refactor: add agg_ops.ApproxTopCountOp to sqlglot compiler

Author: chelsea-lin

bigframes/core/compile/sqlglot/aggregations/unary_compiler.py

@@ -58,6 +58,17 @@ def _(
     )
 
 
+@UNARY_OP_REGISTRATION.register(agg_ops.ApproxTopCountOp)
+def _(
+    op: agg_ops.ApproxTopCountOp,
+    column: typed_expr.TypedExpr,
+    window: typing.Optional[window_spec.WindowSpec] = None,
+) -> sge.Expression:
+    if window is not None:
+        raise NotImplementedError("Approx top count with windowing is not supported.")
+    return sge.func("APPROX_TOP_COUNT", column.expr, sge.convert(op.number))
+
+
 @UNARY_OP_REGISTRATION.register(agg_ops.CountOp)
 def _(
     op: agg_ops.CountOp,

tests/unit/core/compile/sqlglot/aggregations/snapshots/test_unary_compiler/test_approx_top_count/out.sql

@@ -0,0 +1,12 @@
+WITH `bfcte_0` AS (
+  SELECT
+    `int64_col` AS `bfcol_0`
+  FROM `bigframes-dev`.`sqlglot_test`.`scalar_types`
+), `bfcte_1` AS (
+  SELECT
+    APPROX_TOP_COUNT(`bfcol_0`, 10) AS `bfcol_1`
+  FROM `bfcte_0`
+)
+SELECT
+  `bfcol_1` AS `int64_col`
+FROM `bfcte_1`

tests/unit/core/compile/sqlglot/aggregations/test_unary_compiler.py

@@ -53,6 +53,15 @@ def test_approx_quartiles(scalar_types_df: bpd.DataFrame, snapshot):
     snapshot.assert_match(sql, "out.sql")
 
 
+def test_approx_top_count(scalar_types_df: bpd.DataFrame, snapshot):
+    col_name = "int64_col"
+    bf_df = scalar_types_df[[col_name]]
+    agg_expr = agg_ops.ApproxTopCountOp(number=10).as_expr(col_name)
+    sql = _apply_unary_agg_ops(bf_df, [agg_expr], [col_name])
+
+    snapshot.assert_match(sql, "out.sql")
+
+
 def test_count(scalar_types_df: bpd.DataFrame, snapshot):
     col_name = "int64_col"
     bf_df = scalar_types_df[[col_name]]