C++ refactoring: ak.unzip (#1354)

* ak.unzip and testing

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

src/awkward/_v2/operations/structure/ak_unzip.py

@@ -6,70 +6,62 @@
 
 
 def unzip(array, highlevel=True, behavior=None):
-    raise ak._v2._util.error(NotImplementedError)
-
-    # """
-    # Args:
-    #     array: Array to unzip into individual fields.
-    #     highlevel (bool): If True, return an #ak.Array; otherwise, return
-    #         a low-level #ak.layout.Content subclass.
-    #     behavior (None or dict): Custom #ak.behavior for the output array, if
-    #         high-level.
-
-    # If the `array` contains tuples or records, this operation splits them
-    # into a Python tuple of arrays, one for each field.
-
-    # If the `array` does not contain tuples or records, the single `array`
-    # is placed in a length 1 Python tuple.
-
-    # For example,
-
-    #     >>> array = ak.Array([{"x": 1.1, "y": [1]},
-    #     ...                   {"x": 2.2, "y": [2, 2]},
-    #     ...                   {"x": 3.3, "y": [3, 3, 3]}])
-    #     >>> x, y = ak.unzip(array)
-    #     >>> x
-    #     <Array [1.1, 2.2, 3.3] type='3 * float64'>
-    #     >>> y
-    #     <Array [[1], [2, 2], [3, 3, 3]] type='3 * var * int64'>
-    # """
-    # behavior = ak._util.behaviorof(array, behavior=behavior)
-    # layout = ak.operations.convert.to_layout(array, allow_record=True, allow_other=False)
-    # fields = ak.operations.describe.fields(layout)
-
-    ### FIXME: In v2, you can use return_array=False in Content.recursively_apply
-    ###        to perform an action on the whole array but not return a result.
-    ###        No need for (brittle) specialized code like the following.
-
-    # def check_for_union(layout):
-    #     if isinstance(layout, ak.partition.PartitionedArray):
-    #         for x in layout.partitions:
-    #             check_for_union(x)
-
-    #     elif isinstance(layout, ak.layout.RecordArray):
-    #         pass  # don't descend into nested records
-
-    #     elif isinstance(layout, ak.layout.Record):
-    #         pass  # don't descend into nested records
-
-    #     elif isinstance(
-    #         layout,
-    #         (
-    #             ak.layout.UnionArray8_32,
-    #             ak.layout.UnionArray8_U32,
-    #             ak.layout.UnionArray8_64,
-    #         ),
-    #     ):
-    #         for content in layout.contents:
-    #             if set(ak.operations.describe.fields(content)) != set(fields):
-    #                 raise ak._v2._util.error(ValueError("union of different sets of fields, cannot ak.unzip"))
-
-    #     elif hasattr(layout, "content"):
-    #         check_for_union(layout.content)
-
-    # check_for_union(layout)
-
-    # if len(fields) == 0:
-    #     return (ak._util.maybe_wrap(layout, behavior, highlevel),)
-    # else:
-    #     return tuple(ak._util.maybe_wrap(layout[n], behavior, highlevel) for n in fields)
+    """
+    Args:
+        array: Array to unzip into individual fields.
+        highlevel (bool): If True, return an #ak.Array; otherwise, return
+            a low-level #ak.layout.Content subclass.
+        behavior (None or dict): Custom #ak.behavior for the output array, if
+            high-level.
+
+    If the `array` contains tuples or records, this operation splits them
+    into a Python tuple of arrays, one for each field.
+
+    If the `array` does not contain tuples or records, the single `array`
+    is placed in a length 1 Python tuple.
+
+    For example,
+
+        >>> array = ak.Array([{"x": 1.1, "y": [1]},
+        ...                   {"x": 2.2, "y": [2, 2]},
+        ...                   {"x": 3.3, "y": [3, 3, 3]}])
+        >>> x, y = ak.unzip(array)
+        >>> x
+        <Array [1.1, 2.2, 3.3] type='3 * float64'>
+        >>> y
+        <Array [[1], [2, 2], [3, 3, 3]] type='3 * var * int64'>
+    """
+    with ak._v2._util.OperationErrorContext(
+        "ak._v2.unzip",
+        dict(array=array, highlevel=highlevel, behavior=behavior),
+    ):
+        return _impl(array, highlevel, behavior)
+
+
+def _impl(array, highlevel, behavior):
+    behavior = ak._v2._util.behavior_of(array, behavior=behavior)
+    layout = ak._v2.operations.convert.to_layout(
+        array, allow_record=True, allow_other=False
+    )
+    fields = ak._v2.operations.describe.fields(layout)
+
+    def check_for_union(layout, **kwargs):
+        if isinstance(layout, (ak._v2.contents.RecordArray, ak._v2.Record)):
+            pass  # don't descend into nested records
+
+        elif isinstance(layout, ak._v2.contents.UnionArray):
+            for content in layout.contents:
+                if set(ak.operations.describe.fields(content)) != set(fields):
+                    raise ak._v2._util.error(
+                        ValueError("union of different sets of fields, cannot ak.unzip")
+                    )
+
+        elif hasattr(layout, "content"):
+            check_for_union(layout.content)
+
+    layout.recursively_apply(check_for_union, return_array=False)
+
+    if len(fields) == 0:
+        return (ak._v2._util.wrap(layout, behavior, highlevel),)
+    else:
+        return tuple(ak._v2._util.wrap(layout[n], behavior, highlevel) for n in fields)

