viirya commented on code in PR #50430:
URL: https://github.com/apache/arrow/pull/50430#discussion_r3639982715
##########
python/pyarrow/array.pxi:
##########
@@ -3618,18 +3611,49 @@ cdef class MapArray(ListArray):
Concrete class for Arrow arrays of a map data type.
"""
- cdef object _getitem_py(self, int64_t i):
+ cdef object _getitem_py(self, int64_t i, object maps_as_pydicts):
cdef CListArray* arr = <CListArray*> self.ap
+ cdef bint as_dicts = maps_as_pydicts is not None
+ if as_dicts and maps_as_pydicts != "lossy" and maps_as_pydicts !=
"strict":
+ # Matches MapScalar.as_py, which validates before the null check.
+ raise ValueError(
+ "Invalid value for 'maps_as_pydicts': "
+ + "valid values are 'lossy', 'strict' or `None` (default). "
+ + f"Received {maps_as_pydicts!r}."
+ )
if arr.IsNull(i):
return None
if self._children_cache is None:
self._children_cache = (self.keys, self.items)
cdef Array keys = <Array> (<tuple> self._children_cache)[0]
cdef Array items = <Array> (<tuple> self._children_cache)[1]
cdef int64_t j, start = arr.value_offset(i), end = arr.value_offset(i
+ 1)
- # Matches MapScalar.as_py with the default maps_as_pydicts=None:
- # an association list of (key, value) tuples.
- return [(keys._getitem_py(j), items._getitem_py(j)) for j in
range(start, end)]
+ if not as_dicts:
Review Comment:
Applied in 57e004dc54 — benchmarked both map paths after the change, no
measurable difference (tuple path 0.493 s, lossy 0.126 s on the 1M-row case).
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
