Fix off-by-one error in allCharsAreHex

JoshRosen · Jun 25, 2024 · 07f0ed7 · 07f0ed7
1 parent 972cf70
commit 07f0ed7
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkParserUtils.scala b/sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkParserUtils.scala
@@ -44,7 +44,7 @@ trait SparkParserUtils {
     }
 
     def allCharsAreHex(s: String, start: Int, length: Int): Boolean = {
-      val end = start + length - 1
+      val end = start + length
       var i = start
       while (i < end) {
         val c = s.charAt(i)

diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ParserUtilsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/ParserUtilsSuite.scala
@@ -140,6 +140,8 @@ class ParserUtilsSuite extends SparkFunSuite {
     assert(unescapeSQLString("\"abc\\uxxxxa\"") == "abcuxxxxa")
     assert(unescapeSQLString("\"abc\\UXXXXXXXXa\"") == "abcUXXXXXXXXa")
     assert(unescapeSQLString("\"abc\\Uxxxxxxxxa\"") == "abcUxxxxxxxxa")
+    // Guard against off-by-one errors in the "all chars are hex" routine:
+    assert(unescapeSQLString("\"abc\\uAAAXa\"") == "abcuAAAXa")
 
     // scalastyle:on nonascii
   }