perf: Optimize contains expression with SIMD-based scalar pattern sea…

[Shekharrajak]

Which issue does this PR close?

Closes #2972.

Rationale for this change

The contains expression shows poor performance in Comet (0.2X vs Spark) because DataFusion's make_scalar_function wrapper expands scalar patterns to arrays, bypassing arrow-rs's optimized scalar path.

What changes are included in this PR?

• Add SparkContains UDF with optimized scalar pattern handling using memchr::memmem::Finder for SIMD-accelerated substring search
• Register the function in comet_scalar_funcs.rs to override DataFusion's built-in contains
• Add contains to CometStringExpressionBenchmark
• Enhance contains test in CometExpressionSuite

How are these changes tested?

• 4 new unit tests in contains.rs (array-scalar, scalar-scalar, null handling, empty pattern)
• Enhanced integration test in CometExpressionSuite.scala
• All 122 spark-expr tests pass

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 59.58%. Comparing base (f09f8af) to head (54dc054).
⚠️ Report is 803 commits behind head on main.

Additional details and impacted files

@@             Coverage Diff              @@
##               main    #2991      +/-   ##
============================================
+ Coverage     56.12%   59.58%   +3.46%     
- Complexity      976     1377     +401     
============================================
  Files           119      167      +48     
  Lines         11743    15493    +3750     
  Branches       2251     2569     +318     
============================================
+ Hits           6591     9232    +2641     
- Misses         4012     4962     +950     
- Partials       1140     1299     +159     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[andygrove]

I tested locally and see good performance now:

OpenJDK 64-Bit Server VM 17.0.17+10-Ubuntu-122.04 on Linux 6.8.0-90-generic
AMD Ryzen 9 7950X3D 16-Core Processor
contains:                                 Best Time(ms)   Avg Time(ms)   Stdev(ms)    Rate(M/s)   Per Row(ns)   Relative
------------------------------------------------------------------------------------------------------------------------
Spark                                              1864           1870           9          0.6        1777.7       1.0X
Comet (Scan)                                       1986           1992           9          0.5        1894.1       0.9X
Comet (Scan + Exec)                                1328           1330           4          0.8        1266.1       1.4X

[andygrove]

We already depend on arrow. Is contains not re-exported in the arrow crate?

[Shekharrajak]

thanks - removed it a449297

[andygrove]

Thanks @Shekharrajak this is a really nice speedup! Could you fix the clippy errors (you can probably just run cargo clippy --fix).