【Flink】Flink 数据处理流程及 scala 代码实现

叁歲伎倆 2022-10-24 13:29 306阅读 0赞

### 1、Flink 启动运行流程 ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center][]

### 2、assignAscendingTimestamps 算子运行流程 ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center 1][]

### 3、assignTimestampsAndWatermarks 算子运行流程 ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center 2][]

### 4、aggregate 预聚合方法执行流程 ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center 3][]

### 5、热门商品点击 TopN ###

## HotItems.scala
    
    import java.sql.Timestamp
    import java.util.Properties
    
    import org.apache.flink.api.common.functions.AggregateFunction
    import org.apache.flink.api.common.serialization.SimpleStringSchema
    import org.apache.flink.api.common.state.{ ListState, ListStateDescriptor}
    import org.apache.flink.api.java.tuple.{ Tuple, Tuple1}
    import org.apache.flink.configuration.Configuration
    import org.apache.flink.streaming.api.TimeCharacteristic
    import org.apache.flink.streaming.api.functions.KeyedProcessFunction
    import org.apache.flink.streaming.api.scala._
    import org.apache.flink.streaming.api.scala.function.WindowFunction
    import org.apache.flink.streaming.api.windowing.time.Time
    import org.apache.flink.streaming.api.windowing.windows.TimeWindow
    import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer
    import org.apache.flink.util.Collector
    
    import scala.collection.mutable.ListBuffer
    
    // 输入数据
    case class UserBehavior( userId: Long, itemId: Long, categoryId: Int, behavior: String, timestamp: Long )
    // 输出数据
    case class ItemViewCount( itemId: Long, windowEnd: Long, count: Long )
    
    object HotItems { 
      def main(args: Array[String]): Unit = { 
    
        // val properties = new Properties()
    
        // flink的流执行环境
        val env = StreamExecutionEnvironment.getExecutionEnvironment
    
        // 设定Time类型为EventTime
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
        // 并发为1
        env.setParallelism(1)
    
        // 获得数据源的文件
        val stream = env
          .readTextFile("D:\\MyIdeaProjects\\UserBehaviorAnalysis\\HotItemsAnalysis\\src\\main\\resources\\UserBehavior.csv")
    
          // 获得文件中的每一行记录
          .map(line => { 
            val linearray = line.split(",")
            UserBehavior( linearray(0).toLong, linearray(1).toLong, linearray(2).toInt, linearray(3), linearray(4).toLong )
          })
    
          // 指定时间戳
          .assignAscendingTimestamps(_.timestamp * 1000)
          // 进行过滤，只获得pv行为的数据
          .filter(_.behavior == "pv")
          // 按照商品id进行分流
          .keyBy("itemId")
          // 滑动窗口
          .timeWindow(Time.hours(1), Time.minutes(5))
          // 预聚合，第一个参数：求和，第二个参数：每个商品在每个窗口的点击量
          .aggregate( new CountAgg(), new WindowResultFunction() )
          // 不同商品但同一窗口的数据在一起
          .keyBy("windowEnd")
          // 在自定义函数中进行业务逻辑处理
          .process( new TopNHotItems(3))
          .print()
    
    
        env.execute("Hot Items Job")
      }
    
      // 统计出总数
      class CountAgg extends AggregateFunction[UserBehavior, Long, Long]{ 
        override def add(value: UserBehavior, accumulator: Long): Long = accumulator + 1
    
        override def createAccumulator(): Long = 0L
    
        override def getResult(accumulator: Long): Long = accumulator
    
        override def merge(a: Long, b: Long): Long = a + b
      }
    
      // 获得某个商品在一个窗口中的总数
      class WindowResultFunction extends WindowFunction[Long, ItemViewCount, Tuple, TimeWindow]{ 
        override def apply(key: Tuple, window: TimeWindow, input: Iterable[Long], out: Collector[ItemViewCount]): Unit = { 
          val itemId: Long = key.asInstanceOf[Tuple1[Long]].f0
          val count = input.iterator.next()
          out.collect(ItemViewCount(itemId, window.getEnd, count))
        }
      }
    
