adoop版本:1.1.2
集成开发平台:Eclipse SDK 3.5.1
原创作品,转载请标明:http://blog.csdn.net/yming0221/article/details/9013381
1. 首先定义DFS Location(具体的环境搭建请看前面的博文)
2.下面即是Hello World实例
- import java.io.IOException;
- import java.util.StringTokenizer;
- import org.apache.hadoop.conf.Configuration;
- import org.apache.hadoop.fs.Path;
- import org.apache.hadoop.io.IntWritable;
- import org.apache.hadoop.io.Text;
- import org.apache.hadoop.mapreduce.Job;
- import org.apache.hadoop.mapreduce.Mapper;
- import org.apache.hadoop.mapreduce.Reducer;
- import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
- import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
- import org.apache.hadoop.util.GenericOptionsParser;
- public class wordcount {
- public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
- private final static IntWritable one = new IntWritable(1);
- private Text word = new Text();
- public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
- StringTokenizer itr = new StringTokenizer(value.toString());
- while (itr.hasMoreTokens()) {
- word.set(itr.nextToken());
- context.write(word, one);
- }
- }
- }
- public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
- private IntWritable result = new IntWritable();
- public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
- int sum = 0;
- for (IntWritable val : values) {
- sum += val.get();
- }
- result.set(sum);
- context.write(key, result);
- }
- }
- public static void main(String[] args) throws Exception {
- Configuration conf = new Configuration();
- String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
- if (otherArgs.length != 2) {
- System.err.println("Usage: wordcount <in> <out>");
- System.exit(2);
- }
- Job job = new Job(conf, "word count");
- job.setJarByClass(wordcount.class);
- job.setMapperClass(TokenizerMapper.class);
- job.setCombinerClass(IntSumReducer.class);
- job.setReducerClass(IntSumReducer.class);
- job.setOutputKeyClass(Text.class);
- job.setOutputValueClass(IntWritable.class);
- FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
- FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
- System.exit(job.waitForCompletion(true) ? 0 : 1);
- }
- }
3. 运行结果
- 13/06/03 14:45:52 INFO input.FileInputFormat: Total input paths to process : 2
- 13/06/03 14:45:52 WARN snappy.LoadSnappy: Snappy native library not loaded
- 13/06/03 14:45:52 INFO mapred.JobClient: Running job: job_local_0001
- 13/06/03 14:45:52 INFO util.ProcessTree: setsid exited with exit code 0
- 13/06/03 14:45:52 INFO mapred.Task: Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@2b96021e
- 13/06/03 14:45:52 INFO mapred.MapTask: io.sort.mb = 100
- 13/06/03 14:45:53 INFO mapred.MapTask: data buffer = 79691776/99614720
- 13/06/03 14:45:53 INFO mapred.MapTask: record buffer = 262144/327680
- 13/06/03 14:45:53 INFO mapred.MapTask: Starting flush of map output
- 13/06/03 14:45:53 INFO mapred.MapTask: Finished spill 0
- 13/06/03 14:45:53 INFO mapred.Task: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
- 13/06/03 14:45:53 INFO mapred.LocalJobRunner:
- 13/06/03 14:45:53 INFO mapred.Task: Task 'attempt_local_0001_m_000000_0' done.
- 13/06/03 14:45:53 INFO mapred.Task: Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@3621767f
- 13/06/03 14:45:53 INFO mapred.MapTask: io.sort.mb = 100
- 13/06/03 14:45:53 INFO mapred.MapTask: data buffer = 79691776/99614720
- 13/06/03 14:45:53 INFO mapred.MapTask: record buffer = 262144/327680
- 13/06/03 14:45:53 INFO mapred.MapTask: Starting flush of map output
- 13/06/03 14:45:53 INFO mapred.MapTask: Finished spill 0
- 13/06/03 14:45:53 INFO mapred.Task: Task:attempt_local_0001_m_000001_0 is done. And is in the process of commiting
- 13/06/03 14:45:53 INFO mapred.LocalJobRunner:
- 13/06/03 14:45:53 INFO mapred.Task: Task 'attempt_local_0001_m_000001_0' done.
