perf: optimize regexp_instr in datafusion-functions

[andygrove]

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

Removed per-batch default-array/Vec allocations, memoized the compiled regex across rows to skip HashMap hashing for literal patterns, and skipped the O(n) chars() scan on the default start=1 path.

What changes are included in this PR?

Removed per-batch default-array/Vec allocations, memoized the compiled regex across rows to skip HashMap hashing for literal patterns, and skipped the O(n) chars() scan on the default start=1 path.

Are these changes tested?

Correctness: unit tests + seeded differential fuzz (bit-identical Arrow output vs main).

Benchmark (criterion):

• regexp_instr_with_start [size=1024, str_len=32]: 40.073% faster (base 41127ns -> cand 24646ns)
• regexp_instr_with_start [size=1024, str_len=128]: 44.498% faster (base 48215ns -> cand 26760ns)
• regexp_instr_no_start [size=1024, str_len=128]: 47.253% faster (base 49244ns -> cand 25974ns)
• regexp_instr_no_start [size=1024, str_len=32]: 42.18% faster (base 40495ns -> cand 23414ns)

Full criterion output:

regexp_instr_no_start [size=1024, str_len=32]
                        time:   [23.389 µs 23.479 µs 23.645 µs]
                        change: [−42.300% −42.180% −42.004%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
  7 (7.00%) low mild
  2 (2.00%) high severe

regexp_instr_with_start [size=1024, str_len=32]
                        time:   [24.617 µs 24.635 µs 24.659 µs]
                        change: [−40.118% −40.073% −40.026%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high severe

regexp_instr_no_start [size=1024, str_len=128]
                        time:   [25.756 µs 25.791 µs 25.830 µs]
                        change: [−47.394% −47.253% −47.076%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high severe

regexp_instr_with_start [size=1024, str_len=128]
                        time:   [26.645 µs 26.666 µs 26.693 µs]
                        change: [−44.577% −44.498% −44.417%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild

Are there any user-facing changes?