mapleFU commented on code in PR #34193:
URL: https://github.com/apache/arrow/pull/34193#discussion_r1114061205
##########
cpp/src/parquet/column_writer.cc:
##########
@@ -1015,11 +1015,59 @@ 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_size=*/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_size=*/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++;
+ }
+
+ if (end_offset < num_levels) {
+ // This is not the last chunk of batch and end_offset is a record
boundary.
+ // It is a good chance to check the page size.
+ action(offset, end_offset - offset, /*check_page_size=*/true);
+ } else {
+ DCHECK_EQ(end_offset, num_levels);
+ // This is the last chunk of batch, and we do not know whether
end_offset is a
+ // record boundary. Find the offset to beginning of last record in this
chunk,
+ // so we can check page size.
+ int64_t last_record_begin_offset = num_levels - 1;
+ while (last_record_begin_offset >= offset &&
+ rep_levels[last_record_begin_offset] != 0) {
+ last_record_begin_offset--;
+ }
+
+ if (offset < last_record_begin_offset) {
+ // We have found the beginning of last record and can check page size.
+ action(offset, last_record_begin_offset - offset,
/*check_page_size=*/true);
+ offset = last_record_begin_offset;
+ }
+
+ // There is no record boundary in this chunk and cannot check page size.
+ action(offset, end_offset - offset, /*check_page_size=*/false);
Review Comment:
Oh, I got understand. The final batch would have: `[offset, end_offset)`
This patch will split it into two action:
```
1. flush [offset, begining-of-last-record) with check flush page
2. flush [begining-of-last-record, end-offset) force not flush page
```
--
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
