kevinjqliu commented on code in PR #1354:
URL: https://github.com/apache/iceberg-python/pull/1354#discussion_r1854238935
##########
tests/io/test_pyarrow_stats.py:
##########
@@ -681,6 +685,39 @@ def test_stats_types(table_schema_nested: Schema) -> None:
]
+def test_read_missing_statistics() -> None:
+ # write statistics for only for "strings" column
+ metadata, table_metadata =
construct_test_table(write_statistics=["strings"])
+
+ # expect only "strings" column to have statistics in metadata
+ assert metadata.row_group(0).column(0).is_stats_set is True
+ assert metadata.row_group(0).column(0).statistics is not None
+
+ # expect all other columns to have no statistics
+ for r in range(metadata.num_row_groups):
+ for pos in range(1, metadata.num_columns):
+ assert metadata.row_group(r).column(pos).is_stats_set is False
+ assert metadata.row_group(r).column(pos).statistics is None
Review Comment:
nit, why does the range start at 1 here?
wdyt about combining both checks in a single loop?
if its `string` column, assert stat in metadata
if its not `string` column, assert no stat
##########
tests/io/test_pyarrow_stats.py:
##########
@@ -681,6 +685,39 @@ def test_stats_types(table_schema_nested: Schema) -> None:
]
+def test_read_missing_statistics() -> None:
+ # write statistics for only for "strings" column
+ metadata, table_metadata =
construct_test_table(write_statistics=["strings"])
+
+ # expect only "strings" column to have statistics in metadata
+ assert metadata.row_group(0).column(0).is_stats_set is True
+ assert metadata.row_group(0).column(0).statistics is not None
+
+ # expect all other columns to have no statistics
+ for r in range(metadata.num_row_groups):
+ for pos in range(1, metadata.num_columns):
+ assert metadata.row_group(r).column(pos).is_stats_set is False
+ assert metadata.row_group(r).column(pos).statistics is None
+
+ schema = get_current_schema(table_metadata)
+ statistics = data_file_statistics_from_parquet_metadata(
+ parquet_metadata=metadata,
+ stats_columns=compute_statistics_plan(schema,
table_metadata.properties),
+ parquet_column_mapping=parquet_path_to_id_mapping(schema),
+ )
+
+ datafile = DataFile(**statistics.to_serialized_dict())
+
+ # expect only "strings" column values to be reflected in the
+ # upper_bound, lower_bound and null_value_counts props of datafile
+ assert len(datafile.lower_bounds) == 1
+ assert datafile.lower_bounds[1].decode() == "aaaaaaaaaaaaaaaa"
Review Comment:
nit, if theres 1 item, i think we need to access [0], not [1]
##########
tests/io/test_pyarrow_stats.py:
##########
@@ -681,6 +685,39 @@ def test_stats_types(table_schema_nested: Schema) -> None:
]
+def test_read_missing_statistics() -> None:
+ # write statistics for only for "strings" column
+ metadata, table_metadata =
construct_test_table(write_statistics=["strings"])
+
+ # expect only "strings" column to have statistics in metadata
+ assert metadata.row_group(0).column(0).is_stats_set is True
+ assert metadata.row_group(0).column(0).statistics is not None
+
+ # expect all other columns to have no statistics
+ for r in range(metadata.num_row_groups):
+ for pos in range(1, metadata.num_columns):
+ assert metadata.row_group(r).column(pos).is_stats_set is False
+ assert metadata.row_group(r).column(pos).statistics is None
+
+ schema = get_current_schema(table_metadata)
+ statistics = data_file_statistics_from_parquet_metadata(
+ parquet_metadata=metadata,
+ stats_columns=compute_statistics_plan(schema,
table_metadata.properties),
+ parquet_column_mapping=parquet_path_to_id_mapping(schema),
+ )
+
+ datafile = DataFile(**statistics.to_serialized_dict())
+
+ # expect only "strings" column values to be reflected in the
+ # upper_bound, lower_bound and null_value_counts props of datafile
+ assert len(datafile.lower_bounds) == 1
+ assert datafile.lower_bounds[1].decode() == "aaaaaaaaaaaaaaaa"
+ assert len(datafile.upper_bounds) == 1
+ assert datafile.upper_bounds[1].decode() == "zzzzzzzzzzzzzzz{"
+ assert len(datafile.null_value_counts) == 1
+ assert datafile.null_value_counts[1] == 1
Review Comment:
nit, check for both `col_aggs` and `null_value_counts` since thats what this
PR changes
--
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
