Flink CEP 循环模式的连续性

松散连续

默认是松散连续

package com.webank.test01;

import org.apache.flink.cep.CEP;
import org.apache.flink.cep.PatternFlatSelectFunction;
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.util.Collector;

import java.util.Iterator;
import java.util.List;
import java.util.Map;

public class SocketStreamingWordCount {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> text = env.readTextFile("E:\\work\\code\\txt\\tmp\\20210909\\test1.txt");

        Pattern<String, String> pattern = Pattern.<String>begin("start")
                .where(new SimpleCondition<String>() {
                    @Override
                    public boolean filter(String value) throws Exception {
                        return "hello".equals(value);  // 第二次运行将hello修改为world
                    }
                }).times(2);
       /*         .followedByAny("end")
                .where(new SimpleCondition<String>() {
                    @Override
                    public boolean filter(String value) throws Exception {
                        return "world".equals(value.toString());
                    }
                });*/

        PatternStream<String> patternStream = CEP.pattern(text, pattern);

        SingleOutputStreamOperator<String> result = patternStream.flatSelect(new PatternFlatSelectFunction<String, String>() {
            @Override
            public void flatSelect(Map<String, List<String>> map, Collector<String> collector) throws Exception {
                Iterator<String> start = map.get("start").iterator();
                int i = 0;
                while (start.hasNext()){
                    ++i;
                    collector.collect("第"+i+"个"+start.next());
                }

            }
        });

        result.print().setParallelism(1);
        //注意：因为flink是懒加载的，所以必须调用execute方法，上面的代码才会执行
        env.execute("streaming flink cep");
    }
}

test1.txt文件内容如下：

hello
world
world
world
hello
world
运行结果如下：

第1个hello
第2个hello

修改上面的hello为world，运行结果如下：

第1个world
第2个world
第1个world
第2个world
第1个world
第2个world

2. 严格连续

package com.webank.test01;

import org.apache.flink.cep.CEP;
import org.apache.flink.cep.PatternFlatSelectFunction;
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.util.Collector;

import java.util.Iterator;
import java.util.List;
import java.util.Map;

public class SocketStreamingWordCount {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> text = env.readTextFile("E:\\work\\code\\txt\\tmp\\20210909\\test1.txt");

        Pattern<String, String> pattern = Pattern.<String>begin("start")
                .where(new SimpleCondition<String>() {
                    @Override
                    public boolean filter(String value) throws Exception {
                        return "hello".equals(value); //第二次运行将hello修改为world
                    }
                }).times(2).consecutive();
       /*         .followedByAny("end")
                .where(new SimpleCondition<String>() {
                    @Override
                    public boolean filter(String value) throws Exception {
                        return "world".equals(value.toString());
                    }
                });*/

        PatternStream<String> patternStream = CEP.pattern(text, pattern);

        SingleOutputStreamOperator<String> result = patternStream.flatSelect(new PatternFlatSelectFunction<String, String>() {
            @Override
            public void flatSelect(Map<String, List<String>> map, Collector<String> collector) throws Exception {
                Iterator<String> start = map.get("start").iterator();
                int i = 0;
                while (start.hasNext()){
                    ++i;
                    collector.collect("第"+i+"个"+start.next());
                }

            }
        });

        result.print().setParallelism(1);
        //注意：因为flink是懒加载的，所以必须调用execute方法，上面的代码才会执行
        env.execute("streaming flink cep");
    }
}

test1.txt文件内容如下：

hello
world
world
world
hello
world
运行结果如下：

没有任何输出。

修改上面的hello为world，运行结果如下：

第1个world
第2个world
第1个world
第2个world
第1个world
第2个world

运行结果如下：

第1个world
第2个world
第1个world
第2个world

3. 非确定的松散连续

package com.webank.test01;

import org.apache.flink.cep.CEP;
import org.apache.flink.cep.PatternFlatSelectFunction;
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.util.Collector;

import java.util.Iterator;
import java.util.List;
import java.util.Map;

public class SocketStreamingWordCount {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> text = env.readTextFile("E:\\work\\code\\txt\\tmp\\20210909\\test1.txt");

        Pattern<String, String> pattern = Pattern.<String>begin("start")
                .where(new SimpleCondition<String>() {
                    @Override
                    public boolean filter(String value) throws Exception {
                        return "hello".equals(value);
                    }
                }).times(2).allowCombinations();
       /*         .followedByAny("end")
                .where(new SimpleCondition<String>() {
                    @Override
                    public boolean filter(String value) throws Exception {
                        return "world".equals(value.toString());
                    }
                });*/

        PatternStream<String> patternStream = CEP.pattern(text, pattern);

        SingleOutputStreamOperator<String> result = patternStream.flatSelect(new PatternFlatSelectFunction<String, String>() {
            @Override
            public void flatSelect(Map<String, List<String>> map, Collector<String> collector) throws Exception {
                Iterator<String> start = map.get("start").iterator();
                int i = 0;
                while (start.hasNext()){
                    ++i;
                    collector.collect("第"+i+"个"+start.next());
                }

            }
        });

        result.print().setParallelism(1);
        //注意：因为flink是懒加载的，所以必须调用execute方法，上面的代码才会执行
        env.execute("streaming flink cep");
    }
}

test1.txt文件内容如下：

hello
world
world
world
hello
world
运行结果如下：

第1个hello
第2个hello

修改上面的hello为world，运行结果如下：

第1个world
第2个world
第1个world
第2个world
第1个world
第2个world
第1个world
第2个world
第1个world
第2个world
第1个world
第2个world