From ba5fce1a97b76974d7fe54205ceeb6e83a2566e2 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sun, 2 Jan 2022 07:27:35 -0800
Subject: [PATCH 01/12] API: Allow other na values in StringArray Constructor

---
 asv_bench/benchmarks/strings.py            | 17 +++++++++++++++
 doc/source/whatsnew/v1.4.0.rst             |  2 +-
 pandas/_libs/lib.pyx                       | 25 ++++++++++++++++++----
 pandas/core/arrays/string_.py              |  6 ++++--
 pandas/tests/arrays/string_/test_string.py | 13 +++++++----
 5 files changed, 52 insertions(+), 11 deletions(-)

diff --git a/asv_bench/benchmarks/strings.py b/asv_bench/benchmarks/strings.py
index 32fbf4e6c7de3..85487f5d531a3 100644
--- a/asv_bench/benchmarks/strings.py
+++ b/asv_bench/benchmarks/strings.py
@@ -3,10 +3,12 @@
 import numpy as np
 
 from pandas import (
+    NA,
     Categorical,
     DataFrame,
     Series,
 )
+from pandas.arrays import StringArray
 
 from .pandas_vb_common import tm
 
@@ -285,3 +287,18 @@ class Iter(Dtypes):
     def time_iter(self, dtype):
         for i in self.s:
             pass
+
+
+class StringArrayConstruction:
+    def setup(self):
+        self.series_arr = tm.rands_array(nchars=10, size=10 ** 5)
+        self.series_arr_nan = np.concatenate([self.series_arr, np.array([NA] * 1000)])
+
+    def time_string_array_construction(self):
+        StringArray(self.series_arr)
+
+    def time_string_array_with_nan_construction(self):
+        StringArray(self.series_arr_nan)
+
+    def peakmem_stringarray_construction(self):
+        StringArray(self.series_arr)
diff --git a/doc/source/whatsnew/v1.4.0.rst b/doc/source/whatsnew/v1.4.0.rst
index 4c3e53ddcfa26..30933f4d7381f 100644
--- a/doc/source/whatsnew/v1.4.0.rst
+++ b/doc/source/whatsnew/v1.4.0.rst
@@ -225,7 +225,7 @@ Other enhancements
 - :class:`ExtensionDtype` and :class:`ExtensionArray` are now (de)serialized when exporting a :class:`DataFrame` with :meth:`DataFrame.to_json` using ``orient='table'`` (:issue:`20612`, :issue:`44705`).
 - Add support for `Zstandard <http://facebook.github.io/zstd/>`_ compression to :meth:`DataFrame.to_pickle`/:meth:`read_pickle` and friends (:issue:`43925`)
 - :meth:`DataFrame.to_sql` now returns an ``int`` of the number of written rows (:issue:`23998`)
-
+- :class:`StringArray` now accepts nan-likes (``None``, ``np.nan``) for the ``values`` parameter in its constructor in addition to strings and :attr:`pandas.NA`. (:issue:`40839`)
 
 .. ---------------------------------------------------------------------------
 
diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index 950277ce608eb..f6c55f76ddd20 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -669,6 +669,27 @@ def astype_intsafe(ndarray[object] arr, cnp.dtype new_dtype) -> ndarray:
 
     return result
 
+# TODO: get rid of this in StringArray and modify
+#  and go through ensure_string_array instead
+@cython.wraparound(False)
+@cython.boundscheck(False)
+def convert_nans_to_NA(ndarray[object] arr) -> ndarray:
+    """
+    Helper for StringArray that converts null values that
+    are not pd.NA(e.g. np.nan, None) to pd.NA. Assumes elements
+    have already been validated as null.
+    """
+    cdef:
+        Py_ssize_t i, n = len(arr)
+        object val
+        ndarray[object] result
+    result = np.asarray(arr, dtype="object")
+    for i in range(n):
+        val = arr[i]
+        if not isinstance(val, str):
+            result[i] = C_NA
+    return result
+
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
@@ -1880,10 +1901,6 @@ cdef class StringValidator(Validator):
     cdef inline bint is_array_typed(self) except -1:
         return issubclass(self.dtype.type, np.str_)
 
-    cdef bint is_valid_null(self, object value) except -1:
-        # We deliberately exclude None / NaN here since StringArray uses NA
-        return value is C_NA
-
 
 cpdef bint is_string_array(ndarray values, bint skipna=False):
     cdef:
diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index 919b882f22ecb..46a41ae813ca3 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -310,11 +310,11 @@ def __init__(self, values, copy=False):
         values = extract_array(values)
 
         super().__init__(values, copy=copy)
+        if not isinstance(values, type(self)):
+            self._validate()
         # error: Incompatible types in assignment (expression has type "StringDtype",
         # variable has type "PandasDtype")
         NDArrayBacked.__init__(self, self._ndarray, StringDtype(storage="python"))
-        if not isinstance(values, type(self)):
-            self._validate()
 
     def _validate(self):
         """Validate that we only store NA or strings."""
@@ -325,6 +325,8 @@ def _validate(self):
                 "StringArray requires a sequence of strings or pandas.NA. Got "
                 f"'{self._ndarray.dtype}' dtype instead."
             )
+        # Check to see if need to convert Na values to pd.NA
+        lib.convert_nans_to_NA(self._ndarray)
 
     @classmethod
     def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):
diff --git a/pandas/tests/arrays/string_/test_string.py b/pandas/tests/arrays/string_/test_string.py
index 22fe7bb0de949..0919d57f9e612 100644
--- a/pandas/tests/arrays/string_/test_string.py
+++ b/pandas/tests/arrays/string_/test_string.py
@@ -267,15 +267,20 @@ def test_constructor_raises(cls):
         cls(np.array([]))
 
     with pytest.raises(ValueError, match=msg):
-        cls(np.array(["a", np.nan], dtype=object))
-
-    with pytest.raises(ValueError, match=msg):
-        cls(np.array(["a", None], dtype=object))
+        cls(np.array(["a", np.datetime64("nat")], dtype=object))
 
     with pytest.raises(ValueError, match=msg):
         cls(np.array(["a", pd.NaT], dtype=object))
 
 
+@pytest.mark.parametrize("na", [np.nan, np.float64("nan"), float("nan"), None, pd.NA])
+def test_constructor_nan_like(na):
+    expected = pd.arrays.StringArray(np.array(["a", pd.NA]))
+    tm.assert_extension_array_equal(
+        pd.arrays.StringArray(np.array(["a", na], dtype="object")), expected
+    )
+
+
 @pytest.mark.parametrize("copy", [True, False])
 def test_from_sequence_no_mutate(copy, cls, request):
     if cls is ArrowStringArray and copy is False:

From 8011f8d0319b78764daca2473aacbef304df34fb Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sun, 2 Jan 2022 18:24:22 -0800
Subject: [PATCH 02/12] fix compile warning?

---
 pandas/_libs/lib.pyx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index f6c55f76ddd20..70f3631a8aadf 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -687,7 +687,7 @@ def convert_nans_to_NA(ndarray[object] arr) -> ndarray:
     for i in range(n):
         val = arr[i]
         if not isinstance(val, str):
-            result[i] = C_NA
+            result[i] = <object>C_NA
     return result
 
 

From 36ad88611de070bfbd4a26664357b75c4e42ab5a Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sun, 2 Jan 2022 20:13:19 -0800
Subject: [PATCH 03/12] 2d support

---
 pandas/_libs/lib.pyx                  | 27 ++++++++++++++++++++-------
 pandas/tests/dtypes/test_inference.py | 13 ++++++++++---
 2 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index 70f3631a8aadf..4882a6993405e 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -669,25 +669,38 @@ def astype_intsafe(ndarray[object] arr, cnp.dtype new_dtype) -> ndarray:
 
