diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/CatalystSchemaConverter.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/CatalystSchemaConverter.scala index 4fd3e93b70311785f72ae9ba01b61620afd6f8a6..2be7c64612cd2d068366051a329598448830f55f 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/CatalystSchemaConverter.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/CatalystSchemaConverter.scala @@ -177,7 +177,7 @@ private[parquet] class CatalystSchemaConverter( case BINARY => field.getOriginalType match { - case UTF8 => StringType + case UTF8 | ENUM => StringType case null if assumeBinaryIsString => StringType case null => BinaryType case DECIMAL => makeDecimalType() diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala index d0bfcde7e032bba86c3f0462553aa3f33be907bd..35d3c33f99a0605a35767dce266d87da87e1fa1d 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala @@ -161,6 +161,14 @@ class ParquetSchemaInferenceSuite extends ParquetSchemaTest { """.stripMargin, binaryAsString = true) + testSchemaInference[Tuple1[String]]( + "binary enum as string", + """ + |message root { + | optional binary _1 (ENUM); + |} + """.stripMargin) + testSchemaInference[Tuple1[Seq[Int]]]( "non-nullable array - non-standard", """