[SPARK-9170] [SQL] Use OrcStructInspector to be case preserving when writing ORC files

JIRA: https://issues.apache.org/jira/browse/SPARK-9170

`StandardStructObjectInspector` will implicitly lowercase column names. But I think Orc format doesn't have such requirement. In fact, there is a `OrcStructInspector` specified for Orc format. We should use it when serialize rows to Orc file. It can be case preserving when writing ORC files.

Author: Liang-Chi Hsieh <viirya@appier.com>

Closes #7520 from viirya/use_orcstruct.

1 files changed, 14 insertions, 0 deletions

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/OrcQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/OrcQuerySuite.scala
index 744d462938..8bc33fcf5d 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/OrcQuerySuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/OrcQuerySuite.scala
@@ -287,6 +287,20 @@ class OrcQuerySuite extends QueryTest with BeforeAndAfterAll with OrcTest {
     }
   }
 
+  test("SPARK-9170: Don't implicitly lowercase of user-provided columns") {
+    withTempPath { dir =>
+      val path = dir.getCanonicalPath
+
+      sqlContext.range(0, 10).select('id as "Acol").write.format("orc").save(path)
+      sqlContext.read.format("orc").load(path).schema("Acol")
+      intercept[IllegalArgumentException] {
+        sqlContext.read.format("orc").load(path).schema("acol")
+      }
+      checkAnswer(sqlContext.read.format("orc").load(path).select("acol").sort("acol"),
+        (0 until 10).map(Row(_)))
+    }
+  }
+
   test("SPARK-8501: Avoids discovery schema from empty ORC files") {
     withTempPath { dir =>
       val path = dir.getCanonicalPath