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 +1,194 @@
|
|
1
|
+
/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
|
2
|
+
/* ***** BEGIN LICENSE BLOCK *****
|
3
|
+
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
4
|
+
*
|
5
|
+
* The contents of this file are subject to the Mozilla Public License Version
|
6
|
+
* 1.1 (the "License"); you may not use this file except in compliance with
|
7
|
+
* the License. You may obtain a copy of the License at
|
8
|
+
* http://www.mozilla.org/MPL/
|
9
|
+
*
|
10
|
+
* Software distributed under the License is distributed on an "AS IS" basis,
|
11
|
+
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
12
|
+
* for the specific language governing rights and limitations under the
|
13
|
+
* License.
|
14
|
+
*
|
15
|
+
* The Original Code is Mozilla Universal charset detector code.
|
16
|
+
*
|
17
|
+
* The Initial Developer of the Original Code is
|
18
|
+
* Shy Shalom <shooshX@gmail.com>
|
19
|
+
* Portions created by the Initial Developer are Copyright (C) 2005
|
20
|
+
* the Initial Developer. All Rights Reserved.
|
21
|
+
*
|
22
|
+
* Contributor(s):
|
23
|
+
*
|
24
|
+
* Alternatively, the contents of this file may be used under the terms of
|
25
|
+
* either the GNU General Public License Version 2 or later (the "GPL"), or
|
26
|
+
* the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
27
|
+
* in which case the provisions of the GPL or the LGPL are applicable instead
|
28
|
+
* of those above. If you wish to allow use of your version of this file only
|
29
|
+
* under the terms of either the GPL or the LGPL, and not to allow others to
|
30
|
+
* use your version of this file under the terms of the MPL, indicate your
|
31
|
+
* decision by deleting the provisions above and replace them with the notice
|
32
|
+
* and other provisions required by the GPL or the LGPL. If you do not delete
|
33
|
+
* the provisions above, a recipient may use your version of this file under
|
34
|
+
* the terms of any one of the MPL, the GPL or the LGPL.
|
35
|
+
*
|
36
|
+
* ***** END LICENSE BLOCK ***** */
|
37
|
+
|
38
|
+
#include "nsHebrewProber.h"
|
39
|
+
#include <stdio.h>
|
40
|
+
|
41
|
+
// windows-1255 / ISO-8859-8 code points of interest
|
42
|
+
#define FINAL_KAF ('\xea')
|
43
|
+
#define NORMAL_KAF ('\xeb')
|
44
|
+
#define FINAL_MEM ('\xed')
|
45
|
+
#define NORMAL_MEM ('\xee')
|
46
|
+
#define FINAL_NUN ('\xef')
|
47
|
+
#define NORMAL_NUN ('\xf0')
|
48
|
+
#define FINAL_PE ('\xf3')
|
49
|
+
#define NORMAL_PE ('\xf4')
|
50
|
+
#define FINAL_TSADI ('\xf5')
|
51
|
+
#define NORMAL_TSADI ('\xf6')
|
52
|
+
|
53
|
+
// Minimum Visual vs Logical final letter score difference.
|
54
|
+
// If the difference is below this, don't rely solely on the final letter score distance.
|
55
|
+
#define MIN_FINAL_CHAR_DISTANCE (5)
|
56
|
+
|
57
|
+
// Minimum Visual vs Logical model score difference.
|
58
|
+
// If the difference is below this, don't rely at all on the model score distance.
|
59
|
+
#define MIN_MODEL_DISTANCE (0.01)
|
60
|
+
|
61
|
+
#define VISUAL_HEBREW_NAME ("ISO-8859-8")
|
62
|
+
#define LOGICAL_HEBREW_NAME ("WINDOWS-1255")
|
63
|
+
|
64
|
+
PRBool nsHebrewProber::isFinal(char c)
|
65
|
+
{
|
66
|
+
return ((c == FINAL_KAF) || (c == FINAL_MEM) || (c == FINAL_NUN) || (c == FINAL_PE) || (c == FINAL_TSADI));
|
67
|
+
}
|
68
|
+
|
69
|
+
PRBool nsHebrewProber::isNonFinal(char c)
|
70
|
+
{
|
71
|
+
return ((c == NORMAL_KAF) || (c == NORMAL_MEM) || (c == NORMAL_NUN) || (c == NORMAL_PE));
|
72
|
+
// The normal Tsadi is not a good Non-Final letter due to words like
|
73
|
+
// 'lechotet' (to chat) containing an apostrophe after the tsadi. This
|
74
|
+
// apostrophe is converted to a space in FilterWithoutEnglishLetters causing
|
75
|
+
// the Non-Final tsadi to appear at an end of a word even though this is not
|
76
|
+
// the case in the original text.
