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 +1,148 @@
|
|
1
|
+
= Logs of language model for Slovene (sl) =
|
2
|
+
|
3
|
+
- Generated by BuildLangModel.py
|
4
|
+
- Started: 2016-09-28 22:00:35.243966
|
5
|
+
- Maximum depth: 5
|
6
|
+
- Max number of pages: 100
|
7
|
+
|
8
|
+
== Parsed pages ==
|
9
|
+
|
10
|
+
XCOM: Enemy Unknown (revision 4704271)
|
11
|
+
1UP.com (revision 4547348)
|
12
|
+
2K Games (revision 4110089)
|
13
|
+
Android (operacijski sistem) (revision 4619359)
|
14
|
+
Animator videoigre (revision 4702643)
|
15
|
+
App Store (revision 3903089)
|
16
|
+
Artefakt (revision 4484504)
|
17
|
+
Athlon (revision 4524746)
|
18
|
+
Avstralazija (revision 4623530)
|
19
|
+
Avtopsija (revision 4541344)
|
20
|
+
Bralno-pisalni pomnilnik (revision 4256388)
|
21
|
+
Civilization (serija) (revision 4645770)
|
22
|
+
Deus Ex: Human Revolution (revision 4694860)
|
23
|
+
Digitalna distribucija (revision 4696215)
|
24
|
+
DirectX (revision 4477913)
|
25
|
+
Dishonored (revision 4619444)
|
26
|
+
Edge (magazine) (revision 4690049)
|
27
|
+
Electronic Entertainment Expo (revision 4538691)
|
28
|
+
Enoigralska videoigra (revision 4610359)
|
29
|
+
Eurogamer (revision 4694860)
|
30
|
+
Evropa (revision 4687833)
|
31
|
+
Fantasy Flight Games (revision 4649361)
|
32
|
+
Firaxis Games (revision 4110089)
|
33
|
+
GameRankings (revision 3934020)
|
34
|
+
GameSpot (revision 4238015)
|
35
|
+
GameSpy (revision 4538691)
|
36
|
+
GameTrailers (revision 4704271)
|
37
|
+
Game Informer (revision 4704271)
|
38
|
+
GamesTM (revision 4704271)
|
39
|
+
Grafična kartica (revision 4257980)
|
40
|
+
Granata (revision 3859332)
|
41
|
+
Holograf (revision 4477482)
|
42
|
+
IGN (revision 4576233)
|
43
|
+
IOS (revision 4597264)
|
44
|
+
Igra igranja vlog (revision 4642276)
|
45
|
+
Igra na deski (revision 4649363)
|
46
|
+
Igralna konzola (revision 4649866)
|
47
|
+
Igralni pogon (revision 4622773)
|
48
|
+
Intel (revision 4626025)
|
49
|
+
International Standard Book Number (revision 4015087)
|
50
|
+
Izdelovalec videoigre (revision 3851747)
|
51
|
+
Joker (revija) (revision 3867772)
|
52
|
+
Kotaku (revision 4613535)
|
53
|
+
Kristal (revision 4156234)
|
54
|
+
Linux (revision 4524740)
|
55
|
+
Lovec prestreznik (revision 4102792)
|
56
|
+
MTV (revision 4621758)
|
57
|
+
Mac OS X (revision 4601645)
|
58
|
+
Machinima (revision 4601716)
|
59
|
+
Major (revision 4245802)
|
60
|
+
Mednarodna različica (revision 4116054)
|
61
|
+
Metacritic (revision 3934020)
|
62
|
+
Michael McCann (skladatelj) (revision 4694860)
|
63
|
+
MicroProse (revision 4382810)
|
64
|
+
Microsoft Windows (revision 4691357)
|
65
|
+
Nezemeljsko življenje (revision 4620576)
|
66
|
+
NowGamer (revision 4704271)
|
67
|
+
OS X (revision 4601645)
|
68
|
+
Ognjena ekipa (revision 4694450)
|
69
|
+
Operacijski sistem (revision 4698515)
|
70
|
+
Ostrostrelec (revision 4529694)
|
71
|
+
Pilot (revision 4069093)
|
72
|
+
