python (3.12.0)
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 #
13 # This library is free software; you can redistribute it and/or
14 # modify it under the terms of the GNU Lesser General Public
15 # License as published by the Free Software Foundation; either
16 # version 2.1 of the License, or (at your option) any later version.
17 #
18 # This library is distributed in the hope that it will be useful,
19 # but WITHOUT ANY WARRANTY; without even the implied warranty of
20 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
21 # Lesser General Public License for more details.
22 #
23 # You should have received a copy of the GNU Lesser General Public
24 # License along with this library; if not, write to the Free Software
25 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
26 # 02110-1301 USA
27 ######################### END LICENSE BLOCK #########################
28
29 from .charsetgroupprober import CharSetGroupProber
30 from .hebrewprober import HebrewProber
31 from .langbulgarianmodel import ISO_8859_5_BULGARIAN_MODEL, WINDOWS_1251_BULGARIAN_MODEL
32 from .langgreekmodel import ISO_8859_7_GREEK_MODEL, WINDOWS_1253_GREEK_MODEL
33 from .langhebrewmodel import WINDOWS_1255_HEBREW_MODEL
34
35 # from .langhungarianmodel import (ISO_8859_2_HUNGARIAN_MODEL,
36 # WINDOWS_1250_HUNGARIAN_MODEL)
37 from .langrussianmodel import (
38 IBM855_RUSSIAN_MODEL,
39 IBM866_RUSSIAN_MODEL,
40 ISO_8859_5_RUSSIAN_MODEL,
41 KOI8_R_RUSSIAN_MODEL,
42 MACCYRILLIC_RUSSIAN_MODEL,
43 WINDOWS_1251_RUSSIAN_MODEL,
44 )
45 from .langthaimodel import TIS_620_THAI_MODEL
46 from .langturkishmodel import ISO_8859_9_TURKISH_MODEL
47 from .sbcharsetprober import SingleByteCharSetProber
48
49
50 class ESC[4;38;5;81mSBCSGroupProber(ESC[4;38;5;149mCharSetGroupProber):
51 def __init__(self) -> None:
52 super().__init__()
53 hebrew_prober = HebrewProber()
54 logical_hebrew_prober = SingleByteCharSetProber(
55 WINDOWS_1255_HEBREW_MODEL, is_reversed=False, name_prober=hebrew_prober
56 )
57 # TODO: See if using ISO-8859-8 Hebrew model works better here, since
58 # it's actually the visual one
59 visual_hebrew_prober = SingleByteCharSetProber(
60 WINDOWS_1255_HEBREW_MODEL, is_reversed=True, name_prober=hebrew_prober
61 )
62 hebrew_prober.set_model_probers(logical_hebrew_prober, visual_hebrew_prober)
63 # TODO: ORDER MATTERS HERE. I changed the order vs what was in master
64 # and several tests failed that did not before. Some thought
65 # should be put into the ordering, and we should consider making
66 # order not matter here, because that is very counter-intuitive.
67 self.probers = [
68 SingleByteCharSetProber(WINDOWS_1251_RUSSIAN_MODEL),
69 SingleByteCharSetProber(KOI8_R_RUSSIAN_MODEL),
70 SingleByteCharSetProber(ISO_8859_5_RUSSIAN_MODEL),
71 SingleByteCharSetProber(MACCYRILLIC_RUSSIAN_MODEL),
72 SingleByteCharSetProber(IBM866_RUSSIAN_MODEL),
73 SingleByteCharSetProber(IBM855_RUSSIAN_MODEL),
74 SingleByteCharSetProber(ISO_8859_7_GREEK_MODEL),
75 SingleByteCharSetProber(WINDOWS_1253_GREEK_MODEL),
76 SingleByteCharSetProber(ISO_8859_5_BULGARIAN_MODEL),
77 SingleByteCharSetProber(WINDOWS_1251_BULGARIAN_MODEL),
78 # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250)
79 # after we retrain model.
80 # SingleByteCharSetProber(ISO_8859_2_HUNGARIAN_MODEL),
81 # SingleByteCharSetProber(WINDOWS_1250_HUNGARIAN_MODEL),
82 SingleByteCharSetProber(TIS_620_THAI_MODEL),
83 SingleByteCharSetProber(ISO_8859_9_TURKISH_MODEL),
84 hebrew_prober,
85 logical_hebrew_prober,
86 visual_hebrew_prober,
87 ]
88 self.reset()
Browse
Usage
Versions