[SPARK-49204][SQL][FOLLOWUP] Fix IndexOutOfBoundsException when dealing with surrogate pairs

### What changes were proposed in this pull request?
Modified the `StringLocate` ICU codepath and added a codepoint count check for the provided offset.

### Why are the changes needed?
Currently, doing the following throws an `java.lang.IndexOutOfBoundsException`.
```sql
select position('asd' COLLATE UNICODE, 'a', 10)
```
while the correct behavior is to return an false match result (0).

### Does this PR introduce _any_ user-facing change?
Yes, fixes the `java.lang.IndexOutOfBoundsException` error.

### How was this patch tested?
New test cases in this PR.

### Was this patch authored or co-authored using generative AI tooling?
No

Closes #47871 from stevomitric/stevomitric/fix-position-out-of-bounds.

Authored-by: Stevo Mitric <stevo.mitric@databricks.com>
Signed-off-by: Max Gekk <max.gekk@gmail.com>

Author: stevomitric

common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java

@@ -671,6 +671,11 @@ public static int indexOf(final UTF8String target, final UTF8String pattern,
     // Initialize the string search with respect to the specified ICU collation.
     String targetStr = target.toValidString();
     String patternStr = pattern.toValidString();
+    // Check if `start` is out of bounds. The provided offset `start` is given in number of
+    // codepoints, so a simple `targetStr.length` check is not sufficient here. This check is
+    // needed because `String.offsetByCodePoints` throws an `IndexOutOfBoundsException`
+    // exception when the offset is out of bounds.
+    if (targetStr.codePointCount(0, targetStr.length()) <= start) return MATCH_NOT_FOUND;
     StringSearch stringSearch =
       CollationFactory.getStringSearch(targetStr, patternStr, collationId);
     stringSearch.setOverlapping(true);

common/unsafe/src/test/java/org/apache/spark/unsafe/types/CollationSupportSuite.java

@@ -2329,6 +2329,27 @@ public void testStringLocate() throws SparkException {
     assertStringLocate("b", "a🙃x🙃b", 4, "UTF8_LCASE", 5);
     assertStringLocate("b", "a🙃x🙃b", 4, "UNICODE", 5);
     assertStringLocate("b", "a🙃x🙃b", 4, "UNICODE_CI", 5);
+    // Out of bounds test cases.
+    assertStringLocate("a", "asd", 4, "UTF8_BINARY", 0);
+    assertStringLocate("a", "asd", 4, "UTF8_LCASE", 0);
+    assertStringLocate("a", "asd", 4, "UNICODE", 0);
+    assertStringLocate("a", "asd", 4, "UNICODE_CI", 0);
+    assertStringLocate("a", "asd", 100, "UTF8_BINARY", 0);
+    assertStringLocate("a", "asd", 100, "UTF8_LCASE", 0);
+    assertStringLocate("a", "asd", 100, "UNICODE", 0);
+    assertStringLocate("a", "asd", 100, "UNICODE_CI", 0);
+    assertStringLocate("a", "🙃🙃", 4, "UTF8_BINARY", 0);
+    assertStringLocate("a", "🙃🙃", 4, "UTF8_LCASE", 0);
+    assertStringLocate("a", "🙃🙃", 4, "UNICODE", 0);
+    assertStringLocate("a", "🙃🙃", 4, "UNICODE_CI", 0);
+    assertStringLocate("", "asd", 100, "UTF8_BINARY", 1);
+    assertStringLocate("", "asd", 100, "UTF8_LCASE", 1);
+    assertStringLocate("", "asd", 100, "UNICODE", 1);
+    assertStringLocate("", "asd", 100, "UNICODE_CI", 1);
+    assertStringLocate("asd", "", 100, "UTF8_BINARY", 0);
+    assertStringLocate("asd", "", 100, "UTF8_LCASE", 0);
+    assertStringLocate("asd", "", 100, "UNICODE", 0);
+    assertStringLocate("asd", "", 100, "UNICODE_CI", 0);
   }
 
   /**