refactor: add agg_ops.DiffOp

Author: chelsea-lin

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

@@ -107,6 +107,23 @@ def _(
     return apply_window_if_present(sge.func("DENSE_RANK"), window)
 
 
+@UNARY_OP_REGISTRATION.register(agg_ops.DiffOp)
+def _(
+    op: agg_ops.DiffOp,
+    column: typed_expr.TypedExpr,
+    window: typing.Optional[window_spec.WindowSpec] = None,
+) -> sge.Expression:
+    shift_op_impl = UNARY_OP_REGISTRATION[agg_ops.ShiftOp(0)]
+    shifted = shift_op_impl(agg_ops.ShiftOp(op.periods), column, window)
+    if column.dtype in (dtypes.BOOL_DTYPE, dtypes.INT_DTYPE, dtypes.FLOAT_DTYPE):
+        if column.dtype == dtypes.BOOL_DTYPE:
+            return sge.NEQ(this=column.expr, expression=shifted)
+        else:
+            return sge.Sub(this=column.expr, expression=shifted)
+    else:
+        raise TypeError(f"Cannot perform diff on type {column.dtype}")
+
+
 @UNARY_OP_REGISTRATION.register(agg_ops.MaxOp)
 def _(
     op: agg_ops.MaxOp,

tests/unit/core/compile/sqlglot/aggregations/snapshots/test_unary_compiler/test_diff/diff_bool.sql

@@ -0,0 +1,13 @@
+WITH `bfcte_0` AS (
+  SELECT
+    `bool_col` AS `bfcol_0`
+  FROM `bigframes-dev`.`sqlglot_test`.`scalar_types`
+), `bfcte_1` AS (
+  SELECT
+    *,
+    `bfcol_0` <> LAG(`bfcol_0`, 1) OVER (ORDER BY `bfcol_0` IS NULL ASC NULLS LAST, `bfcol_0` ASC NULLS LAST) AS `bfcol_1`
+  FROM `bfcte_0`
+)
+SELECT
+  `bfcol_1` AS `diff_bool`
+FROM `bfcte_1`

tests/unit/core/compile/sqlglot/aggregations/snapshots/test_unary_compiler/test_diff/diff_int.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
+    *,
+    `bfcol_0` - LAG(`bfcol_0`, 1) OVER (ORDER BY `bfcol_0` IS NULL ASC NULLS LAST, `bfcol_0` ASC NULLS LAST) AS `bfcol_1`
+  FROM `bfcte_0`
+)
+SELECT
+  `bfcol_1` AS `diff_int`
+FROM `bfcte_1`

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

@@ -126,6 +126,28 @@ def test_dense_rank(scalar_types_df: bpd.DataFrame, snapshot):
     snapshot.assert_match(sql, "out.sql")
 
 
+def test_diff(scalar_types_df: bpd.DataFrame, snapshot):
+    # Test integer
+    int_col = "int64_col"
+    bf_df_int = scalar_types_df[[int_col]]
+    window = window_spec.WindowSpec(ordering=(ordering.ascending_over(int_col),))
+    int_op = agg_exprs.UnaryAggregation(
+        agg_ops.DiffOp(periods=1), expression.deref(int_col)
+    )
+    int_sql = _apply_unary_window_op(bf_df_int, int_op, window, "diff_int")
+    snapshot.assert_match(int_sql, "diff_int.sql")
+
+    # Test boolean
+    bool_col = "bool_col"
+    bf_df_bool = scalar_types_df[[bool_col]]
+    window = window_spec.WindowSpec(ordering=(ordering.ascending_over(bool_col),))
+    bool_op = agg_exprs.UnaryAggregation(
+        agg_ops.DiffOp(periods=1), expression.deref(bool_col)
+    )
+    bool_sql = _apply_unary_window_op(bf_df_bool, bool_op, window, "diff_bool")
+    snapshot.assert_match(bool_sql, "diff_bool.sql")
+
+
 def test_max(scalar_types_df: bpd.DataFrame, snapshot):
     col_name = "int64_col"
     bf_df = scalar_types_df[[col_name]]