- 13/06/03 14:45:53 INFO mapred.Task: Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@76d6d675
- 13/06/03 14:45:53 INFO mapred.LocalJobRunner:
- 13/06/03 14:45:53 INFO mapred.Merger: Merging 2 sorted segments
- 13/06/03 14:45:53 INFO mapred.Merger: Down to the last merge-pass, with 2 segments left of total size: 53 bytes
- 13/06/03 14:45:53 INFO mapred.LocalJobRunner:
- 13/06/03 14:45:53 INFO mapred.JobClient: map 100% reduce 0%
- 13/06/03 14:45:53 INFO mapred.Task: Task:attempt_local_0001_r_000000_0 is done. And is in the process of commiting
- 13/06/03 14:45:53 INFO mapred.LocalJobRunner:
- 13/06/03 14:45:53 INFO mapred.Task: Task attempt_local_0001_r_000000_0 is allowed to commit now
- 13/06/03 14:45:53 INFO output.FileOutputCommitter: Saved output of task 'attempt_local_0001_r_000000_0' to output
- 13/06/03 14:45:53 INFO mapred.LocalJobRunner: reduce > reduce
- 13/06/03 14:45:53 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
- 13/06/03 14:45:54 INFO mapred.JobClient: map 100% reduce 100%
- 13/06/03 14:45:54 INFO mapred.JobClient: Job complete: job_local_0001
- 13/06/03 14:45:54 INFO mapred.JobClient: Counters: 22
- 13/06/03 14:45:54 INFO mapred.JobClient: File Output Format Counters
- 13/06/03 14:45:54 INFO mapred.JobClient: Bytes Written=25
- 13/06/03 14:45:54 INFO mapred.JobClient: FileSystemCounters
- 13/06/03 14:45:54 INFO mapred.JobClient: FILE_BYTES_READ=18029
- 13/06/03 14:45:54 INFO mapred.JobClient: HDFS_BYTES_READ=63
- 13/06/03 14:45:54 INFO mapred.JobClient: FILE_BYTES_WRITTEN=213880
- 13/06/03 14:45:54 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=25
- 13/06/03 14:45:54 INFO mapred.JobClient: File Input Format Counters
- 13/06/03 14:45:54 INFO mapred.JobClient: Bytes Read=25
- 13/06/03 14:45:54 INFO mapred.JobClient: Map-Reduce Framework
- 13/06/03 14:45:54 INFO mapred.JobClient: Reduce input groups=3
- 13/06/03 14:45:54 INFO mapred.JobClient: Map output materialized bytes=61
- 13/06/03 14:45:54 INFO mapred.JobClient: Combine output records=4
- 13/06/03 14:45:54 INFO mapred.JobClient: Map input records=2
- 13/06/03 14:45:54 INFO mapred.JobClient: Reduce shuffle bytes=0
- 13/06/03 14:45:54 INFO mapred.JobClient: Physical memory (bytes) snapshot=0
- 13/06/03 14:45:54 INFO mapred.JobClient: Reduce output records=3
- 13/06/03 14:45:54 INFO mapred.JobClient: Spilled Records=8
- 13/06/03 14:45:54 INFO mapred.JobClient: Map output bytes=41
- 13/06/03 14:45:54 INFO mapred.JobClient: CPU time spent (ms)=0
- 13/06/03 14:45:54 INFO mapred.JobClient: Total committed heap usage (bytes)=683409408
- 13/06/03 14:45:54 INFO mapred.JobClient: Virtual memory (bytes) snapshot=0
- 13/06/03 14:45:54 INFO mapred.JobClient: Combine input records=4
- 13/06/03 14:45:54 INFO mapred.JobClient: Map output records=4
- 13/06/03 14:45:54 INFO mapred.JobClient: SPLIT_RAW_BYTES=226
- 13/06/03 14:45:54 INFO mapred.JobClient: Reduce input records=4