add to _from_sequence and fixes

doc/source/whatsnew/v1.3.0.rst

@@ -644,7 +644,7 @@ Other API changes
 - Partially initialized :class:`CategoricalDtype` (i.e. those with ``categories=None`` objects will no longer compare as equal to fully initialized dtype objects.
 - Accessing ``_constructor_expanddim`` on a :class:`DataFrame` and ``_constructor_sliced`` on a :class:`Series` now raise an ``AttributeError``. Previously a ``NotImplementedError`` was raised (:issue:`38782`)
 - Added new ``engine`` and ``**engine_kwargs`` parameters to :meth:`DataFrame.to_sql` to support other future "SQL engines". Currently we still only use ``SQLAlchemy`` under the hood, but more engines are planned to be supported such as ``turbodbc`` (:issue:`36893`)
-- :class:`StringArray` now accepts nan-likes(``None``, ``nan``, ``NaT``, ``NA``, Decimal("NaN")) in its constructor in addition to strings.
+- :class:`StringArray` now accepts nan-likes(``None``, ``nan``, ``NA``) in its constructor in addition to strings.
 - Removed redundant ``freq`` from :class:`PeriodIndex` string representation (:issue:`41653`)
 
 

pandas/core/arrays/string_.py

@@ -145,7 +145,7 @@ class StringArray(PandasArray):
 
            Currently, this expects an object-dtype ndarray
            where the elements are Python strings
-           or nan-likes(``None``, ``nan``, ``NaT``, ``NA``, Decimal("NaN")).
+           or nan-likes(``None``, ``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.
@@ -239,23 +239,33 @@ def _validate(self):
             raise ValueError("StringArray requires a sequence of strings or pandas.NA")
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy=False):
+    def _from_sequence(
+        cls, scalars, *, dtype: Dtype | None = None, copy=False, coerce=True
+    ):
         if dtype:
             assert dtype == "string"
 
         from pandas.core.arrays.masked import BaseMaskedArray
 
         if isinstance(scalars, BaseMaskedArray):
             # avoid costly conversion to object dtype
+            if coerce:
+                coerce = "non-null"
+            else:
+                coerce = None
             na_values = scalars._mask
             result = scalars._data
-            result = lib.ensure_string_array(result, copy=copy, coerce="non-null")
+            result = lib.ensure_string_array(result, copy=copy, coerce=coerce)
             result[na_values] = StringDtype.na_value
 
         else:
             # convert non-na-likes to str, and nan-likes to StringDtype.na_value
+            if coerce:
+                coerce = "all"
+            else:
+                coerce = "strict-null"
             result = lib.ensure_string_array(
-                scalars, na_value=StringDtype.na_value, copy=copy
+                scalars, na_value=StringDtype.na_value, copy=copy, coerce=coerce
             )
 
         # Manually creating new array avoids the validation step in the __init__, so is

pandas/core/arrays/string_arrow.py

@@ -237,7 +237,9 @@ def __init__(self, values):
             )
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype: Dtype | None = None, copy: bool = False):
+    def _from_sequence(
+        cls, scalars, dtype: Dtype | None = None, copy: bool = False, coerce=True
+    ):
         from pandas.core.arrays.masked import BaseMaskedArray
 
         _chk_pyarrow_available()
@@ -247,11 +249,19 @@ def _from_sequence(cls, scalars, dtype: Dtype | None = None, copy: bool = False)
             # numerical issues with Float32Dtype
             na_values = scalars._mask
             result = scalars._data
-            result = lib.ensure_string_array(result, copy=copy, coerce="non-null")
+            if coerce:
+                coerce = "non-null"
+            else:
+                coerce = None
+            result = lib.ensure_string_array(result, copy=copy, coerce=coerce)
             return cls(pa.array(result, mask=na_values, type=pa.string()))
 
         # convert non-na-likes to str
-        result = lib.ensure_string_array(scalars, copy=copy)
+        if coerce:
+            coerce = "all"
+        else:
+            coerce = "strict-null"
+        result = lib.ensure_string_array(scalars, copy=copy, coerce=coerce)
         return cls(pa.array(result, type=pa.string(), from_pandas=True))
 
     @classmethod