summaryrefslogtreecommitdiff
path: root/venv/lib/python3.7/site-packages/pip-10.0.1-py3.7.egg/pip/_vendor/chardet/sjisprober.py
diff options
context:
space:
mode:
authorShubham Saini <shubham6405@gmail.com>2018-12-11 10:01:23 +0000
committerShubham Saini <shubham6405@gmail.com>2018-12-11 10:01:23 +0000
commit68df54d6629ec019142eb149dd037774f2d11e7c (patch)
tree345bc22d46b4e01a4ba8303b94278952a4ed2b9e /venv/lib/python3.7/site-packages/pip-10.0.1-py3.7.egg/pip/_vendor/chardet/sjisprober.py
First commit
Diffstat (limited to 'venv/lib/python3.7/site-packages/pip-10.0.1-py3.7.egg/pip/_vendor/chardet/sjisprober.py')
-rw-r--r--venv/lib/python3.7/site-packages/pip-10.0.1-py3.7.egg/pip/_vendor/chardet/sjisprober.py92
1 files changed, 92 insertions, 0 deletions
diff --git a/venv/lib/python3.7/site-packages/pip-10.0.1-py3.7.egg/pip/_vendor/chardet/sjisprober.py b/venv/lib/python3.7/site-packages/pip-10.0.1-py3.7.egg/pip/_vendor/chardet/sjisprober.py
new file mode 100644
index 0000000..683add0
--- /dev/null
+++ b/venv/lib/python3.7/site-packages/pip-10.0.1-py3.7.egg/pip/_vendor/chardet/sjisprober.py
@@ -0,0 +1,92 @@
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
28from .mbcharsetprober import MultiByteCharSetProber
29from .codingstatemachine import CodingStateMachine
30from .chardistribution import SJISDistributionAnalysis
31from .jpcntx import SJISContextAnalysis
32from .mbcssm import SJIS_SM_MODEL
33from .enums import ProbingState, MachineState
34
35
36class SJISProber(MultiByteCharSetProber):
37 def __init__(self):
38 super(SJISProber, self).__init__()
39 self.coding_sm = CodingStateMachine(SJIS_SM_MODEL)
40 self.distribution_analyzer = SJISDistributionAnalysis()
41 self.context_analyzer = SJISContextAnalysis()
42 self.reset()
43
44 def reset(self):
45 super(SJISProber, self).reset()
46 self.context_analyzer.reset()
47
48 @property
49 def charset_name(self):
50 return self.context_analyzer.charset_name
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 coding_state = self.coding_sm.next_state(byte_str[i])
59 if coding_state == MachineState.ERROR:
60 self.logger.debug('%s %s prober hit error at byte %s',
61 self.charset_name, self.language, i)
62 self._state = ProbingState.NOT_ME
63 break
64 elif coding_state == MachineState.ITS_ME:
65 self._state = ProbingState.FOUND_IT
66 break
67 elif coding_state == MachineState.START:
68 char_len = self.coding_sm.get_current_charlen()
69 if i == 0:
70 self._last_char[1] = byte_str[0]
71 self.context_analyzer.feed(self._last_char[2 - char_len:],
72 char_len)
73 self.distribution_analyzer.feed(self._last_char, char_len)
74 else:
75 self.context_analyzer.feed(byte_str[i + 1 - char_len:i + 3
76 - char_len], 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)