C++ refactoring: ak.with_name (#1233)

* Worked on ak.with_name, two tests remaining to be fixed

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

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

* Renamed ak.with_name test to match the PR nr

* Fixed issue on mergemany for recordarray parameters

* Fixed all params passing in mergemany

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

src/awkward/_v2/contents/indexedarray.py

@@ -528,7 +528,7 @@ def mergemany(self, others):
         contentlength_so_far = 0
         length_so_far = 0
         nextindex = ak._v2.index.Index64.empty(total_length, self._nplike)
-        parameters = {}
+        parameters = self._parameters
 
         for array in head:
             parameters = ak._v2._util.merge_parameters(

src/awkward/_v2/contents/indexedoptionarray.py

@@ -613,7 +613,7 @@ def mergemany(self, others):
         contentlength_so_far = 0
         length_so_far = 0
         nextindex = ak._v2.index.Index64.empty(total_length, self._nplike)
-        parameters = {}
+        parameters = self._parameters
 
         for array in head:
             parameters = ak._v2._util.merge_parameters(

src/awkward/_v2/contents/recordarray.py

@@ -535,7 +535,7 @@ def mergemany(self, others):
 
         head, tail = self._merging_strategy(others)
 
-        parameters = {}
+        parameters = self._parameters
         headless = head[1:]
 
         for_each_field = []

src/awkward/_v2/contents/unionarray.py

@@ -782,7 +782,7 @@ def mergemany(self, others):
 
         nextcontents = []
         length_so_far = 0
-        parameters = {}
+        parameters = self._parameters
 
         for array in head:
             parameters = ak._v2._util.merge_parameters(

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

@@ -8,55 +8,53 @@
 
 
 def with_name(array, name, highlevel=True, behavior=None):
-    raise NotImplementedError
-
-
-#     """
-#     Args:
-#         base: Data containing records or tuples.
-#         name (str): Name to give to the records or tuples; this assigns
-#             the `"__record__"` parameter.
-#         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.
-
-#     Returns an #ak.Array or #ak.Record (or low-level equivalent, if
-#     `highlevel=False`) with a new name. This function does not change the
-#     array in-place.
-
-#     The records or tuples may be nested within multiple levels of nested lists.
-#     If records are nested within records, only the outermost are affected.
-
-#     Setting the `"__record__"` parameter makes it possible to add behaviors
-#     to the data; see #ak.Array and #ak.behavior for a more complete
-#     description.
-#     """
-
-#     def getfunction(layout):
-#         if isinstance(layout, ak._v2.contents.RecordArray):
-#             parameters = dict(layout.parameters)
-#             parameters["__record__"] = name
-#             return lambda: ak._v2.contents.RecordArray(
-#                 layout.contents,
-#                 layout.recordlookup,
-#                 len(layout),
-#                 layout.identities,
-#                 parameters,
-#             )
-#         else:
-#             return None
-
-#     out = ak._v2._util.recursively_apply(
-#         ak._v2.operations.convert.to_layout(array), getfunction, pass_depth=False
-#     )
-
-#     def getfunction2(layout):
-#         if isinstance(layout, ak._v2._util.uniontypes):
-#             return lambda: layout.simplify(merge=True, mergebool=False)
-#         else:
-#             return None
-
-#     out2 = ak._v2._util.recursively_apply(out, getfunction2, pass_depth=False)
-
-#     return ak._v2._util.maybe_wrap_like(out2, array, behavior, highlevel)
+
+    """
+    Args:
+        base: Data containing records or tuples.
+        name (str): Name to give to the records or tuples; this assigns
+            the `"__record__"` parameter.
+        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.
+
+    Returns an #ak.Array or #ak.Record (or low-level equivalent, if
+    `highlevel=False`) with a new name. This function does not change the
+    array in-place.
+
+    The records or tuples may be nested within multiple levels of nested lists.
+    If records are nested within records, only the outermost are affected.
+
+    Setting the `"__record__"` parameter makes it possible to add behaviors
+    to the data; see #ak.Array and #ak.behavior for a more complete
+    description.
+    """
+
+    layout = ak._v2.operations.convert.to_layout(array)
+
+    def action(layout, **ignore):
+        if isinstance(layout, ak._v2.contents.RecordArray):
+            parameters = dict(layout.parameters)
+            parameters["__record__"] = name
+            return ak._v2.contents.RecordArray(
+                layout.contents,
+                layout.fields,
+                len(layout),
+                layout.identifier,
+                parameters,
+            )
+        else:
+            return None
+
+    out = layout.recursively_apply(action)
+
+    def action2(layout, **ignore):
+        if layout.is_UnionType:
+            return layout.simplify_uniontype(merge=True, mergebool=False)
+        else:
+            return None
+
+    out2 = out.recursively_apply(action2)
+
+    return ak._v2._util.wrap(out2, behavior, highlevel)

