kevinjqliu commented on code in PR #2291:
URL: https://github.com/apache/iceberg-python/pull/2291#discussion_r2260704048
##########
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:
nit: i think its better to pass these in through the properties field
https://py.iceberg.apache.org/configuration/#hdfs
we can get the env variable and then pass into the properties.
##########
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 ""
+
+ # Apply logic
+ scheme = uri.scheme or default_scheme
+ netloc = uri.netloc or 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:
i actually really want to get rid of this if {scheme} logic here.
Is there a way to refactor these changes down to the `_initialize_hdfs_fs`?
so we can keep the hdfs logic in the same place?
--
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
