agscpp opened a new issue, #13000:
URL: https://github.com/apache/datafusion/issues/13000
### Describe the bug
For functions whose signature contains Volatility::Volatile and arguments,
invoke is called once and without _number_rows
### To Reproduce
```
struct AddIndexToStringScalarUDF {
name: String,
signature: Signature,
return_type: DataType,
}
impl AddIndexToStringScalarUDF {
fn new() -> Self {
Self {
name: "add_index_to_string".to_string(),
signature: Signature::exact(vec![DataType::Utf8],
Volatility::Volatile),
return_type: DataType::Utf8,
}
}
}
impl std::fmt::Debug for AddIndexToStringScalarUDF {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
f.debug_struct("ScalarUDF")
.field("name", &self.name)
.field("signature", &self.signature)
.field("fun", &"<FUNC>")
.finish()
}
}
impl ScalarUDFImpl for AddIndexToStringScalarUDF {
fn as_any(&self) -> &dyn Any {
self
}
fn name(&self) -> &str {
&self.name
}
fn signature(&self) -> &Signature {
&self.signature
}
fn return_type(&self, _arg_types: &[DataType]) -> Result<DataType> {
Ok(self.return_type.clone())
}
fn invoke(&self, _args: &[ColumnarValue]) -> Result<ColumnarValue> {
not_impl_err!("index_with_offset function does not accept arguments")
}
fn invoke_batch(
&self,
_args: &[ColumnarValue],
_number_rows: usize,
) -> Result<ColumnarValue> {
let answer = match &_args[0] {
ColumnarValue::Scalar(ScalarValue::Utf8(Some(value))) => {
let mut answer = vec![];
for index in 1..=_number_rows {
answer.push(index.to_string() + ") " + value);
}
answer
}
ColumnarValue::Array(array) => {
let string_array = as_string_array(array);
let mut counter = HashMap::<&str, u64>::new();
string_array
.iter()
.map(|value| {
let value = value.expect("Unexpected null");
let index = counter.get(value).unwrap_or(&0) + 1;
counter.insert(value, index);
index.to_string() + ". " + value
})
.collect()
}
_ => unimplemented!(),
};
Ok(ColumnarValue::Array(
Arc::new(StringArray::from(answer)) as ArrayRef
))
}
}
```
TEST:
```
async fn scalar_udf_with_params() -> Result<()> {
let schema = Schema::new(vec![Field::new("a", DataType::Utf8,
false)]);
let batch = RecordBatch::try_new(
Arc::new(schema.clone()),
vec![Arc::new(StringArray::from(vec![
"test_1", "test_1", "test_1", "test_2", "test_2", "test_1",
"test_2",
]))],
)?;
let ctx = SessionContext::new();
ctx.register_batch("t", batch)?;
let get_new_str_udf = AddIndexToStringScalarUDF::new();
ctx.register_udf(ScalarUDF::from(get_new_str_udf));
let result =
plan_and_collect(&ctx, "select add_index_to_string(t.a) AS str
from t")
.await?;
let expected = [
"+-----------+", //
"| str |", //
"+-----------+", //
"| 1. test_1 |", //
"| 2. test_1 |", //
"| 3. test_1 |", //
"| 1. test_2 |", //
"| 2. test_2 |", //
"| 4. test_1 |", //
"| 3. test_2 |", //
"+-----------+",
];
assert_batches_eq!(expected, &result);
let result =
plan_and_collect(&ctx, "select add_index_to_string('test') AS
str from t")
.await?;
let expected = [
"+---------+", //
"| str |", //
"+---------+", //
"| 1) test |", //
"| 2) test |", //
"| 3) test |", //
"| 4) test |", //
"| 5) test |", //
"| 6) test |", //
"| 7) test |", //
"+---------+",
];
assert_batches_eq!(expected, &result);
}
```
### Expected behavior
_No response_
### Additional context
_No response_
--
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]
