move _manifests to manifest.py

pyiceberg/manifest.py

@@ -28,9 +28,12 @@
     List,
     Literal,
     Optional,
+    Tuple,
     Type,
 )
 
+from cachetools import LRUCache, cached
+from cachetools.keys import hashkey
 from pydantic_core import to_json
 
 from pyiceberg.avro.file import AvroFile, AvroOutputFile
@@ -620,6 +623,13 @@ def fetch_manifest_entry(self, io: FileIO, discard_deleted: bool = True) -> List
             ]
 
 
+@cached(cache=LRUCache(maxsize=128), key=lambda io, manifest_list: hashkey(manifest_list))
+def _manifests(io: FileIO, manifest_list: str) -> Tuple[ManifestFile, ...]:
+    """Read and cache manifests from the given manifest list, returning a tuple to prevent modification."""
+    file = io.new_input(manifest_list)
+    return tuple(read_manifest_list(file))
+
+
 def read_manifest_list(input_file: InputFile) -> Iterator[ManifestFile]:
     """
     Read the manifests from the manifest list.

pyiceberg/table/snapshots.py

@@ -19,14 +19,12 @@
 import time
 from collections import defaultdict
 from enum import Enum
-from typing import TYPE_CHECKING, Any, DefaultDict, Dict, Iterable, List, Mapping, Optional, Tuple
+from typing import TYPE_CHECKING, Any, DefaultDict, Dict, Iterable, List, Mapping, Optional
 
-from cachetools import LRUCache, cached
-from cachetools.keys import hashkey
 from pydantic import Field, PrivateAttr, model_serializer
 
 from pyiceberg.io import FileIO
-from pyiceberg.manifest import DataFile, DataFileContent, ManifestFile, read_manifest_list
+from pyiceberg.manifest import DataFile, DataFileContent, ManifestFile, _manifests
 from pyiceberg.partitioning import UNPARTITIONED_PARTITION_SPEC, PartitionSpec
 from pyiceberg.schema import Schema
 
@@ -232,13 +230,6 @@ def __eq__(self, other: Any) -> bool:
         )
 
 
-@cached(cache=LRUCache(maxsize=128), key=lambda io, manifest_list: hashkey(manifest_list))
-def _manifests(io: FileIO, manifest_list: str) -> Tuple[ManifestFile, ...]:
-    """Read and cache manifests from the given manifest list, returning a tuple to prevent modification."""
-    file = io.new_input(manifest_list)
-    return tuple(read_manifest_list(file))
-
-
 class Snapshot(IcebergBaseModel):
     snapshot_id: int = Field(alias="snapshot-id")
     parent_snapshot_id: Optional[int] = Field(alias="parent-snapshot-id", default=None)

tests/utils/test_manifest.py

@@ -32,13 +32,14 @@
     ManifestEntryStatus,
     ManifestFile,
     PartitionFieldSummary,
+    _manifests,
     read_manifest_list,
     write_manifest,
     write_manifest_list,
 )
 from pyiceberg.partitioning import UNPARTITIONED_PARTITION_SPEC, PartitionField, PartitionSpec
 from pyiceberg.schema import Schema
-from pyiceberg.table.snapshots import Operation, Snapshot, Summary, _manifests
+from pyiceberg.table.snapshots import Operation, Snapshot, Summary
 from pyiceberg.transforms import IdentityTransform
 from pyiceberg.typedef import Record, TableVersion
 from pyiceberg.types import IntegerType, NestedField
@@ -314,8 +315,7 @@ def test_read_manifest_v2(generated_manifest_file_file_v2: str) -> None:
 
 
 def test_read_manifest_cache(generated_manifest_file_file_v2: str) -> None:
-    # Mock the read_manifest_list function relative to the module path
-    with patch("pyiceberg.table.snapshots.read_manifest_list") as mocked_read_manifest_list:
+    with patch("pyiceberg.manifest.read_manifest_list") as mocked_read_manifest_list:
         io = load_file_io()
 
         snapshot = Snapshot(