Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
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 #########################
28import logging
30from .codingstatemachinedict import CodingStateMachineDict
31from .enums import MachineState
34class 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:
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.
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.
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 """
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()
66 def reset(self) -> None:
67 self._curr_state = MachineState.START
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
82 def get_current_charlen(self) -> int:
83 return self._curr_char_len
85 def get_coding_state_machine(self) -> str:
86 return self._model["name"]
88 @property
89 def language(self) -> str:
90 return self._model["language"]