Jefffrey commented on code in PR #20361:
URL: https://github.com/apache/datafusion/pull/20361#discussion_r2822331972
##########
datafusion/functions/src/string/concat_ws.rs:
##########
@@ -162,23 +156,55 @@ impl ScalarUDFImpl for ConcatWsFunc {
// parse sep
let sep = match &args[0] {
- ColumnarValue::Scalar(ScalarValue::Utf8(Some(s))) => {
- data_size += s.len() * len * (args.len() - 2); // estimate
- ColumnarValueRef::Scalar(s.as_bytes())
- }
- ColumnarValue::Scalar(ScalarValue::Utf8(None)) => {
- return
Ok(ColumnarValue::Array(Arc::new(StringArray::new_null(len))));
- }
- ColumnarValue::Array(array) => {
- let string_array = as_string_array(array)?;
- data_size += string_array.values().len() * (args.len() - 2);
// estimate
- if array.is_nullable() {
- ColumnarValueRef::NullableArray(string_array)
- } else {
- ColumnarValueRef::NonNullableArray(string_array)
+ ColumnarValue::Scalar(scalar) => match scalar.try_as_str() {
+ Some(Some(s)) => {
+ data_size += s.len() * len * (args.len() - 2); // estimate
+ ColumnarValueRef::Scalar(s.as_bytes())
}
- }
- _ => unreachable!("concat ws"),
+ Some(None) => {
+ return
Ok(ColumnarValue::Array(Arc::new(StringArray::new_null(
Review Comment:
We can probably return scalar here
##########
datafusion/functions/src/string/concat_ws.rs:
##########
@@ -162,23 +156,55 @@ impl ScalarUDFImpl for ConcatWsFunc {
// parse sep
let sep = match &args[0] {
- ColumnarValue::Scalar(ScalarValue::Utf8(Some(s))) => {
- data_size += s.len() * len * (args.len() - 2); // estimate
- ColumnarValueRef::Scalar(s.as_bytes())
- }
- ColumnarValue::Scalar(ScalarValue::Utf8(None)) => {
- return
Ok(ColumnarValue::Array(Arc::new(StringArray::new_null(len))));
- }
- ColumnarValue::Array(array) => {
- let string_array = as_string_array(array)?;
- data_size += string_array.values().len() * (args.len() - 2);
// estimate
- if array.is_nullable() {
- ColumnarValueRef::NullableArray(string_array)
- } else {
- ColumnarValueRef::NonNullableArray(string_array)
+ ColumnarValue::Scalar(scalar) => match scalar.try_as_str() {
+ Some(Some(s)) => {
+ data_size += s.len() * len * (args.len() - 2); // estimate
+ ColumnarValueRef::Scalar(s.as_bytes())
}
- }
- _ => unreachable!("concat ws"),
+ Some(None) => {
+ return
Ok(ColumnarValue::Array(Arc::new(StringArray::new_null(
+ len,
+ ))));
+ }
+ None => {
+ return internal_err!("Expected string separator, got
{scalar:?}");
+ }
+ },
+ ColumnarValue::Array(array) => match array.data_type() {
+ DataType::Utf8 => {
+ let string_array = as_string_array(array)?;
+ data_size += string_array.values().len() * (args.len() -
2);
+ if array.is_nullable() {
+ ColumnarValueRef::NullableArray(string_array)
+ } else {
+ ColumnarValueRef::NonNullableArray(string_array)
+ }
+ }
+ DataType::LargeUtf8 => {
+ let string_array = as_largestring_array(array);
Review Comment:
nit: we seem to be mixing cast methods here; this comes from arrow but we're
using datafusion sourced ones for utf8 & utf8view
--
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]
