cchardet 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +8 -0
- data/.gitmodules +3 -0
- data/.rubocop.yml +11 -0
- data/CHANGELOG.md +5 -0
- data/Gemfile +10 -0
- data/README.md +35 -0
- data/Rakefile +15 -0
- data/cchardet.gemspec +30 -0
- data/ext/cchardet/extconf.rb +26 -0
- data/ext/uchardet/.gitignore +1 -0
- data/ext/uchardet/.gitlab-ci.yml +106 -0
- data/ext/uchardet/AUTHORS +16 -0
- data/ext/uchardet/CMakeLists.txt +74 -0
- data/ext/uchardet/COPYING +1316 -0
- data/ext/uchardet/INSTALL +26 -0
- data/ext/uchardet/README.md +295 -0
- data/ext/uchardet/build-mac/uchardet.cpp +7 -0
- data/ext/uchardet/build-mac/uchardet.xcodeproj/project.pbxproj +543 -0
- data/ext/uchardet/build-mac/uchardet.xcodeproj/project.xcworkspace/contents.xcworkspacedata +7 -0
- data/ext/uchardet/build-mac/uchardet.xcodeproj/project.xcworkspace/xcshareddata/uchardet.xccheckout +41 -0
- data/ext/uchardet/build-mac/uchardet.xcodeproj/xcshareddata/xcschemes/uchardet-ios.xcscheme +77 -0
- data/ext/uchardet/build-mac/uchardet.xcodeproj/xcshareddata/xcschemes/uchardet.xcscheme +77 -0
- data/ext/uchardet/doc/CMakeLists.txt +6 -0
- data/ext/uchardet/doc/README.maintainer +59 -0
- data/ext/uchardet/doc/uchardet.1 +18 -0
- data/ext/uchardet/script/BuildLangModel.py +533 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangArabicModel.log +142 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangCroatianModel.log +157 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangCzechModel.log +161 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangDanishModel.log +158 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangEsperantoModel.log +110 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangEstonianModel.log +159 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangFinnishModel.log +156 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangFrenchModel.log +116 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangGermanModel.log +159 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangGreekModel.log +272 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangHungarianModel.log +109 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangIrishModel.log +156 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangItalianModel.log +162 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangLatvianModel.log +162 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangLithuanianModel.log +162 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangMalteseModel.log +147 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangPolishModel.log +154 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangPortugueseModel.log +166 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangRomanianModel.log +153 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangSlovakModel.log +158 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangSloveneModel.log +148 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangSpanishModel.log +109 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangSwedishModel.log +151 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangThaiModel.log +141 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangTurkishModel.log +113 -0
- data/ext/uchardet/script/BuildLangModelLogs/LangVietnameseModel.log +121 -0
- data/ext/uchardet/script/README +63 -0
- data/ext/uchardet/script/charsets/codepoints.py +53 -0
- data/ext/uchardet/script/charsets/db.py +73 -0
- data/ext/uchardet/script/charsets/ibm852.py +72 -0
- data/ext/uchardet/script/charsets/iso-8859-1.py +85 -0
- data/ext/uchardet/script/charsets/iso-8859-10.py +73 -0
- data/ext/uchardet/script/charsets/iso-8859-11.py +77 -0
- data/ext/uchardet/script/charsets/iso-8859-13.py +72 -0
- data/ext/uchardet/script/charsets/iso-8859-15.py +80 -0
- data/ext/uchardet/script/charsets/iso-8859-16.py +83 -0
- data/ext/uchardet/script/charsets/iso-8859-2.py +73 -0
- data/ext/uchardet/script/charsets/iso-8859-3.py +75 -0
- data/ext/uchardet/script/charsets/iso-8859-4.py +73 -0
- data/ext/uchardet/script/charsets/iso-8859-6.py +73 -0
- data/ext/uchardet/script/charsets/iso-8859-7.py +73 -0
- data/ext/uchardet/script/charsets/iso-8859-9.py +76 -0
- data/ext/uchardet/script/charsets/mac-centraleurope.py +72 -0
- data/ext/uchardet/script/charsets/tis-620.py +77 -0
- data/ext/uchardet/script/charsets/viscii.py +72 -0
- data/ext/uchardet/script/charsets/windows-1250.py +75 -0
- data/ext/uchardet/script/charsets/windows-1252.py +76 -0
- data/ext/uchardet/script/charsets/windows-1253.py +72 -0
- data/ext/uchardet/script/charsets/windows-1256.py +75 -0
- data/ext/uchardet/script/charsets/windows-1257.py +72 -0
- data/ext/uchardet/script/charsets/windows-1258.py +72 -0
