bug fix: mergeWithMetastoreSchema with Uuniform lower case comparison

(cherry picked from commit f47a765)
apache · Mar 7, 2019 · dec978d · dec978d
1 parent a0e26cf
commit dec978d
Show file tree

Hide file tree

Showing 2 changed files with 27 additions and 1 deletion.
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala
@@ -326,8 +326,8 @@ private[hive] object HiveMetastoreCatalog {
     // Merge missing nullable fields to inferred schema and build a case-insensitive field map.
     val inferredFields = StructType(inferredSchema ++ missingNullables)
       .map(f => f.name.toLowerCase -> f).toMap
+    StructType(metastoreSchema.map(f => f.copy(name = inferredFields(f.name.toLowerCase).name)))
     // scalastyle:on caselocale
-    StructType(metastoreSchema.map(f => f.copy(name = inferredFields(f.name).name)))
   } catch {
     case NonFatal(_) =>
       val msg = s"""Detected conflicting schemas when merging the schema obtained from the Hive

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveSchemaInferenceSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveSchemaInferenceSuite.scala
@@ -264,6 +264,32 @@ class HiveSchemaInferenceSuite
         StructType(Seq(StructField("lowerCase", BinaryType))))
     }
 
+    // Parquet schema is subset of metaStore schema and has uppercase field name
+    assertResult(
+      StructType(Seq(
+        StructField("UPPERCase", DoubleType, nullable = true),
+        StructField("lowerCase", BinaryType, nullable = true)))) {
+
+      HiveMetastoreCatalog.mergeWithMetastoreSchema(
+        StructType(Seq(
+          StructField("UPPERCase", DoubleType, nullable = true),
+          StructField("lowerCase", BinaryType, nullable = true))),
+
+        StructType(Seq(
+          StructField("lowerCase", BinaryType, nullable = true))))
+    }
+
+    // Metastore schema contains additional nullable fields.
+    assert(intercept[Throwable] {
+      HiveMetastoreCatalog.mergeWithMetastoreSchema(
+        StructType(Seq(
+          StructField("UPPERCase", DoubleType, nullable = false),
+          StructField("lowerCase", BinaryType, nullable = true))),
+
+        StructType(Seq(
+          StructField("lowerCase", BinaryType, nullable = true))))
+    }.getMessage.contains("Detected conflicting schemas"))
+
     // Check that merging missing nullable fields works as expected.
     assertResult(
       StructType(Seq(