fix: make start truly optional in regexp_count

Author: mesejo

python/datafusion/functions.py

@@ -817,7 +817,7 @@ def regexp_replace(
 
 
 def regexp_count(
-    string: Expr, pattern: Expr, start: Expr, flags: Expr | None = None
+    string: Expr, pattern: Expr, start: Expr | None = None, flags: Expr | None = None
 ) -> Expr:
     """Returns the number of matches in a string.
 
@@ -826,7 +826,7 @@ def regexp_count(
     """
     if flags is not None:
         flags = flags.expr
-    start = start.expr if start is not None else Expr.expr
+    start = (start if start is not None else Expr.literal(1)).expr
     return Expr(f.regexp_count(string.expr, pattern.expr, start, flags))
 
 

python/tests/test_functions.py

@@ -772,6 +772,10 @@ def test_array_function_obj_tests(stmt, py_expr):
             f.regexp_count(column("a"), literal("(ell|orl)"), literal(1)),
             pa.array([1, 1, 0], type=pa.int64()),
         ),
+        (
+            f.regexp_count(column("a"), literal("(ell|orl)")),
+            pa.array([1, 1, 0], type=pa.int64()),
+        ),
         (
             f.regexp_instr(column("a"), literal("(ell|orl)")),
             pa.array([2, 2, 0], type=pa.int64()),