I used this code to run the word count hadoop job. WordCountDriver runs when I run it from inside eclipse with the hadoop eclipse plugin. WordCountDriver also runs from the command line when I package the mapper and reducer classes as a jar and drop it in the classpath.
However, it fails if I try to run it from the command line without adding the mapper and reducer class as a jar to the classpath although I added both the classes to the classpath. I wanted to know is there some restriction in hadoop from accepting mapper & reducer classes as normal class files. Is creating a jar always mandatory ?
public class WordCountDriver extends Configured implements Tool {
public static final String HADOOP_ROOT_DIR = "hdfs://universe:54310/app/hadoop/tmp";
static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private Text word = new Text();
private final IntWritable one = new IntWritable(1);
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer itr = new StringTokenizer(line.toLowerCase());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
};
static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable value : values) {
sum += value.get(); // process value
}
context.write(key, new IntWritable(sum));
}
};
/**
*
*/
public int run(String[] args) throws Exception {
Configuration conf = getConf();
conf.set("mapred.job.tracker", "universe:54311");
Job job = new Job(conf, "Word Count");
// specify output types
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// specify input and output dirs
FileInputFormat.addInputPath(job, new Path(HADOOP_ROOT_DIR + "/input"));
FileOutputFormat.setOutputPath(job, new Path(HADOOP_ROOT_DIR + "/output"));
// specify a mapper
job.setMapperClass(WordCountDriver.WordCountMapper.class);
// specify a reducer
job.setReducerClass(WordCountDriver.WordCountReducer.class);
job.setCombinerClass(WordCountDriver.WordCountReducer.class);
job.setJarByClass(WordCountDriver.WordCountMapper.class);
return job.waitForCompletion(true) ? 0 : 1;
}
/**
*
* @param args
* @throws Exception
*/
public static void main(String[] args) throws Exception {
int res = ToolRunner.run(new Configuration(), new WordCountDriver(), args);
System.exit(res);
}
}
