|
内容：所有原创文章分类汇总及配套源码，涉及Java、Docker、Kubernetes、DevOPS等； 系列文章链接本篇概览
参考文章梳理流程
源码下载如果您不想写代码，整个系列的源码可在GitHub下载到，地址和链接信息如下表所示(https://github.com/zq2599/blog_demos)：
这个git项目中有多个文件夹，本章的应用在flinkstudy文件夹下，如下图红框所示： CoProcessFunction的子类
package com.bolingcavalry.coprocessfunction;
import com.bolingcavalry.Utils;
import org.apache.flink.api.common.state.ValueState;
import org.apache.flink.api.common.state.ValueStateDescriptor;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.functions.co.CoProcessFunction;
import org.apache.flink.util.Collector;
import org.apache.flink.util.OutputTag;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* 实现双流业务逻辑的功能类
*/
public class ExecuteWithTimeoutCoProcessFunction extends CoProcessFunction<Tuple2<String, Integer>, Tuple2<String, Integer>, Tuple2<String, Integer>> {
private static final Logger logger = LoggerFactory.getLogger(ExecuteWithTimeoutCoProcessFunction.class);
/**
* 等待时间
*/
private static final long WAIT_TIME = 10000L;
public ExecuteWithTimeoutCoProcessFunction(OutputTag<String> source1SideOutput, OutputTag<String> source2SideOutput) {
super();
this.source1SideOutput = source1SideOutput;
this.source2SideOutput = source2SideOutput;
}
private OutputTag<String> source1SideOutput;
private OutputTag<String> source2SideOutput;
// 某个key在processElement1中存入的状态
private ValueState<Integer> state1;
// 某个key在processElement2中存入的状态
private ValueState<Integer> state2;
// 如果创建了定时器，就在状态中保存定时器的key
private ValueState<Long> timerState;
// onTimer中拿不到当前key，只能提前保存在状态中（KeyedProcessFunction的OnTimerContext有API可以取到，但是CoProcessFunction的OnTimerContext却没有）
private ValueState<String> currentKeyState;
@Override
public void open(Configuration parameters) throws Exception {
// 初始化状态
state1 = getRuntimeContext().getState(new ValueStateDescriptor<>("myState1", Integer.class));
state2 = getRuntimeContext().getState(new ValueStateDescriptor<>("myState2", Integer.class));
timerState = getRuntimeContext().getState(new ValueStateDescriptor<>("timerState", Long.class));
currentKeyState = getRuntimeContext().getState(new ValueStateDescriptor<>("currentKeyState", String.class));
}
/**
* 所有状态都清理掉
*/
private void clearAllState() {
state1.clear();
state2.clear();
currentKeyState.clear();
timerState.clear();
}
@Override
public void processElement1(Tuple2<String, Integer> value, Context ctx, Collector<Tuple2<String, Integer>> out) throws Exception {
logger.info("processElement1：处理元素1：{}", value);
String key = value.f0;
Integer value2 = state2.value();
// value2为空，就表示processElement2还没有处理或这个key，
// 这时候就把value1保存起来
if(null==value2) {
logger.info("processElement1：2号流还未收到过[{}]，把1号流收到的值[{}]保存起来", key, value.f1);
state1.update(value.f1);
currentKeyState.update(key);
// 开始10秒的定时器，10秒后会进入
long timerKey = ctx.timestamp() + WAIT_TIME;
ctx.timerService().registerProcessingTimeTimer(timerKey);
// 保存定时器的key
timerState.update(timerKey);
logger.info("processElement1：创建定时器[{}]，等待2号流接收数据", Utils.time(timerKey));
} else {
logger.info("processElement1：2号流收到过[{}]，值是[{}]，现在把两个值相加后输出", key, value2);
