Mercurial Repositories > eric / file comparison
comparison: eric6/ThirdParty/CharDet/chardet/sbcsgroupprober.py
eric6/ThirdParty/CharDet/chardet/sbcsgroupprober.py
- changeset 8258
- 82b608e352ec
- parent 8257
- 28146736bbfc
- child 8259
- 2bbec88047dd
equal
deleted
inserted
replaced
| 8257:28146736bbfc | 8258:82b608e352ec |
|---|---|
| 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, | |
| 32 WINDOWS_1251_BULGARIAN_MODEL) | |
| 33 from .langgreekmodel import ISO_8859_7_GREEK_MODEL, WINDOWS_1253_GREEK_MODEL | |
| 34 from .langhebrewmodel import WINDOWS_1255_HEBREW_MODEL | |
| 35 # from .langhungarianmodel import (ISO_8859_2_HUNGARIAN_MODEL, | |
| 36 # WINDOWS_1250_HUNGARIAN_MODEL) | |
| 37 from .langrussianmodel import (IBM855_RUSSIAN_MODEL, IBM866_RUSSIAN_MODEL, | |
| 38 ISO_8859_5_RUSSIAN_MODEL, KOI8_R_RUSSIAN_MODEL, | |
| 39 MACCYRILLIC_RUSSIAN_MODEL, | |
| 40 WINDOWS_1251_RUSSIAN_MODEL) | |
| 41 from .langthaimodel import TIS_620_THAI_MODEL | |
| 42 from .langturkishmodel import ISO_8859_9_TURKISH_MODEL | |
| 43 from .sbcharsetprober import SingleByteCharSetProber | |
| 44 | |
| 45 | |
| 46 class SBCSGroupProber(CharSetGroupProber): | |
| 47 def __init__(self): | |
| 48 super(SBCSGroupProber, self).__init__() | |
| 49 hebrew_prober = HebrewProber() | |
| 50 logical_hebrew_prober = SingleByteCharSetProber(WINDOWS_1255_HEBREW_MODEL, | |
| 51 False, hebrew_prober) | |
| 52 # TODO: See if using ISO-8859-8 Hebrew model works better here, since | |
| 53 # it's actually the visual one | |
| 54 visual_hebrew_prober = SingleByteCharSetProber(WINDOWS_1255_HEBREW_MODEL, | |
| 55 True, hebrew_prober) | |
| 56 hebrew_prober.set_model_probers(logical_hebrew_prober, | |
| 57 visual_hebrew_prober) | |
| 58 # TODO: ORDER MATTERS HERE. I changed the order vs what was in master | |
| 59 # and several tests failed that did not before. Some thought | |
| 60 # should be put into the ordering, and we should consider making | |
| 61 # order not matter here, because that is very counter-intuitive. | |
| 62 self.probers = [ | |
| 63 SingleByteCharSetProber(WINDOWS_1251_RUSSIAN_MODEL), | |
| 64 SingleByteCharSetProber(KOI8_R_RUSSIAN_MODEL), | |
| 65 SingleByteCharSetProber(ISO_8859_5_RUSSIAN_MODEL), | |
| 66 SingleByteCharSetProber(MACCYRILLIC_RUSSIAN_MODEL), | |
| 67 SingleByteCharSetProber(IBM866_RUSSIAN_MODEL), | |
| 68 SingleByteCharSetProber(IBM855_RUSSIAN_MODEL), | |
| 69 SingleByteCharSetProber(ISO_8859_7_GREEK_MODEL), | |
| 70 SingleByteCharSetProber(WINDOWS_1253_GREEK_MODEL), | |
| 71 SingleByteCharSetProber(ISO_8859_5_BULGARIAN_MODEL), | |
| 72 SingleByteCharSetProber(WINDOWS_1251_BULGARIAN_MODEL), | |
| 73 # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250) | |
| 74 # after we retrain model. | |
| 75 # SingleByteCharSetProber(ISO_8859_2_HUNGARIAN_MODEL), | |
| 76 # SingleByteCharSetProber(WINDOWS_1250_HUNGARIAN_MODEL), | |
| 77 SingleByteCharSetProber(TIS_620_THAI_MODEL), | |
| 78 SingleByteCharSetProber(ISO_8859_9_TURKISH_MODEL), | |
| 79 hebrew_prober, | |
| 80 logical_hebrew_prober, | |
| 81 visual_hebrew_prober, | |
| 82 ] | |
| 83 self.reset() |