      // 求某个窗口中前N名的热门点击商品
      class TopNHotItems(topSize: Int) extends KeyedProcessFunction[Tuple, ItemViewCount, String]{ 
    
        // ListState用于保存状态
        private var itemState: ListState[ItemViewCount] = _
    
        override def open(parameters: Configuration): Unit = { 
          super.open(parameters)
    
          val itemStateDesc = new ListStateDescriptor[ItemViewCount]("itemState", classOf[ItemViewCount])
          // 创建ListState对象
          itemState = getRuntimeContext.getListState(itemStateDesc)
        }
    
        // 注册定时器
        override def processElement(i: ItemViewCount, context: KeyedProcessFunction[Tuple, ItemViewCount, String]#Context, collector: Collector[String]): Unit = { 
          // 添加本窗口中的所有数据
          itemState.add(i)
    
          // windowEnd+1ms作为关闭窗口的触发时间，1ms
          context.timerService.registerEventTimeTimer( i.windowEnd + 1 )
        }
    
        // 到了windowEnd+1时间后，执行onTimer方法
        override def onTimer(timestamp: Long, ctx: KeyedProcessFunction[Tuple, ItemViewCount, String]#OnTimerContext, out: Collector[String]): Unit = { 
    
          val allItems: ListBuffer[ItemViewCount] = ListBuffer()
          import  scala.collection.JavaConversions._
    
          // 将ListStae对象的数据存入到ListBuffer对象
          for(item <- itemState.get){ 
            allItems += item
          }
    
          // 清除状态中的数据
          itemState.clear()
    
          // 按count进行降序排序，获得前3名的数据
          val sortedItems = allItems.sortBy(_.count)(Ordering.Long.reverse).take(topSize)
    
          // 格式化，打印
          val result: StringBuilder = new StringBuilder
          result.append("====================================\n")
          result.append("时间：").append(new Timestamp(timestamp - 1)).append("\n")
    
          for( i <- sortedItems.indices ){ 
            val currentItem: ItemViewCount = sortedItems(i)
    
            result.append("No").append(i+1).append(":")
              .append(" 商品ID=").append(currentItem.itemId)
              .append(" 浏览量=").append(currentItem.count).append("\n")
          }
          result.append("====================================\n\n")
    
          // 控制输出频率，模拟实时滚动
          Thread.sleep(1000)
          out.collect(result.toString)
        }
      }
    }

## KafkaProducer.scala
    
    import java.util.Properties
    import org.apache.kafka.clients.producer.{ KafkaProducer, ProducerRecord}
    
    object KafkaProducer { 
    
      def main(args: Array[String]): Unit = { 
        writeToKafka("hotitems")
      }
    
      def writeToKafka(topic: String): Unit = { 
        val props = new Properties()
        props.put("bootstrap.servers", "localhost:9092")
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer")
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer")
        val producer = new KafkaProducer[String, String](props)
        val bufferedSource = io.Source.fromFile("D:\\Projects\\BigData\\UserBehaviorAnalysis\\HotItemsAnalysis\\src\\main\\resources\\UserBehavior.csv")
        for (line <- bufferedSource.getLines) { 
          val record = new ProducerRecord[String, String](topic, line)
          producer.send(record)
        }
        producer.close()
      }
    }

### 6、登录失败检测 ###

## LoginFailWithCep.scala
    
    package com.gupao.LoginFailDetect
    
    import org.apache.flink.cep.scala.CEP
    import org.apache.flink.cep.scala.pattern.Pattern
    import org.apache.flink.streaming.api.TimeCharacteristic
    import org.apache.flink.streaming.api.scala._
    import org.apache.flink.streaming.api.windowing.time.Time
    
    object LoginFailWithCep { 
      def main(args: Array[String]): Unit = { 
        val env = StreamExecutionEnvironment.getExecutionEnvironment
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
        env.setParallelism(1)
    
        val loginStream = env.fromCollection(List(
          LoginEvent(1, "192.168.0.1", "fail", 1558430832),
          LoginEvent(1, "192.168.0.2", "fail", 1558430843),
          LoginEvent(1, "192.168.0.3", "fail", 1558430844),
          LoginEvent(2, "192.168.0.3", "fail", 1558430845),
          LoginEvent(2, "192.168.10.10", "success", 1558430845)
        ))
          .assignAscendingTimestamps(_.eventTime * 1000)
          .keyBy(_.userId)
    
