环境:Vmware 8.0 和ubuntu11.04
Hadoop 实战之运行MultiFile(二)---将输入数据的不同列提取为不同文件的程序
第一步:首先创建一个工程命名为HadoopTest.目录结构如下图:
第二步: 在/home/tanglg1987目录下新建一个start.sh脚本文件,每次启动虚拟机都要删除/tmp目录下的全部文件,重新格式化namenode,代码如下:
sudo rm -rf /tmp/*
rm -rf /home/tanglg1987/hadoop-0.20.2/logs
hadoop namenode -format
hadoop datanode -format
start-all.sh
hadoop fs -mkdir input
hadoop dfsadmin -safemode leave
第三步:给start.sh增加执行权限并启动hadoop伪分布式集群,代码如下:
chmod 777 /home/tanglg1987/start.sh
./start.sh
执行过程如下:
第四步:上传本地文件到hdfs
在专利局http://data.nber.org/patents/网站下载专利数据
http://data.nber.org/patents/apat63_99.zip
hadoop fs -put /home/tanglg1987/apat63_99.txt input
五步:新建一个MultiFile2.java,代码如下:
package com.baison.action;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.SequenceFileInputFormat;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.lib.MultipleTextOutputFormat;
import org.apache.hadoop.mapred.lib.MultipleOutputs;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class MultiFile2 extends Configured implements Tool {
public static class MapClass extends MapReduceBase
implements Mapper<LongWritable, Text, NullWritable, Text> {
private MultipleOutputs mos;
private OutputCollector<NullWritable, Text> collector;
public void configure(JobConf conf) {
mos = new MultipleOutputs(conf);
}
public void map(LongWritable key, Text value,
OutputCollector<NullWritable, Text> output,
Reporter reporter) throws IOException {
String[] arr = value.toString().split(",", -1);
String chrono = arr[0] + "," + arr[1] + "," + arr[2];
String geo = arr[0] + "," + arr[4] + "," + arr[5];
collector = mos.getCollector("chrono", reporter);
collector.collect(NullWritable.get(), new Text(chrono));
collector = mos.getCollector("geo", reporter);
collector.collect(NullWritable.get(), new Text(geo));
}
public void close() throws IOException {
mos.close();
}
}
public int run(String[] args) throws Exception {
// Configuration processed by ToolRunner
Configuration conf = getConf();
// Create a JobConf using the processed conf
JobConf job = new JobConf(conf, MultiFile.class);
// Process custom command-line options
Path in = new Path(args[0]);
Path out = new Path(args[1]);
FileInputFormat.setInputPaths(job, in);
FileOutputFormat.setOutputPath(job, out);
// Specify various job-specific parameters
job.setJobName("MultiFile");
job.setMapperClass(MapClass.class);
job.setInputFormat(TextInputFormat.class);
// job.setOutputFormat(PartitionByCountryMTOF.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(Text.class);
job.setNumReduceTasks(0);
MultipleOutputs.addNamedOutput(job,
"chrono",
TextOutputFormat.class,
NullWritable.class,
Text.class);
MultipleOutputs.addNamedOutput(job,
"geo",
TextOutputFormat.class,
NullWritable.class,
Text.class);
// Submit the job, then poll for progress until the job is complete
JobClient.runJob(job);
return 0;
}
public static void main(String[] args) throws Exception {
// Let ToolRunner handle generic command-line options
String [] arg={"hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt","hdfs://localhost:9100/user/tanglg1987/output"};
int res = ToolRunner.run(new Configuration(), new MultiFile(), arg);
System.exit(res);
}
}
第六步:Run On Hadoop,运行过程如下:
12/10/22 21:25:59 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
12/10/22 21:25:59 WARN mapred.JobClient: No job jar file set. User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
12/10/22 21:25:59 INFO mapred.FileInputFormat: Total input paths to process : 1
12/10/22 21:25:59 INFO mapred.JobClient: Running job: job_local_0001
12/10/22 21:26:00 INFO mapred.FileInputFormat: Total input paths to process : 1
12/10/22 21:26:00 INFO mapred.MapTask: numReduceTasks: 0
12/10/22 21:26:00 INFO mapred.JobClient: map 0% reduce 0%
12/10/22 21:26:03 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:0+67108864
12/10/22 21:26:04 INFO mapred.JobClient: map 17% reduce 0%
12/10/22 21:26:06 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:0+67108864
12/10/22 21:26:07 INFO mapred.JobClient: map 37% reduce 0%
12/10/22 21:26:09 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:0+67108864
12/10/22 21:26:10 INFO mapred.JobClient: map 58% reduce 0%
12/10/22 21:26:12 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:0+67108864
12/10/22 21:26:12 INFO mapred.JobClient: map 84% reduce 0%
12/10/22 21:26:14 INFO mapred.TaskRunner: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
12/10/22 21:26:14 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:0+67108864
12/10/22 21:26:14 INFO mapred.TaskRunner: Task attempt_local_0001_m_000000_0 is allowed to commit now
12/10/22 21:26:15 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:0+67108864
12/10/22 21:26:15 INFO mapred.JobClient: map 100% reduce 0%
12/10/22 21:26:15 INFO mapred.FileOutputCommitter: Saved output of task 'attempt_local_0001_m_000000_0' to hdfs://localhost:9100/user/tanglg1987/output
12/10/22 21:26:15 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:0+67108864
12/10/22 21:26:15 INFO mapred.TaskRunner: Task 'attempt_local_0001_m_000000_0' done.
