(fileOutput.path());
    configureFileOutputPaths(job, path);
}

From source file:com.conversantmedia.mapreduce.tool.annotation.handler.TableOutputAnnotationHandler.java

License:Apache License

@Override
public void process(Annotation annotation, Job job, Object target) throws ToolException {

    TableOutput tableOutput = (TableOutput) annotation;

    // Base setup of the table job
    Configuration conf = job.getConfiguration();
    HBaseConfiguration.merge(conf, HBaseConfiguration.create(conf));

    // Add dependencies
    try {/*from  w w w . j  av  a 2 s  .  c om*/
        TableMapReduceUtil.addDependencyJars(job);
    } catch (IOException e) {
        throw new ToolException(e);
    }

    // Set table output format
    job.setOutputFormatClass(TableOutputFormat.class);

    // Set the table name
    String tableName = (String) this.evaluateExpression(tableOutput.value());
    job.getConfiguration().set(TableOutputFormat.OUTPUT_TABLE, tableName);

}

From source file:com.cotdp.hadoop.ZipFileTest.java

License:Apache License

/**
 * This test operates on a single file/*from w  w  w  .  j a  v  a 2 s. co  m*/
 * 
 * Expected result: success
 * 
 * @throws IOException 
 * @throws InterruptedException 
 * @throws ClassNotFoundException 
 */
public void testSingle() throws IOException, ClassNotFoundException, InterruptedException

{
    LOG.info("============================================================");
    LOG.info("==                Running testSingle()                    ==");
    LOG.info("============================================================");

    // Standard stuff
    Job job = new Job(conf);
    job.setJobName(this.getClass().getSimpleName());
    job.setJarByClass(this.getClass());
    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    // 
    job.setInputFormatClass(ZipFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // The output files will contain "Word [TAB] Count"
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    //
    ZipFileInputFormat.setInputPaths(job, new Path(inputPath, "zip-01.zip"));
    TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_Single"));

    //
    assertTrue(job.waitForCompletion(true));
}

From source file:com.cotdp.hadoop.ZipFileTest.java

License:Apache License

/**
 * This test operates on a Path containing files that will cause the Job to fail
 * /*from   w  ww .  j a  va 2  s.c o m*/
 * Expected result: failure
 * 
 * @throws IOException 
 * @throws InterruptedException 
 * @throws ClassNotFoundException 
 */
public void testMultiple() throws IOException, ClassNotFoundException, InterruptedException

{
    LOG.info("============================================================");
    LOG.info("==                Running testMultiple()                  ==");
    LOG.info("============================================================");

    // Standard stuff
    Job job = new Job(conf);
    job.setJobName(this.getClass().getSimpleName());
    job.setJarByClass(this.getClass());
    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    // 
    job.setInputFormatClass(ZipFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // The output files will contain "Word [TAB] Count"
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    //
    ZipFileInputFormat.setInputPaths(job, inputPath);
    TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_Multiple"));

    //
    assertFalse(job.waitForCompletion(true));
}

From source file:com.cotdp.hadoop.ZipFileTest.java

License:Apache License

/**
 * This test is identical to testMultiple() however the ZipFileInputFormat is set to
 * be lenient, errors that cause testMultiple() to fail will be quietly ignored here.
 * //  ww w. j  a v a2s.  c o  m
 * Expected result: success
 * 
 * @throws IOException 
 * @throws InterruptedException 
 * @throws ClassNotFoundException 
 */
public void testMultipleLenient() throws IOException, ClassNotFoundException, InterruptedException

{
    LOG.info("============================================================");
    LOG.info("==                Running testMultipleLenient()           ==");
    LOG.info("============================================================");

    // Standard stuff
    Job job = new Job(conf);
    job.setJobName(this.getClass().getSimpleName());
    job.setJarByClass(this.getClass());
    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    // 
    job.setInputFormatClass(ZipFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // The output files will contain "Word [TAB] Count"
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    //
    ZipFileInputFormat.setLenient(true);
    ZipFileInputFormat.setInputPaths(job, inputPath);
    TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_MultipleLenient"));

    //
    assertTrue(job.waitForCompletion(true));
}