Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/19943#discussion_r159220027 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcColumnarBatchReader.scala --- @@ -0,0 +1,432 @@ +/* + * 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.datasources.orc + +import org.apache.hadoop.mapreduce.{InputSplit, RecordReader, TaskAttemptContext} +import org.apache.hadoop.mapreduce.lib.input.FileSplit +import org.apache.orc._ +import org.apache.orc.mapred.OrcInputFormat +import org.apache.orc.storage.ql.exec.vector._ +import org.apache.orc.storage.serde2.io.HiveDecimalWritable + +import org.apache.spark.internal.Logging +import org.apache.spark.memory.MemoryMode +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.execution.vectorized._ +import org.apache.spark.sql.types._ + + +/** + * To support vectorization in WholeStageCodeGen, this reader returns ColumnarBatch. + */ +private[orc] class OrcColumnarBatchReader extends RecordReader[Void, ColumnarBatch] with Logging { + import OrcColumnarBatchReader._ + + /** + * ORC File Reader. + */ + private var reader: Reader = _ + + /** + * Vectorized Row Batch. + */ + private var batch: VectorizedRowBatch = _ + + /** + * Requested Column IDs. + */ + private var requestedColIds: Array[Int] = _ + + /** + * Record reader from row batch. + */ + private var rows: org.apache.orc.RecordReader = _ + + /** + * Required Schema. + */ + private var requiredSchema: StructType = _ + + /** + * ColumnarBatch for vectorized execution by whole-stage codegen. + */ + private var columnarBatch: ColumnarBatch = _ + + /** + * Writable columnVectors of ColumnarBatch. --- End diff -- so it should be `Writable column vectors`
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org