package com.ctgu.flink.project;
import com.ctgu.flink.entity.OrderEvent;
import com.ctgu.flink.entity.ReceiptEvent;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
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.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.co.CoProcessFunction;
import org.apache.flink.streaming.api.functions.co.ProcessJoinFunction;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;
import org.apache.flink.util.OutputTag;
import java.time.Duration;
public class Flink_Sql_Join {
static OutputTag orderOutput = new OutputTag("unCompare Pay") {};
static OutputTag receiptOutput = new OutputTag("unReceipt") {};
public static void main(String[] args) throws Exception {
long start = System.currentTimeMillis();
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(1);
DataStream orderStream = env.readTextFile("data/OrderLog.csv")
.filter(line -> line.split(",").length >= 4)
.map(line -> {
String[] s = line.split(",");
return new OrderEvent(Long.valueOf(s[0]), s[1], s[2], Long.valueOf(s[3]) * 1000);
})
.assignTimestampsAndWatermarks(
WatermarkStrategy.forBoundedOutOfOrderness(Duration.ZERO)
.withTimestampAssigner((event, timestamp) -> event.getTimestamp()))
.filter(data -> !data.getTxId().equals(""));
DataStream receiptStream = env.readTextFile("data/ReceiptLog.csv")
.filter(line -> line.split(",").length >= 3)
.map(line -> {
String[] s = line.split(",");
return new ReceiptEvent(s[0], s[1], Long.valueOf(s[2]) * 1000);
})
.assignTimestampsAndWatermarks(
WatermarkStrategy.forBoundedOutOfOrderness(Duration.ZERO)
.withTimestampAssigner((event, timestamp) -> event.getTimestamp()));
SingleOutputStreamOperator> resultStream
= orderStream.keyBy(OrderEvent::getTxId)
.connect(receiptStream.keyBy(ReceiptEvent::getTxId))
.process(new MyCoProcessFunction());
resultStream.print("success");
resultStream.getSideOutput(orderOutput).print("unPay");
resultStream.getSideOutput(receiptOutput).print("unReceipt");
orderStream.keyBy(OrderEvent::getTxId)
.intervalJoin(receiptStream.keyBy(ReceiptEvent::getTxId))
.between(Time.seconds(-30), Time.seconds(50))
.process(new Flink_Sql_MatchByJoin.MyProcessJoinFunction()).print("success join");
env.execute("Table SQL");
System.out.println("耗时: " + (System.currentTimeMillis() - start) / 1000);
}
public static class MyCoProcessFunction
extends CoProcessFunction> {
ValueState payState;
ValueState receiptState;
@Override
public void open(Configuration parameters) throws Exception {
payState = getRuntimeContext().getState(new ValueStateDescriptor<>("pay", OrderEvent.class));
receiptState = getRuntimeContext().getState(new ValueStateDescriptor<>("receipt", ReceiptEvent.class));
}
@Override
public void processElement1(OrderEvent pay, Context context,
Collector> out) throws Exception {
ReceiptEvent receipt = receiptState.value();
if (receipt != null) {
out.collect(new Tuple2<>(pay, receipt));
payState.clear();
receiptState.clear();
} else {
context.timerService().registerEventTimeTimer(pay.getTimestamp() + 5000);
payState.update(pay);
}
}
@Override
public void processElement2(ReceiptEvent receipt, Context context,
Collector> out) throws Exception {
OrderEvent pay = payState.value();
if (pay != null) {
out.collect(new Tuple2<>(pay, receipt));
payState.clear();
receiptState.clear();
} else {
context.timerService().registerEventTimeTimer(receipt.getTimestamp() + 3000);
receiptState.update(receipt);
}
}
@Override
public void onTimer(long timestamp, OnTimerContext ctx, Collector> out) throws Exception {
if(payState.value() != null) {
ctx.output(orderOutput, payState.value());
}
if(receiptState.value() != null) {
ctx.output(receiptOutput, receiptState.value());
}
payState.clear();
receiptState.clear();
}
}
public static class MyProcessJoinFunction
extends ProcessJoinFunction> {
@Override
public void processElement(OrderEvent orderEvent, ReceiptEvent receiptEvent,
Context context, Collector> collector) throws Exception {
collector.collect(new Tuple2<>(orderEvent, receiptEvent));
}
}
}
测试data
ewr342as4,wechat,1558430845
sd76f87d6,wechat,1558430847
3hu3k2432,alipay,1558430848
8fdsfae83,alipay,1558430850
32h3h4b4t,wechat,1558430852
766lk5nk4,wechat,1558430855
435kjb45d,alipay,1558430859
5k432k4n,wechat,1558430862
435kjb45s,wechat,1558430866
324jnd45s,wechat,1558430868
43jhin3k4,wechat,1558430871
98x0f8asd,alipay,1558430874
392094j32,wechat,1558430877
88df0wn92,alipay,1558430882
435kjb4432,alipay,1558430884
3hefw8jf,alipay,1558430885
499dfano2,wechat,1558430886
8xz09ddsaf,wechat,1558430889
3243hr9h9,wechat,1558430892
329d09f9f,alipay,1558430893
809saf0ff,wechat,1558430895
324n0239,wechat,1558430899
sad90df3,alipay,1558430901
24309dsf,alipay,1558430902
rnp435rk,wechat,1558430905
8c6vs8dd,wechat,1558430906
3245nbo7,alipay,1558430908
8x0zvy8w3,alipay,1558430911
9032n4fd2,wechat,1558430913
d8938034,wechat,1558430915
32499fd9w,alipay,1558430921
9203kmfn,alipay,1558430922
390mf2398,alipay,1558430926
902dsqw45,wechat,1558430927
84309dw31r,alipay,1558430933
sddf9809ew,alipay,1558430936
832jksmd9,wechat,1558430938
m23sare32e,wechat,1558430940
92nr903msa,wechat,1558430944
sdafen9932,alipay,1558430949