[GitHub] [hudi] alexeykudinkin commented on a diff in pull request #5364: [HUDI-3204] Fixing partition-values being derived from partition-path instead of source columns

[GitBox <gi...@apache.org>]

alexeykudinkin commented on code in PR #5364:
URL: https://github.com/apache/hudi/pull/5364#discussion_r853393411


##########
hudi-spark-datasource/hudi-spark2/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark24HoodieParquetFileFormat.scala:
##########
@@ -0,0 +1,229 @@
+/*
+ * 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.parquet
+
+import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.fs.Path
+import org.apache.hadoop.mapreduce.lib.input.FileSplit
+import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl
+import org.apache.hadoop.mapreduce.{JobID, TaskAttemptID, TaskID, TaskType}
+import org.apache.parquet.filter2.compat.FilterCompat
+import org.apache.parquet.filter2.predicate.FilterApi
+import org.apache.parquet.format.converter.ParquetMetadataConverter.SKIP_ROW_GROUPS
+import org.apache.parquet.hadoop.{ParquetFileReader, ParquetInputFormat, ParquetRecordReader}
+import org.apache.spark.TaskContext
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.avro.AvroDeserializer
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.codegen.GenerateUnsafeProjection
+import org.apache.spark.sql.catalyst.expressions.{JoinedRow, UnsafeRow}
+import org.apache.spark.sql.catalyst.util.DateTimeUtils
+import org.apache.spark.sql.execution.datasources.{PartitionedFile, RecordReaderIterator}
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.sources.Filter
+import org.apache.spark.sql.types.{AtomicType, StructType}
+import org.apache.spark.util.SerializableConfiguration
+
+import java.net.URI
+
+/**
+ * This class is an extension of [[ParquetFileFormat]] overriding Spark-specific behavior
+ * that's not possible to customize in any other way
+ *
+ * NOTE: This is a version of [[AvroDeserializer]] impl from Spark 2.4.4 w/ w/ the following changes applied to it:
+ * <ol>
+ *   <li>Avoiding appending partition values to the rows read from the data file</li>
+ * </ol>
+ */
+class Spark24HoodieParquetFileFormat(private val shouldAppendPartitionValues: Boolean) extends ParquetFileFormat {

Review Comment:
   Only aspects that diverge from the source are the ones using `shouldAppendPartitionValues`



-- 
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: commits-unsubscribe@hudi.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org