PlayStation 3 (revision 4382944)
|
73
|
+
PlayStation Network (revision 4382944)
|
74
|
+
PlayStation Vita (revision 3944025)
|
75
|
+
Pogon igre (revision 4622773)
|
76
|
+
Procesor (revision 4702518)
|
77
|
+
Producent videoiger (revision 4599904)
|
78
|
+
Razvijalec videoiger (revision 4093281)
|
79
|
+
Računalniška miška (revision 4385579)
|
80
|
+
Računalniška platforma (revision 4673669)
|
81
|
+
Severna Amerika (revision 4643798)
|
82
|
+
Sid Meier (revision 4061487)
|
83
|
+
Stealth (revision 4618630)
|
84
|
+
Steam (revision 4696215)
|
85
|
+
Strateška videoigra (revision 4236795)
|
86
|
+
Tablični računalnik (revision 4409985)
|
87
|
+
Take-Two Interactive (revision 4110089)
|
88
|
+
Telepatija (revision 4481192)
|
89
|
+
The Bureau: XCOM Declassified (revision 4704271)
|
90
|
+
The Guardian (revision 3929479)
|
91
|
+
Trdi disk (revision 4644623)
|
92
|
+
UFO: Enemy Unknown (revision 4704271)
|
93
|
+
Unreal Engine (revision 4622773)
|
94
|
+
Unreal Engine 3 (revision 4622773)
|
95
|
+
Uporabniški vmesnik (revision 4552473)
|
96
|
+
Valve Corporation (revision 4110105)
|
97
|
+
Večigralska videoigra (revision 4618639)
|
98
|
+
VideoGamer.com (revision 4704271)
|
99
|
+
Vohunski satelit (revision 4215166)
|
100
|
+
Vojaška taktika (revision 3970259)
|
101
|
+
Vojaški čini (revision 4363026)
|
102
|
+
|
103
|
+
== End of Parsed pages ==
|
104
|
+
|
105
|
+
- Wikipedia parsing ended at: 2016-09-28 22:06:46.133919
|
106
|
+
|
107
|
+
41 characters appeared 411226 times.
|
108
|
+
|
109
|
+
First 29 characters:
|
110
|
+
[ 0] Char a: 10.090315301075321 %
|
111
|
+
[ 1] Char e: 9.90477255815537 %
|
112
|
+
[ 2] Char i: 9.666703953543793 %
|
113
|
+
[ 3] Char o: 9.177921629468953 %
|
114
|
+
[ 4] Char n: 7.28309980400072 %
|
115
|
+
[ 5] Char r: 5.808241696779873 %
|
116
|
+
[ 6] Char s: 4.575586174025961 %
|
117
|
+
[ 7] Char t: 4.4963110309173056 %
|
118
|
+
[ 8] Char j: 4.343840126840229 %
|
119
|
+
[ 9] Char l: 4.2672399118732764 %
|
120
|
+
[10] Char v: 3.802775116359374 %
|
121
|
+
[11] Char p: 3.5216644861949393 %
|
122
|
+
[12] Char k: 3.5136397017698293 %
|
123
|
+
[13] Char d: 3.0387183689747244 %
|
124
|
+
[14] Char m: 2.9487435132992563 %
|
125
|
+
[15] Char z: 2.350775485985808 %
|
126
|
+
[16] Char u: 1.9719083910064055 %
|
127
|
+
[17] Char g: 1.9342162217369525 %
|
128
|
+
[18] Char b: 1.5392995579073308 %
|
129
|
+
[19] Char c: 1.2924766430138173 %
|
130
|
+
[20] Char h: 1.1864522184881305 %
|
131
|
+
[21] Char č: 1.137087635509428 %
|
132
|
+
[22] Char š: 0.6932927392723223 %
|
133
|
+
[23] Char ž: 0.45303555709026183 %
|
134
|
+
[24] Char f: 0.40707542811009034 %
|
135
|
+
[25] Char x: 0.19381070263067024 %
|
136
|
+
[26] Char y: 0.19040624863213904 %
|
137
|
+
[27] Char w: 0.18919037220409216 %
|
138
|
+
[28] Char q: 0.011186063138031156 %
|
139
|
+
|
140
|
+
The first 29 characters have an accumulated ratio of 0.9998978663800442.
|
141
|
+
|
142
|
+
727 sequences found.
