hadoop word count

code/build.gradle

@@ -12,6 +12,7 @@ repositories {
     maven {
         //url 'https://mvnrepository.com/artifact/org.apache.storm/storm-core'
         url 'http://clojars.org/repo/'
+        //url 'http://mirrors.163.com/maven/#browse/browse/components:maven-public/'
     }
 }
 
@@ -27,6 +28,16 @@ dependencies {
     // https://mvnrepository.com/artifact/org.apache.commons/commons-collections4
     compile group: 'org.apache.commons', name: 'commons-collections4', version: '4.0'
 
+    // https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common
+    compile group: 'org.apache.hadoop', name: 'hadoop-common', version: '2.7.4'
+
+    // https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs
+    compile group: 'org.apache.hadoop', name: 'hadoop-hdfs', version: '2.7.4'
+
+    // https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-core
+    compile group: 'org.apache.hadoop', name: 'hadoop-mapreduce-client-core', version: '2.7.4'
+
+
 }
 
 jar {

code/src/main/java/com/raorao/hadoop/WordCount.java

@@ -0,0 +1,74 @@
+package com.raorao.hadoop;
+
+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;
+
+/**
+ * 使用map reduce实现计数操作.
+ *
+ * @author Xiong Raorao
+ * @since 2018-07-31-10:22
+ */
+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, "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(otherArgs[0]));
+    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
+    System.exit(job.waitForCompletion(true) ? 0 : 1);
+  }
+}