GH-50312: [Python] Fix UUID extension type round-trip to pandas returning bytes

Author: parker-cassar

python/pyarrow/pandas_compat.py

@@ -780,6 +780,13 @@ def _reconstruct_block(item, columns=None, extension_columns=None, return_block=
             raise ValueError("This column does not support to be converted "
                              "to a pandas ExtensionArray")
         arr = pandas_dtype.__from_arrow__(arr)
+        if isinstance(arr, np.ndarray) and arr.ndim == 1:
+            # A plain (non-ExtensionArray) 1-D result — e.g. from the UUID
+            # extension type — must be reshaped to the (1, n) single-column
+            # block layout that make_block and create_dataframe_from_blocks
+            # expect. pandas ExtensionArrays are 1-D and handled directly, so
+            # they are intentionally left untouched here.
+            arr = arr.reshape(1, -1)
     else:
         arr = block_arr
 

python/pyarrow/tests/parquet/test_data_types.py

@@ -604,6 +604,39 @@ def test_uuid_extension_type():
         store_schema=False)
 
 
+@pytest.mark.pandas
+def test_uuid_roundtrip(tempdir):
+    import uuid
+    u1, u2 = uuid.uuid4(), uuid.uuid4()
+    df = pd.DataFrame({"id": [u1, None, u2]})
+    table = pa.Table.from_pandas(df)
+    assert table.column("id").type == pa.uuid()
+
+    path = tempdir / "uuid_pandas_roundtrip.parquet"
+    pq.write_table(table, path)
+    read_table = pq.read_table(path)
+    assert read_table.column("id").type == pa.uuid()
+
+    result_df = read_table.to_pandas()
+    assert isinstance(result_df.loc[0, "id"], uuid.UUID)
+    assert isinstance(result_df.loc[2, "id"], uuid.UUID)
+    assert result_df.loc[0, "id"] == u1
+    assert result_df.loc[2, "id"] == u2
+    assert pd.isna(result_df.loc[1, "id"])
+
+
+@pytest.mark.pandas
+def test_uuid_array_to_pandas():
+    from uuid import uuid4
+    import pandas as pd
+    import pandas.testing as tm
+    values = [uuid4(), None, uuid4()]
+    arr = pa.array(values, type=pa.uuid())
+    result = arr.to_pandas()
+    expected = pd.Series(values, dtype=object)
+    tm.assert_series_equal(result, expected)
+
+
 def test_undefined_logical_type(parquet_test_datadir):
     test_file = f"{parquet_test_datadir}/unknown-logical-type.parquet"
 

python/pyarrow/types.pxi

@@ -1969,6 +1969,14 @@ cdef class JsonType(BaseExtensionType):
         return JsonScalar
 
 
+class _UuidPandasDtype:
+    def __from_arrow__(self, array):
+        # Return a 1-D object array of uuid.UUID values (nulls become None).
+        # Per pandas' __from_arrow__ contract this is 1-D; the table-to-blocks
+        # path reshapes it to the single-column block layout as needed.
+        return np.asarray(array.to_pylist(), dtype=object)
+
+
 cdef class UuidType(BaseExtensionType):
     """
     Concrete class for UUID extension type.
@@ -1987,6 +1995,9 @@ cdef class UuidType(BaseExtensionType):
     def __arrow_ext_scalar_class__(self):
         return UuidScalar
 
+    def to_pandas_dtype(self):
+        return _UuidPandasDtype()
+
 
 cdef class FixedShapeTensorType(BaseExtensionType):
     """