stringSplit

Author: chelsea-lin

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

@@ -681,6 +681,11 @@ def _(op: ops.base_ops.UnaryOp, expr: TypedExpr) -> sge.Expression:
     )
 
 
+@UNARY_OP_REGISTRATION.register(ops.StringSplitOp)
+def _(op: ops.StringSplitOp, expr: TypedExpr) -> sge.Expression:
+    return sge.Split(this=expr.expr, expression=sge.convert(op.pat))
+
+
 @UNARY_OP_REGISTRATION.register(ops.StrGetOp)
 def _(op: ops.StrGetOp, expr: TypedExpr) -> sge.Expression:
     return sge.Substring(

tests/unit/core/compile/sqlglot/expressions/snapshots/test_unary_compiler/test_string_split/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
+    *,
+    SPLIT(`bfcol_0`, ',') 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

@@ -674,6 +674,12 @@ def test_sinh(scalar_types_df: bpd.DataFrame, snapshot):
     snapshot.assert_match(sql, "out.sql")
 
 
+def test_string_split(scalar_types_df: bpd.DataFrame, snapshot):
+    bf_df = scalar_types_df[["string_col"]]
+    sql = _apply_unary_op(bf_df, ops.StringSplitOp(pat=","), "string_col")
+    snapshot.assert_match(sql, "out.sql")
+
+
 def test_tan(scalar_types_df: bpd.DataFrame, snapshot):
     bf_df = scalar_types_df[["float64_col"]]
     sql = _apply_unary_op(bf_df, ops.tan_op, "float64_col")