[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, 18 insertions, 8 deletions

diff --git a/sql/catalyst/src/test/java/org/apache/spark/sql/streaming/JavaOutputModeSuite.java b/sql/catalyst/src/test/java/org/apache/spark/sql/streaming/JavaOutputModeSuite.java
index e0a54fe30a..d8845e0c83 100644
--- a/sql/catalyst/src/test/java/org/apache/spark/sql/streaming/JavaOutputModeSuite.java
+++ b/sql/catalyst/src/test/java/org/apache/spark/sql/streaming/JavaOutputModeSuite.java
@@ -17,6 +17,8 @@
 
 package org.apache.spark.sql.streaming;
 
+import java.util.Locale;
+
 import org.junit.Test;
 
 public class JavaOutputModeSuite {
@@ -24,8 +26,8 @@ public class JavaOutputModeSuite {
   @Test
   public void testOutputModes() {
     OutputMode o1 = OutputMode.Append();
-    assert(o1.toString().toLowerCase().contains("append"));
+    assert(o1.toString().toLowerCase(Locale.ROOT).contains("append"));
     OutputMode o2 = OutputMode.Complete();
-    assert (o2.toString().toLowerCase().contains("complete"));
+    assert (o2.toString().toLowerCase(Locale.ROOT).contains("complete"));
   }
 }
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisTest.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisTest.scala
index 1be25ec06c..82015b1e06 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisTest.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisTest.scala
@@ -17,6 +17,8 @@
 
 package org.apache.spark.sql.catalyst.analysis
 
+import java.util.Locale
+
 import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.catalog.{InMemoryCatalog, SessionCatalog}
 import org.apache.spark.sql.catalyst.plans.PlanTest
@@ -79,7 +81,8 @@ trait AnalysisTest extends PlanTest {
       analyzer.checkAnalysis(analyzer.execute(inputPlan))
     }
 
-    if (!expectedErrors.map(_.toLowerCase).forall(e.getMessage.toLowerCase.contains)) {
+    if (!expectedErrors.map(_.toLowerCase(Locale.ROOT)).forall(
+        e.getMessage.toLowerCase(Locale.ROOT).contains)) {
       fail(
         s"""Exception message should contain the following substrings:
            |
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationsSuite.scala
index 8f0a0c0d99..c39e372c27 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationsSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationsSuite.scala
@@ -17,19 +17,20 @@
 
 package org.apache.spark.sql.catalyst.analysis
 
+import java.util.Locale
+
 import org.apache.spark.SparkFunSuite
 import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.dsl.plans._
 import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
-import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference, Literal, NamedExpression}
+import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference, NamedExpression}
 import org.apache.spark.sql.catalyst.expressions.aggregate.Count
 import org.apache.spark.sql.catalyst.plans._
 import org.apache.spark.sql.catalyst.plans.logical.{FlatMapGroupsWithState, _}
 import org.apache.spark.sql.catalyst.streaming.InternalOutputModes._
 import org.apache.spark.sql.streaming.OutputMode
 import org.apache.spark.sql.types.{IntegerType, LongType, MetadataBuilder}
-import org.apache.spark.unsafe.types.CalendarInterval
 
 /** A dummy command for testing unsupported operations. */
 case class DummyCommand() extends Command
@@ -696,7 +697,7 @@ class UnsupportedOperationsSuite extends SparkFunSuite {
         testBody
       }
       expectedMsgs.foreach { m =>
-        if (!e.getMessage.toLowerCase.contains(m.toLowerCase)) {
+        if (!e.getMessage.toLowerCase(Locale.ROOT).contains(m.toLowerCase(Locale.ROOT))) {
           fail(s"Exception message should contain: '$m', " +
             s"actual exception message:\n\t'${e.getMessage}'")
         }
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDFSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDFSuite.scala
index 7e45028653..13bd363c8b 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDFSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ScalaUDFSuite.scala
@@ -17,6 +17,8 @@
 
 package org.apache.spark.sql.catalyst.expressions
 
+import java.util.Locale
+
 import org.apache.spark.{SparkException, SparkFunSuite}
 import org.apache.spark.sql.types.{IntegerType, StringType}
 
@@ -32,7 +34,7 @@ class ScalaUDFSuite extends SparkFunSuite with ExpressionEvalHelper {
 
   test("better error message for NPE") {
     val udf = ScalaUDF(
-      (s: String) => s.toLowerCase,
+      (s: String) => s.toLowerCase(Locale.ROOT),
       StringType,
       Literal.create(null, StringType) :: Nil)
 
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/streaming/InternalOutputModesSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/streaming/InternalOutputModesSuite.scala
index 201dac35ed..3159b541dc 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/streaming/InternalOutputModesSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/streaming/InternalOutputModesSuite.scala
@@ -17,6 +17,8 @@
 
 package org.apache.spark.sql.catalyst.streaming
 
+import java.util.Locale
+
 import org.apache.spark.SparkFunSuite
 import org.apache.spark.sql.streaming.OutputMode
 
@@ -40,7 +42,7 @@ class InternalOutputModesSuite extends SparkFunSuite {
       val acceptedModes = Seq("append", "update", "complete")
       val e = intercept[IllegalArgumentException](InternalOutputModes(outputMode))
       (Seq("output mode", "unknown", outputMode) ++ acceptedModes).foreach { s =>
-        assert(e.getMessage.toLowerCase.contains(s.toLowerCase))
+        assert(e.getMessage.toLowerCase(Locale.ROOT).contains(s.toLowerCase(Locale.ROOT)))
       }
     }
     testMode("Xyz")