[SPARK-33468][SQL] ParseUrl in ANSI mode should fail if input string is not a valid url

docs/sql-ref-ansi-compliance.md

@@ -114,6 +114,7 @@ The behavior of some SQL functions can be different under ANSI mode (`spark.sql.
   - `element_at`: This function throws `ArrayIndexOutOfBoundsException` if using invalid indices. 
   - `element_at`: This function throws `NoSuchElementException` if key does not exist in map. 
   - `elt`: This function throws `ArrayIndexOutOfBoundsException` if using invalid indices.
+  - `parse_url`: This function throws `IllegalArgumentException` if input string is not a valid url.
 
 ### SQL Operators
 

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala

@@ -1357,7 +1357,7 @@ object ParseUrl {
        1
   """,
   since = "2.0.0")
-case class ParseUrl(children: Seq[Expression])
+case class ParseUrl(children: Seq[Expression], failOnError: Boolean = SQLConf.get.ansiEnabled)
   extends Expression with ExpectsInputTypes with CodegenFallback {
 
   override def nullable: Boolean = true
@@ -1404,7 +1404,9 @@ case class ParseUrl(children: Seq[Expression])
     try {
       new URI(url.toString)
     } catch {
-      case e: URISyntaxException => null
+      case e: URISyntaxException if failOnError =>
+        throw new IllegalArgumentException(s"Find an invaild url string ${url.toString}", e)
+      case _: URISyntaxException => null
     }
   }
 

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala

@@ -943,6 +943,20 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     GenerateUnsafeProjection.generate(ParseUrl(Seq(Literal("\"quote"), Literal("\"quote"))) :: Nil)
   }
 
+  test("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url") {
+    withSQLConf(SQLConf.ANSI_ENABLED.key -> "true") {
+      val msg = intercept[IllegalArgumentException] {
+        evaluateWithoutCodegen(
+          ParseUrl(Seq("https://a.b.c/index.php?params1=a|b&params2=x", "HOST")))
+      }.getMessage
+      assert(msg.contains("Find an invaild url string"))
+    }
+    withSQLConf(SQLConf.ANSI_ENABLED.key -> "false") {
+      checkEvaluation(
+        ParseUrl(Seq("https://a.b.c/index.php?params1=a|b&params2=x", "HOST")), null)
+    }
+  }
+
   test("Sentences") {
     val nullString = Literal.create(null, StringType)
     checkEvaluation(Sentences(nullString, nullString, nullString), null)