You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
106 lines
3.5 KiB
106 lines
3.5 KiB
"""
|
|
websocket - WebSocket client library for Python
|
|
|
|
Copyright (C) 2010 Hiroki Ohtani(liris)
|
|
|
|
This library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
This library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with this library; if not, write to the Free Software
|
|
Foundation, Inc., 51 Franklin Street, Fifth Floor,
|
|
Boston, MA 02110-1335 USA
|
|
|
|
"""
|
|
import six
|
|
|
|
__all__ = ["NoLock", "validate_utf8", "extract_err_message"]
|
|
|
|
|
|
class NoLock(object):
|
|
|
|
def __enter__(self):
|
|
pass
|
|
|
|
def __exit__(self, exc_type, exc_value, traceback):
|
|
pass
|
|
|
|
try:
|
|
# If wsaccel is available we use compiled routines to validate UTF-8
|
|
# strings.
|
|
from wsaccel.utf8validator import Utf8Validator
|
|
|
|
def _validate_utf8(utfbytes):
|
|
return Utf8Validator().validate(utfbytes)[0]
|
|
|
|
except ImportError:
|
|
# UTF-8 validator
|
|
# python implementation of http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
|
|
|
|
_UTF8_ACCEPT = 0
|
|
_UTF8_REJECT = 12
|
|
|
|
_UTF8D = [
|
|
# The first part of the table maps bytes to character classes that
|
|
# to reduce the size of the transition table and create bitmasks.
|
|
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,
|
|
7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, 7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
|
|
8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
|
|
10,3,3,3,3,3,3,3,3,3,3,3,3,4,3,3, 11,6,6,6,5,8,8,8,8,8,8,8,8,8,8,8,
|
|
|
|
# The second part is a transition table that maps a combination
|
|
# of a state of the automaton and a character class to a state.
|
|
0,12,24,36,60,96,84,12,12,12,48,72, 12,12,12,12,12,12,12,12,12,12,12,12,
|
|
12, 0,12,12,12,12,12, 0,12, 0,12,12, 12,24,12,12,12,12,12,24,12,24,12,12,
|
|
12,12,12,12,12,12,12,24,12,12,12,12, 12,24,12,12,12,12,12,12,12,24,12,12,
|
|
12,12,12,12,12,12,12,36,12,36,12,12, 12,36,12,12,12,12,12,36,12,36,12,12,
|
|
12,36,12,12,12,12,12,12,12,12,12,12, ]
|
|
|
|
def _decode(state, codep, ch):
|
|
tp = _UTF8D[ch]
|
|
|
|
codep = (ch & 0x3f) | (codep << 6) if (
|
|
state != _UTF8_ACCEPT) else (0xff >> tp) & ch
|
|
state = _UTF8D[256 + state + tp]
|
|
|
|
return state, codep
|
|
|
|
def _validate_utf8(utfbytes):
|
|
state = _UTF8_ACCEPT
|
|
codep = 0
|
|
for i in utfbytes:
|
|
if six.PY2:
|
|
i = ord(i)
|
|
state, codep = _decode(state, codep, i)
|
|
if state == _UTF8_REJECT:
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
def validate_utf8(utfbytes):
|
|
"""
|
|
validate utf8 byte string.
|
|
utfbytes: utf byte string to check.
|
|
return value: if valid utf8 string, return true. Otherwise, return false.
|
|
"""
|
|
return _validate_utf8(utfbytes)
|
|
|
|
|
|
def extract_err_message(exception):
|
|
if exception.args:
|
|
return exception.args[0]
|
|
else:
|
|
return None
|