Mercurial > repos > shellac > guppy_basecaller

comparison env/lib/python3.7/site-packages/chardet/mbcharsetprober.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 Universal charset detector 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) 2001
7 # the Initial Developer. All Rights Reserved.
8 #
9 # Contributor(s):
10 # Mark Pilgrim - port to Python
11 # Shy Shalom - original C code
12 # Proofpoint, Inc.
13 #
14 # This library is free software; you can redistribute it and/or
15 # modify it under the terms of the GNU Lesser General Public
16 # License as published by the Free Software Foundation; either
17 # version 2.1 of the License, or (at your option) any later version.
18 #
19 # This library is distributed in the hope that it will be useful,
20 # but WITHOUT ANY WARRANTY; without even the implied warranty of
21 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
22 # Lesser General Public License for more details.
23 #
24 # You should have received a copy of the GNU Lesser General Public
25 # License along with this library; if not, write to the Free Software
26 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
27 # 02110-1301 USA
28 ######################### END LICENSE BLOCK #########################
29
30 from .charsetprober import CharSetProber
31 from .enums import ProbingState, MachineState
32
33
34 class MultiByteCharSetProber(CharSetProber):
35 """
36 MultiByteCharSetProber
37 """
38
39 def __init__(self, lang_filter=None):
40 super(MultiByteCharSetProber, self).__init__(lang_filter=lang_filter)
41 self.distribution_analyzer = None
42 self.coding_sm = None
43 self._last_char = [0, 0]
44
45 def reset(self):
46 super(MultiByteCharSetProber, self).reset()
47 if self.coding_sm:
48 self.coding_sm.reset()
49 if self.distribution_analyzer:
50 self.distribution_analyzer.reset()
51 self._last_char = [0, 0]
52
53 @property
54 def charset_name(self):
55 raise NotImplementedError
56
57 @property
58 def language(self):
59 raise NotImplementedError
60
61 def feed(self, byte_str):
62 for i in range(len(byte_str)):
63 coding_state = self.coding_sm.next_state(byte_str[i])
64 if coding_state == MachineState.ERROR:
65 self.logger.debug('%s %s prober hit error at byte %s',
66 self.charset_name, self.language, i)
67 self._state = ProbingState.NOT_ME
68 break
69 elif coding_state == MachineState.ITS_ME:
70 self._state = ProbingState.FOUND_IT
71 break
72 elif coding_state == MachineState.START:
73 char_len = self.coding_sm.get_current_charlen()
74 if i == 0:
75 self._last_char[1] = byte_str[0]
76 self.distribution_analyzer.feed(self._last_char, char_len)
77 else:
78 self.distribution_analyzer.feed(byte_str[i - 1:i + 1],
79 char_len)
80
81 self._last_char[0] = byte_str[-1]
82
83 if self.state == ProbingState.DETECTING:
84 if (self.distribution_analyzer.got_enough_data() and
85 (self.get_confidence() > self.SHORTCUT_THRESHOLD)):
86 self._state = ProbingState.FOUND_IT
87
88 return self.state
89
90 def get_confidence(self):
91 return self.distribution_analyzer.get_confidence()