From 81275a43764f0245710649e27a68191c08206fcd Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Wed, 31 May 2023 10:19:35 -0700
Subject: [PATCH 1/2] Backport PR #53391: BUG: read_csv with
 dtype=bool[pyarrow]

---
 doc/source/whatsnew/v2.0.3.rst       |  2 +-
 pandas/_libs/parsers.pyx             |  6 +++++-
 pandas/io/parsers/base_parser.py     |  3 ++-
 pandas/tests/extension/test_arrow.py | 15 ++++++++-------
 4 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/doc/source/whatsnew/v2.0.3.rst b/doc/source/whatsnew/v2.0.3.rst
index 73779d7e4cc74..a25999d8085cb 100644
--- a/doc/source/whatsnew/v2.0.3.rst
+++ b/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:
diff --git a/pandas/_libs/parsers.pyx b/pandas/_libs/parsers.pyx
index 2839730ca46bd..0bd0597f32ad0 100644
--- a/pandas/_libs/parsers.pyx
+++ b/pandas/_libs/parsers.pyx
@@ -117,6 +117,8 @@ from pandas.core.dtypes.common import (
 from pandas.core.dtypes.dtypes import CategoricalDtype
 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
@@ -1167,7 +1169,9 @@ cdef class TextReader:
             array_type = dtype.construct_array_type()
             try:
                 # use _from_sequence_of_strings if the class defines it
-                if is_bool_dtype(dtype):
+                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(
diff --git a/pandas/io/parsers/base_parser.py b/pandas/io/parsers/base_parser.py
index 2db759719fcb4..22ab8607e060a 100644
--- a/pandas/io/parsers/base_parser.py
+++ b/pandas/io/parsers/base_parser.py
@@ -80,6 +80,7 @@
     FloatingArray,
     IntegerArray,
 )
+from pandas.core.arrays.boolean import BooleanDtype
 from pandas.core.indexes.api import (
     Index,
     MultiIndex,
@@ -800,7 +801,7 @@ 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
diff --git a/pandas/tests/extension/test_arrow.py b/pandas/tests/extension/test_arrow.py
index 8907137c71844..5d38a6b0d0031 100644
--- a/pandas/tests/extension/test_arrow.py
+++ b/pandas/tests/extension/test_arrow.py
@@ -45,6 +45,7 @@
 
 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,
@@ -738,14 +739,11 @@ 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,
@@ -770,7 +768,10 @@ 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)

From c578723472c9ddcb1a6a50f2f2572b79855d5d82 Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Wed, 31 May 2023 12:57:47 -0700
Subject: [PATCH 2/2] Add xfail

---
 pandas/tests/extension/test_arrow.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/pandas/tests/extension/test_arrow.py b/pandas/tests/extension/test_arrow.py
index 5d38a6b0d0031..3efb59fc6afce 100644
--- a/pandas/tests/extension/test_arrow.py
+++ b/pandas/tests/extension/test_arrow.py
@@ -761,6 +761,17 @@ def test_EA_types(self, engine, data, dtype_backend, request):
             request.node.add_marker(
                 pytest.mark.xfail(reason="CSV parsers don't correctly handle binary")
             )
+        elif (
+            pa.types.is_duration(pa_dtype)
+            and dtype_backend == "pyarrow"
+            and engine == "python"
+        ):
+            request.node.add_marker(
+                pytest.mark.xfail(
+                    raises=TypeError,
+                    reason="Invalid type for timedelta scalar: NAType",
+                )
+            )
         df = pd.DataFrame({"with_dtype": pd.Series(data, dtype=str(data.dtype))})
         csv_output = df.to_csv(index=False, na_rep=np.nan)
         if pa.types.is_binary(pa_dtype):