|
143
|
+
|
144
|
+
First 512 (typical positive ratio): 0.9983524317161332
|
145
|
+
Next 512 (512-1024): 2.4317528560937295e-06
|
146
|
+
Rest: -3.859759734048396e-17
|
147
|
+
|
148
|
+
- Processing end: 2016-09-28 22:06:46.601266
|
@@ -0,0 +1,109 @@
|
|
1
|
+
= Logs of language model for Spanish (es) =
|
2
|
+
|
3
|
+
- Generated by BuildLangModel.py
|
4
|
+
- Started: 2015-12-12 18:37:37.085123
|
5
|
+
- Maximum depth: 2
|
6
|
+
- Max number of pages: 50
|
7
|
+
|
8
|
+
== Parsed pages ==
|
9
|
+
|
10
|
+
Wikipedia:Portada (revision 84894710)
|
11
|
+
11 de diciembre (revision 87735970)
|
12
|
+
12 de diciembre (revision 87742023)
|
13
|
+
13 de diciembre (revision 87697780)
|
14
|
+
1474 (revision 66715698)
|
15
|
+
1915 (revision 86935345)
|
16
|
+
2000 (revision 87686385)
|
17
|
+
2015 (revision 87743360)
|
18
|
+
Actuación (revision 87459085)
|
19
|
+
Akiyuki Nosaka (revision 87726149)
|
20
|
+
Alberto Podestá (revision 87729965)
|
21
|
+
Alejandro Magno (revision 87717064)
|
22
|
+
Argentina (revision 87742018)
|
23
|
+
Arnold Peralta (revision 87733100)
|
24
|
+
Atentados del 11 de diciembre de 2007 (revision 87720544)
|
25
|
+
Cantante (revision 86761085)
|
26
|
+
Canto (revision 87664585)
|
27
|
+
Carlo Furno (revision 87726011)
|
28
|
+
Ciencia ficción (revision 87662615)
|
29
|
+
Copa Mundial de Clubes de la FIFA 2015 (revision 87734956)
|
30
|
+
Corona de Castilla (revision 87209578)
|
31
|
+
Crisis migratoria en Europa (revision 87609406)
|
32
|
+
Dictadura de Primo de Rivera (revision 87371131)
|
33
|
+
Dionisio Miguel Recio (revision 87724426)
|
34
|
+
Disneyland (revision 87665192)
|
35
|
+
Dolph Schayes (revision 87730770)
|
36
|
+
Día Internacional de las Montañas (revision 87739490)
|
37
|
+
El discurso del rey (revision 87570241)
|
38
|
+
Elecciones regionales de Francia de 2015 (revision 87744011)
|
39
|
+
Estados Unidos (revision 87510736)
|
40
|
+
Fiction House (revision 87732511)
|
41
|
+
Filoxeno de Eretria (revision 83958621)
|
42
|
+
Frank Sinatra (revision 87742871)
|
43
|
+
Fundación Wikimedia (revision 87703852)
|
44
|
+
Geoffrey Marcy (revision 87706505)
|
45
|
+
Gheorghe Gruia (revision 87737327)
|
46
|
+
Grupo de Acción Republicana (revision 87739104)
|
47
|
+
Guerra contra el Estado Islámico (revision 87648946)
|
48
|
+
Here We Go Again (canción) (revision 87680365)
|
49
|
+
Isaac Asimov (revision 87591711)
|
50
|
+
Isabel I de Castilla (revision 87743713)
|
51
|
+
John "Hot Rod" Williams (revision 87730438)
|
52
|
+
José Subirà-Puig (revision 87740413)
|
53
|
+
Julio Terrazas Sandoval (revision 87736542)
|
54
|
+
Libertad Lamarque (revision 87508996)
|
55
|
+
Mosaico de Issos (revision 87731652)
|
56
|
+
Museo Arqueológico Nacional de Nápoles (revision 87302262)
|
57
|
+
Philip K. Dick (revision 87725371)
|
58
|
+
Planet Comics (revision 86698920)
|
59
|
+
|
60
|
+
== End of Parsed pages ==
|
61
|
+
|
62
|
+
- Wikipedia parsing ended at: 2015-12-12 18:39:02.288858
|
63
|
+
|
64
|
+
52 characters appeared 991829 times.