// 输出一个新的元素到下游节点
out.collect(new Tuple2<>(key, value.f1 + value2));
// 删除定时器（这个定时器应该是processElement2创建的）
long timerKey = timerState.value();
logger.info("processElement1：[{}]的新元素已输出到下游，删除定时器[{}]", key, Utils.time(timerKey));
ctx.timerService().deleteProcessingTimeTimer(timerKey);
clearAllState();
}
}
@Override
public void processElement2(Tuple2<String, Integer> value, Context ctx, Collector<Tuple2<String, Integer>> out) throws Exception {
logger.info("processElement2：处理元素2：{}", value);
String key = value.f0;
Integer value1 = state1.value();
// value1为空，就表示processElement1还没有处理或这个key，
// 这时候就把value2保存起来
if(null==value1) {
logger.info("processElement2：1号流还未收到过[{}]，把2号流收到的值[{}]保存起来", key, value.f1);
state2.update(value.f1);
currentKeyState.update(key);
// 开始10秒的定时器，10秒后会进入
long timerKey = ctx.timestamp() + WAIT_TIME;
ctx.timerService().registerProcessingTimeTimer(timerKey);
// 保存定时器的key
timerState.update(timerKey);
logger.info("processElement2：创建定时器[{}]，等待1号流接收数据", Utils.time(timerKey));
} else {
logger.info("processElement2：1号流收到过[{}]，值是[{}]，现在把两个值相加后输出", key, value1);
// 输出一个新的元素到下游节点
out.collect(new Tuple2<>(key, value.f1 + value1));
// 删除定时器（这个定时器应该是processElement1创建的）
long timerKey = timerState.value();
logger.info("processElement2：[{}]的新元素已输出到下游，删除定时器[{}]", key, Utils.time(timerKey));
ctx.timerService().deleteProcessingTimeTimer(timerKey);
clearAllState();
}
}
@Override
public void onTimer(long timestamp, OnTimerContext ctx, Collector<Tuple2<String, Integer>> out) throws Exception {
super.onTimer(timestamp, ctx, out);
String key = currentKeyState.value();
// 定时器被触发，意味着此key只在一个中出现过
logger.info("[{}]的定时器[{}]被触发了", key, Utils.time(timestamp));
Integer value1 = state1.value();
Integer value2 = state2.value();
if(null!=value1) {
logger.info("只有1号流收到过[{}]，值为[{}]", key, value1);
// 侧输出
ctx.output(source1SideOutput, "source1 side, key [" + key+ "], value [" + value1 + "]");
}
if(null!=value2) {
logger.info("只有2号流收到过[{}]，值为[{}]", key, value2);
// 侧输出
ctx.output(source2SideOutput, "source2 side, key [" + key+ "], value [" + value2 + "]");
}
clearAllState();
}
}
业务执行类AddTwoSourceValueWithTimeout
package com.bolingcavalry.coprocessfunction;
import com.bolingcavalry.Utils;
import org.apache.flink.api.java.tuple.Tuple;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.AssignerWithPeriodicWatermarks;
import org.apache.flink.streaming.api.functions.co.CoProcessFunction;
import org.apache.flink.streaming.api.watermark.Watermark;
import org.apache.flink.util.OutputTag;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* @author will
* @email zq2599@gmail.com
* @date 2020-11-11 09:48
* @description 将两个流中相通key的value相加，当key在一个流中出现后，
* 会在有限时间内等待它在另一个流中出现，如果超过等待时间任未出现就在旁路输出
*/
public class AddTwoSourceValueWithTimeout extends AbstractCoProcessFunctionExecutor {
private static final Logger logger = LoggerFactory.getLogger(AddTwoSourceValueWithTimeout.class);
// 假设aaa流入1号源后，在2号源超过10秒没有收到aaa，那么1号源的aaa就会流入source1SideOutput
final OutputTag<String> source1SideOutput = new OutputTag<String>("source1-sideoutput"){};
