Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/4173#discussion_r23488167
--- Diff: sql/core/src/main/scala/org/apache/spark/sql/DataFrame.scala ---
@@ -0,0 +1,273 @@
+/*
+* 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
+
+import scala.language.implicitConversions
+import scala.reflect.ClassTag
+
+import com.fasterxml.jackson.core.JsonFactory
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.rdd.RDD
+import org.apache.spark.storage.StorageLevel
+import org.apache.spark.sql.catalyst.ScalaReflection
+import org.apache.spark.sql.catalyst.analysis.UnresolvedRelation
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.expressions.{Literal => LiteralExpr}
+import org.apache.spark.sql.catalyst.plans.{JoinType, Inner}
+import org.apache.spark.sql.catalyst.plans.logical._
+import org.apache.spark.sql.execution.LogicalRDD
+import org.apache.spark.sql.json.JsonRDD
+import org.apache.spark.sql.types.{NumericType, StructType}
+
+
+class DataFrame(
+ val sqlContext: SQLContext,
+ val baseLogicalPlan: LogicalPlan,
+ operatorsEnabled: Boolean)
+ extends DataFrameSpecificApi with RDDApi[Row] {
+
+ def this(sqlContext: Option[SQLContext], plan: Option[LogicalPlan]) =
+ this(sqlContext.orNull, plan.orNull, sqlContext.isDefined &&
plan.isDefined)
+
+ def this(sqlContext: SQLContext, plan: LogicalPlan) = this(sqlContext,
plan, true)
+
+ @transient
+ protected[sql] lazy val queryExecution =
sqlContext.executePlan(baseLogicalPlan)
+
+ @transient protected[sql] val logicalPlan: LogicalPlan = baseLogicalPlan
match {
+ // For various commands (like DDL) and queries with side effects, we
force query optimization to
+ // happen right away to let these side effects take place eagerly.
+ case _: Command | _: InsertIntoTable | _: CreateTableAsSelect[_] |_:
WriteToFile =>
+ LogicalRDD(queryExecution.analyzed.output,
queryExecution.toRdd)(sqlContext)
+ case _ =>
+ baseLogicalPlan
+ }
+
+ private[this] implicit def toDataFrame(logicalPlan: LogicalPlan):
DataFrame = {
+ new DataFrame(sqlContext, logicalPlan, true)
+ }
+
+ protected[sql] def numericColumns: Seq[Expression] = {
+ schema.fields.filter(_.dataType.isInstanceOf[NumericType]).map { n =>
+ logicalPlan.resolve(n.name, sqlContext.analyzer.resolver).get
+ }
+ }
+
+ protected[sql] def resolve(colName: String): NamedExpression = {
+ logicalPlan.resolve(colName, sqlContext.analyzer.resolver).getOrElse(
+ throw new RuntimeException(s"""Cannot resolve column name
"$colName""""))
+ }
+
+ def toSchemaRDD: DataFrame = this
+
+ override def schema: StructType = queryExecution.analyzed.schema
+
+ override def dtypes: Array[(String, String)] = schema.fields.map { field
=>
+ (field.name, field.dataType.toString)
+ }
+
+ override def columns: Array[String] = schema.fields.map(_.name)
+
+ override def printSchema(): Unit = println(schema.treeString)
+
+ override def show(): Unit = {
+ ???
+ }
+
+ override def join(right: DataFrame): DataFrame = {
+ Join(logicalPlan, right.logicalPlan, joinType = Inner, None)
+ }
+
+ override def join(right: DataFrame, joinExprs: Column): DataFrame = {
+ Join(logicalPlan, right.logicalPlan, Inner, Some(joinExprs.expr))
+ }
+
+ override def join(right: DataFrame, joinType: String, joinExprs:
Column): DataFrame = {
+ Join(logicalPlan, right.logicalPlan, JoinType(joinType),
Some(joinExprs.expr))
+ }
+
+ override def sort(colName: String): DataFrame = {
--- End diff --
support sort by multiple columns
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
