String dtype: still return nullable NA-variant in object inference (maybe_converts_object) if requested

pandas/_libs/lib.pyx

@@ -2699,16 +2699,16 @@ def maybe_convert_objects(ndarray[object] objects,
         seen.object_ = True
 
     elif seen.str_:
-        if using_string_dtype() and is_string_array(objects, skipna=True):
+        if convert_to_nullable_dtype and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype(na_value=np.nan)
+            dtype = StringDtype()
             return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)
 
-        elif convert_to_nullable_dtype and is_string_array(objects, skipna=True):
+        elif using_string_dtype() and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype()
+            dtype = StringDtype(na_value=np.nan)
             return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)
 
         seen.object_ = True

pandas/core/arrays/datetimelike.py

@@ -130,9 +130,9 @@
 from pandas.core.arrays.integer import IntegerArray
 import pandas.core.common as com
 from pandas.core.construction import (
-    array as pd_array,
     ensure_wrapped_if_datetimelike,
     extract_array,
+    sanitize_array,
 )
 from pandas.core.indexers import (
     check_array_indexer,
@@ -667,12 +667,10 @@ def _validate_listlike(self, value, allow_object: bool = False):
                     msg = self._validation_error_message(value, True)
                     raise TypeError(msg) from err
 
-        # Do type inference if necessary up front (after unpacking
-        # NumpyExtensionArray)
+        # Do type inference if necessary up front
         # e.g. we passed PeriodIndex.values and got an ndarray of Periods
-        value = extract_array(value, extract_numpy=True)
-        value = pd_array(value)
-        value = extract_array(value, extract_numpy=True)
+        value = sanitize_array(value, index=None)
+        value = ensure_wrapped_if_datetimelike(value)
 
         if is_all_strings(value):
             # We got a StringArray

pandas/tests/arrays/string_/test_string_arrow.py

@@ -4,7 +4,6 @@
 import numpy as np
 import pytest
 
-from pandas.compat import HAS_PYARROW
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -27,20 +26,14 @@ def test_eq_all_na():
     tm.assert_extension_array_equal(result, expected)
 
 
-def test_config(string_storage, request, using_infer_string):
-    if using_infer_string and string_storage == "python" and HAS_PYARROW:
-        # string storage with na_value=NaN always uses pyarrow if available
-        # -> does not yet honor the option
-        request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)"))
-
+def test_config(string_storage):
     with pd.option_context("string_storage", string_storage):
         assert StringDtype().storage == string_storage
         result = pd.array(["a", "b"])
         assert result.dtype.storage == string_storage
 
-    dtype = StringDtype(
-        string_storage, na_value=np.nan if using_infer_string else pd.NA
-    )
+    # pd.array(..) by default always returns the NA-variant
+    dtype = StringDtype(string_storage, na_value=pd.NA)
     expected = dtype.construct_array_type()._from_sequence(["a", "b"], dtype=dtype)
     tm.assert_equal(result, expected)
 

pandas/tests/arrays/test_array.py

@@ -5,8 +5,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 import pandas._testing as tm
 from pandas.api.extensions import register_extension_dtype
@@ -215,21 +213,43 @@ def test_dt64_array(dtype_unit):
             .construct_array_type()
             ._from_sequence(["a", None], dtype=pd.StringDtype()),
         ),
+        (
+            ["a", None],
+            "str",
+            pd.StringDtype(na_value=np.nan)
+            .construct_array_type()
+            ._from_sequence(["a", None], dtype=pd.StringDtype(na_value=np.nan)),
+        ),
         (
             ["a", None],
             pd.StringDtype(),
             pd.StringDtype()
             .construct_array_type()
             ._from_sequence(["a", None], dtype=pd.StringDtype()),
         ),
+        (
+            ["a", None],
+            pd.StringDtype(na_value=np.nan),
+            pd.StringDtype(na_value=np.nan)
+            .construct_array_type()
+            ._from_sequence(["a", None], dtype=pd.StringDtype(na_value=np.nan)),
+        ),
         (
             # numpy array with string dtype
             np.array(["a", "b"], dtype=str),
-            None,
+            pd.StringDtype(),
             pd.StringDtype()
             .construct_array_type()
             ._from_sequence(["a", "b"], dtype=pd.StringDtype()),
         ),
+        (
+            # numpy array with string dtype
+            np.array(["a", "b"], dtype=str),
+            pd.StringDtype(na_value=np.nan),
+            pd.StringDtype(na_value=np.nan)
+            .construct_array_type()
+            ._from_sequence(["a", "b"], dtype=pd.StringDtype(na_value=np.nan)),
+        ),
         # Boolean
         (
             [True, None],
@@ -287,7 +307,6 @@ def test_array_copy():
     assert tm.shares_memory(a, b)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "data, expected",
     [
@@ -387,6 +406,13 @@ def test_array_copy():
             .construct_array_type()
             ._from_sequence(["a", None], dtype=pd.StringDtype()),
         ),
+        (
+            # numpy array with string dtype
+            np.array(["a", "b"], dtype=str),
+            pd.StringDtype()
+            .construct_array_type()
+            ._from_sequence(["a", "b"], dtype=pd.StringDtype()),
+        ),
         # Boolean
         ([True, False], BooleanArray._from_sequence([True, False], dtype="boolean")),
         ([True, None], BooleanArray._from_sequence([True, None], dtype="boolean")),

pandas/tests/base/test_value_counts.py

@@ -114,7 +114,7 @@ def test_value_counts_inferred(index_or_series, using_infer_string):
     else:
         exp = np.unique(np.array(s_values, dtype=np.object_))
         if using_infer_string:
-            exp = array(exp)
+            exp = array(exp, dtype="str")
         tm.assert_equal(s.unique(), exp)
 
     assert s.nunique() == 4
@@ -192,7 +192,7 @@ def test_value_counts_bins(index_or_series, using_infer_string):
     else:
         exp = np.array(["a", "b", np.nan, "d"], dtype=object)
         if using_infer_string:
-            exp = array(exp)
+            exp = array(exp, dtype="str")
         tm.assert_equal(s.unique(), exp)
     assert s.nunique() == 3
 

pandas/tests/dtypes/cast/test_construct_ndarray.py

@@ -21,7 +21,7 @@ def test_construct_1d_ndarray_preserving_na(
 ):
     result = sanitize_array(values, index=None, dtype=dtype)
     if using_infer_string and expected.dtype == object and dtype is None:
-        tm.assert_extension_array_equal(result, pd.array(expected))
+        tm.assert_extension_array_equal(result, pd.array(expected, dtype="str"))
     else:
         tm.assert_numpy_array_equal(result, expected)
 

pandas/tests/io/parser/usecols/test_usecols_basic.py

@@ -8,8 +8,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.errors import ParserError
 
 from pandas import (
@@ -531,7 +529,6 @@ def test_usecols_additional_columns_integer_columns(all_parsers):
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_usecols_dtype(all_parsers):
     parser = all_parsers
     data = """