import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
@Configuration(
inputPath = "/input",
outputPath = "/output"
)
public class WordCountJob {
public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
// Mapper implementation
}
public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
// Reducer implementation
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCountJob.class);
job.setMapperClass(WordCountMapper.class);
job.setCombinerClass(WordCountReducer.class);
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// Set input and output paths based on the configuration annotation
Path inputPath = new Path(WordCountJob.class.getAnnotation(Configuration.class).inputPath());
Path outputPath = new Path(WordCountJob.class.getAnnotation(Configuration.class).outputPath());
FileInputFormat.addInputPath(job, inputPath);
FileOutputFormat.setOutputPath(job, outputPath);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
