Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19651#discussion_r150201579
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFilters.scala
---
@@ -0,0 +1,180 @@
+/*
+ * 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.orc.storage.ql.io.sarg.{PredicateLeaf, SearchArgument,
SearchArgumentFactory}
+import org.apache.orc.storage.ql.io.sarg.SearchArgument.Builder
+import org.apache.orc.storage.serde2.io.HiveDecimalWritable
+
+import org.apache.spark.sql.sources.Filter
+import org.apache.spark.sql.types._
+
+/**
+ * Utility functions to convert Spark data source filters to ORC filters.
+ */
+private[orc] object OrcFilters {
+
+ /**
+ * Create ORC filter as a SearchArgument instance.
+ */
+ def createFilter(schema: StructType, filters: Seq[Filter]):
Option[SearchArgument] = {
+ val dataTypeMap = schema.map(f => f.name -> f.dataType).toMap
+
+ // First, tries to convert each filter individually to see whether
it's convertible, and then
+ // collect all convertible ones to build the final `SearchArgument`.
+ val convertibleFilters = for {
+ filter <- filters
+ _ <- buildSearchArgument(dataTypeMap, filter,
SearchArgumentFactory.newBuilder())
+ } yield filter
+
+ for {
+ conjunction <-
convertibleFilters.reduceOption(org.apache.spark.sql.sources.And)
+ builder <- buildSearchArgument(dataTypeMap, conjunction,
SearchArgumentFactory.newBuilder())
+ } yield builder.build()
+ }
+
+ /**
+ * Return true if this is a searchable type in ORC.
+ */
+ private def isSearchableType(dataType: DataType) = dataType match {
+ case ByteType | ShortType | FloatType | DoubleType => true
+ case IntegerType | LongType | StringType | BooleanType => true
+ case TimestampType | _: DecimalType => true
--- End diff --
It looks like you randomly group the data types into 3 cases. Actually you
do something like
```
case BinaryType => false
case AtomicType => true
case _ => false
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
