[GitHub] [spark] gengliangwang commented on a change in pull request #24327: [WIP][SPARK-27418][SQL] Migrate Parquet to File Data Source V2

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

gengliangwang commented on a change in pull request #24327: [WIP][SPARK-27418][SQL] Migrate Parquet to File Data Source V2
URL: https://github.com/apache/spark/pull/24327#discussion_r283856128
 
 

 ##########
 File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetScanBuilder.scala
 ##########
 @@ -0,0 +1,59 @@
+/*
+ * 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.parquet
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.execution.datasources.PartitioningAwareFileIndex
+import org.apache.spark.sql.execution.datasources.v2.FileScanBuilder
+import org.apache.spark.sql.sources.Filter
+import org.apache.spark.sql.sources.v2.reader.{Scan, SupportsPushDownFilters}
+import org.apache.spark.sql.types.StructType
+import org.apache.spark.sql.util.CaseInsensitiveStringMap
+
+case class ParquetScanBuilder(
+    sparkSession: SparkSession,
+    fileIndex: PartitioningAwareFileIndex,
+    schema: StructType,
+    dataSchema: StructType,
+    options: CaseInsensitiveStringMap)
+  extends FileScanBuilder(sparkSession, fileIndex, dataSchema) with SupportsPushDownFilters {
+  lazy val hadoopConf = {
+    val caseSensitiveMap = options.asCaseSensitiveMap.asScala.toMap
+    // Hadoop Configurations are case sensitive.
+    sparkSession.sessionState.newHadoopConfWithOptions(caseSensitiveMap)
+  }
+
+  private var filters: Array[Filter] = _
+
+  override def pushFilters(filters: Array[Filter]): Array[Filter] = {
+    this.filters = filters
+    this.filters
+  }
+
+  // The actual filter push down happens in [[ParquetPartitionReaderFactory]].
+  // It requires the Parquet physical schema to determine whether a filter is convertible.
+  // So here we simply mark that all the filters are pushed down.
+  override def pushedFilters(): Array[Filter] = this.filters
 
 Review comment:
   created https://github.com/apache/spark/pull/24597 for this.

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


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org