Skip to content

Fix chunks scanner #7913

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ivanmorozov333 merged 3 commits into from
Aug 16, 2024
Merged

Fix chunks scanner #7913

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4210d22
fix chunks scanner for empty subchunks in chunked array
ivanmorozov333 Aug 16, 2024
e426977
fixes
ivanmorozov333 Aug 16, 2024
4cf05b4
fix build
ivanmorozov333 Aug 16, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 16 additions & 9 deletions ydb/core/formats/arrow/arrow_helpers.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -940,16 +940,23 @@ std::vector<std::shared_ptr<arrow::RecordBatch>> SliceToRecordBatches(const std:
for (auto&& i : t->columns()) {
ui32 currentPosition = 0;
auto it = i->chunks().begin();
ui32 length = (*it)->length();
ui32 length = 0;
const auto initializeIt = [&length, &it, &i]() {
for (; it != i->chunks().end() && !(*it)->length(); ++it) {
}
if (it != i->chunks().end()) {
length = (*it)->length();
}
};
initializeIt();
for (ui32 idx = 0; idx + 1 < positions.size(); ++idx) {
AFL_VERIFY(it != i->chunks().end());
AFL_VERIFY(positions[idx + 1] - currentPosition <= length)("length", length)("idx+1", positions[idx + 1])("pos", currentPosition);
auto chunk = (*it)->Slice(positions[idx] - currentPosition, positions[idx + 1] - positions[idx]);
AFL_VERIFY_DEBUG(chunk->length() == positions[idx + 1] - positions[idx])("length", chunk->length())(
"delta", positions[idx + 1] - positions[idx]);
AFL_VERIFY_DEBUG(chunk->length())("delta", positions[idx + 1] - positions[idx]);
AFL_VERIFY_DEBUG(chunk->length() == positions[idx + 1] - positions[idx])("length", chunk->length())("expect", positions[idx + 1] - positions[idx]);
if (positions[idx + 1] - currentPosition == length) {
if (++it != i->chunks().end()) {
length = (*it)->length();
}
++it;
initializeIt();
currentPosition = positions[idx + 1];
}
slicedData[idx].emplace_back(chunk);
Expand All @@ -958,8 +965,8 @@ std::vector<std::shared_ptr<arrow::RecordBatch>> SliceToRecordBatches(const std:
std::vector<std::shared_ptr<arrow::RecordBatch>> result;
ui32 count = 0;
for (auto&& i : slicedData) {
AFL_VERIFY_DEBUG(i.size());
AFL_VERIFY_DEBUG(i.front()->length());
AFL_VERIFY(i.size());
AFL_VERIFY(i.front()->length());
result.emplace_back(arrow::RecordBatch::Make(t->schema(), i.front()->length(), i));
count += result.back()->num_rows();
}
Expand Down