update prek libraries, make lint (#2696)

<!--
Thanks for opening a pull request!
-->

<!-- In the case this PR will resolve an issue, please replace
${GITHUB_ISSUE_ID} below with the actual Github issue id. -->
<!-- Closes #${GITHUB_ISSUE_ID} -->

# Rationale for this change
Updated prek libraries (`poetry run prek auto-update`)
This also triggered updates to deprecate `Union` and `Optional` since we
no longer support python 3.9
Skipping [ruff `zip-without-explicit-strict
(B905)`](https://docs.astral.sh/ruff/rules/zip-without-explicit-strict/)
for now

## Are these changes tested?
Yes, `make lint`

## Are there any user-facing changes?

<!-- In the case of user-facing changes, please add the changelog label.
-->

Author: kevinjqliu

.pre-commit-config.yaml

@@ -27,13 +27,13 @@ repos:
       - id: check-yaml
       - id: check-ast
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.9
+    rev: v0.14.3
     hooks:
       - id: ruff
         args: [ --fix, --exit-non-zero-on-fix ]
       - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.17.1
+    rev: v1.18.2
     hooks:
       - id: mypy
         args:

pyiceberg/avro/codecs/__init__.py

@@ -26,7 +26,7 @@
 
 from __future__ import annotations
 
-from typing import Dict, Literal, Optional, Type
+from typing import Dict, Literal, Type
 
 from typing_extensions import TypeAlias
 
@@ -40,7 +40,7 @@
 
 AVRO_CODEC_KEY = "avro.codec"
 
-KNOWN_CODECS: Dict[AvroCompressionCodec, Optional[Type[Codec]]] = {
+KNOWN_CODECS: Dict[AvroCompressionCodec, Type[Codec] | None] = {
     "null": None,
     "bzip2": BZip2Codec,
     "snappy": SnappyCodec,

pyiceberg/avro/decoder.py

@@ -21,7 +21,6 @@
     Dict,
     List,
     Tuple,
-    Union,
     cast,
 )
 
@@ -137,7 +136,7 @@ class StreamingBinaryDecoder(BinaryDecoder):
     __slots__ = "_input_stream"
     _input_stream: InputStream
 
-    def __init__(self, input_stream: Union[bytes, InputStream]) -> None:
+    def __init__(self, input_stream: bytes | InputStream) -> None:
         """Reader is a Python object on which we can call read, seek, and tell."""
         if isinstance(input_stream, bytes):
             # In the case of bytes, we wrap it into a BytesIO to make it a stream

pyiceberg/avro/file.py

@@ -30,7 +30,6 @@
     Dict,
     Generic,
     List,
-    Optional,
     Type,
     TypeVar,
 )
@@ -85,7 +84,7 @@ def meta(self) -> Dict[str, str]:
     def sync(self) -> bytes:
         return self._data[2]
 
-    def compression_codec(self) -> Optional[Type[Codec]]:
+    def compression_codec(self) -> Type[Codec] | None:
         """Get the file's compression codec algorithm from the file's metadata.
 
         In the case of a null codec, we return a None indicating that we
@@ -146,20 +145,20 @@ class AvroFile(Generic[D]):
         "block",
     )
     input_file: InputFile
-    read_schema: Optional[Schema]
+    read_schema: Schema | None
     read_types: Dict[int, Callable[..., StructProtocol]]
     read_enums: Dict[int, Callable[..., Enum]]
     header: AvroFileHeader
     schema: Schema
     reader: Reader
 
     decoder: BinaryDecoder
-    block: Optional[Block[D]]
+    block: Block[D] | None
 
     def __init__(
         self,
         input_file: InputFile,
-        read_schema: Optional[Schema] = None,
+        read_schema: Schema | None = None,
         read_types: Dict[int, Callable[..., StructProtocol]] = EMPTY_DICT,
         read_enums: Dict[int, Callable[..., Enum]] = EMPTY_DICT,
     ) -> None:
@@ -186,9 +185,7 @@ def __enter__(self) -> AvroFile[D]:
 
         return self
 
-    def __exit__(
-        self, exctype: Optional[Type[BaseException]], excinst: Optional[BaseException], exctb: Optional[TracebackType]
-    ) -> None:
+    def __exit__(self, exctype: Type[BaseException] | None, excinst: BaseException | None, exctb: TracebackType | None) -> None:
         """Perform cleanup when exiting the scope of a 'with' statement."""
 
