tustvold commented on code in PR #2022:
URL: https://github.com/apache/arrow-rs/pull/2022#discussion_r916866463
##########
parquet/src/column/writer.rs:
##########
@@ -302,61 +308,52 @@ impl<'a, T: DataType> ColumnWriterImpl<'a, T> {
// Find out the minimal length to prevent index out of bound errors.
let mut min_len = values.len();
if let Some(levels) = def_levels {
- min_len = cmp::min(min_len, levels.len());
+ min_len = min_len.min(levels.len());
}
if let Some(levels) = rep_levels {
- min_len = cmp::min(min_len, levels.len());
+ min_len = min_len.min(levels.len());
}
// Find out number of batches to process.
let write_batch_size = self.props.write_batch_size();
let num_batches = min_len / write_batch_size;
- // Process pre-calculated statistics
- match (min, max) {
- (Some(min), Some(max)) => {
- if self
- .min_column_value
- .as_ref()
- .map_or(true, |v| self.compare_greater(v, min))
- {
- self.min_column_value = Some(min.clone());
+ if self.statistics_enabled == EnabledStatistics::Chunk {
Review Comment:
I'll add a comment explaining why we only care if it is exactly this
variant, any other variants would need to be computed at a different level
--
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]
