BUG: read_csv with dtype=bool[pyarrow]

doc/source/whatsnew/v2.0.3.rst

@@ -20,7 +20,7 @@ Fixed regressions
 
 Bug fixes
 ~~~~~~~~~
--
+- Bug in :func:`read_csv` when defining ``dtype`` with ``bool[pyarrow]`` for the ``"c"`` and ``"python"`` engines (:issue:`53390`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_203.other:

pandas/_libs/parsers.pyx

@@ -111,6 +111,8 @@ from pandas.core.dtypes.dtypes import (
 )
 from pandas.core.dtypes.inference import is_dict_like
 
+from pandas.core.arrays.boolean import BooleanDtype
+
 cdef:
     float64_t INF = <float64_t>np.inf
     float64_t NEGINF = -INF
@@ -1194,7 +1196,9 @@ cdef class TextReader:
             array_type = dtype.construct_array_type()
             try:
                 # use _from_sequence_of_strings if the class defines it
-                if dtype.kind == "b":
+                if isinstance(dtype, BooleanDtype):
+                    # xref GH 47534: BooleanArray._from_sequence_of_strings has extra
+                    # kwargs
                     true_values = [x.decode() for x in self.true_values]
                     false_values = [x.decode() for x in self.false_values]
                     result = array_type._from_sequence_of_strings(

pandas/io/parsers/base_parser.py

@@ -75,6 +75,7 @@
     FloatingArray,
     IntegerArray,
 )
+from pandas.core.arrays.boolean import BooleanDtype
 from pandas.core.indexes.api import (
     Index,
     MultiIndex,
@@ -809,7 +810,7 @@ def _cast_types(self, values: ArrayLike, cast_type: DtypeObj, column) -> ArrayLi
         elif isinstance(cast_type, ExtensionDtype):
             array_type = cast_type.construct_array_type()
             try:
-                if is_bool_dtype(cast_type):
+                if isinstance(cast_type, BooleanDtype):
                     # error: Unexpected keyword argument "true_values" for
                     # "_from_sequence_of_strings" of "ExtensionArray"
                     return array_type._from_sequence_of_strings(  # type: ignore[call-arg]  # noqa: E501

pandas/tests/extension/test_arrow.py

@@ -47,6 +47,7 @@
 
 import pandas as pd
 import pandas._testing as tm
+from pandas.api.extensions import no_default
 from pandas.api.types import (
     is_bool_dtype,
     is_float_dtype,
@@ -723,14 +724,11 @@ def test_setitem_preserves_views(self, data):
 
 
 class TestBaseParsing(base.BaseParsingTests):
+    @pytest.mark.parametrize("dtype_backend", ["pyarrow", no_default])
     @pytest.mark.parametrize("engine", ["c", "python"])
-    def test_EA_types(self, engine, data, request):
+    def test_EA_types(self, engine, data, dtype_backend, request):
         pa_dtype = data.dtype.pyarrow_dtype
-        if pa.types.is_boolean(pa_dtype):
-            request.node.add_marker(
-                pytest.mark.xfail(raises=TypeError, reason="GH 47534")
-            )
-        elif pa.types.is_decimal(pa_dtype):
+        if pa.types.is_decimal(pa_dtype):
             request.node.add_marker(
                 pytest.mark.xfail(
                     raises=NotImplementedError,
@@ -755,7 +753,10 @@ def test_EA_types(self, engine, data, request):
         else:
             csv_output = StringIO(csv_output)
         result = pd.read_csv(
-            csv_output, dtype={"with_dtype": str(data.dtype)}, engine=engine
+            csv_output,
+            dtype={"with_dtype": str(data.dtype)},
+            engine=engine,
+            dtype_backend=dtype_backend,
         )
         expected = df
         self.assert_frame_equal(result, expected)