chore: Scala client for certified events

.gitignore

@@ -87,4 +87,3 @@ metastore_db/
 **/build/*
 **/dist/*
 **/*.egg-info/*
-

core/src/main/scala/com/microsoft/azure/synapse/ml/logging/SynapseMLLogging.scala

@@ -5,13 +5,16 @@ package com.microsoft.azure.synapse.ml.logging
 
 import com.microsoft.azure.synapse.ml.build.BuildInfo
 import com.microsoft.azure.synapse.ml.logging.common.SASScrubber
+import com.microsoft.azure.synapse.ml.logging.fabric.CertifiedEventClient.logToCertifiedEvents
 import org.apache.spark.internal.Logging
 import org.apache.spark.sql.SparkSession
 import spray.json.DefaultJsonProtocol._
 import spray.json._
 
 import scala.collection.JavaConverters._
 import scala.collection.mutable
+import scala.concurrent.ExecutionContext.Implicits.global
+import scala.concurrent.Future
 
 case class RequiredLogFields(uid: String,
                              className: String,
@@ -110,16 +113,29 @@ trait SynapseMLLogging extends Logging {
 
   protected def logBase(methodName: String,
                         numCols: Option[Int],
-                        executionSeconds: Option[Double]
+                        executionSeconds: Option[Double],
+                        logCertifiedEvent: Boolean = false
                        ): Unit = {
     logBase(getPayload(
       methodName,
       numCols,
       executionSeconds,
-      None))
+      None), logCertifiedEvent)
   }
 
-  protected def logBase(info: Map[String, String]): Unit = {
+  protected def logBase(info: Map[String, String], logCertifiedEvent: Boolean): Unit = {
+    if (logCertifiedEvent) {
+      Future {
+        logToCertifiedEvents(
+          info("libraryName"),
+          info("method"),
+          info -- Seq("libraryName", "method")
+        )
+      }.failed.map {
+        case e: Exception => logErrorBase("certifiedEventLogging", e)
+      }
+    }
+
     logInfo(info.toJson.compactPrint)
   }
 
@@ -130,23 +146,23 @@ trait SynapseMLLogging extends Logging {
   }
 
   def logClass(): Unit = {
-    logBase("constructor", None, None)
+    logBase("constructor", None, None, true)
   }
 
-  def logFit[T](f: => T, columns: Int): T = {
-    logVerb("fit", f, Some(columns))
+  def logFit[T](f: => T, columns: Int, logCertifiedEvent: Boolean = true): T = {
+    logVerb("fit", f, columns, logCertifiedEvent)
   }
 
-  def logTransform[T](f: => T, columns: Int): T = {
-    logVerb("transform", f, Some(columns))
+  def logTransform[T](f: => T, columns: Int, logCertifiedEvent: Boolean = true): T = {
+    logVerb("transform", f, columns, logCertifiedEvent)
   }
 
-  def logVerb[T](verb: String, f: => T, columns: Option[Int] = None): T = {
+  def logVerb[T](verb: String, f: => T, columns: Int = -1, logCertifiedEvent: Boolean = false): T = {
     val startTime = System.nanoTime()
     try {
-      val ret = f
-      logBase(verb, columns, Some((System.nanoTime() - startTime) / 1e9))
-      ret
+      // Begin emitting certified event.
+      logBase(verb, Some(columns), Some((System.nanoTime() - startTime) / 1e9), logCertifiedEvent)
+      f
     } catch {
       case e: Exception =>
         logErrorBase(verb, e)

core/src/main/scala/com/microsoft/azure/synapse/ml/logging/common/PlatformDetails.scala

