大数据HelloWorld-Flink实现WordCount

mvn archetype:generate                \
   -DarchetypeGroupId=.apache.flink       \
   -DarchetypeArtifactId=flink-quickstart-java   \
   -DarchetypeVersion=1.8.0

mvn archetype:generate                \
   -DarchetypeGroupId=.apache.flink       \
   -DarchetypeArtifactId=flink-quickstart-scala   \
   -DarchetypeVersion=1.8.0

├── pom.xml
└── src
  └── main
    ├── resources
    │  └── log4j.properties
    └── scala/java
      └── 
        └── my
          └── quickstart
            ├── BatchJob.scala
            └── StreamingJob.scala

package jar;

import .apache.flink.api.mon.functions.FlatMapFunction;
import .apache.flink.api.mon.functions.ReduceFunction;
import .apache.flink.api.java.ExecutionEnvironment;
import .apache.flink.api.java.operators.DataSource;
import .apache.flink.api.java.tuple.Tuple2;
import .apache.flink.util.Collector;

public class BatchJob {

	public static void main(String[] args) throws Exception {
		// set up the batch execution environment
		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
		//读取目录下的文件
		DataSource<String> data = env.readTextFile("/opt/Server_Packets/log/ServerLog_1_runtime.log");
		//把文件中的内容按照空格进行拆分为 word,1  1 是为了能够在狼蚁网站SEO优化进行计算.
		data.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
			@Override
			public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
				for (String word : s.split(" ")){
					collector.collect(new Tuple2<>(word,1));
				}
			}
		})
		// 按照元组中的第1位进行分组
		.groupBy(0)
		// 分组的元组的计算方式为 value +value 也就是刚才的 同样的词 把 1+1
		.reduce(new ReduceFunction<Tuple2<String, Integer>>() {
			@Override
			public Tuple2<String, Integer> reduce(Tuple2<String, Integer> t2, Tuple2<String, Integer> t1) throws Exception {
				return new Tuple2<>(t1.f0,t1.f1+ t2.f1);
			}
		})
		//输出结果
		.print();
	}
}