package org.apache.hadoop.examples;
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.mapreduc e.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce. lib.output.FileOutputFormat;
import org.apache.hadoop.ut il.GenericOptionsParser;
public class WordCount {
  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{
    private final static IntWritable one = new IntWritable(1);//VALUEOUT
    private Text word = new Text();//KEYOUT
    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 cl ass IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable re sult = 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(Str ing[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOpt ionsParser(conf, args). getRemainingArgs();
    if (otherArgs.length < 2) {
      System.err.println("Usage:  wordcount <in> [<in>...] <out>");
      System.exit(2);
    }
    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.setOutputValue Class(IntWritable.class);
        for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

$ vi mywords.txt
#  輸入如下單詞，行內以空格分隔，行間換行符分隔
Hello World
Hello Hive
Hello Hadoop
#  上傳至HDFS
$ hdfs dfs -mkdir -p /data/wordcount
$ hdfs dfs -put mywords.txt /data/wordcount

$ hive
#  創建表
hive> create external table lines(ling string);
#  裝載數據
hive> load data inpath  '/data/wordcount' overwrite into table lines;
#  查詢統計
hive> select word,count(*) as wc from lines lateral view explode(split(line,' ')) t1 as word group by word;

hive> create external  table lines(line string);
OK
Time taken: 4.742 seconds
hive> load data inpath  '/data/wordcount' overwrite into table lines;
Loading data to table default. lines
Table default.lines stats: [numFiles=l, totalSize=36]
OK
Time taken: 0.514 seconds
hive> select word,count(*) as wc from lines lateral view explode(spl it(line,' ')) tl as word group by word;
Query ID = root_20181129142424_2948e218-ddd7-4e7c-803e-bcd3d21db21f
Total jobs = 1
Launching Job 1 out of 1
Number of reduce tasks not specified . Estimated from input data size: 1
In order to change the average load for a reducer (in bytes):
  set hive.exec.reducers.bytes.per.reducer=<number>
In order to limit the maximum number of reducers:
  set hive.exec.reducers.max=<number>
Hadoop job information for Stage-1: number of mappers:
14:24:46,642    Stage-1 map = 0%,reduce = 0%
14:24:55,246    Stage-1 map = 100%,reduce = 0%,Cumulative CPU 4.41 sec
14:25:04,715    Stage-1 map = 100%, redu ce = 100%,Cumulative CPU 9.13 sec
MapReduce Total cumulative CPU time: 9 seconds 130 msec
Ended Job = job_1543310100051_0033
MapReduce Jobs Launched:
Stage-Stage-1: Map: 1 Reduce: 1 Cumulative CPU: 9.13 sec HDFS Read: 9637 HDFS Write: 32 SUCCESS
Total MapReduce CPU Time Spent: 9 seconds 130 msec
OK
Hadoop 1
Hello 3
Hive 1
World 1
Time taken: 47.78 seconds, Fetched: 4 row(s)
hive>