- data/ext/uchardet/script/debug.sh +9 -0
- data/ext/uchardet/script/header-template.cpp +38 -0
- data/ext/uchardet/script/langs/ar.py +59 -0
- data/ext/uchardet/script/langs/cs.py +80 -0
- data/ext/uchardet/script/langs/da.py +69 -0
- data/ext/uchardet/script/langs/de.py +69 -0
- data/ext/uchardet/script/langs/el.py +55 -0
- data/ext/uchardet/script/langs/eo.py +67 -0
- data/ext/uchardet/script/langs/es.py +69 -0
- data/ext/uchardet/script/langs/et.py +57 -0
- data/ext/uchardet/script/langs/fi.py +60 -0
- data/ext/uchardet/script/langs/fr.py +79 -0
- data/ext/uchardet/script/langs/ga.py +60 -0
- data/ext/uchardet/script/langs/hr.py +59 -0
- data/ext/uchardet/script/langs/hu.py +66 -0
- data/ext/uchardet/script/langs/it.py +56 -0
- data/ext/uchardet/script/langs/lt.py +70 -0
- data/ext/uchardet/script/langs/lv.py +69 -0
- data/ext/uchardet/script/langs/mt.py +80 -0
- data/ext/uchardet/script/langs/pl.py +81 -0
- data/ext/uchardet/script/langs/pt.py +80 -0
- data/ext/uchardet/script/langs/ro.py +65 -0
- data/ext/uchardet/script/langs/sk.py +80 -0
- data/ext/uchardet/script/langs/sl.py +59 -0
- data/ext/uchardet/script/langs/sv.py +56 -0
- data/ext/uchardet/script/langs/th.py +55 -0
- data/ext/uchardet/script/langs/tr.py +67 -0
- data/ext/uchardet/script/langs/vi.py +64 -0
- data/ext/uchardet/script/release.sh +8 -0
- data/ext/uchardet/script/win32.sh +7 -0
- data/ext/uchardet/src/Big5Freq.tab +943 -0
- data/ext/uchardet/src/CMakeLists.txt +160 -0
- data/ext/uchardet/src/CharDistribution.cpp +109 -0
- data/ext/uchardet/src/CharDistribution.h +242 -0
- data/ext/uchardet/src/EUCKRFreq.tab +614 -0
- data/ext/uchardet/src/EUCTWFreq.tab +447 -0
- data/ext/uchardet/src/GB2312Freq.tab +491 -0
- data/ext/uchardet/src/JISFreq.tab +589 -0
- data/ext/uchardet/src/JpCntx.cpp +230 -0
- data/ext/uchardet/src/JpCntx.h +140 -0
- data/ext/uchardet/src/LangModels/LangArabicModel.cpp +267 -0
- data/ext/uchardet/src/LangModels/LangBulgarianModel.cpp +249 -0
- data/ext/uchardet/src/LangModels/LangCroatianModel.cpp +298 -0
- data/ext/uchardet/src/LangModels/LangCzechModel.cpp +285 -0
- data/ext/uchardet/src/LangModels/LangDanishModel.cpp +201 -0
- data/ext/uchardet/src/LangModels/LangEsperantoModel.cpp +142 -0
- data/ext/uchardet/src/LangModels/LangEstonianModel.cpp +268 -0
- data/ext/uchardet/src/LangModels/LangFinnishModel.cpp +297 -0
- data/ext/uchardet/src/LangModels/LangFrenchModel.cpp +209 -0
- data/ext/uchardet/src/LangModels/LangGermanModel.cpp +170 -0
- data/ext/uchardet/src/LangModels/LangGreekModel.cpp +231 -0
- data/ext/uchardet/src/LangModels/LangHebrewModel.cpp +220 -0
- data/ext/uchardet/src/LangModels/LangHungarianModel.cpp +171 -0
- data/ext/uchardet/src/LangModels/LangIrishModel.cpp +234 -0
- data/ext/uchardet/src/LangModels/LangItalianModel.cpp +269 -0
- data/ext/uchardet/src/LangModels/LangLatvianModel.cpp +210 -0
- data/ext/uchardet/src/LangModels/LangLithuanianModel.cpp +209 -0
- data/ext/uchardet/src/LangModels/LangMalteseModel.cpp +138 -0
- data/ext/uchardet/src/LangModels/LangPolishModel.cpp +304 -0
- data/ext/uchardet/src/LangModels/LangPortugueseModel.cpp +241 -0
- data/ext/uchardet/src/LangModels/LangRomanianModel.cpp +236 -0
- data/ext/uchardet/src/LangModels/LangRussianModel.cpp +367 -0
- data/ext/uchardet/src/LangModels/LangSlovakModel.cpp +293 -0
- data/ext/uchardet/src/LangModels/LangSloveneModel.cpp +264 -0
- data/ext/uchardet/src/LangModels/LangSpanishModel.cpp +204 -0
- data/ext/uchardet/src/LangModels/LangSwedishModel.cpp +266 -0
- data/ext/uchardet/src/LangModels/LangThaiModel.cpp +267 -0
- data/ext/uchardet/src/LangModels/LangTurkishModel.cpp +175 -0
- data/ext/uchardet/src/LangModels/LangVietnameseModel.cpp +249 -0
- data/ext/uchardet/src/nsBig5Prober.cpp +88 -0
- data/ext/uchardet/src/nsBig5Prober.h +75 -0
- data/ext/uchardet/src/nsCharSetProber.cpp +125 -0
- data/ext/uchardet/src/nsCharSetProber.h +77 -0
- data/ext/uchardet/src/nsCodingStateMachine.h +105 -0
- data/ext/uchardet/src/nsEUCJPProber.cpp +99 -0
- data/ext/uchardet/src/nsEUCJPProber.h +79 -0
- data/ext/uchardet/src/nsEUCKRProber.cpp +91 -0
- data/ext/uchardet/src/nsEUCKRProber.h +81 -0
- data/ext/uchardet/src/nsEUCTWProber.cpp +91 -0
- data/ext/uchardet/src/nsEUCTWProber.h +75 -0
- data/ext/uchardet/src/nsEscCharsetProber.cpp +101 -0
- data/ext/uchardet/src/nsEscCharsetProber.h +70 -0
- data/ext/uchardet/src/nsEscSM.cpp +267 -0
- data/ext/uchardet/src/nsGB2312Prober.cpp +96 -0
- data/ext/uchardet/src/nsGB2312Prober.h +77 -0
- data/ext/uchardet/src/nsHebrewProber.cpp +194 -0
- data/ext/uchardet/src/nsHebrewProber.h +177 -0
- data/ext/uchardet/src/nsLatin1Prober.cpp +182 -0
- data/ext/uchardet/src/nsLatin1Prober.h +73 -0
- data/ext/uchardet/src/nsMBCSGroupProber.cpp +242 -0
