lint fixes

Author: rambleraptor

pyiceberg/table/puffin.py

@@ -17,7 +17,8 @@
 import io
 import math
 import zlib
-from typing import TYPE_CHECKING, Dict, Iterable, List, Literal, Optional
+from collections.abc import Iterable
+from typing import TYPE_CHECKING, Literal
 
 from pydantic import Field
 from pyroaring import BitMap, FrozenBitMap
@@ -65,9 +66,9 @@ def _deserialize_bitmap(pl: bytes) -> list[BitMap]:
     return bitmaps
 
 
-def _serialize_bitmaps(bitmaps: Dict[int, BitMap]) -> bytes:
+def _serialize_bitmaps(bitmaps: dict[int, BitMap]) -> bytes:
     """
-    Serializes a dictionary of bitmaps into a byte array.
+    Serialize a dictionary of bitmaps into a byte array.
 
     The format is:
     - 8 bytes: number of bitmaps (little-endian)
@@ -149,8 +150,8 @@ def to_vector(self) -> dict[str, "pa.ChunkedArray"]:
 
 
 class PuffinWriter:
-    _blobs: List[PuffinBlobMetadata]
-    _blob_payloads: List[bytes]
+    _blobs: list[PuffinBlobMetadata]
+    _blob_payloads: list[bytes]
 
     def __init__(self) -> None:
         self._blobs = []
@@ -162,7 +163,7 @@ def add(
         referenced_data_file: str,
     ) -> None:
         # 1. Create bitmaps from positions
-        bitmaps: Dict[int, BitMap] = {}
+        bitmaps: dict[int, BitMap] = {}
         cardinality = 0
         for pos in positions:
             cardinality += 1
@@ -219,7 +220,7 @@ def finish(self) -> bytes:
             for blob_payload in self._blob_payloads:
                 payload_buffer.write(blob_payload)
 
-            updated_blobs_metadata: List[PuffinBlobMetadata] = []
+            updated_blobs_metadata: list[PuffinBlobMetadata] = []
             current_offset = 4  # Start after file magic (4 bytes)
             for i, blob_payload in enumerate(self._blob_payloads):
                 original_metadata_dict = self._blobs[i].model_dump(by_alias=True, exclude_none=True)

tests/table/test_puffin.py

@@ -19,7 +19,7 @@
 import pytest
 from pyroaring import BitMap
 
-from pyiceberg.table.puffin import _deserialize_bitmap, PuffinFile, PuffinWriter, PROPERTY_REFERENCED_DATA_FILE
+from pyiceberg.table.puffin import PROPERTY_REFERENCED_DATA_FILE, PuffinFile, PuffinWriter, _deserialize_bitmap
 
 
 def _open_file(file: str) -> bytes:
@@ -73,10 +73,10 @@ def test_map_high_vals() -> None:
         _ = _deserialize_bitmap(puffin)
 
 
-def test_puffin_round_trip():
+def test_puffin_round_trip() -> None:
     # Define some deletion positions for multiple files
     deletions1 = [10, 20, 30]
-    deletions2 = [5, (1 << 32) + 1] # Test with a high-bit position
+    deletions2 = [5, (1 << 32) + 1]  # Test with a high-bit position
 
     file1_path = "path/to/data1.parquet"
     file2_path = "path/to/data2.parquet"
@@ -92,7 +92,7 @@ def test_puffin_round_trip():
 
     # Assert footer metadata
     assert len(reader.footer.blobs) == 2
-    
+
     blob1_meta = reader.footer.blobs[0]
     assert blob1_meta.properties[PROPERTY_REFERENCED_DATA_FILE] == file1_path
     assert blob1_meta.properties["cardinality"] == str(len(deletions1))
@@ -103,15 +103,15 @@ def test_puffin_round_trip():
 
     # Assert the content of deletion vectors
     read_vectors = reader.to_vector()
-    
+
     assert file1_path in read_vectors
     assert file2_path in read_vectors
 
     assert read_vectors[file1_path].to_pylist() == sorted(deletions1)
     assert read_vectors[file2_path].to_pylist() == sorted(deletions2)
 
 
-def test_write_and_read_puffin_file():
+def test_write_and_read_puffin_file() -> None:
     writer = PuffinWriter()
     writer.add(positions=[1, 2, 3], referenced_data_file="file1.parquet")
     writer.add(positions=[4, 5, 6], referenced_data_file="file2.parquet")
@@ -139,7 +139,7 @@ def test_write_and_read_puffin_file():
     assert vectors["file2.parquet"].to_pylist() == [4, 5, 6]
 
 
-def test_puffin_file_with_no_blobs():
+def test_puffin_file_with_no_blobs() -> None:
     writer = PuffinWriter()
     puffin_bytes = writer.finish()