Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

OB-70 - OnDemandDruidExhuast Job to support CSP Absolute Path changes_Updated #167

Open
wants to merge 2 commits into
base: release-5.1.0
Choose a base branch
from
Open

OB-70 - OnDemandDruidExhuast Job to support CSP Absolute Path changes_Updated #167

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
28d56cf
5.1 changes
Shakthieshwari Nov 28, 2022
50b0398
CSP Changes
Shakthieshwari Nov 28, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 14 additions & 5 deletions batch-models/src/main/scala/org/ekstep/analytics/exhaust/OnDemandDruidExhaustJob.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ package org.ekstep.analytics.exhaust
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, SQLContext, SparkSession}
import org.apache.spark.sql.functions.{col, when}
import org.apache.spark.sql.functions.{col, when,concat,lit}
import org.ekstep.analytics.framework.Level.{ERROR, INFO}
import org.ekstep.analytics.framework.conf.AppConf
import org.ekstep.analytics.framework.util.{CommonUtil, JSONUtils, JobLogger, RestUtil}
Expand Down Expand Up @@ -85,7 +85,7 @@ object OnDemandDruidExhaustJob extends BaseReportsJob with Serializable with IJo
updateStatus(request);
}

def druidPostProcess(data: RDD[DruidOutput], request_id: String, reportConfig: ReportConfig, storageConfig: StorageConfig, sortDfColNames: Option[List[String]])(implicit spark: SparkSession, sqlContext: SQLContext, fc: FrameworkContext, sc: SparkContext, config: JobConfig): OnDemandDruidResponse = {
def druidPostProcess(data: RDD[DruidOutput], request_id: String, reportConfig: ReportConfig, storageConfig: StorageConfig, sortDfColNames: Option[List[String]], pubAttachObj: Map[String,AnyRef])(implicit spark: SparkSession, sqlContext: SQLContext, fc: FrameworkContext, sc: SparkContext, config: JobConfig): OnDemandDruidResponse = {
val labelsLookup = reportConfig.labels
val dimFields = reportConfig.metrics.flatMap { m =>
if (m.druidQuery.dimensions.nonEmpty) m.druidQuery.dimensions.get.map(f => f.aliasName.getOrElse(f.fieldName))
Expand All @@ -100,6 +100,14 @@ object OnDemandDruidExhaustJob extends BaseReportsJob with Serializable with IJo
(df.columns).map(f1 => {
df = df.withColumn(f1, when((col(f1) === "unknown") || (col(f1) === "<NULL>"), "Null").otherwise(col(f1)))
})

if (pubAttachObj.nonEmpty && pubAttachObj.get("exists").get.asInstanceOf[Boolean] == true) {
val attachColName = pubAttachObj.get("druid_col_names").asInstanceOf[Option[List[String]]].get
attachColName.map(ev => {
df = df.withColumn(ev, concat(lit(pubAttachObj.get("base_url").get.asInstanceOf[String]), col(ev)))
})
}

df = df.dropDuplicates()
if (dataCount.value > 0) {
val metricFields = f.metrics
Expand Down Expand Up @@ -131,10 +139,10 @@ object OnDemandDruidExhaustJob extends BaseReportsJob with Serializable with IJo
new SimpleDateFormat(pattern)
}

def processRequest(request: JobRequest, reportConfig: ReportConfig, storageConfig: StorageConfig, sortDfColNames: Option[List[String]])(implicit spark: SparkSession, fc: FrameworkContext, sqlContext: SQLContext, sc: SparkContext, config: JobConfig, conf: Configuration): JobRequest = {
def processRequest(request: JobRequest, reportConfig: ReportConfig, storageConfig: StorageConfig, sortDfColNames: Option[List[String]], pubAttachObj: Map[String,AnyRef])(implicit spark: SparkSession, fc: FrameworkContext, sqlContext: SQLContext, sc: SparkContext, config: JobConfig, conf: Configuration): JobRequest = {
markRequestAsProcessing(request)
val druidData: RDD[DruidOutput] = fetchDruidData(reportConfig, true, false, false)
val result = CommonUtil.time(druidPostProcess(druidData, request.request_id, JSONUtils.deserialize[ReportConfig](JSONUtils.serialize(reportConfig)), storageConfig, sortDfColNames))
val result = CommonUtil.time(druidPostProcess(druidData, request.request_id, JSONUtils.deserialize[ReportConfig](JSONUtils.serialize(reportConfig)), storageConfig, sortDfColNames, pubAttachObj))
val response = result._2;
val failedOnDemandDruidRes = response.status.equals("FAILED")
if (failedOnDemandDruidRes) {
Expand Down Expand Up @@ -176,6 +184,7 @@ object OnDemandDruidExhaustJob extends BaseReportsJob with Serializable with IJo
val datasetConf = getDataSetDetails(requestType)
var reportConf = if(datasetConf.druid_query.nonEmpty) JSONUtils.deserialize[Map[String,AnyRef]](datasetConf.druid_query.get) else JSONUtils.deserialize[Map[String,AnyRef]](AppConf.getConfig("druid_query." + requestType))
val sortDfColNames = reportConf.get("sort").asInstanceOf[Option[List[String]]]
val pubAttachObj = reportConf.getOrElse("publicAttachments",Map()).asInstanceOf[Map[String,AnyRef]]
// Date Range with dynamic Start Date and End Date
if (requestParamsBody.contains("start_date")){
val updatedInterval = reportConf.getOrElse("dateRange",None).asInstanceOf[Map[String,AnyRef]].getOrElse("interval",None).asInstanceOf[Map[String,AnyRef]]
Expand All @@ -200,7 +209,7 @@ object OnDemandDruidExhaustJob extends BaseReportsJob with Serializable with IJo
val reportConfig = JSONUtils.deserialize[ReportConfig](JSONUtils.serialize(updatedReportConf))
val storageConfig = getStorageConfig(config, AppConf.getConfig("collection.exhaust.store.prefix"))
JobLogger.log("Total Requests are ", Some(Map("jobId" -> jobId, "totalRequests" -> requests.length)), INFO)
val res = processRequest(request, reportConfig, storageConfig, sortDfColNames)
val res = processRequest(request, reportConfig, storageConfig, sortDfColNames,pubAttachObj)
JobLogger.log("Request is ",Some(request),INFO)
JobLogger.log("Report Config is ",Some(reportConfig),INFO)
JobLogger.log("The Request is processed. Pending zipping", Some(Map("requestId" -> request.request_id, "timeTaken" -> res.execution_time,
Expand Down
Loading