     def __iter__(self) -> AvroFile[D]:
@@ -242,7 +239,7 @@ def __init__(
         output_file: OutputFile,
         file_schema: Schema,
         schema_name: str,
-        record_schema: Optional[Schema] = None,
+        record_schema: Schema | None = None,
         metadata: Dict[str, str] = EMPTY_DICT,
     ) -> None:
         self.output_file = output_file
@@ -270,9 +267,7 @@ def __enter__(self) -> AvroOutputFile[D]:
 
         return self
 
-    def __exit__(
-        self, exctype: Optional[Type[BaseException]], excinst: Optional[BaseException], exctb: Optional[TracebackType]
-    ) -> None:
+    def __exit__(self, exctype: Type[BaseException] | None, excinst: BaseException | None, exctb: TracebackType | None) -> None:
         """Perform cleanup when exiting the scope of a 'with' statement."""
         self.output_stream.close()
 
@@ -289,7 +284,7 @@ def _write_header(self) -> None:
         header = AvroFileHeader(MAGIC, meta, self.sync_bytes)
         construct_writer(META_SCHEMA).write(self.encoder, header)
 
-    def compression_codec(self) -> Optional[Type[Codec]]:
+    def compression_codec(self) -> Type[Codec] | None:
         """Get the file's compression codec algorithm from the file's metadata.
 
         In the case of a null codec, we return a None indicating that we

pyiceberg/avro/reader.py

@@ -35,7 +35,6 @@
     Callable,
     List,
     Mapping,
-    Optional,
     Tuple,
 )
 from uuid import UUID
@@ -292,7 +291,7 @@ def __repr__(self) -> str:
 class OptionReader(Reader):
     option: Reader = dataclassfield()
 
-    def read(self, decoder: BinaryDecoder) -> Optional[Any]:
+    def read(self, decoder: BinaryDecoder) -> Any | None:
         # For the Iceberg spec it is required to set the default value to null
         # From https://iceberg.apache.org/spec/#avro
         # Optional fields must always set the Avro field default value to null.
@@ -320,14 +319,14 @@ class StructReader(Reader):
         "_hash",
         "_max_pos",
     )
-    field_readers: Tuple[Tuple[Optional[int], Reader], ...]
+    field_readers: Tuple[Tuple[int | None, Reader], ...]
     create_struct: Callable[..., StructProtocol]
     struct: StructType
-    field_reader_functions = Tuple[Tuple[Optional[str], int, Optional[Callable[[BinaryDecoder], Any]]], ...]
+    field_reader_functions = Tuple[Tuple[str | None, int, Callable[[BinaryDecoder], Any] | None], ...]
 
     def __init__(
         self,
-        field_readers: Tuple[Tuple[Optional[int], Reader], ...],
+        field_readers: Tuple[Tuple[int | None, Reader], ...],
         create_struct: Callable[..., StructProtocol],
         struct: StructType,
     ) -> None:
@@ -339,7 +338,7 @@ def __init__(
         if not isinstance(self.create_struct(), StructProtocol):
             raise ValueError(f"Incompatible with StructProtocol: {self.create_struct}")
 
-        reading_callbacks: List[Tuple[Optional[int], Callable[[BinaryDecoder], Any]]] = []
+        reading_callbacks: List[Tuple[int | None, Callable[[BinaryDecoder], Any]]] = []
         max_pos = -1
         for pos, field in field_readers:
             if pos is not None: