wesm commented on a change in pull request #7122:
URL: https://github.com/apache/arrow/pull/7122#discussion_r421631022
##########
File path: python/pyarrow/feather.py
##########
@@ -234,11 +234,24 @@ def read_table(source, columns=None, memory_map=True):
column_types = [type(column) for column in columns]
if all(map(lambda t: t == int, column_types)):
- return reader.read_indices(columns)
+ table = reader.read_indices(columns)
elif all(map(lambda t: t == str, column_types)):
- return reader.read_names(columns)
-
- column_type_names = [t.__name__ for t in column_types]
- raise TypeError("Columns must be indices or names. "
- "Got columns {} of types {}"
- .format(columns, column_type_names))
+ table = reader.read_names(columns)
+ else:
+ column_type_names = [t.__name__ for t in column_types]
+ raise TypeError("Columns must be indices or names. "
+ "Got columns {} of types {}"
+ .format(columns, column_type_names))
+
+ # Feather v1 already respects the column selection
+ if reader.version < 3:
+ return table
+ # Feather v2 reads with sorted / deduplicated selection
+ elif sorted(set(columns)) == columns:
+ return table
+ else:
+ # follow exact order / selection of names
+ new_fields = [table.schema.field(c) for c in columns]
+ new_schema = schema(new_fields, metadata=table.schema.metadata)
+ new_columns = [table.column(c) for c in columns]
+ return Table.from_arrays(new_columns, schema=new_schema)
Review comment:
This seems useful enough to have a helper method (doesn't need to be in
this PR)
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
