2010YOUY01 commented on code in PR #17837:
URL: https://github.com/apache/datafusion/pull/17837#discussion_r2394240646
##########
datafusion/functions-aggregate/src/string_agg.rs:
##########
@@ -269,6 +301,103 @@ fn filter_index<T: Clone>(values: &[T], index: usize) ->
Vec<T> {
.collect::<Vec<_>>()
}
+/// StringAgg accumulator for the simple case (no order or distinct specified)
+/// This accumulator is more efficient than `StringAggAccumulator`
+#[derive(Debug)]
+pub(crate) struct SimpleStringAggAccumulator {
+ delimiter: String,
+ // Updating during `update_batch()`. e.g. "foo,bar"
+ in_progress_string: String,
+ has_value: bool,
+}
+
+impl SimpleStringAggAccumulator {
+ pub fn new(delimiter: &str) -> Self {
+ Self {
+ delimiter: delimiter.to_string(),
+ in_progress_string: "".to_string(),
+ has_value: false,
+ }
+ }
+
+ #[inline]
+ fn append_strings<'a, I>(&mut self, iter: I)
+ where
+ I: Iterator<Item = Option<&'a str>>,
+ {
+ for value in iter.flatten() {
+ if self.has_value {
+ self.in_progress_string.push_str(&self.delimiter);
+ }
+
+ self.in_progress_string.push_str(value);
+ self.has_value = true;
+ }
+ }
+}
+
+impl Accumulator for SimpleStringAggAccumulator {
+ fn update_batch(&mut self, values: &[ArrayRef]) -> Result<()> {
+ let string_arr = values.first().ok_or_else(|| {
Review Comment:
Yes, it's an array of arg1. The arg is validated during the planning time,
and we can also assume it's the right type here (`values[0]` is a string array)
--
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]