- data/ext/uchardet/src/nsMBCSGroupProber.h +81 -0
- data/ext/uchardet/src/nsMBCSSM.cpp +513 -0
- data/ext/uchardet/src/nsPkgInt.h +89 -0
- data/ext/uchardet/src/nsSBCSGroupProber.cpp +343 -0
- data/ext/uchardet/src/nsSBCSGroupProber.h +71 -0
- data/ext/uchardet/src/nsSBCharSetProber.cpp +160 -0
- data/ext/uchardet/src/nsSBCharSetProber.h +258 -0
- data/ext/uchardet/src/nsSJISProber.cpp +98 -0
- data/ext/uchardet/src/nsSJISProber.h +81 -0
- data/ext/uchardet/src/nsUTF8Prober.cpp +87 -0
- data/ext/uchardet/src/nsUTF8Prober.h +66 -0
- data/ext/uchardet/src/nsUniversalDetector.cpp +339 -0
- data/ext/uchardet/src/nsUniversalDetector.h +91 -0
- data/ext/uchardet/src/nscore.h +59 -0
- data/ext/uchardet/src/prmem.h +49 -0
- data/ext/uchardet/src/symbols.cmake +41 -0
- data/ext/uchardet/src/tools/CMakeLists.txt +23 -0
- data/ext/uchardet/src/tools/uchardet.cpp +254 -0
- data/ext/uchardet/src/uchardet.cpp +274 -0
- data/ext/uchardet/src/uchardet.h +136 -0
- data/ext/uchardet/test/CMakeLists.txt +47 -0
- data/ext/uchardet/test/ar/iso-8859-6.txt +3 -0
- data/ext/uchardet/test/ar/utf-8.txt +3 -0
- data/ext/uchardet/test/ar/windows-1256.txt +3 -0
- data/ext/uchardet/test/bg/windows-1251.txt +3 -0
- data/ext/uchardet/test/cs/ibm852.txt +4 -0
- data/ext/uchardet/test/cs/iso-8859-2.txt +4 -0
- data/ext/uchardet/test/cs/mac-centraleurope.txt +4 -0
- data/ext/uchardet/test/cs/utf-8.txt +4 -0
- data/ext/uchardet/test/cs/windows-1250.txt +4 -0
- data/ext/uchardet/test/da/iso-8859-1.txt +7 -0
- data/ext/uchardet/test/da/iso-8859-15.txt +10 -0
- data/ext/uchardet/test/da/utf-8.txt +10 -0
- data/ext/uchardet/test/da/windows-1252.txt +10 -0
- data/ext/uchardet/test/de/iso-8859-1.txt +11 -0
- data/ext/uchardet/test/de/windows-1252.txt +11 -0
- data/ext/uchardet/test/el/iso-8859-7.txt +3 -0
- data/ext/uchardet/test/el/utf-8.txt +3 -0
- data/ext/uchardet/test/el/windows-1253.txt +5 -0
- data/ext/uchardet/test/en/ascii.txt +4 -0
- data/ext/uchardet/test/eo/iso-8859-3.txt +7 -0
- data/ext/uchardet/test/es/iso-8859-1.txt +5 -0
- data/ext/uchardet/test/es/iso-8859-15.txt +5 -0
- data/ext/uchardet/test/es/utf-8.txt +5 -0
- data/ext/uchardet/test/es/windows-1252.txt +5 -0
- data/ext/uchardet/test/et/iso-8859-13.txt +6 -0
- data/ext/uchardet/test/et/iso-8859-15.txt +6 -0
- data/ext/uchardet/test/et/iso-8859-4.txt +6 -0
- data/ext/uchardet/test/et/utf-8.txt +6 -0
- data/ext/uchardet/test/et/windows-1252.txt +6 -0
- data/ext/uchardet/test/et/windows-1257.txt +6 -0
- data/ext/uchardet/test/fi/iso-8859-1.txt +8 -0
- data/ext/uchardet/test/fi/utf-8.txt +8 -0
- data/ext/uchardet/test/fr/iso-8859-1.txt +5 -0
- data/ext/uchardet/test/fr/iso-8859-15.txt +16 -0
- data/ext/uchardet/test/fr/utf-16.be +0 -0
- data/ext/uchardet/test/fr/utf-32.le +0 -0
- data/ext/uchardet/test/fr/utf-8.txt +14 -0
- data/ext/uchardet/test/fr/windows-1252.txt +3 -0
- data/ext/uchardet/test/ga/iso-8859-1.txt +6 -0
- data/ext/uchardet/test/ga/utf-8.txt +6 -0
- data/ext/uchardet/test/ga/windows-1252.txt +6 -0
- data/ext/uchardet/test/he/iso-8859-8.txt +2 -0
- data/ext/uchardet/test/he/utf-8.txt +3 -0
- data/ext/uchardet/test/he/windows-1255.txt +1 -0
- data/ext/uchardet/test/hr/ibm852.txt +4 -0
- data/ext/uchardet/test/hr/iso-8859-13.txt +4 -0
- data/ext/uchardet/test/hr/iso-8859-16.txt +4 -0
- data/ext/uchardet/test/hr/iso-8859-2.txt +4 -0
- data/ext/uchardet/test/hr/mac-centraleurope.txt +4 -0
- data/ext/uchardet/test/hr/utf-8.txt +4 -0
- data/ext/uchardet/test/hr/windows-1250.txt +4 -0
- data/ext/uchardet/test/hu/iso-8859-2.txt +3 -0
- data/ext/uchardet/test/hu/windows-1250.txt +1 -0
- data/ext/uchardet/test/it/iso-8859-1.txt +18 -0
- data/ext/uchardet/test/it/utf-8.txt +18 -0
- data/ext/uchardet/test/ja/euc-jp.txt +10 -0
- data/ext/uchardet/test/ja/iso-2022-jp.txt +8 -0
- data/ext/uchardet/test/ja/shift_jis.txt +1 -0
- data/ext/uchardet/test/ja/utf-16be.txt +0 -0
- data/ext/uchardet/test/ja/utf-16le.txt +0 -0
- data/ext/uchardet/test/ja/utf-8.txt +9 -0
- data/ext/uchardet/test/ko/iso-2022-kr.txt +8 -0
- data/ext/uchardet/test/ko/uhc.smi +16 -0
- data/ext/uchardet/test/ko/utf-16.le +0 -0
- data/ext/uchardet/test/ko/utf-32.be +0 -0
- data/ext/uchardet/test/ko/utf-8.txt +3 -0
- data/ext/uchardet/test/lt/iso-8859-10.txt +3 -0
- data/ext/uchardet/test/lt/iso-8859-13.txt +3 -0
- data/ext/uchardet/test/lt/iso-8859-4.txt +3 -0
- data/ext/uchardet/test/lt/utf-8.txt +3 -0
- data/ext/uchardet/test/lv/iso-8859-10.txt +6 -0
- data/ext/uchardet/test/lv/iso-8859-13.txt +6 -0
- data/ext/uchardet/test/lv/iso-8859-4.txt +6 -0
- data/ext/uchardet/test/lv/utf-8.txt +6 -0
- data/ext/uchardet/test/mt/iso-8859-3.txt +4 -0
- data/ext/uchardet/test/mt/utf-8.txt +4 -0
- data/ext/uchardet/test/pl/ibm852.txt +3 -0