|
65
|
+
|
66
|
+
First 33 characters:
|
67
|
+
[ 0] Char e: 12.571925200815867 %
|
68
|
+
[ 1] Char a: 11.81988024145291 %
|
69
|
+
[ 2] Char o: 8.07941691561751 %
|
70
|
+
[ 3] Char n: 7.234513207417812 %
|
71
|
+
[ 4] Char s: 7.042242160695039 %
|
72
|
+
[ 5] Char i: 7.040528155559072 %
|
73
|
+
[ 6] Char r: 6.8208330266608455 %
|
74
|
+
[ 7] Char l: 5.722559029832763 %
|
75
|
+
[ 8] Char d: 5.275707808503281 %
|
76
|
+
[ 9] Char t: 4.668647518876742 %
|
77
|
+
[10] Char c: 4.466999855821921 %
|
78
|
+
[11] Char u: 3.673717949364255 %
|
79
|
+
[12] Char m: 2.710547886782903 %
|
80
|
+
[13] Char p: 2.4541528832086983 %
|
81
|
+
[14] Char b: 1.3867309788280036 %
|
82
|
+
[15] Char g: 1.2748165258325779 %
|
83
|
+
[16] Char f: 0.925058654263991 %
|
84
|
+
[17] Char y: 0.9045914164639268 %
|
85
|
+
[18] Char v: 0.8877538365988492 %
|
86
|
+
[19] Char ó: 0.8641610600214351 %
|
87
|
+
[20] Char h: 0.7369213846338432 %
|
88
|
+
[21] Char q: 0.5913317719082624 %
|
89
|
+
[22] Char í: 0.5612862701130941 %
|
90
|
+
[23] Char j: 0.43283670874717317 %
|
91
|
+
[24] Char z: 0.38071078784750195 %
|
92
|
+
[25] Char á: 0.37587124393418625 %
|
93
|
+
[26] Char é: 0.29632124085905936 %
|
94
|
+
[27] Char k: 0.2001353055819098 %
|
95
|
+
[28] Char x: 0.18743150280945606 %
|
96
|
+
[29] Char ñ: 0.17462687620547493 %
|
97
|
+
[30] Char ú: 0.12865120902897575 %
|
98
|
+
[31] Char w: 0.0972949974239511 %
|
99
|
+
[32] Char ü: 0.004436248587206061 %
|
100
|
+
|
101
|
+
The first 33 characters have an accumulated ratio of 0.9999263986029848.
|
102
|
+
|
103
|
+
897 sequences found.
|
104
|
+
|
105
|
+
First 512 (typical positive ratio): 0.9970385677528184
|
106
|
+
Next 512 (512-1024): 1.0082383152741046e-06
|
107
|
+
Rest: 4.597017211338539e-17
|
108
|
+
|
109
|
+
- Processing end: 2015-12-12 18:39:02.460105
|
@@ -0,0 +1,151 @@
|
|
1
|
+
= Logs of language model for Swedish (sv) =
|
2
|
+
|
3
|
+
- Generated by BuildLangModel.py
|
4
|
+
- Started: 2016-09-28 22:26:37.221506
|
5
|
+
- Maximum depth: 5
|
6
|
+
- Max number of pages: 100
|
7
|
+
|
8
|
+
== Parsed pages ==
|
9
|
+
|
10
|
+
Kakapo (revision 36509929)
|
11
|
+
Akut hotad (revision 32517788)
|
12
|
+
Aotearoa (revision 36575359)
|
13
|
+
Art (revision 36771341)
|
14
|
+
Artepitet (revision 36771341)
|
15
|
+
Auckland (revision 35752058)
|
16
|
+
Auktorsnamn (revision 35976965)
|
17
|
+
BBC (revision 36508743)
|
18
|
+
Basalomsättning (revision 30567523)
|
19
|
+
Beilschmiedia tawa (revision 29101923)
|
20
|
+
Berguv (revision 36295501)
|
21
|
+
Betesmark (revision 34292168)
|
22
|
+
Biotop (revision 35528052)
|
23
|
+
BirdLife International (revision 36124283)
|
24
|
+
Bonaparte (revision 37325183)
|
25
|
+
British Museum (revision 36420244)
|
26
|
+
Bröstben (revision 30602527)
|
27
|
+
Dacrydium cupressinum (revision 32986501)
|
28
|
+
Digital object identifier (revision 27637223)
|
29
|
+
Djur (revision 37300775)
|
30
|
+
Djurpark (revision 37147093)
|
31
|
+
Domän (biologi) (revision 33377709)
|
32
|
+
Don Merton (revision 36509929)
