def mask(self, data):
"""
Performs the masking or unmasking operation on data
using the simple masking algorithm:
..
j = i MOD 4
transformed-octet-i = original-octet-i XOR masking-key-octet-j
"""
masked = bytearray(data)
if py3k: key = self.masking_key
else: key = map(ord, self.masking_key)
for i in range(len(data)):
masked[i] = masked[i] ^ key[i%4]
return masked
def mask(self, data):
"""
Performs the masking or unmasking operation on data
using the simple masking algorithm:
..
j = i MOD 4
transformed-octet-i = original-octet-i XOR masking-key-octet-j
"""
masked = bytearray(data)
if py3k: key = self.masking_key
else: key = map(ord, self.masking_key)
for i in range(len(data)):
masked[i] = masked[i] ^ key[i%4]
return masked
def validate(self, ba):
"""
Incrementally validate a chunk of bytes provided as bytearray.
Will return a quad (valid?, endsOnCodePoint?, currentIndex, totalIndex).
As soon as an octet is encountered which renders the octet sequence
invalid, a quad with valid? == False is returned. currentIndex returns
the index within the currently consumed chunk, and totalIndex the
index within the total consumed sequence that was the point of bail out.
When valid? == True, currentIndex will be len(ba) and totalIndex the
total amount of consumed bytes.
"""
l = len(ba)
for i in range(0, l):
## optimized version of decode(), since we are not interested in actual code points
self.state = Utf8Validator.UTF8VALIDATOR_DFA[256 + (
self.state << 4) + Utf8Validator.UTF8VALIDATOR_DFA[ba[i]]]
if self.state == Utf8Validator.UTF8_REJECT:
self.i += i
return False, False, i, self.i
self.i += l
return True, self.state == Utf8Validator.UTF8_ACCEPT, l, self.i
def validate(self, ba):
"""
Incrementally validate a chunk of bytes provided as bytearray.
Will return a quad (valid?, endsOnCodePoint?, currentIndex, totalIndex).
As soon as an octet is encountered which renders the octet sequence
invalid, a quad with valid? == False is returned. currentIndex returns
the index within the currently consumed chunk, and totalIndex the
index within the total consumed sequence that was the point of bail out.
When valid? == True, currentIndex will be len(ba) and totalIndex the
total amount of consumed bytes.
"""
l = len(ba)
for i in range(0, l):
## optimized version of decode(), since we are not interested in actual code points
self.state = Utf8Validator.UTF8VALIDATOR_DFA[
256 + (self.state << 4) + Utf8Validator.UTF8VALIDATOR_DFA[ba[i]]
]
if self.state == Utf8Validator.UTF8_REJECT:
self.i += i
return False, False, i, self.i
self.i += l
return True, self.state == Utf8Validator.UTF8_ACCEPT, l, self.i
