Record filtering in the filter2 API could possibly short circuit
- Dominant language
- Java
- Stars
- 3.1k
- Forks
- 1.6k
- Avg merge
- 3d 12h
- Merged PRs (30d)
- 33
Description
Record level filtering in the filter2 api still requires visiting every value of the record. We may be able to short circuit as soon as the filter predicate reaches a known state.
Another approach would be to figure out how to get essentially random access to the values referenced by the predicate and check them first. This could be tricky because it would require re-structuring the assembly algorithm.
**Reporter**: [Alex Levenson](https://issues.apache.org/jira/secure/ViewProfile.jspa?name=alexlevenson) / @isnotinvain
**Note**: *This issue was originally created as [PARQUET-37](https://issues.apache.org/jira/browse/PARQUET-37). Please see the [migration documentation](https://issues.apache.org/jira/browse/PARQUET-2502) for further details.*
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by tracing the filter2 API's record-level filtering and the assembly algorithm, since the issue names no files or tests. Determine whether predicate evaluation can stop once its state is known, or whether predicate-referenced values need earlier access; done means preserving filtering behavior while avoiding unnecessary value visits.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java
- Domain
- data-engineering, performance
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100