######################## BEGIN LICENSE BLOCK ######################## # The Original Code is Mozilla Universal charset detector code. # # The Initial Developer of the Original Code is # Netscape Communications Corporation. # Portions created by the Initial Developer are Copyright (C) 2001 # the Initial Developer. All Rights Reserved. # # Contributor(s): # Mark Pilgrim - port to Python # Shy Shalom - original C code # # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the Free Software # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA # 02110-1301 USA ######################### END LICENSE BLOCK ######################### from .charsetgroupprober import CharSetGroupProber from .hebrewprober import HebrewProber from .langbulgarianmodel import (ISO_8859_5_BULGARIAN_MODEL, WINDOWS_1251_BULGARIAN_MODEL) from .langgreekmodel import ISO_8859_7_GREEK_MODEL, WINDOWS_1253_GREEK_MODEL from .langhebrewmodel import WINDOWS_1255_HEBREW_MODEL # from .langhungarianmodel import (ISO_8859_2_HUNGARIAN_MODEL, # WINDOWS_1250_HUNGARIAN_MODEL) from .langrussianmodel import (IBM855_RUSSIAN_MODEL, IBM866_RUSSIAN_MODEL, ISO_8859_5_RUSSIAN_MODEL, KOI8_R_RUSSIAN_MODEL, MACCYRILLIC_RUSSIAN_MODEL, WINDOWS_1251_RUSSIAN_MODEL) from .langthaimodel import TIS_620_THAI_MODEL from .langturkishmodel import ISO_8859_9_TURKISH_MODEL from .sbcharsetprober import SingleByteCharSetProber class SBCSGroupProber(CharSetGroupProber): def __init__(self): super(SBCSGroupProber, self).__init__() hebrew_prober = HebrewProber() logical_hebrew_prober = SingleByteCharSetProber(WINDOWS_1255_HEBREW_MODEL, False, hebrew_prober) # TODO: See if using ISO-8859-8 Hebrew model works better here, since # it's actually the visual one visual_hebrew_prober = SingleByteCharSetProber(WINDOWS_1255_HEBREW_MODEL, True, hebrew_prober) hebrew_prober.set_model_probers(logical_hebrew_prober, visual_hebrew_prober) # TODO: ORDER MATTERS HERE. I changed the order vs what was in master # and several tests failed that did not before. Some thought # should be put into the ordering, and we should consider making # order not matter here, because that is very counter-intuitive. self.probers = [ SingleByteCharSetProber(WINDOWS_1251_RUSSIAN_MODEL), SingleByteCharSetProber(KOI8_R_RUSSIAN_MODEL), SingleByteCharSetProber(ISO_8859_5_RUSSIAN_MODEL), SingleByteCharSetProber(MACCYRILLIC_RUSSIAN_MODEL), SingleByteCharSetProber(IBM866_RUSSIAN_MODEL), SingleByteCharSetProber(IBM855_RUSSIAN_MODEL), SingleByteCharSetProber(ISO_8859_7_GREEK_MODEL), SingleByteCharSetProber(WINDOWS_1253_GREEK_MODEL), SingleByteCharSetProber(ISO_8859_5_BULGARIAN_MODEL), SingleByteCharSetProber(WINDOWS_1251_BULGARIAN_MODEL), # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250) # after we retrain model. # SingleByteCharSetProber(ISO_8859_2_HUNGARIAN_MODEL), # SingleByteCharSetProber(WINDOWS_1250_HUNGARIAN_MODEL), SingleByteCharSetProber(TIS_620_THAI_MODEL), SingleByteCharSetProber(ISO_8859_9_TURKISH_MODEL), hebrew_prober, logical_hebrew_prober, visual_hebrew_prober, ] self.reset()
Name | Type | Size | Permission | Actions |
---|---|---|---|---|
__pycache__ | Folder | 0755 |
|
|
cli | Folder | 0755 |
|
|
metadata | Folder | 0755 |
|
|
__init__.py | File | 3.19 KB | 0644 |
|
big5freq.py | File | 30.52 KB | 0644 |
|
big5prober.py | File | 1.72 KB | 0644 |
|
chardistribution.py | File | 9.19 KB | 0644 |
|
charsetgroupprober.py | File | 3.75 KB | 0644 |
|
charsetprober.py | File | 4.99 KB | 0644 |
|
codingstatemachine.py | File | 3.51 KB | 0644 |
|
compat.py | File | 1.17 KB | 0644 |
|
cp949prober.py | File | 1.81 KB | 0644 |
|
enums.py | File | 1.62 KB | 0644 |
|
escprober.py | File | 3.86 KB | 0644 |
|
escsm.py | File | 10.26 KB | 0644 |
|
eucjpprober.py | File | 3.66 KB | 0644 |
|
euckrfreq.py | File | 13.23 KB | 0644 |
|
euckrprober.py | File | 1.71 KB | 0644 |
|
euctwfreq.py | File | 30.88 KB | 0644 |
|
euctwprober.py | File | 1.71 KB | 0644 |
|
gb2312freq.py | File | 20.23 KB | 0644 |
|
gb2312prober.py | File | 1.71 KB | 0644 |
|
hebrewprober.py | File | 13.51 KB | 0644 |
|
jisfreq.py | File | 25.17 KB | 0644 |
|
jpcntx.py | File | 19.18 KB | 0644 |
|
langbulgarianmodel.py | File | 103.21 KB | 0644 |
|
langgreekmodel.py | File | 97.23 KB | 0644 |
|
langhebrewmodel.py | File | 96.45 KB | 0644 |
|
langhungarianmodel.py | File | 100.08 KB | 0644 |
|
langrussianmodel.py | File | 128.09 KB | 0644 |
|
langthaimodel.py | File | 100.88 KB | 0644 |
|
langturkishmodel.py | File | 93.69 KB | 0644 |
|
latin1prober.py | File | 5.24 KB | 0644 |
|
mbcharsetprober.py | File | 3.33 KB | 0644 |
|
mbcsgroupprober.py | File | 1.96 KB | 0644 |
|
mbcssm.py | File | 24.88 KB | 0644 |
|
sbcharsetprober.py | File | 5.99 KB | 0644 |
|
sbcsgroupprober.py | File | 4.21 KB | 0644 |
|
sjisprober.py | File | 3.69 KB | 0644 |
|
universaldetector.py | File | 12.21 KB | 0644 |
|
utf8prober.py | File | 2.7 KB | 0644 |
|
version.py | File | 242 B | 0644 |
|