From 3a652f691b220fada0286f8d0a562c5657973d4d Mon Sep 17 00:00:00 2001
From: Reynold Xin <rxin@databricks.com>
Date: Fri, 6 Nov 2015 14:47:41 -0800
Subject: [PATCH] [SPARK-11561][SQL] Rename text data source's column name to
value.
Author: Reynold Xin <rxin@databricks.com>
Closes #9527 from rxin/SPARK-11561.
---
.../sql/execution/datasources/text/DefaultSource.scala | 6 ++----
.../spark/sql/execution/datasources/text/TextSuite.scala | 2 +-
2 files changed, 3 insertions(+), 5 deletions(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/DefaultSource.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/DefaultSource.scala
index 52c4421d7e..4b8b8e4e74 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/DefaultSource.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/DefaultSource.scala
@@ -30,14 +30,12 @@ import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.mapred.SparkHadoopMapRedUtil
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.expressions.{UnsafeRow, GenericMutableRow}
+import org.apache.spark.sql.catalyst.expressions.UnsafeRow
import org.apache.spark.sql.catalyst.expressions.codegen.{UnsafeRowWriter, BufferHolder}
-import org.apache.spark.sql.columnar.MutableUnsafeRow
import org.apache.spark.sql.{AnalysisException, Row, SQLContext}
import org.apache.spark.sql.execution.datasources.PartitionSpec
import org.apache.spark.sql.sources._
import org.apache.spark.sql.types.{StringType, StructType}
-import org.apache.spark.unsafe.types.UTF8String
import org.apache.spark.util.SerializableConfiguration
/**
@@ -78,7 +76,7 @@ private[sql] class TextRelation(
extends HadoopFsRelation(maybePartitionSpec) {
/** Data schema is always a single column, named "text". */
- override def dataSchema: StructType = new StructType().add("text", StringType)
+ override def dataSchema: StructType = new StructType().add("value", StringType)
/** This is an internal data source that outputs internal row format. */
override val needConversion: Boolean = false
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/text/TextSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/text/TextSuite.scala
index 0a2306c066..914e516613 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/text/TextSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/text/TextSuite.scala
@@ -65,7 +65,7 @@ class TextSuite extends QueryTest with SharedSQLContext {
/** Verifies data and schema. */
private def verifyFrame(df: DataFrame): Unit = {
// schema
- assert(df.schema == new StructType().add("text", StringType))
+ assert(df.schema == new StructType().add("value", StringType))
// verify content
val data = df.collect()
--
GitLab