0
私は、特定の時間内に同じcorrelationIdを持つ3カフカソースストリームで3つのイベントを収集し、遅れて到着した場合、これらのイベントのすべてまたは一部を収集できる必要があります。PatternStreamの同じイベントをPatternSelectFunctionとPatternTimeoutFunctionの両方に送信できるのはなぜですか？
3 DataStreamとCEPパターンで共用体を使用しました。しかし、私は、に達すると、パターンとよく一致し、したがってselect関数で収集されるイベントもタイムアウト関数で送信されることに気付きました。
私の例で何が間違っていたのか、私が理解できなかったことはわかりませんが、正に一致しているイベントはタイムアウトしていないと予想していました。
個別の時間スナップショットが保存されるという印象を受けます。
私は1.3.0 Flinkバージョンを使用しています。
ありがとうございました。
我々は3つの相関イベントの2を選択し、タイムアウトしていることがわかりますコンソール出力、：
マッチングイベントを：
キー--- 0b3c116e-0703-43cb-8b3e-54b0b5e93948
キー - --f969dd4d-47ff-445C-9182-0f95a569febb
キー--- 2ecbb89d-1463から4669-a657-555f73b6fb1d
タイムアウトしましたイベント：タイムアウト機能へ
最初の呼び出し：0
--- f969dd4d-47ff-445C-9182-0f95a569febb キーキー--- 0b3c116e-0703-43cb-8b3e-54b0b5e93948
第二コール：
キー--- f969dd4d-47ff-445C-9182- 0f95a569febb
11:01:44,677 INFO com.bnpp.pe.cep.Main - Matching events:
11:01:44,678 INFO com.bnpp.pe.cep.Main - SctRequestProcessStep2Event(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---0b3c116e-0703-43cb-8b3e-54b0b5e93948, debtorIban=BE42063929068055, creditorIban=BE42063929068056, amount=100.0, communication=test), succeeded=false)
11:01:44,678 INFO com.bnpp.pe.cep.Main - SctRequestProcessStep1Event(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---2ecbb89d-1463-4669-a657-555f73b6fb1d, debtorIban=BE42063929068055, creditorIban=BE42063929068056, amount=100.0, communication=test), succeeded=false)
11:01:44,678 INFO com.bnpp.pe.cep.Main - SctRequestProcessStep3Event(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---f969dd4d-47ff-445c-9182-0f95a569febb, debtorIban=BE42063929068055, creditorIban=BE42063929068056, amount=100.0, communication=test), succeeded=false)
Right(SctRequestFinalEvent(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---2196fdb0-01e8-4cc6-af4b-04bcf9dc67a2, debtorIban=null, creditorIban=null, amount=null, communication=null), state=SUCCESS))
11:01:49,635 INFO com.bnpp.pe.cep.Main - Timed out events:
11:01:49,636 INFO com.bnpp.pe.cep.Main - SctRequestProcessStep3Event(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---f969dd4d-47ff-445c-9182-0f95a569febb, debtorIban=BE42063929068055, creditorIban=BE42063929068056, amount=100.0, communication=test), succeeded=false)
11:01:49,636 INFO com.bnpp.pe.cep.Main - SctRequestProcessStep2Event(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---0b3c116e-0703-43cb-8b3e-54b0b5e93948, debtorIban=BE42063929068055, creditorIban=BE42063929068056, amount=100.0, communication=test), succeeded=false)
11:01:49,636 INFO com.bnpp.pe.cep.Main - Timed out events:
11:01:49,636 INFO com.bnpp.pe.cep.Main - SctRequestProcessStep3Event(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---f969dd4d-47ff-445c-9182-0f95a569febb, debtorIban=BE42063929068055, creditorIban=BE42063929068056, amount=100.0, communication=test), succeeded=false)
Left(SctRequestFinalEvent(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---aa437bcf-ecaa-4561-9f4e-08a902f0e248, debtorIban=null, creditorIban=null, amount=null, communication=null), state=FAILED))
Left(SctRequestFinalEvent(super=SctRequestEvent(correlationId=cId---a14a4e23-56c5-4242-9c43-d465d2b84454, key=Key---5420eb41-2723-42ac-83fd-d203d6bf2526, debtorIban=null, creditorIban=null, amount=null, communication=null), state=FAILED))
私のテストコード：
package com.bnpp.pe.cep;
import com.bnpp.pe.event.Event;
import com.bnpp.pe.event.SctRequestFinalEvent;
import com.bnpp.pe.util.EventHelper;
import lombok.extern.slf4j.Slf4j;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.cep.CEP;
import org.apache.flink.cep.PatternSelectFunction;
import org.apache.flink.cep.PatternStream;
import org.apache.flink.cep.PatternTimeoutFunction;
import org.apache.flink.cep.pattern.Pattern;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer010;
import org.apache.flink.streaming.util.serialization.DeserializationSchema;
import java.io.Serializable;
import java.util.List;
import java.util.Map;
import java.util.Properties;
/**
* Created by Laurent Bauchau on 2/08/2017.
