Skip to content
Closed
Prev Previous commit
Next Next commit
[SPARK-48658][SQL] Encode/Decode functions report coding error instea…
…d of mojibake
  • Loading branch information
yaooqinn committed Jun 19, 2024
commit afb2d08a794edd56465c602e86ff1bf5f8618ae8
Original file line number Diff line number Diff line change
Expand Up @@ -912,14 +912,14 @@ SetCommand (spark.sql.legacy.codingErrorAction,Some(true))


-- !query
select decode('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
select decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
-- !query analysis
Project [decode(E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII) AS decode(E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII)#x]
Project [decode(0xE58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII) AS decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', US-ASCII)#x]
+- OneRowRelation


-- !query
select decode(scol, ecol) from values('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
-- !query analysis
Project [decode(scol#x, ecol#x) AS decode(scol, ecol)#x]
+- SubqueryAlias t
Expand All @@ -933,14 +933,14 @@ SetCommand (spark.sql.legacy.codingErrorAction,Some(false))


-- !query
select decode('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
select decode(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
-- !query analysis
Project [decode(E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII) AS decode(E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII)#x]
Project [decode(0xE8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII) AS decode(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', US-ASCII)#x]
+- OneRowRelation


-- !query
select decode(scol, ecol) from values('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
-- !query analysis
Project [decode(scol#x, ecol#x) AS decode(scol, ecol)#x]
+- SubqueryAlias t
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -912,14 +912,14 @@ SetCommand (spark.sql.legacy.codingErrorAction,Some(true))


-- !query
select decode('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
select decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
-- !query analysis
Project [decode(E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII) AS decode(E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII)#x]
Project [decode(0xE58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII) AS decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', US-ASCII)#x]
+- OneRowRelation


-- !query
select decode(scol, ecol) from values('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
-- !query analysis
Project [decode(scol#x, ecol#x) AS decode(scol, ecol)#x]
+- SubqueryAlias t
Expand All @@ -933,14 +933,14 @@ SetCommand (spark.sql.legacy.codingErrorAction,Some(false))


-- !query
select decode('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
select decode(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
-- !query analysis
Project [decode(E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII) AS decode(E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII)#x]
Project [decode(0xE8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII) AS decode(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', US-ASCII)#x]
+- OneRowRelation


-- !query
select decode(scol, ecol) from values('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
-- !query analysis
Project [decode(scol#x, ecol#x) AS decode(scol, ecol)#x]
+- SubqueryAlias t
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -154,11 +154,11 @@ set spark.sql.legacy.javaCharsets=false;
select decode(X'68656c6c6f', 'WINDOWS-1252');
select decode(scol, ecol) from values(X'68656c6c6f', 'WINDOWS-1252') as t(scol, ecol);
set spark.sql.legacy.codingErrorAction=true;
select decode('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII');
select decode(scol, ecol) from values('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol);
select decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII');
select decode(scol, ecol) from values(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol);
set spark.sql.legacy.codingErrorAction=false;
select decode('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII');
select decode(scol, ecol) from values('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol);
select decode(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII');
select decode(scol, ecol) from values(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol);

-- contains
SELECT CONTAINS(null, 'Spark');
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -1198,19 +1198,19 @@ spark.sql.legacy.codingErrorAction true


-- !query
select decode('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
select decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
-- !query schema
struct<decode(E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII):string>
struct<decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', US-ASCII):string>
-- !query output
E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592
���������������������


-- !query
select decode(scol, ecol) from values('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
-- !query schema
struct<decode(scol, ecol):string>
-- !query output
E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592
���������������������


-- !query
Expand All @@ -1222,19 +1222,35 @@ spark.sql.legacy.codingErrorAction false


-- !query
select decode('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
select decode(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
-- !query schema
struct<decode(E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII):string>
struct<>
-- !query output
E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA
org.apache.spark.SparkRuntimeException
{
"errorClass" : "MALFORMED_CHARACTER_CODING",
"sqlState" : "22000",
"messageParameters" : {
"charset" : "US-ASCII",
"function" : "`decode`"
}
}


-- !query
select decode(scol, ecol) from values('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
-- !query schema
struct<decode(scol, ecol):string>
struct<>
-- !query output
E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA
org.apache.spark.SparkRuntimeException
{
"errorClass" : "MALFORMED_CHARACTER_CODING",
"sqlState" : "22000",
"messageParameters" : {
"charset" : "US-ASCII",
"function" : "`decode`"
}
}


-- !query
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -1130,19 +1130,19 @@ spark.sql.legacy.codingErrorAction true


-- !query
select decode('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
select decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII')
-- !query schema
struct<decode(E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592, US-ASCII):string>
struct<decode(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', US-ASCII):string>
-- !query output
E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592
���������������������


-- !query
select decode(scol, ecol) from values('E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592', 'US-ASCII') as t(scol, ecol)
-- !query schema
struct<decode(scol, ecol):string>
-- !query output
E58A9DE5909BE69BB4E5B0BDE4B880E69DAFE98592
���������������������


-- !query
Expand All @@ -1154,19 +1154,35 @@ spark.sql.legacy.codingErrorAction false


-- !query
select decode('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
select decode(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII')
-- !query schema
struct<decode(E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA, US-ASCII):string>
struct<>
-- !query output
E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA
org.apache.spark.SparkRuntimeException
{
"errorClass" : "MALFORMED_CHARACTER_CODING",
"sqlState" : "22000",
"messageParameters" : {
"charset" : "US-ASCII",
"function" : "`decode`"
}
}


-- !query
select decode(scol, ecol) from values('E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
select decode(scol, ecol) from values(X'E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA', 'US-ASCII') as t(scol, ecol)
-- !query schema
struct<decode(scol, ecol):string>
struct<>
-- !query output
E8A5BFE587BAE998B3E585B3E697A0E69585E4BABA
org.apache.spark.SparkRuntimeException
{
"errorClass" : "MALFORMED_CHARACTER_CODING",
"sqlState" : "22000",
"messageParameters" : {
"charset" : "US-ASCII",
"function" : "`decode`"
}
}


-- !query
Expand Down