doctest: use print_function and convert bytes to unicode where needed

doctest: do not embed non-ascii characters in docstring Since the outer docstring is parsed as a unicode on Python 3, we have to either double-escape or construct non-ascii string from ascii string.

doctest: pass encoding name as system string

doctest: replace str() with bytes()

doctest: replace chr() with pycompat.bytechr()

doctest: replace .iteritems() with .items()

doctest: bulk-replace string literals with b'' for Python 3 Our code transformer can't rewrite string literals in docstrings, and I don't want to make the transformer more complex.

debuginstall: do not pass exception object to formatter (issue5676)

debuginstall: use codecs.lookup() to detect invalid encoding encoding.fromlocal() never tries to decode an ascii string since 853574db5b12, and there's no universal non-ascii string which can be decoded as any valid character set.

extensions: fix wrapcommand/function of class instance 5361771f9714 changed _updatewrapper() to copy the __name__ attribute, but not all callable objects has __name__. Spotted by loading mq with extdiff.