Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/20933#discussion_r178308839
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcUnsafeRowReaderFactory.scala
---
@@ -0,0 +1,115 @@
+/*
+ * 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.v2.orc
+
+import java.net.URI
+
+import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.fs.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.{OrcConf, OrcFile}
+import org.apache.orc.mapred.OrcStruct
+import org.apache.orc.mapreduce.OrcInputFormat
+
+import org.apache.spark.TaskContext
+import org.apache.spark.broadcast.Broadcast
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.{JoinedRow, UnsafeRow}
+import
org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection
+import org.apache.spark.sql.execution.datasources._
+import org.apache.spark.sql.execution.datasources.orc.{OrcDeserializer,
OrcUtils}
+import org.apache.spark.sql.sources.v2.reader.{DataReader,
DataReaderFactory}
+import org.apache.spark.sql.types.StructType
+import org.apache.spark.util.SerializableConfiguration
+
+case class OrcUnsafeRowReaderFactory(
--- End diff --
there are a lot of duplication between this and
`OrcBatchDataReaderFactory`, and we may have more when migrating other file
formats.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
