[SPARK-20156][CORE][SQL][STREAMING][MLLIB] Java String toLowerCase "Turkish locale bug" causes Spark problems

## What changes were proposed in this pull request?

Add Locale.ROOT to internal calls to String `toLowerCase`, `toUpperCase`, to avoid inadvertent locale-sensitive variation in behavior (aka the "Turkish locale problem").

The change looks large but it is just adding `Locale.ROOT` (the locale with no country or language specified) to every call to these methods.

## How was this patch tested?

Existing tests.

Author: Sean Owen <sowen@cloudera.com>

Closes #17527 from srowen/SPARK-20156.

5 files changed, 10 insertions, 7 deletions

diff --git a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java
index 1e6ac4f3df..c5ade65283 100644
--- a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java
+++ b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/HiveAuthFactory.java
@@ -24,6 +24,7 @@ import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.HashMap;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 
 import javax.net.ssl.SSLServerSocket;
@@ -259,12 +260,12 @@ public class HiveAuthFactory {
     if (thriftServerSocket.getServerSocket() instanceof SSLServerSocket) {
       List<String> sslVersionBlacklistLocal = new ArrayList<String>();
       for (String sslVersion : sslVersionBlacklist) {
-        sslVersionBlacklistLocal.add(sslVersion.trim().toLowerCase());
+        sslVersionBlacklistLocal.add(sslVersion.trim().toLowerCase(Locale.ROOT));
       }
       SSLServerSocket sslServerSocket = (SSLServerSocket) thriftServerSocket.getServerSocket();
       List<String> enabledProtocols = new ArrayList<String>();
       for (String protocol : sslServerSocket.getEnabledProtocols()) {
-        if (sslVersionBlacklistLocal.contains(protocol.toLowerCase())) {
+        if (sslVersionBlacklistLocal.contains(protocol.toLowerCase(Locale.ROOT))) {
           LOG.debug("Disabling SSL Protocol: " + protocol);
         } else {
           enabledProtocols.add(protocol);
diff --git a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/SaslQOP.java b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/SaslQOP.java
index ab3ac6285a..ad4dfd75f4 100644
--- a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/SaslQOP.java
+++ b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/auth/SaslQOP.java
@@ -19,6 +19,7 @@
 package org.apache.hive.service.auth;
 
 import java.util.HashMap;
+import java.util.Locale;
 import java.util.Map;
 
 /**
@@ -52,7 +53,7 @@ public enum SaslQOP {
 
   public static SaslQOP fromString(String str) {
     if (str != null) {
-      str = str.toLowerCase();
+      str = str.toLowerCase(Locale.ROOT);
     }
     SaslQOP saslQOP = STR_TO_ENUM.get(str);
     if (saslQOP == null) {
diff --git a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/Type.java b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/Type.java
index a96d2ac371..7752ec03a2 100644
--- a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/Type.java
+++ b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/Type.java
@@ -19,6 +19,7 @@
 package org.apache.hive.service.cli;
 
 import java.sql.DatabaseMetaData;
+import java.util.Locale;
 
 import org.apache.hadoop.hive.common.type.HiveDecimal;
 import org.apache.hive.service.cli.thrift.TTypeId;
@@ -160,7 +161,7 @@ public enum Type {
       if (name.equalsIgnoreCase(type.name)) {
         return type;
       } else if (type.isQualifiedType() || type.isComplexType()) {
-        if (name.toUpperCase().startsWith(type.name)) {
+        if (name.toUpperCase(Locale.ROOT).startsWith(type.name)) {
             return type;
         }
       }
diff --git a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2.scala b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2.scala
index 14553601b1..5e4734ad3a 100644
--- a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2.scala
+++ b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2.scala
@@ -294,7 +294,7 @@ private[hive] class HiveThriftServer2(sqlContext: SQLContext)
 
   private def isHTTPTransportMode(hiveConf: HiveConf): Boolean = {
     val transportMode = hiveConf.getVar(ConfVars.HIVE_SERVER2_TRANSPORT_MODE)
-    transportMode.toLowerCase(Locale.ENGLISH).equals("http")
+    transportMode.toLowerCase(Locale.ROOT).equals("http")
   }
 
 
diff --git a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala
index 1bc5c3c62f..d5cc3b3855 100644
--- a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala
+++ b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala
@@ -302,7 +302,7 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
 
   override def processCmd(cmd: String): Int = {
     val cmd_trimmed: String = cmd.trim()
-    val cmd_lower = cmd_trimmed.toLowerCase(Locale.ENGLISH)
+    val cmd_lower = cmd_trimmed.toLowerCase(Locale.ROOT)
     val tokens: Array[String] = cmd_trimmed.split("\\s+")
     val cmd_1: String = cmd_trimmed.substring(tokens(0).length()).trim()
     if (cmd_lower.equals("quit") ||
@@ -310,7 +310,7 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
       sessionState.close()
       System.exit(0)
     }
-    if (tokens(0).toLowerCase(Locale.ENGLISH).equals("source") ||
+    if (tokens(0).toLowerCase(Locale.ROOT).equals("source") ||
       cmd_trimmed.startsWith("!") || isRemoteMode) {
       val start = System.currentTimeMillis()
       super.processCmd(cmd)