@@ -0,0 +1,34 @@
+// Copyright (C) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License. See LICENSE in project root for information.
+
+package com.microsoft.azure.synapse.ml.logging.common
+
+import org.apache.spark.sql.SparkSession
+
+object PlatformDetails {
+  val PlatformSynapseInternal = "synapse_internal"
+  val PlatformSynapse = "synapse"
+  val PlatformBinder = "binder"
+  val PlatformDatabricks = "databricks"
+  val PlatformUnknown = "unknown"
+  val SynapseProjectName = "Microsoft.ProjectArcadia"
+
+  private def currentPlatform(): String = {
+    val azureService = sys.env.get("AZURE_SERVICE")
+    azureService match {
+      case Some(serviceName) if serviceName == SynapseProjectName =>
+        val spark = SparkSession.builder.getOrCreate()
+        val clusterType = spark.conf.get("spark.cluster.type")
+        if (clusterType == "synapse") PlatformSynapse else PlatformSynapseInternal
+      case _ if new java.io.File("/dbfs").exists() => PlatformDatabricks
+      case _ if sys.env.get("BINDER_LAUNCH_HOST").isDefined => PlatformBinder
+      case _ => PlatformUnknown
+    }
+  }
+
+  private def runningOnSynapseInternal(): Boolean = currentPlatform() == PlatformSynapseInternal
+
+  private def runningOnSynapse(): Boolean = currentPlatform() == PlatformSynapse
+
+  private[ml] def runningOnFabric(): Boolean = runningOnSynapseInternal
+}

core/src/main/scala/com/microsoft/azure/synapse/ml/logging/fabric/CertifiedEventClient.scala

@@ -0,0 +1,118 @@
+// Copyright (C) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License. See LICENSE in project root for information.
+
+package com.microsoft.azure.synapse.ml.logging.fabric
+
+import org.apache.spark.sql.SparkSession
+import spray.json.DefaultJsonProtocol.{StringJsonFormat, _}
+import spray.json._
+
+import java.time.Instant
+import java.util.UUID
+import scala.reflect.runtime.currentMirror
+import scala.reflect.runtime.universe._
+
+import com.microsoft.azure.synapse.ml.logging.common.PlatformDetails.runningOnFabric
+
+object CertifiedEventClient extends RESTUtils {
+
+  private val EmitUsage = "EmitUsage"
+
+  private val FabricFakeTelemetryReportCalls = "fabric_fake_usage_telemetry"
+
+  private val PbiGlobalServiceEndpoints = Map(
+    "public" -> "https://api.powerbi.com/",
+    "fairfax" -> "https://api.powerbigov.us",
+    "mooncake" -> "https://api.powerbi.cn",
+    "blackforest" -> "https://app.powerbi.de",
+    "msit" -> "https://api.powerbi.com/",
+    "prod" -> "https://api.powerbi.com/",
+    "int3" -> "https://biazure-int-edog-redirect.analysis-df.windows.net/",
+    "dxt" -> "https://powerbistagingapi.analysis.windows.net/",
+    "edog" -> "https://biazure-int-edog-redirect.analysis-df.windows.net/",
+    "dev" -> "https://onebox-redirect.analysis.windows-int.net/",
+    "console" -> "http://localhost:5001/",
+    "daily" -> "https://dailyapi.powerbi.com/")
+
+
+  private lazy val CertifiedEventUri = getCertifiedEventUri
+
+  private def getAccessToken: String = {
+    val objectName = "com.microsoft.azure.trident.tokenlibrary.TokenLibrary"
+    val mirror = currentMirror
+    val module = mirror.staticModule(objectName)
+    val obj = mirror.reflectModule(module).instance
+    val objType = mirror.reflect(obj).symbol.toType
+    val methodName = "getAccessToken"
+    val methodSymbols = objType.decl(TermName(methodName)).asTerm.alternatives
+    val argType = typeOf[String]
+    val selectedMethodSymbol = methodSymbols.find { m =>
+      m.asMethod.paramLists match {
+        case List(List(param)) => param.typeSignature =:= argType
+        case _ => false
+      }
+    }.getOrElse(throw new NoSuchMethodException(s"Method $methodName with argument type $argType not found"))
+    val methodMirror = mirror.reflect(obj).reflectMethod(selectedMethodSymbol.asMethod)
+    methodMirror("pbi").asInstanceOf[String]
+  }
+
+  private def getHeaders: Map[String, String] = {
+    Map(
+      "Authorization" -> s"Bearer $getAccessToken",
+      "RequestId" -> UUID.randomUUID().toString,
+      "Content-Type" -> "application/json",
+      "x-ms-workload-resource-moniker" -> UUID.randomUUID().toString
+    )
+  }
+
+  private def getCertifiedEventUri: String = {
+    val sc = SparkSession.builder().getOrCreate().sparkContext
+    val workspaceId = sc.hadoopConfiguration.get("trident.artifact.workspace.id")
+    val capacityId = sc.hadoopConfiguration.get("trident.capacity.id")
+    val pbiEnv = sc.getConf.get("spark.trident.pbienv").toLowerCase()
+
+    val clusterDetailUrl = s"${PbiGlobalServiceEndpoints(pbiEnv)}powerbi/globalservice/v201606/clusterDetails"
+    val headers = getHeaders
+
+    val clusterUrl = usageGet(clusterDetailUrl, headers)
+      .asJsObject.fields("clusterUrl").convertTo[String]
+    val tokenUrl: String = s"$clusterUrl/metadata/v201606/generatemwctokenv2"
+
+    val payload =
+      s"""{
+         |"capacityObjectId": "$capacityId",
+         |"workspaceObjectId": "$workspaceId",
+         |"workloadType": "ML"
+         |}""".stripMargin
+
+
+    val host = usagePost(tokenUrl, payload, headers)
+      .asJsObject.fields("TargetUriHost").convertTo[String]
+
+    s"https://$host/webapi/Capacities/$capacityId/workloads/ML/MLAdmin/Automatic/workspaceid/$workspaceId/telemetry"
+  }
+
+
+  private[ml] def logToCertifiedEvents(featureName: String,
+                                       activityName: String,
+                                       attributes: Map[String, String]): Unit = {
+
+    val shouldEmitCertifiedEvent = (
+      (sys.env.getOrElse(EmitUsage, "true").toLowerCase == "true") &&
+      (sys.env.getOrElse(FabricFakeTelemetryReportCalls, "false").toLowerCase == "false")
+        && runningOnFabric
+      )
+
+    if (shouldEmitCertifiedEvent) {
+      val payload =
+        s"""{
+           |"timestamp":${Instant.now().getEpochSecond},
+           |"feature_name":"$featureName",
+           |"activity_name":"$activityName",
+           |"attributes":${attributes.toJson.compactPrint}
+           |}""".stripMargin
+
+      usagePost(CertifiedEventUri, payload, getHeaders)
+    }
+  }
+}

