aboutsummaryrefslogtreecommitdiff
path: root/python/olm
diff options
context:
space:
mode:
authorDamir Jelić <poljar@termina.org.uk>2019-06-18 13:38:22 +0200
committerDamir Jelić <poljar@termina.org.uk>2019-06-18 13:44:22 +0200
commite1a4e6ebf1568935a57ba8cec48e43dd7c1ebcd3 (patch)
tree069b4d432dd9305bde33391aea9727d30caed246 /python/olm
parent327d6ac0eb788429dcbb0b012037ea30020a14fe (diff)
compat: Add a method to convert bytes to a string that handles unicode errors.
Diffstat (limited to 'python/olm')
-rw-r--r--python/olm/_compat.py23
1 files changed, 23 insertions, 0 deletions
diff --git a/python/olm/_compat.py b/python/olm/_compat.py
index 91e4d1b..d81bdb5 100644
--- a/python/olm/_compat.py
+++ b/python/olm/_compat.py
@@ -18,6 +18,8 @@
from builtins import bytes, str
from typing import AnyStr
+from future.utils import bytes_to_native_str, native_str
+
try:
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.
+
+ Args:
+ byte_string (bytes): The bytestring that will be converted to a native
+ string.
+ 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.
+ """
+ try:
+ return native_str(byte_string, errors=errors)
+ except TypeError:
+ return bytes(byte_string).decode(errors=errors)