read_html, read_parquet

Author: cmp0xff

pandas-stubs/__init__.pyi

@@ -114,7 +114,9 @@ from pandas.io.api import (
     read_feather as read_feather,
     read_fwf as read_fwf,
     read_hdf as read_hdf,
+    read_html as read_html,
     read_json as read_json,
+    read_parquet as read_parquet,
     read_pickle as read_pickle,
     read_sas as read_sas,
     read_spss as read_spss,
@@ -126,15 +128,9 @@ from pandas.io.api import (
 from pandas.io.api import (
     read_excel as read_excel,  # pyright: ignore[reportUnknownVariableType]
 )
-from pandas.io.api import (
-    read_html as read_html,  # pyright: ignore[reportUnknownVariableType]
-)
 from pandas.io.api import (
     read_orc as read_orc,  # pyright: ignore[reportUnknownVariableType]
 )
-from pandas.io.api import (
-    read_parquet as read_parquet,  # pyright: ignore[reportUnknownVariableType]
-)
 from pandas.io.api import (
     read_sql as read_sql,  # pyright: ignore[reportUnknownVariableType]
 )

pandas-stubs/io/api.pyi

@@ -7,17 +7,13 @@ from pandas.io.excel import (
     read_excel as read_excel,  # pyright: ignore[reportUnknownVariableType]
 )
 from pandas.io.feather_format import read_feather as read_feather
-from pandas.io.html import (
-    read_html as read_html,  # pyright: ignore[reportUnknownVariableType]
-)
+from pandas.io.html import read_html as read_html
 from pandas.io.json import read_json as read_json
 from pandas.io.orc import (
     read_orc as read_orc,  # pyright: ignore[reportUnknownVariableType]
 )
-from pandas.io.parquet import (
-    read_parquet as read_parquet,  # pyright: ignore[reportUnknownVariableType]
-)
-from pandas.io.parsers import (
+from pandas.io.parquet import read_parquet as read_parquet
+from pandas.io.parsers.readers import (
     read_csv as read_csv,
     read_fwf as read_fwf,
     read_table as read_table,

pandas-stubs/io/html.pyi

@@ -29,7 +29,7 @@ from pandas._typing import (
 def read_html(
     io: FilePath | ReadBuffer[str],
     *,
-    match: str | Pattern = ...,
+    match: str | Pattern[str] = ...,
     flavor: HTMLFlavors | Sequence[HTMLFlavors] | None = ...,
     header: int | Sequence[int] | None = ...,
     index_col: int | Sequence[int] | list[HashableT1] | None = ...,

pandas-stubs/io/parquet.pyi

@@ -1,4 +1,8 @@
-from typing import Any
+from typing import (
+    Any,
+    Literal,
+    TypeAlias,
+)
 
 from pandas import DataFrame
 
@@ -10,13 +14,16 @@ from pandas._typing import (
     StorageOptions,
 )
 
+_OP: TypeAlias = Literal["==", "=", ">", ">=", "<", "<=", "!=", "in", "not in"]
+_FILTER: TypeAlias = tuple[str, _OP, Any]
+
 def read_parquet(
     path: FilePath | ReadBuffer[bytes],
     engine: ParquetEngine = "auto",
     columns: list[str] | None = None,
     storage_options: StorageOptions = None,
     dtype_backend: DtypeBackend = "numpy_nullable",
     filesystem: Any = None,
-    filters: list[tuple] | list[list[tuple]] | None = None,
+    filters: list[_FILTER] | list[list[_FILTER]] | None = None,
     **kwargs: Any,
 ) -> DataFrame: ...