core/src/main/scala/com/microsoft/azure/synapse/ml/logging/fabric/RESTUtils.scala

@@ -0,0 +1,47 @@
+// Copyright (C) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License. See LICENSE in project root for information.
+
+package com.microsoft.azure.synapse.ml.logging.fabric
+
+import com.microsoft.azure.synapse.ml.io.http.RESTHelpers
+import org.apache.commons.io.IOUtils
+import org.apache.http.client.methods.{CloseableHttpResponse, HttpGet, HttpPost}
+import org.apache.http.entity.StringEntity
+import spray.json.{JsObject, JsValue, _}
+
+trait RESTUtils {
+  def usagePost(url: String, body: String, headers: Map[String, String]): JsValue = {
+    val request = new HttpPost(url)
+
+    for ((k, v) <- headers)
+      request.addHeader(k, v)
+
+    request.setEntity(new StringEntity(body))
+
+    val response = RESTHelpers.safeSend(request, close = false)
+    val parsedResponse = parseResponse(response)
+    response.close()
+    parsedResponse
+  }
+
+  def usageGet(url: String, headers: Map[String, String]): JsValue = {
+    val request = new HttpGet(url)
+    for ((k, v) <- headers)
+      request.addHeader(k, v)
+
+    val response = RESTHelpers.safeSend(request, close = false)
+    val result = parseResponse(response)
+    response.close()
+    result
+  }
+
+  private def parseResponse(response: CloseableHttpResponse): JsValue = {
+    val content: String = IOUtils.toString(response.getEntity.getContent, "utf-8")
+    if (content.nonEmpty) {
+      content.parseJson
+    } else {
+      JsObject()
+    }
+  }
+
+}

environment.yml

@@ -50,4 +50,3 @@ dependencies:
     - pypandoc
     - markdownify
     - traitlets
-

tools/docgen/docgen/manifest.yaml

@@ -90,7 +90,7 @@ channels:
       - path: Explore Algorithms/OpenAI/OpenAI.ipynb
         metadata:
           title: Azure OpenAI for big data
-          description: Use Azure OpenAI service to solve a large number of natural language tasks through prompting the completion API. 
+          description: Use Azure OpenAI service to solve a large number of natural language tasks through prompting the completion API.
           ms.topic: how-to
           ms.custom: build-2023
           ms.reviewer: jessiwang