AVRO-4060: Use JDK to Hash Byte Array in UTF8

Author: belugabehr

lang/java/avro/src/main/java/org/apache/avro/util/Utf8.java

@@ -68,6 +68,11 @@ public Utf8(byte[] bytes) {
     this.length = length;
   }
 
+  Utf8(String string, int length) {
+    this(string);
+    this.length = length;
+  }
+
   /**
    * Return UTF-8 encoded bytes. Only valid through {@link #getByteLength()}.
    */
@@ -175,9 +180,15 @@ public int hashCode() {
     if (h == 0) {
       byte[] bytes = this.bytes;
       int length = this.length;
-      h = 1;
-      for (int i = 0; i < length; i++) {
-        h = h * 31 + bytes[i];
+      // If the array is filled, use the underlying JDK hash functionality.
+      // Starting with JDK 21, the underlying implementation is vectorized.
+      if (bytes.length == length) {
+        h = Arrays.hashCode(bytes);
+      } else {
+        h = 1;
+        for (int i = 0; i < length; i++) {
+          h = h * 31 + bytes[i];
+        }
       }
       this.hash = h;
     }

lang/java/avro/src/test/java/org/apache/avro/util/TestUtf8.java

@@ -99,6 +99,26 @@ void hashCodeReused() {
     assertEquals(4122302, u.hashCode());
   }
 
+  /**
+   * There are two different code paths that hashcode() can call depending on the
+   * state of the internal buffer. If the buffer is full (string length eq. buffer
+   * length) then the JDK hashcode function can be used. This function can is
+   * vectorized JDK 21+ and therefore should be preferable. However, if the buffer
+   * is not full (string length le. buffer length), then the JDK does not support
+   * this and a scalar implementation is the only option as of today. This
+   * difference can be resolved with JDK 23 as it supports both cases.
+   */
+  @Test
+  void hashCodeBasedOnCapacity() {
+    // string = 3; buffer = 3
+    Utf8 fullCapacity = new Utf8("abc", 3);
+
+    // string = 3; buffer = 4
+    Utf8 partialCapacity = new Utf8("abcX", 3);
+
+    assertEquals(fullCapacity.hashCode(), partialCapacity.hashCode());
+  }
+
   @Test
   void oversizeUtf8() {
     Utf8 u = new Utf8();