MapOp compiler

Author: chelsea-lin

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

@@ -455,6 +455,17 @@ def _(op: ops.base_ops.UnaryOp, expr: TypedExpr) -> sge.Expression:
     return sge.Lower(this=expr.expr)
 
 
+@UNARY_OP_REGISTRATION.register(ops.MapOp)
+def _(op: ops.MapOp, expr: TypedExpr) -> sge.Expression:
+    return sge.Case(
+        this=expr.expr,
+        ifs=[
+            sge.If(this=sge.convert(key), true=sge.convert(value))
+            for key, value in op.mappings
+        ],
+    )
+
+
 @UNARY_OP_REGISTRATION.register(ops.minute_op)
 def _(op: ops.base_ops.UnaryOp, expr: TypedExpr) -> sge.Expression:
     return sge.Extract(this=sge.Identifier(this="MINUTE"), expression=expr.expr)

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

@@ -0,0 +1,13 @@
+WITH `bfcte_0` AS (
+  SELECT
+    `string_col` AS `bfcol_0`
+  FROM `bigframes-dev`.`sqlglot_test`.`scalar_types`
+), `bfcte_1` AS (
+  SELECT
+    *,
+    CASE `bfcol_0` WHEN 'value1' THEN 'mapped1' 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

@@ -391,6 +391,15 @@ def test_lower(scalar_types_df: bpd.DataFrame, snapshot):
     snapshot.assert_match(sql, "out.sql")
 
 
+def test_map(scalar_types_df: bpd.DataFrame, snapshot):
+    bf_df = scalar_types_df[["string_col"]]
+    sql = _apply_unary_op(
+        bf_df, ops.MapOp(mappings=(("value1", "mapped1"),)), "string_col"
+    )
+
+    snapshot.assert_match(sql, "out.sql")
+
+
 def test_lstrip(scalar_types_df: bpd.DataFrame, snapshot):
     bf_df = scalar_types_df[["string_col"]]
     sql = _apply_unary_op(bf_df, ops.StrLstripOp(" "), "string_col")