perf: improve performance of string repeat (#19502)

## 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.
-->

N/A

## Rationale for this change

<!--
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.
-->

Use a re-usable string buffer instead of allocating a new string for
each input value.

| Benchmark            | Main (µs) | Optimized (µs) | Improvement     |
|----------------------|-----------|----------------|-----------------|
| size=1024, repeat=3  |           |                |                 |
| repeat_string_view   | 76.51     | 70.14          | -8.3%           |
| repeat_string        | 78.63     | 71.41          | -9.2%           |
| repeat_large_string  | 76.40     | 71.08          | -7.0%           |
| size=1024, repeat=30 |           |                |                 |
| repeat_string_view   | 109.02    | 93.51          | -14.2%          |
| repeat_string        | 108.46    | 92.12          | -15.1%          |
| repeat_large_string  | 105.99    | 91.66          | -13.5%          |
| size=4096, repeat=3  |           |                |                 |
| repeat_string_view   | 139.44    | 113.95         | -18.3%          |
| repeat_string        | 133.62    | 112.25         | -16.0%          |
| repeat_large_string  | 131.94    | 108.41         | -17.8%          |
| size=4096, repeat=30 |           |                |                 |
| repeat_string_view   | 251.77    | 193.95         | -23.0%          |
| repeat_string        | 250.58    | 191.86         | -23.4%          |
| repeat_large_string  | 248.88    | 188.43         | -24.3%          |
| overflow tests       |           |                |                 |
| size=1024            | 58.14     | 58.02          | ~0% (no change) |
| size=4096            | 58.26     | 58.08          | ~0% (no change) |


## What changes are included in this PR?

<!--
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?

<!--
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?

<!--
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: andygrove

datafusion/functions/src/string/repeat.rs

@@ -153,6 +153,7 @@ where
     S: StringArrayType<'a>,
 {
     let mut total_capacity = 0;
+    let mut max_item_capacity = 0;
     string_array.iter().zip(number_array.iter()).try_for_each(
         |(string, number)| -> Result<(), DataFusionError> {
             match (string, number) {
@@ -166,6 +167,7 @@ where
                         );
                     }
                     total_capacity += item_capacity;
+                    max_item_capacity = max_item_capacity.max(item_capacity);
                 }
                 _ => (),
             }
@@ -176,18 +178,37 @@ where
     let mut builder =
         GenericStringBuilder::<T>::with_capacity(string_array.len(), total_capacity);
 
-    string_array.iter().zip(number_array.iter()).try_for_each(
-        |(string, number)| -> Result<(), DataFusionError> {
+    // Reusable buffer to avoid allocations in string.repeat()
+    let mut buffer = Vec::<u8>::with_capacity(max_item_capacity);
+
+    string_array
+        .iter()
+        .zip(number_array.iter())
+        .for_each(|(string, number)| {
             match (string, number) {
                 (Some(string), Some(number)) if number >= 0 => {
-                    builder.append_value(string.repeat(number as usize));
+                    buffer.clear();
+                    let count = number as usize;
+                    if count > 0 && !string.is_empty() {
+                        let src = string.as_bytes();
+                        // Initial copy
+                        buffer.extend_from_slice(src);
+                        // Doubling strategy: copy what we have so far until we reach the target
+                        while buffer.len() < src.len() * count {
+                            let copy_len =
+                                buffer.len().min(src.len() * count - buffer.len());
+                            // SAFETY: we're copying valid UTF-8 bytes that we already verified
+                            buffer.extend_from_within(..copy_len);
+                        }
+                    }
+                    // SAFETY: buffer contains valid UTF-8 since we only ever copy from a valid &str
+                    builder
+                        .append_value(unsafe { std::str::from_utf8_unchecked(&buffer) });
                 }
                 (Some(_), Some(_)) => builder.append_value(""),
                 _ => builder.append_null(),
             }
-            Ok(())
-        },
-    )?;
+        });
     let array = builder.finish();
 
     Ok(Arc::new(array) as ArrayRef)