From 55bea56911a958f6d3ec3ad96fb425cc71ec03f4 Mon Sep 17 00:00:00 2001
From: Xiao Li <gatorsmile@gmail.com>
Date: Thu, 20 Apr 2017 11:13:48 +0100
Subject: [SPARK-20156][SQL][FOLLOW-UP] Java String toLowerCase "Turkish locale
 bug" in Database and Table DDLs

### What changes were proposed in this pull request?
Database and Table names conform the Hive standard ("[a-zA-z_0-9]+"), i.e. if this name only contains characters, numbers, and _.

When calling `toLowerCase` on the names, we should add `Locale.ROOT` to the `toLowerCase`for avoiding inadvertent locale-sensitive variation in behavior (aka the "Turkish locale problem").

### How was this patch tested?
Added a test case

Author: Xiao Li <gatorsmile@gmail.com>

Closes #17655 from gatorsmile/locale.
---
 .../apache/spark/sql/internal/SharedState.scala    |  4 +++-
 .../spark/sql/execution/command/DDLSuite.scala     | 19 +++++++++++++++
 .../org/apache/spark/sql/test/SQLTestUtils.scala   | 28 +++++++++++++++++++++-
 3 files changed, 49 insertions(+), 2 deletions(-)

(limited to 'sql/core')

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala
index 0289471bf8..d06dbaa2d0 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/internal/SharedState.scala
@@ -17,6 +17,8 @@
 
 package org.apache.spark.sql.internal
 
+import java.util.Locale
+
 import scala.reflect.ClassTag
 import scala.util.control.NonFatal
 
@@ -114,7 +116,7 @@ private[sql] class SharedState(val sparkContext: SparkContext) extends Logging {
     // System preserved database should not exists in metastore. However it's hard to guarantee it
     // for every session, because case-sensitivity differs. Here we always lowercase it to make our
     // life easier.
-    val globalTempDB = sparkContext.conf.get(GLOBAL_TEMP_DATABASE).toLowerCase
+    val globalTempDB = sparkContext.conf.get(GLOBAL_TEMP_DATABASE).toLowerCase(Locale.ROOT)
     if (externalCatalog.databaseExists(globalTempDB)) {
       throw new SparkException(
         s"$globalTempDB is a system preserved database, please rename your existing database " +
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
index fe74ab49f9..2f4eb1b155 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
@@ -2295,5 +2295,24 @@ abstract class DDLSuite extends QueryTest with SQLTestUtils {
         }
       }
     }
+
+    test(s"basic DDL using locale tr - caseSensitive $caseSensitive") {
+      withSQLConf(SQLConf.CASE_SENSITIVE.key -> s"$caseSensitive") {
+        withLocale("tr") {
+          val dbName = "DaTaBaSe_I"
+          withDatabase(dbName) {
+            sql(s"CREATE DATABASE $dbName")
+            sql(s"USE $dbName")
+
+            val tabName = "tAb_I"
+            withTable(tabName) {
+              sql(s"CREATE TABLE $tabName(col_I int) USING PARQUET")
+              sql(s"INSERT OVERWRITE TABLE $tabName SELECT 1")
+              checkAnswer(sql(s"SELECT col_I FROM $tabName"), Row(1) :: Nil)
+            }
+          }
+        }
+      }
+    }
   }
 }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala b/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala
index 6a4cc95d36..b5ad73b746 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala
@@ -20,7 +20,7 @@ package org.apache.spark.sql.test
 import java.io.File
 import java.net.URI
 import java.nio.file.Files
-import java.util.UUID
+import java.util.{Locale, UUID}
 
 import scala.language.implicitConversions
 import scala.util.control.NonFatal
@@ -228,6 +228,32 @@ private[sql] trait SQLTestUtils
     }
   }
 
+  /**
+   * Drops database `dbName` after calling `f`.
+   */
+  protected def withDatabase(dbNames: String*)(f: => Unit): Unit = {
+    try f finally {
+      dbNames.foreach { name =>
+        spark.sql(s"DROP DATABASE IF EXISTS $name")
+      }
+    }
+  }
+
+  /**
+   * Enables Locale `language` before executing `f`, then switches back to the default locale of JVM
+   * after `f` returns.
+   */
+  protected def withLocale(language: String)(f: => Unit): Unit = {
+    val originalLocale = Locale.getDefault
+    try {
+      // Add Locale setting
+      Locale.setDefault(new Locale(language))
+      f
+    } finally {
+      Locale.setDefault(originalLocale)
+    }
+  }
+
   /**
    * Activates database `db` before executing `f`, then switches back to `default` database after
    * `f` returns.
-- 
cgit v1.2.3