java flink（十九） 实战之电商页面统计热门(apache log)访问地址 使用：map、filter、aggregate、process、定时器、状态

实战二说明：

看视频学习之二，继续根据实战一往后进行学习

1、首先新建模块 目录结构：

同样我们模块内的pom不需要进行修改 利用主pom即可

2、数据源（这里数据源使用文件读取，展示部分内容）

3、代码展示 

首先是pojo类里边的接收类，把接收到的数据转成对象

package Bean;

public class ApachLogEvent {
    private String ip;
    private String userId;
    private Long timestamp;
    private String method;
    private String url;

    public ApachLogEvent() {
    }

    public ApachLogEvent(String ip, String userId, Long timestamp, String method, String url) {
        this.ip = ip;
        this.userId = userId;
        this.timestamp = timestamp;
        this.method = method;
        this.url = url;
    }

    public String getIp() {
        return ip;
    }

    public void setIp(String ip) {
        this.ip = ip;
    }

    public String getUserId() {
        return userId;
    }

    public void setUserId(String userId) {
        this.userId = userId;
    }

    public Long getTimestamp() {
        return timestamp;
    }

    public void setTimestamp(Long timestamp) {
        this.timestamp = timestamp;
    }

    public String getMethod() {
        return method;
    }

    public void setMethod(String method) {
        this.method = method;
    }

    public String getUrl() {
        return url;
    }

    public void setUrl(String url) {
        this.url = url;
    }

    @Override
    public String toString() {
        return "Bean.ApachLogEvent{" +
                "ip='" + ip + '\'' +
                ", userId='" + userId + '\'' +
                ", timestamp=" + timestamp +
                ", method='" + method + '\'' +
                ", url='" + url + '\'' +
                '}';
    }
}

然后是转换类，用于记录结果及部分属性

package Bean;

public class PageViewCount {
    private String url;
    private Long windowEnd;
    private Long count;

    public PageViewCount() {
    }

    public PageViewCount(String url, Long windowEnd, Long count) {
        this.url = url;
        this.windowEnd = windowEnd;
        this.count = count;
    }

    public String getUrl() {
        return url;
    }

    public void setUrl(String url) {
        this.url = url;
    }

    public Long getWindowEnd() {
        return windowEnd;
    }

    public void setWindowEnd(Long windowEnd) {
        this.windowEnd = windowEnd;
    }

    public Long getCount() {
        return count;
    }

    public void setCount(Long count) {
        this.count = count;
    }

    @Override
    public String toString() {
        return "PageViewCount{" +
                "url='" + url + '\'' +
                ", windowEnd=" + windowEnd +
                ", count=" + count +
                '}';
    }
}

最后是项目代码flink主程序

代码主要逻辑：

1、转换数据成pojo类、顺便进行数据过滤

2、开窗统计每个url在该滑动窗口的访问次数

3、再根据窗口末尾时间分组，统计该时间段的窗口内前三名的url

package Project;

import Bean.ApachLogEvent;
import Bean.PageViewCount;
import com.sun.org.apache.xerces.internal.dom.PSVIElementNSImpl;
import org.apache.commons.compress.utils.Lists;
import org.apache.flink.api.common.functions.AggregateFunction;
import org.apache.flink.api.common.state.ListState;
import org.apache.flink.api.common.state.ListStateDescriptor;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.TimeCharacteristic;
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.KeyedProcessFunction;
import org.apache.flink.streaming.api.functions.timestamps.BoundedOutOfOrdernessTimestampExtractor;
import org.apache.flink.streaming.api.functions.windowing.WindowFunction;
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.net.URL;
import java.sql.Timestamp;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Comparator;

public class HotPages {
    public static void main(String[] args) throws Exception{
        //创建环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        //设置时间语义
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
        //设置并行度
        env.setParallelism(1);

