求最大访问量
package com.atguigu.chapter05;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.functions.ReduceFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
public class TransReduceTest {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(1);
// 这里的使用了之前自定义数据源小节中的ClickSource()
env.addSource(new ClickSource())
// 将Event数据类型转换成元组类型
.map(new MapFunction>() {
@Override
public Tuple2 map(Event e) throws Exception {
return Tuple2.of(e.user, 1L);
}
})
.keyBy(r -> r.f0) // 使用用户名来进行分流
.reduce(new ReduceFunction>() {
@Override
public Tuple2 reduce(Tuple2 value1, Tuple2 value2) throws Exception {
// 每到一条数据,用户pv的统计值加1
return Tuple2.of(value1.f0, value1.f1 + value2.f1);
}
})
.keyBy(r -> true) // 为每一条数据分配同一个key,将聚合结果发送到一条流中去
.reduce(new ReduceFunction>() {
@Override
public Tuple2 reduce(Tuple2 value1, Tuple2 value2) throws Exception {
// 将累加器更新为当前最大的pv统计值,然后向下游发送累加器的值
return value1.f1 > value2.f1 ? value1 : value2;
}
})
.print();
env.execute();
}
}
package com.atguigu.chapter05; import org.apache.flink.streaming.api.functions.source.SourceFunction; import java.util.Calendar; import java.util.Random; public class ClickSource implements SourceFunction{ // 声明一个布尔变量,作为控制数据生成的标识位 private Boolean running = true; @Override public void run(SourceContext ctx) throws Exception { Random random = new Random(); // 在指定的数据集中随机选取数据 String[] users = {"Mary", "Alice", "Bob", "Cary"}; String[] urls = {"./home", "./cart", "./fav", "./prod?id=1", "./prod?id=2"}; while (running) { ctx.collect(new Event( users[random.nextInt(users.length)], urls[random.nextInt(urls.length)], Calendar.getInstance().getTimeInMillis() )); // 隔1秒生成一个点击事件,方便观测 Thread.sleep(1000); } } @Override public void cancel() { running = false; } }
以上摘自尚硅谷教程



