From 9bff3c9e65720fbb3268d204c72dfb8c8a0c45b4 Mon Sep 17 00:00:00 2001
From: belugabehr <12578579+belugabehr@users.noreply.github.com>
Date: Sun, 22 Sep 2024 22:08:58 -0400
Subject: [PATCH] AVRO-4049: Use JDK Arrays equal to test if two UTF8 strings
 are equal (#3131)

---
 lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java b/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java
index 9238fd78c65..6de9ebb22c5 100644
--- a/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java
+++ b/lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java
@@ -158,6 +158,10 @@ public boolean equals(Object o) {
     Utf8 that = (Utf8) o;
     if (!(this.length == that.length))
       return false;
+    // For longer strings, leverage vectorization (JDK 9+) to determine equality
+    // For shorter strings, the overhead of this method defeats the value
+    if (this.length > 7)
+      return Arrays.equals(this.bytes, 0, this.length, that.bytes, 0, that.length);
     byte[] thatBytes = that.bytes;
     for (int i = 0; i < this.length; i++)
       if (bytes[i] != thatBytes[i])