wgtmac commented on code in PR #34193:
URL: https://github.com/apache/arrow/pull/34193#discussion_r1109387229
##########
cpp/src/parquet/column_writer.cc:
##########
@@ -1014,11 +1014,33 @@ template <typename Action>
inline void DoInBatches(int64_t total, int64_t batch_size, Action&& action) {
int64_t num_batches = static_cast<int>(total / batch_size);
for (int round = 0; round < num_batches; round++) {
- action(round * batch_size, batch_size);
+ action(round * batch_size, batch_size, /*check_page=*/true);
}
// Write the remaining values
if (total % batch_size > 0) {
- action(num_batches * batch_size, total % batch_size);
+ action(num_batches * batch_size, total % batch_size, /*check_page=*/true);
+ }
+}
+
+template <typename Action>
+inline void DoInBatches(const int16_t* def_levels, const int16_t* rep_levels,
+ int64_t num_levels, int64_t batch_size, Action&&
action,
+ bool pages_change_on_record_boundaries) {
+ if (!pages_change_on_record_boundaries || !rep_levels) {
+ // If rep_levels is null, then we are writing a non-repeated column.
+ // In this case, every record contains only one level.
+ return DoInBatches(num_levels, batch_size, std::forward<Action>(action));
+ }
+
+ int64_t offset = 0;
+ while (offset < num_levels) {
+ int64_t end_offset = std::min(offset + batch_size, num_levels);
+ // Find next record boundary (i.e. ref_level = 0)
+ while (end_offset < num_levels && rep_levels[end_offset] != 0) {
+ end_offset++;
+ }
+ action(offset, end_offset - offset, /*check_page=*/end_offset <
num_levels);
Review Comment:
The caveat is that if `num_levels` is less than `batch_size`, we cannot
check page size because the loop in line 1039 does not work any more. I will
fix it shortly.
--
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]