     return result
 
+ctypedef fused ndarr_object:
+    ndarray[object, ndim=1]
+    ndarray[object, ndim=2]
+
 # TODO: get rid of this in StringArray and modify
 #  and go through ensure_string_array instead
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def convert_nans_to_NA(ndarray[object] arr) -> ndarray:
+def convert_nans_to_NA(ndarr_object arr) -> ndarray:
     """
     Helper for StringArray that converts null values that
     are not pd.NA(e.g. np.nan, None) to pd.NA. Assumes elements
     have already been validated as null.
     """
     cdef:
-        Py_ssize_t i, n = len(arr)
+        Py_ssize_t i, m, n
         object val
-        ndarray[object] result
+        ndarr_object result
     result = np.asarray(arr, dtype="object")
-    for i in range(n):
-        val = arr[i]
-        if not isinstance(val, str):
-            result[i] = <object>C_NA
+    if arr.ndim == 2:
+        m,n = arr.shape[0], arr.shape[1]
+        for i in range(m):
+            for j in range(n):
+                val = arr[i][j]
+                if not isinstance(val, str):
+                    result[i][j] = <object>C_NA
+    else:
+        n = len(arr)
+        for i in range(n):
+            val = arr[i]
+            if not isinstance(val, str):
+                result[i] = <object>C_NA
     return result
 
 
diff --git a/pandas/tests/dtypes/test_inference.py b/pandas/tests/dtypes/test_inference.py
index 7953d650636be..178c91efa0c27 100644
--- a/pandas/tests/dtypes/test_inference.py
+++ b/pandas/tests/dtypes/test_inference.py
@@ -1542,11 +1542,18 @@ def test_is_string_array(self):
         assert lib.is_string_array(
             np.array(["foo", "bar", pd.NA], dtype=object), skipna=True
         )
-        # NaN is not valid for string array, just NA
+        assert lib.is_string_array(
+            np.array(["foo", "bar", None], dtype=object), skipna=True
+        )
         assert not lib.is_string_array(
-            np.array(["foo", "bar", np.nan], dtype=object), skipna=True
+            np.array(["foo", "bar", pd.NaT], dtype=object), skipna=True
+        )
+        assert not lib.is_string_array(
+            np.array(["foo", "bar", None], dtype=object), skipna=False
+        )
+        assert not lib.is_string_array(
+            np.array(["foo", "bar", np.nan], dtype=object), skipna=False
         )
-
         assert not lib.is_string_array(np.array([1, 2]))
 
     def test_to_object_array_tuples(self):

From 3ddcf37472d58267d57f4d76611187ab3a3713a6 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Mon, 3 Jan 2022 19:09:35 -0800
Subject: [PATCH 04/12] fix last tests and address comments

---
 pandas/_libs/lib.pyx          | 4 ++--
 pandas/core/arrays/string_.py | 6 +++++-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index 4882a6993405e..4a00a9dcbb183 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -692,9 +692,9 @@ def convert_nans_to_NA(ndarr_object arr) -> ndarray:
         m,n = arr.shape[0], arr.shape[1]
         for i in range(m):
             for j in range(n):
-                val = arr[i][j]
+                val = arr[i, j]
                 if not isinstance(val, str):
-                    result[i][j] = <object>C_NA
+                    result[i, j] = <object>C_NA
     else:
         n = len(arr)
         for i in range(n):
diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index 46a41ae813ca3..1ba739f1a4c45 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -326,7 +326,11 @@ def _validate(self):
                 f"'{self._ndarray.dtype}' dtype instead."
             )
         # Check to see if need to convert Na values to pd.NA
-        lib.convert_nans_to_NA(self._ndarray)
+        if self._ndarray.ndim > 2:
+            # Ravel if ndims > 2 b/c no cythonized version available
+            lib.convert_nans_to_NA(self._ndarray.ravel("K"))
+        else:
+            lib.convert_nans_to_NA(self._ndarray)
 
     @classmethod
     def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):

From 4c60d0f5044b32d07dc06a49b36db295fe1646dd Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Tue, 4 Jan 2022 08:27:44 -0800
Subject: [PATCH 05/12] fix typing?

---
 pandas/_libs/lib.pyi | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/pandas/_libs/lib.pyi b/pandas/_libs/lib.pyi
index a7ebd9d0c77ad..6a1519c827c7a 100644
--- a/pandas/_libs/lib.pyi
+++ b/pandas/_libs/lib.pyi
@@ -161,6 +161,9 @@ def astype_intsafe(
     arr: npt.NDArray[np.object_],
     new_dtype: np.dtype,
 ) -> np.ndarray: ...
+def convert_nans_to_NA(
+    arr: npt.NDArray[np.object_],
+) -> npt.NDArray[np.object_]: ...
 def fast_zip(ndarrays: list) -> npt.NDArray[np.object_]: ...
 