12/10/22 21:26:15 INFO mapred.MapTask: numReduceTasks: 0
12/10/22 21:26:18 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:67108864+67108864
12/10/22 21:26:19 INFO mapred.JobClient: map 63% reduce 0%
12/10/22 21:26:21 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:67108864+67108864
12/10/22 21:26:22 INFO mapred.JobClient: map 80% reduce 0%
12/10/22 21:26:24 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:67108864+67108864
12/10/22 21:26:25 INFO mapred.JobClient: map 93% reduce 0%
12/10/22 21:26:27 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:67108864+67108864
12/10/22 21:26:28 INFO mapred.JobClient: map 100% reduce 0%
12/10/22 21:26:28 INFO mapred.TaskRunner: Task:attempt_local_0001_m_000001_0 is done. And is in the process of commiting
12/10/22 21:26:28 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:67108864+67108864
12/10/22 21:26:28 INFO mapred.TaskRunner: Task attempt_local_0001_m_000001_0 is allowed to commit now
12/10/22 21:26:29 INFO mapred.FileOutputCommitter: Saved output of task 'attempt_local_0001_m_000001_0' to hdfs://localhost:9100/user/tanglg1987/output
12/10/22 21:26:29 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:67108864+67108864
12/10/22 21:26:29 INFO mapred.TaskRunner: Task 'attempt_local_0001_m_000001_0' done.
12/10/22 21:26:29 INFO mapred.MapTask: numReduceTasks: 0
12/10/22 21:26:32 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:134217728+67108864
12/10/22 21:26:32 INFO mapred.JobClient: map 78% reduce 0%
12/10/22 21:26:35 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:134217728+67108864
12/10/22 21:26:35 INFO mapred.JobClient: map 89% reduce 0%
12/10/22 21:26:38 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:134217728+67108864
12/10/22 21:26:38 INFO mapred.JobClient: map 99% reduce 0%
12/10/22 21:26:40 INFO mapred.TaskRunner: Task:attempt_local_0001_m_000002_0 is done. And is in the process of commiting
12/10/22 21:26:40 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:134217728+67108864
12/10/22 21:26:40 INFO mapred.TaskRunner: Task attempt_local_0001_m_000002_0 is allowed to commit now
12/10/22 21:26:41 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:134217728+67108864
12/10/22 21:26:41 INFO mapred.JobClient: map 100% reduce 0%
12/10/22 21:26:41 INFO mapred.FileOutputCommitter: Saved output of task 'attempt_local_0001_m_000002_0' to hdfs://localhost:9100/user/tanglg1987/output
12/10/22 21:26:41 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:134217728+67108864
12/10/22 21:26:41 INFO mapred.TaskRunner: Task 'attempt_local_0001_m_000002_0' done.
12/10/22 21:26:41 INFO mapred.MapTask: numReduceTasks: 0
12/10/22 21:26:44 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:201326592+35576587
12/10/22 21:26:45 INFO mapred.JobClient: map 86% reduce 0%
12/10/22 21:26:47 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:201326592+35576587
12/10/22 21:26:48 INFO mapred.TaskRunner: Task:attempt_local_0001_m_000003_0 is done. And is in the process of commiting
12/10/22 21:26:48 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:201326592+35576587
12/10/22 21:26:48 INFO mapred.TaskRunner: Task attempt_local_0001_m_000003_0 is allowed to commit now
12/10/22 21:26:48 INFO mapred.JobClient: map 100% reduce 0%
12/10/22 21:26:48 INFO mapred.FileOutputCommitter: Saved output of task 'attempt_local_0001_m_000003_0' to hdfs://localhost:9100/user/tanglg1987/output
12/10/22 21:26:48 INFO mapred.LocalJobRunner: hdfs://localhost:9100/user/tanglg1987/input/apat63_99.txt:201326592+35576587
12/10/22 21:26:48 INFO mapred.TaskRunner: Task 'attempt_local_0001_m_000003_0' done.
12/10/22 21:26:49 INFO mapred.JobClient: Job complete: job_local_0001
12/10/22 21:26:49 INFO mapred.JobClient: Counters: 8
12/10/22 21:26:49 INFO mapred.JobClient: FileSystemCounters
12/10/22 21:26:49 INFO mapred.JobClient: FILE_BYTES_READ=66764
12/10/22 21:26:49 INFO mapred.JobClient: HDFS_BYTES_READ=639593233
12/10/22 21:26:49 INFO mapred.JobClient: FILE_BYTES_WRITTEN=137016
12/10/22 21:26:49 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=639556540
12/10/22 21:26:49 INFO mapred.JobClient: Map-Reduce Framework
12/10/22 21:26:49 INFO mapred.JobClient: Map input records=2923923
12/10/22 21:26:49 INFO mapred.JobClient: Spilled Records=0
12/10/22 21:26:49 INFO mapred.JobClient: Map input bytes=236903179
12/10/22 21:26:49 INFO mapred.JobClient: Map output records=2923923
第七步:查看结果集,运行结果如下: