perf(substr_index): speed up scalar and Utf8View (#21754)

## Which issue does this PR close?

<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->

- Part of #20585.

## Rationale for this change

`substr_index` is part of the Utf8View epic. This function was still
missing the Utf8View optimization path, and it also did extra work when
delimiter and count were constant scalars.

This PR adds the same kind of optimization used in similar string work
and includes benchmark coverage.

<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->

## What changes are included in this PR?

  - Return the input string type directly, including `Utf8View`.
  - Add a zero-copy `Utf8View` path for `substr_index`.
  - Add a scalar fast path when delimiter and count are constant.
- Keep the hot path specialized after checking a cleaner shared-helper
version and benchmarking it.
  - Add SQL coverage for `Utf8View` type and value results.
- Add unit tests for the scalar fast path, sliced `Utf8View` arrays, and
the unchanged original-view case.
- Extend the benchmark to cover `Utf8`, `Utf8View`, array arguments,
scalar delimiter/count, and positive and negative counts.

<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->

## Are these changes tested?

Yes

<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->

## Are there any user-facing changes?

No

<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

Author: kumarUjjawal

datafusion/functions/benches/substr_index.rs

@@ -18,15 +18,20 @@
 use std::hint::black_box;
 use std::sync::Arc;
 
-use arrow::array::{ArrayRef, Int64Array, StringArray};
+use arrow::array::{ArrayRef, Int64Array, StringArray, StringViewArray};
 use arrow::datatypes::{DataType, Field};
 use criterion::{Criterion, criterion_group, criterion_main};
-use datafusion_common::config::ConfigOptions;
+use datafusion_common::{ScalarValue, config::ConfigOptions};
 use datafusion_expr::{ColumnarValue, ScalarFunctionArgs};
 use datafusion_functions::unicode::substr_index;
 use rand::Rng;
+use rand::SeedableRng;
 use rand::distr::{Alphanumeric, Uniform};
 use rand::prelude::Distribution;
+use rand::rngs::StdRng;
+
+const ARRAY_DATA_SEED: u64 = 0x5EED_AAAA;
+const SCALAR_DATA_SEED: u64 = 0x5EED_BBBB;
 
 struct Filter<Dist, Test> {
     dist: Dist,
@@ -48,28 +53,72 @@ where
     }
 }
 
-fn data(
+#[derive(Clone, Copy)]
+enum StringRep {
+    Utf8,
+    Utf8View,
+}
+
+impl StringRep {
+    fn name(self) -> &'static str {
+        match self {
+            Self::Utf8 => "utf8",
+            Self::Utf8View => "utf8view",
+        }
+    }
+
+    fn data_type(self) -> DataType {
+        match self {
+            Self::Utf8 => DataType::Utf8,
+            Self::Utf8View => DataType::Utf8View,
+        }
+    }
+
+    fn array(self, values: &[String]) -> ArrayRef {
+        match self {
+            Self::Utf8 => Arc::new(StringArray::from(values.to_vec())) as ArrayRef,
+            Self::Utf8View => Arc::new(
+                values
+                    .iter()
+                    .map(|value| Some(value.as_str()))
+                    .collect::<StringViewArray>(),
+            ) as ArrayRef,
+        }
+    }
+
+    fn scalar(self, value: &str) -> ScalarValue {
+        match self {
+            Self::Utf8 => ScalarValue::Utf8(Some(value.to_string())),
+            Self::Utf8View => ScalarValue::Utf8View(Some(value.to_string())),
+        }
+    }
+}
+
+fn random_token<R: Rng + ?Sized>(rng: &mut R, len: usize) -> String {
+    rng.sample_iter(&Alphanumeric)
+        .take(len)
+        .map(char::from)
+        .collect()
+}
+
+fn array_data(
     batch_size: usize,
     single_char_delimiter: bool,
-) -> (StringArray, StringArray, Int64Array) {
-    let dist = Filter {
-        dist: Uniform::new(-4, 5),
+) -> (Vec<String>, Vec<String>, Vec<i64>) {
+    let count_dist = Filter {
+        dist: Uniform::new(-4, 5).expect("valid count distribution"),
         test: |x: &i64| x != &0,
     };
-    let mut rng = rand::rng();
-    let mut strings: Vec<String> = vec![];
-    let mut delimiters: Vec<String> = vec![];
-    let mut counts: Vec<i64> = vec![];
+    let mut rng = StdRng::seed_from_u64(ARRAY_DATA_SEED);
+    let mut strings = Vec::with_capacity(batch_size);
+    let mut delimiters = Vec::with_capacity(batch_size);
+    let mut counts = Vec::with_capacity(batch_size);
 
     for _ in 0..batch_size {
         let length = rng.random_range(20..50);
-        let base: String = (&mut rng)
-            .sample_iter(&Alphanumeric)
-            .take(length)
-            .map(char::from)
-            .collect();
+        let base = random_token(&mut rng, length);
 
-        let (string_value, delimiter): (String, String) = if single_char_delimiter {
+        let (string_value, delimiter) = if single_char_delimiter {
             let char_idx = rng.random_range(0..base.chars().count());
             let delimiter = base.chars().nth(char_idx).unwrap().to_string();
             (base, delimiter)
@@ -80,7 +129,6 @@ fn data(
 
             let delimiter_count = rng.random_range(1..4);
             let mut result = String::new();
-
             for i in 0..delimiter_count {
                 result.push_str(&base);
                 if i < delimiter_count - 1 {
@@ -90,32 +138,37 @@ fn data(
             (result, delimiter)
         };
 
-        let count = rng.sample(dist.dist.unwrap());
-
         strings.push(string_value);
         delimiters.push(delimiter);
-        counts.push(count);
+        counts.push(count_dist.sample(&mut rng));
+    }
+
+    (strings, delimiters, counts)
+}
+
+fn scalar_data(batch_size: usize, delimiter: &str) -> Vec<String> {
+    let mut rng = StdRng::seed_from_u64(SCALAR_DATA_SEED);
+    let mut strings = Vec::with_capacity(batch_size);
+
+    for _ in 0..batch_size {
+        let left_len = rng.random_range(12..24);
+        let middle_len = rng.random_range(12..24);
+        let right_len = rng.random_range(12..24);
+        let left = random_token(&mut rng, left_len);
+        let middle = random_token(&mut rng, middle_len);
+        let right = random_token(&mut rng, right_len);
+        strings.push(format!("{left}{delimiter}{middle}{delimiter}{right}"));
     }
 
-    (
-        StringArray::from(strings),
-        StringArray::from(delimiters),
-        Int64Array::from(counts),
-    )
+    strings
 }
 
 fn run_benchmark(
     b: &mut criterion::Bencher,
-    strings: StringArray,
-    delimiters: StringArray,
-    counts: Int64Array,
-    batch_size: usize,
+    args: &[ColumnarValue],
+    return_type: &DataType,
+    number_rows: usize,
 ) {
-    let strings = ColumnarValue::Array(Arc::new(strings) as ArrayRef);
-    let delimiters = ColumnarValue::Array(Arc::new(delimiters) as ArrayRef);
-    let counts = ColumnarValue::Array(Arc::new(counts) as ArrayRef);
-
-    let args = vec![strings, delimiters, counts];
     let arg_fields = args
         .iter()
         .enumerate()
@@ -129,10 +182,10 @@ fn run_benchmark(
         black_box(
             substr_index()
                 .invoke_with_args(ScalarFunctionArgs {
-                    args: args.clone(),
+                    args: args.to_vec(),
                     arg_fields: arg_fields.clone(),
-                    number_rows: batch_size,
-                    return_field: Field::new("f", DataType::Utf8, true).into(),
+                    number_rows,
+                    return_field: Field::new("f", return_type.clone(), true).into(),
                     config_options: Arc::clone(&config_options),
                 })
                 .expect("substr_index should work on valid values"),
@@ -142,22 +195,62 @@ fn run_benchmark(
 
 fn criterion_benchmark(c: &mut Criterion) {
     let mut group = c.benchmark_group("substr_index");
-
     let batch_sizes = [100, 1000, 10_000];
 
     for batch_size in batch_sizes {
-        group.bench_function(
-            format!("substr_index_{batch_size}_single_delimiter"),
-            |b| {
-                let (strings, delimiters, counts) = data(batch_size, true);
-                run_benchmark(b, strings, delimiters, counts, batch_size);
-            },
-        );
-
-        group.bench_function(format!("substr_index_{batch_size}_long_delimiter"), |b| {
-            let (strings, delimiters, counts) = data(batch_size, false);
-            run_benchmark(b, strings, delimiters, counts, batch_size);
-        });
+        for rep in [StringRep::Utf8, StringRep::Utf8View] {
+            let rep_name = rep.name();
+
+            group.bench_function(
+                format!("substr_index_{rep_name}_{batch_size}_array_single_delimiter"),
+                |b| {
+                    let (strings, delimiters, counts) = array_data(batch_size, true);
+                    let args = vec![
+                        ColumnarValue::Array(rep.array(&strings)),
+                        ColumnarValue::Array(rep.array(&delimiters)),
+                        ColumnarValue::Array(
+                            Arc::new(Int64Array::from(counts)) as ArrayRef
+                        ),
+                    ];
+                    run_benchmark(b, &args, &rep.data_type(), batch_size);
+                },
+            );
+
+            group.bench_function(
+                format!("substr_index_{rep_name}_{batch_size}_array_long_delimiter"),
+                |b| {
+                    let (strings, delimiters, counts) = array_data(batch_size, false);
+                    let args = vec![
+                        ColumnarValue::Array(rep.array(&strings)),
+                        ColumnarValue::Array(rep.array(&delimiters)),
+                        ColumnarValue::Array(
+                            Arc::new(Int64Array::from(counts)) as ArrayRef
+                        ),
+                    ];
+                    run_benchmark(b, &args, &rep.data_type(), batch_size);
+                },
+            );
+
+            for (name, delimiter, count) in [
+                ("single_delimiter_pos", ".", 1_i64),
+                ("single_delimiter_neg", ".", -1_i64),
+                ("long_delimiter_pos", "|||", 1_i64),
+                ("long_delimiter_neg", "|||", -1_i64),
+            ] {
+                group.bench_function(
+                    format!("substr_index_{rep_name}_{batch_size}_scalar_{name}"),
+                    |b| {
+                        let strings = scalar_data(batch_size, delimiter);
+                        let args = vec![
+                            ColumnarValue::Array(rep.array(&strings)),
+                            ColumnarValue::Scalar(rep.scalar(delimiter)),
+                            ColumnarValue::Scalar(ScalarValue::Int64(Some(count))),
+                        ];
+                        run_benchmark(b, &args, &rep.data_type(), batch_size);
+                    },
+                );
+            }
+        }
     }
 
     group.finish();