jorisvandenbossche commented on a change in pull request #7000:
URL: https://github.com/apache/arrow/pull/7000#discussion_r412191161



##########
File path: python/pyarrow/tests/test_dataset.py
##########
@@ -671,41 +669,29 @@ def test_fragments(tempdir):
     f = fragments[0]
 
     # file's schema does not include partition column
-    phys_schema = f.schema.remove(f.schema.get_field_index('part'))
-    assert f.format.inspect(f.path, f.filesystem) == phys_schema
+    assert f.physical_schema.names == ['f1', 'f2']
+    assert f.format.inspect(f.path, f.filesystem) == f.physical_schema
     assert f.partition_expression.equals(ds.field('part') == 'a')
 
     # scanning fragment includes partition columns
-    result = f.to_table()
-    assert f.schema == result.schema
+    result = f.to_table(schema=dataset.schema)
     assert result.column_names == ['f1', 'f2', 'part']
-    assert len(result) == 4
     assert result.equals(table.slice(0, 4))
-
-    # scanning fragments follow column projection
-    fragments = list(dataset.get_fragments(columns=['f1', 'part']))

Review comment:
       Keep this but where the columns selection is passed to `to_table` ?




----------------------------------------------------------------
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:
us...@infra.apache.org


Reply via email to