MaxGekk commented on code in PR #37483:
URL: https://github.com/apache/spark/pull/37483#discussion_r950732296
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala:
##########
@@ -452,6 +452,90 @@ class StringExpressionsSuite extends SparkFunSuite with
ExpressionEvalHelper {
// scalastyle:on
}
+ test("to_binary") {
+ // Base64 - Positive cases
+ val base64Literal = Literal("base64")
+ Seq(
+ ("", ""),
+ (" \r\n \t", ""),
+ ("ag", "ag=="),
+ ("abc", "abc="),
+ ("abcd", "abcd"),
+ ("ab\r\n\t cd", "abcd"),
+ ("ab cd ef", "abcdeQ=="),
+ ("+ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789/",
+ "+ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789/"),
+
("b25lIHR3byB0aHJlZSBmb3VyIGZpdmUgc2l4IHNldmVuIGVpZ2h0IG5pbmUgdGVuIGVsZXZlbiB0\r\n"
+
+
"d2VsdmUgdGhpcnRlZW4gZm91cnRlZW4gZml2dGVlbiBzaXh0ZWVuIHNldmVudGVlbiBlaWdodGVl\r\n"
+
+ "biBuaW5ldGVlbiB0d2VudHkgdHdlbnR5LW9uZQ==",
+
"b25lIHR3byB0aHJlZSBmb3VyIGZpdmUgc2l4IHNldmVuIGVpZ2h0IG5pbmUgdGVuIGVsZXZlbiB0\r\n"
+
+
"d2VsdmUgdGhpcnRlZW4gZm91cnRlZW4gZml2dGVlbiBzaXh0ZWVuIHNldmVudGVlbiBlaWdodGVl\r\n"
+
+ "biBuaW5ldGVlbiB0d2VudHkgdHdlbnR5LW9uZQ==")
+ ).foreach {
+ case (input: String, expected: String) =>
+ checkEvaluation(Base64(ToBinary(Literal(input), base64Literal)),
expected)
+ }
+ checkEvaluation(ToBinary(Literal.create(null, StringType), base64Literal),
null)
+
+ // Base64 - Negative cases
+ Seq(
+ "a", // Too short
+ "abc==", // Invalid padding
+ "abcdef==a", // String should end with padding
+ "[email protected]" // Invalid character
+ ).foreach { input =>
+ val errMsg = "[CONVERSION_INVALID_INPUT]"
+ checkExceptionInExpression[Exception](ToBinary(Literal(input),
base64Literal), errMsg)
+ }
+
+ // UTF-8/UTF8
+ val utf8Literal = Literal("Utf8")
+ val utf_8Literal = Literal("uTf-8")
+ // scalastyle:off
+ Seq(
+ "∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨
β)",
+ "大千世界",
+ ""
+ ).foreach {
+ input =>
+ checkEvaluation(StringDecode(ToBinary(Literal(input), utf8Literal),
utf_8Literal), input)
+ checkEvaluation(StringDecode(ToBinary(Literal(input), utf_8Literal),
utf_8Literal), input)
+ }
+ // scalastyle:on
+ checkEvaluation(ToBinary(Literal.create(null, StringType), utf8Literal),
null)
+ checkEvaluation(ToBinary(Literal.create(null, StringType), utf_8Literal),
null)
+
+ // HEX - Positive cases
+ val hexLiteral = Literal("hEx")
+ Seq(
+ ("737472696E67", "737472696E67"),
+ ("", ""),
+ ("F", "0F"),
+ ("ff", "FF"),
+ ("00", "00")
+ ).foreach {
+ case (input, expected) =>
+ checkEvaluation(Hex(ToBinary(Literal(input), hexLiteral)), expected)
+ }
+ checkEvaluation(ToBinary(Literal.create(null, StringType), hexLiteral),
null)
+
+ // HEX - Negative cases
+ Seq(
+ "GG",
+ "FF 01"
+ ).foreach { input =>
+ val errMsg = "[CONVERSION_INVALID_INPUT]"
+ checkExceptionInExpression[Exception](ToBinary(Literal(input),
hexLiteral), errMsg)
+ }
+
+ // Invalid format
+ val errMsg = "[CONVERSION_INVALID_FORMAT]"
Review Comment:
Could you transform this to a test in `QueryExecutionErrorsSuite` and use
`checkError()` to check the error class and other fields.
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala:
##########
@@ -452,6 +452,90 @@ class StringExpressionsSuite extends SparkFunSuite with
ExpressionEvalHelper {
// scalastyle:on
}
+ test("to_binary") {
+ // Base64 - Positive cases
+ val base64Literal = Literal("base64")
+ Seq(
+ ("", ""),
+ (" \r\n \t", ""),
+ ("ag", "ag=="),
+ ("abc", "abc="),
+ ("abcd", "abcd"),
+ ("ab\r\n\t cd", "abcd"),
+ ("ab cd ef", "abcdeQ=="),
+ ("+ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789/",
+ "+ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789/"),
+
("b25lIHR3byB0aHJlZSBmb3VyIGZpdmUgc2l4IHNldmVuIGVpZ2h0IG5pbmUgdGVuIGVsZXZlbiB0\r\n"
+
+
"d2VsdmUgdGhpcnRlZW4gZm91cnRlZW4gZml2dGVlbiBzaXh0ZWVuIHNldmVudGVlbiBlaWdodGVl\r\n"
+
+ "biBuaW5ldGVlbiB0d2VudHkgdHdlbnR5LW9uZQ==",
+
"b25lIHR3byB0aHJlZSBmb3VyIGZpdmUgc2l4IHNldmVuIGVpZ2h0IG5pbmUgdGVuIGVsZXZlbiB0\r\n"
+
+
"d2VsdmUgdGhpcnRlZW4gZm91cnRlZW4gZml2dGVlbiBzaXh0ZWVuIHNldmVudGVlbiBlaWdodGVl\r\n"
+
+ "biBuaW5ldGVlbiB0d2VudHkgdHdlbnR5LW9uZQ==")
+ ).foreach {
+ case (input: String, expected: String) =>
+ checkEvaluation(Base64(ToBinary(Literal(input), base64Literal)),
expected)
+ }
+ checkEvaluation(ToBinary(Literal.create(null, StringType), base64Literal),
null)
+
+ // Base64 - Negative cases
+ Seq(
+ "a", // Too short
+ "abc==", // Invalid padding
+ "abcdef==a", // String should end with padding
+ "[email protected]" // Invalid character
+ ).foreach { input =>
+ val errMsg = "[CONVERSION_INVALID_INPUT]"
+ checkExceptionInExpression[Exception](ToBinary(Literal(input),
base64Literal), errMsg)
+ }
Review Comment:
Please, use `checkError` to check the error classes.
##########
core/src/main/resources/error/error-classes.json:
##########
@@ -70,6 +70,16 @@
"Another instance of this query was just started by a concurrent
session."
]
},
+ "CONVERSION_INVALID_FORMAT" : {
Review Comment:
Can't we use the error class `INVALID_PARAMETER_VALUE` instead of it?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