- data/ext/uchardet/test/pl/iso-8859-13.txt +3 -0
- data/ext/uchardet/test/pl/iso-8859-16.txt +3 -0
- data/ext/uchardet/test/pl/iso-8859-2.txt +3 -0
- data/ext/uchardet/test/pl/mac-centraleurope.txt +3 -0
- data/ext/uchardet/test/pl/utf-8.txt +3 -0
- data/ext/uchardet/test/pl/windows-1250.txt +3 -0
- data/ext/uchardet/test/pt/iso-8859-1.txt +6 -0
- data/ext/uchardet/test/pt/utf-8.txt +6 -0
- data/ext/uchardet/test/ro/ibm852.txt +9 -0
- data/ext/uchardet/test/ro/iso-8859-16.txt +9 -0
- data/ext/uchardet/test/ro/utf-8.txt +9 -0
- data/ext/uchardet/test/ro/windows-1250.txt +9 -0
- data/ext/uchardet/test/ru/ibm855.txt +5 -0
- data/ext/uchardet/test/ru/ibm866.txt +11 -0
- data/ext/uchardet/test/ru/iso-8859-5.txt +3 -0
- data/ext/uchardet/test/ru/koi8-r.txt +1 -0
- data/ext/uchardet/test/ru/mac-cyrillic.txt +9 -0
- data/ext/uchardet/test/ru/windows-1251.txt +4 -0
- data/ext/uchardet/test/sk/ibm852.txt +3 -0
- data/ext/uchardet/test/sk/iso-8859-2.txt +3 -0
- data/ext/uchardet/test/sk/mac-centraleurope.txt +3 -0
- data/ext/uchardet/test/sk/utf-8.txt +3 -0
- data/ext/uchardet/test/sk/windows-1250.txt +3 -0
- data/ext/uchardet/test/sl/ibm852.txt +9 -0
- data/ext/uchardet/test/sl/iso-8859-16.txt +9 -0
- data/ext/uchardet/test/sl/iso-8859-2.txt +9 -0
- data/ext/uchardet/test/sl/mac-centraleurope.txt +9 -0
- data/ext/uchardet/test/sl/utf-8.txt +9 -0
- data/ext/uchardet/test/sl/windows-1250.txt +9 -0
- data/ext/uchardet/test/sv/iso-8859-1.txt +10 -0
- data/ext/uchardet/test/sv/utf-8.txt +10 -0
- data/ext/uchardet/test/sv/windows-1252.txt +10 -0
- data/ext/uchardet/test/th/iso-8859-11.txt +5 -0
- data/ext/uchardet/test/th/tis-620.txt +5 -0
- data/ext/uchardet/test/th/utf-8.txt +1 -0
- data/ext/uchardet/test/tr/iso-8859-3.txt +13 -0
- data/ext/uchardet/test/tr/iso-8859-9.txt +13 -0
- data/ext/uchardet/test/uchardet-tests.c +130 -0
- data/ext/uchardet/test/vi/utf-8.txt +4 -0
- data/ext/uchardet/test/vi/viscii.txt +4 -0
- data/ext/uchardet/test/vi/windows-1258.txt +4 -0
- data/ext/uchardet/test/zh/big5.txt +1 -0
- data/ext/uchardet/test/zh/euc-tw.txt +1 -0
- data/ext/uchardet/test/zh/gb18030.txt +1 -0
- data/ext/uchardet/test/zh/utf-8.txt +1 -0
- data/ext/uchardet/uchardet.doap +51 -0
- data/ext/uchardet/uchardet.pc.in +10 -0
- data/lib/cchardet.rb +56 -0
- data/lib/cchardet/lib_finder.rb +32 -0
- data/lib/cchardet/version.rb +5 -0
- metadata +362 -0
@@ -0,0 +1,113 @@
|
|
1
|
+
= Logs of language model for Turkish (tr) =
|
2
|
+
|
3
|
+
- Generated by BuildLangModel.py
|
4
|
+
- Started: 2015-12-04 02:22:03.929245
|
5
|
+
- Maximum depth: 3
|
6
|
+
- Max number of pages: 50
|
7
|
+
|
8
|
+
== Parsed pages ==
|
9
|
+
|
10
|
+
Ana_Sayfa (revision 16293313)
|
11
|
+
1048 (revision 12894005)
|
12
|
+
1131 (revision 14840814)
|
13
|
+
16. yüzyıl (revision 15185081)
|
14
|
+
1859 (revision 16014427)
|
15
|
+
1866 (revision 16120346)
|
16
|
+
1869 (revision 12888270)
|
17
|
+
1892 (revision 13955858)
|
18
|
+
1895 (revision 15334635)
|
19
|
+
1902 (revision 16283638)
|
20
|
+
1906 (revision 15874323)
|
21
|
+
1918 (revision 16099474)
|
22
|
+
1926 (revision 16180584)
|
23
|
+
1927 (revision 15370980)
|
24
|
+
1940 (revision 15370990)
|
25
|
+
1943 (revision 16091797)
|
26
|
+
1944 (revision 16247827)
|
27
|
+
1945 (revision 16281147)
|
28
|
+
1948 (revision 15443886)
|
29
|
+
1961 (revision 15799529)
|
30
|
+
1964 (revision 16085332)
|
31
|
+
1975 (revision 15006928)
|
32
|
+
1980 (revision 16213240)
|
33
|
+
1981 (revision 16295456)
|
34
|
+
1983 (revision 16327128)
|
35
|
+
1993 (revision 16300456)
|
36
|
+
2002 (revision 16297206)
|
37
|
+
2015 (revision 16328338)
|
38
|
+
24 Ekim (revision 16213661)
|
39
|
+
4 Aralık (revision 16341162)
|
40
|
+
ABD (revision 16325951)
|
41
|
+
ABD Senatosu (revision 15970439)
|
42
|
+
Adam Horowitz (revision 14362106)
|
43
|
+
Akçe (revision 16261547)
|
44
|
+
Altın Takım (revision 13503001)
|
45
|
+
American Broadcasting Company (revision 16055235)
|
46
|
+
Amerika Birleşik Devletleri (revision 16325951)
|
47
|
+
Ana Sayfa/Kardeş projeler (revision 16293313)
|
48
|
+
Ana Sayfa/Kategoriler (revision 16293313)
|
49
|
+
Aptullah Kuran (revision 15744893)
|
50
|
+
Avrupa (revision 16299756)
|
51
|
+
Ayasofya (revision 16305207)
|
52
|
+
BM Güvenlik Konseyi (revision 16085518)
|
53
|
+
Birleşmiş Milletler (revision 16258474)
|
54
|
+
Budapeşte (revision 16219173)
|
55
|
+
CIA (revision 16054325)
|
56
|
+
Charlie Pace (revision 16129416)
|
57
|
+
Cuma (revision 14197127)
|
58
|
+
Desmond Hume (revision 16035300)
|
59
|
+
Diğerleri (Lost) (revision 16329444)
|
60
|
+
|
61
|
+
== End of Parsed pages ==
|
62
|
+
|
63
|
+
- Wikipedia parsing ended at: 2015-12-04 02:24:44.728803
|
64
|
+
|
65
|
+
48 characters appeared 267623 times.
