This file is indexed.

/usr/lib/python2.7/dist-packages/chardet/mbcharsetprober.py is in python-chardet 2.0.1-2build2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Universal charset detector code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 2001
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Mark Pilgrim - port to Python
#   Shy Shalom - original C code
#   Proofpoint, Inc.
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
# 
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# Lesser General Public License for more details.
# 
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301  USA
######################### END LICENSE BLOCK #########################

import constants, sys
from constants import eStart, eError, eItsMe
from charsetprober import CharSetProber

class MultiByteCharSetProber(CharSetProber):
    def __init__(self):
        CharSetProber.__init__(self)
        self._mDistributionAnalyzer = None
        self._mCodingSM = None
        self._mLastChar = ['\x00', '\x00']

    def reset(self):
        CharSetProber.reset(self)
        if self._mCodingSM:
            self._mCodingSM.reset()
        if self._mDistributionAnalyzer:
            self._mDistributionAnalyzer.reset()
        self._mLastChar = ['\x00', '\x00']

    def get_charset_name(self):
        pass

    def feed(self, aBuf):
        aLen = len(aBuf)
        for i in range(0, aLen):
            codingState = self._mCodingSM.next_state(aBuf[i])
            if codingState == eError:
                if constants._debug:
                    sys.stderr.write(self.get_charset_name() + ' prober hit error at byte ' + str(i) + '\n')
                self._mState = constants.eNotMe
                break
            elif codingState == eItsMe:
                self._mState = constants.eFoundIt
                break
            elif codingState == eStart:
                charLen = self._mCodingSM.get_current_charlen()
                if i == 0:
                    self._mLastChar[1] = aBuf[0]
                    self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
                else:
                    self._mDistributionAnalyzer.feed(aBuf[i-1:i+1], charLen)
                    
        self._mLastChar[0] = aBuf[aLen - 1]
        
        if self.get_state() == constants.eDetecting:
            if self._mDistributionAnalyzer.got_enough_data() and \
               (self.get_confidence() > constants.SHORTCUT_THRESHOLD):
                self._mState = constants.eFoundIt

        return self.get_state()

    def get_confidence(self):
        return self._mDistributionAnalyzer.get_confidence()