|
33
|
+
Douglas Adams (revision 36556245)
|
34
|
+
Däggdjur (revision 37328286)
|
35
|
+
Ekologisk nisch (revision 33898643)
|
36
|
+
Ekosystem (revision 36598266)
|
37
|
+
Endemisk (revision 30647109)
|
38
|
+
Eukaryoter (revision 37095313)
|
39
|
+
Evolution (revision 37093592)
|
40
|
+
Familj (biologi) (revision 30280200)
|
41
|
+
Femininum (revision 30597527)
|
42
|
+
Fjäder (biologi) (revision 36364943)
|
43
|
+
Fjäderdräkt (revision 36364943)
|
44
|
+
Fladdermöss (revision 37307257)
|
45
|
+
Flygg (revision 36479633)
|
46
|
+
Frukter (revision 34088588)
|
47
|
+
Frö (revision 37333131)
|
48
|
+
Fågelläte (revision 34034723)
|
49
|
+
Fåglar (revision 37387306)
|
50
|
+
Fåglarnas liv (revision 36509929)
|
51
|
+
Genitiv (revision 37388438)
|
52
|
+
George Edward Grey (revision 36509929)
|
53
|
+
George Robert Gray (revision 20426710)
|
54
|
+
Haasts örn (revision 29175076)
|
55
|
+
Hauturu/Little Barrier Island (revision 36509929)
|
56
|
+
Hermelin (revision 36578682)
|
57
|
+
Hertz (revision 37104488)
|
58
|
+
Hjortdjur (revision 36493550)
|
59
|
+
Hund (revision 37351832)
|
60
|
+
Husdjur (revision 37384850)
|
61
|
+
Huskatt (revision 32922967)
|
62
|
+
Hāngi (revision 29609696)
|
63
|
+
IUCN (revision 30570280)
|
64
|
+
Iller (revision 30663158)
|
65
|
+
Infraröd (revision 36770733)
|
66
|
+
Internationella naturvårdsunionen (revision 30570280)
|
67
|
+
Jordbruk (revision 37352625)
|
68
|
+
Kahurangi National Park (revision 35956142)
|
69
|
+
Kamouflage (revision 36579595)
|
70
|
+
Kaniner (revision 36877621)
|
71
|
+
Kapiti Island (revision 37395588)
|
72
|
+
Katt (revision 36734686)
|
73
|
+
Kelp (revision 30312471)
|
74
|
+
Kivier (revision 36373234)
|
75
|
+
Klass (biologi) (revision 30280201)
|
76
|
+
Kroppsfett (revision 35066611)
|
77
|
+
Könsdimorfism (revision 30816932)
|
78
|
+
Könsfördelning (revision 24769321)
|
79
|
+
Lamm- och fårkött (revision 36187205)
|
80
|
+
Lek (fortplantningsbeteende) (revision 30508235)
|
81
|
+
Mandel (revision 36577529)
|
82
|
+
Maori (revision 32560474)
|
83
|
+
Maorier (revision 35862066)
|
84
|
+
Maoripapegojor (revision 36545138)
|
85
|
+
Mark Carwardine (revision 20375916)
|
86
|
+
Markpapegoja (revision 36295722)
|
87
|
+
Maskulinum (revision 32704551)
|
88
|
+
Masterton (revision 29859631)
|
89
|
+
Metrosideros umbellata (revision 29071212)
|
90
|
+
Milford Sound (revision 20284758)
|
91
|
+
Morrhår (revision 36533839)
|
92
|
+
Muskelmage (revision 31196380)
|
93
|
+
Mustela (revision 20934105)
|
94
|
+
Mårddjur (revision 37306347)
|
95
|
+
Māori (revision 32560474)
|
96
|
+
NHNZ (revision 36509929)
|
97
|
+
Nattpapegoja (revision 33486517)
|
98
|
+
Nordön (revision 24810231)
|
99
|
+
Nya Zeeland (revision 36575359)
|
100
|
+
Näbb (revision 23648463)
|
101
|
+
Ollonår (revision 36509929)
|
102
|
+
Ordning (biologi) (revision 30280196)
|
103
|
+
|
104
|
+
== End of Parsed pages ==
|
105
|
+
|
106
|
+
- Wikipedia parsing ended at: 2016-09-28 22:29:21.480287
|
107
|
+
|
108
|
+
48 characters appeared 594415 times.