|
66
|
+
|
67
|
+
First 36 characters:
|
68
|
+
[ 0] Char a: 12.311722086666691 %
|
69
|
+
[ 1] Char e: 8.716365932673948 %
|
70
|
+
[ 2] Char i: 8.507863673899479 %
|
71
|
+
[ 3] Char n: 7.322987934519828 %
|
72
|
+
[ 4] Char r: 6.979220769515326 %
|
73
|
+
[ 5] Char l: 6.609297407173524 %
|
74
|
+
[ 6] Char ı: 4.514933320379788 %
|
75
|
+
[ 7] Char d: 4.3475336574210734 %
|
76
|
+
[ 8] Char t: 4.2634601659797555 %
|
77
|
+
[ 9] Char k: 4.240293248338147 %
|
78
|
+
[10] Char s: 3.929781819948211 %
|
79
|
+
[11] Char m: 3.429451130881875 %
|
80
|
+
[12] Char u: 3.0998830444319063 %
|
81
|
+
[13] Char y: 2.9212735826143494 %
|
82
|
+
[14] Char o: 2.7135186437638024 %
|
83
|
+
[15] Char b: 2.3129551645411643 %
|
84
|
+
[16] Char ü: 1.8305601536489764 %
|
85
|
+
[17] Char ş: 1.5988909772328985 %
|
86
|
+
[18] Char z: 1.2267256551193282 %
|
87
|
+
[19] Char h: 1.1983274980102607 %
|
88
|
+
[20] Char v: 1.194964558352608 %
|
89
|
+
[21] Char c: 1.143773143563894 %
|
90
|
+
[22] Char g: 1.1004285879763698 %
|
91
|
+
[23] Char p: 1.0178497363828969 %
|
92
|
+
[24] Char ç: 0.8295251155543433 %
|
93
|
+
[25] Char ğ: 0.8205572764672693 %
|
94
|
+
[26] Char f: 0.7047226882592303 %
|
95
|
+
[27] Char ö: 0.6710932916827029 %
|
96
|
+
[28] Char j: 0.1296600068006113 %
|
97
|
+
[29] Char w: 0.11359262843627041 %
|
98
|
+
[30] Char â: 0.07846859201189733 %
|
99
|
+
[31] Char î: 0.04147625577771716 %
|
100
|
+
[32] Char x: 0.024287897527492032 %
|
101
|
+
[33] Char é: 0.014946398478456635 %
|
102
|
+
[34] Char q: 0.01083613889688106 %
|
103
|
+
[35] Char û: 0.009341499049035397 %
|
104
|
+
|
105
|
+
The first 36 characters have an accumulated ratio of 0.99980569681978.
|
106
|
+
|
107
|
+
935 sequences found.
|
108
|
+
|
109
|
+
First 512 (typical positive ratio): 0.991865243864388
|
110
|
+
Next 512 (512-1024): 3.7365996196141585e-06
|
111
|
+
Rest: 2.949029909160572e-17
|
112
|
+
|
113
|
+
- Processing end: 2015-12-04 02:24:44.883537
|
@@ -0,0 +1,121 @@
|
|
1
|
+
= Logs of language model for Vietnamese (vi) =
|
2
|
+
|
3
|
+
- Generated by BuildLangModel.py
|
4
|
+
- Started: 2016-02-13 03:37:17.480303
|
5
|
+
- Maximum depth: 3
|
6
|
+
- Max number of pages: 40
|
7
|
+
|
8
|
+
== Parsed pages ==
|
9
|
+
|
10
|
+
Chữ_Quốc_ngữ (revision 22887853)
|
11
|
+
1651 (revision 21455247)
|
12
|
+
1773 (revision 21354755)
|
13
|
+
1815 (revision 21361292)
|
14
|
+
1838 (revision 21361314)
|
15
|
+
1865 (revision 21361338)
|
16
|
+
1869 (revision 21361342)
|
17
|
+
1888 (revision 21389506)
|
18
|
+
1902 (revision 21354811)
|
19
|
+
1918 (revision 21354828)
|
20
|
+
1919 (revision 21354829)
|
21
|
+
1938 (revision 21354849)
|
22
|
+
1945 (revision 21354857)
|
23
|
+
22 tháng 2 (revision 21376086)
|
24
|
+
26 tháng 11 (revision 22579845)
|
25
|
+
28 tháng 12 (revision 22475308)
|
26
|
+
A (revision 22549334)
|
27
|
+
ASCII (revision 22528409)
|
28
|
+
Alexandre de Rhodes (revision 22859954)
|
29
|
+
Antonio Barbosa (revision 22145269)
|
30
|
+
B (revision 22836557)
|
31
|
+
BBC (revision 22863903)
|
32
|
+
Biên khảo (revision 22531516)
|
33
|
+
Bán nguyên âm (revision 22655600)
|
34
|
+
Bình luận (revision 22117664)
|
35
|
+
Bảng chữ cái Bồ Đào Nha (revision 22887853)
|
36
|
+
Bảng chữ cái Hy Lạp (revision 21362081)
|
37
|
+
Bảng chữ cái Latinh (revision 22442448)
|
38
|
+
Bắc Kỳ (revision 22393289)
|
39
|
+
Bồ Đào Nha (revision 22620858)
|
40
|
+
C (revision 21341881)
|
41
|
+
Cao Xuân Dục (revision 22620201)
|
42
|
+
Chính tả (revision 22187359)
|
43
|
+
Chính tả tiếng Việt (revision 20897580)
|
44
|
+
Chữ Hán (revision 22889609)
|
45
|
+
Chữ Nôm (revision 22781506)
|
46
|
+
Chữ cái (revision 22169220)
|
47
|
+
Công giáo (revision 22173119)
|
48
|
+
D (revision 21447691)
|
49
|
+
|
50
|
+
== End of Parsed pages ==
|
51
|
+
|
52
|
+
- Wikipedia parsing ended at: 2016-02-13 03:42:06.560479
|
53
|
+
|
54
|
+
101 characters appeared 222814 times.