|
77
|
+
// The letters Pe and Kaf rarely display a related behavior of not being a
|
78
|
+
// good Non-Final letter. Words like 'Pop', 'Winamp' and 'Mubarak' for
|
79
|
+
// example legally end with a Non-Final Pe or Kaf. However, the benefit of
|
80
|
+
// these letters as Non-Final letters outweighs the damage since these words
|
81
|
+
// are quite rare.
|
82
|
+
}
|
83
|
+
|
84
|
+
/** HandleData
|
85
|
+
* Final letter analysis for logical-visual decision.
|
86
|
+
* Look for evidence that the received buffer is either logical Hebrew or
|
87
|
+
* visual Hebrew.
|
88
|
+
* The following cases are checked:
|
89
|
+
* 1) A word longer than 1 letter, ending with a final letter. This is an
|
90
|
+
* indication that the text is laid out "naturally" since the final letter
|
91
|
+
* really appears at the end. +1 for logical score.
|
92
|
+
* 2) A word longer than 1 letter, ending with a Non-Final letter. In normal
|
93
|
+
* Hebrew, words ending with Kaf, Mem, Nun, Pe or Tsadi, should not end with
|
94
|
+
* the Non-Final form of that letter. Exceptions to this rule are mentioned
|
95
|
+
* above in isNonFinal(). This is an indication that the text is laid out
|
96
|
+
* backwards. +1 for visual score
|
97
|
+
* 3) A word longer than 1 letter, starting with a final letter. Final letters
|
98
|
+
* should not appear at the beginning of a word. This is an indication that
|
99
|
+
* the text is laid out backwards. +1 for visual score.
|
100
|
+
*
|
101
|
+
* The visual score and logical score are accumulated throughout the text and
|
102
|
+
* are finally checked against each other in GetCharSetName().
|
103
|
+
* No checking for final letters in the middle of words is done since that case
|
104
|
+
* is not an indication for either Logical or Visual text.
|
105
|
+
*
|
106
|
+
* The input buffer should not contain any white spaces that are not (' ')
|
107
|
+
* or any low-ascii punctuation marks.
|
108
|
+
*/
|
109
|
+
nsProbingState nsHebrewProber::HandleData(const char* aBuf, PRUint32 aLen)
|
110
|
+
{
|
111
|
+
// Both model probers say it's not them. No reason to continue.
|
112
|
+
if (GetState() == eNotMe)
|
113
|
+
return eNotMe;
|
114
|
+
|
115
|
+
const char *curPtr, *endPtr = aBuf+aLen;
|
116
|
+
char cur;
|
117
|
+
|
118
|
+
for (curPtr = (char*)aBuf; curPtr < endPtr; ++curPtr)
|
119
|
+
{
|
120
|
+
cur = *curPtr;
|
121
|
+
if (cur == ' ') // We stand on a space - a word just ended
|
122
|
+
{
|
123
|
+
if (mBeforePrev != ' ') // *(curPtr-2) was not a space so prev is not a 1 letter word
|
124
|
+
{
|
125
|
+
if (isFinal(mPrev)) // case (1) [-2:not space][-1:final letter][cur:space]
|
126
|
+
++mFinalCharLogicalScore;
|
127
|
+
else if (isNonFinal(mPrev)) // case (2) [-2:not space][-1:Non-Final letter][cur:space]
|
128
|
+
++mFinalCharVisualScore;
|
129
|
+
}
|
130
|
+
}
|
131
|
+
else // Not standing on a space
|
132
|
+
{
|
133
|
+
if ((mBeforePrev == ' ') && (isFinal(mPrev)) && (cur != ' ')) // case (3) [-2:space][-1:final letter][cur:not space]
|
134
|
+
++mFinalCharVisualScore;
|
135
|
+
}
|
136
|
+
mBeforePrev = mPrev;
|
137
|
+
mPrev = cur;
|
138
|
+
}
|
139
|
+
|
140
|
+
// Forever detecting, till the end or until both model probers return eNotMe (handled above).
