Mercurial > repos > shellac > guppy_basecaller

comparison env/lib/python3.7/site-packages/chardet/eucjpprober.py @ 0:26e78fe6e8c4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit c699937486c35866861690329de38ec1a5d9f783"
author shellac
date Sat, 02 May 2020 07:14:21 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:26e78fe6e8c4
1 ######################## BEGIN LICENSE BLOCK ########################
2 # The Original Code is mozilla.org 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) 1998
7 # the Initial Developer. All Rights Reserved.
8 #
9 # Contributor(s):
10 # Mark Pilgrim - port to Python
11 #
12 # This library is free software; you can redistribute it and/or
13 # modify it under the terms of the GNU Lesser General Public
14 # License as published by the Free Software Foundation; either
15 # version 2.1 of the License, or (at your option) any later version.
16 #
17 # This library is distributed in the hope that it will be useful,
18 # but WITHOUT ANY WARRANTY; without even the implied warranty of
19 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
20 # Lesser General Public License for more details.
21 #
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
24 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
25 # 02110-1301 USA
26 ######################### END LICENSE BLOCK #########################
27
28 from .enums import ProbingState, MachineState
29 from .mbcharsetprober import MultiByteCharSetProber
30 from .codingstatemachine import CodingStateMachine
31 from .chardistribution import EUCJPDistributionAnalysis
32 from .jpcntx import EUCJPContextAnalysis
33 from .mbcssm import EUCJP_SM_MODEL
34
35
36 class EUCJPProber(MultiByteCharSetProber):
37 def __init__(self):
38 super(EUCJPProber, self).__init__()
39 self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL)
40 self.distribution_analyzer = EUCJPDistributionAnalysis()
41 self.context_analyzer = EUCJPContextAnalysis()
42 self.reset()
43
44 def reset(self):
45 super(EUCJPProber, self).reset()
46 self.context_analyzer.reset()
47
48 @property
49 def charset_name(self):
50 return "EUC-JP"
51
52 @property
53 def language(self):
54 return "Japanese"
55
56 def feed(self, byte_str):
57 for i in range(len(byte_str)):
58 # PY3K: byte_str is a byte array, so byte_str[i] is an int, not a byte
59 coding_state = self.coding_sm.next_state(byte_str[i])
60 if coding_state == MachineState.ERROR:
61 self.logger.debug('%s %s prober hit error at byte %s',
62 self.charset_name, self.language, i)
63 self._state = ProbingState.NOT_ME
64 break
65 elif coding_state == MachineState.ITS_ME:
66 self._state = ProbingState.FOUND_IT
67 break
68 elif coding_state == MachineState.START:
69 char_len = self.coding_sm.get_current_charlen()
70 if i == 0:
71 self._last_char[1] = byte_str[0]
72 self.context_analyzer.feed(self._last_char, char_len)
73 self.distribution_analyzer.feed(self._last_char, char_len)
74 else:
75 self.context_analyzer.feed(byte_str[i - 1:i + 1],
76 char_len)
77 self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
78 char_len)
79
80 self._last_char[0] = byte_str[-1]
81
82 if self.state == ProbingState.DETECTING:
83 if (self.context_analyzer.got_enough_data() and
84 (self.get_confidence() > self.SHORTCUT_THRESHOLD)):
85 self._state = ProbingState.FOUND_IT
86
87 return self.state
88
89 def get_confidence(self):
90 context_conf = self.context_analyzer.get_confidence()
91 distrib_conf = self.distribution_analyzer.get_confidence()
92 return max(context_conf, distrib_conf)