mccormickt12 commented on code in PR #2291:
URL: https://github.com/apache/iceberg-python/pull/2291#discussion_r2285892406
##########
pyiceberg/io/pyarrow.py:
##########
@@ -381,21 +381,38 @@ def to_input_file(self) -> PyArrowFile:
class PyArrowFileIO(FileIO):
fs_by_scheme: Callable[[str, Optional[str]], FileSystem]
+ config: Config
def __init__(self, properties: Properties = EMPTY_DICT):
self.fs_by_scheme: Callable[[str, Optional[str]], FileSystem] =
lru_cache(self._initialize_fs)
+ self.config = Config()
super().__init__(properties=properties)
@staticmethod
- def parse_location(location: str) -> Tuple[str, str, str]:
- """Return the path without the scheme."""
+ def parse_location(location: str, config: Config) -> Tuple[str, str, str]:
+ """Return (scheme, netloc, path) for the given location.
+
+ Uses environment variables DEFAULT_SCHEME and DEFAULT_NETLOC
+ if scheme/netloc are missing.
+ """
uri = urlparse(location)
- if not uri.scheme:
- return "file", uri.netloc, os.path.abspath(location)
- elif uri.scheme in ("hdfs", "viewfs"):
- return uri.scheme, uri.netloc, uri.path
+
+ # Load defaults from environment
+ default_scheme = config.get_str("default-scheme") or "file"
+ default_netloc = config.get_str("default-netloc") or ""
+
Review Comment:
sorry im not totally following. When is load_catalog called for client? I
don't see it called in table or pyarrow. Are you saying i should load_catalog
there? That doesn't seem obviously correct to me, and my example code doesn't
call load_catalog either.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
