From 2078851b480e90e473d37c0622106d5f29a7d07c Mon Sep 17 00:00:00 2001
From: yangjie01 <yangjie01@baidu.com>
Date: Tue, 2 Jun 2026 17:07:02 +0800
Subject: [PATCH] [SPARK-57208][SQL] Simplify Ascii codegen by extracting a
 static Java helper

Move Ascii's first-character logic into a single ExpressionImplUtils.ascii(UTF8String) helper. nullSafeEval delegates to it and doGenCode becomes a one-line defineCodeGen call, so eval and codegen share one implementation instead of duplicating the substring/codePointAt block. This collapses the inlined block into one invokestatic per call site (fewer constant-pool entries, smaller generated method), helping with the JVM 64KB method / constant-pool limits, Janino compile time, and JIT work.

Part of SPARK-56908.
---
 .../expressions/ExpressionImplUtils.java      | 15 +++++++++++++
 .../expressions/stringExpressions.scala       | 22 +++----------------
 .../expressions/StringExpressionsSuite.scala  |  5 +++++
 3 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java
index 7bad7c430b862..5b32fcf99d89f 100644
--- a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java
+++ b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionImplUtils.java
@@ -354,4 +354,19 @@ public static long crc32(byte[] bytes) {
     checksum.update(bytes, 0, bytes.length);
     return checksum.getValue();
   }
+
+  /**
+   * Returns the numeric value of the first character of the input string, or 0 if it is empty.
+   * Shared by the Ascii expression's eval and codegen paths so the generated Java is a single
+   * call rather than an inline substring/if-else block.
+   */
+  public static int ascii(UTF8String str) {
+    // only pick the first character to reduce the `toString` cost
+    UTF8String firstCharStr = str.substring(0, 1);
+    if (firstCharStr.numChars() > 0) {
+      return firstCharStr.toString().codePointAt(0);
+    } else {
+      return 0;
+    }
+  }
 }
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
index 5b5a63812dcab..5d8363d0e5260 100755
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala
@@ -2774,27 +2774,11 @@ case class Ascii(child: Expression)
   override def inputTypes: Seq[AbstractDataType] =
     Seq(StringTypeWithCollation(supportsTrimCollation = true))
 
-  protected override def nullSafeEval(string: Any): Any = {
-    // only pick the first character to reduce the `toString` cost
-    val firstCharStr = string.asInstanceOf[UTF8String].substring(0, 1)
-    if (firstCharStr.numChars > 0) {
-      firstCharStr.toString.codePointAt(0)
-    } else {
-      0
-    }
-  }
+  protected override def nullSafeEval(string: Any): Any =
+    ExpressionImplUtils.ascii(string.asInstanceOf[UTF8String])
 
   override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
-    nullSafeCodeGen(ctx, ev, (child) => {
-      val firstCharStr = ctx.freshName("firstCharStr")
-      s"""
-        UTF8String $firstCharStr = $child.substring(0, 1);
-        if ($firstCharStr.numChars() > 0) {
-          ${ev.value} = $firstCharStr.toString().codePointAt(0);
-        } else {
-          ${ev.value} = 0;
-        }
-       """})
+    defineCodeGen(ctx, ev, c => s"${classOf[ExpressionImplUtils].getName}.ascii($c)")
   }
 
   override protected def withNewChildInternal(newChild: Expression): Ascii = copy(child = newChild)
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
index bca4984cfac9c..aac4fafb78028 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
@@ -378,6 +378,11 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     val a = $"a".string.at(0)
     checkEvaluation(Ascii(Literal("efg")), 101, create_row("abdef"))
     checkEvaluation(Ascii(a), 97, create_row("abdef"))
+    // U+1F600 is a supplementary-plane code point; ascii must return the full code point
+    // (128512 via codePointAt), not the leading UTF-16 surrogate (55357 via charAt).
+    // scalastyle:off
+    checkEvaluation(Ascii(Literal("😀")), 128512, create_row("😀"))
+    // scalastyle:on
     checkEvaluation(Ascii(a), 0, create_row(""))
     checkEvaluation(Ascii(a), null, create_row(null))
     checkEvaluation(Ascii(Literal.create(null, StringType)), null, create_row("abdef"))