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")
python类latin_1_decode()的实例源码
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
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")
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
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")
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
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")
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
def get_entitydefs():
import htmlentitydefs
from codecs import latin_1_decode
entitydefs = {}
try:
htmlentitydefs.name2codepoint
except AttributeError:
entitydefs = {}
for name, char in htmlentitydefs.entitydefs.items():
uc = latin_1_decode(char)[0]
if uc.startswith("&#") and uc.endswith(";"):
uc = unescape_charref(uc[2:-1], None)
entitydefs["&%s;" % name] = uc
else:
for name, codepoint in htmlentitydefs.name2codepoint.items():
entitydefs["&%s;" % name] = unichr(codepoint)
return entitydefs
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def name2cp(k):
if k == 'apos': return ord("'")
if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
return htmlentitydefs.name2codepoint[k]
else:
k = htmlentitydefs.entitydefs[k]
if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
return ord(codecs.latin_1_decode(k)[0])
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def name2cp(k):
if k == 'apos': return ord("'")
if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
return htmlentitydefs.name2codepoint[k]
else:
k = htmlentitydefs.entitydefs[k]
if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
return ord(codecs.latin_1_decode(k)[0])
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
def decode(self, input, final=False):
return codecs.latin_1_decode(input,self.errors)[0]
