Add non-TopK benchmark variants for Utf8/Utf8View string aggregates

[kosiew]

Summary

Add benchmark variants that run string-aggregate workloads with TopK disabled (representative case) in addition to the existing TopK-enabled worst-case benchmarks, so we can directly compare performance and verify correctness across Utf8 and Utf8View group keys.

Background

• The current datafusion/core/benches/topk_aggregate.rs benchmarks exercise the TopK-enabled code path for string aggregates.
• @haohuaijin suggested adding non-TopK benchmarks so we can compare the TopK and non-TopK behavior/performances and validate the TopK fix in PR Fix TopK aggregation for UTF-8/Utf8View group keys and add safe fallback for unsupported string aggregates #19285.

Why this matters

• Allows straightforward measurement of TopK's benefit (or regression) relative to the fallback path.
• Helps validate correctness (e.g., Utf8View grouping) under both code paths.
• Provides repeatable benchmarks to include in PRs and discussions.