Mercurial Repositories > eric / file comparison
comparison: ThirdParty/CharDet/chardet/codingstatemachine.py
ThirdParty/CharDet/chardet/codingstatemachine.py
- changeset 3537
- 7662053c3906
- parent 12
- 1d8dd9706f46
- child 5714
- 90c57b50600f
equal
deleted
inserted
replaced
| 3536:c06338ca892b | 3537:7662053c3906 |
|---|---|
| 11 # | 11 # |
| 12 # This library is free software; you can redistribute it and/or | 12 # This library is free software; you can redistribute it and/or |
| 13 # modify it under the terms of the GNU Lesser General Public | 13 # modify it under the terms of the GNU Lesser General Public |
| 14 # License as published by the Free Software Foundation; either | 14 # License as published by the Free Software Foundation; either |
| 15 # version 2.1 of the License, or (at your option) any later version. | 15 # version 2.1 of the License, or (at your option) any later version. |
| 16 # | 16 # |
| 17 # This library is distributed in the hope that it will be useful, | 17 # This library is distributed in the hope that it will be useful, |
| 18 # but WITHOUT ANY WARRANTY; without even the implied warranty of | 18 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 19 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | 19 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 20 # Lesser General Public License for more details. | 20 # Lesser General Public License for more details. |
| 21 # | 21 # |
| 22 # You should have received a copy of the GNU Lesser General Public | 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 | 23 # License along with this library; if not, write to the Free Software |
| 24 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA | 24 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA |
| 25 # 02110-1301 USA | 25 # 02110-1301 USA |
| 26 ######################### END LICENSE BLOCK ######################### | 26 ######################### END LICENSE BLOCK ######################### |
| 27 | 27 |
| 28 from .constants import eStart, eError, eItsMe | 28 from .constants import eStart |
| 29 from .compat import wrap_ord | |
| 30 | |
| 29 | 31 |
| 30 class CodingStateMachine: | 32 class CodingStateMachine: |
| 31 def __init__(self, sm): | 33 def __init__(self, sm): |
| 32 self._mModel = sm | 34 self._mModel = sm |
| 33 self._mCurrentBytePos = 0 | 35 self._mCurrentBytePos = 0 |
| 39 | 41 |
| 40 def next_state(self, c): | 42 def next_state(self, c): |
| 41 # for each byte we get its class | 43 # for each byte we get its class |
| 42 # if it is first byte, we also get byte length | 44 # if it is first byte, we also get byte length |
| 43 # PY3K: aBuf is a byte stream, so c is an int, not a byte | 45 # PY3K: aBuf is a byte stream, so c is an int, not a byte |
| 44 byteCls = self._mModel['classTable'][c] | 46 byteCls = self._mModel['classTable'][wrap_ord(c)] |
| 45 if self._mCurrentState == eStart: | 47 if self._mCurrentState == eStart: |
| 46 self._mCurrentBytePos = 0 | 48 self._mCurrentBytePos = 0 |
| 47 self._mCurrentCharLen = self._mModel['charLenTable'][byteCls] | 49 self._mCurrentCharLen = self._mModel['charLenTable'][byteCls] |
| 48 # from byte's class and stateTable, we get its next state | 50 # from byte's class and stateTable, we get its next state |
| 49 self._mCurrentState = self._mModel['stateTable'][self._mCurrentState * self._mModel['classFactor'] + byteCls] | 51 curr_state = (self._mCurrentState * self._mModel['classFactor'] |
| 52 + byteCls) | |
| 53 self._mCurrentState = self._mModel['stateTable'][curr_state] | |
| 50 self._mCurrentBytePos += 1 | 54 self._mCurrentBytePos += 1 |
| 51 return self._mCurrentState | 55 return self._mCurrentState |
| 52 | 56 |
| 53 def get_current_charlen(self): | 57 def get_current_charlen(self): |
| 54 return self._mCurrentCharLen | 58 return self._mCurrentCharLen |
