Flink-7.Flink 广告点击黑名单

package com.ctgu.flink.project;

import com.ctgu.flink.entity.BlackInfo;
import org.apache.flink.api.common.functions.AggregateFunction;
import org.apache.flink.api.common.state.ValueState;
import org.apache.flink.api.common.state.ValueStateDescriptor;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.tuple.Tuple3;
import org.apache.flink.configuration.Configuration;
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.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.table.api.EnvironmentSettings;
import org.apache.flink.table.api.Schema;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.apache.flink.types.Row;
import org.apache.flink.util.Collector;
import org.apache.flink.util.OutputTag;


public class Flink_Sql_AdClick {
    public static void main(String[] args) throws Exception {

        long start = System.currentTimeMillis();

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);

        EnvironmentSettings settings = EnvironmentSettings
                .newInstance()
                .inStreamingMode()
                .build();

        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env, settings);

        String createSql =
                "CREATE TABLE source " +
                        "    (" +
                        "    `userId` BIGINT," +
                        "    `adId` BIGINT," +
                        "    `province` STRING," +
                        "    `city` STRING," +
                        "    `ts` BIGINT" +
                        "    )" +
                        "    WITH (" +
                        "       'connector'='filesystem'," +
                        "       'format'='csv'," +
                        "       'csv.field-delimiter'=','," +
                        "       'path'='data/AdClickLog.csv'" +
                        "    )";

        tableEnv.executeSql(createSql);

        String targetSql = "select *, ts * 1000 as `timestamp` from source";

        Table targetTable = tableEnv.sqlQuery(targetSql);

        DataStream<Row> rowDataStream = tableEnv.toDataStream(targetTable);

        Table source =
                tableEnv.fromDataStream(
                        rowDataStream,
                        Schema.newBuilder()
                                .columnByExpression("time_ltz", "TO_TIMESTAMP_LTZ(`timestamp`, 3)")
                                .watermark("time_ltz", "time_ltz - INTERVAL '5' SECOND")
                                .build());

        DataStream<Row> dataStream = tableEnv.toDataStream(source);

        SingleOutputStreamOperator<Row> filterDataStream = dataStream
                .filter(row -> row.getField("userId") != null && row.getField("adId") != null)
                .keyBy(new KeySelector<Row, Tuple2<Long, Long>>() {

            @Override
            public Tuple2<Long, Long> getKey(Row row) throws Exception {
                return new Tuple2<>((Long) row.getField("userId"), (Long) row.getField("adId"));
            }
        }).process(new MyProcessFunction(2L));

        DataStream<BlackInfo> blackList =
                filterDataStream.getSideOutput(new OutputTag<BlackInfo>("blackList"){});

        blackList.print();

        filterDataStream
                .keyBy(new KeySelector<Row, String>() {

                    @Override
                    public String getKey(Row row) throws Exception {
                        return (String) row.getField("province");
                    }
                })
                .window(TumblingEventTimeWindows.of(Time.hours(1)))
                .aggregate(new AverageAggregate(), new MyWindowFunction()).print();

        env.execute("Table SQL");

        System.out.println("耗时: " + (System.currentTimeMillis() - start) / 1000);
    }

    private static class AverageAggregate
            implements AggregateFunction<Row, Long, Long> {
        @Override
        public Long createAccumulator() {
            return 0L;
        }

        @Override
        public Long add(Row row, Long aLong) {
            return aLong + 1;
        }

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

        @Override
        public Long merge(Long a, Long b) {
            return a + b;
        }
    }

    private static class MyWindowFunction
            implements WindowFunction<Long, Tuple3<String, Long, Long>, String, TimeWindow> {

        @Override
        public void apply(String key,
                          TimeWindow timeWindow,
                          Iterable<Long> iterable,
                          Collector<Tuple3<String, Long, Long>> collector) throws Exception {
            collector.collect(new Tuple3<>(key, timeWindow.getEnd(), iterable.iterator().next()));
        }
    }

    private static class MyProcessFunction
            extends KeyedProcessFunction<Tuple2<Long, Long>, Row, Row> {

        private Long threshold;

        private ValueState<Long> clickCount;

        private ValueState<Boolean> isBlack;

        public MyProcessFunction(Long threshold) {
            this.threshold = threshold;
        }

        @Override
        public void open(Configuration parameters) throws Exception {
            clickCount = getRuntimeContext().getState(
                    new ValueStateDescriptor<>("count", Long.class, 0L));
            isBlack = getRuntimeContext().getState(
                    new ValueStateDescriptor<>("isBlack", Boolean.class, false));
        }

        @Override
        public void processElement(Row row, Context context, Collector<Row> collector) throws Exception {
            Long curCount = clickCount.value();
            if (curCount == 0) {
                Long ts = (context.timerService().currentProcessingTime() / (24 * 60 * 60 * 1000) + 1) * (24 * 60 * 60 * 1000);
                context.timerService().registerProcessingTimeTimer(ts);
            }
            if (!isBlack.value()) {
                if (curCount >= threshold) {
                    isBlack.update(true);
                    context.output(new OutputTag<BlackInfo>("blackList"){},
                            new BlackInfo((Long) row.getField("userId"),
                                    (Long) row.getField("adId"),
                                    (String) row.getField("province")));
                } else {
                    curCount += 1;
                    clickCount.update(curCount);
                    collector.collect(row);
                }
            }
        }

        @Override
        public void onTimer(long timestamp, OnTimerContext ctx, Collector<Row> out) throws Exception {
            isBlack.clear();
            clickCount.clear();
        }
    }

}

最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 203,271评论 5 476
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 85,275评论 2 380
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 150,151评论 0 336
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 54,550评论 1 273
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 63,553评论 5 365
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 48,559评论 1 281
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 37,924评论 3 395
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 36,580评论 0 257
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 40,826评论 1 297
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 35,578评论 2 320
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 37,661评论 1 329
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 33,363评论 4 318
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 38,940评论 3 307
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 29,926评论 0 19
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 31,156评论 1 259
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 42,872评论 2 349
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 42,391评论 2 342

推荐阅读更多精彩内容