def test_unquote_bad():
testv = (
# in error
('x"zzz"', 'no starting "'),
('"zzz', 'no closing "'),
('"\\', 'unexpected EOL after \\'),
('"\\x', 'unexpected EOL after \\x'),
('"\\x0', 'unexpected EOL after \\x'),
('"\\z"', 'invalid escape \\z'),
)
for tin, err in testv:
with raises(ValueError) as exc:
unquote(tin)
assert exc.value.args == (err, )
def test_unquote_noncanon():
testv = (
# quoted w/o " unquoted
(r'\a', "\x07"),
(r'\b', "\x08"),
(r'\v', "\x0b"),
(r'\f', "\x0c"),
)
for tquoted, tunquoted in testv:
q = '"' + tquoted + '"'
assert unquote(q) == tunquoted
def test_quote():
testv = (
# in quoted without leading/trailing "
('', r""),
(byterange(0, 32),
br'\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f'
),
('\'', r"'"),
('"', r"\""),
('ab c\ndef', r"ab c\ndef"),
('a\'c\ndef', r"a'c\ndef"),
('a\"c\ndef', r"a\"c\ndef"),
(u'a\"c\ndef', u"a\\\"c\\ndef"),
(b'a\"c\ndef', br'a\"c\ndef'),
('привет\nмир', r"привет\nмир"),
(u'привет\nмир', u"привет\\nмир"),
# invalid utf-8
(b"\xd0a", br"\xd0a"),
# non-printable utf-8
(u"\u007f\u0080\u0081\u0082\u0083\u0084\u0085\u0086\u0087",
u"\\x7f\\xc2\\x80\\xc2\\x81\\xc2\\x82\\xc2\\x83\\xc2\\x84\\xc2\\x85\\xc2\\x86\\xc2\\x87"
),
)
for tin, tquoted in testv:
# quote(in) == quoted
# in = unquote(quoted)
q = b'"' if isinstance(tquoted, bytes) else '"'
tail = b'123' if isinstance(tquoted, bytes) else '123'
tquoted = q + tquoted + q # add lead/trail "
assert quote(tin) == tquoted
assert unquote(tquoted) == tin
assert unquote_next(tquoted) == (tin, type(tin)())
assert unquote_next(tquoted + tail) == (tin, tail)
with raises(ValueError):
unquote(tquoted + tail)
# qq always gives str
assert qq(tin) == asstr(tquoted)
# also check how it works on complementary unicode/bytes input type
if isinstance(tin, bytes):
try:
tin = tin.decode('utf-8')
except UnicodeDecodeError:
# some inputs are not valid UTF-8
continue
tquoted = tquoted.decode('utf-8')
tail = tail.decode('utf-8')
else:
# tin was unicode
tin = tin.encode('utf-8')
tquoted = tquoted.encode('utf-8')
tail = tail.encode('utf-8')
assert quote(tin) == tquoted
assert unquote(tquoted) == tin
assert unquote_next(tquoted) == (tin, type(tin)())
assert unquote_next(tquoted + tail) == (tin, tail)
with raises(ValueError):
unquote(tquoted + tail)
# qq always gives str
assert qq(tin) == asstr(tquoted)
def get(name):
l = self._readline()
if l is None or not l.startswith(b'%s ' % name):
self._badline('no %s' % name)
return strconv.unquote(l[len(name) + 1:])