def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
python类unicode_escape_decode()的实例源码
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def test_empty(self):
self.assertEqual(codecs.unicode_escape_encode(u""), ("", 0))
self.assertEqual(codecs.unicode_escape_decode(""), (u"", 0))
def test_raw_decode(self):
decode = codecs.unicode_escape_decode
for b in range(256):
if b != ord('\\'):
self.assertEqual(decode(chr(b) + '0'), (unichr(b) + u'0', 2))
def test_escape_decode(self):
decode = codecs.unicode_escape_decode
check = coding_checker(self, decode)
check("[\\\n]", u"[]")
check(r'[\"]', u'["]')
check(r"[\']", u"[']")
check(r"[\\]", ur"[\]")
check(r"[\a]", u"[\x07]")
check(r"[\b]", u"[\x08]")
check(r"[\t]", u"[\x09]")
check(r"[\n]", u"[\x0a]")
check(r"[\v]", u"[\x0b]")
check(r"[\f]", u"[\x0c]")
check(r"[\r]", u"[\x0d]")
check(r"[\7]", u"[\x07]")
check(r"[\8]", ur"[\8]")
check(r"[\78]", u"[\x078]")
check(r"[\41]", u"[!]")
check(r"[\418]", u"[!8]")
check(r"[\101]", u"[A]")
check(r"[\1010]", u"[A0]")
check(r"[\x41]", u"[A]")
check(r"[\x410]", u"[A0]")
check(r"\u20ac", u"\u20ac")
check(r"\U0001d120", u"\U0001d120")
for b in range(256):
if chr(b) not in '\n"\'\\abtnvfr01234567xuUN':
check('\\' + chr(b), u'\\' + unichr(b))
def test_decode_errors(self):
decode = codecs.unicode_escape_decode
for c, d in ('x', 2), ('u', 4), ('U', 4):
for i in range(d):
self.assertRaises(UnicodeDecodeError, decode,
"\\" + c + "0"*i)
self.assertRaises(UnicodeDecodeError, decode,
"[\\" + c + "0"*i + "]")
data = "[\\" + c + "0"*i + "]\\" + c + "0"*i
self.assertEqual(decode(data, "ignore"), (u"[]", len(data)))
self.assertEqual(decode(data, "replace"),
(u"[\ufffd]\ufffd", len(data)))
self.assertRaises(UnicodeDecodeError, decode, r"\U00110000")
self.assertEqual(decode(r"\U00110000", "ignore"), (u"", 10))
self.assertEqual(decode(r"\U00110000", "replace"), (u"\ufffd", 10))
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def test_empty(self):
self.assertEqual(codecs.unicode_escape_encode(u""), ("", 0))
self.assertEqual(codecs.unicode_escape_decode(""), (u"", 0))
def test_raw_decode(self):
decode = codecs.unicode_escape_decode
for b in range(256):
if b != ord('\\'):
self.assertEqual(decode(chr(b) + '0'), (unichr(b) + u'0', 2))
def test_escape_decode(self):
decode = codecs.unicode_escape_decode
check = coding_checker(self, decode)
check("[\\\n]", u"[]")
check(r'[\"]', u'["]')
check(r"[\']", u"[']")
check(r"[\\]", ur"[\]")
check(r"[\a]", u"[\x07]")
check(r"[\b]", u"[\x08]")
check(r"[\t]", u"[\x09]")
check(r"[\n]", u"[\x0a]")
check(r"[\v]", u"[\x0b]")
check(r"[\f]", u"[\x0c]")
check(r"[\r]", u"[\x0d]")
check(r"[\7]", u"[\x07]")
check(r"[\8]", ur"[\8]")
check(r"[\78]", u"[\x078]")
check(r"[\41]", u"[!]")
check(r"[\418]", u"[!8]")
check(r"[\101]", u"[A]")
check(r"[\1010]", u"[A0]")
check(r"[\x41]", u"[A]")
check(r"[\x410]", u"[A0]")
check(r"\u20ac", u"\u20ac")
check(r"\U0001d120", u"\U0001d120")
for b in range(256):
if chr(b) not in '\n"\'\\abtnvfr01234567xuUN':
check('\\' + chr(b), u'\\' + unichr(b))
def test_decode_errors(self):
decode = codecs.unicode_escape_decode
for c, d in ('x', 2), ('u', 4), ('U', 4):
for i in range(d):
self.assertRaises(UnicodeDecodeError, decode,
"\\" + c + "0"*i)
self.assertRaises(UnicodeDecodeError, decode,
"[\\" + c + "0"*i + "]")
data = "[\\" + c + "0"*i + "]\\" + c + "0"*i
self.assertEqual(decode(data, "ignore"), (u"[]", len(data)))
self.assertEqual(decode(data, "replace"),
(u"[\ufffd]\ufffd", len(data)))
self.assertRaises(UnicodeDecodeError, decode, r"\U00110000")
self.assertEqual(decode(r"\U00110000", "ignore"), (u"", 10))
self.assertEqual(decode(r"\U00110000", "replace"), (u"\ufffd", 10))
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def to_str(x):
if isinstance(x, text_type):
return x
if isinstance(x, numbers.Number):
x = str(x)
elif x is None:
x = ''
return codecs.unicode_escape_decode(x)[0]
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def decode(self, input, final=False):
return codecs.unicode_escape_decode(input, self.errors)[0]
def test_unicode_escape(self):
# Escape-decoding an unicode string is supported ang gives the same
# result as decoding the equivalent ASCII bytes string.
self.assertEqual(codecs.unicode_escape_decode(r"\u1234"), ("\u1234", 6))
self.assertEqual(codecs.unicode_escape_decode(br"\u1234"), ("\u1234", 6))
self.assertEqual(codecs.raw_unicode_escape_decode(r"\u1234"), ("\u1234", 6))
self.assertEqual(codecs.raw_unicode_escape_decode(br"\u1234"), ("\u1234", 6))
self.assertRaises(UnicodeDecodeError, codecs.unicode_escape_decode, br"\U00110000")
self.assertEqual(codecs.unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10))
self.assertRaises(UnicodeDecodeError, codecs.raw_unicode_escape_decode, br"\U00110000")
self.assertEqual(codecs.raw_unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10))