 # TODO: can we be more specific about rows?

From d5e594d83ba1ab46a318325356dbce40608ba95e Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Mon, 10 Jan 2022 20:18:31 -0800
Subject: [PATCH 06/12] add more doc

---
 pandas/core/arrays/string_.py | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index 1ba739f1a4c45..29dfea4ea2d71 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -246,11 +246,19 @@ class StringArray(BaseStringArray, PandasArray):
         .. warning::
 
            Currently, this expects an object-dtype ndarray
-           where the elements are Python strings or :attr:`pandas.NA`.
+           where the elements are Python strings
+           or nan-likes(``None``, ``np.nan``, ``NA``).
            This may change without warning in the future. Use
            :meth:`pandas.array` with ``dtype="string"`` for a stable way of
            creating a `StringArray` from any sequence.
 
+        .. versionchanged:: 1.5.0
+
+           StringArray now accepts nan-likes(``None``, ``np.nan``) for the
+           ``values`` parameter in its constructor
+           in addition to strings and :attr:`pandas.NA`
+
+
     copy : bool, default False
         Whether to copy the array of data.
 

From 9c6e9d3fced6a249cee7b0179e24f50c0ce6d875 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Mon, 10 Jan 2022 20:20:26 -0800
Subject: [PATCH 07/12] move whatsnew

---
 doc/source/whatsnew/v1.4.0.rst | 1 -
 doc/source/whatsnew/v1.5.0.rst | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/doc/source/whatsnew/v1.4.0.rst b/doc/source/whatsnew/v1.4.0.rst
index 7c9345a6a6b75..12bd51cba47a3 100644
--- a/doc/source/whatsnew/v1.4.0.rst
+++ b/doc/source/whatsnew/v1.4.0.rst
@@ -226,7 +226,6 @@ Other enhancements
 - :class:`ExtensionDtype` and :class:`ExtensionArray` are now (de)serialized when exporting a :class:`DataFrame` with :meth:`DataFrame.to_json` using ``orient='table'`` (:issue:`20612`, :issue:`44705`).
 - Add support for `Zstandard <http://facebook.github.io/zstd/>`_ compression to :meth:`DataFrame.to_pickle`/:meth:`read_pickle` and friends (:issue:`43925`)
 - :meth:`DataFrame.to_sql` now returns an ``int`` of the number of written rows (:issue:`23998`)
-- :class:`StringArray` now accepts nan-likes (``None``, ``np.nan``) for the ``values`` parameter in its constructor in addition to strings and :attr:`pandas.NA`. (:issue:`40839`)
 
 .. ---------------------------------------------------------------------------
 
diff --git a/doc/source/whatsnew/v1.5.0.rst b/doc/source/whatsnew/v1.5.0.rst
index 2cbc7b06b89df..a952d65c3cb84 100644
--- a/doc/source/whatsnew/v1.5.0.rst
+++ b/doc/source/whatsnew/v1.5.0.rst
@@ -30,7 +30,7 @@ enhancement2
 
 Other enhancements
 ^^^^^^^^^^^^^^^^^^
--
+- :class:`StringArray` now accepts nan-likes (``None``, ``np.nan``) for the ``values`` parameter in its constructor in addition to strings and :attr:`pandas.NA`. (:issue:`40839`)
 -
 
 .. ---------------------------------------------------------------------------

From 1fca52467211764a6cbe4de5403ecd107b234878 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Tue, 11 Jan 2022 16:53:20 -0800
Subject: [PATCH 08/12] Update string_.py

---
 pandas/core/arrays/string_.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index 29dfea4ea2d71..66a7da4dc4078 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -258,7 +258,6 @@ class StringArray(BaseStringArray, PandasArray):
            ``values`` parameter in its constructor
            in addition to strings and :attr:`pandas.NA`
 
-
     copy : bool, default False
         Whether to copy the array of data.
 

