chardet/sbcharsetprober.py

   1 ######################## BEGIN LICENSE BLOCK ########################
   2 # The Original Code is Mozilla Universal charset detector 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) 2001
   7 # the Initial Developer. All Rights Reserved.
   8 #
   9 # Contributor(s):
  10 #   Mark Pilgrim - port to Python
  11 #   Shy Shalom - original C code
  12 #
  13 # This library is free software; you can redistribute it and/or
  14 # modify it under the terms of the GNU Lesser General Public
  15 # License as published by the Free Software Foundation; either
  16 # version 2.1 of the License, or (at your option) any later version.
  17 #
  18 # This library is distributed in the hope that it will be useful,
  19 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  20 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  21 # Lesser General Public License for more details.
  22 #
  23 # You should have received a copy of the GNU Lesser General Public
  24 # License along with this library; if not, write to the Free Software
  25 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
  26 # 02110-1301  USA
  27 ######################### END LICENSE BLOCK #########################
  28
  29 import constants, sys
  30 from charsetprober import CharSetProber
  31
  32 SAMPLE_SIZE = 64
  33 SB_ENOUGH_REL_THRESHOLD = 1024
  34 POSITIVE_SHORTCUT_THRESHOLD = 0.95
  35 NEGATIVE_SHORTCUT_THRESHOLD = 0.05
  36 SYMBOL_CAT_ORDER = 250
  37 NUMBER_OF_SEQ_CAT = 4
  38 POSITIVE_CAT = NUMBER_OF_SEQ_CAT - 1
  39 #NEGATIVE_CAT = 0
  40
  41 class SingleByteCharSetProber(CharSetProber):
  42     def __init__(self, model, reversed=constants.False, nameProber=None):
  43         CharSetProber.__init__(self)
  44         self._mModel = model
  45         self._mReversed = reversed # TRUE if we need to reverse every pair in the model lookup
  46         self._mNameProber = nameProber # Optional auxiliary prober for name decision
  47         self.reset()
  48
  49     def reset(self):
  50         CharSetProber.reset(self)
  51         self._mLastOrder = 255 # char order of last character
  52         self._mSeqCounters = [0] * NUMBER_OF_SEQ_CAT
  53         self._mTotalSeqs = 0
  54         self._mTotalChar = 0
  55         self._mFreqChar = 0 # characters that fall in our sampling range
  56
  57     def get_charset_name(self):
  58         if self._mNameProber:
  59             return self._mNameProber.get_charset_name()
  60         else:
  61             return self._mModel['charsetName']
  62
  63     def feed(self, aBuf):
  64         if not self._mModel['keepEnglishLetter']:
  65             aBuf = self.filter_without_english_letters(aBuf)
  66         aLen = len(aBuf)
  67         if not aLen:
  68             return self.get_state()
  69         for c in aBuf:
  70             order = self._mModel['charToOrderMap'][ord(c)]
  71             if order < SYMBOL_CAT_ORDER:
  72                 self._mTotalChar += 1
  73             if order < SAMPLE_SIZE:
  74                 self._mFreqChar += 1
  75                 if self._mLastOrder < SAMPLE_SIZE:
  76                     self._mTotalSeqs += 1
  77                     if not self._mReversed:
  78                         self._mSeqCounters[self._mModel['precedenceMatrix'][(self._mLastOrder * SAMPLE_SIZE) + order]] += 1
  79                     else: # reverse the order of the letters in the lookup
  80                         self._mSeqCounters[self._mModel['precedenceMatrix'][(order * SAMPLE_SIZE) + self._mLastOrder]] += 1
  81             self._mLastOrder = order
  82
  83         if self.get_state() == constants.eDetecting:
  84             if self._mTotalSeqs > SB_ENOUGH_REL_THRESHOLD:
  85                 cf = self.get_confidence()
  86                 if cf > POSITIVE_SHORTCUT_THRESHOLD:
  87                     if constants._debug:
  88                         sys.stderr.write('%s confidence = %s, we have a winner\n' % (self._mModel['charsetName'], cf))
  89                     self._mState = constants.eFoundIt
  90                 elif cf < NEGATIVE_SHORTCUT_THRESHOLD:
  91                     if constants._debug:
  92                         sys.stderr.write('%s confidence = %s, below negative shortcut threshhold %s\n' % (self._mModel['charsetName'], cf, NEGATIVE_SHORTCUT_THRESHOLD))
  93                     self._mState = constants.eNotMe
  94
  95         return self.get_state()
  96
  97     def get_confidence(self):
  98         r = 0.01
  99         if self._mTotalSeqs > 0:
 100 #            print self._mSeqCounters[POSITIVE_CAT], self._mTotalSeqs, self._mModel['mTypicalPositiveRatio']
 101             r = (1.0 * self._mSeqCounters[POSITIVE_CAT]) / self._mTotalSeqs / self._mModel['mTypicalPositiveRatio']
 102 #            print r, self._mFreqChar, self._mTotalChar
 103             r = r * self._mFreqChar / self._mTotalChar
 104             if r >= 1.0:
 105                 r = 0.99
 106         return r