    
        // 定义匹配模式（规则）
        // begin：第一次，where：出现fail
        // next：紧接着第二次出现fail
        // times：出现一次
        // within：表示是在2秒内
        val loginFailPattern = Pattern.begin[LoginEvent]("begin").where(_.eventType == "fail")
          .next("next").where(_.eventType == "fail")
          .times(1)
          .within(Time.seconds(2))
    
        // 获得模式流
        val patternStream = CEP.pattern( loginStream, loginFailPattern )
    
        import scala.collection.Map
    
        // select方法分别获得符合匹配的begin和next值
        // 输出符合需求的结果
        val loginFailDataStream = patternStream.select(
          ( pattern: Map[String, Iterable[LoginEvent]] ) =>{ 
            val begin = pattern.getOrElse("begin", null).iterator.next()
            val next = pattern.getOrElse("next", null).iterator.next()
            (next.userId, begin.ip, next.ip, next.eventType)
          }
        )
          .print()
    
        env.execute("Login Fail Detect Job")
      }
    }

## LoginFail.scala
    
    package com.gupao.LoginFailDetect
    
    import org.apache.flink.api.common.state.{ ListState, ListStateDescriptor}
    import org.apache.flink.streaming.api.TimeCharacteristic
    import org.apache.flink.streaming.api.functions.KeyedProcessFunction
    import org.apache.flink.streaming.api.scala._
    import org.apache.flink.util.Collector
    import scala.collection.mutable.ListBuffer
    
    case class LoginEvent( userId: Long, ip: String, eventType: String, eventTime: Long )
    
    object LoginFail { 
      def main(args: Array[String]): Unit = { 
        val env = StreamExecutionEnvironment.getExecutionEnvironment
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
        env.setParallelism(1)
    
        val loginStream = env.fromCollection(List(
          LoginEvent(1, "192.168.0.1", "fail", 1558430832),
          LoginEvent(1, "192.168.0.2", "fail", 1558430843),
          LoginEvent(1, "192.168.0.3", "fail", 1558430844),
          LoginEvent(2, "192.168.0.3", "fail", 1558430845),
          LoginEvent(2, "192.168.10.10", "success", 1558430845)
        ))
          .assignAscendingTimestamps(_.eventTime * 1000)
          .filter(_.eventType == "fail")
          .keyBy(_.userId)
          .process( new MatchFunction() )
          .print()
    
        env.execute("Login Fail Detect Job")
      }
    
    
      class MatchFunction extends KeyedProcessFunction[Long, LoginEvent, LoginEvent]{ 
    
        lazy val loginState: ListState[LoginEvent] = getRuntimeContext.getListState( new ListStateDescriptor[LoginEvent]("loginState", classOf[LoginEvent]) )
    
        override def processElement(i: LoginEvent, context: KeyedProcessFunction[Long, LoginEvent, LoginEvent]#Context, collector: Collector[LoginEvent]): Unit = { 
          loginState.add(i)
          context.timerService().registerEventTimeTimer( i.eventTime * 1000 + 2 * 1000 )
        }
    
    
        override def onTimer(timestamp: Long, ctx: KeyedProcessFunction[Long, LoginEvent, LoginEvent]#OnTimerContext, out: Collector[LoginEvent]): Unit = { 
          val allLogins: ListBuffer[LoginEvent] = ListBuffer()
          import scala.collection.JavaConversions._
          for( login <- loginState.get() ){ 
            allLogins += login
          }
          loginState.clear()
    
          if(allLogins.length > 1){ 
            out.collect(allLogins.head)
          }
        }
      }
    }

