venv/lib/python3.11/site-packages/pip/_vendor/chardet/codingstatemachine.py

   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
  28 import logging
  29
  30 from .codingstatemachinedict import CodingStateMachineDict
  31 from .enums import MachineState
  32
  33
  34 class CodingStateMachine:
  35     """
  36     A state machine to verify a byte sequence for a particular encoding. For
  37     each byte the detector receives, it will feed that byte to every active
  38     state machine available, one byte at a time. The state machine changes its
  39     state based on its previous state and the byte it receives. There are 3
  40     states in a state machine that are of interest to an auto-detector:
  41
  42     START state: This is the state to start with, or a legal byte sequence
  43                  (i.e. a valid code point) for character has been identified.
  44
  45     ME state:  This indicates that the state machine identified a byte sequence
  46                that is specific to the charset it is designed for and that
  47                there is no other possible encoding which can contain this byte
  48                sequence. This will to lead to an immediate positive answer for
  49                the detector.
  50
  51     ERROR state: This indicates the state machine identified an illegal byte
  52                  sequence for that encoding. This will lead to an immediate
  53                  negative answer for this encoding. Detector will exclude this
  54                  encoding from consideration from here on.
  55     """
  56
  57     def __init__(self, sm: CodingStateMachineDict) -> None:
  58         self._model = sm
  59         self._curr_byte_pos = 0
  60         self._curr_char_len = 0
  61         self._curr_state = MachineState.START
  62         self.active = True
  63         self.logger = logging.getLogger(__name__)
  64         self.reset()
  65
  66     def reset(self) -> None:
  67         self._curr_state = MachineState.START
  68
  69     def next_state(self, c: int) -> int:
  70         # for each byte we get its class
  71         # if it is first byte, we also get byte length
  72         byte_class = self._model["class_table"][c]
  73         if self._curr_state == MachineState.START:
  74             self._curr_byte_pos = 0
  75             self._curr_char_len = self._model["char_len_table"][byte_class]
  76         # from byte's class and state_table, we get its next state
  77         curr_state = self._curr_state * self._model["class_factor"] + byte_class
  78         self._curr_state = self._model["state_table"][curr_state]
  79         self._curr_byte_pos += 1
  80         return self._curr_state
  81
  82     def get_current_charlen(self) -> int:
  83         return self._curr_char_len
  84
  85     def get_coding_state_machine(self) -> str:
  86         return self._model["name"]
  87
  88     @property
  89     def language(self) -> str:
  90         return self._model["language"]