kylebarron commented on code in PR #3447:
URL: https://github.com/apache/iceberg-python/pull/3447#discussion_r3507324140
##########
pyiceberg/io/pyarrow.py:
##########
@@ -3043,3 +3060,23 @@ def _get_field_from_arrow_table(arrow_table: pa.Table,
field_path: str) -> pa.Ar
field_array = arrow_table[path_parts[0]]
# Navigate into the struct using the remaining path parts
return pc.struct_field(field_array, path_parts[1:])
+
+
+def _coerce_arrow_input(df: pa.Table | pa.RecordBatchReader |
ArrowStreamExportable) -> pa.Table | pa.RecordBatchReader:
+ """Normalize Arrow write input to a pa.Table or pa.RecordBatchReader.
+
+ Native pyarrow inputs pass through unchanged; any object implementing the
+ Arrow PyCapsule stream interface (``__arrow_c_stream__``) is imported as a
+ streaming RecordBatchReader.
+ """
+ if isinstance(df, (pa.Table, pa.RecordBatchReader)):
+ return df
+
+ # Any object implementing the Arrow PyCapsule stream interface.
+ if hasattr(df, "__arrow_c_stream__"):
+ return pa.RecordBatchReader.from_stream(df)
+
+ raise ValueError(
+ f"Expected pa.Table, pa.RecordBatchReader, or an object implementing
the "
+ f"Arrow PyCapsule interface (__arrow_c_stream__), got: {df!r}"
+ )
Review Comment:
This looks to be the core change in this PR and looks valid 👍
--
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]
