hadoop mapreduce-白红宇

hadoop mapreduce

阅读量：5087 次

发布时间：2019-06-13

本文共 4005 字，大约阅读时间需要 13 分钟。

写在前面：

需要保证hadoop版本各个jar版本一致，否则可能出现各种哦莫名奇妙的错误！

maven 依赖：


      
          
       
        4.0.0
           
       
        jar
           
       
        BaseTecLearn
           
       
        BaseTecLearn
           
       
        1.0-SNAPSHOT
           
               
                    
         
          org.apache.spark
                     
         
          spark-core_2.11
                     
         
          2.2.0
                 
                
                    
         
          org.apache.spark
                     
         
          spark-sql_2.11
                     
         
          2.2.0
                 
                
                    
         
          org.apache.thrift
                     
         
          libthrift
                     
         
          0.6.1
                 
                
                    
         
          org.apache.hadoop
                     
         
          hadoop-common
                     
         
          2.7.1
                 
                
                    
         
          org.apache.hadoop
                     
         
          hadoop-mapreduce-client-core
                     
         
          2.7.4

View Code

resource目录下配置日志（很重要，可以查看警告啥的）

log4j.rootLogger=WARN,stdout,logfile  log4j.appender.stdout=org.apache.log4j.ConsoleAppender  log4j.appender.stdout.layout=org.apache.log4j.PatternLayout  log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n  log4j.appender.logfile=org.apache.log4j.FileAppender  log4j.appender.logfile.File=hadoop.log   log4j.appender.logfile.layout=org.apache.log4j.PatternLayout  log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%ns

package top.letsgogo;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;public class WordCount {  public static class TokenizerMapper       extends Mapper
     
      {    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
      
        {    private IntWritable result = new IntWritable();    public void reduce(Text key, Iterable
       
         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();    Job job = Job.getInstance(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("/home/panteng/IdeaProjects/pushscore-sdk/baseTecLearn/target/classes/regular.txt"));    FileOutputFormat.setOutputPath(job, new Path("/home/panteng/IdeaProjects/pushscore-sdk/baseTecLearn/target/classes/regular"));    System.out.println(job.waitForCompletion(true));    //System.exit(job.waitForCompletion(true) ? 0 : 1);  }}