|
109
|
+
|
110
|
+
First 31 characters:
|
111
|
+
[ 0] Char a: 10.070741821791172 %
|
112
|
+
[ 1] Char e: 9.737136512369304 %
|
113
|
+
[ 2] Char r: 9.110638190489809 %
|
114
|
+
[ 3] Char n: 8.378826240925951 %
|
115
|
+
[ 4] Char t: 7.481305148759705 %
|
116
|
+
[ 5] Char s: 5.828587771169974 %
|
117
|
+
[ 6] Char i: 5.359891658184939 %
|
118
|
+
[ 7] Char l: 5.173489901836259 %
|
119
|
+
[ 8] Char o: 4.694195133029954 %
|
120
|
+
[ 9] Char d: 4.597293136949774 %
|
121
|
+
[10] Char k: 3.297359588839447 %
|
122
|
+
[11] Char m: 3.1898589369379975 %
|
123
|
+
[12] Char g: 3.004466576381821 %
|
124
|
+
[13] Char v: 2.2324470277499726 %
|
125
|
+
[14] Char f: 2.1988005013332437 %
|
126
|
+
[15] Char p: 2.06017681249632 %
|
127
|
+
[16] Char u: 2.0499146219392173 %
|
128
|
+
[17] Char ä: 2.0475593650900468 %
|
129
|
+
[18] Char h: 2.028380845032511 %
|
130
|
+
[19] Char å: 1.5443755625278637 %
|
131
|
+
[20] Char c: 1.442594820117258 %
|
132
|
+
[21] Char ö: 1.3515809661600062 %
|
133
|
+
[22] Char b: 1.268642278542769 %
|
134
|
+
[23] Char j: 0.7302978558751041 %
|
135
|
+
[24] Char y: 0.6699023409570755 %
|
136
|
+
[25] Char x: 0.2111319532649748 %
|
137
|
+
[26] Char w: 0.10262190557102362 %
|
138
|
+
[27] Char z: 0.09151855185350302 %
|
139
|
+
[28] Char é: 0.021197311642539303 %
|
140
|
+
[29] Char ā: 0.011103353717520588 %
|
141
|
+
[30] Char q: 0.007570468443764037 %
|
142
|
+
|
143
|
+
The first 31 characters have an accumulated ratio of 0.999936071599808.
|
144
|
+
|
145
|
+
748 sequences found.
|
146
|
+
|
147
|
+
First 512 (typical positive ratio): 0.997323508584682
|
148
|
+
Next 512 (512-1024): 1.6823263208364526e-06
|
149
|
+
Rest: 1.7780915628762273e-17
|
150
|
+
|
151
|
+
- Processing end: 2016-09-28 22:29:21.590354
|
@@ -0,0 +1,141 @@
|
|
1
|
+
= Logs of language model for Thai (th) =
|
2
|
+
|
3
|
+
- Generated by BuildLangModel.py
|
4
|
+
- Started: 2015-12-04 03:01:52.148282
|
5
|
+
- Maximum depth: 3
|
6
|
+
- Max number of pages: 50
|
7
|
+
|
8
|
+
== Parsed pages ==
|
9
|
+
|
10
|
+
หน้าหลัก (revision 5512633)
|
11
|
+
26 พฤศจิกายน (revision 5570053)
|
12
|
+
27 พฤศจิกายน (revision 5888433)
|
13
|
+
28 พฤศจิกายน (revision 6110206)
|
14
|
+
