TST (string dtype): fix sql xfails with using_infer_string

Author: WillAyd

pandas/core/dtypes/cast.py

@@ -1162,6 +1162,7 @@ def convert_dtypes(
 
 def maybe_infer_to_datetimelike(
     value: npt.NDArray[np.object_],
+    convert_to_nullable_dtype: bool = False,
 ) -> np.ndarray | DatetimeArray | TimedeltaArray | PeriodArray | IntervalArray:
     """
     we might have a array (or single object) that is datetime like,
@@ -1199,6 +1200,7 @@ def maybe_infer_to_datetimelike(
         #  numpy would have done it for us.
         convert_numeric=False,
         convert_non_numeric=True,
+        convert_to_nullable_dtype=convert_to_nullable_dtype,
         dtype_if_all_nat=np.dtype("M8[s]"),
     )
 

pandas/core/internals/construction.py

@@ -966,8 +966,9 @@ def convert(arr):
             if dtype is None:
                 if arr.dtype == np.dtype("O"):
                     # i.e. maybe_convert_objects didn't convert
-                    arr = maybe_infer_to_datetimelike(arr)
-                    if dtype_backend != "numpy" and arr.dtype == np.dtype("O"):
+                    convert_to_nullable_dtype = dtype_backend != "numpy"
+                    arr = maybe_infer_to_datetimelike(arr, convert_to_nullable_dtype)
+                    if convert_to_nullable_dtype and arr.dtype == np.dtype("O"):
                         new_dtype = StringDtype()
                         arr_cls = new_dtype.construct_array_type()
                         arr = arr_cls._from_sequence(arr, dtype=new_dtype)

pandas/io/sql.py

@@ -58,6 +58,7 @@
     Series,
 )
 from pandas.core.arrays import ArrowExtensionArray
+from pandas.core.arrays.string_ import StringDtype
 from pandas.core.base import PandasObject
 import pandas.core.common as com
 from pandas.core.common import maybe_make_list
@@ -1316,7 +1317,6 @@ def _harmonize_columns(
                 elif dtype_backend == "numpy" and col_type is float:
                     # floats support NA, can always convert!
                     self.frame[col_name] = df_col.astype(col_type)
-
                 elif dtype_backend == "numpy" and len(df_col) == df_col.count():
                     # No NA values, can convert ints and bools
                     if col_type is np.dtype("int64") or col_type is bool:
@@ -1403,6 +1403,7 @@ def _get_dtype(self, sqltype):
             DateTime,
             Float,
             Integer,
+            String,
         )
 
         if isinstance(sqltype, Float):
@@ -1422,6 +1423,10 @@ def _get_dtype(self, sqltype):
             return date
         elif isinstance(sqltype, Boolean):
             return bool
+        elif isinstance(sqltype, String):
+            if using_string_dtype():
+                return StringDtype(na_value=np.nan)
+
         return object
 
 
@@ -2205,7 +2210,7 @@ def read_table(
         elif using_string_dtype():
             from pandas.io._util import arrow_string_types_mapper
 
-            arrow_string_types_mapper()
+            mapping = arrow_string_types_mapper()
         else:
             mapping = None
 
@@ -2286,6 +2291,10 @@ def read_query(
             from pandas.io._util import _arrow_dtype_mapping
 
             mapping = _arrow_dtype_mapping().get
+        elif using_string_dtype():
+            from pandas.io._util import arrow_string_types_mapper
+
+            mapping = arrow_string_types_mapper()
         else:
             mapping = None
 

pandas/tests/io/test_sql.py

@@ -18,8 +18,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs import lib
 from pandas.compat import pa_version_under14p1
 from pandas.compat._optional import import_optional_dependency
@@ -60,7 +58,6 @@
     pytest.mark.filterwarnings(
         "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
     ),
-    pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False),
 ]
 
 
@@ -3554,7 +3551,8 @@ def test_read_sql_dtype_backend(
         result = getattr(pd, func)(
             f"Select * from {table}", conn, dtype_backend=dtype_backend
         )
-    expected = dtype_backend_expected(string_storage, dtype_backend, conn_name)
+        expected = dtype_backend_expected(string_storage, dtype_backend, conn_name)
+
     tm.assert_frame_equal(result, expected)
 
     if "adbc" in conn_name:
@@ -3604,7 +3602,7 @@ def test_read_sql_dtype_backend_table(
 
     with pd.option_context("mode.string_storage", string_storage):
         result = getattr(pd, func)(table, conn, dtype_backend=dtype_backend)
-    expected = dtype_backend_expected(string_storage, dtype_backend, conn_name)
+        expected = dtype_backend_expected(string_storage, dtype_backend, conn_name)
     tm.assert_frame_equal(result, expected)
 
     if "adbc" in conn_name:
@@ -4120,7 +4118,7 @@ def tquery(query, con=None):
 def test_xsqlite_basic(sqlite_buildin):
     frame = DataFrame(
         np.random.default_rng(2).standard_normal((10, 4)),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
         index=date_range("2000-01-01", periods=10, freq="B"),
     )
     assert sql.to_sql(frame, name="test_table", con=sqlite_buildin, index=False) == 10
@@ -4147,7 +4145,7 @@ def test_xsqlite_basic(sqlite_buildin):
 def test_xsqlite_write_row_by_row(sqlite_buildin):
     frame = DataFrame(
         np.random.default_rng(2).standard_normal((10, 4)),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
         index=date_range("2000-01-01", periods=10, freq="B"),
     )
     frame.iloc[0, 0] = np.nan
@@ -4170,7 +4168,7 @@ def test_xsqlite_write_row_by_row(sqlite_buildin):
 def test_xsqlite_execute(sqlite_buildin):
     frame = DataFrame(
         np.random.default_rng(2).standard_normal((10, 4)),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
         index=date_range("2000-01-01", periods=10, freq="B"),
     )
     create_sql = sql.get_schema(frame, "test")
@@ -4191,7 +4189,7 @@ def test_xsqlite_execute(sqlite_buildin):
 def test_xsqlite_schema(sqlite_buildin):
     frame = DataFrame(
         np.random.default_rng(2).standard_normal((10, 4)),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
         index=date_range("2000-01-01", periods=10, freq="B"),
     )
     create_sql = sql.get_schema(frame, "test")