0

我一直在尝试使用新的样条线 jsr 运行以下代码：za.co.absa.spline.agent.spark:spark-3.0-spline-agent-bundle_2.12:0.6.0 但遇到了特定于 UserExtraMetadataProvider 的错误在较新的版本中已弃用。我还尝试使用第一个代码块下方显示的代码将 UserExtraMetadataProvider 替换为 UserExtraAppendingPostProcessingFilter，但仍然出现错误。您能否验证并分享如何使用新的样条线束正确编写后处理过滤器代码。

%scala
import za.co.absa.spline.harvester.conf.StandardSplineConfigurationStack
import za.co.absa.spline.harvester.extra.UserExtraMetadataProvider
import za.co.absa.spline.harvester.HarvestingContext
import org.apache.commons.configuration.Configuration
import za.co.absa.spline.harvester.SparkLineageInitializer._
import za.co.absa.spline.harvester.conf.DefaultSplineConfigurer
import za.co.absa.spline.producer.model._
import scala.util.parsing.json.JSON

val splineConf: Configuration = StandardSplineConfigurationStack(spark)

spark.enableLineageTracking(new DefaultSplineConfigurer(splineConf) {
//override protected def userExtraMetadataProvider = new UserExtraMetaDataProvider {
//val test = dbutils.notebook.getContext.notebookPath
val notebookInformationJson = dbutils.notebook.getContext.toJson
val outerMap = JSON.parseFull(notebookInformationJson).getOrElse(0).asInstanceOf[Map[String,String]]
val tagMap = outerMap("tags").asInstanceOf[Map[String,String]]

val extraContextMap = outerMap("extraContext").asInstanceOf[Map[String,String]]
val notebookPath = extraContextMap("notebook_path").split("/")

val notebookURL = tagMap("browserHostName")+"/?o="+tagMap("orgId")+tagMap("browserHash")
val user = tagMap("user")
val name = notebookPath(notebookPath.size-1)

val notebookInfo = Map("notebookURL" -> notebookURL,
"user" -> user,
"name" -> name,
"mounts" -> dbutils.fs.ls("/mnt").map(_.path),
"timestamp" -> System.currentTimeMillis)
val notebookInfoJson = scala.util.parsing.json.JSONObject(notebookInfo)

override protected def userExtraMetadataProvider: UserExtraMetadataProvider = new UserExtraMetadataProvider {
override def forExecEvent(event: ExecutionEvent, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar1")
override def forExecPlan(plan: ExecutionPlan, ctx: HarvestingContext): Map[String, Any] = Map("notebookInfo" -> notebookInfoJson) // tilføj mount info til searchAndReplace denne funktion indeholder infoen
override def forOperation(op: ReadOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar3")
override def forOperation(op: WriteOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar4")
override def forOperation(op: DataOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar5")
}
})

这是仍然有错误的更新代码

%scala
import za.co.absa.spline.harvester.conf.StandardSplineConfigurationStack
import za.co.absa.spline.harvester.extra.UserExtraMetadataProvider
import za.co.absa.spline.harvester.HarvestingContext
import org.apache.commons.configuration.Configuration
import za.co.absa.spline.harvester.SparkLineageInitializer._
import za.co.absa.spline.harvester.conf.DefaultSplineConfigurer
import za.co.absa.spline.producer.model._
import play.api.libs.json._

val splineConf: Configuration = StandardSplineConfigurationStack(spark)

spark.enableLineageTracking(new DefaultSplineConfigurer(splineConf) {
val notebookInformationJson = Json.toJson(dbutils.notebook.getContext)
val outerMap = Json.toJson(notebookInformationJson).getOrElse(0).asInstanceOf[Map[String,String]]
val tagMap = outerMap("tags").asInstanceOf[Map[String,String]]

val extraContextMap = outerMap("extraContext").asInstanceOf[Map[String,String]]
val notebookPath = extraContextMap("notebook_path").split("/")

