大数据-122 - Flink Time Watermark Java代码测试实现Tumbling Window - ToB企服应用市场:ToB评测及商务社交产业平台

DataStream<Tuple2<String, Integer>> mainStream =
stream.keyBy(t -> t.f0)
.window(TumblingEventTimeWindows.of(Time.seconds(10)))
.allowedLateness(Time.seconds(5))
.sideOutputLateData(lateOutputTag);

复制代码

01,1586489566000
01,1586489567000
01,1586489568000
01,1586489569000
01,1586489570000
01,1586489571000
01,1586489572000
01,1586489573000
01,1586489574000
01,1586489575000
01,1586489576000
01,1586489577000
01,1586489578000
01,1586489579000

复制代码

SingleOutputStreamOperator<String> res = waterMark
.keyBy(new KeySelector<Tuple2<String, Long>, String>() {
@Override
public String getKey(Tuple2<String, Long> value) throws Exception {
return value.f0;
}
})
.window(TumblingEventTimeWindows.of(Time.seconds(5)))
.apply(new WindowFunction<Tuple2<String, Long>, String, String, TimeWindow>() {
@Override
public void apply(String s, TimeWindow window, Iterable<Tuple2<String, Long>> input, Collector<String> out) throws Exception {
List<Long> list = new ArrayList<>();
for (Tuple2<String, Long> next : input) {
list.add(next.f1);
}
Collections.sort(list);
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS");
String result = "key: " + s + ", list.size(): " + list.size() + ", list.get(0): " + sdf.format(list.get(0)) + ", list.get(last): " + sdf.format(list.get(list.size() - 1))
+ ", start: " + sdf.format(window.getStart()) + ", end: " + sdf.format(window.getEnd());
out.collect(result);
}
});

复制代码

WatermarkStrategy<Tuple2<String, Long>> watermarkStrategy = WatermarkStrategy
.<Tuple2<String, Long>>forBoundedOutOfOrderness(Duration.ofSeconds(5))
.withTimestampAssigner(new SerializableTimestampAssigner<Tuple2<String, Long>>() {
Long currentMaxTimestamp = 0L;
final SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS");
@Override
public long extractTimestamp(Tuple2<String, Long> element, long recordTimestamp) {
long timestamp = element.f1;
currentMaxTimestamp = Math.max(currentMaxTimestamp, timestamp);
System.out.println("Key:" + element.f0 + ", EventTime: " + element.f1 + ", " + format.format(element.f1));
return element.f1;
}
});

复制代码

package icu.wzk;
import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.TimeCharacteristic;
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.windowing.WindowFunction;
import org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.api.windowing.windows.TimeWindow;
import org.apache.flink.util.Collector;
import java.text.SimpleDateFormat;
import java.time.Duration;
import java.util.ArrayList;
import java.util.Collections;
import java.util.List;
public class WatermarkTest01 {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(1);
env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
DataStreamSource<String> data = env.socketTextStream("localhost", 9999);
SingleOutputStreamOperator<Tuple2<String, Long>> mapped = data.map(
new MapFunction<String, Tuple2<String, Long>>() {
@Override
public Tuple2<String, Long> map(String value) throws Exception {
String[] split = value.split(",");
return new Tuple2<>(split[0], Long.valueOf(split[1]));
}
}
);
WatermarkStrategy<Tuple2<String, Long>> watermarkStrategy = WatermarkStrategy
.<Tuple2<String, Long>>forBoundedOutOfOrderness(Duration.ofSeconds(5))
.withTimestampAssigner(new SerializableTimestampAssigner<Tuple2<String, Long>>() {
Long currentMaxTimestamp = 0L;
final SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS");
@Override
public long extractTimestamp(Tuple2<String, Long> element, long recordTimestamp) {
long timestamp = element.f1;
currentMaxTimestamp = Math.max(currentMaxTimestamp, timestamp);
System.out.println("Key:" + element.f0 + ", EventTime: " + element.f1 + ", " + format.format(element.f1));
return element.f1;
}
});
SingleOutputStreamOperator<Tuple2<String, Long>> waterMark = mapped
.assignTimestampsAndWatermarks(watermarkStrategy);
SingleOutputStreamOperator<String> res = waterMark
.keyBy(new KeySelector<Tuple2<String, Long>, String>() {
@Override
public String getKey(Tuple2<String, Long> value) throws Exception {
return value.f0;
}
})
.window(TumblingEventTimeWindows.of(Time.seconds(5)))
.apply(new WindowFunction<Tuple2<String, Long>, String, String, TimeWindow>() {
@Override
public void apply(String s, TimeWindow window, Iterable<Tuple2<String, Long>> input, Collector<String> out) throws Exception {
List<Long> list = new ArrayList<>();
for (Tuple2<String, Long> next : input) {
list.add(next.f1);
}
Collections.sort(list);
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS");
String result = "key: " + s + ", list.size(): " + list.size() + ", list.get(0): " + sdf.format(list.get(0)) + ", list.get(last): " + sdf.format(list.get(list.size() - 1))
+ ", start: " + sdf.format(window.getStart()) + ", end: " + sdf.format(window.getEnd());
out.collect(result);
}
});
res.print();
env.execute();
}
}

复制代码