Infer JSON as UTF-8 (#3376)

apache · Dec 20, 2022 · a8968cd · a8968cd
1 parent 9cdc1c1
commit a8968cd
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/parquet/src/arrow/schema.rs → parquet/src/arrow/schema/mod.rs b/parquet/src/arrow/schema.rs → parquet/src/arrow/schema/mod.rs
@@ -526,6 +526,7 @@ mod tests {
             OPTIONAL FLOAT   float;
             OPTIONAL BINARY  string (UTF8);
             OPTIONAL BINARY  string_2 (STRING);
+            OPTIONAL BINARY  json (JSON);
         }
         ";
         let parquet_group_type = parse_message_type(message_type).unwrap();
@@ -546,6 +547,7 @@ mod tests {
             Field::new("float", DataType::Float32, true),
             Field::new("string", DataType::Utf8, true),
             Field::new("string_2", DataType::Utf8, true),
+            Field::new("json", DataType::Utf8, true),
         ];
 
         assert_eq!(&arrow_fields, converted_arrow_schema.fields());

diff --git a/parquet/src/arrow/schema/primitive.rs b/parquet/src/arrow/schema/primitive.rs
@@ -227,11 +227,11 @@ fn from_int64(info: &BasicTypeInfo, scale: i32, precision: i32) -> Result<DataTy
 fn from_byte_array(info: &BasicTypeInfo, precision: i32, scale: i32) -> Result<DataType> {
     match (info.logical_type(), info.converted_type()) {
         (Some(LogicalType::String), _) => Ok(DataType::Utf8),
-        (Some(LogicalType::Json), _) => Ok(DataType::Binary),
+        (Some(LogicalType::Json), _) => Ok(DataType::Utf8),
         (Some(LogicalType::Bson), _) => Ok(DataType::Binary),
         (Some(LogicalType::Enum), _) => Ok(DataType::Binary),
         (None, ConvertedType::NONE) => Ok(DataType::Binary),
-        (None, ConvertedType::JSON) => Ok(DataType::Binary),
+        (None, ConvertedType::JSON) => Ok(DataType::Utf8),
         (None, ConvertedType::BSON) => Ok(DataType::Binary),
         (None, ConvertedType::ENUM) => Ok(DataType::Binary),
         (None, ConvertedType::UTF8) => Ok(DataType::Utf8),