viirya commented on code in PR #50327:
URL: https://github.com/apache/arrow/pull/50327#discussion_r3630948471
##########
python/pyarrow/tests/test_array.py:
##########
@@ -465,6 +465,56 @@ def test_array_getitem_numpy_scalars():
assert arr[np.int32(idx)].as_py() == lst[idx]
+def test_to_pylist_bulk_paths():
+ # GH-50326: to_pylist converts through scalar-free _getitem_py
+ # specializations; the result must match the per-scalar conversion
+ # exactly.
+ arrays = [
+ pa.array([[1, None, 3], None, [], [4]], type=pa.list_(pa.int32())),
+ pa.array([["a", None], None, [], ["bcd", ""]],
+ type=pa.list_(pa.string())),
+ pa.array([["a", None], None, [], ["bcd", ""]],
+ type=pa.large_list(pa.large_string())),
+ pa.array([[1, None], None, [3, 4]], type=pa.list_(pa.int32(), 2)),
+ pa.array([[[1], [2, None]], None, [None, [3]]],
+ type=pa.list_(pa.list_(pa.int32()))),
+ pa.array([[("k1", 1), ("k2", None)], None, []],
+ type=pa.map_(pa.string(), pa.int32())),
+ pa.array(["a", None, "", "\N{GRINNING FACE} \N{SNOWMAN}"],
+ type=pa.string()),
+ pa.array(["a", None, "", "\N{GRINNING FACE} \N{SNOWMAN}"],
+ type=pa.large_string()),
+ pa.array([b"a\x00b", None, b"", b"\xff"], type=pa.binary()),
+ pa.array([b"a\x00b", None, b""], type=pa.large_binary()),
+ pa.array([[b"x", None, b"\x00y"], None, []],
+ type=pa.list_(pa.binary())),
+ pa.array([1, None, -(2**62), 2**62], type=pa.int64()),
+ pa.array([0, None, 2**63 + 7], type=pa.uint64()),
+ pa.array([-128, 127, None], type=pa.int8()),
+ pa.array([1.5, None, -0.5], type=pa.float64()),
+ pa.array([1.5, None], type=pa.float32()),
+ pa.array([True, None, False], type=pa.bool_()),
+ pa.array([{"a": 1, "b": "x"}, None, {"a": None, "b": None}],
+ type=pa.struct([("a", pa.int32()), ("b", pa.string())])),
+ pa.array([], type=pa.list_(pa.int32())),
+ pa.array([None, None], type=pa.list_(pa.string())),
+ ]
Review Comment:
You're right, apologies — 3d303ce487's commit message described these test
changes but `test_array.py` never made it into that commit, and I replied
without re-checking the pushed diff. Now actually added in 1d80beb925
(string_view/binary_view cases covering inline and out-of-line values; verified
the view specializations engage — ~13x faster than the per-Scalar path on 1M
rows).
--
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]
