Test fixups

Author: rhshadrach

pandas/io/sas/sas7bdat.py

@@ -22,6 +22,8 @@
 
 import numpy as np
 
+from pandas._config import get_option
+
 from pandas._libs.byteswap import (
     read_double_with_byteswap,
     read_float_with_byteswap,
@@ -699,6 +701,7 @@ def _chunk_to_dataframe(self) -> DataFrame:
         rslt = {}
 
         js, jb = 0, 0
+        infer_string = get_option("future.infer_string")
         for j in range(self.column_count):
             name = self.column_names[j]
 
@@ -715,6 +718,9 @@ def _chunk_to_dataframe(self) -> DataFrame:
                 rslt[name] = pd.Series(self._string_chunk[js, :], index=ix, copy=False)
                 if self.convert_text and (self.encoding is not None):
                     rslt[name] = self._decode_string(rslt[name].str)
+                    if infer_string:
+                        rslt[name] = rslt[name].astype("str")
+
                 js += 1
             else:
                 self.close()

pandas/tests/io/sas/test_sas7bdat.py

@@ -240,11 +240,13 @@ def test_zero_variables(datapath):
         pd.read_sas(fname)
 
 
-def test_zero_rows(datapath):
+@pytest.mark.parametrize("encoding", [None, "utf8"])
+def test_zero_rows(datapath, encoding):
     # GH 18198
     fname = datapath("io", "sas", "data", "zero_rows.sas7bdat")
-    result = pd.read_sas(fname)
-    expected = pd.DataFrame([{"char_field": "a", "num_field": 1.0}]).iloc[:0]
+    result = pd.read_sas(fname, encoding=encoding)
+    str_value = b"a" if encoding is None else "a"
+    expected = pd.DataFrame([{"char_field": str_value, "num_field": 1.0}]).iloc[:0]
     tm.assert_frame_equal(result, expected)
 
 
@@ -403,7 +405,7 @@ def test_0x40_control_byte(datapath):
     fname = datapath("io", "sas", "data", "0x40controlbyte.sas7bdat")
     df = pd.read_sas(fname, encoding="ascii")
     fname = datapath("io", "sas", "data", "0x40controlbyte.csv")
-    df0 = pd.read_csv(fname, dtype="object")
+    df0 = pd.read_csv(fname, dtype="str")
     tm.assert_frame_equal(df, df0)