Add edge case tests: empty string, zero/False, pd.NA, literal NaN string, datetime in DataFrame

Author: Saurabh Badenkal

tests/unit/test_pandas_helpers.py

@@ -243,6 +243,51 @@ def test_multiple_rows_na_as_null(self):
         self.assertEqual(result[0], {"name": "A", "phone": None})
         self.assertEqual(result[1], {"name": None, "phone": "555-0200"})
 
+    def test_empty_string_preserved(self):
+        """Empty string is kept in output, not treated as missing."""
+        df = pd.DataFrame([{"name": ""}])
+        result = dataframe_to_records(df)
+        self.assertIn("name", result[0])
+        self.assertEqual(result[0]["name"], "")
+
+    def test_zero_and_false_preserved(self):
+        """Zero and False are kept in output, not treated as missing."""
+        df = pd.DataFrame([{"count": 0, "score": 0.0, "active": False}])
+        result = dataframe_to_records(df)
+        self.assertEqual(result[0]["count"], 0)
+        self.assertEqual(result[0]["score"], 0.0)
+        self.assertIs(result[0]["active"], False)
+
+    def test_pd_na_nullable_int(self):
+        """pd.NA in nullable Int64 column is dropped by default."""
+        df = pd.DataFrame({"val": pd.array([1, pd.NA], dtype="Int64")})
+        result = dataframe_to_records(df)
+        self.assertEqual(result[0]["val"], 1)
+        self.assertNotIn("val", result[1])
+
+    def test_pd_na_nullable_int_as_null(self):
+        """pd.NA in nullable Int64 column becomes None with na_as_null=True."""
+        df = pd.DataFrame({"val": pd.array([1, pd.NA], dtype="Int64")})
+        result = dataframe_to_records(df, na_as_null=True)
+        self.assertEqual(result[0]["val"], 1)
+        self.assertIsNone(result[1]["val"])
+
+    def test_datetime_in_dataframe(self):
+        """datetime.datetime values in a DataFrame are converted to ISO strings."""
+        import datetime
+
+        dt = datetime.datetime(2024, 6, 15, 10, 30)
+        df = pd.DataFrame([{"createdon": dt}])
+        result = dataframe_to_records(df)
+        self.assertIsInstance(result[0]["createdon"], str)
+        self.assertIn("2024-06-15", result[0]["createdon"])
+
+    def test_literal_nan_string(self):
+        """Literal string 'NaN' is preserved, not treated as missing."""
+        df = pd.DataFrame([{"name": "NaN"}])
+        result = dataframe_to_records(df)
+        self.assertEqual(result[0]["name"], "NaN")
+
 
 if __name__ == "__main__":
     unittest.main()