Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/993#discussion_r15332175
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala
---
@@ -0,0 +1,458 @@
+/*
+ * 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.catalyst.expressions.codegen
+
+import com.google.common.cache.{CacheLoader, CacheBuilder}
+
+import scala.language.existentials
+
+import org.apache.spark.Logging
+import org.apache.spark.sql.catalyst.expressions
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.types._
+
+/**
+ * A base class for generators of byte code to perform expression
evaluation. Includes a set of
+ * helpers for referring to Catalyst types and building trees that perform
evaluation of individual
+ * expressions.
+ */
+abstract class CodeGenerator[InType <: AnyRef, OutType <: AnyRef] extends
Logging {
+ import scala.reflect.runtime.{universe => ru}
+ import scala.reflect.runtime.universe._
+
+ import scala.tools.reflect.ToolBox
+
+ protected val toolBox =
runtimeMirror(getClass.getClassLoader).mkToolBox()
+
+ protected val rowType = typeOf[Row]
+ protected val mutableRowType = typeOf[MutableRow]
+ protected val genericRowType = typeOf[GenericRow]
+ protected val genericMutableRowType = typeOf[GenericMutableRow]
+
+ protected val projectionType = typeOf[Projection]
+ protected val mutableProjectionType = typeOf[MutableProjection]
+
+ private val curId = new java.util.concurrent.atomic.AtomicInteger()
+ private val javaSeparator = "$"
+
+ /**
+ * Generates a class for a given input expression. Called when there is
not cached code
+ * already available.
+ */
+ protected def create(in: InType): OutType
+
+ /**
+ * Canonicalizes an input expression. Used to avoid double caching
expressions that differ only
+ * cosmetically.
+ */
+ protected def canonicalize(in: InType): InType
+
+ /** Binds an input expression to a given input schema */
+ protected def bind(in: InType, inputSchema: Seq[Attribute]): InType
+
+ protected val cache = CacheBuilder.newBuilder()
+ .maximumSize(1000)
+ .build(
+ new CacheLoader[InType, OutType]() {
+ override def load(in: InType): OutType = globalLock.synchronized {
+ create(in)
+ }
+ })
+
+ def apply(expressions: InType, inputSchema: Seq[Attribute]): OutType=
--- End diff --
actually after reading through the code more, i'd argue we should rename
this function from apply to something more informative. unless semantically
very explicit & obvious (e.g. array), the use of apply makes it harder to
understand code around its usage.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
