[SPARK-23072][SQL][TEST] Add a Unicode schema test for file-based data sources

sql/core/src/test/scala/org/apache/spark/sql/FileBasedDataSourceSuite.scala

@@ -0,0 +1,76 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql
+
+import org.apache.spark.sql.test.SharedSQLContext
+
+class FileBasedDataSourceSuite extends QueryTest with SharedSQLContext {
+  import testImplicits._
+
+  Seq("orc", "parquet", "csv", "json", "text").foreach { format =>
+    test(s"Writing empty datasets should not fail - $format") {
+      withTempPath { dir =>
+        Seq("str").toDS().limit(0).write.format(format).save(dir.getCanonicalPath)
+      }
+    }
+  }
+
+  Seq("orc", "parquet", "csv", "json").foreach { format =>
+    test(s"SPARK-23072 Write and read back unicode schema - $format") {
+      withTempPath { path =>
+        val dir = path.getCanonicalPath
+
+        // scalastyle:off nonascii
+        val df = Seq("a").toDF("한글")
+        // scalastyle:on nonascii
+
+        df.write.format(format).option("header", "true").save(dir)
+        val answerDf = spark.read.format(format).option("header", "true").load(dir)
+
+        assert(df.schema === answerDf.schema)
+        checkAnswer(df, answerDf)
+      }
+    }
+  }
+
+  Seq("orc", "parquet").foreach { format =>
+    test(s"SPARK-15474 Write and read back non-emtpy schema with empty dataframe - $format") {
+      withTempPath { file =>
+        val path = file.getCanonicalPath
+        val emptyDf = Seq((true, 1, "str")).toDF().limit(0)
+        emptyDf.write.format(format).save(path)
+
+        val df = spark.read.format(format).load(path)
+        assert(df.schema.sameType(emptyDf.schema))
+        checkAnswer(df, emptyDf)
+      }
+    }
+  }
+
+  Seq("orc", "parquet", "csv", "json", "text").foreach { format =>
+    test(s"SPARK-22146 read files containing special characters using $format") {
+      val nameWithSpecialChars = s"sp&cial%chars"
+      withTempDir { dir =>
+        val tmpFile = s"$dir/$nameWithSpecialChars"
+        spark.createDataset(Seq("a", "b")).write.format(format).save(tmpFile)
+        val fileContent = spark.read.format(format).load(tmpFile)
+        checkAnswer(fileContent, Seq(Row("a"), Row("b")))
+      }
+    }
+  }
+}

sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala

@@ -2757,20 +2757,4 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext {
       }
     }
   }
-
-  // Only New OrcFileFormat supports this
-  Seq(classOf[org.apache.spark.sql.execution.datasources.orc.OrcFileFormat].getCanonicalName,
-      "parquet").foreach { format =>
-    test(s"SPARK-15474 Write and read back non-emtpy schema with empty dataframe - $format") {
-      withTempPath { file =>
-        val path = file.getCanonicalPath
-        val emptyDf = Seq((true, 1, "str")).toDF.limit(0)
-        emptyDf.write.format(format).save(path)
-
-        val df = spark.read.format(format).load(path)
-        assert(df.schema.sameType(emptyDf.schema))
-        checkAnswer(df, emptyDf)
-      }
-    }
-  }
 }

sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala

@@ -23,14 +23,12 @@ import scala.collection.mutable.ArrayBuffer
 
 import org.apache.hadoop.fs.Path
 
-import org.apache.spark.SparkContext
 import org.apache.spark.sql._
 import org.apache.spark.sql.catalyst.TableIdentifier
 import org.apache.spark.sql.catalyst.catalog.{CatalogStorageFormat, CatalogTable, CatalogTableType}
 import org.apache.spark.sql.execution.command.CreateTableCommand
 import org.apache.spark.sql.execution.datasources.{HadoopFsRelation, LogicalRelation}
 import org.apache.spark.sql.hive.HiveExternalCatalog._
-import org.apache.spark.sql.hive.client.HiveClient
 import org.apache.spark.sql.hive.test.TestHiveSingleton
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.internal.StaticSQLConf._
@@ -1344,18 +1342,6 @@ class MetastoreDataSourcesSuite extends QueryTest with SQLTestUtils with TestHiv
     }
   }
 
-  Seq("orc", "parquet", "csv", "json", "text").foreach { format =>
-    test(s"SPARK-22146: read files containing special characters using $format") {
-      val nameWithSpecialChars = s"sp&cial%chars"
-      withTempDir { dir =>
-        val tmpFile = s"$dir/$nameWithSpecialChars"
-        spark.createDataset(Seq("a", "b")).write.format(format).save(tmpFile)
-        val fileContent = spark.read.format(format).load(tmpFile)
-        checkAnswer(fileContent, Seq(Row("a"), Row("b")))
-      }
-    }
-  }
-
   private def withDebugMode(f: => Unit): Unit = {
     val previousValue = sparkSession.sparkContext.conf.get(DEBUG_MODE)
     try {

sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala

@@ -2159,12 +2159,4 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
       }
     }
   }
-
-  Seq("orc", "parquet", "csv", "json", "text").foreach { format =>
-    test(s"Writing empty datasets should not fail - $format") {
-      withTempDir { dir =>
-        Seq("str").toDS.limit(0).write.format(format).save(dir.getCanonicalPath + "/tmp")
-      }
-    }
-  }
 }