(Re)Support old syntax for approx_percentile_cont and approx_percentile_cont_with_weight (apache#16999)

* Add sqllogictests

* Allow both new and old sytanx for approx_percentile_cont and approx_percentile_cont_with_weight

* Update docs

* Add documentation and more tests

Author: alamb

datafusion/functions-aggregate/src/approx_percentile_cont.rs

@@ -91,7 +91,24 @@ pub fn approx_percentile_cont(
 +-----------------------------------------------------------------------+
 | 65.0                                                                  |
 +-----------------------------------------------------------------------+
-```"#,
+```
+An alternate syntax is also supported:
+```sql
+> SELECT approx_percentile_cont(column_name, 0.75) FROM table_name;
++-----------------------------------------------+
+| approx_percentile_cont(column_name, 0.75)     |
++-----------------------------------------------+
+| 65.0                                          |
++-----------------------------------------------+
+
+> SELECT approx_percentile_cont(column_name, 0.75, 100) FROM table_name;
++----------------------------------------------------------+
+| approx_percentile_cont(column_name, 0.75, 100)           |
++----------------------------------------------------------+
+| 65.0                                                     |
++----------------------------------------------------------+
+```
+"#,
     standard_argument(name = "expression",),
     argument(
         name = "percentile",

datafusion/functions-aggregate/src/approx_percentile_cont_with_weight.rs

@@ -85,6 +85,16 @@ pub fn approx_percentile_cont_with_weight(
 +--------------------------------------------------------------------------------------------------+
 | 78.5                                                                                             |
 +--------------------------------------------------------------------------------------------------+
+```
+An alternative syntax is also supported:
+
+```sql
+> SELECT approx_percentile_cont_with_weight(column_name, weight_column, 0.90) FROM table_name;
++--------------------------------------------------+
+| approx_percentile_cont_with_weight(column_name, weight_column, 0.90) |
++--------------------------------------------------+
+| 78.5                                             |
++--------------------------------------------------+
 ```"#,
     standard_argument(name = "expression", prefix = "The"),
     argument(

datafusion/sql/src/expr/function.rs

@@ -380,10 +380,6 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
         } else {
             // User defined aggregate functions (UDAF) have precedence in case it has the same name as a scalar built-in function
             if let Some(fm) = self.context_provider.get_aggregate_meta(&name) {
-                if fm.is_ordered_set_aggregate() && within_group.is_empty() {
-                    return plan_err!("WITHIN GROUP clause is required when calling ordered set aggregate function({})", fm.name());
-                }
-
                 if null_treatment.is_some() && !fm.supports_null_handling_clause() {
                     return plan_err!(
                         "[IGNORE | RESPECT] NULLS are not permitted for {}",
@@ -403,7 +399,8 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
                         None,
                     )?;
 
-                    // add target column expression in within group clause to function arguments
+                    // Add the WITHIN GROUP ordering expressions to the front of the argument list
+                    // So function(arg) WITHIN GROUP (ORDER BY x) becomes function(x, arg)
                     if !within_group.is_empty() {
                         args = within_group
                             .iter()

datafusion/sqllogictest/test_files/aggregate.slt

@@ -1287,7 +1287,7 @@ SELECT approx_distinct(c9) AS a, approx_distinct(c9) AS b FROM aggregate_test_10
 ## Column `c12` is omitted due to a large relative error (~10%) due to the small
 ## float values.
 
-#csv_query_approx_percentile_cont (c2)
+# csv_query_approx_percentile_cont (c2)
 query B
 SELECT (ABS(1 - CAST(approx_percentile_cont(0.1) WITHIN GROUP (ORDER BY c2) AS DOUBLE) / 1.0) < 0.05) AS q FROM aggregate_test_100
 ----
@@ -1303,6 +1303,23 @@ SELECT (ABS(1 - CAST(approx_percentile_cont(0.9) WITHIN GROUP (ORDER BY c2) AS D
 ----
 true
 
+
+# csv_query_approx_percentile_cont (c2, alternate syntax, should be the same as above)
+query B
+SELECT (ABS(1 - CAST(approx_percentile_cont(c2, 0.1) AS DOUBLE) / 1.0) < 0.05) AS q FROM aggregate_test_100
+----
+true
+
+query B
+SELECT (ABS(1 - CAST(approx_percentile_cont(c2, 0.5) AS DOUBLE) / 3.0) < 0.05) AS q FROM aggregate_test_100
+----
+true
+
+query B
+SELECT (ABS(1 - CAST(approx_percentile_cont(c2, 0.9) AS DOUBLE) / 5.0) < 0.05) AS q FROM aggregate_test_100
+----
+true
+
 # csv_query_approx_percentile_cont (c3)
 query B
 SELECT (ABS(1 - CAST(approx_percentile_cont(0.1) WITHIN GROUP (ORDER BY c3) AS DOUBLE) / -95.3) < 0.05) AS q FROM aggregate_test_100
@@ -1743,6 +1760,17 @@ c 122
 d 124
 e 115
 
+
+# csv_query_approx_percentile_cont_with_weight (should be the same as above)
+query TI
+SELECT c1, approx_percentile_cont(c3, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
 query TI
 SELECT c1, approx_percentile_cont(0.95) WITHIN GROUP (ORDER BY c3 DESC) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
 ----
@@ -1762,6 +1790,17 @@ c 122
 d 124
 e 115
 
+# csv_query_approx_percentile_cont_with_weight alternate syntax
+query TI
+SELECT c1, approx_percentile_cont_with_weight(c3, 1, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
+
 query TI
 SELECT c1, approx_percentile_cont_with_weight(1, 0.95) WITHIN GROUP (ORDER BY c3 DESC) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
 ----

docs/source/user-guide/sql/aggregate_functions.md

@@ -860,6 +860,24 @@ approx_percentile_cont(percentile [, centroids]) WITHIN GROUP (ORDER BY expressi
 +-----------------------------------------------------------------------+
 ```
 
+An alternate syntax is also supported:
+
+```sql
+> SELECT approx_percentile_cont(column_name, 0.75) FROM table_name;
++-----------------------------------------------+
+| approx_percentile_cont(column_name, 0.75)     |
++-----------------------------------------------+
+| 65.0                                          |
++-----------------------------------------------+
+
+> SELECT approx_percentile_cont(column_name, 0.75, 100) FROM table_name;
++----------------------------------------------------------+
+| approx_percentile_cont(column_name, 0.75, 100)           |
++----------------------------------------------------------+
+| 65.0                                                     |
++----------------------------------------------------------+
+```
+
 ### `approx_percentile_cont_with_weight`
 
 Returns the weighted approximate percentile of input values using the t-digest algorithm.
@@ -891,3 +909,14 @@ approx_percentile_cont_with_weight(weight, percentile [, centroids]) WITHIN GROU
 | 78.5                                                                                             |
 +--------------------------------------------------------------------------------------------------+
 ```
+
+An alternative syntax is also supported:
+
+```sql
+> SELECT approx_percentile_cont_with_weight(column_name, weight_column, 0.90) FROM table_name;
++--------------------------------------------------+
+| approx_percentile_cont_with_weight(column_name, weight_column, 0.90) |
++--------------------------------------------------+
+| 78.5                                             |
++--------------------------------------------------+
+```