feat: implement delete file index #435
Open
+2,667
−24
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
wgtmac
force-pushed
the
delete_file_index
branch
from
a23aa2b to
67d3b69
Compare
HuaHuaY
reviewed
Dec 24, 2025
wgtmac
force-pushed
the
delete_file_index
branch
3 times, most recently
from
6549a62 to
9345afc
Compare
wgtmac
force-pushed
the
delete_file_index
branch
from
9345afc to
0b8f579
Compare
HuaHuaY
reviewed
Dec 25, 2025
| /// \file iceberg/delete_file_index.h | ||
| /// An index of delete files by sequence number. | ||
|
|
||
| #include <algorithm> |
Contributor
There was a problem hiding this comment.
Suggested change
| #include <algorithm> |
|
|
||
| std::vector<std::shared_ptr<DataFile>> PositionDeletes::ReferencedDeleteFiles() { | ||
| IndexIfNeeded(); | ||
| return std::ranges::transform_view(files_, |
Comment on lines
+202
to
+204
| std::ranges::sort(files_, [](const auto& a, const auto& b) { | ||
| return a.sequence_number.value() < b.sequence_number.value(); | ||
| }); |
Contributor
There was a problem hiding this comment.
Suggested change
| std::ranges::sort(files_, [](const auto& a, const auto& b) { | |
| return a.sequence_number.value() < b.sequence_number.value(); | |
| }); | |
| std::ranges::sort(files_, std::ranges::less{}, &ManifestEntry::sequence_number); |
| }); | ||
|
|
||
| // Build sequence number array for binary search | ||
| seqs_ = std::ranges::transform_view( |
Comment on lines
+179
to
+186
| size_t start = FindStartIndex(seqs_, seq); | ||
| if (start >= files_.size()) { | ||
| return {}; | ||
| } | ||
|
|
||
| return files_ | std::views::drop(start) | | ||
| std::views::transform(&ManifestEntry::data_file) | | ||
| std::ranges::to<std::vector<std::shared_ptr<DataFile>>>(); |
Contributor
There was a problem hiding this comment.
Suggested change
| size_t start = FindStartIndex(seqs_, seq); | |
| if (start >= files_.size()) { | |
| return {}; | |
| } | |
| return files_ | std::views::drop(start) | | |
| std::views::transform(&ManifestEntry::data_file) | | |
| std::ranges::to<std::vector<std::shared_ptr<DataFile>>>(); | |
| auto iter = std::ranges::lower_bound(seqs_, seq); | |
| if (iter == seqs_.end()) { | |
| return {}; | |
| } | |
| return files_ | std::views::drop(iter - seqs_.begin()) | | |
| std::views::transform(&ManifestEntry::data_file) | | |
| std::ranges::to<std::vector<std::shared_ptr<DataFile>>>(); |
I think adding FindStartIndex is not needed.
Comment on lines
+229
to
+243
| size_t start = FindStartIndex(seqs_, seq); | ||
| if (start >= files_.size()) { | ||
| return {}; | ||
| } | ||
|
|
||
| std::vector<std::shared_ptr<DataFile>> result; | ||
| result.reserve(files_.size() - start); | ||
| for (size_t i = start; i < files_.size(); ++i) { | ||
| const auto& delete_file = files_[i]; | ||
| ICEBERG_ASSIGN_OR_RAISE(bool may_contain, | ||
| CanContainEqDeletesForFile(data_file, delete_file)); | ||
| if (may_contain) { | ||
| result.push_back(delete_file.wrapped.data_file); | ||
| } | ||
| } |
Contributor
There was a problem hiding this comment.
Suggested change
| size_t start = FindStartIndex(seqs_, seq); | |
| if (start >= files_.size()) { | |
| return {}; | |
| } | |
| std::vector<std::shared_ptr<DataFile>> result; | |
| result.reserve(files_.size() - start); | |
| for (size_t i = start; i < files_.size(); ++i) { | |
| const auto& delete_file = files_[i]; | |
| ICEBERG_ASSIGN_OR_RAISE(bool may_contain, | |
| CanContainEqDeletesForFile(data_file, delete_file)); | |
| if (may_contain) { | |
| result.push_back(delete_file.wrapped.data_file); | |
| } | |
| } | |
| auto iter = std::ranges::lower_bound(seqs_, seq); | |
| if (iter == seqs_.end()) { | |
| return {}; | |
| } | |
| std::vector<std::shared_ptr<DataFile>> result; | |
| result.reserve(seqs_.end() - iter); | |
| for (auto& delete_file : files_ | std::views::drop(iter - seqs_.begin())) { | |
| ICEBERG_ASSIGN_OR_RAISE(bool may_contain, | |
| CanContainEqDeletesForFile(data_file, delete_file)); | |
| if (may_contain) { | |
| result.push_back(delete_file.wrapped.data_file); | |
| } | |
| } |
|
|
||
| std::vector<std::shared_ptr<DataFile>> EqualityDeletes::ReferencedDeleteFiles() { | ||
| IndexIfNeeded(); | ||
| return std::ranges::transform_view( |
| } | ||
|
|
||
| // Sort by apply sequence number | ||
| std::ranges::sort(files_, [](const auto& a, const auto& b) { |
| }); | ||
|
|
||
| // Build sequence number array for binary search | ||
| seqs_ = std::ranges::transform_view( |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implemented the DeleteFileIndex and Builder to manage and efficiently filter
delete files (equality deletes, position deletes, and deletion vectors)
based on sequence numbers and partitions.
Key changes:
DeleteFileIndexandDeleteFileIndex::Builderinsrc/iceberg/delete_file_index.{h,cc}.ContentFileUtilfor helper functions related to content files and DVs.ManifestReaderto support dropping stats viaTryDropStats().src/iceberg/test/delete_file_index_test.cc.