Arrow: Suppress warning and cache bucket location

Attemt to remove the unneccessary warning, and cache the
location of the bucket independent of the FileIO.

Fixes #1705
Fixes #1708

Author: Fokko

pyiceberg/io/pyarrow.py

@@ -194,6 +194,13 @@
 T = TypeVar("T")
 
 
+@lru_cache
+def _cached_resolve_s3_region(bucket: str) -> str:
+    from pyarrow.fs import resolve_s3_region
+
+    return resolve_s3_region(bucket=bucket)
+
+
 class UnsupportedPyArrowTypeException(Exception):
     """Cannot convert PyArrow type to corresponding Iceberg type."""
 
@@ -414,19 +421,19 @@ def _initialize_oss_fs(self) -> FileSystem:
         return S3FileSystem(**client_kwargs)
 
     def _initialize_s3_fs(self, netloc: Optional[str]) -> FileSystem:
-        from pyarrow.fs import S3FileSystem, resolve_s3_region
+        from pyarrow.fs import S3FileSystem
 
         # Resolve region from netloc(bucket), fallback to user-provided region
         provided_region = get_first_property_value(self.properties, S3_REGION, AWS_REGION)
 
         try:
-            bucket_region = resolve_s3_region(bucket=netloc)
+            bucket_region = _cached_resolve_s3_region(bucket=netloc)
         except (OSError, TypeError):
             bucket_region = None
             logger.warning(f"Unable to resolve region for bucket {netloc}, using default region {provided_region}")
 
         bucket_region = bucket_region or provided_region
-        if bucket_region != provided_region:
+        if provided_region is not None and bucket_region != provided_region:
             logger.warning(
                 f"PyArrow FileIO overriding S3 bucket region for bucket {netloc}: "
                 f"provided region {provided_region}, actual region {bucket_region}"