ThirdParty/CharDet/chardet/codingstatemachine.py

changeset 0
de9c2efb9d02
child 12
1d8dd9706f46
equal deleted inserted replaced
-1:000000000000 0:de9c2efb9d02
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 from constants import eStart, eError, eItsMe
29
30 class CodingStateMachine:
31 def __init__(self, sm):
32 self._mModel = sm
33 self._mCurrentBytePos = 0
34 self._mCurrentCharLen = 0
35 self.reset()
36
37 def reset(self):
38 self._mCurrentState = eStart
39
40 def next_state(self, c):
41 # for each byte we get its class
42 # if it is first byte, we also get byte length
43 byteCls = self._mModel['classTable'][ord(c)]
44 if self._mCurrentState == eStart:
45 self._mCurrentBytePos = 0
46 self._mCurrentCharLen = self._mModel['charLenTable'][byteCls]
47 # from byte's class and stateTable, we get its next state
48 self._mCurrentState = self._mModel['stateTable'][self._mCurrentState * self._mModel['classFactor'] + byteCls]
49 self._mCurrentBytePos += 1
50 return self._mCurrentState
51
52 def get_current_charlen(self):
53 return self._mCurrentCharLen
54
55 def get_coding_state_machine(self):
56 return self._mModel['name']

eric ide

mercurial