init

ulysses-you · ulysses-you · commit 62bf87fbdb29 · 2020-11-18T00:06:35.000+08:00
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
@@ -1404,7 +1404,10 @@ case class ParseUrl(children: Seq[Expression])
     try {
       new URI(url.toString)
     } catch {
-      case e: URISyntaxException => null
+      // We fail on error if in ansi mode.
+      case e: URISyntaxException if SQLConf.get.ansiEnabled =>
+        throw new IllegalArgumentException(s"Find an invaild url string ${url.toString}", e)
+      case _: URISyntaxException => null
     }
   }
 
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
@@ -943,6 +943,21 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     GenerateUnsafeProjection.generate(ParseUrl(Seq(Literal("\"quote"), Literal("\"quote"))) :: Nil)
   }
 
+  test("SPARK-33468: ParseUrl should fail if input string is not a valid url") {
+    // fail on error if in ansi mode.
+    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)

Original file line number	Diff line number	Diff line change
`@@ -1404,7 +1404,10 @@ case class ParseUrl(children: Seq[Expression])`
`1404`	`1404`	`try {`
`1405`	`1405`	`new URI(url.toString)`
`1406`	`1406`	`} catch {`
`1407`		`- case e: URISyntaxException => null`
	`1407`	`+ // We fail on error if in ansi mode.`
	`1408`	`+ case e: URISyntaxException if SQLConf.get.ansiEnabled =>`
	`1409`	`+ throw new IllegalArgumentException(s"Find an invaild url string ${url.toString}", e)`
	`1410`	`+ case _: URISyntaxException => null`
`1408`	`1411`	`}`
`1409`	`1412`	`}`
`1410`	`1413`