// 假设aaa流入2号源后，如果1号源超过10秒没有收到aaa，那么2号源的aaa就会流入source2SideOutput
final OutputTag<String> source2SideOutput = new OutputTag<String>("source2-sideoutput"){};
/**
* 重写父类的方法，保持父类逻辑不变，仅增加了时间戳分配器，向元素中加入时间戳
* @param port
* @return
*/
@Override
protected KeyedStream<Tuple2<String, Integer>, Tuple> buildStreamFromSocket(StreamExecutionEnvironment env, int port) {
return env
// 监听端口
.socketTextStream("localhost", port)
// 得到的字符串"aaa,3"转成Tuple2实例，f0="aaa"，f1=3
.map(new WordCountMap())
// 设置时间戳分配器，用当前时间作为时间戳
.assignTimestampsAndWatermarks(new AssignerWithPeriodicWatermarks<Tuple2<String, Integer>>() {
@Override
public long extractTimestamp(Tuple2<String, Integer> element, long previousElementTimestamp) {
long timestamp = System.currentTimeMillis();
logger.info("添加时间戳，值：{}，时间戳：{}", element, Utils.time(timestamp));
// 使用当前系统时间作为时间戳
return timestamp;
}
@Override
public Watermark getCurrentWatermark() {
// 本例不需要watermark，返回null
return null;
}
})
// 将单词作为key分区
.keyBy(0);
}
@Override
protected CoProcessFunction<Tuple2<String, Integer>, Tuple2<String, Integer>, Tuple2<String, Integer>> getCoProcessFunctionInstance() {
return new ExecuteWithTimeoutCoProcessFunction(source1SideOutput, source2SideOutput);
}
@Override
protected void doSideOutput(SingleOutputStreamOperator<Tuple2<String, Integer>> mainDataStream) {
// 两个侧输出都直接打印
mainDataStream.getSideOutput(source1SideOutput).print();
mainDataStream.getSideOutput(source2SideOutput).print();
}
public static void main(String[] args) throws Exception {
new AddTwoSourceValueWithTimeout().execute();
}
}
验证（不超时的操作）
18:18:10,472 INFO AddTwoSourceValueWithTimeout - 添加时间戳，值：(aaa,1)，时间戳：2020-11-12 06:18:10 18:18:10,550 INFO ExecuteWithTimeoutCoProcessFunction - processElement1：处理元素1：(aaa,1) 18:18:10,550 INFO ExecuteWithTimeoutCoProcessFunction - processElement1：2号流还未收到过[aaa]，把1号流收到的值[1]保存起来 18:18:10,553 INFO ExecuteWithTimeoutCoProcessFunction - processElement1：创建定时器[2020-11-12 06:18:20]，等待2号流接收数据
18:18:15,813 INFO AddTwoSourceValueWithTimeout - 添加时间戳，值：(aaa,2)，时间戳：2020-11-12 06:18:15 18:18:15,887 INFO ExecuteWithTimeoutCoProcessFunction - processElement2：处理元素2：(aaa,2) 18:18:15,887 INFO ExecuteWithTimeoutCoProcessFunction - processElement2：1号流收到过[aaa]，值是[1]，现在把两个值相加后输出 (aaa,3) 18:18:15,888 INFO ExecuteWithTimeoutCoProcessFunction - processElement2：[aaa]的新元素已输出到下游，删除定时器[2020-11-12 06:18:20] 验证（超时的操作）
18:23:37,393 INFO AddTwoSourceValueWithTimeout - 添加时间戳，值：(aaa,1)，时间戳：2020-11-12 06:23:37 18:23:37,417 INFO ExecuteWithTimeoutCoProcessFunction - processElement1：处理元素1：(aaa,1) 18:23:37,417 INFO ExecuteWithTimeoutCoProcessFunction - processElement1：2号流还未收到过[aaa]，把1号流收到的值[1]保存起来 18:23:37,417 INFO ExecuteWithTimeoutCoProcessFunction - processElement1：创建定时器[2020-11-12 06:23:47]，等待2号流接收数据 18:23:47,398 INFO ExecuteWithTimeoutCoProcessFunction - [aaa]的定时器[2020-11-12 06:23:47]被触发了 18:23:47,399 INFO ExecuteWithTimeoutCoProcessFunction - 只有1号流收到过[aaa]，值为[1] source1 side, key [aaa], value [1]
|
|
|
来自： python_lover > 《待分类》