        //读取文件 转换成POJO类型
        URL resource = HotPages.class.getResource("/apache.log");
        DataStream<String> inputStream = env.readTextFile(resource.getPath());
        DataStream<ApachLogEvent> dataStream = inputStream
                .map(line -> {
                    //分隔文件内容
                    String[] fields = line.split(" ");
                    //格式化时间格式
                    SimpleDateFormat simpleDateFormat = new SimpleDateFormat("dd/MM/yyyy:HH:mm:ss");
                    Long timestamp = simpleDateFormat.parse(fields[3]).getTime();
                    return new ApachLogEvent(fields[0], fields[1],timestamp,fields[5],fields[6]);
                })
                //Watermark 设置延迟时间
                .assignTimestampsAndWatermarks(new BoundedOutOfOrdernessTimestampExtractor<ApachLogEvent>(Time.seconds(60)) {
                    @Override
                    public long extractTimestamp(ApachLogEvent apachLogEvent) {
                        return apachLogEvent.getTimestamp();
                    }
                });
        //分组开窗聚合
        //首先过滤 只要get请求即可
        SingleOutputStreamOperator<PageViewCount> windowAggStream = dataStream.filter(data -> "GET".equals(data.getMethod()))
                //按照url分组
                //.keyBy(data ->data.getUrl())
                .keyBy(ApachLogEvent::getUrl)
                //.keyBy("url")
                //开窗 10分钟统计一次 5秒钟滑动一次
                .timeWindow(Time.minutes(10), Time.seconds(5))
                .aggregate(new PageCountAgg(), new PageCountResult());
        //收集同一窗口count数据，排序输出
        DataStream<String> resultStream = windowAggStream.keyBy(PageViewCount::getWindowEnd)
                .process(new TopNHotPages(3));
        resultStream.print();
        env.execute("hot pages job");
    }
    //自定义预聚合函数
    public static class PageCountAgg implements AggregateFunction<ApachLogEvent, Long, Long>{
        @Override
        public Long createAccumulator() {
            return 0L;
        }

        @Override
        public Long add(ApachLogEvent apachLogEvent, Long aLong) {
            return aLong+1;
        }

        @Override
        public Long getResult(Long aLong) {
            return aLong;
        }

        @Override
        public Long merge(Long aLong, Long acc1) {
            return aLong+acc1;
        }
    }
    //实现自定义窗口函数
     public static class PageCountResult implements WindowFunction<Long, PageViewCount, String, TimeWindow>{
        @Override
        public void apply(String s, TimeWindow timeWindow, Iterable<Long> iterable, Collector<PageViewCount> collector) throws Exception {
            collector.collect( new PageViewCount(s, timeWindow.getEnd(), iterable.iterator().next()));;
        }
    }
    //实现自定义的窗口函数
    public static class TopNHotPages extends KeyedProcessFunction<Long, PageViewCount,String>{
        private static Integer topSize;

        public TopNHotPages(int i) {
            topSize=i;
        }

        //定义状态 保存当前所有PageViewCount到List中
        ListState<PageViewCount> pageViewCountListState;
        @Override
        public void processElement(PageViewCount pageViewCount, Context context, Collector<String> collector) throws Exception {
            pageViewCountListState.add(pageViewCount);
            //定时器+1
            context.timerService().registerProcessingTimeTimer(pageViewCount.getWindowEnd()+1);

        }

        @Override
        public void open(Configuration parameters) throws Exception {
            pageViewCountListState = getRuntimeContext().getListState(new ListStateDescriptor<PageViewCount>("page-count-list",PageViewCount.class));

        }

        @Override
        public void onTimer(long timestamp, OnTimerContext ctx, Collector<String> out) throws Exception {
            ArrayList<PageViewCount> pageViewCounts  = Lists.newArrayList(pageViewCountListState.get().iterator());

            //排序
            pageViewCounts.sort(new Comparator<PageViewCount>() {
                @Override
                public int compare(PageViewCount o1, PageViewCount o2) {
                    if(o1.getCount()>o2.getCount()){
                        //不用排序
                        return -1;
                    }else if(o1.getCount()<o2.getCount()){
                        return 1;
                    }else{
                        return 0;
                    }
                }
            });
            //格式化成字符串输出
            //排名信息格式化成string，方便打印输出
            StringBuilder resultBuilder = new StringBuilder();
            resultBuilder.append("==========");
            resultBuilder.append("窗口结束时间: ").append( new Timestamp(timestamp-1)).append("\n");
            //遍历列表，取topN输出
            for(int i = 0;i<Math.min(topSize,pageViewCounts.size());i++){
                PageViewCount currentItemViewCount = pageViewCounts.get(i);
                resultBuilder.append("NO ").append(i+1).append(":")
                        .append(" url=").append(currentItemViewCount.getUrl())
                        .append("热门度: ").append(currentItemViewCount.getCount())
                        .append("\n");
            }
            resultBuilder.append("==========\n");
            Thread.sleep(1000L);
            out.collect(resultBuilder.toString());
        }
    }
}

4、结果展示