From 9016c0084fc88c6240b4996f498632abf385173d Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Tue, 11 Jan 2022 20:09:15 -0800
Subject: [PATCH 09/12] fixes

---
 pandas/_libs/lib.pyx                  | 2 +-
 pandas/tests/dtypes/test_inference.py | 7 ++++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index 71fdda1e60649..9a82e89481b45 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -689,7 +689,7 @@ def convert_nans_to_NA(ndarr_object arr) -> ndarray:
         ndarr_object result
     result = np.asarray(arr, dtype="object")
     if arr.ndim == 2:
-        m,n = arr.shape[0], arr.shape[1]
+        m, n = arr.shape[0], arr.shape[1]
         for i in range(m):
             for j in range(n):
                 val = arr[i, j]
diff --git a/pandas/tests/dtypes/test_inference.py b/pandas/tests/dtypes/test_inference.py
index 178c91efa0c27..404df6f4daadb 100644
--- a/pandas/tests/dtypes/test_inference.py
+++ b/pandas/tests/dtypes/test_inference.py
@@ -1534,7 +1534,9 @@ def test_is_numeric_array(self):
         assert not lib.is_integer_array(np.array([1, 2.0]))
 
     def test_is_string_array(self):
-
+        # We should only be accepting pd.NA, np.nan, 
+        # other floating point nans e.g. float('nan')]
+        # when skipna is True.
         assert lib.is_string_array(np.array(["foo", "bar"]))
         assert not lib.is_string_array(
             np.array(["foo", "bar", pd.NA], dtype=object), skipna=False
@@ -1545,6 +1547,9 @@ def test_is_string_array(self):
         assert lib.is_string_array(
             np.array(["foo", "bar", None], dtype=object), skipna=True
         )
+        assert lib.is_string_array(
+            np.array(["foo", "bar", np.nan], dtype=object), skipna=True
+        )
         assert not lib.is_string_array(
             np.array(["foo", "bar", pd.NaT], dtype=object), skipna=True
         )

From 6ec20595276ceb5b21657757f0130e0fa5e51e30 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Wed, 12 Jan 2022 04:24:56 +0000
Subject: [PATCH 10/12] Fixes from pre-commit [automated commit]

---
 pandas/tests/dtypes/test_inference.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/tests/dtypes/test_inference.py b/pandas/tests/dtypes/test_inference.py
index 404df6f4daadb..9ae5b42161b73 100644
--- a/pandas/tests/dtypes/test_inference.py
+++ b/pandas/tests/dtypes/test_inference.py
@@ -1534,7 +1534,7 @@ def test_is_numeric_array(self):
         assert not lib.is_integer_array(np.array([1, 2.0]))
 
     def test_is_string_array(self):
-        # We should only be accepting pd.NA, np.nan, 
+        # We should only be accepting pd.NA, np.nan,
         # other floating point nans e.g. float('nan')]
         # when skipna is True.
         assert lib.is_string_array(np.array(["foo", "bar"]))

From 1fb424c2f53210bf4a96dd1dd628572f99a6cbc8 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sat, 15 Jan 2022 07:56:46 -0800
Subject: [PATCH 11/12] code review

---
 pandas/core/arrays/string_.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index 66a7da4dc4078..8142f66dcd3b3 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -247,15 +247,15 @@ class StringArray(BaseStringArray, PandasArray):
 
            Currently, this expects an object-dtype ndarray
            where the elements are Python strings
-           or nan-likes(``None``, ``np.nan``, ``NA``).
+           or nan-likes (``None``, ``np.nan``, ``NA``).
            This may change without warning in the future. Use
            :meth:`pandas.array` with ``dtype="string"`` for a stable way of
            creating a `StringArray` from any sequence.
 
         .. versionchanged:: 1.5.0
 
-           StringArray now accepts nan-likes(``None``, ``np.nan``) for the
-           ``values`` parameter in its constructor
+           StringArray now accepts array-likes containing 
+           nan-likes(``None``, ``np.nan``) for the ``values`` parameter
            in addition to strings and :attr:`pandas.NA`
 
     copy : bool, default False

From ad55cd393485028d0a39e66556838751aff736d4 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sat, 15 Jan 2022 15:58:11 +0000
Subject: [PATCH 12/12] Fixes from pre-commit [automated commit]

---
 pandas/core/arrays/string_.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index 8142f66dcd3b3..b79e915fa6c94 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -254,7 +254,7 @@ class StringArray(BaseStringArray, PandasArray):
 
         .. versionchanged:: 1.5.0
 
-           StringArray now accepts array-likes containing 
+           StringArray now accepts array-likes containing
            nan-likes(``None``, ``np.nan``) for the ``values`` parameter
            in addition to strings and :attr:`pandas.NA`