Allow for byte decoding of windows codespace 1252 (#100)

bapsflib/utils/__init__.py

@@ -24,6 +24,9 @@ def _bytes_to_str(string: Union[bytes, str]) -> str:
         return string
 
     if isinstance(string, bytes):
-        return str(string, "utf-8")
+        try:
+            return str(string, "utf-8")
+        except UnicodeDecodeError:
+            return str(string, "cp1252")
 
     raise TypeError(f"Argument 'string' is not of type str or bytes, got {type(string)}.")

bapsflib/utils/tests/test_bytes_to_str.py

@@ -15,6 +15,8 @@ def test_valid_vals(self):
         conditions = [
             ("Hello", "Hello"),
             (b"Goodbye", "Goodbye"),
+            (b"doesn't", "doesn't"),
+            (b"doesn\x92t", "doesn’t"),
         ]
         for inputs, expected in conditions:
             with self.subTest(inputs=inputs, expected=expected):

changelog/100.bugfix.rst

@@ -0,0 +1,3 @@
+Updated :func:`bapsflib.utils._bytes_to_str` to handle byte strings
+that my have been encoded using
+`Windows codespace 1252 <https://en.wikipedia.org/wiki/Windows-1252>`_.

docs/conf.py

@@ -106,7 +106,7 @@
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = "en"
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.