กล้องโทรทรรศน์อวกาศฮับเบิล (revision 5830742)
|
15
|
+
การประชุมสภาสงฆ์แห่งแคลมงต์ (revision 5463877)
|
16
|
+
ความเอนเอียงเพื่อยืนยัน (revision 6231756)
|
17
|
+
คัมภีร์พระเวท (revision 6109417)
|
18
|
+
คาบสมุทรไซนาย (revision 5661104)
|
19
|
+
จักรวรรดิโรมันตะวันออก (revision 6150148)
|
20
|
+
ชาวมุสลิม (revision 6242838)
|
21
|
+
ซุคฮอย ซู-24 (revision 6015891)
|
22
|
+
ดาวอังคาร (revision 6235017)
|
23
|
+
ดาวเคราะห์นอกระบบ (revision 5823077)
|
24
|
+
ดินแดนศักดิ์สิทธิ์ (revision 6179072)
|
25
|
+
ทฤษฎี (revision 5606447)
|
26
|
+
ทะกะอะกิ คะจิตะ (revision 6177601)
|
27
|
+
ท่าอากาศยานนานาชาติตริภูวัน (revision 6010470)
|
28
|
+
นกกาเหว่า (revision 6142782)
|
29
|
+
ประเทศอัฟกานิสถาน (revision 6216996)
|
30
|
+
ประเทศเนปาล (revision 6206980)
|
31
|
+
ปรากฏการณ์การวางกรอบ (revision 6046655)
|
32
|
+
ปารีส (revision 6222115)
|
33
|
+
พ.ศ. 1638 (revision 4723508)
|
34
|
+
พ.ศ. 2438 (revision 5737055)
|
35
|
+
พ.ศ. 2515 (revision 6197082)
|
36
|
+
พ.ศ. 2544 (revision 6189598)
|
37
|
+
พินัยกรรม (revision 5607889)
|
38
|
+
มูลนิธิวิกิมีเดีย (revision 5816103)
|
39
|
+
ระบบสุริยะ (revision 6201228)
|
40
|
+
รางวัลโนเบล (revision 5828030)
|
41
|
+
รางวัลโนเบลสาขาฟิสิกส์ (revision 6177103)
|
42
|
+
รายชื่อบทความวันนี้ในอดีต (revision 5410610)
|
43
|
+
ลักกีสไตรก์ (เพลง) (revision 6195816)
|
44
|
+
ลุฟต์ฮันซา (revision 6116038)
|
45
|
+
วิกฤตการณ์ผู้ย้ายถิ่นยุโรป (revision 6219634)
|
46
|
+
วิกิพีเดีย (revision 6086299)
|
47
|
+
วิกิพีเดียภาษาไทย (revision 6209148)
|
48
|
+
สงครามครูเสด (revision 6228828)
|
49
|
+
สงครามอังกฤษ–แซนซิบาร์ (revision 5829349)
|
50
|
+
สติ (จิตวิทยา) (revision 6039161)
|
51
|
+
สมมติฐาน (revision 6221744)
|
52
|
+
สมเด็จพระราชินีมารีแห่งโรมาเนีย (revision 6211695)
|
53
|
+
สมเด็จพระสันตะปาปาเออร์บันที่ 2 (revision 5828365)
|
54
|
+
สารานุกรม (revision 6070482)
|
55
|
+
อัลเฟรด โนเบล (revision 6214514)
|
56
|
+
อาร์เธอร์ แมคโดนัลด์ (revision 6188035)
|
57
|
+
เซนต์ปีเตอร์สเบิร์ก (revision 6162201)
|
58
|
+
เทือกเขาฮินดูกูช (revision 5218921)
|
59
|
+
เนื้อหาเสรี (revision 6160507)
|
60
|
+
|
61
|
+
== End of Parsed pages ==
|
62
|
+
|
63
|
+
- Wikipedia parsing ended at: 2015-12-04 03:05:06.181487
|
64
|
+
|
65
|
+
105 characters appeared 401052 times.
