[SPARK-8286] Rewrite UTF8String in Java and move it into unsafe package.

Unit test is still in Scala.

Author: Reynold Xin <rxin@databricks.com>

Closes #6738 from rxin/utf8string-java and squashes the following commits:

562dc6e [Reynold Xin] Flag...
98e600b [Reynold Xin] Another try with encoding setting ..
cfa6bdf [Reynold Xin] Merge branch 'master' into utf8string-java
a3b124d [Reynold Xin] Try different UTF-8 encoded characters.
1ff7c82 [Reynold Xin] Enable UTF-8 encoding.
82d58cc [Reynold Xin] Reset run-tests.
2cb3c69 [Reynold Xin] Use utf-8 encoding in set bytes.
53f8ef4 [Reynold Xin] Hack Jenkins to run one test.
9a48e8d [Reynold Xin] Fixed runtime compilation error.
911c450 [Reynold Xin] Moved unit test also to Java.
4eff7bd [Reynold Xin] Improved unit test coverage.
8e89a3c [Reynold Xin] Fixed tests.
77c64bd [Reynold Xin] Fixed string type codegen.
ffedb62 [Reynold Xin] Code review feedback.
0967ce6 [Reynold Xin] Fixed import ordering.
45a123d [Reynold Xin] [SPARK-8286] Rewrite UTF8String in Java and move it into unsafe package.

1 files changed, 7 insertions, 6 deletions

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
index 1f14cba78f..fd01a8722b 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
@@ -28,6 +28,7 @@ import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.util.DateUtils
 import org.apache.spark.sql.types
 import org.apache.spark.sql.types._
+import org.apache.spark.unsafe.types.UTF8String
 
 /* Implicit conversions */
 import scala.collection.JavaConversions._
@@ -242,9 +243,9 @@ private[hive] trait HiveInspectors {
   def unwrap(data: Any, oi: ObjectInspector): Any = oi match {
     case coi: ConstantObjectInspector if coi.getWritableConstantValue == null => null
     case poi: WritableConstantStringObjectInspector =>
-      UTF8String(poi.getWritableConstantValue.toString)
+      UTF8String.fromString(poi.getWritableConstantValue.toString)
     case poi: WritableConstantHiveVarcharObjectInspector =>
-      UTF8String(poi.getWritableConstantValue.getHiveVarchar.getValue)
+      UTF8String.fromString(poi.getWritableConstantValue.getHiveVarchar.getValue)
     case poi: WritableConstantHiveDecimalObjectInspector =>
       HiveShim.toCatalystDecimal(
         PrimitiveObjectInspectorFactory.javaHiveDecimalObjectInspector,
@@ -288,13 +289,13 @@ private[hive] trait HiveInspectors {
     case pi: PrimitiveObjectInspector => pi match {
       // We think HiveVarchar is also a String
       case hvoi: HiveVarcharObjectInspector if hvoi.preferWritable() =>
-        UTF8String(hvoi.getPrimitiveWritableObject(data).getHiveVarchar.getValue)
+        UTF8String.fromString(hvoi.getPrimitiveWritableObject(data).getHiveVarchar.getValue)
       case hvoi: HiveVarcharObjectInspector =>
-        UTF8String(hvoi.getPrimitiveJavaObject(data).getValue)
+        UTF8String.fromString(hvoi.getPrimitiveJavaObject(data).getValue)
       case x: StringObjectInspector if x.preferWritable() =>
-        UTF8String(x.getPrimitiveWritableObject(data).toString)
+        UTF8String.fromString(x.getPrimitiveWritableObject(data).toString)
       case x: StringObjectInspector =>
-        UTF8String(x.getPrimitiveJavaObject(data))
+        UTF8String.fromString(x.getPrimitiveJavaObject(data))
       case x: IntObjectInspector if x.preferWritable() => x.get(data)
       case x: BooleanObjectInspector if x.preferWritable() => x.get(data)
       case x: FloatObjectInspector if x.preferWritable() => x.get(data)