ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-32586][SQL] Fix NumberFormatException error message when ansi is enabled

Browse source 
### What changes were proposed in this pull request?

This pr fixes the error message of `NumberFormatException` when casting invalid input to FractionalType and enabling **ansi**:
```
spark-sql> set spark.sql.ansi.enabled=true;
spark.sql.ansi.enabled	true
spark-sql> create table SPARK_32586 using parquet as select 's' s;
spark-sql> select * from SPARK_32586 where s > 1.13D;
java.lang.NumberFormatException: invalid input syntax for type numeric: columnartorow_value_0
```

After this pr:
```
spark-sql> select * from SPARK_32586 where s > 1.13D;
java.lang.NumberFormatException: invalid input syntax for type numeric: s
```

### Why are the changes needed?

Improve error message.

### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?

Unit test.

Closes #29405 from wangyum/SPARK-32586.

Authored-by: Yuming Wang <yumwang@ebay.com>
Signed-off-by: HyukjinKwon <gurwls223@apache.org>
This commit is contained in:
Yuming Wang 2020-08-12 13:16:57 +09:00 committed by HyukjinKwon
parent e7c1204f6c
commit 5d130f0360
2 changed files with 12 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
View file

@ -1189,7 +1189,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
case StringType =>
(c, evPrim, evNull) =>
val handleException = if (ansiEnabled) {
s"""throw new NumberFormatException("invalid input syntax for type numeric: $c");"""
s"""throw new NumberFormatException("invalid input syntax for type numeric: " + $c);"""
} else {
s"$evNull =true;"
}
@ -1549,7 +1549,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
val floatStr = ctx.freshVariable("floatStr", StringType)
(c, evPrim, evNull) =>
val handleNull = if (ansiEnabled) {
s"""throw new NumberFormatException("invalid input syntax for type numeric: $c");"""
s"""throw new NumberFormatException("invalid input syntax for type numeric: " + $c);"""
} else {
s"$evNull = true;"
}
@ -1585,7 +1585,7 @@ abstract class CastBase extends UnaryExpression with TimeZoneAwareExpression wit
val doubleStr = ctx.freshVariable("doubleStr", StringType)
(c, evPrim, evNull) =>
val handleNull = if (ansiEnabled) {
s"""throw new NumberFormatException("invalid input syntax for type numeric: $c");"""
s"""throw new NumberFormatException("invalid input syntax for type numeric: " + $c);"""
} else {
s"$evNull = true;"
}

17
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala
View file

@ -1366,24 +1366,25 @@ class AnsiCastSuite extends CastSuiteBase {
val array = Literal.create(Seq("123", "true", "f", null),
ArrayType(StringType, containsNull = true))
checkExceptionInExpression[NumberFormatException](
cast(array, ArrayType(dataType, containsNull = true)), "invalid input")
cast(array, ArrayType(dataType, containsNull = true)),
"invalid input syntax for type numeric: true")
checkExceptionInExpression[NumberFormatException](
cast("string", dataType), "invalid input")
cast("string", dataType), "invalid input syntax for type numeric: string")
checkExceptionInExpression[NumberFormatException](
cast("123-string", dataType), "invalid input")
cast("123-string", dataType), "invalid input syntax for type numeric: 123-string")
checkExceptionInExpression[NumberFormatException](
cast("2020-07-19", dataType), "invalid input")
cast("2020-07-19", dataType), "invalid input syntax for type numeric: 2020-07-19")
checkExceptionInExpression[NumberFormatException](
cast("1.23", dataType), "invalid input")
cast("1.23", dataType), "invalid input syntax for type numeric: 1.23")
}
Seq(DoubleType, FloatType, DecimalType.USER_DEFAULT).foreach { dataType =>
checkExceptionInExpression[NumberFormatException](
cast("string", dataType), "invalid input")
cast("string", dataType), "invalid input syntax for type numeric: string")
checkExceptionInExpression[NumberFormatException](
cast("123.000.00", dataType), "invalid input")
cast("123.000.00", dataType), "invalid input syntax for type numeric: 123.000.00")
checkExceptionInExpression[NumberFormatException](
cast("abc.com", dataType), "invalid input")
cast("abc.com", dataType), "invalid input syntax for type numeric: abc.com")
}
}