refactor: fix ops.len_op for array

Author: chelsea-lin

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

@@ -18,6 +18,7 @@
 
 import sqlglot.expressions as sge
 
+from bigframes import dtypes
 from bigframes import operations as ops
 from bigframes.core.compile.sqlglot.expressions.typed_expr import TypedExpr
 import bigframes.core.compile.sqlglot.scalar_compiler as scalar_compiler
@@ -195,6 +196,9 @@ def _(expr: TypedExpr) -> sge.Expression:
 
 @register_unary_op(ops.len_op)
 def _(expr: TypedExpr) -> sge.Expression:
+    if dtypes.is_array_like(expr.dtype):
+        return sge.func("ARRAY_LENGTH", expr.expr)
+
     return sge.Length(this=expr.expr)
 
 

tests/unit/core/compile/sqlglot/expressions/snapshots/test_string_ops/test_len_w_array/out.sql

@@ -0,0 +1,13 @@
+WITH `bfcte_0` AS (
+  SELECT
+    `int_list_col`
+  FROM `bigframes-dev`.`sqlglot_test`.`repeated_types`
+), `bfcte_1` AS (
+  SELECT
+    *,
+    ARRAY_LENGTH(`int_list_col`) AS `bfcol_1`
+  FROM `bfcte_0`
+)
+SELECT
+  `bfcol_1` AS `int_list_col`
+FROM `bfcte_1`

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

@@ -120,6 +120,14 @@ def test_len(scalar_types_df: bpd.DataFrame, snapshot):
     snapshot.assert_match(sql, "out.sql")
 
 
+def test_len_w_array(repeated_types_df: bpd.DataFrame, snapshot):
+    col_name = "int_list_col"
+    bf_df = repeated_types_df[[col_name]]
+    sql = utils._apply_ops_to_sql(bf_df, [ops.len_op.as_expr(col_name)], [col_name])
+
+    snapshot.assert_match(sql, "out.sql")
+
+
 def test_lower(scalar_types_df: bpd.DataFrame, snapshot):
     col_name = "string_col"
     bf_df = scalar_types_df[[col_name]]