Fokko commented on code in PR #2291:
URL: https://github.com/apache/iceberg-python/pull/2291#discussion_r2306681310
##########
pyiceberg/io/pyarrow.py:
##########
@@ -387,15 +387,29 @@ def __init__(self, properties: Properties = EMPTY_DICT):
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, properties: Properties = EMPTY_DICT) ->
Tuple[str, str, str]:
+ """Return (scheme, netloc, path) for the given location.
+
+ Uses DEFAULT_SCHEME and DEFAULT_NETLOC if scheme/netloc are missing.
+ """
uri = urlparse(location)
+
+ default_scheme = properties.get("DEFAULT_SCHEME", "file")
+ default_netloc = properties.get("DEFAULT_NETLOC", "")
+
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
+ scheme = default_scheme
+ if not uri.netloc:
+ netloc = default_netloc
+
+ if scheme in ("hdfs", "viewfs"):
+ return scheme, netloc, uri.path
else:
- return uri.scheme, uri.netloc, f"{uri.netloc}{uri.path}"
+ # For non-HDFS URIs, include netloc in the path if present
+ path = uri.path if uri.scheme else os.path.abspath(location)
+ if netloc and not path.startswith(netloc):
+ path = f"{netloc}{path}"
+ return scheme, netloc, path
Review Comment:
It looks like the tests are faling:
```python
@staticmethod
def parse_location(location: str, properties: Properties = EMPTY_DICT)
-> Tuple[str, str, str]:
"""Return (scheme, netloc, path) for the given location.
Uses DEFAULT_SCHEME and DEFAULT_NETLOC if scheme/netloc are missing.
"""
uri = urlparse(location)
default_scheme = properties.get("DEFAULT_SCHEME", "file")
default_netloc = properties.get("DEFAULT_NETLOC", "")
if not uri.scheme:
scheme = default_scheme
if not uri.netloc:
netloc = default_netloc
> if scheme in ("hdfs", "viewfs"):
E UnboundLocalError: local variable 'scheme' referenced before
assignment
```
I agree with @kevinjqliu that it would be best to keep the changes in the
logic to a minimum. This piece of logic contains a lot of historical knowledge
as it is amended over time.
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