### 7、网络流量分析 ###

## NetworkTraffic.scala
    
    package com.gupao.NetWorkTrafficAnalysis
    
    import java.sql.Timestamp
    import java.text.SimpleDateFormat
    
    import org.apache.flink.api.common.functions.AggregateFunction
    import org.apache.flink.api.common.state.{ ListState, ListStateDescriptor}
    import org.apache.flink.streaming.api.TimeCharacteristic
    import org.apache.flink.streaming.api.functions.KeyedProcessFunction
    import org.apache.flink.streaming.api.functions.timestamps.BoundedOutOfOrdernessTimestampExtractor
    import org.apache.flink.streaming.api.scala._
    import org.apache.flink.streaming.api.scala.function.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 scala.collection.mutable.ListBuffer
    
    
    // 输入数据类型
    case class ApacheLogEvent( ip: String, userId: String, eventTime: Long, method: String, url: String )
    
    // 输出数据类型
    case class UrlViewCount( url: String, windowEnd: Long, count: Long )
    
    object NetworkTraffic { 
    
      def main(args: Array[String]): Unit = { 
        val env = StreamExecutionEnvironment.getExecutionEnvironment
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
        env.setParallelism(1)
    
        val stream = env
          .readTextFile("D:\\MyIdeaProjects\\UserBehaviorAnalysis\\NetworkTrafficAnalysis\\src\\main\\resources\\apache.log")
          .map(line =>{ 
            val linearray = line.split(" ")
    
            val simpleDateFormat = new SimpleDateFormat("dd/MM/yyyy:HH:mm:ss")
            // 转换为时间戳
            val timestamp = simpleDateFormat.parse(linearray(3)).getTime
            ApacheLogEvent( linearray(0), linearray(1), timestamp, linearray(5), linearray(6) )
          })
    
          // 设置时间戳和watermark
          .assignTimestampsAndWatermarks(new BoundedOutOfOrdernessTimestampExtractor[ApacheLogEvent](Time.seconds(10)) { 
              override def extractTimestamp(t: ApacheLogEvent): Long = { 
                t.eventTime
          }
        })
          .filter(_.method == "GET")
          .keyBy(_.url)
          .timeWindow(Time.minutes(1), Time.seconds(5))
          .aggregate( new CountAgg(), new WindowResultFunction() )
          .keyBy(_.windowEnd)
          .process( new TopNHotUrls(5) )
          .print()
    
        env.execute("Network Traffic Analysis Job")
      }
    
      class CountAgg extends AggregateFunction[ApacheLogEvent, Long, Long]{ 
        override def add(value: ApacheLogEvent, accumulator: Long): Long = accumulator + 1
        override def createAccumulator(): Long = 0L
        override def getResult(accumulator: Long): Long = accumulator
        override def merge(a: Long, b: Long): Long = a + b
      }
    
      class WindowResultFunction extends WindowFunction[Long, UrlViewCount, String, TimeWindow]{ 
        override def apply(key: String, window: TimeWindow, input: Iterable[Long], out: Collector[UrlViewCount]): Unit = { 
          val url: String = key
          val count = input.iterator.next()
          out.collect(UrlViewCount(url, window.getEnd, count))
        }
      }
    
    
      class TopNHotUrls(topSize: Int) extends KeyedProcessFunction[Long, UrlViewCount, String]{ 
    
        lazy val urlState: ListState[UrlViewCount] = getRuntimeContext.getListState( new ListStateDescriptor[UrlViewCount]( "urlState", classOf[UrlViewCount] ) )
    
        override def processElement(i: UrlViewCount, context: KeyedProcessFunction[Long, UrlViewCount, String]#Context, collector: Collector[String]): Unit = { 
    
          urlState.add(i)
    