tests/v2/test_0898-unzip-heterogeneous-records.py

@@ -0,0 +1,59 @@
+# BSD 3-Clause License; see https://github.com/scikit-hep/awkward-1.0/blob/main/LICENSE
+
+
+import pytest  # noqa: F401
+import numpy as np  # noqa: F401
+import awkward as ak  # noqa: F401
+
+to_list = ak._v2.operations.convert.to_list
+
+
+def test():
+    a = ak._v2.Array([{"this": 100}])
+    b = ak._v2.Array([{"this": 90, "that": 100}])
+    c = ak._v2.operations.structure.concatenate((a, b))
+
+    with pytest.raises(ValueError):
+        ak._v2.operations.structure.unzip(c)
+
+    a = ak._v2.Array([{"this": 100}])
+    b = ak._v2.Array([{"this": 90}])
+    c = ak._v2.operations.structure.concatenate((a, b))
+
+    (tmp,) = ak._v2.operations.structure.unzip(c)
+
+    assert tmp.tolist() == [100, 90]
+
+
+def test_zip_and_unzip():
+    x = ak._v2.Array([[1, 2, 3], [], [4, 5], [6], [7, 8, 9, 10]])
+    y = ak._v2.Array([1.1, 2.2, 3.3, 4.4, 5.5])
+
+    one = ak._v2.operations.structure.zip({"x": x, "y": y})
+    two = ak._v2.operations.structure.zip({"x": x, "y": y}, depth_limit=1)
+    xx, yy = ak._v2.operations.structure.unzip(two)
+    assert isinstance(one.layout, ak._v2.contents.Content)
+    assert isinstance(two.layout, ak._v2.contents.Content)
+    assert isinstance(xx.layout, ak._v2.contents.Content)
+    assert isinstance(yy.layout, ak._v2.contents.Content)
+    assert to_list(one) == [
+        [{"x": 1, "y": 1.1}, {"x": 2, "y": 1.1}, {"x": 3, "y": 1.1}],
+        [],
+        [{"x": 4, "y": 3.3}, {"x": 5, "y": 3.3}],
+        [{"x": 6, "y": 4.4}],
+        [
+            {"x": 7, "y": 5.5},
+            {"x": 8, "y": 5.5},
+            {"x": 9, "y": 5.5},
+            {"x": 10, "y": 5.5},
+        ],
+    ]
+    assert to_list(two) == [
+        {"x": [1, 2, 3], "y": 1.1},
+        {"x": [], "y": 2.2},
+        {"x": [4, 5], "y": 3.3},
+        {"x": [6], "y": 4.4},
+        {"x": [7, 8, 9, 10], "y": 5.5},
+    ]
+    assert to_list(xx) == [[1, 2, 3], [], [4, 5], [6], [7, 8, 9, 10]]
+    assert to_list(yy) == [1.1, 2.2, 3.3, 4.4, 5.5]