diff --git a/python/pyspark/sql/types.py b/python/pyspark/sql/types.py index 6f74b7162f7cc48887cd4f2ae0e7c0731d0fa86a..e2e6f03ae9fd78daab2460afe5ea16325b6b05fb 100644 --- a/python/pyspark/sql/types.py +++ b/python/pyspark/sql/types.py @@ -1197,13 +1197,36 @@ class Row(tuple): else: raise ValueError("No args or kwargs") - def asDict(self): + def asDict(self, recursive=False): """ Return as an dict + + :param recursive: turns the nested Row as dict (default: False). + + >>> Row(name="Alice", age=11).asDict() == {'name': 'Alice', 'age': 11} + True + >>> row = Row(key=1, value=Row(name='a', age=2)) + >>> row.asDict() == {'key': 1, 'value': Row(age=2, name='a')} + True + >>> row.asDict(True) == {'key': 1, 'value': {'name': 'a', 'age': 2}} + True """ if not hasattr(self, "__fields__"): raise TypeError("Cannot convert a Row class into dict") - return dict(zip(self.__fields__, self)) + + if recursive: + def conv(obj): + if isinstance(obj, Row): + return obj.asDict(True) + elif isinstance(obj, list): + return [conv(o) for o in obj] + elif isinstance(obj, dict): + return dict((k, conv(v)) for k, v in obj.items()) + else: + return obj + return dict(zip(self.__fields__, (conv(o) for o in self))) + else: + return dict(zip(self.__fields__, self)) # let object acts like class def __call__(self, *args):