refactor: add agg_ops.var_op for the sqlglot compiler

Author: chelsea-lin

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

@@ -347,3 +347,17 @@ def _(
         expression=shifted,
         unit=sge.Identifier(this="MICROSECOND"),
     )
+
+
+@UNARY_OP_REGISTRATION.register(agg_ops.VarOp)
+def _(
+    op: agg_ops.VarOp,
+    column: typed_expr.TypedExpr,
+    window: typing.Optional[window_spec.WindowSpec] = None,
+) -> sge.Expression:
+    expr = column.expr
+    if column.dtype == dtypes.BOOL_DTYPE:
+        expr = sge.Cast(this=expr, to="INT64")
+
+    expr = sge.func("VAR_SAMP", expr)
+    return apply_window_if_present(expr, window)

tests/system/small/engines/test_aggregation.py

@@ -111,7 +111,7 @@ def test_engines_unary_aggregates(
     assert_equivalence_execution(node, REFERENCE_ENGINE, engine)
 
 
-@pytest.mark.parametrize("engine", ["polars", "bq"], indirect=True)
+@pytest.mark.parametrize("engine", ["polars", "bq", "bq-sqlglot"], indirect=True)
 @pytest.mark.parametrize(
     "op",
     [agg_ops.std_op, agg_ops.var_op, agg_ops.PopVarOp()],

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

@@ -0,0 +1,15 @@
+WITH `bfcte_0` AS (
+  SELECT
+    `bool_col` AS `bfcol_0`,
+    `int64_col` AS `bfcol_1`
+  FROM `bigframes-dev`.`sqlglot_test`.`scalar_types`
+), `bfcte_1` AS (
+  SELECT
+    VARIANCE(`bfcol_1`) AS `bfcol_4`,
+    VARIANCE(CAST(`bfcol_0` AS INT64)) AS `bfcol_5`
+  FROM `bfcte_0`
+)
+SELECT
+  `bfcol_4` AS `int64_col`,
+  `bfcol_5` AS `bool_col`
+FROM `bfcte_1`

tests/unit/core/compile/sqlglot/aggregations/snapshots/test_unary_compiler/test_var/window_out.sql

@@ -0,0 +1,13 @@
+WITH `bfcte_0` AS (
+  SELECT
+    `int64_col` AS `bfcol_0`
+  FROM `bigframes-dev`.`sqlglot_test`.`scalar_types`
+), `bfcte_1` AS (
+  SELECT
+    *,
+    CASE WHEN `bfcol_0` IS NULL THEN NULL ELSE VARIANCE(`bfcol_0`) OVER () END AS `bfcol_1`
+  FROM `bfcte_0`
+)
+SELECT
+  `bfcol_1` AS `agg_int64`
+FROM `bfcte_1`

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

@@ -502,3 +502,25 @@ def test_time_series_diff(scalar_types_df: bpd.DataFrame, snapshot):
     )
     sql = _apply_unary_window_op(bf_df, op, window, "diff_time")
     snapshot.assert_match(sql, "out.sql")
+
+
+def test_var(scalar_types_df: bpd.DataFrame, snapshot):
+    col_names = ["int64_col", "bool_col"]
+    bf_df = scalar_types_df[col_names]
+
+    agg_ops_map = {
+        "int64_col": agg_ops.VarOp().as_expr("int64_col"),
+        "bool_col": agg_ops.VarOp().as_expr("bool_col"),
+    }
+    sql = _apply_unary_agg_ops(
+        bf_df, list(agg_ops_map.values()), list(agg_ops_map.keys())
+    )
+    snapshot.assert_match(sql, "out.sql")
+
+    # Window tests
+    col_name = "int64_col"
+    bf_df_int = scalar_types_df[[col_name]]
+    agg_expr = agg_ops.VarOp().as_expr(col_name)
+    window = window_spec.WindowSpec(ordering=(ordering.descending_over(col_name),))
+    sql_window = _apply_unary_window_op(bf_df_int, agg_expr, window, "agg_int64")
+    snapshot.assert_match(sql_window, "window_out.sql")