adding some ignores to pass more checks

Author: rok

.github/workflows/python.yml

@@ -140,10 +140,11 @@ jobs:
 
       - name: Type check with mypy and pyright
         run: |-
-            python -m pip install mypy pyright griffe libcst scipy-stubs pandas-stubs types-python-dateutil types-psutil types-requests griffe libcst types-cffi
+            python -m pip install mypy pyright griffe libcst pytest hypothesis fsspec scipy-stubs pandas-stubs types-python-dateutil types-psutil types-requests griffe libcst types-cffi
             pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple pyarrow
             cd python
-            mypy ./pyarrow-stubs ./pyarrow/tests/test_array.py ./pyarrow/tests/test_io.py
+            # mypy pyarrow-stubs/ pyarrow/tests/interchange pyarrow/tests/parquet pyarrow/tests/test_array.py pyarrow/tests/test_io.py
+            mypy --ignore-missing-imports pyarrow-stubs/ pyarrow/tests
             pyright ./pyarrow-stubs
             cd ..
             python ./dev/update_stub_docstrings.py -f ./python/pyarrow-stubs

python/pyarrow-stubs/_compute.pyi

@@ -176,7 +176,7 @@ class DictionaryEncodeOptions(FunctionOptions):
 
 class RunEndEncodeOptions(FunctionOptions):
     # TODO: default is DataType(int32)
-    def __init__(self, run_end_type: lib.DataType = ...) -> None: ...
+    def __init__(self, run_end_type: lib.DataType | str = ...) -> None: ...
 
 
 class ElementWiseAggregateOptions(FunctionOptions):

python/pyarrow-stubs/_compute_docstring.pyi

@@ -0,0 +1,18 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+function_doc_additions: dict[str, str]

python/pyarrow-stubs/_types.pyi

@@ -864,8 +864,8 @@ def type_for_alias(name: Any) -> DataType: ...
 
 def schema(
     fields: Iterable[Field[Any]]
-    | Iterable[tuple[str, DataType]]
-    | Mapping[str, DataType],
+    | Iterable[tuple[str, DataType | str]]
+    | Mapping[str, DataType | str],
     metadata: dict[bytes | str, bytes | str] | None = None,
 ) -> Schema: ...
 

python/pyarrow-stubs/acero.pyi

@@ -29,6 +29,7 @@ from typing import Literal
 
 from . import lib
 from .compute import Expression, FunctionOptions
+from .dataset import InMemoryDataset, Dataset
 
 _StrOrExpr: TypeAlias = str | Expression
 
@@ -111,3 +112,23 @@ class AsofJoinNodeOptions(ExecNodeOptions):
         right_by: _StrOrExpr | list[_StrOrExpr],
         tolerance: int,
     ) -> None: ...
+
+
+def _perform_join(
+    join_type: str,
+    left_operand: lib.Table | Dataset,
+    left_keys: str | list[str],
+    right_operand: lib.Table | Dataset,
+    right_keys: str | list[str],
+    left_suffix: str,
+    right_suffix: str,
+    use_threads: bool,
+    coalesce_keys: bool,
+    output_type: type[lib.Table | InMemoryDataset] = lib.Table,
+    filter_expression: Expression | None = None,
+) -> lib.Table | InMemoryDataset: ...
+
+
+def _filter_table(
+    table: lib.Table | lib.RecordBatch, filter_expression: Expression,
+    use_threads: bool = True) -> lib.Table | lib.RecordBatch: ...

python/pyarrow-stubs/compute.pyi

@@ -52,6 +52,7 @@ from pyarrow._compute import RoundBinaryOptions as RoundBinaryOptions
 from pyarrow._compute import RoundOptions as RoundOptions
 from pyarrow._compute import RoundTemporalOptions as RoundTemporalOptions
 from pyarrow._compute import RoundToMultipleOptions as RoundToMultipleOptions
+from pyarrow._compute import RunEndEncodeOptions as RunEndEncodeOptions
 from pyarrow._compute import ScalarAggregateOptions as ScalarAggregateOptions
 from pyarrow._compute import SelectKOptions as SelectKOptions
 from pyarrow._compute import SetLookupOptions as SetLookupOptions
@@ -73,6 +74,7 @@ from pyarrow._compute import WeekOptions as WeekOptions
 
 from pyarrow._compute import _Order, _Placement
 from pyarrow._stubs_typing import ArrayLike, ScalarLike
+from pyarrow._types import _RunEndType
 from . import lib
 
