1######################## BEGIN LICENSE BLOCK ######################## 2# The Original Code is mozilla.org code. 3# 4# The Initial Developer of the Original Code is 5# Netscape Communications Corporation. 6# Portions created by the Initial Developer are Copyright (C) 1998 7# the Initial Developer. All Rights Reserved. 8# 9# Contributor(s): 10# Mark Pilgrim - port to Python 11# 12# This library is free software; you can redistribute it and/or 13# modify it under the terms of the GNU Lesser General Public 14# License as published by the Free Software Foundation; either 15# version 2.1 of the License, or (at your option) any later version. 16# 17# This library is distributed in the hope that it will be useful, 18# but WITHOUT ANY WARRANTY; without even the implied warranty of 19# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 20# Lesser General Public License for more details. 21# 22# You should have received a copy of the GNU Lesser General Public 23# License along with this library; if not, write to the Free Software 24# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 25# 02110-1301 USA 26######################### END LICENSE BLOCK ######################### 27 28import logging 29 30from .enums import MachineState 31 32 33class CodingStateMachine(object): 34 """ 35 A state machine to verify a byte sequence for a particular encoding. For 36 each byte the detector receives, it will feed that byte to every active 37 state machine available, one byte at a time. The state machine changes its 38 state based on its previous state and the byte it receives. There are 3 39 states in a state machine that are of interest to an auto-detector: 40 41 START state: This is the state to start with, or a legal byte sequence 42 (i.e. a valid code point) for character has been identified. 43 44 ME state: This indicates that the state machine identified a byte sequence 45 that is specific to the charset it is designed for and that 46 there is no other possible encoding which can contain this byte 47 sequence. This will to lead to an immediate positive answer for 48 the detector. 49 50 ERROR state: This indicates the state machine identified an illegal byte 51 sequence for that encoding. This will lead to an immediate 52 negative answer for this encoding. Detector will exclude this 53 encoding from consideration from here on. 54 """ 55 def __init__(self, sm): 56 self._model = sm 57 self._curr_byte_pos = 0 58 self._curr_char_len = 0 59 self._curr_state = None 60 self.logger = logging.getLogger(__name__) 61 self.reset() 62 63 def reset(self): 64 self._curr_state = MachineState.START 65 66 def next_state(self, c): 67 # for each byte we get its class 68 # if it is first byte, we also get byte length 69 byte_class = self._model['class_table'][c] 70 if self._curr_state == MachineState.START: 71 self._curr_byte_pos = 0 72 self._curr_char_len = self._model['char_len_table'][byte_class] 73 # from byte's class and state_table, we get its next state 74 curr_state = (self._curr_state * self._model['class_factor'] 75 + byte_class) 76 self._curr_state = self._model['state_table'][curr_state] 77 self._curr_byte_pos += 1 78 return self._curr_state 79 80 def get_current_charlen(self): 81 return self._curr_char_len 82 83 def get_coding_state_machine(self): 84 return self._model['name'] 85 86 @property 87 def language(self): 88 return self._model['language'] 89