alamb commented on code in PR #10924:
URL: https://github.com/apache/datafusion/pull/10924#discussion_r1640395042
##########
datafusion/core/src/datasource/file_format/parquet.rs:
##########
@@ -295,86 +297,6 @@ impl FileFormat for ParquetFormat {
}
}
-fn summarize_min_max(
- max_values: &mut [Option<MaxAccumulator>],
- min_values: &mut [Option<MinAccumulator>],
- fields: &Fields,
- i: usize,
- stat: &ParquetStatistics,
-) {
- if !stat.has_min_max_set() {
- max_values[i] = None;
- min_values[i] = None;
- return;
- }
- match stat {
- ParquetStatistics::Boolean(s) if DataType::Boolean ==
*fields[i].data_type() => {
- if let Some(max_value) = &mut max_values[i] {
- max_value
-
.update_batch(&[Arc::new(BooleanArray::from(vec![*s.max()]))])
- .unwrap_or_else(|_| max_values[i] = None);
- }
- if let Some(min_value) = &mut min_values[i] {
- min_value
-
.update_batch(&[Arc::new(BooleanArray::from(vec![*s.min()]))])
- .unwrap_or_else(|_| min_values[i] = None);
- }
- }
- ParquetStatistics::Int32(s) if DataType::Int32 ==
*fields[i].data_type() => {
- if let Some(max_value) = &mut max_values[i] {
- max_value
- .update_batch(&[Arc::new(Int32Array::from_value(*s.max(),
1))])
- .unwrap_or_else(|_| max_values[i] = None);
- }
- if let Some(min_value) = &mut min_values[i] {
- min_value
- .update_batch(&[Arc::new(Int32Array::from_value(*s.min(),
1))])
- .unwrap_or_else(|_| min_values[i] = None);
- }
- }
- ParquetStatistics::Int64(s) if DataType::Int64 ==
*fields[i].data_type() => {
- if let Some(max_value) = &mut max_values[i] {
- max_value
- .update_batch(&[Arc::new(Int64Array::from_value(*s.max(),
1))])
Review Comment:
Previously, even though update_batch is called, it first creates a single
row array
--
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]
