Imbruced commented on code in PR #2593: URL: https://github.com/apache/sedona/pull/2593#discussion_r2725945610
########## spark/spark-3.5/src/main/scala/org/apache/spark/sql/execution/python/SedonaArrowStrategy.scala: ########## @@ -0,0 +1,161 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ +package org.apache.spark.sql.execution.python + +import org.apache.sedona.sql.UDF.PythonEvalType +import org.apache.sedona.sql.UDF.PythonEvalType.{SQL_SCALAR_SEDONA_DB_SPEEDUP_UDF, SQL_SCALAR_SEDONA_DB_UDF, SQL_SCALAR_SEDONA_UDF} +import org.apache.spark.api.python.ChainedPythonFunctions +import org.apache.spark.sql.Strategy +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Attribute, GenericInternalRow, PythonUDF} +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.udf.SedonaArrowEvalPython +import org.apache.spark.{JobArtifactSet, TaskContext} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.sedona_sql.UDT.GeometryUDT + +import scala.collection.JavaConverters.asScalaIteratorConverter + +// We use custom Strategy to avoid Apache Spark assert on types, we +// can consider extending this to support other engines working with +// arrow data +class SedonaArrowStrategy extends Strategy { + override def apply(plan: LogicalPlan): Seq[SparkPlan] = plan match { + case SedonaArrowEvalPython(udfs, output, child, evalType) => + SedonaArrowEvalPythonExec(udfs, output, planLater(child), evalType) :: Nil + case _ => Nil + } +} + +// It's modification og Apache Spark's ArrowEvalPythonExec, we remove the check on the types to allow geometry types +// here, it's initial version to allow the vectorized udf for Sedona geometry types. We can consider extending this +// to support other engines working with arrow data +case class SedonaArrowEvalPythonExec( + udfs: Seq[PythonUDF], + resultAttrs: Seq[Attribute], + child: SparkPlan, + evalType: Int) + extends EvalPythonExec + with PythonSQLMetrics { + + private val batchSize = conf.arrowMaxRecordsPerBatch + private val sessionLocalTimeZone = conf.sessionLocalTimeZone + private val largeVarTypes = conf.arrowUseLargeVarTypes + private val pythonRunnerConf = + Map[String, String](SQLConf.SESSION_LOCAL_TIMEZONE.key -> conf.sessionLocalTimeZone) + private[this] val jobArtifactUUID = JobArtifactSet.getCurrentJobArtifactState.map(_.uuid) + + private def inferCRS(iterator: Iterator[InternalRow], schema: StructType): Seq[(Int, Int)] = { + // this triggers the iterator + if (!iterator.hasNext) { + return Seq.empty + } + + val row = iterator.next() + + val rowMatched = row match { + case generic: GenericInternalRow => + Some(generic) + case _ => None + } + + schema Review Comment: infer for geometry fields by taking the firs value -- 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]
