You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@datafusion.apache.org by "andygrove (via GitHub)" <gi...@apache.org> on 2026/04/18 17:46:05 UTC

[PR] docs: refresh README with current features and Spark version support [datafusion-comet]

andygrove opened a new pull request, #3994:
URL: https://github.com/apache/datafusion-comet/pull/3994

   ## Which issue does this PR close?
   
   <!-- No linked issue. -->
   
   ## Rationale for this change
   
   The README has not been meaningfully updated in several releases. The benchmark images still reference 0.11.0, the benefits section predates a year of feature work, there is no mention of which Spark versions are supported, and Iceberg acceleration is buried in a single sentence. This PR refreshes the content so new readers get an accurate picture of what Comet does today.
   
   ## What changes are included in this PR?
   
   - Add a **Supported Spark Versions** section that points to the installation-guide compatibility matrix (3.4, 3.5, experimental 4.0).
   - Add a **What Comet Accelerates** features list covering Parquet scans, Iceberg, native shuffle, expressions, aggregations (including `FILTER (WHERE ...)`), joins, window functions (`LEAD`/`LAG` with `IGNORE NULLS`), and Spark metrics integration.
   - Fix heading hierarchy: *Benefits of Using Comet* is now `##` with `###` subsections, consistent with the rest of the document.
   - Expand **Getting Started** with a concrete `--conf` snippet and a link to the configuration reference.
   - Split out a **Community** section so the Slack/Discord link is discoverable.
   - Remove the hard-coded "687s → 302s, 2.2x" number so the narrative does not go stale every release; the charts remain.
   - Drop the self-referential *Acknowledgments* and *Active Community* sections.
   - Fix minor prose issues (FPGA → FPGAs, "charts shows" → "charts show").
   
   Benchmark images still point at `0.11.0/`. Refreshing them is out of scope for this PR and will be done separately when new benchmark runs are available.
   
   ## How are these changes tested?
   
   Documentation-only change; no code paths affected. Verified links manually.


-- 
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-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] docs: refresh README with current features and Spark version support [datafusion-comet]

Posted by "andygrove (via GitHub)" <gi...@apache.org>.
andygrove closed pull request #3994: docs: refresh README with current features and Spark version support
URL: https://github.com/apache/datafusion-comet/pull/3994


-- 
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-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org