BUG: checking for value type when parquet is partitioned

doc/source/whatsnew/v2.1.0.rst

@@ -533,13 +533,13 @@ Sparse
 
 ExtensionArray
 ^^^^^^^^^^^^^^
+- Bug in :class:`ArrowStringArray` constructor raises ``ValueError`` with dictionary types of strings (:issue:`54074`)
 - Bug in :class:`DataFrame` constructor not copying :class:`Series` with extension dtype when given in dict (:issue:`53744`)
 - Bug in :class:`~arrays.ArrowExtensionArray` converting pandas non-nanosecond temporal objects from non-zero values to zero values (:issue:`53171`)
 - Bug in :meth:`Series.quantile` for pyarrow temporal types raising ArrowInvalid (:issue:`52678`)
 - Bug in :meth:`Series.rank` returning wrong order for small values with ``Float64`` dtype (:issue:`52471`)
 - Bug in :meth:`~arrays.ArrowExtensionArray.__iter__` and :meth:`~arrays.ArrowExtensionArray.__getitem__` returning python datetime and timedelta objects for non-nano dtypes (:issue:`53326`)
 - Bug where the ``__from_arrow__`` method of masked ExtensionDtypes(e.g. :class:`Float64Dtype`, :class:`BooleanDtype`) would not accept pyarrow arrays of type ``pyarrow.null()`` (:issue:`52223`)
--
 
 Styler
 ^^^^^^

pandas/core/arrays/string_arrow.py

@@ -118,7 +118,10 @@ def __init__(self, values) -> None:
  super().__init__(values)
  self._dtype = StringDtype(storage="pyarrow")
 
- if not pa.types.is_string(self._pa_array.type):
+ if not pa.types.is_string(self._pa_array.type) and not (
+ pa.types.is_dictionary(self._pa_array.type)
+ and pa.types.is_string(self._pa_array.type.value_type)
+ ):
  raise ValueError(
  "ArrowStringArray requires a PyArrow (chunked) array of string type"
  )

pandas/tests/arrays/string_/test_string_arrow.py

@@ -69,6 +69,33 @@ def test_constructor_not_string_type_raises(array, chunked):
  ArrowStringArray(arr)
 
 
+@pytest.mark.parametrize("chunked", [True, False])
+def test_constructor_not_string_type_value_dictionary_raises(chunked):
+ pa = pytest.importorskip("pyarrow")
+
+ arr = pa.array([1, 2, 3], pa.dictionary(pa.int32(), pa.int32()))
+ if chunked:
+ arr = pa.chunked_array(arr)
+
+ msg = re.escape(
+ "ArrowStringArray requires a PyArrow (chunked) array of string type"
+ )
+ with pytest.raises(ValueError, match=msg):
+ ArrowStringArray(arr)
+
+
+@pytest.mark.parametrize("chunked", [True, False])
+def test_constructor_valid_string_type_value_dictionary(chunked):
+ pa = pytest.importorskip("pyarrow")
+
+ arr = pa.array(["1", "2", "3"], pa.dictionary(pa.int32(), pa.utf8()))
+ if chunked:
+ arr = pa.chunked_array(arr)
+
+ arr = ArrowStringArray(arr)
+ assert pa.types.is_string(arr._pa_array.type.value_type)
+
+
 @skip_if_no_pyarrow
 def test_from_sequence_wrong_dtype_raises():
  with pd.option_context("string_storage", "python"):