          // 设置超过watermark就触发计算
          context.timerService().registerEventTimeTimer(i.windowEnd + 10 * 1000)
        }
    
    
        override def onTimer(timestamp: Long, ctx: KeyedProcessFunction[Long, UrlViewCount, String]#OnTimerContext, out: Collector[String]): Unit = { 
    
          val allUrlViews: ListBuffer[UrlViewCount] = ListBuffer()
          import scala.collection.JavaConversions._
          for( urlView <- urlState.get() ){ 
            allUrlViews += urlView
          }
    
          urlState.clear()
    
          val sortedUrlViews = allUrlViews.sortBy(_.count)(Ordering.Long.reverse).take(topSize)
    
          var result: StringBuilder = new StringBuilder
          result.append("====================================\n")
          result.append("时间: ").append(new Timestamp(timestamp - 10 * 1000)).append("\n")
    
          for (i <- sortedUrlViews.indices) { 
            val currentUrlView: UrlViewCount = sortedUrlViews(i)
    
            result.append("No").append(i+1).append(":")
              .append(" URL=").append(currentUrlView.url)
              .append(" 流量=").append(currentUrlView.count).append("\n")
          }
          result.append("====================================\n\n")
    
          Thread.sleep(1000)
          out.collect(result.toString())
    
        }
      }
    }

### 8、订单超时检测 ###

## OrderTimeout.scala
    
    package com.gupao.OrderTimeoutDetect
    
    import org.apache.flink.cep.scala.CEP
    import org.apache.flink.cep.scala.pattern.Pattern
    import org.apache.flink.streaming.api.TimeCharacteristic
    import org.apache.flink.streaming.api.scala._
    import org.apache.flink.streaming.api.windowing.time.Time
    
    
    // 订单事件流样例类
    case class OrderEvent( orderId: Long, eventType: String, eventTime: Long )
    // 输出结果的样例类
    case class OrderResult( orderId: Long, eventType: String )
    
    object OrderTimeout { 
      def main(args: Array[String]): Unit = { 
        val env = StreamExecutionEnvironment.getExecutionEnvironment
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
        env.setParallelism(1)
    
        val orderEventStream = env.fromCollection(List(
          OrderEvent(1, "create", 1558430842),
          OrderEvent(2, "create", 1558430843),
          OrderEvent(1, "pay", 1558436842),
          OrderEvent(2, "pay", 1558430844)
        ))
          .assignAscendingTimestamps(_.eventTime * 1000)
          .keyBy(_.orderId)
    
    
        // followedBy：比较宽松的连续性
        // within：创建订单和支付之间在15分钟之内
        val orderPayPattern = Pattern.begin[OrderEvent]("begin").where(_.eventType == "create")
          .followedBy("follow").where(_.eventType == "pay")
          .within(Time.minutes(15))
    
    
        // 定义一个输出标签，用于标题侧输出流
        val orderTimoutOutput = OutputTag[OrderResult]("orderTimeout")
    
        // 获得模式流
        val patternStream = CEP.pattern( orderEventStream, orderPayPattern )
    
        import scala.collection.Map
    
        val completedResultDataStream = patternStream.select(orderTimoutOutput)(
          // orderTimoutOutput部分为侧输出流的超时部分
          ( pattern: Map[String, Iterable[OrderEvent]], timestamp: Long ) => { 
            val timeoutOrderId = pattern.getOrElse("begin", null).iterator.next().orderId
            println(timestamp)
            OrderResult( timeoutOrderId, "timeout" )
          }
          // 主输出流：符合规则
        )(
    
          ( pattern: Map[String, Iterable[OrderEvent]] ) => { 
            val payedOrderId = pattern.getOrElse("follow", null).iterator.next().orderId
            OrderResult( payedOrderId, "success" )
          }
        )
        // 打印匹配输出流即未超时部分
        completedResultDataStream.print()
    
