Mercurial > repos > shellac > guppy_basecaller

comparison env/lib/python3.7/site-packages/chardet/utf8prober.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 .charsetprober import CharSetProber
29 from .enums import ProbingState, MachineState
30 from .codingstatemachine import CodingStateMachine
31 from .mbcssm import UTF8_SM_MODEL
32
33
34
35 class UTF8Prober(CharSetProber):
36 ONE_CHAR_PROB = 0.5
37
38 def __init__(self):
39 super(UTF8Prober, self).__init__()
40 self.coding_sm = CodingStateMachine(UTF8_SM_MODEL)
41 self._num_mb_chars = None
42 self.reset()
43
44 def reset(self):
45 super(UTF8Prober, self).reset()
46 self.coding_sm.reset()
47 self._num_mb_chars = 0
48
49 @property
50 def charset_name(self):
51 return "utf-8"
52
53 @property
54 def language(self):
55 return ""
56
57 def feed(self, byte_str):
58 for c in byte_str:
59 coding_state = self.coding_sm.next_state(c)
60 if coding_state == MachineState.ERROR:
61 self._state = ProbingState.NOT_ME
62 break
63 elif coding_state == MachineState.ITS_ME:
64 self._state = ProbingState.FOUND_IT
65 break
66 elif coding_state == MachineState.START:
67 if self.coding_sm.get_current_charlen() >= 2:
68 self._num_mb_chars += 1
69
70 if self.state == ProbingState.DETECTING:
71 if self.get_confidence() > self.SHORTCUT_THRESHOLD:
72 self._state = ProbingState.FOUND_IT
73
74 return self.state
75
76 def get_confidence(self):
77 unlike = 0.99
78 if self._num_mb_chars < 6:
79 unlike *= self.ONE_CHAR_PROB ** self._num_mb_chars
80 return 1.0 - unlike
81 else:
82 return unlike