tests/v2/test_0049-distinguish-record-and-recordarray-behaviors.py

@@ -0,0 +1,34 @@
+# BSD 3-Clause License; see https://github.com/scikit-hep/awkward-1.0/blob/main/LICENSE
+
+from __future__ import absolute_import
+
+import pytest  # noqa: F401
+import numpy as np  # noqa: F401
+import awkward as ak  # noqa: F401
+
+
+class Point(ak._v2.record.Record):
+    def __repr__(self):
+        return "<{} {}>".format(self["x"], self["y"])
+
+
+@pytest.mark.skip(reason="Missing check for overridden __repr__")
+def test():
+    behavior = {}
+    behavior["__typestr__", "Point"] = "P"
+    behavior["Point"] = Point
+    array = ak._v2.highlevel.Array(
+        [
+            [{"x": 1, "y": [1.1]}, {"x": 2, "y": [2.0, 0.2]}],
+            [],
+            [{"x": 3, "y": [3.0, 0.3, 3.3]}],
+        ],
+        with_name="Point",
+        behavior=behavior,
+        check_valid=True,
+    )
+    assert repr(array[0, 0]) == "<1 [1.1]>"
+    assert repr(array[0]) == "<Array [<1 [1.1]>, <2 [2, 0.2]>] type='2 * P'>"
+    assert (
+        repr(array) == "<Array [[<1 [1.1]>, ... <3 [3, 0.3, 3.3]>]] type='3 * var * P'>"
+    )

tests/v2/test_0788-indexedarray-carrying-recordarray-parameters.py

@@ -0,0 +1,29 @@
+# BSD 3-Clause License; see https://github.com/scikit-hep/awkward-1.0/blob/main/LICENSE
+
+from __future__ import absolute_import
+
+import pytest  # noqa: F401
+import numpy as np  # noqa: F401
+import awkward as ak  # noqa: F401
+
+
+def test():
+    one = ak._v2.highlevel.Array([[{"x": 1}], [], [{"x": 2}]], with_name="One")
+    two = ak._v2.highlevel.Array([[{"x": 1.1}], [], [{"x": 2.2}]], with_name="Two")
+    assert (
+        str(
+            ak._v2.operations.structure.with_name(
+                ak._v2.operations.structure.concatenate([one, two], axis=1), "All"
+            ).type
+        )
+        == "3 * var * All[x: float64]"
+    )
+    assert (
+        str(
+            ak._v2.operations.structure.with_name(
+                ak._v2.operations.structure.concatenate([one[1:], two[1:]], axis=1),
+                "All",
+            ).type
+        )
+        == "2 * var * All[x: float64]"
+    )

tests/v2/test_1233-ak-with_name.py

@@ -0,0 +1,79 @@
+# BSD 3-Clause License; see https://github.com/scikit-hep/awkward-1.0/blob/main/LICENSE
+
+from __future__ import absolute_import
+
+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_with_name():
+    array = ak._v2.highlevel.Array(
+        [
+            {"x": 0.0, "y": []},
+            {"x": 1.1, "y": [1]},
+            {"x": 2.2, "y": [2, 2]},
+            {"x": 3.3, "y": [3, 3, 3]},
+        ]
+    )
+
+    one = ak._v2.operations.structure.with_name(array, "Wilbur")
+    assert isinstance(one.layout, ak._v2.contents.Content)
+    assert one.layout.parameters["__record__"] == "Wilbur"
+
+    array2 = ak._v2.operations.convert.from_iter(
+        [
+            [[1], 2.2, [2, 2], 3.3, [3, 3, 3], 4.4, [4, 4, 4, 4]],
+            [
+                {"x": 0.0, "y": []},
+                {"x": 1.1, "y": [1]},
+                {"x": 2.2, "y": [2, 2]},
+                {"x": 3.3, "y": [3, 3, 3]},
+            ],
+        ],
+        highlevel=False,
+    )
+    one = ak._v2.operations.structure.with_name(array2, "Wilbur")
+    assert one.layout.content.contents[2].parameters["__record__"] == "Wilbur"
+
+    array = ak._v2.highlevel.Array(
+        [
+            {"a": [[0.0, 4.5], [], None], "b": []},
+            {"a": 1.1, "b": [[1]]},
+        ]
+    )
+    one = ak._v2.operations.structure.with_name(array, "James")
+    assert isinstance(one.layout, ak._v2.contents.Content)
+    assert one.layout.parameters["__record__"] == "James"
+
+
+def test_simplify_unionarray_with_name():
+    one = ak._v2.operations.convert.from_iter([5, 4, 3, 2, 1], highlevel=False)
+    two = ak._v2.operations.convert.from_iter(
+        [[], [1], [2, 2], [3, 3, 3]], highlevel=False
+    )
+    three = ak._v2.operations.convert.from_iter(
+        [
+            {"x": 0.0, "y": []},
+            {"x": 1.1, "y": [1]},
+            {"x": 2.2, "y": [2, 2]},
+            {"x": 3.3, "y": [3, 3, 3]},
+        ],
+        highlevel=False,
+    )
+
+    tags2 = ak._v2.index.Index8(np.array([0, 1, 0, 1, 0, 0, 1], dtype=np.int8))
+    index2 = ak._v2.index.Index32(np.array([0, 0, 1, 1, 2, 3, 2], dtype=np.int32))
+    inner = ak._v2.contents.UnionArray(tags2, index2, [two, three])
+    tags1 = ak._v2.index.Index8(
+        np.array([0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0], dtype=np.int8)
+    )
+    index1 = ak._v2.index.Index64(
+        np.array([0, 1, 0, 1, 2, 2, 3, 4, 5, 3, 6, 4], dtype=np.int64)
+    )
+    outer = ak._v2.contents.UnionArray(tags1, index1, [one, inner])
+    one = ak._v2.operations.structure.with_name(outer, "James")
+
+    assert outer.contents[1].is_UnionType != one.layout.contents[1].is_UnionType