|
141
|
+
return eDetecting;
|
142
|
+
}
|
143
|
+
|
144
|
+
// Make the decision: is it Logical or Visual?
|
145
|
+
const char* nsHebrewProber::GetCharSetName()
|
146
|
+
{
|
147
|
+
// If the final letter score distance is dominant enough, rely on it.
|
148
|
+
PRInt32 finalsub = mFinalCharLogicalScore - mFinalCharVisualScore;
|
149
|
+
if (finalsub >= MIN_FINAL_CHAR_DISTANCE)
|
150
|
+
return LOGICAL_HEBREW_NAME;
|
151
|
+
if (finalsub <= -(MIN_FINAL_CHAR_DISTANCE))
|
152
|
+
return VISUAL_HEBREW_NAME;
|
153
|
+
|
154
|
+
// It's not dominant enough, try to rely on the model scores instead.
|
155
|
+
float modelsub = mLogicalProb->GetConfidence() - mVisualProb->GetConfidence();
|
156
|
+
if (modelsub > MIN_MODEL_DISTANCE)
|
157
|
+
return LOGICAL_HEBREW_NAME;
|
158
|
+
if (modelsub < -(MIN_MODEL_DISTANCE))
|
159
|
+
return VISUAL_HEBREW_NAME;
|
160
|
+
|
161
|
+
// Still no good, back to final letter distance, maybe it'll save the day.
|
162
|
+
if (finalsub < 0)
|
163
|
+
return VISUAL_HEBREW_NAME;
|
164
|
+
|
165
|
+
// (finalsub > 0 - Logical) or (don't know what to do) default to Logical.
|
166
|
+
return LOGICAL_HEBREW_NAME;
|
167
|
+
}
|
168
|
+
|
169
|
+
|
170
|
+
void nsHebrewProber::Reset(void)
|
171
|
+
{
|
172
|
+
mFinalCharLogicalScore = 0;
|
173
|
+
mFinalCharVisualScore = 0;
|
174
|
+
|
175
|
+
// mPrev and mBeforePrev are initialized to space in order to simulate a word
|
176
|
+
// delimiter at the beginning of the data
|
177
|
+
mPrev = ' ';
|
178
|
+
mBeforePrev = ' ';
|
179
|
+
}
|
180
|
+
|
181
|
+
nsProbingState nsHebrewProber::GetState(void)
|
182
|
+
{
|
183
|
+
// Remain active as long as any of the model probers are active.
|
184
|
+
if ((mLogicalProb->GetState() == eNotMe) && (mVisualProb->GetState() == eNotMe))
|
185
|
+
return eNotMe;
|
186
|
+
return eDetecting;
|
187
|
+
}
|
188
|
+
|
189
|
+
#ifdef DEBUG_chardet
|
190
|
+
void nsHebrewProber::DumpStatus()
|
191
|
+
{
|
192
|
+
printf(" HEB: %d - %d [Logical-Visual score]\r\n", mFinalCharLogicalScore, mFinalCharVisualScore);
|
193
|
+
}
|
194
|
+
#endif
|
@@ -0,0 +1,177 @@
|
|
1
|
+
/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
|
2
|
+
/* ***** BEGIN LICENSE BLOCK *****
|
3
|
+
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
4
|
+
*
|
5
|
+
* The contents of this file are subject to the Mozilla Public License Version
|
6
|
+
* 1.1 (the "License"); you may not use this file except in compliance with
|
7
|
+
* the License. You may obtain a copy of the License at
|
8
|
+
* http://www.mozilla.org/MPL/
|
9
|
+
*
|
10
|
+
* Software distributed under the License is distributed on an "AS IS" basis,
|
11
|
+
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
12
|
+
* for the specific language governing rights and limitations under the
|
13
|
+
* License.
|
14
|
+
*
|
15
|
+
* The Original Code is Mozilla Universal charset detector code.
|
16
|
+
*
|
17
|
+
* The Initial Developer of the Original Code is
|
18
|
+
* Shy Shalom <shooshX@gmail.com>
|
19
|
+
* Portions created by the Initial Developer are Copyright (C) 2005
|
20
|
+
* the Initial Developer: All Rights Reserved.
