[GitHub] [spark] MaxGekk commented on a diff in pull request #42632: [SPARK-44983][SQL] Convert binary to string by `to_char` for the formats: `hex`, `base64`, `utf-8`

["MaxGekk (via GitHub)" <gi...@apache.org>]

MaxGekk commented on code in PR #42632:
URL: https://github.com/apache/spark/pull/42632#discussion_r1307065601


##########
sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala:
##########
@@ -854,28 +854,53 @@ class StringFunctionsSuite extends QueryTest with SharedSparkSession {
     )
   }
 
-  test("to_char") {
-    val df = Seq(78.12).toDF("a")
-    checkAnswer(
-      df.selectExpr("to_char(a, '$99.99')"),
-      Seq(Row("$78.12"))
-    )
-    checkAnswer(
-      df.select(to_char(col("a"), lit("$99.99"))),
-      Seq(Row("$78.12"))
-    )
-  }
-
-  test("to_varchar") {
-    val df = Seq(78.12).toDF("a")
-    checkAnswer(
-      df.selectExpr("to_varchar(a, '$99.99')"),
-      Seq(Row("$78.12"))
-    )
-    checkAnswer(
-      df.select(to_varchar(col("a"), lit("$99.99"))),
-      Seq(Row("$78.12"))
-    )
+  test("to_char/to_varchar") {
+    Seq(
+      "to_char" -> ((e: Column, fmt: Column) => to_char(e, fmt)),
+      "to_varchar" -> ((e: Column, fmt: Column) => to_varchar(e, fmt))
+    ).foreach { case (funcName, func) =>
+      val df = Seq(78.12).toDF("a")
+      checkAnswer(df.selectExpr(s"$funcName(a, '$$99.99')"), Seq(Row("$78.12")))
+      checkAnswer(df.select(func(col("a"), lit("$99.99"))), Seq(Row("$78.12")))
+
+      val df2 = Seq((Array(100.toByte), "base64")).toDF("input", "format")
+      checkAnswer(df2.selectExpr(s"$funcName(input, 'hex')"), Seq(Row("64")))
+      checkAnswer(df2.select(func(col("input"), lit("hex"))), Seq(Row("64")))
+      checkAnswer(df2.selectExpr(s"$funcName(input, 'base64')"), Seq(Row("ZA==")))
+      checkAnswer(df2.select(func(col("input"), lit("base64"))), Seq(Row("ZA==")))
+      checkAnswer(df2.selectExpr(s"$funcName(input, 'utf-8')"), Seq(Row("d")))
+      checkAnswer(df2.select(func(col("input"), lit("utf-8"))), Seq(Row("d")))
+
+      checkError(
+        exception = intercept[AnalysisException] {
+          df2.select(func(col("input"), col("format"))).collect()
+        },
+        errorClass = "_LEGACY_ERROR_TEMP_1100",

Review Comment:
   TODO: Open an JIRA to assign proper name for the error class.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org