代码
package wordcount;
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, "wordcount");
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);
}
}
报错一:
hadoop jar ~/workspace/HadoopTest02.jar wordcount.WordCount /user/hadoop/test1/input /user/hadoop/test1/output
Application application_1488773330457_0001 failed 2 times due to AM Container for appattempt_1488773330457_0001_000002 exited with exitCode: -1000
For more detailed output, check application tracking page:http://hadoop001:23188/proxy/application_1488773330457_0001/Then, click on links to logs of each attempt.
Diagnostics: Could not find any valid local directory for nmPrivate/container_1488773330457_0001_02_000001.tokens
Failing this attempt. Failing the application.
报错二:
hadoop jar ~/workspace/HadoopTest02.jar wordcount.WordCount /user/hadoop/test1/input /user/hadoop/test1/output
Usage:wordcount<in><out>
没有识别后面的俩路径,什么情况???
|
|