From c53f154bb161a1e15a1efab0286a3480ad141eaf Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Tue, 27 Aug 2024 08:04:50 -0700
Subject: [PATCH] DEPR: na validation for startswith, endswith

---
 pandas/core/strings/object_array.py       | 16 +++++++++++++
 pandas/tests/strings/test_find_replace.py | 28 +++++++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/pandas/core/strings/object_array.py b/pandas/core/strings/object_array.py
index a754c57558adc6..c6b18d7049c578 100644
--- a/pandas/core/strings/object_array.py
+++ b/pandas/core/strings/object_array.py
@@ -156,10 +156,26 @@ def _str_contains(
 
     def _str_startswith(self, pat, na=None):
         f = lambda x: x.startswith(pat)
+        if not isna(na) and not isinstance(na, bool):
+            # GH#59561
+            warnings.warn(
+                "Allowing a non-bool 'na' in obj.str.startswith is deprecated "
+                "and will raise in a future version.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
         return self._str_map(f, na_value=na, dtype=np.dtype(bool))
 
     def _str_endswith(self, pat, na=None):
         f = lambda x: x.endswith(pat)
+        if not isna(na) and not isinstance(na, bool):
+            # GH#59561
+            warnings.warn(
+                "Allowing a non-bool 'na' in obj.str.endswith is deprecated "
+                "and will raise in a future version.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
         return self._str_map(f, na_value=na, dtype=np.dtype(bool))
 
     def _str_replace(
diff --git a/pandas/tests/strings/test_find_replace.py b/pandas/tests/strings/test_find_replace.py
index 407b51d4bbe491..c1dfe4d4a0b0b2 100644
--- a/pandas/tests/strings/test_find_replace.py
+++ b/pandas/tests/strings/test_find_replace.py
@@ -268,6 +268,34 @@ def test_contains_nan(any_string_dtype):
 # --------------------------------------------------------------------------------------
 
 
+def test_startswith_endswith_validate_na(any_string_dtype):
+    # GH#59615
+    ser = Series(
+        ["om", np.nan, "foo_nom", "nom", "bar_foo", np.nan, "foo"],
+        dtype=any_string_dtype,
+    )
+
+    dtype = ser.dtype
+    if (
+        isinstance(dtype, pd.StringDtype) and dtype.storage == "python"
+    ) or dtype == np.dtype("object"):
+        msg = "Allowing a non-bool 'na' in obj.str.startswith is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            ser.str.startswith("kapow", na="baz")
+        msg = "Allowing a non-bool 'na' in obj.str.endswith is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            ser.str.endswith("bar", na="baz")
+    else:
+        # TODO: don't surface pyarrow errors
+        import pyarrow as pa
+
+        msg = "Could not convert 'baz' with type str: tried to convert to boolean"
+        with pytest.raises(pa.lib.ArrowInvalid, match=msg):
+            ser.str.startswith("kapow", na="baz")
+        with pytest.raises(pa.lib.ArrowInvalid, match=msg):
+            ser.str.endswith("kapow", na="baz")
+
+
 @pytest.mark.parametrize("pat", ["foo", ("foo", "baz")])
 @pytest.mark.parametrize("dtype", ["object", "category"])
 @pytest.mark.parametrize("null_value", [None, np.nan, pd.NA])