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
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable
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(); System.setProperty(\
?
?
8、运行
8.1、在HDFS上创建目录input
[hadoop@name01 hadoop-2.3.0]$ hadoop fs -ls /
[hadoop@name01 hadoop-2.3.0]$ hadoop fs -mkdir input
mkdir: `input': No such file or directory
[hadoop@name01 hadoop-2.3.0]$ PS：fs需要全目录的方式来创建文件夹
如果Apache hadoop版本是0.x 或者1.x,
bin/hadoop hdfs fs -mkdir -p /in
bin/hadoop hdfs fs -put /home/du/input /in
?
如果Apache hadoop版本是2.x.
bin/hdfs dfs -mkdir -p /in
bin/hdfs dfs -put /home/du/input /in
?
如果是发行版的hadoop,比如Cloudera CDH,IBM BI,Hortonworks HDP 则第一种命令即可。要注意创建目录的全路径。另外hdfs的根目录是 /
?
?
2、拷贝本地README.txt到HDFS的input里
[hadoop@name01 hadoop-2.3.0]$ find . -name README.txt
./share/doc/hadoop/common/README.txt
[hadoop@name01 ~]$ hadoop fs -copyFromLocal ./src/hadoop-2.3.0/share/doc/hadoop/common/README.txt /data/input
[hadoop@name01 ~]$
[hadoop@name01 ~]$ hadoop fs -ls /
3，运行hadoop结束后，查看输出结果
2014-12-16 15:34:01,303 INFO [main] Configuration.deprecation (Configuration.java:warnOnceIfDeprecated(996)) - session.id is deprecated. Instead, use dfs.metrics.session-id2014-12-16 15:34:01,309 INFO [main] jvm.JvmMetrics (JvmMetrics.java:init(76)) - Initializing JVM Metrics with processName=JobTracker, sessionId=
2014-12-16 15:34:02,047 INFO [main] input.FileInputFormat (FileInputFormat.java:listStatus(287)) - Total input paths to process : 1
2014-12-16 15:34:02,120 INFO [main] mapreduce.JobSubmitter (JobSubmitter.java:submitJobInternal(396)) - number of splits:1
2014-12-16 15:34:02,323 INFO [main] mapreduce.JobSubmitter (JobSubmitter.java:printTokens(479)) - Submitting tokens for job: job_local1764589720_0001
2014-12-16 15:34:02,367 WARN [main] conf.Configuration (Configuration.java:loadProperty(2345)) - file:/tmp/hadoop-hadoop/mapred/staging/hadoop1764589720/.staging/job_local1764589720_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval; Ignoring.
2014-12-16 15:34:02,368 WARN [main] conf.Configuration (Configuration.java:loadProperty(2345)) - file:/tmp/hadoop-hadoop/mapred/staging/hadoop1764589720/.staging/job_local1764589720_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts; Ignoring.
2014-12-16 15:34:02,682 WARN [main] conf.Configuration (Configuration.java:loadProperty(2345)) - file:/tmp/hadoop-hadoop/mapred/local/localRunner/hadoop/job_local1764589720_0001/job_local1764589720_0001.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval; Ignoring.
2014-12-16 15:34:02,682 WARN [main] conf.Configuration (Configuration.java:loadProperty(2345)) - file:/tmp/hadoop-ha