idea远程提交任务wordcount避坑指南

代码在这里

讲解wordcount:

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;

import java.io.IOException;
import java.util.StringTokenizer;

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 {
//-DHADOOP_USER_NAME=hadoop 配置这个vm option 是为了替换当前用户名字

Configuration conf = new Configuration();

// String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
// if (otherArgs.length != 2) {
// System.err.println("Usage: wordcount ");
// System.exit(2);
// }
Job job = new Job(conf, “word count suc”);

job.setJar("/Users/***/Documents/gitProject/gitUserHand/cms/target/hadoop-example.jar");//必须要先打包出jar包

job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
Path inputPath = new Path("/user/zcyTest/input");
Path outputPath = new Path("/user/zcyTest/output18");
FileInputFormat.addInputPath(job, inputPath);
FileOutputFormat.setOutputPath(job, outputPath);

// FileInputFormat.addInputPath(job, new Path(args[0]));
// FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}

第一步：新建maven工程

第二部：添加配置文件：
注意：这5个配置文件内容同集群配置文件。如果你们没有这么多也没有关系，只要和集群保持一致即可。

第三步：编写wordcount代码，下载官方源码，然后注意打成jar包，然后在源码里面加上下面这行代码即可。
job.setJar("/Users/***/Documents/gitProject/gitUserHand/cms/target/hadoop-example.jar");

后记：
不懂的可以加qq讨论，共同学习。
参考学习网址
[1]: https://www.cnblogs.com/ksWorld/p/8670165.html