 _P = ParamSpec("_P")
@@ -645,8 +647,8 @@ def atan2(
 
 # ========================= 2.5 Comparisons functions =========================
 def equal(
-    x: lib.Scalar | lib.Array | lib.ChunkedArray | Expression,
-    y: lib.Scalar | lib.Array | lib.ChunkedArray | Expression,
+    x: lib.Scalar | lib.Array | lib.ChunkedArray | Expression | Any,
+    y: lib.Scalar | lib.Array | lib.ChunkedArray | Expression | Any,
     /, *, memory_pool: lib.MemoryPool | None = None
 ) -> lib.BooleanScalar | lib.BooleanArray | Expression: ...
 
@@ -1634,4 +1636,11 @@ def pairwise_diff(
 ) -> _NumericOrTemporalArrayT | Expression: ...
 
 
+def run_end_encode(
+    input: _NumericOrTemporalArrayT | Expression, /, *, run_end_type: _RunEndType,
+    value_type: _DataTypeT, options: RunEndEncodeOptions | None = None,
+    memory_pool: lib.MemoryPool | None = None
+) -> _NumericOrTemporalArrayT | Expression: ...
+
+
 pairwise_diff_checked = _clone_signature(pairwise_diff)

python/pyarrow-stubs/interchange/from_dataframe.pyi

@@ -38,6 +38,9 @@ ColumnObject: TypeAlias = Any
 def from_dataframe(df: DataFrameObject, allow_copy=True) -> Table: ...
 
 
+def _from_dataframe(df: DataFrameObject, allow_copy=True) -> Table: ...
+
+
 def protocol_df_chunk_to_pyarrow(
     df: DataFrameObject, allow_copy: bool = True) -> RecordBatch: ...
 

python/pyarrow-stubs/pandas_compat.pyi

@@ -22,7 +22,7 @@ import pandas as pd
 
 from pandas import DatetimeTZDtype
 
-from .lib import Array, DataType, Schema, Table
+from .lib import Array, DataType, Schema, Table, _pandas_api
 
 _T = TypeVar("_T")
 
@@ -85,3 +85,8 @@ def table_to_dataframe(
 
 
 def make_tz_aware(series: pd.Series, tz: str) -> pd.Series: ...
+
+
+__all__ = [
+    "_pandas_api",
+]

python/pyarrow-stubs/scalar.pyi

@@ -399,7 +399,7 @@ class FixedShapeTensorScalar(ExtensionScalar):
 
 def scalar(
     value: Any,
-    type: _DataTypeT,
+    type: _DataTypeT | None = None,
     *,
     from_pandas: bool | None = None,
     memory_pool: MemoryPool | None = None,

python/pyarrow-stubs/table.pyi

@@ -249,7 +249,7 @@ class ChunkedArray(_PandasConvertible[pd.Series], Generic[_Scalar_co]):
 def chunked_array(
     arrays: Iterable[NullableCollection[Any]]
     | Iterable[Iterable[Any] | SupportArrowStream | SupportArrowArray]
-    | Iterable[Array[_ScalarT]],
+    | Iterable[Array[_ScalarT]] | Array[_ScalarT],
     type: DataType | str | None = None,
 ) -> ChunkedArray[Scalar[Any]] | ChunkedArray[_ScalarT]: ...
 
@@ -586,8 +586,8 @@ class Table(_Tabular[ChunkedArray[Any]]):
 
 
 def record_batch(
-    data: dict[str, list[Any] | Array[Any]]
-    | Collection[Array[Any]]
+    data: Mapping[str, list[Any] | Array[Any]]
+    | Collection[Array[Any] | ChunkedArray[Any]]
     | pd.DataFrame
     | SupportArrowArray
     | SupportArrowDeviceArray,
@@ -598,7 +598,7 @@ def record_batch(
 
 
 def table(
-    data: dict[str, list[Any] | Array[Any]]
+    data: Mapping[str, list[Any] | Array[Any]]
     | Collection[ArrayOrChunkedArray[Any]]
     | pd.DataFrame
     | SupportArrowArray