diff options
author | Richard van der Hoff <1389908+richvdh@users.noreply.github.com> | 2018-12-04 11:55:52 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2018-12-04 11:55:52 +0100 |
commit | ecc23188f4b88bef1f08a8fac2779720308863d6 (patch) | |
tree | b41761dfa8f6acab760c3a9deb78dd0afa34d22f /synapse/util | |
parent | Merge pull request #4244 from aaronraimist/drop-sent-txt (diff) | |
download | synapse-ecc23188f4b88bef1f08a8fac2779720308863d6.tar.xz |
Fix UnicodeDecodeError when postgres is not configured in english (#4253)
This is a bit of a half-assed effort at fixing https://github.com/matrix-org/synapse/issues/4252. Fundamentally the right answer is to drop support for Python 2.
Diffstat (limited to 'synapse/util')
-rw-r--r-- | synapse/util/stringutils.py | 39 |
1 files changed, 38 insertions, 1 deletions
diff --git a/synapse/util/stringutils.py b/synapse/util/stringutils.py index 6f318c6a29..fdcb375f95 100644 --- a/synapse/util/stringutils.py +++ b/synapse/util/stringutils.py @@ -16,7 +16,8 @@ import random import string -from six import PY3 +import six +from six import PY2, PY3 from six.moves import range _string_with_symbols = ( @@ -71,3 +72,39 @@ def to_ascii(s): return s.encode("ascii") except UnicodeEncodeError: return s + + +def exception_to_unicode(e): + """Helper function to extract the text of an exception as a unicode string + + Args: + e (Exception): exception to be stringified + + Returns: + unicode + """ + # urgh, this is a mess. The basic problem here is that psycopg2 constructs its + # exceptions with PyErr_SetString, with a (possibly non-ascii) argument. str() will + # then produce the raw byte sequence. Under Python 2, this will then cause another + # error if it gets mixed with a `unicode` object, as per + # https://github.com/matrix-org/synapse/issues/4252 + + # First of all, if we're under python3, everything is fine because it will sort this + # nonsense out for us. + if not PY2: + return str(e) + + # otherwise let's have a stab at decoding the exception message. We'll circumvent + # Exception.__str__(), which would explode if someone raised Exception(u'non-ascii') + # and instead look at what is in the args member. + + if len(e.args) == 0: + return u"" + elif len(e.args) > 1: + return six.text_type(repr(e.args)) + + msg = e.args[0] + if isinstance(msg, bytes): + return msg.decode('utf-8', errors='replace') + else: + return msg |