| ######################## BEGIN LICENSE BLOCK ######################## |
| # The Original Code is mozilla.org code. |
| # |
| # The Initial Developer of the Original Code is |
| # Netscape Communications Corporation. |
| # Portions created by the Initial Developer are Copyright (C) 1998 |
| # the Initial Developer. All Rights Reserved. |
| # |
| # Contributor(s): |
| # Mark Pilgrim - port to Python |
| # |
| # 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 St, Fifth Floor, Boston, MA |
| # 02110-1301 USA |
| ######################### END LICENSE BLOCK ######################### |
| |
| import logging |
| |
| from .enums import MachineState |
| |
| |
| class CodingStateMachine: |
| """ |
| A state machine to verify a byte sequence for a particular encoding. For |
| each byte the detector receives, it will feed that byte to every active |
| state machine available, one byte at a time. The state machine changes its |
| state based on its previous state and the byte it receives. There are 3 |
| states in a state machine that are of interest to an auto-detector: |
| |
| START state: This is the state to start with, or a legal byte sequence |
| (i.e. a valid code point) for character has been identified. |
| |
| ME state: This indicates that the state machine identified a byte sequence |
| that is specific to the charset it is designed for and that |
| there is no other possible encoding which can contain this byte |
| sequence. This will to lead to an immediate positive answer for |
| the detector. |
| |
| ERROR state: This indicates the state machine identified an illegal byte |
| sequence for that encoding. This will lead to an immediate |
| negative answer for this encoding. Detector will exclude this |
| encoding from consideration from here on. |
| """ |
| |
| def __init__(self, sm): |
| self._model = sm |
| self._curr_byte_pos = 0 |
| self._curr_char_len = 0 |
| self._curr_state = None |
| self.logger = logging.getLogger(__name__) |
| self.reset() |
| |
| def reset(self): |
| self._curr_state = MachineState.START |
| |
| def next_state(self, c): |
| # for each byte we get its class |
| # if it is first byte, we also get byte length |
| byte_class = self._model["class_table"][c] |
| if self._curr_state == MachineState.START: |
| self._curr_byte_pos = 0 |
| self._curr_char_len = self._model["char_len_table"][byte_class] |
| # from byte's class and state_table, we get its next state |
| curr_state = self._curr_state * self._model["class_factor"] + byte_class |
| self._curr_state = self._model["state_table"][curr_state] |
| self._curr_byte_pos += 1 |
| return self._curr_state |
| |
| def get_current_charlen(self): |
| return self._curr_char_len |
| |
| def get_coding_state_machine(self): |
| return self._model["name"] |
| |
| @property |
| def language(self): |
| return self._model["language"] |
