eric6/ThirdParty/CharDet/chardet/gb2312prober.py

Wed, 13 Jul 2022 15:34:50 +0200

author
Detlev Offenbach <detlev@die-offenbachs.de>
date
Wed, 13 Jul 2022 15:34:50 +0200
branch
with_python2
changeset 9225
bf799f79455c
parent 6942
2602857055c5
permissions
-rw-r--r--

Revisions <no_multi_processing, Variables Viewer, with_python2> closed.

3537
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
1 ######################## BEGIN LICENSE BLOCK ########################
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
2 # The Original Code is mozilla.org code.
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
3 #
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
4 # The Initial Developer of the Original Code is
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
5 # Netscape Communications Corporation.
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
6 # Portions created by the Initial Developer are Copyright (C) 1998
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
7 # the Initial Developer. All Rights Reserved.
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
8 #
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
9 # Contributor(s):
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
10 # Mark Pilgrim - port to Python
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
11 #
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
12 # This library is free software; you can redistribute it and/or
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
13 # modify it under the terms of the GNU Lesser General Public
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
14 # License as published by the Free Software Foundation; either
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
15 # version 2.1 of the License, or (at your option) any later version.
5714
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
16 #
3537
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
17 # This library is distributed in the hope that it will be useful,
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
18 # but WITHOUT ANY WARRANTY; without even the implied warranty of
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
19 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
20 # Lesser General Public License for more details.
5714
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
21 #
3537
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
22 # You should have received a copy of the GNU Lesser General Public
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
23 # License along with this library; if not, write to the Free Software
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
24 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
25 # 02110-1301 USA
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
26 ######################### END LICENSE BLOCK #########################
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
27
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
28 from .mbcharsetprober import MultiByteCharSetProber
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
29 from .codingstatemachine import CodingStateMachine
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
30 from .chardistribution import GB2312DistributionAnalysis
5714
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
31 from .mbcssm import GB2312_SM_MODEL
3537
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
32
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
33 class GB2312Prober(MultiByteCharSetProber):
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
34 def __init__(self):
5714
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
35 super(GB2312Prober, self).__init__()
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
36 self.coding_sm = CodingStateMachine(GB2312_SM_MODEL)
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
37 self.distribution_analyzer = GB2312DistributionAnalysis()
3537
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
38 self.reset()
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
39
5714
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
40 @property
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
41 def charset_name(self):
3537
7662053c3906 updated CharDet to 2.2.1, updated changelog
T.Rzepka <Tobias.Rzepka@gmail.com>
parents: 12
diff changeset
42 return "GB2312"
5714
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
43
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
44 @property
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
45 def language(self):
90c57b50600f Updated chardet to 3.0.2.
Detlev Offenbach <detlev@die-offenbachs.de>
parents: 3537
diff changeset
46 return "Chinese"

eric ide

mercurial