implement ZfillOp

Author: chelsea-lin

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

@@ -838,3 +838,31 @@ def _(op: ops.base_ops.UnaryOp, expr: TypedExpr) -> sge.Expression:
 @UNARY_OP_REGISTRATION.register(ops.year_op)
 def _(op: ops.base_ops.UnaryOp, expr: TypedExpr) -> sge.Expression:
     return sge.Extract(this=sge.Identifier(this="YEAR"), expression=expr.expr)
+
+
+@UNARY_OP_REGISTRATION.register(ops.ZfillOp)
+def _(op: ops.ZfillOp, expr: TypedExpr) -> sge.Expression:
+    return sge.Case(
+        ifs=[
+            sge.If(
+                this=sge.EQ(
+                    this=sge.Substring(
+                        this=expr.expr, start=sge.convert(1), length=sge.convert(1)
+                    ),
+                    expression=sge.convert("-"),
+                ),
+                true=sge.Concat(
+                    expressions=[
+                        sge.convert("-"),
+                        sge.func(
+                            "LPAD",
+                            sge.Substring(this=expr.expr, start=sge.convert(1)),
+                            sge.convert(op.width - 1),
+                            sge.convert("0"),
+                        ),
+                    ]
+                ),
+            )
+        ],
+        default=sge.func("LPAD", expr.expr, sge.convert(op.width), sge.convert("0")),
+    )

tests/unit/core/compile/sqlglot/expressions/snapshots/test_unary_compiler/test_zfill/out.sql

@@ -0,0 +1,17 @@
+WITH `bfcte_0` AS (
+  SELECT
+    `string_col` AS `bfcol_0`
+  FROM `bigframes-dev`.`sqlglot_test`.`scalar_types`
+), `bfcte_1` AS (
+  SELECT
+    *,
+    CASE
+      WHEN SUBSTRING(`bfcol_0`, 1, 1) = '-'
+      THEN CONCAT('-', LPAD(SUBSTRING(`bfcol_0`, 1), 9, '0'))
+      ELSE LPAD(`bfcol_0`, 10, '0')
+    END AS `bfcol_1`
+  FROM `bfcte_0`
+)
+SELECT
+  `bfcol_1` AS `string_col`
+FROM `bfcte_1`

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

@@ -820,3 +820,9 @@ def test_year(scalar_types_df: bpd.DataFrame, snapshot):
     sql = _apply_unary_op(bf_df, ops.year_op, "timestamp_col")
 
     snapshot.assert_match(sql, "out.sql")
+
+
+def test_zfill(scalar_types_df: bpd.DataFrame, snapshot):
+    bf_df = scalar_types_df[["string_col"]]
+    sql = _apply_unary_op(bf_df, ops.ZfillOp(width=10), "string_col")
+    snapshot.assert_match(sql, "out.sql")