Copilot commented on code in PR #50430:
URL: https://github.com/apache/arrow/pull/50430#discussion_r3552600127
##########
python/pyarrow/array.pxi:
##########
@@ -3551,6 +3615,52 @@ 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)
+ ]
+ cdef dict result = {}
+ for j in range(start, end):
+ result[keys._getitem_py(j, None)] = items._getitem_py(j,
maps_as_pydicts)
+ if len(result) == end - start:
+ return result
+ # Duplicate keys: redo the row with the per-key loop so the 'lossy'
+ # warnings and 'strict' KeyError match MapScalar.as_py exactly.
+ result = {}
+ for j in range(start, end):
+ key = keys._getitem_py(j, None)
+ 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(j, maps_as_pydicts)
+ return result
Review Comment:
MapArray._getitem_py currently builds the dict in a first pass that converts
*all* values before checking for duplicate keys. This can change semantics vs
MapScalar.as_py: in strict mode a duplicate key should raise KeyError before
converting the duplicate value (and before any later value conversions), and in
lossy mode the warning should be emitted before converting the duplicate value.
If a value conversion can raise (e.g. nested maps/scalars), the current first
pass can raise a different exception or raise before the warning/KeyError.
--
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]
