dtenedor commented on code in PR #41948:
URL: https://github.com/apache/spark/pull/41948#discussion_r1264029412
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala:
##########
@@ -91,3 +122,104 @@ case class UserDefinedPythonTableFunction(
Dataset.ofRows(session, udtf)
}
}
+
+object UserDefinedPythonTableFunction {
+
+ private[this] val workerModule = "pyspark.sql.worker.analyze_udtf"
+
+ /**
+ * Runs the Python UDTF's `analyze` static method.
+ */
+ def analyzeInPython(func: PythonFunction, exprs: Seq[Expression]):
StructType = {
+ val env = SparkEnv.get
+ val bufferSize: Int = env.conf.get(BUFFER_SIZE)
+ val authSocketTimeout = env.conf.get(PYTHON_AUTH_SOCKET_TIMEOUT)
+ val reuseWorker = env.conf.get(PYTHON_WORKER_REUSE)
+ val simplifiedTraceback: Boolean = SQLConf.get.pysparkSimplifiedTraceback
+
+ val envVars = new HashMap[String, String](func.envVars)
+ val pythonExec = func.pythonExec
+ val pythonVer = func.pythonVer
+
+ if (reuseWorker) {
+ envVars.put("SPARK_REUSE_WORKER", "1")
+ }
+ if (simplifiedTraceback) {
+ envVars.put("SPARK_SIMPLIFIED_TRACEBACK", "1")
+ }
+ envVars.put("SPARK_AUTH_SOCKET_TIMEOUT", authSocketTimeout.toString)
+ envVars.put("SPARK_BUFFER_SIZE", bufferSize.toString)
+
+ EvaluatePython.registerPicklers()
+ val pickler = new Pickler(/* useMemo = */ true,
Review Comment:
My mistake on this, carry on!
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/UserDefinedPythonFunction.scala:
##########
@@ -91,3 +122,104 @@ case class UserDefinedPythonTableFunction(
Dataset.ofRows(session, udtf)
}
}
+
+object UserDefinedPythonTableFunction {
+
+ private[this] val workerModule = "pyspark.sql.worker.analyze_udtf"
+
+ /**
+ * Runs the Python UDTF's `analyze` static method.
+ */
+ def analyzeInPython(func: PythonFunction, exprs: Seq[Expression]):
StructType = {
+ val env = SparkEnv.get
+ val bufferSize: Int = env.conf.get(BUFFER_SIZE)
+ val authSocketTimeout = env.conf.get(PYTHON_AUTH_SOCKET_TIMEOUT)
+ val reuseWorker = env.conf.get(PYTHON_WORKER_REUSE)
+ val simplifiedTraceback: Boolean = SQLConf.get.pysparkSimplifiedTraceback
+
+ val envVars = new HashMap[String, String](func.envVars)
+ val pythonExec = func.pythonExec
+ val pythonVer = func.pythonVer
+
+ if (reuseWorker) {
+ envVars.put("SPARK_REUSE_WORKER", "1")
+ }
+ if (simplifiedTraceback) {
+ envVars.put("SPARK_SIMPLIFIED_TRACEBACK", "1")
+ }
+ envVars.put("SPARK_AUTH_SOCKET_TIMEOUT", authSocketTimeout.toString)
+ envVars.put("SPARK_BUFFER_SIZE", bufferSize.toString)
+
+ EvaluatePython.registerPicklers()
+ val pickler = new Pickler(/* useMemo = */ true,
+ /* valueCompare = */ false)
Review Comment:
My mistake on this, carry on!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