|
55
|
+
|
56
|
+
First 55 characters:
|
57
|
+
[ 0] Char n: 11.262308472537633 %
|
58
|
+
[ 1] Char h: 8.881398834902654 %
|
59
|
+
[ 2] Char t: 7.022898022565907 %
|
60
|
+
[ 3] Char c: 6.365398942615815 %
|
61
|
+
[ 4] Char i: 6.198443544840091 %
|
62
|
+
[ 5] Char g: 5.591210606155808 %
|
63
|
+
[ 6] Char a: 3.5998635633308496 %
|
64
|
+
[ 7] Char u: 2.8499106878382867 %
|
65
|
+
[ 8] Char m: 2.615185760320267 %
|
66
|
+
[ 9] Char o: 2.6012728105056238 %
|
67
|
+
[10] Char đ: 2.222032726848403 %
|
68
|
+
[11] Char r: 2.1102803234985235 %
|
69
|
+
[12] Char à: 2.0447548179198796 %
|
70
|
+
[13] Char v: 1.9437737305555307 %
|
71
|
+
[14] Char l: 1.9119085874316697 %
|
72
|
+
[15] Char á: 1.7539292863105551 %
|
73
|
+
[16] Char p: 1.6453185167897888 %
|
74
|
+
[17] Char b: 1.541195795596327 %
|
75
|
+
[18] Char ư: 1.4397659033992478 %
|
76
|
+
[19] Char s: 1.3760356171515256 %
|
77
|
+
[20] Char y: 1.280440187779942 %
|
78
|
+
[21] Char e: 1.2454334108269678 %
|
79
|
+
[22] Char d: 1.1251537156552103 %
|
80
|
+
[23] Char ế: 1.071745940560288 %
|
81
|
+
[24] Char k: 1.0695019163966357 %
|
82
|
+
[25] Char â: 0.9658280000359044 %
|
83
|
+
[26] Char ữ: 0.9604423420431392 %
|
84
|
+
[27] Char ê: 0.8374698178749989 %
|
85
|
+
[28] Char ệ: 0.7459136319979893 %
|
86
|
+
[29] Char ô: 0.7073164163831717 %
|
87
|
+
[30] Char ạ: 0.6727584442629277 %
|
88
|
+
[31] Char ộ: 0.6705144200992756 %
|
89
|
+
[32] Char ố: 0.6476253736300233 %
|
90
|
+
[33] Char ó: 0.6072329386842837 %
|
91
|
+
[34] Char ả: 0.5484395055965963 %
|
92
|
+
[35] Char ủ: 0.5475418959311353 %
|
93
|
+
[36] Char q: 0.5138815334763525 %
|
94
|
+
[37] Char ợ: 0.48560682901433483 %
|
95
|
+
[38] Char ờ: 0.4851580241816044 %
|
96
|
+
[39] Char ể: 0.4748355130288043 %
|
97
|
+
[40] Char ớ: 0.4676546357051173 %
|
98
|
+
[41] Char ấ: 0.418286104104769 %
|
99
|
+
[42] Char ị: 0.40212913012647317 %
|
100
|
+
[43] Char ầ: 0.3904602044754818 %
|
101
|
+
[44] Char ọ: 0.3801376933226817 %
|
102
|
+
[45] Char ề: 0.3787912788244904 %
|
103
|
+
[46] Char ơ: 0.3590438661843511 %
|
104
|
+
[47] Char í: 0.35679984202069887 %
|
105
|
+
[48] Char ụ: 0.35276059852612496 %
|
106
|
+
[49] Char ậ: 0.3469261357006292 %
|
107
|
+
[50] Char ì: 0.32762752789322036 %
|
108
|
+
[51] Char ă: 0.3253835037295682 %
|
109
|
+
[52] Char ứ: 0.29665999443482005 %
|
110
|
+
[53] Char ồ: 0.29665999443482005 %
|
111
|
+
[54] Char x: 0.2939671654384374 %
|
112
|
+
|
113
|
+
The first 55 characters have an accumulated ratio of 0.9603301408349568.
|
114
|
+
|
115
|
+
1494 sequences found.
|
116
|
+
|
117
|
+
First 512 (typical positive ratio): 0.9321889118082535
|
118
|
+
Next 512 (512-1024): 0.009604423420431392
|
119
|
+
Rest: 0.0068905733918831966
|
120
|
+
|
121
|
+
- Processing end: 2016-02-13 03:42:07.174723
|
@@ -0,0 +1,63 @@
|
|
1
|
+
# Supporting new or Updating languages #
|
2
|
+
|
3
|
+
We generate statistical language data using Wikipedia as natural
|
4
|
+
language text resource.
|
5
|
+
|
6
|
+
Right now, we have automated scripts only to generate statistical data
|
7
|
+
for single-byte encodings. Multi-byte encodings usually requires more
|
8
|
+
in-depth knowledge of its specification.
|
9
|
+
|
10
|
+
## New single-byte encoding ##
|
11
|
+
|
12
|
+
Uchardet uses language data, and therefore rather than supporting a
|
13
|
+
charset, we in fact support a couple (language, charset). So for
|
14
|
+
instance if uchardet supports (French, ISO-8859-15), it should be able
|
15
|
+
to recognize French text encoded in ISO-8859-15, but may fail at
|
16
|
+
detecting ISO-8859-15 for non-supported languages.
|
17
|
+
|
18
|
+
This is why, though less flexible, it also makes uchardet much more
|
19
|
+
accurate than other detection system, as well as making it an efficient
|
20
|
+
language recognition system.
|
21
|
+
Since many single-byte charsets actually share the same layout (or very
|
22
|
+
similar ones), it is actually impossible to have an accurate single-byte
|
23
|
+
encoding detector for random text.
|
24
|
+
|
25
|
+
Therefore you need to describe the language and the codepoint layouts of
|
26
|
+
every charset you want to add support for.
|
27
|
+
|
28
|
+
I recommend having a look at langs/fr.py which is heavily commented as
|
29
|
+
a base of a new language description, and charsets/windows-1252.py as a
|
30
|
+
base for a new charset layout (note that charset layouts can be shared
|
31
|
+
between languages. If yours is already there, you have nothing to do).
