andygrove opened a new pull request, #4927:
URL: https://github.com/apache/datafusion-comet/pull/4927
> This PR was created by an LLM as a draft PR. I will mark it as ready for
review after human review.
## Which issue does this PR close?
N/A — autonomous exploratory PR.
## Rationale for this change
Build to_json rows directly in the StringBuilder with pre-rendered field
prefixes, a right-sized buffer, and a single vectorizable column-wide escape
scan replacing the per-value byte scan.
## What changes are included in this PR?
Build to_json rows directly in the StringBuilder with pre-rendered field
prefixes, a right-sized buffer, and a single vectorizable column-wide escape
scan replacing the per-value byte scan.
## How are these changes tested?
Correctness: unit tests + seeded differential fuzz (bit-identical Arrow
output vs `main`).
Benchmark (criterion):
- to_json: 9.92% faster (base 353519ns -> cand 318450ns)
Full criterion output:
```text
to_json time: [316.38 µs 316.78 µs 317.25 µs]
change: [−10.245% −9.9200% −9.6049%] (p = 0.00 <
0.05)
Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
1 (1.00%) low mild
6 (6.00%) high mild
```
--
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]
