pitrou commented on code in PR #14545:
URL: https://github.com/apache/arrow/pull/14545#discussion_r1010278228
##########
cpp/src/parquet/column_reader.cc:
##########
@@ -1141,12 +1146,14 @@ int64_t TypedColumnReaderImpl<DType>::ReadBatchSpaced(
template <typename DType>
int64_t TypedColumnReaderImpl<DType>::Skip(int64_t num_values_to_skip) {
int64_t values_to_skip = num_values_to_skip;
- while (HasNext() && values_to_skip > 0) {
+ // Optimization: Do not call HasNext() when values_to_skip == 0.
+ while (values_to_skip > 0 && HasNext()) {
// If the number of values to skip is more than the number of undecoded
values, skip
// the Page.
- if (values_to_skip > (this->num_buffered_values_ -
this->num_decoded_values_)) {
- values_to_skip -= this->num_buffered_values_ - this->num_decoded_values_;
- this->num_decoded_values_ = this->num_buffered_values_;
+ const int64_t available_values = this->available_values_current_page();
+ if (values_to_skip >= available_values) {
Review Comment:
I see, thanks.
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