|
32
|
+
The important name in the charset file are:
|
33
|
+
|
34
|
+
- `name`: an iconv-compatible name.
|
35
|
+
- `charmap`: fill it with CTR (control character), SYM (symbol), NUM
|
36
|
+
(number), LET (letter), ILL (illegal codepoint).
|
37
|
+
|
38
|
+
## Tools ##
|
39
|
+
|
40
|
+
You must install Python 3 and the [`Wikipedia` Python
|
41
|
+
tool](https://github.com/goldsmith/Wikipedia).
|
42
|
+
|
43
|
+
## Run script ##
|
44
|
+
|
45
|
+
Let's say you added (or modified) support for French (`fr`), run:
|
46
|
+
|
47
|
+
> ./BuildLangModel.py fr --max-page=100 --max-depth=4
|
48
|
+
|
49
|
+
The options can be changed to any value. Bigger values mean the script
|
50
|
+
will process more data, so more processing time now, but uchardet may
|
51
|
+
possibly be more accurate in the end.
|
52
|
+
|
53
|
+
## Updating core code ##
|
54
|
+
|
55
|
+
If you were only updating data for a language model, you have nothing
|
56
|
+
else to do. Just build `uchardet` again and test it.
|
57
|
+
|
58
|
+
If you were creating new models though, you will have to add these in
|
59
|
+
src/nsSBCSGroupProber.cpp and src/nsSBCharSetProber.h, and increase the
|
60
|
+
value of `NUM_OF_SBCS_PROBERS` in src/nsSBCSGroupProber.h.
|
61
|
+
Finally add the new file in src/CMakeLists.txt.
|
62
|
+
|
63
|
+
I will be looking to make this step more straightforward in the future.
|
@@ -0,0 +1,53 @@
|
|
1
|
+
#!/usr/bin/python3
|
2
|
+
# -*- coding: utf-8 -*-
|
3
|
+
|
4
|
+
# ##### BEGIN LICENSE BLOCK #####
|
5
|
+
# Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
6
|
+
#
|
7
|
+
# The contents of this file are subject to the Mozilla Public License Version
|
8
|
+
# 1.1 (the "License"); you may not use this file except in compliance with
|
9
|
+
# the License. You may obtain a copy of the License at
|
10
|
+
# http://www.mozilla.org/MPL/
|
11
|
+
#
|
12
|
+
# Software distributed under the License is distributed on an "AS IS" basis,
|
13
|
+
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
14
|
+
# for the specific language governing rights and limitations under the
|
15
|
+
# License.
|
16
|
+
#
|
17
|
+
# The Original Code is Mozilla Universal charset detector code.
|
18
|
+
#
|
19
|
+
# The Initial Developer of the Original Code is
|
20
|
+
# Netscape Communications Corporation.
|
21
|
+
# Portions created by the Initial Developer are Copyright (C) 2001
|
22
|
+
# the Initial Developer. All Rights Reserved.
|
23
|
+
#
|
24
|
+
# Contributor(s):
|
25
|
+
# Jehan <jehan@girinstud.io>
|
26
|
+
#
|
27
|
+
# Alternatively, the contents of this file may be used under the terms of
|
28
|
+
# either the GNU General Public License Version 2 or later (the "GPL"), or
|
29
|
+
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
30
|
+
# in which case the provisions of the GPL or the LGPL are applicable instead
|
31
|
+
# of those above. If you wish to allow use of your version of this file only
|
32
|
+
# under the terms of either the GPL or the LGPL, and not to allow others to
|
33
|
+
# use your version of this file under the terms of the MPL, indicate your
|
34
|
+
# decision by deleting the provisions above and replace them with the notice
|
35
|
+
# and other provisions required by the GPL or the LGPL. If you do not delete
|
36
|
+
# the provisions above, a recipient may use your version of this file under
|
37
|
+
# the terms of any one of the MPL, the GPL or the LGPL.
|
38
|
+
#
|
39
|
+
# ##### END LICENSE BLOCK #####
|
40
|
+
|
41
|
+
# Illegal codepoints.
|
42
|
+
ILL = 255
|
43
|
+
# Control characters
|
44
|
+
CTR = 254
|
45
|
+
# Symbols and punctuations.
|
46
|
+
SYM = 253
|
47
|
+
# Return/Line feeds.
|
48
|
+
RET = 252
|
49
|
+
# Numbers 0-9.
|
50
|
+
NUM = 251
|
51
|
+
|
52
|
+
# Letters (should be all the rest).
|
53
|
+
LET = 0
|
@@ -0,0 +1,73 @@
|
|
1
|
+
#!/usr/bin/python3
|
2
|
+
# -*- coding: utf-8 -*-
|
3
|
+
|
4
|
+
# ##### BEGIN LICENSE BLOCK #####
|
5
|
+
# Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
6
|
+
#
|
7
|
+
# The contents of this file are subject to the Mozilla Public License Version
|
8
|
+
# 1.1 (the "License"); you may not use this file except in compliance with
|
9
|
+
# the License. You may obtain a copy of the License at
|
10
|
+
# http://www.mozilla.org/MPL/
|
11
|
+
#
|
12
|
+
# Software distributed under the License is distributed on an "AS IS" basis,
|
13
|
+
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
14
|
+
# for the specific language governing rights and limitations under the
|
15
|
+
# License.
|
16
|
+
#
|
17
|
+
# The Original Code is Mozilla Universal charset detector code.
|
18
|
+
#
|
19
|
+
# The Initial Developer of the Original Code is
|
20
|
+
# Netscape Communications Corporation.
|
21
|
+
# Portions created by the Initial Developer are Copyright (C) 2001
|
22
|
+
# the Initial Developer. All Rights Reserved.
|
23
|
+
#
|
24
|
+
# Contributor(s):
|
25
|
+
# Jehan <jehan@girinstud.io>
|
26
|
+
#
|
27
|
+
# Alternatively, the contents of this file may be used under the terms of
|
28
|
+
# either the GNU General Public License Version 2 or later (the "GPL"), or
|
29
|
+
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
30
|
+
# in which case the provisions of the GPL or the LGPL are applicable instead
|
31
|
+
# of those above. If you wish to allow use of your version of this file only
|
32
|
+
# under the terms of either the GPL or the LGPL, and not to allow others to
|
33
|
+
# use your version of this file under the terms of the MPL, indicate your
|
34
|
+
# decision by deleting the provisions above and replace them with the notice
|
35
|
+
# and other provisions required by the GPL or the LGPL. If you do not delete
|
36
|
+
# the provisions above, a recipient may use your version of this file under
|
37
|
+
# the terms of any one of the MPL, the GPL or the LGPL.
|
38
|
+
#
|
39
|
+
# ##### END LICENSE BLOCK #####
|
40
|
+
|
41
|
+
import importlib
|
42
|
+
import sys
|
43
|
+
import os
|
44
|
+
|
45
|
+
def load(charset_names):
|
46
|
+
'''
|
47
|
+
Load a list of charsets.
