8281315: Unicode, (?i) flag and backreference throwing IndexOutOfBounds Exception

src/java.base/share/classes/java/util/regex/Pattern.java

@@ -5060,22 +5060,28 @@ boolean match(Matcher matcher, int i, CharSequence seq) {
             int j = matcher.groups[groupIndex];
             int k = matcher.groups[groupIndex+1];
 
-            int groupSize = k - j;
+            int groupSizeChars = k - j; //Group size in chars
 
             // If the referenced group didn't match, neither can this
             if (j < 0)
                 return false;
 
             // If there isn't enough input left no match
-            if (i + groupSize > matcher.to) {
+            if (i + groupSizeChars > matcher.to) {
                 matcher.hitEnd = true;
                 return false;
             }
 
             // Check each new char to make sure it matches what the group
             // referenced matched last time around
             int x = i;
-            for (int index=0; index<groupSize; index++) {
+
+            // We set groupCodepoints to the number of chars
+            // in the given subsequence but this is an upper bound estimate
+            // we reduce by one if we spot 2-char codepoints.
+            int groupCodepoints = groupSizeChars;
+
+            for (int index=0; index<groupCodepoints; index++) {
                 int c1 = Character.codePointAt(seq, x);
                 int c2 = Character.codePointAt(seq, j);
                 if (c1 != c2) {
@@ -5093,9 +5099,15 @@ boolean match(Matcher matcher, int i, CharSequence seq) {
                 }
                 x += Character.charCount(c1);
                 j += Character.charCount(c2);
+
+                if(c1 >= Character.MIN_SUPPLEMENTARY_CODE_POINT) {
+                    //Group size is guessed in terms of chars, but we need to
+                    //adjust if we spot a 2-char codePoint.
+                    groupCodepoints--;
+                }
             }
 
-            return next.match(matcher, i+groupSize, seq);
+            return next.match(matcher, i+groupSizeChars, seq);
         }
         boolean study(TreeInfo info) {
             info.maxValid = false;

test/jdk/java/util/regex/RegExTest.java

@@ -4556,4 +4556,13 @@ public static void badIntersectionSyntax() {
                 Pattern.compile(pattern));
         assertTrue(e.getMessage().contains("Bad intersection syntax"));
     }
+
+    //This test is for 8281315
+    @Test
+    public static void iOOBForCIBackrefs(){
+        String line = "\ud83d\udc95\ud83d\udc95\ud83d\udc95";
+        var pattern2 = Pattern.compile("(?i)(.)\\1{2,}");
+        assertTrue(pattern2.matcher(line).find());
+
+    }
 }