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.marklogic.mapreduce.examples.ContentLoader.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 2) {
        System.err.println("Usage: ContentLoader configFile inputDir");
        System.exit(2);/*from  w  w w . ja  v a2  s .c  om*/
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "content loader");
    job.setJarByClass(ContentLoader.class);
    job.setInputFormatClass(ContentInputFormat.class);
    job.setMapperClass(ContentMapper.class);
    job.setMapOutputKeyClass(DocumentURI.class);
    job.setMapOutputValueClass(Text.class);
    job.setOutputFormatClass(ContentOutputFormat.class);

    ContentInputFormat.setInputPaths(job, new Path(otherArgs[1]));

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);

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

From source file:com.marklogic.mapreduce.examples.ContentReader.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 2) {
        System.err.println("Usage: ContentReader configFile outputDir");
        System.exit(2);//from   ww w  .j  ava2  s  . co  m
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "content reader");
    job.setJarByClass(ContentReader.class);
    job.setInputFormatClass(DocumentInputFormat.class);
    job.setMapperClass(DocMapper.class);
    job.setMapOutputKeyClass(DocumentURI.class);
    job.setMapOutputValueClass(DatabaseDocument.class);
    job.setOutputFormatClass(CustomOutputFormat.class);

    CustomOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);
    conf.setClass(MarkLogicConstants.INPUT_SSL_OPTIONS_CLASS, SslOptions.class, SslConfigOptions.class);

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

From source file:com.marklogic.mapreduce.examples.HelloWorld.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();

    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    Job job = Job.getInstance(conf, "hello world");
    job.setJarByClass(HelloWorld.class);

    // Map related configuration
    job.setInputFormatClass(DocumentInputFormat.class);
    job.setMapperClass(MyMapper.class);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(Text.class);

    // Reduce related configuration
    job.setReducerClass(MyReducer.class);
    job.setOutputFormatClass(ContentOutputFormat.class);
    job.setOutputKeyClass(DocumentURI.class);
    job.setOutputValueClass(Text.class);

    conf = job.getConfiguration();/*from w  w  w.j  ava  2  s.  c o  m*/
    conf.addResource("marklogic-hello-world.xml");

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

From source file:com.marklogic.mapreduce.examples.LinkCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 2) {
        System.err.println("Usage: LinkCount configFile outputDir");
        System.exit(2);/*  w ww  . ja  v  a  2 s . c o m*/
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "link count");
    job.setJarByClass(LinkCount.class);
    job.setInputFormatClass(ValueInputFormat.class);
    job.setMapperClass(RefMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);
    conf.setClass(MarkLogicConstants.INPUT_VALUE_CLASS, Text.class, Writable.class);

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

From source file:com.marklogic.mapreduce.examples.LinkCountCooccurrences.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 2) {
        System.err.println("Usage: LinkCountCooccurrences configFile outputDir");
        System.exit(2);//  w ww  .  j  ava 2 s.  co m
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "link count cooccurrences");
    job.setJarByClass(LinkCountCooccurrences.class);
    job.setInputFormatClass(KeyValueInputFormat.class);
    job.setMapperClass(RefMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);
    conf.setClass(MarkLogicConstants.INPUT_KEY_CLASS, Text.class, Writable.class);
    conf.setClass(MarkLogicConstants.INPUT_VALUE_CLASS, Text.class, Writable.class);
    conf.setClass(MarkLogicConstants.INPUT_LEXICON_FUNCTION_CLASS, HrefTitleMap.class,
            ElemAttrValueCooccurrences.class);

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

From source file:com.marklogic.mapreduce.examples.LinkCountHDFS.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 2) {
        System.err.println("Usage: LinkCountHDFS inputDir outputDir");
        System.exit(2);//from  ww  w .j  av  a 2s .  c  o m
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "link count hdfs");
    job.setJarByClass(LinkCountHDFS.class);
    job.setInputFormatClass(HDFSInputFormat.class);
    job.setMapperClass(RefMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setReducerClass(IntSumReducer.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    HDFSInputFormat.setInputPaths(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

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

From source file:com.marklogic.mapreduce.examples.LinkCountInDoc.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 1) {
        System.err.println("Usage: LinkCountInDoc configFile");
        System.exit(2);/* w  w  w.  j  ava 2  s .c  o m*/
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "link count in doc");
    job.setJarByClass(LinkCountInDoc.class);
    job.setInputFormatClass(NodeInputFormat.class);
    job.setMapperClass(RefMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputFormatClass(NodeOutputFormat.class);
    job.setOutputKeyClass(NodePath.class);
    job.setOutputValueClass(MarkLogicNode.class);

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);

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

From source file:com.marklogic.mapreduce.examples.LinkCountInProperty.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 1) {
        System.err.println("Usage: LinkCountInProperty configFile");
        System.exit(2);//from w  ww . ja v a2s. c o  m
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "link count in property");
    job.setJarByClass(LinkCountInProperty.class);
    job.setInputFormatClass(ValueInputFormat.class);
    job.setMapperClass(RefMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputFormatClass(PropertyOutputFormat.class);
    job.setOutputKeyClass(DocumentURI.class);
    job.setOutputValueClass(MarkLogicNode.class);

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);
    conf.setClass(MarkLogicConstants.INPUT_VALUE_CLASS, Text.class, Writable.class);

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

From source file:com.marklogic.mapreduce.examples.LinkCountValue.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 2) {
        System.err.println("Usage: LinkCountValue configFile outputDir");
        System.exit(2);/*from   w  ww.j av  a  2s. c o  m*/
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "link count value");
    job.setJarByClass(LinkCountValue.class);
    job.setInputFormatClass(ValueInputFormat.class);
    job.setMapperClass(RefMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);
    conf.setClass(MarkLogicConstants.INPUT_VALUE_CLASS, Text.class, Writable.class);

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

From source file:com.marklogic.mapreduce.examples.RevisionGrouper.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    if (args.length < 1) {
        System.err.println("Usage: RevisionGrouper configFile");
        System.exit(2);//from   w  ww  .  ja v  a 2 s  .  c om
    }
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    Job job = Job.getInstance(conf, "revision grouper");
    job.setJarByClass(RevisionGrouper.class);
    job.setInputFormatClass(NodeInputFormat.class);
    job.setMapperClass(RevisionMapper.class);

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

    conf = job.getConfiguration();
    conf.addResource(otherArgs[0]);

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