    
        // 打印不匹配输出流即超时部分
        val timeoutResultDataStream = completedResultDataStream.getSideOutput(orderTimoutOutput)
        timeoutResultDataStream.print()
    
        env.execute("Order Timeout Detect Job")
      }
    }

## SqlDemo.scala
    
    package com.gupao.OrderTimeoutDetect
    
    import org.apache.flink.api.scala.ExecutionEnvironment
    import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
    import org.apache.flink.table.api.{ Table, TableEnvironment}
    import org.apache.flink.streaming.api.scala._
    import org.apache.flink.table.api.scala._
    
    
    object SqlDemo { 
    
      def main(args: Array[String]): Unit = { 
        // 得到批环境
        val env = ExecutionEnvironment.getExecutionEnvironment
    
    
        val dataSet = env.fromElements((1,"小明",15,"男",1500),(2,"小王",45,"男",4000),(3,"小李",25,"女",800),(4,"小慧",35,"女",500))
        val dataSetGrade = env.fromElements((1,"语文",100),(2,"数学",80),(1,"外语",50) )
    
        // 得到Table环境
        val tableEnv = TableEnvironment.getTableEnvironment(env)
        // 注册table，表名是user1和grade，也就是用户表和成绩表，
        // 用户表的字段名分别是第三个参数中的id,'name,'age,'sex,'salary，也就是用户id、用户姓名、用户性别、用户薪资，
        // 成绩表的字段是'userId,'name,'fraction，也就是用户id、科目名、分数
    
        tableEnv.registerDataSet("user1",dataSet,'id,'name,'age,'sex,'salary)
        tableEnv.registerDataSet("grade",dataSetGrade,'userId,'name,'fraction)
        // 我们这里为了展示flink的sql应用，获得的是一些getSideOutput测试数据，
        // 在生产环境中，更多的是从不同的文件、数据库以及消息系统进行读取，
        // 比如比较常见的从消息系统kafka中获得数据，
        // 然后registerTableSource注册输入表也就是源数据表，然后用registerTableSink来获得目标数据表，
        // 再用比如sqlUpdate方法，执行sql语句，
        // 类似insert into 目标表 select 。。。 from 源表 where 。。。，来获得我们想要的数据，
        // 再对目标表进行任何的sql操作，就是类似下面的这些sql操作，
    
    
        // 查询
        tableEnv.sqlQuery(s"select name,age FROM user1")
          .first(100).print()
    
        // 给表起别名
        tableEnv.sqlQuery(s"select t1.name,t1.age FROM user1 as t1")
          .first(100).print()
    
        // 给列起别名
        tableEnv.sqlQuery(s"select name a,age as b FROM user1 ")
          .first(100).print()
    
        // 降序排序，取前3位
        tableEnv.sqlQuery(s"select name,age FROM user1 ORDER BY age desc LIMIT 3 ")
          .first(100).print()
    
        // where条件，取性别为女的
        tableEnv.sqlQuery(s"select name,age,sex FROM user1 where sex = '女'")
          .first(100).print()
    
        // 查询年龄范围
        tableEnv.sqlQuery(s"select name,age,sex FROM user1 where age between 20 and 35")
          .first(100).print()
    
        // 求薪平均年龄，其余如max、min、sum、count等汇总同理
        tableEnv.sqlQuery(s"select avg(age) FROM user1")
          .first(100).print()
    
        // 求女性和男性的平均工资
        tableEnv.sqlQuery(s"select sex,sum(salary) FROM user1 group by sex")
          .first(100).print()
    
        // 分组统计，哪个性别的总工资大于1500
        tableEnv.sqlQuery(s"select sex,sum(salary) FROM user1 group by sex having sum(salary) >1500")
          .first(100).print()
    
        // 去重
        tableEnv.sqlQuery("select distinct sex FROM user1 ")
          .first(100).print()
    
        // 内连接，两个表，输出user1的所有字段，以及grade表中的科目名和分数
        // tableEnv.sqlQuery("select * FROM user1 INNER JOIN grade on `user`.id = grade.userId ")
        tableEnv.sqlQuery("select u.*,g.name,g.fraction FROM user1 u INNER JOIN grade g on u.id = g.userId ")
          .first(100).print()
      }
    }

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center]: /images/20221024/9075def9f1914eea81fead13f64791ea.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20221024/98c9b3ef13aa4521a321d7bfbfca47c5.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center 2]: /images/20221024/e492c9ea760c410ba2115ef3c5d46e6e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center 3]: /images/20221024/29c08503bbe4460cb84439bdd7bf2d75.png