|
48
|
+
|
49
|
+
This function will return a dictionary of charsets from our
|
50
|
+
charset database.
|
51
|
+
|
52
|
+
:param charset_names: a list of supported charset names.
|
53
|
+
:return: a dictionary with all the loaded charsets.
|
54
|
+
:rtype: dict
|
55
|
+
'''
|
56
|
+
charsets = {}
|
57
|
+
|
58
|
+
# Temporarily change the search path for modules.
|
59
|
+
sys_path_backup = sys.path
|
60
|
+
current_dir = os.path.dirname(os.path.realpath(__file__))
|
61
|
+
sys.path = [current_dir + '/../charsets']
|
62
|
+
|
63
|
+
for name in charset_names:
|
64
|
+
try:
|
65
|
+
charset = importlib.import_module(name.lower())
|
66
|
+
except ImportError:
|
67
|
+
print('Unknown charset "{}": '
|
68
|
+
'file "charsets/{}.py" does not exist.'.format(name, name.lower()))
|
69
|
+
exit(1)
|
70
|
+
charsets[charset.name] = charset
|
71
|
+
# Set back the default module paths.
|
72
|
+
sys.path = sys_path_backup
|
73
|
+
return charsets
|
@@ -0,0 +1,72 @@
|
|
1
|
+
#!/usr/bin/python
|
2
|
+
# -*- coding: utf-8 -*-
|
3
|
+
|
4
|
+
# ##### BEGIN LICENSE BLOCK #####
|
5
|
+
# Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
6
|
+
#
|
7
|
+
# The contents of this file are subject to the Mozilla Public License Version
|
8
|
+
# 1.1 (the "License"); you may not use this file except in compliance with
|
9
|
+
# the License. You may obtain a copy of the License at
|
10
|
+
# http://www.mozilla.org/MPL/
|
11
|
+
#
|
12
|
+
# Software distributed under the License is distributed on an "AS IS" basis,
|
13
|
+
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
14
|
+
# for the specific language governing rights and limitations under the
|
15
|
+
# License.
|
16
|
+
#
|
17
|
+
# The Original Code is Mozilla Universal charset detector code.
|
18
|
+
#
|
19
|
+
# The Initial Developer of the Original Code is
|
20
|
+
# Netscape Communications Corporation.
|
21
|
+
# Portions created by the Initial Developer are Copyright (C) 2001
|
22
|
+
# the Initial Developer. All Rights Reserved.
|
23
|
+
#
|
24
|
+
# Contributor(s):
|
25
|
+
# Jehan <jehan@girinstud.io>
|
26
|
+
#
|
27
|
+
# Alternatively, the contents of this file may be used under the terms of
|
28
|
+
# either the GNU General Public License Version 2 or later (the "GPL"), or
|
29
|
+
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
30
|
+
# in which case the provisions of the GPL or the LGPL are applicable instead
|
31
|
+
# of those above. If you wish to allow use of your version of this file only
|
32
|
+
# under the terms of either the GPL or the LGPL, and not to allow others to
|
33
|
+
# use your version of this file under the terms of the MPL, indicate your
|
34
|
+
# decision by deleting the provisions above and replace them with the notice
|
35
|
+
# and other provisions required by the GPL or the LGPL. If you do not delete
|
36
|
+
# the provisions above, a recipient may use your version of this file under
|
37
|
+
# the terms of any one of the MPL, the GPL or the LGPL.
|
38
|
+
#
|
39
|
+
# ##### END LICENSE BLOCK #####
|
40
|
+
|
41
|
+
from codepoints import *
|
42
|
+
|
43
|
+
name = 'IBM852'
|
44
|
+
aliases = ['CP852']
|
45
|
+
|
46
|
+
language = \
|
47
|
+
{
|
48
|
+
'complete': [ 'bs', 'hr', 'cs', 'de', 'hu', 'pl', 'sr', 'sk', 'sl',
|
49
|
+
'hsb', 'dsb', 'tk' ],
|
50
|
+
'incomplete': [ 'ro' ]
|
51
|
+
}
|
52
|
+
|
53
|
+
# X0 X1 X2 X3 X4 X5 X6 X7 X8 X9 XA XB XC XD XE XF #
|
54
|
+
charmap = \
|
55
|
+
[
|
56
|
+
CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,RET,CTR,CTR,RET,CTR,CTR, # 0X
|
57
|
+
CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR,CTR, # 1X
|
58
|
+
SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM, # 2X
|
59
|
+
NUM,NUM,NUM,NUM,NUM,NUM,NUM,NUM,NUM,NUM,SYM,SYM,SYM,SYM,SYM,SYM, # 3X
|
60
|
+
SYM,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET, # 4X
|
61
|
+
LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,SYM,SYM,SYM,SYM,SYM, # 5X
|
62
|
+
SYM,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET, # 6X
|
63
|
+
LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,SYM,SYM,SYM,SYM,CTR, # 7X
|
64
|
+
LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET, # 8X
|
65
|
+
LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,SYM,LET, # 9X
|
66
|
+
LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,SYM,LET,LET,LET,SYM,SYM, # AX
|
67
|
+
SYM,SYM,SYM,SYM,SYM,LET,LET,LET,LET,SYM,SYM,SYM,SYM,LET,LET,SYM, # BX
|
68
|
+
SYM,SYM,SYM,SYM,SYM,SYM,LET,LET,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM, # CX
|
69
|
+
LET,LET,LET,LET,LET,LET,LET,LET,LET,SYM,SYM,SYM,SYM,LET,LET,SYM, # DX
|
70
|
+
LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,LET,SYM, # EX
|
71
|
+
SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,SYM,LET,LET,LET,SYM,SYM, # FX
|
72
|
+
]
|