ndrluis commented on code in PR #1043:
URL: https://github.com/apache/iceberg-python/pull/1043#discussion_r1717675207
##########
pyiceberg/io/pyarrow.py:
##########
@@ -1308,6 +1309,192 @@ def _read_all_delete_files(fs: FileSystem, tasks:
Iterable[FileScanTask]) -> Dic
return deletes_per_file
+def _fs_from_file_path(file_path: str, io: FileIO) -> FileSystem:
+ scheme, netloc, _ = _parse_location(file_path)
+ if isinstance(io, PyArrowFileIO):
+ return io.fs_by_scheme(scheme, netloc)
+ else:
+ try:
+ from pyiceberg.io.fsspec import FsspecFileIO
+
+ if isinstance(io, FsspecFileIO):
+ from pyarrow.fs import PyFileSystem
+
+ return PyFileSystem(FSSpecHandler(io.get_fs(scheme)))
+ else:
+ raise ValueError(f"Expected PyArrowFileIO or FsspecFileIO,
got: {io}")
+ except ModuleNotFoundError as e:
+ # When FsSpec is not installed
+ raise ValueError(f"Expected PyArrowFileIO or FsspecFileIO, got:
{io}") from e
+
+
+class PyArrowProjector:
+ _table_metadata: TableMetadata
+ _io: FileIO
+ _fs: FileSystem
+ _projected_schema: Schema
+ _bound_row_filter: BooleanExpression
+ _case_sensitive: bool
+ _limit: Optional[int]
+ """Projects an Iceberg Table to a PyArrow construct.
Review Comment:
hinking about it again, to_table (the arrow feels redundant to me) or
to_record_batches might make more sense than the for prefix.
The for prefix would make more sense in a scenario where the scan doesn't
happen.
--
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
