问题
For example A should be followed by B within 10 seconds. I know how to track if this DID occur (.next, .within), but I want to send an alert if B never happened within the window.
public static void main(String[] args) throws Exception {
final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// checkpointing is required for exactly-once or at-least-once guarantees
// env.enableCheckpointing(1000);
final RMQConnectionConfig connectionConfig = new RMQConnectionConfig.Builder()
.setHost("localhost")
.setPort(5672)
.setVirtualHost("/")
.setUserName("guest")
.setPassword("guest")
.build();
final DataStream<String> inputStream = env
.addSource(new RMQSource<String>(
connectionConfig, // config for the RabbitMQ connection
"cep", // name of the RabbitMQ queue to consume
true, // use correlation ids; can be false if only at-least-once is required
new SimpleStringSchema())) // deserialization schema to turn messages into Java objects
.setParallelism(1); // non-parallel source is only required for exactly-once
inputStream.print();
Pattern<String, ?> simplePattern =
Pattern.<String>begin("start")
.where(new SimpleCondition<String>() {
@Override
public boolean filter(String event) {
return event.equals("A");
}
})
.next("end")
.where(new SimpleCondition<String>() {
@Override
public boolean filter(String event) {
return event.equals("B");
}
});
PatternStream<String> timedOutPatternStream = CEP.pattern(inputStream, simplePattern.within(Time.seconds(10)));
OutputTag<String> timedout = new OutputTag<String>("timedout"){};
SingleOutputStreamOperator<String> timedOutNotificationsStream = timedOutPatternStream.flatSelect(
timedout,
new TimedOut<String>(),
new FlatSelectNothing<String>()
);
timedOutNotificationsStream.getSideOutput(timedout).print();
env.execute("mynotification");
}
public static class TimedOut<String> implements PatternFlatTimeoutFunction<String, String> {
@Override
public void timeout(Map<java.lang.String, List<String>> pattern, long timeoutTimestamp, Collector<String> out) throws Exception {
out.collect((String) "LATE!");
}
}
public static class FlatSelectNothing<T> implements PatternFlatSelectFunction<T, T> {
@Override
public void flatSelect(Map<String, List<T>> pattern, Collector<T> collector) {}
}
Actual behavior:
publish "A"
(wait 5 seconds)
publish "B"
=> (no alert)
publish "A"
(wait 10 seconds)
=> (no alert, but should be)
publish "A"
(wait 10 seconds)
publish "B"
=> "LATE!"
Expected behavior:
publish "A"
(wait 10 seconds)
=> "LATE!"
回答1:
You can do it via timed out patterns. You can specify pattern like
A followedBy B within 10 seconds and check for patterns that timed out, which means that there were only A's. You can check docs for timed out patterns here
For a full example you can refer to this training or straight to the solution to the excercise.
EDIT: Right now (flink <1.5) in processing time pruning is done only on incoming element. Therefore unfortunately after the timeout there must be at least one event(irrelevant if matching or not) that will trigger the timeout. Efforts to improve it can be tracked with this jira ticket
回答2:
Can you try with below solution?
package com.nirav.modi.cep;
import com.nirav.modi.dto.Event;
import org.apache.flink.cep.CEP;
import org.apache.flink.cep.PatternFlatSelectFunction;
import org.apache.flink.cep.PatternFlatTimeoutFunction;
import org.apache.flink.cep.PatternStream;
import org.apache.flink.cep.pattern.Pattern;
import org.apache.flink.cep.pattern.conditions.SimpleCondition;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.source.SourceFunction;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;
import org.apache.flink.util.OutputTag;
import java.util.List;
import java.util.Map;
public class EventNotOccur {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
DataStreamSource<Event> source = env.addSource(new SourceFunction<Event>() {
@Override
public void run(SourceContext<Event> ctx) throws Exception {
for (int i = 0; i < 1; i++) {
ctx.collect(new Event("A"));
Thread.sleep(5000);
ctx.collect(new Event("B"));
Thread.sleep(5000);
ctx.collect(new Event("A"));
Thread.sleep(15000);
ctx.collect(new Event("B"));
Thread.sleep(5000);
ctx.collect(new Event("B"));
}
}
@Override
public void cancel() {
}
});
Pattern<Event, ?> simplePattern =
Pattern.<Event>begin("start")
.where(new SimpleCondition<Event>() {
@Override
public boolean filter(Event event) {
return event.getName().equals("A");
}
})
.next("end")
.where(new SimpleCondition<Event>() {
@Override
public boolean filter(Event event) {
return event.getName().equals("B");
}
});
source.print();
PatternStream<Event> timedOutPatternStream = CEP.pattern(source, simplePattern.within(Time.seconds(10)));
OutputTag<Event> timedout = new OutputTag<Event>("timedout") {
};
timedOutPatternStream.flatSelect(new PatternFlatSelectFunction<Event, String>() {
@Override
public void flatSelect(Map<String, List<Event>> pattern, Collector<String> out) throws Exception {
out.collect("Pattern Match...............");
}
}).print();
SingleOutputStreamOperator<Event> longRides = timedOutPatternStream
.flatSelect(
timedout,
new EventTimeOut(),
new FlatSelectNothing()
);
longRides.getSideOutput(timedout).print();
env.execute("Flink Streaming Java API Skeleton");
}
public static class EventTimeOut<Event> implements PatternFlatTimeoutFunction<Event, Event> {
@Override
public void timeout(Map<String, List<Event>> map, long l, Collector<Event> collector) throws Exception {
Event rideStarted = map.get("start").get(0);
System.out.println("Time out Partial Event : " + rideStarted);
collector.collect(rideStarted);
}
}
public static class FlatSelectNothing<T> implements PatternFlatSelectFunction<T, T> {
@Override
public void flatSelect(Map<String, List<T>> pattern, Collector<T> collector) {
System.out.println("Flat select nothing: " + pattern.get("start").get(0));
collector.collect(pattern.get("start").get(0));
}
}
}
来源：https://stackoverflow.com/questions/50356981/apache-flink-cep-how-to-detect-if-event-did-not-occur-within-x-seconds