This file is indexed.

/usr/lib/python3/dist-packages/chardet/eucjpprober.py is in python3-chardet 2.0.1-1.

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
83
84
85
86
87
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is mozilla.org code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Mark Pilgrim - port to Python
#
# 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 #########################

from . import constants
import sys
from .constants import eStart, eError, eItsMe
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from .chardistribution import EUCJPDistributionAnalysis
from .jpcntx import EUCJPContextAnalysis
from .mbcssm import EUCJPSMModel

class EUCJPProber(MultiByteCharSetProber):
    def __init__(self):
        MultiByteCharSetProber.__init__(self)
        self._mCodingSM = CodingStateMachine(EUCJPSMModel)
        self._mDistributionAnalyzer = EUCJPDistributionAnalysis()
        self._mContextAnalyzer = EUCJPContextAnalysis()
        self.reset()

    def reset(self):
        MultiByteCharSetProber.reset(self)
        self._mContextAnalyzer.reset()
        
    def get_charset_name(self):
        return "EUC-JP"

    def feed(self, aBuf):
        aLen = len(aBuf)
        for i in range(0, aLen):
            # PY3K: aBuf is a byte array, so aBuf[i] is an int, not a byte
            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._mContextAnalyzer.feed(self._mLastChar, charLen)
                    self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
                else:
                    self._mContextAnalyzer.feed(aBuf[i-1:i+1], charLen)
                    self._mDistributionAnalyzer.feed(aBuf[i-1:i+1], charLen)
                    
        self._mLastChar[0] = aBuf[aLen - 1]
        
        if self.get_state() == constants.eDetecting:
            if self._mContextAnalyzer.got_enough_data() and \
                   (self.get_confidence() > constants.SHORTCUT_THRESHOLD):
                self._mState = constants.eFoundIt

        return self.get_state()

    def get_confidence(self):
        contxtCf = self._mContextAnalyzer.get_confidence()
        distribCf = self._mDistributionAnalyzer.get_confidence()
        return max(contxtCf, distribCf)