Skip to content

refactor: support agg_ops.AllOp and AnyValueOp in sqlglot compiler #2127

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
chelsea-lin merged 2 commits into from
Sep 30, 2025
+62 −0
Merged

refactor: support agg_ops.AllOp and AnyValueOp in sqlglot compiler #2127

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bacab0e
refactor: support agg_ops.AnyValueOp in sqlglot compiler
chelsea-lin Sep 30, 2025
0a22f85
refactor: support agg_ops.All in sqlglot compiler
chelsea-lin Sep 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions bigframes/core/compile/sqlglot/aggregations/unary_compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,17 @@ def compile(
return UNARY_OP_REGISTRATION[op](op, column, window=window)


@UNARY_OP_REGISTRATION.register(agg_ops.AllOp)
def _(
op: agg_ops.AllOp,
column: typed_expr.TypedExpr,
window: typing.Optional[window_spec.WindowSpec] = None,
) -> sge.Expression:
# BQ will return null for empty column, result would be false in pandas.
result = apply_window_if_present(sge.func("LOGICAL_AND", column.expr), window)
return sge.func("IFNULL", result, sge.true())


@UNARY_OP_REGISTRATION.register(agg_ops.ApproxQuartilesOp)
def _(
op: agg_ops.ApproxQuartilesOp,
Expand Down Expand Up @@ -69,6 +80,15 @@ def _(
return sge.func("APPROX_TOP_COUNT", column.expr, sge.convert(op.number))


@UNARY_OP_REGISTRATION.register(agg_ops.AnyValueOp)
def _(
op: agg_ops.AnyValueOp,
column: typed_expr.TypedExpr,
window: typing.Optional[window_spec.WindowSpec] = None,
) -> sge.Expression:
return apply_window_if_present(sge.func("ANY_VALUE", column.expr), window)


@UNARY_OP_REGISTRATION.register(agg_ops.CountOp)
def _(
op: agg_ops.CountOp,
Expand Down
12 changes: 12 additions & 0 deletions tests/unit/core/compile/sqlglot/aggregations/snapshots/test_unary_compiler/test_all/out.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
WITH `bfcte_0` AS (
SELECT
`bool_col` AS `bfcol_0`
FROM `bigframes-dev`.`sqlglot_test`.`scalar_types`
), `bfcte_1` AS (
SELECT
COALESCE(LOGICAL_AND(`bfcol_0`), TRUE) AS `bfcol_1`
FROM `bfcte_0`
)
SELECT
`bfcol_1` AS `bool_col`
FROM `bfcte_1`
12 changes: 12 additions & 0 deletions ...it/core/compile/sqlglot/aggregations/snapshots/test_unary_compiler/test_any_value/out.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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
ANY_VALUE(`bfcol_0`) AS `bfcol_1`
FROM `bfcte_0`
)
SELECT
`bfcol_1` AS `int64_col`
FROM `bfcte_1`
18 changes: 18 additions & 0 deletions tests/unit/core/compile/sqlglot/aggregations/test_unary_compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,15 @@ def _apply_unary_window_op(
return sql


def test_all(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "bool_col"
bf_df = scalar_types_df[[col_name]]
agg_expr = agg_ops.AllOp().as_expr(col_name)
sql = _apply_unary_agg_ops(bf_df, [agg_expr], [col_name])

snapshot.assert_match(sql, "out.sql")


def test_approx_quartiles(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "int64_col"
bf_df = scalar_types_df[[col_name]]
Expand All @@ -87,6 +96,15 @@ def test_approx_top_count(scalar_types_df: bpd.DataFrame, snapshot):
snapshot.assert_match(sql, "out.sql")


def test_any_value(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "int64_col"
bf_df = scalar_types_df[[col_name]]
agg_expr = agg_ops.AnyValueOp().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]]
Expand Down