Mercurial Repositories > eric / file comparison
comparison: ThirdParty/CharDet/chardet/utf8prober.py
ThirdParty/CharDet/chardet/utf8prober.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 . import constants | 28 from . import constants |
| 29 import sys | |
| 30 from .constants import eStart, eError, eItsMe | |
| 31 from .charsetprober import CharSetProber | 29 from .charsetprober import CharSetProber |
| 32 from .codingstatemachine import CodingStateMachine | 30 from .codingstatemachine import CodingStateMachine |
| 33 from .mbcssm import UTF8SMModel | 31 from .mbcssm import UTF8SMModel |
| 34 | 32 |
| 35 ONE_CHAR_PROB = 0.5 | 33 ONE_CHAR_PROB = 0.5 |
| 34 | |
| 36 | 35 |
| 37 class UTF8Prober(CharSetProber): | 36 class UTF8Prober(CharSetProber): |
| 38 def __init__(self): | 37 def __init__(self): |
| 39 CharSetProber.__init__(self) | 38 CharSetProber.__init__(self) |
| 40 self._mCodingSM = CodingStateMachine(UTF8SMModel) | 39 self._mCodingSM = CodingStateMachine(UTF8SMModel) |
| 49 return "utf-8" | 48 return "utf-8" |
| 50 | 49 |
| 51 def feed(self, aBuf): | 50 def feed(self, aBuf): |
| 52 for c in aBuf: | 51 for c in aBuf: |
| 53 codingState = self._mCodingSM.next_state(c) | 52 codingState = self._mCodingSM.next_state(c) |
| 54 if codingState == eError: | 53 if codingState == constants.eError: |
| 55 self._mState = constants.eNotMe | 54 self._mState = constants.eNotMe |
| 56 break | 55 break |
| 57 elif codingState == eItsMe: | 56 elif codingState == constants.eItsMe: |
| 58 self._mState = constants.eFoundIt | 57 self._mState = constants.eFoundIt |
| 59 break | 58 break |
| 60 elif codingState == eStart: | 59 elif codingState == constants.eStart: |
| 61 if self._mCodingSM.get_current_charlen() >= 2: | 60 if self._mCodingSM.get_current_charlen() >= 2: |
| 62 self._mNumOfMBChar += 1 | 61 self._mNumOfMBChar += 1 |
| 63 | 62 |
| 64 if self.get_state() == constants.eDetecting: | 63 if self.get_state() == constants.eDetecting: |
| 65 if self.get_confidence() > constants.SHORTCUT_THRESHOLD: | 64 if self.get_confidence() > constants.SHORTCUT_THRESHOLD: |
