beliefer commented on code in PR #42398: URL: https://github.com/apache/spark/pull/42398#discussion_r1368419550
########## sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseParser.g4: ########## @@ -988,6 +988,8 @@ primaryExpression | name=(PERCENTILE_CONT | PERCENTILE_DISC) LEFT_PAREN percentage=valueExpression RIGHT_PAREN WITHIN GROUP LEFT_PAREN ORDER BY sortItem RIGHT_PAREN (FILTER LEFT_PAREN WHERE where=booleanExpression RIGHT_PAREN)? ( OVER windowSpec)? #percentile + | LISTAGG LEFT_PAREN setQuantifier? aggEpxr=expression (COMMA delimiter=stringLit)? RIGHT_PAREN + WITHIN GROUP LEFT_PAREN ORDER BY sortItem RIGHT_PAREN (OVER windowSpec)? #listAgg Review Comment: ```suggestion WITHIN GROUP LEFT_PAREN ORDER BY sortItem RIGHT_PAREN (OVER windowSpec)? #listAgg ``` ########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala: ########## @@ -245,3 +249,98 @@ case class CollectTopK( override def withNewInputAggBufferOffset(newInputAggBufferOffset: Int): CollectTopK = copy(inputAggBufferOffset = newInputAggBufferOffset) } + +@ExpressionDescription( + usage = "_FUNC_(expr) - Returns the concatenated input values," + + " separated by the delimiter string.", + examples = """ + Examples: + > SELECT _FUNC_(col) FROM VALUES ('a'), ('b'), ('c') AS tab(col); + a,b,c + > SELECT _FUNC_(col) FROM VALUES (NULL), ('a'), ('b') AS tab(col); + a,b + > SELECT _FUNC_(col) FROM VALUES ('a'), ('a') AS tab(col); + a,a + > SELECT _FUNC_(DISTINCT col) FROM VALUES ('a'), ('a'), ('b') AS tab(col); + a,b + > SELECT _FUNC_(col, '|') FROM VALUES ('a'), ('b') AS tab(col); + a|b + > SELECT _FUNC_(col) FROM VALUES (NULL), (NULL) AS tab(col); + "" + """, + group = "agg_funcs", + since = "4.0.0") +case class ListAgg( + child: Expression, + delimiter: Expression = Literal.create(",", StringType), + orderExpression: Expression, + reverse: Boolean = false, + mutableAggBufferOffset: Int = 0, + inputAggBufferOffset: Int = 0) extends Collect[mutable.ArrayBuffer[Any]] Review Comment: Proxy mode can also be used. ########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala: ########## @@ -245,3 +249,98 @@ case class CollectTopK( override def withNewInputAggBufferOffset(newInputAggBufferOffset: Int): CollectTopK = copy(inputAggBufferOffset = newInputAggBufferOffset) } + +@ExpressionDescription( + usage = "_FUNC_(expr) - Returns the concatenated input values," + + " separated by the delimiter string.", + examples = """ + Examples: + > SELECT _FUNC_(col) FROM VALUES ('a'), ('b'), ('c') AS tab(col); + a,b,c + > SELECT _FUNC_(col) FROM VALUES (NULL), ('a'), ('b') AS tab(col); + a,b + > SELECT _FUNC_(col) FROM VALUES ('a'), ('a') AS tab(col); + a,a + > SELECT _FUNC_(DISTINCT col) FROM VALUES ('a'), ('a'), ('b') AS tab(col); + a,b + > SELECT _FUNC_(col, '|') FROM VALUES ('a'), ('b') AS tab(col); + a|b + > SELECT _FUNC_(col) FROM VALUES (NULL), (NULL) AS tab(col); + "" + """, + group = "agg_funcs", + since = "4.0.0") +case class ListAgg( + child: Expression, + delimiter: Expression = Literal.create(",", StringType), + orderExpression: Expression, + reverse: Boolean = false, + mutableAggBufferOffset: Int = 0, + inputAggBufferOffset: Int = 0) extends Collect[mutable.ArrayBuffer[Any]] Review Comment: I think we should avoid change `Collect`. We can declare a field of `CollectList` and `ListAgg` extended `BinaryLike[Expression]` -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org