Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/19943#discussion_r160069594 --- Diff: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/orc/JavaOrcColumnarBatchReader.java --- @@ -0,0 +1,503 @@ +/* + * 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 java.io.IOException; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.mapreduce.InputSplit; +import org.apache.hadoop.mapreduce.RecordReader; +import org.apache.hadoop.mapreduce.TaskAttemptContext; +import org.apache.hadoop.mapreduce.lib.input.FileSplit; +import org.apache.orc.OrcConf; +import org.apache.orc.OrcFile; +import org.apache.orc.Reader; +import org.apache.orc.TypeDescription; +import org.apache.orc.mapred.OrcInputFormat; +import org.apache.orc.storage.common.type.HiveDecimal; +import org.apache.orc.storage.ql.exec.vector.*; +import org.apache.orc.storage.serde2.io.HiveDecimalWritable; + +import org.apache.spark.memory.MemoryMode; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.execution.vectorized.ColumnVectorUtils; +import org.apache.spark.sql.execution.vectorized.OffHeapColumnVector; +import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector; +import org.apache.spark.sql.execution.vectorized.WritableColumnVector; +import org.apache.spark.sql.types.*; +import org.apache.spark.sql.vectorized.ColumnarBatch; + + +/** + * To support vectorization in WholeStageCodeGen, this reader returns ColumnarBatch. + * After creating, `initialize` and `setRequiredSchema` should be called sequentially. + */ +public class JavaOrcColumnarBatchReader extends RecordReader<Void, ColumnarBatch> { + + /** + * ORC File Reader. + */ + private Reader reader; + + /** + * Vectorized Row Batch. + */ + private VectorizedRowBatch batch; + + /** + * Requested Column IDs. + */ + private int[] requestedColIds; + + /** + * Record reader from row batch. + */ + private org.apache.orc.RecordReader recordReader; + + /** + * Required Schema. + */ + private StructType requiredSchema; + + /** + * ColumnarBatch for vectorized execution by whole-stage codegen. + */ + private ColumnarBatch columnarBatch; + + /** + * Writable column vectors of ColumnarBatch. --- End diff -- `... of the result columnar batch`
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org