cloud-fan commented on code in PR #46280: URL: https://github.com/apache/spark/pull/46280#discussion_r1603406813
########## sql/catalyst/src/test/scala/org/apache/spark/sql/types/DataTypeSuite.scala: ########## @@ -712,4 +714,181 @@ class DataTypeSuite extends SparkFunSuite { assert(result === expected) } + + test("schema with collation should not change during ser/de") { + val simpleStruct = StructType( + StructField("c1", StringType(UNICODE_COLLATION_ID)) :: Nil) + + val nestedStruct = StructType( + StructField("nested", simpleStruct) :: Nil) + + val caseInsensitiveNames = StructType( + StructField("c1", StringType(UNICODE_COLLATION_ID)) :: + StructField("C1", StringType(UNICODE_COLLATION_ID)) :: Nil) + + val specialCharsInName = StructType( + StructField("c1.*23?", StringType(UNICODE_COLLATION_ID)) :: Nil) + + val arrayInSchema = StructType( + StructField("arrayField", ArrayType(StringType(UNICODE_COLLATION_ID))) :: Nil) + + val mapInSchema = StructType( + StructField("mapField", + MapType(StringType(UNICODE_COLLATION_ID), StringType(UNICODE_COLLATION_ID))) :: Nil) + + val mapWithKeyInNameInSchema = StructType( + StructField("name.key", StringType) :: + StructField("name", + MapType(StringType(UNICODE_COLLATION_ID), StringType(UNICODE_COLLATION_ID))) :: Nil) + + val arrayInMapInNestedSchema = StructType( + StructField("arrInMap", + MapType(StringType(UNICODE_COLLATION_ID), + ArrayType(StringType(UNICODE_COLLATION_ID)))) :: Nil) + + val nestedArrayInMap = StructType( + StructField("nestedArrayInMap", + ArrayType(MapType(StringType(UNICODE_COLLATION_ID), + ArrayType(ArrayType(StringType(UNICODE_COLLATION_ID)))))) :: Nil) + + val schemaWithMultipleFields = StructType( + simpleStruct.fields ++ nestedStruct.fields ++ arrayInSchema.fields ++ mapInSchema.fields ++ + mapWithKeyInNameInSchema ++ arrayInMapInNestedSchema.fields ++ nestedArrayInMap.fields) + + Seq( + simpleStruct, caseInsensitiveNames, specialCharsInName, nestedStruct, arrayInSchema, + mapInSchema, mapWithKeyInNameInSchema, nestedArrayInMap, arrayInMapInNestedSchema, + schemaWithMultipleFields) + .foreach { schema => + val json = schema.json + val parsed = DataType.fromJson(json) + assert(parsed === schema) + } + } + + test("non string field has collation metadata") { Review Comment: how do we decide to put test in here or `StructTypeSuite`? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org