|
66
|
+
|
67
|
+
First 64 characters:
|
68
|
+
[ 0] Char า: 8.857704237854442 %
|
69
|
+
[ 1] Char น: 6.7679502907353655 %
|
70
|
+
[ 2] Char ร: 6.739026360671434 %
|
71
|
+
[ 3] Char ก: 5.388079351306065 %
|
72
|
+
[ 4] Char อ: 5.099837427565503 %
|
73
|
+
[ 5] Char ง: 4.861713692987443 %
|
74
|
+
[ 6] Char เ: 4.5198627609387305 %
|
75
|
+
[ 7] Char ม: 4.133628556895365 %
|
76
|
+
[ 8] Char ว: 3.864336794231172 %
|
77
|
+
[ 9] Char ด: 3.3152808114658447 %
|
78
|
+
[10] Char ย: 3.195844927839781 %
|
79
|
+
[11] Char ล: 3.1312647736453125 %
|
80
|
+
[12] Char ท: 2.69615910156289 %
|
81
|
+
[13] Char ส: 2.6001615750575984 %
|
82
|
+
[14] Char ะ: 2.392457835891605 %
|
83
|
+
[15] Char ค: 2.384229476476866 %
|
84
|
+
[16] Char บ: 2.3321165335168503 %
|
85
|
+
[17] Char ต: 2.196473275285998 %
|
86
|
+
[18] Char ห: 1.983782651626223 %
|
87
|
+
[19] Char ป: 1.9192024974317545 %
|
88
|
+
[20] Char แ: 1.7813151411787 %
|
89
|
+
[21] Char จ: 1.76261432432702 %
|
90
|
+
[22] Char พ: 1.5075351824701035 %
|
91
|
+
[23] Char ข: 1.3519443862641254 %
|
92
|
+
[24] Char ใ: 1.3295034060421091 %
|
93
|
+
[25] Char ไ: 1.2227840778751882 %
|
94
|
+
[26] Char ช: 1.0407627938521689 %
|
95
|
+
[27] Char โ: 0.9382823175049619 %
|
96
|
+
[28] Char ศ: 0.8078752879925796 %
|
97
|
+
[29] Char ำ: 0.7393056262030859 %
|
98
|
+
[30] Char ถ: 0.599672860377208 %
|
99
|
+
[31] Char ซ: 0.541076967575277 %
|
100
|
+
[32] Char e: 0.43734977010462484 %
|
101
|
+
[33] Char ผ: 0.43585370475649043 %
|
102
|
+
[34] Char ณ: 0.4019428901987772 %
|
103
|
+
[35] Char a: 0.3897250231890129 %
|
104
|
+
[36] Char i: 0.3657879776188624 %
|
105
|
+
[37] Char ษ: 0.3647906007201061 %
|
106
|
+
[38] Char ภ: 0.34185093204871186 %
|
107
|
+
[39] Char ธ: 0.3181632307032505 %
|
108
|
+
[40] Char o: 0.3176645422538723 %
|
109
|
+
[41] Char n: 0.3139243788835363 %
|
110
|
+
[42] Char ญ: 0.29248077556027646 %
|
111
|
+
[43] Char r: 0.28350438347147006 %
|
112
|
+
[44] Char t: 0.2705384837876385 %
|
113
|
+
[45] Char s: 0.2488455362396896 %
|
114
|
+
[46] Char l: 0.19598456060560726 %
|
115
|
+
[47] Char ฟ: 0.19473783948216192 %
|
116
|
+
[48] Char c: 0.16356981139602844 %
|
117
|
+
[49] Char ฐ: 0.15833358267755804 %
|
118
|
+
[50] Char ฤ: 0.15284800973439852 %
|
119
|
+
[51] Char ๆ: 0.14910784636406252 %
|
120
|
+
[52] Char d: 0.13090571796176056 %
|
121
|
+
[53] Char ฮ: 0.1244227681198448 %
|
122
|
+
[54] Char h: 0.12043326052481973 %
|
123
|
+
[55] Char u: 0.12043326052481973 %
|
124
|
+
[56] Char m: 0.09599752650529109 %
|
125
|
+
[57] Char y: 0.08951457666337533 %
|
126
|
+
[58] Char ฏ: 0.08677179019179557 %
|
127
|
+
[59] Char p: 0.08253293837208142 %
|
128
|
+
[60] Char f: 0.08153556147332515 %
|
129
|
+
[61] Char S: 0.07604998853016566 %
|
130
|
+
[62] Char ฝ: 0.07330720205858592 %
|
131
|
+
[63] Char ฉ: 0.0673229406660483 %
|
132
|
+
|
133
|
+
The first 64 characters have an accumulated ratio of 0.989480167160368.
|
134
|
+
|
135
|
+
2324 sequences found.
|
136
|
+
|
137
|
+
First 512 (typical positive ratio): 0.8815720594354438
|
138
|
+
Next 512 (512-1024): 7.480326740672033e-06
|
139
|
+
Rest: 0.026341928296264486
|
140
|
+
|
141
|
+
- Processing end: 2015-12-04 03:05:06.800467
|