viirya commented on code in PR #50430:
URL: https://github.com/apache/arrow/pull/50430#discussion_r3631308299
##########
python/pyarrow/array.pxi:
##########
@@ -3551,6 +3615,57 @@ cdef class MapArray(ListArray):
Concrete class for Arrow arrays of a map data type.
"""
+ 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)
+ if not as_dicts:
+ # Matches MapScalar.as_py with the default maps_as_pydicts=None:
+ # an association list of (key, value) tuples.
+ return [
+ (keys._getitem_py(j, None), items._getitem_py(j,
maps_as_pydicts))
+ for j in range(start, end)
+ ]
+ # Convert all keys first (as MapScalar.as_py does via keys()) and
+ # detect duplicates before converting any value, so that the 'lossy'
+ # warnings and the 'strict' KeyError are emitted at the same point as
+ # in MapScalar.as_py even when a later value conversion raises.
+ cdef int64_t count = end - start
+ cdef list keys_py = [keys._getitem_py(j, None) for j in range(start,
end)]
+ cdef dict result = {}
+ cdef int64_t k
+ if len(set(keys_py)) == count:
+ for k in range(count):
+ result[keys_py[k]] = items._getitem_py(start + k,
maps_as_pydicts)
+ return result
+ # Duplicate keys: per-key loop matching MapScalar.as_py exactly.
+ for k in range(count):
+ key = keys_py[k]
+ if key in result:
+ if maps_as_pydicts == "strict":
+ raise KeyError(
+ "Converting to Python dictionary is not supported in
strict mode "
+ f"when duplicate keys are present (duplicate key was
'{key}')."
+ )
+ else:
+ warnings.warn(
+ f"Encountered key '{key}' which was already
encountered.")
+ result[key] = items._getitem_py(start + k, maps_as_pydicts)
+ return result
Review Comment:
Good catch again — with unhashable keys `set()` raised before duplicate
detection, while `MapScalar.as_py` raises at the first dict membership test
(after a `'strict'` duplicate `KeyError`, if one comes first). Fixed in
8c3b3b44d3 exactly as you suggest: the `TypeError` from `set()` now falls back
to the per-key loop, which mirrors the Scalar ordering including where the
`TypeError` is raised. Added struct-keyed map tests asserting parity with the
Scalar path in both modes (and that the association-list mode, which involves
no hashing, is unaffected).
--
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]
