From 1971fcfe0875eeb200dbcb66f385e504cfad6609 Mon Sep 17 00:00:00 2001
From: Chinmay Bhat <12948588+chinmay-bhat@users.noreply.github.com>
Date: Tue, 10 Sep 2024 22:15:43 +0530
Subject: [PATCH] Cache Manifest files (#787)

* cache manifests

* update API

* small fix

* move cache to module level

* update signature and check
---
 pyiceberg/table/snapshots.py | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/pyiceberg/table/snapshots.py b/pyiceberg/table/snapshots.py
index 1ccb079922..980399a2ab 100644
--- a/pyiceberg/table/snapshots.py
+++ b/pyiceberg/table/snapshots.py
@@ -19,6 +19,7 @@
 import time
 from collections import defaultdict
 from enum import Enum
+from functools import lru_cache
 from typing import TYPE_CHECKING, Any, DefaultDict, Dict, Iterable, List, Mapping, Optional
 
 from pydantic import Field, PrivateAttr, model_serializer
@@ -230,6 +231,13 @@ def __eq__(self, other: Any) -> bool:
         )
 
 
+@lru_cache
+def _manifests(io: FileIO, manifest_list: str) -> List[ManifestFile]:
+    """Return the manifests from the manifest list."""
+    file = io.new_input(manifest_list)
+    return list(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)
@@ -250,9 +258,9 @@ def __str__(self) -> str:
         return result_str
 
     def manifests(self, io: FileIO) -> List[ManifestFile]:
-        if self.manifest_list is not None:
-            file = io.new_input(self.manifest_list)
-            return list(read_manifest_list(file))
+        """Return the manifests for the given snapshot."""
+        if self.manifest_list:
+            return _manifests(io, self.manifest_list)
         return []