def utf_7_imap_decode(str):
"""TODO"""
shiftEnd = 0
shiftStart = find(str, "&")
if shiftStart == -1:
plusPos = find(str, "+", shiftEnd, shiftStart)
while plusPos != -1:
str = str[:plusPos + 1] + "-" + str[plusPos + 1:]
plusPos = find(str, "+", plusPos + 2, shiftStart)
while shiftStart != -1:
plusPos = find(str, "+", shiftEnd, shiftStart)
while plusPos != -1:
str = str[:plusPos + 1] + "-" + str[plusPos + 1:]
plusPos = find(str, "+", plusPos + 2, shiftStart)
shiftEnd = find(str, "-", shiftStart)
if shiftEnd != -1:
if (shiftEnd - shiftStart) == 1:
str = str[:shiftStart + 1] + str[shiftStart + 2:]
else:
str = str[:shiftStart] + "+" + str[shiftStart + 1:]
commaPos = find(str, ",", shiftStart, shiftEnd)
while commaPos != -1:
str = str[:commaPos] + "/" + str[commaPos + 1:]
commaPos = find(str, "+", commaPos + 2, shiftEnd)
shiftStart = find(str, "&", shiftEnd)
return utf_7_decode(str)
def utf7_decode(self, string):
"""
utf-7解码
"""
try:
result = codecs.utf_7_decode(string)[0]
return result
except TypeError:
raise TypeError("Data Type Error!")
def test_utf7_decode_incremental(self):
b = "abc\u20acxyz".encode('utf-7')
b += "abc\u20ad\u20aexyz".encode('utf-7')
b += "abc\u20af\u20b0\u20b1xyz".encode('utf-7')
# expected results generated by CPython 3.4
expected = [
('', 0),
('a', 1),
('ab', 2),
('abc', 3),
('abc', 3),
('abc', 3),
('abc', 3),
('abc', 3),
('abc€', 8),
('abc€x', 9),
('abc€xy', 10),
('abc€xyz', 11),
('abc€xyza', 12),
('abc€xyzab', 13),
('abc€xyzabc', 14),
('abc€xyzabc', 14),
('abc€xyzabc', 14),
('abc€xyzabc', 14),
('abc€xyzabc', 14),
('abc€xyzabc', 14),
('abc€xyzabc', 14),
('abc€xyzabc', 14),
('abc€xyzabc₭₮', 22),
('abc€xyzabc₭₮x', 23),
('abc€xyzabc₭₮xy', 24),
('abc€xyzabc₭₮xyz', 25),
('abc€xyzabc₭₮xyza', 26),
('abc€xyzabc₭₮xyzab', 27),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc', 28),
('abc€xyzabc₭₮xyzabc₯₰₱', 38),
('abc€xyzabc₭₮xyzabc₯₰₱x', 39),
('abc€xyzabc₭₮xyzabc₯₰₱xy', 40),
('abc€xyzabc₭₮xyzabc₯₰₱xyz', 41)
]
for i in range(len(b) + 1):
res = codecs.utf_7_decode(b[:i])
self.assertEqual(res, expected[i])
def test_codecs_builtins(self):
s = "abc"
encoded = codecs.utf_8_encode(s)
self.assertEqual(s, codecs.utf_8_decode(encoded[0])[0])
encoded = codecs.utf_7_encode(s)
self.assertEqual(s, codecs.utf_7_decode(encoded[0])[0])
encoded = codecs.utf_16_encode(s)
self.assertEqual(s, codecs.utf_16_decode(encoded[0])[0])
encoded = codecs.utf_16_le_encode(s)
self.assertEqual(s, codecs.utf_16_le_decode(encoded[0])[0])
encoded = codecs.utf_16_be_encode(s)
self.assertEqual(s, codecs.utf_16_be_decode(encoded[0])[0])
encoded = codecs.utf_32_encode(s)
self.assertEqual(s, codecs.utf_32_decode(encoded[0])[0])
encoded = codecs.utf_32_le_encode(s)
self.assertEqual(s, codecs.utf_32_le_decode(encoded[0])[0])
encoded = codecs.utf_32_be_encode(s)
self.assertEqual(s, codecs.utf_32_be_decode(encoded[0])[0])
encoded = codecs.utf_32_be_encode(s)
self.assertEqual(s, codecs.utf_32_be_decode(encoded[0])[0])
encoded = codecs.raw_unicode_escape_encode(s)
self.assertEqual(s, codecs.raw_unicode_escape_decode(encoded[0])[0])
encoded = codecs.unicode_escape_encode(s)
self.assertEqual(s, codecs.unicode_escape_decode(encoded[0])[0])
encoded = codecs.latin_1_encode(s)
self.assertEqual(s, codecs.latin_1_decode(encoded[0])[0])
encoded = codecs.ascii_encode(s)
self.assertEqual(s, codecs.ascii_decode(encoded[0])[0])
def test_utf_7_decode(self):
#sanity
new_str, size = codecs.utf_7_decode("abc")
self.assertEqual(new_str, u'abc')
self.assertEqual(size, 3)
def decode(input, errors='strict'):
return codecs.utf_7_decode(input, errors, True)
def decode(input, errors = 'strict'):
return codecs.utf_7_decode(input, errors, True)
def test_utf_7_decode(self):
#sanity
new_str, num_processed = codecs.utf_7_decode(b"abc")
self.assertEqual(new_str, 'abc')
self.assertEqual(num_processed, 3)
def _buffer_decode(self, input, errors, final):
return codecs.utf_7_decode(input, self.errors)
def _buffer_decode(self, input, errors, final):
return codecs.utf_7_decode(input, self.errors)
def test_utf_7_decode(self):
#sanity
new_str, size = codecs.utf_7_decode("abc")
self.assertEqual(new_str, u'abc')
self.assertEqual(size, 3)
def update_event(self, inp=-1):
self.set_output_val(
0, codecs.utf_7_decode(self.input(0), self.input(1),
self.input(2)))
