Commit e1a4e6eb authored by poljar's avatar poljar
Browse files

compat: Add a method to convert bytes to a string that handles unicode errors.

parent 327d6ac0
......@@ -18,6 +18,8 @@
from builtins import bytes, str
from typing import AnyStr
from future.utils import bytes_to_native_str, native_str
import secrets
URANDOM = secrets.token_bytes # pragma: no cover
......@@ -44,3 +46,24 @@ def to_bytes(string):
return bytes(string, "utf-8")
raise TypeError("Invalid type {}".format(type(string)))
def to_native_str(byte_string, errors="replace"):
"""Turn a byte string into a native string decoding it as UTF-8.
byte_string (bytes): The bytestring that will be converted to a native
errors (str, optional): The error handling scheme that should be used
to handle unicode decode errors. Can be one of "strict" (raise an
UnicodeDecodeError exception, "ignore" (remove the offending
characters), "replace" (replace the offending character with
U+FFFD), "xmlcharrefreplace" as well as any other name registered
with codecs.register_error that can handle UnicodeEncodeErrors.
Returns the decoded native string.
return native_str(byte_string, errors=errors)
except TypeError:
return bytes(byte_string).decode(errors=errors)
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment