Flink实时仓库-DWD层(处理复杂数据-流和表的装换处理)模板代码

单有复制的数据处理的时候，我们可以把表装换成流来处理

public class KafkaUtil {
    private final static String BOOTSTRAP_SERVERS="master:9092";

    
    public static String getKafkaDDL(String topic, String groupId) {

        return " with ('connector' = 'kafka', " +
                " 'topic' = '" + topic + "'," +
                " 'properties.bootstrap.servers' = '" + BOOTSTRAP_SERVERS + "', " +
                " 'properties.group.id' = '" + groupId + "', " +
                " 'format' = 'json', " +
                " 'scan.startup.mode' = 'group-offsets')";
    }

    
    public static String getUpsertKafkaDDL(String topic) {

        return "WITH ( " +
                "  'connector' = 'upsert-kafka', " +
                "  'topic' = '" + topic + "', " +
                "  'properties.bootstrap.servers' = '" + BOOTSTRAP_SERVERS + "', " +
                "  'key.format' = 'json', " +
                "  'value.format' = 'json' " +
                ")";
    }
}

@Data
public class CouponUseOrderBean {
    // 优惠券领用记录 id
    String id;

    // 优惠券 id
    String coupon_id;

    // 用户 id
    String user_id;

    // 订单 id
    String order_id;

    // 优惠券使用日期（下单）
    String date_id;

    // 优惠券使用时间（下单）
    String using_time;

    // 历史数据
    String old;

    // 时间戳
    String ts;
}

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

        // TODO 1. 环境准备
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(4);
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

        // TODO 2. 状态后端设置
        env.enableCheckpointing(3000L, CheckpointingMode.EXACTLY_ONCE);
        env.getCheckpointConfig().setCheckpointTimeout(60 * 1000L);
        env.getCheckpointConfig().setMinPauseBetweenCheckpoints(3000L);
        env.getCheckpointConfig().enableExternalizedCheckpoints(
                CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION
        );
        env.setRestartStrategy(RestartStrategies.failureRateRestart(
                3, Time.days(1), Time.minutes(1)
        ));
        env.setStateBackend(new HashMapStateBackend());
        env.getCheckpointConfig().setCheckpointStorage(
                "hdfs://hadoop102:8020/ck"
        );
        System.setProperty("HADOOP_USER_NAME", "atguigu");

        // TODO 3. 从 Kafka 读取业务数据，封装为 Flink SQL 表
        tableEnv.executeSql("create table `topic_db` ( " +
                "`database` string, " +
                "`table` string, " +
                "`data` map, " +
                "`type` string, " +
                "`old` string, " +
                "`ts` string " +
                ")" + KafkaUtil.getKafkaDDL("topic_db", "dwd_tool_coupon_order"));

        // TODO 4. 读取优惠券领用表数据，封装为流
        Table couponUseOrder = tableEnv.sqlQuery("select " +
                "data['id'] id, " +
                "data['coupon_id'] coupon_id, " +
                "data['user_id'] user_id, " +
                "data['order_id'] order_id, " +
                "date_format(data['using_time'],'yyyy-MM-dd') date_id, " +
                "data['using_time'] using_time, " +
                "`old`, " +
                "ts " +
                "from topic_db " +
                "where `table` = 'coupon_use' " +
                "and `type` = 'update' ");
        DataStream couponUseOrderDS = tableEnv.toAppendStream(couponUseOrder, CouponUseOrderBean.class);

        // TODO 5. 过滤满足条件的优惠券下单数据，封装为表
        SingleOutputStreamOperator filteredDS = couponUseOrderDS.filter(
                couponUseOrderBean -> {
                    String old = couponUseOrderBean.getOld();
                    if(old != null) {
                        Map oldMap = JSON.parseObject(old, Map.class);
                        Set changeKeys = oldMap.keySet();
                        return changeKeys.contains("using_time");
                    }
                    return true;
                }
        );
        Table resultTable = tableEnv.fromDataStream(filteredDS);
        tableEnv.createTemporaryView("result_table", resultTable);

        // TODO 6. 建立 Upsert-Kafka dwd_tool_coupon_order 表
        tableEnv.executeSql("create table dwd_tool_coupon_order( " +
                "id string, " +
                "coupon_id string, " +
                "user_id string, " +
                "order_id string, " +
                "date_id string, " +
                "order_time string, " +
                "ts string, " +
                "primary key(id) not enforced " +
                ")" + KafkaUtil.getUpsertKafkaDDL("dwd_tool_coupon_order"));

        // TODO 7. 将数据写入 Upsert-Kafka 表
        tableEnv.executeSql("" +
                "insert into dwd_tool_coupon_order select " +
                "id, " +
                "coupon_id, " +
                "user_id, " +
                "order_id, " +
                "date_id, " +
                "using_time order_time, " +
                "ts from result_table");

        env.execute();
    }
}