val notebookURL = tagMap("browserHostName")+"/?o="+tagMap("orgId")+tagMap("browserHash")
val user = tagMap("user")
val name = notebookPath(notebookPath.size-1)

val notebookInfo = Map("notebookURL" -> Json.toJson(notebookURL),
"user" -> Json.toJson(user),
"name" -> Json.toJson(name),
"mounts" -> Json.toJson(dbutils.fs.ls("/mnt").map(_.path)),
"timestamp" -> Json.toJson(System.currentTimeMillis))

val notebookInfoJson = Json.toJson(notebookInfo)

def userExtraMetadataProvider: UserExtraAppendingPostProcessingFilter
= new UserExtraAppendingPostProcessingFilter

{
def processExecutionEvent(event: ExecutionEvent, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar1")
def processExecutionPlan (plan: ExecutionPlan, ctx: HarvestingContext): Map[String, Any] = Map("notebookInfo" -> notebookInfoJson)
def processReadOperation(op: ReadOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar3")
def processWriteOperation(op: WriteOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar4")
def processDataOperation(op: DataOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar5")
}
})

这是错误：

    command-2044409137370707:12: error: not enough arguments for constructor DefaultSplineConfigurer: (sparkSession: org.apache.spark.sql.SparkSession, userConfiguration: org.apache.commons.configuration.Configuration)za.co.absa.spline.harvester.conf.DefaultSplineConfigurer.
Unspecified value parameter userConfiguration.
spark.enableLineageTracking(new DefaultSplineConfigurer(splineConf) {
                                ^
command-2044409137370707:32: error: not found: type UserExtraAppendingPostProcessingFilter
 def userExtraMetadataProvider: UserExtraAppendingPostProcessingFilter
                                ^
command-2044409137370707:33: error: not found: type UserExtraAppendingPostProcessingFilter
 = new UserExtraAppendingPostProcessingFilter
       ^
command-2044409137370707:37: error: not found: type ExecutionEvent
    def processExecutionEvent(event: ExecutionEvent, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar1")
                                     ^
command-2044409137370707:38: error: not found: type ExecutionPlan
    def processExecutionPlan (plan: ExecutionPlan, ctx: HarvestingContext): Map[String, Any] = Map("notebookInfo" -> notebookInfoJson)
                                    ^
command-2044409137370707:39: error: not found: type ReadOperation
    def processReadOperation(op: ReadOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar3")
                                 ^
command-2044409137370707:40: error: not found: type WriteOperation
    def processWriteOperation(op: WriteOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar4")
                                  ^
command-2044409137370707:41: error: not found: type DataOperation
    def processDataOperation(op: DataOperation, ctx: HarvestingContext): Map[String, Any] = Map("foo" -> "bar5")
                                 ^
command-2044409137370707:36: warning: a pure expression does nothing in statement position; multiline expressions may require enclosing parentheses
  {
  ^
4

1 回答 1

0

由于以下几个原因，您的代码无法编译：

  1. 您错过了一些导入（错误日志清楚地表明了这一点）：

    import za.co.absa.spline.producer.model.v1_1._
import za.co.absa.spline.harvester.extra.UserExtraAppendingPostProcessingFilter

  2. 额外元数据提供者的正确签名如下：

    protected def maybeUserExtraMetadataProvider: Option[UserExtraMetadataProvider]

  3. UserExtraAppendingPostProcessingFilter只是已弃用的适配器UserExtraMetadataProvider。所以你仍然需要创建一个实例：

    new UserExtraAppendingPostProcessingFilter(new UserExtraMetadataProvider() { 
  // ???
})

请注意，我们正在开发一种用于捕获额外元数据的声明式解决方案，以便可以在配置中定义大多数规则和值，并且几乎不需要编码。见https://github.com/AbsaOSS/spline-spark-agent/issues/169

现在只需使用UserExtraMetadataProvider

有关更多详细信息，请参阅https://github.com/AbsaOSS/spline-spark-agent/discussions/228#discussioncomment-819620

于 2021-10-12T20:46:13.973 回答