[SPARK-33100][SQL] Ignore a semicolon inside a bracketed comment in spark-sql

sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala

@@ -519,14 +519,22 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
   // Note: [SPARK-31595] if there is a `'` in a double quoted string, or a `"` in a single quoted
   // string, the origin implementation from Hive will not drop the trailing semicolon as expected,
   // hence we refined this function a little bit.
+  // Note: [SPARK-33100] Ignore a semicolon inside a bracketed comment in spark-sql.
   private def splitSemiColon(line: String): JList[String] = {
     var insideSingleQuote = false
     var insideDoubleQuote = false
-    var insideComment = false
+    var insideSimpleComment = false
+    var bracketedCommentLevel = 0
     var escape = false
     var beginIndex = 0
+    var includingStatement = false
     val ret = new JArrayList[String]
 
+    def insideBracketedComment: Boolean = bracketedCommentLevel > 0
+    def insideComment: Boolean = insideSimpleComment || insideBracketedComment
+    def statementBegin(index: Int): Boolean = includingStatement || (!insideComment &&
+      index > beginIndex && !s"${line.charAt(index)}".trim.isEmpty)
+
     for (index <- 0 until line.length) {
       if (line.charAt(index) == '\'' && !insideComment) {
         // take a look to see if it is escaped
@@ -550,21 +558,33 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
           // Sample query: select "quoted value --"
           //                                    ^^ avoids starting a comment if it's inside quotes.
         } else if (hasNext && line.charAt(index + 1) == '-') {
-          // ignore quotes and ;
-          insideComment = true
+          // ignore quotes and ; in simple comment
+          insideSimpleComment = true
         }
       } else if (line.charAt(index) == ';') {
         if (insideSingleQuote || insideDoubleQuote || insideComment) {
           // do not split
         } else {
-          // split, do not include ; itself
-          ret.add(line.substring(beginIndex, index))
+          if (includingStatement) {
+            // split, do not include ; itself
+            ret.add(line.substring(beginIndex, index))
+          }
           beginIndex = index + 1
+          includingStatement = false
         }
       } else if (line.charAt(index) == '\n') {
-        // with a new line the inline comment should end.
+        // with a new line the inline simple comment should end.
         if (!escape) {
-          insideComment = false
+          insideSimpleComment = false
+        }
+      } else if (line.charAt(index) == '/' && !insideSimpleComment) {
+        val hasNext = index + 1 < line.length
+        if (insideSingleQuote || insideDoubleQuote) {
+          // Ignores '/' in any case of quotes
+        } else if (insideBracketedComment && line.charAt(index - 1) == '*' ) {
+          bracketedCommentLevel -= 1
+        } else if (hasNext && !insideBracketedComment && line.charAt(index + 1) == '*') {
+          bracketedCommentLevel += 1
         }
       }
       // set the escape
@@ -573,8 +593,12 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
       } else if (line.charAt(index) == '\\') {
         escape = true
       }
+
+      includingStatement = statementBegin(index)
+    }
+    if (includingStatement) {
+      ret.add(line.substring(beginIndex))
     }
-    ret.add(line.substring(beginIndex))
     ret
   }
 }

sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala

@@ -573,4 +573,27 @@ class CliSuite extends SparkFunSuite with BeforeAndAfterAll with Logging {
     // the date formatter for `java.sql.LocalDate` must output negative years with sign.
     runCliWithin(1.minute)("SELECT MAKE_DATE(-44, 3, 15);" -> "-0044-03-15")
   }
+
+  test("SPARK-33100: Ignore a semicolon inside a bracketed comment in spark-sql") {
+    runCliWithin(4.minute)(
+      "/* SELECT 'test';*/ SELECT 'test';" -> "test",
+      ";;/* SELECT 'test';*/ SELECT 'test';" -> "test",
+      "/* SELECT 'test';*/;; SELECT 'test';" -> "test",
+      "SELECT 'test'; -- SELECT 'test';" -> "",
+      "SELECT 'test'; /* SELECT 'test';*/;" -> "",
+      "/*$meta chars{^\\;}*/ SELECT 'test';" -> "test",
+      "/*\nmulti-line\n*/ SELECT 'test';" -> "test",
+      "/*/* multi-level bracketed*/ SELECT 'test';" -> "test"
+    )
+  }
+
+  test("SPARK-33100: test sql statements with hint in bracketed comment") {
+    runCliWithin(2.minute)(
+      "CREATE TEMPORARY VIEW t1 AS SELECT * FROM VALUES(1, 2) AS t1(k, v);" -> "",
+      "CREATE TEMPORARY VIEW t2 AS SELECT * FROM VALUES(2, 1) AS t2(k, v);" -> "",
+      "EXPLAIN SELECT /*+ MERGEJOIN(t1) */ t1.* FROM t1 JOIN t2 ON t1.k = t2.v;" -> "SortMergeJoin",
+      "EXPLAIN SELECT /* + MERGEJOIN(t1) */ t1.* FROM t1 JOIN t2 ON t1.k = t2.v;"
+        -> "BroadcastHashJoin"
+    )
+  }
 }