*/
@Slf4j
public class Main implements Serializable {
public static void main(String... args) {
new Main();
}
public static final String step1Topic = "sctinst-step1";
public static final String step2Topic = "sctinst-step2";
public static final String step3Topic = "sctinst-step3";
private static final String PATTERN_NAME = "the_3_correlated_events_pattern";
private final FlinkKafkaConsumer010<Event> kafkaSource1;
private final DeserializationSchema<Event> deserializationSchema1;
private final FlinkKafkaConsumer010<Event> kafkaSource2;
private final DeserializationSchema<Event> deserializationSchema2;
private final FlinkKafkaConsumer010<Event> kafkaSource3;
private final DeserializationSchema<Event> deserializationSchema3;
private Main() {
// Kafka init
Properties kafkaProperties = new Properties();
kafkaProperties.setProperty("bootstrap.servers", "localhost:9092");
kafkaProperties.setProperty("zookeeper.connect", "localhost:2180");
kafkaProperties.setProperty("group.id", "sct-validation-cgroup1");
deserializationSchema1 = new SctRequestProcessStep1EventDeserializer();
kafkaSource1 = new FlinkKafkaConsumer010<>(step1Topic, deserializationSchema1, kafkaProperties);
deserializationSchema2 = new SctRequestProcessStep2EventDeserializer();
kafkaSource2 = new FlinkKafkaConsumer010<>(step2Topic, deserializationSchema2, kafkaProperties);
deserializationSchema3 = new SctRequestProcessStep3EventDeserializer();
kafkaSource3 = new FlinkKafkaConsumer010<>(step3Topic, deserializationSchema3, kafkaProperties);
try {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setStreamTimeCharacteristic(TimeCharacteristic.IngestionTime);
DataStream<Event> s1 = env.addSource(kafkaSource1);
DataStream<Event> s2 = env.addSource(kafkaSource2);
DataStream<Event> s3 = env.addSource(kafkaSource3);
DataStream<Event> unionStream = s1.union(s2, s3);
Pattern successPattern = Pattern.<Event>begin(PATTERN_NAME)
.times(3)
.within(Time.seconds(5));
PatternStream<Event> matchingStream = CEP.pattern(
unionStream.keyBy(new CIDKeySelector()),
successPattern);
matchingStream.select(new MyPatternTimeoutFunction(), new MyPatternSelectFunction())
.print()
.setParallelism(1);
env.execute();
} catch (Exception e) {
log.error(e.getMessage(), e);
}
}
private static class MyPatternTimeoutFunction implements PatternTimeoutFunction<Event, SctRequestFinalEvent> {
@Override
public SctRequestFinalEvent timeout(Map<String, List<Event>> pattern, long timeoutTimestamp) throws Exception {
List<Event> events = pattern.get(PATTERN_NAME);
log.info("Timed out events:");
events.forEach(e -> log.info(e.toString()));
// Resulting event creation
SctRequestFinalEvent event = new SctRequestFinalEvent();
EventHelper.correlate(events.get(0), event);
EventHelper.injectKey(event);
event.setState(SctRequestFinalEvent.State.FAILED);
return event;
}
}
private static class MyPatternSelectFunction
implements PatternSelectFunction<Event, SctRequestFinalEvent> {
@Override
public SctRequestFinalEvent select(Map<String, List<Event>> pattern) throws Exception {
List<Event> events = pattern.get(PATTERN_NAME);
log.info("Matching events:");
events.forEach(e -> log.info(e.toString()));
// Resulting event creation
SctRequestFinalEvent event = new SctRequestFinalEvent();
EventHelper.correlate(events.get(0), event);
EventHelper.injectKey(event);
event.setState(SctRequestFinalEvent.State.SUCCESS);
return event;
}
}
private static class CIDKeySelector implements KeySelector<Event, String> {
@Override
public String getKey(Event event) throws Exception {
return event.getCorrelationId();
}
}
}