Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/17924#discussion_r115646099
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcColumnarBatchReader.scala
---
@@ -0,0 +1,407 @@
+/*
+ * 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.spark.internal.Logging
+import org.apache.spark.memory.MemoryMode
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
+import org.apache.spark.sql.execution.vectorized.{ColumnarBatch,
ColumnVectorUtils}
+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 = _
+
+ /**
+ * ORC Data Schema.
+ */
+ private var schema: TypeDescription = _
+
+ /**
+ * Vectorized Row Batch.
+ */
+ private var batch: VectorizedRowBatch = _
+
+ /**
+ * Record reader from row batch.
+ */
+ private var rows: org.apache.orc.RecordReader = _
+
+ /**
+ * Spark Schema.
+ */
+ private var sparkSchema: StructType = _
+
+ /**
+ * Required Schema.
+ */
+ private var requiredSchema: StructType = _
+
+ /**
+ * Partition Column.
+ */
+ private var partitionColumns: StructType = _
+
+ private var useIndex: Boolean = false
+
+ /**
+ * Full Schema: requiredSchema + partition schema.
+ */
+ private var fullSchema: StructType = _
+
+ /**
+ * ColumnarBatch for vectorized execution by whole-stage codegen.
+ */
+ private var columnarBatch: ColumnarBatch = _
--- End diff --
IIRC, @viirya also has a PR for vectorized orc reader. In that PR, we
simply wrap the orc column batch to expose spark column batch interfaces,
instead of writing orc column batch to spark column batch. I think that
approach is more efficient.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
