cfmcgrady commented on code in PR #5591: URL: https://github.com/apache/kyuubi/pull/5591#discussion_r1420227178
########## externals/kyuubi-spark-sql-engine/src/main/scala/org/apache/kyuubi/engine/spark/operation/FetchOrcStatement.scala: ########## @@ -0,0 +1,147 @@ +/* + * 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.kyuubi.engine.spark.operation + +import scala.Array._ +import scala.collection.mutable.ListBuffer + +import org.apache.hadoop.conf.Configuration +import org.apache.hadoop.fs.{LocatedFileStatus, Path} +import org.apache.hadoop.mapreduce.{JobID, TaskAttemptID, TaskID, TaskType} +import org.apache.hadoop.mapreduce.lib.input.FileSplit +import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl +import org.apache.orc.mapred.OrcStruct +import org.apache.orc.mapreduce.OrcInputFormat +import org.apache.spark.sql.{Row, SparkSession} +import org.apache.spark.sql.catalyst.{CatalystTypeConverters, InternalRow} +import org.apache.spark.sql.catalyst.expressions.AttributeReference +import org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection +import org.apache.spark.sql.execution.datasources.RecordReaderIterator +import org.apache.spark.sql.execution.datasources.orc.OrcDeserializer +import org.apache.spark.sql.types.StructType + +import org.apache.kyuubi.KyuubiException +import org.apache.kyuubi.engine.spark.KyuubiSparkUtil.SPARK_ENGINE_RUNTIME_VERSION +import org.apache.kyuubi.operation.{FetchIterator, IterableFetchIterator} +import org.apache.kyuubi.util.reflect.DynConstructors + +class FetchOrcStatement(spark: SparkSession) { + + var orcIter: OrcFileIterator = _ + def getIterator(path: String, orcSchema: StructType): FetchIterator[Row] = { + val conf = spark.sparkContext.hadoopConfiguration + val savePath = new Path(path) + val fsIterator = savePath.getFileSystem(conf).listFiles(savePath, false) + val list = new ListBuffer[LocatedFileStatus] + while (fsIterator.hasNext) { + val file = fsIterator.next() + if (file.getPath.getName.endsWith(".orc")) { + list += file + } + } + val toRowConverter: InternalRow => Row = { + CatalystTypeConverters.createToScalaConverter(orcSchema) + .asInstanceOf[InternalRow => Row] + } + val colId = range(0, orcSchema.size) + val fullSchema = orcSchema.map(f => + AttributeReference(f.name, f.dataType, f.nullable, f.metadata)()) + val unsafeProjection = GenerateUnsafeProjection.generate(fullSchema, fullSchema) + val deserializer = getOrcDeserializer(orcSchema, colId) + orcIter = new OrcFileIterator(list) + val iterRow = orcIter.map(value => + unsafeProjection(deserializer.deserialize(value))) + .map(value => toRowConverter(value)) + new IterableFetchIterator[Row](iterRow.toIterable) + } + + def close(): Unit = { + orcIter.close() + } + + private def getOrcDeserializer(orcSchema: StructType, colId: Array[Int]): OrcDeserializer = { + try { + if (SPARK_ENGINE_RUNTIME_VERSION >= "3.2") { + // SPARK-34535 changed the constructor signature of OrcDeserializer + DynConstructors.builder() + .impl(classOf[OrcDeserializer], classOf[StructType], classOf[Array[Int]]) + .build[OrcDeserializer]() + .newInstance( + orcSchema, + colId) + } else { + DynConstructors.builder() + .impl( + classOf[OrcDeserializer], + classOf[StructType], + classOf[StructType], + classOf[Array[Int]]) + .build[OrcDeserializer]() + .newInstance( + new StructType, + orcSchema, + colId) + } + } catch { + case e: Throwable => + throw new KyuubiException("Failed to create OrcDeserializer", e) + } + } +} + +class OrcFileIterator(fileList: ListBuffer[LocatedFileStatus]) extends Iterator[OrcStruct] { + + private val iters = fileList.map(x => getOrcFileIterator(x)) + + var idx = 0 + + override def hasNext: Boolean = { + if (iters(idx).hasNext) { + true + } else { + iters(idx).close() + idx < iters.size - 1 + } + } + + override def next(): OrcStruct = { + if (iters(idx).hasNext) { + iters(idx).next() + } else { + idx = idx + 1 + iters(idx).next() Review Comment: Is it possible that the `iters(idx)` can be empty? -- 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]
