Dandandan opened a new pull request, #21370: URL: https://github.com/apache/datafusion/pull/21370
## Which issue does this PR close? N/A ## Rationale for this change The `ParquetPushDecoder` may request adjacent byte ranges (e.g. `4-534` and `534-1064`) that can be merged into a single range (`4-1064`), reducing the number of object store I/O operations. ## What changes are included in this PR? - Added `coalesce_ranges()` function that merges adjacent/overlapping byte ranges in-place - Applied coalescing to the `NeedsData` branch of the `PushDecoderStreamState` transition loop in `opener.rs` - Updated test expectations to reflect the reduced number of range requests ## Are these changes tested? Yes, existing tests in `object_store_access.rs` verify the coalesced ranges. ## Are there any user-facing changes? No API changes. Users may see improved I/O performance when reading Parquet files due to fewer object store requests. 🤖 Generated with [Claude Code](https://claude.com/claude-code) -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
