本文整理汇总了Python中codecs.utf_8_decode方法的典型用法代码示例。如果您正苦于以下问题：Python codecs.utf_8_decode方法的具体用法？Python codecs.utf_8_decode怎么用？Python codecs.utf_8_decode使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类codecs的用法示例。
在下文中一共展示了codecs.utf_8_decode方法的9个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _buffer_decode
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def _buffer_decode(self, input, errors, final):
if self.first:
if len(input) < 3:
if codecs.BOM_UTF8.startswith(input):
# not enough data to decide if this really is a BOM
# => try again on the next call
return ("", 0)
else:
self.first = 0
else:
self.first = 0
if input[:3] == codecs.BOM_UTF8:
(output, consumed) = \
codecs.utf_8_decode(input[3:], errors, final)
return (output, consumed+3)
return codecs.utf_8_decode(input, errors, final) 示例2: decode
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def decode(input, errors='strict', *args):
"""Finds indent and add a colon on previous line"""
u, l = codecs.utf_8_decode(input, errors, True)
out = []
offset = 0
for line in u.split('\n'):
if line.strip():
indent = len(line) - len(line.lstrip())
if indent > offset:
i = -1
while not out[i].strip() and len(out) > -i:
i -= 1
if out[i].rstrip()[-1] != ':':
out[i] += ':'
offset = indent
out.append(line)
return '\n'.join(out), l 示例3: test_decode_unicode
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def test_decode_unicode(self):
# Most decoders don't accept unicode input
decoders = [
codecs.utf_7_decode,
codecs.utf_8_decode,
codecs.utf_16_le_decode,
codecs.utf_16_be_decode,
codecs.utf_16_ex_decode,
codecs.utf_32_decode,
codecs.utf_32_le_decode,
codecs.utf_32_be_decode,
codecs.utf_32_ex_decode,
codecs.latin_1_decode,
codecs.ascii_decode,
codecs.charmap_decode,
]
if hasattr(codecs, "mbcs_decode"):
decoders.append(codecs.mbcs_decode)
for decoder in decoders:
self.assertRaises(TypeError, decoder, "xxx") 示例4: decode
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def decode(input, errors='strict'):
return codecs.utf_8_decode(input, errors, True) 示例5: determine_encoding
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def determine_encoding(self):
while not self.eof and len(self.raw_buffer) < 2:
self.update_raw()
if not isinstance(self.raw_buffer, unicode):
if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
self.raw_decode = codecs.utf_16_le_decode
self.encoding = 'utf-16-le'
elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
self.raw_decode = codecs.utf_16_be_decode
self.encoding = 'utf-16-be'
else:
self.raw_decode = codecs.utf_8_decode
self.encoding = 'utf-8'
self.update(1) 示例6: determine_encoding
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def determine_encoding(self):
while not self.eof and (self.raw_buffer is None or len(self.raw_buffer) < 2):
self.update_raw()
if isinstance(self.raw_buffer, bytes):
if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
self.raw_decode = codecs.utf_16_le_decode
self.encoding = 'utf-16-le'
elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
self.raw_decode = codecs.utf_16_be_decode
self.encoding = 'utf-16-be'
else:
self.raw_decode = codecs.utf_8_decode
self.encoding = 'utf-8'
self.update(1) 示例7: decode
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def decode(input, errors='strict'):
prefix = 0
if input[:3] == codecs.BOM_UTF8:
input = input[3:]
prefix = 3
(output, consumed) = codecs.utf_8_decode(input, errors, True)
return (output, consumed+prefix) 示例8: _buffer_decode
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def _buffer_decode(self, input, errors, final):
if self.first:
if len(input) < 3:
if codecs.BOM_UTF8.startswith(input):
# not enough data to decide if this really is a BOM
# => try again on the next call
return (u"", 0)
else:
self.first = None
else:
self.first = None
if input[:3] == codecs.BOM_UTF8:
(output, consumed) = codecs.utf_8_decode(input[3:], errors, final)
return (output, consumed+3)
return codecs.utf_8_decode(input, errors, final) 示例9: test_utf_8_decode
# 需要导入模块: import codecs [as 别名]
# 或者: from codecs import utf_8_decode [as 别名]
def test_utf_8_decode(self):
#sanity
new_str, size = codecs.utf_8_decode("abc")
self.assertEqual(new_str, u'abc')
self.assertEqual(size, 3)