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
88
89
90
91
92
|
######################## 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 .enums import ProbingState, MachineState
from .mbcharsetprober import MultiByteCharSetProber
from .codingstatemachine import CodingStateMachine
from .chardistribution import EUCJPDistributionAnalysis
from .jpcntx import EUCJPContextAnalysis
from .mbcssm import EUCJP_SM_MODEL
class EUCJPProber(MultiByteCharSetProber):
def __init__(self):
super(EUCJPProber, self).__init__()
self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL)
self.distribution_analyzer = EUCJPDistributionAnalysis()
self.context_analyzer = EUCJPContextAnalysis()
self.reset()
def reset(self):
super(EUCJPProber, self).reset()
self.context_analyzer.reset()
@property
def charset_name(self):
return "EUC-JP"
@property
def language(self):
return "Japanese"
def feed(self, byte_str):
for i in range(len(byte_str)):
# PY3K: byte_str is a byte array, so byte_str[i] is an int, not a byte
coding_state = self.coding_sm.next_state(byte_str[i])
if coding_state == MachineState.ERROR:
self.logger.debug('%s %s prober hit error at byte %s',
self.charset_name, self.language, i)
self._state = ProbingState.NOT_ME
break
elif coding_state == MachineState.ITS_ME:
self._state = ProbingState.FOUND_IT
break
elif coding_state == MachineState.START:
char_len = self.coding_sm.get_current_charlen()
if i == 0:
self._last_char[1] = byte_str[0]
self.context_analyzer.feed(self._last_char, char_len)
self.distribution_analyzer.feed(self._last_char, char_len)
else:
self.context_analyzer.feed(byte_str[i - 1:i + 1],
char_len)
self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
char_len)
self._last_char[0] = byte_str[-1]
if self.state == ProbingState.DETECTING:
if (self.context_analyzer.got_enough_data() and
(self.get_confidence() > self.SHORTCUT_THRESHOLD)):
self._state = ProbingState.FOUND_IT
return self.state
def get_confidence(self):
context_conf = self.context_analyzer.get_confidence()
distrib_conf = self.distribution_analyzer.get_confidence()
return max(context_conf, distrib_conf)
|
