Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/2563#discussion_r18321520
--- Diff: python/pyspark/sql.py ---
@@ -385,50 +429,32 @@ def _parse_datatype_string(datatype_string):
>>> check_datatype(complex_maptype)
True
"""
- index = datatype_string.find("(")
- if index == -1:
- # It is a primitive type.
- index = len(datatype_string)
- type_or_field = datatype_string[:index]
- rest_part = datatype_string[index + 1:len(datatype_string) - 1].strip()
-
- if type_or_field in _all_primitive_types:
- return _all_primitive_types[type_or_field]()
-
- elif type_or_field == "ArrayType":
- last_comma_index = rest_part.rfind(",")
- containsNull = True
- if rest_part[last_comma_index + 1:].strip().lower() == "false":
- containsNull = False
- elementType = _parse_datatype_string(
- rest_part[:last_comma_index].strip())
- return ArrayType(elementType, containsNull)
-
- elif type_or_field == "MapType":
- last_comma_index = rest_part.rfind(",")
- valueContainsNull = True
- if rest_part[last_comma_index + 1:].strip().lower() == "false":
- valueContainsNull = False
- keyType, valueType = _parse_datatype_list(
- rest_part[:last_comma_index].strip())
- return MapType(keyType, valueType, valueContainsNull)
-
- elif type_or_field == "StructField":
- first_comma_index = rest_part.find(",")
- name = rest_part[:first_comma_index].strip()
- last_comma_index = rest_part.rfind(",")
- nullable = True
- if rest_part[last_comma_index + 1:].strip().lower() == "false":
- nullable = False
- dataType = _parse_datatype_string(
- rest_part[first_comma_index + 1:last_comma_index].strip())
- return StructField(name, dataType, nullable)
-
- elif type_or_field == "StructType":
- # rest_part should be in the format like
- # List(StructField(field1,IntegerType,false)).
- field_list_string = rest_part[rest_part.find("(") + 1:-1]
- fields = _parse_datatype_list(field_list_string)
+ return _parse_datatype_json_value(json.loads(json_string))
+
+
+def _parse_datatype_json_value(json_value):
+ if json_value in _all_primitive_types.keys():
--- End diff --
if json_value is {}, it's not hashable, you can not use 'in' for it.
I would like to use same type of json_value for all types, such as dict,
with a key called type, such as:
```
{'type': 'int'}
```
for other types, it could have additional keys, based on the type, such as:
```
{'type':'array', 'element': {'type':'int'}, 'null': True}
```
In this ways, it will be easier to do the type switch.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
