[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.

2 files changed, 7 insertions, 3 deletions

diff --git a/common/network-common/src/main/java/org/apache/spark/network/util/JavaUtils.java b/common/network-common/src/main/java/org/apache/spark/network/util/JavaUtils.java
index 51d7fda0cb..afc59efaef 100644
--- a/common/network-common/src/main/java/org/apache/spark/network/util/JavaUtils.java
+++ b/common/network-common/src/main/java/org/apache/spark/network/util/JavaUtils.java
@@ -24,6 +24,7 @@ import java.io.IOException;
 import java.nio.ByteBuffer;
 import java.nio.channels.ReadableByteChannel;
 import java.nio.charset.StandardCharsets;
+import java.util.Locale;
 import java.util.concurrent.TimeUnit;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
@@ -210,7 +211,7 @@ public class JavaUtils {
    * The unit is also considered the default if the given string does not specify a unit.
    */
   public static long timeStringAs(String str, TimeUnit unit) {
-    String lower = str.toLowerCase().trim();
+    String lower = str.toLowerCase(Locale.ROOT).trim();
 
     try {
       Matcher m = Pattern.compile("(-?[0-9]+)([a-z]+)?").matcher(lower);
@@ -258,7 +259,7 @@ public class JavaUtils {
    * provided, a direct conversion to the provided unit is attempted.
    */
   public static long byteStringAs(String str, ByteUnit unit) {
-    String lower = str.toLowerCase().trim();
+    String lower = str.toLowerCase(Locale.ROOT).trim();
 
     try {
       Matcher m = Pattern.compile("([0-9]+)([a-z]+)?").matcher(lower);
diff --git a/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java b/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java
index c226d8f3bc..a25078e262 100644
--- a/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java
+++ b/common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java
@@ -17,6 +17,7 @@
 
 package org.apache.spark.network.util;
 
+import java.util.Locale;
 import java.util.Properties;
 
 import com.google.common.primitives.Ints;
@@ -75,7 +76,9 @@ public class TransportConf {
   }
 
   /** IO mode: nio or epoll */
-  public String ioMode() { return conf.get(SPARK_NETWORK_IO_MODE_KEY, "NIO").toUpperCase(); }
+  public String ioMode() {
+    return conf.get(SPARK_NETWORK_IO_MODE_KEY, "NIO").toUpperCase(Locale.ROOT);
+  }
 
   /** If true, we will prefer allocating off-heap byte buffers within Netty. */
   public boolean preferDirectBufs() {