|
21
|
+
*
|
22
|
+
* Contributor(s):
|
23
|
+
*
|
24
|
+
* Alternatively, the contents of this file may be used under the terms of
|
25
|
+
* either the GNU General Public License Version 2 or later (the "GPL"), or
|
26
|
+
* the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
27
|
+
* in which case the provisions of the GPL or the LGPL are applicable instead
|
28
|
+
* of those above. If you wish to allow use of your version of this file only
|
29
|
+
* under the terms of either the GPL or the LGPL, and not to allow others to
|
30
|
+
* use your version of this file under the terms of the MPL, indicate your
|
31
|
+
* decision by deleting the provisions above and replace them with the notice
|
32
|
+
* and other provisions required by the GPL or the LGPL. If you do not delete
|
33
|
+
* the provisions above, a recipient may use your version of this file under
|
34
|
+
* the terms of any one of the MPL, the GPL or the LGPL.
|
35
|
+
*
|
36
|
+
* ***** END LICENSE BLOCK ***** */
|
37
|
+
|
38
|
+
#ifndef nsHebrewProber_h__
|
39
|
+
#define nsHebrewProber_h__
|
40
|
+
|
41
|
+
#include "nsSBCharSetProber.h"
|
42
|
+
|
43
|
+
// This prober doesn't actually recognize a language or a charset.
|
44
|
+
// It is a helper prober for the use of the Hebrew model probers
|
45
|
+
class nsHebrewProber: public nsCharSetProber
|
46
|
+
{
|
47
|
+
public:
|
48
|
+
nsHebrewProber(void) :mLogicalProb(0), mVisualProb(0) { Reset(); }
|
49
|
+
|
50
|
+
virtual ~nsHebrewProber(void) {}
|
51
|
+
virtual nsProbingState HandleData(const char* aBuf, PRUint32 aLen);
|
52
|
+
virtual const char *GetCharSetName();
|
53
|
+
virtual const char *GetLanguage(void) { return "he"; }
|
54
|
+
virtual void Reset(void);
|
55
|
+
|
56
|
+
virtual nsProbingState GetState(void);
|
57
|
+
|
58
|
+
virtual float GetConfidence(void) { return (float)0.0; }
|
59
|
+
virtual void SetOpion() {}
|
60
|
+
|
61
|
+
void SetModelProbers(nsCharSetProber *logicalPrb, nsCharSetProber *visualPrb)
|
62
|
+
{ mLogicalProb = logicalPrb; mVisualProb = visualPrb; }
|
63
|
+
|
64
|
+
#ifdef DEBUG_chardet
|
65
|
+
virtual void DumpStatus();
|
66
|
+
#endif
|
67
|
+
|
68
|
+
protected:
|
69
|
+
static PRBool isFinal(char c);
|
70
|
+
static PRBool isNonFinal(char c);
|
71
|
+
|
72
|
+
PRInt32 mFinalCharLogicalScore, mFinalCharVisualScore;
|
73
|
+
|
74
|
+
// The two last characters seen in the previous buffer.
|
75
|
+
char mPrev, mBeforePrev;
|
76
|
+
|
77
|
+
// These probers are owned by the group prober.
|
78
|
+
nsCharSetProber *mLogicalProb, *mVisualProb;
|
79
|
+
};
|
80
|
+
|
81
|
+
/**
|
82
|
+
* ** General ideas of the Hebrew charset recognition **
|
83
|
+
*
|
84
|
+
* Four main charsets exist in Hebrew:
|
85
|
+
* "ISO-8859-8" - Visual Hebrew
|
86
|
+
* "windows-1255" - Logical Hebrew
|
87
|
+
* "ISO-8859-8-I" - Logical Hebrew
|
88
|
+
* "x-mac-hebrew" - ?? Logical Hebrew ??
|
89
|
+
*
|
90
|
+
* Both "ISO" charsets use a completely identical set of code points, whereas
|
91
|
+
* "windows-1255" and "x-mac-hebrew" are two different proper supersets of
|
92
|
+
* these code points. windows-1255 defines additional characters in the range
|
93
|
+
* 0x80-0x9F as some misc punctuation marks as well as some Hebrew-specific
|
94
|
+
* diacritics and additional 'Yiddish' ligature letters in the range 0xc0-0xd6.
|
95
|
+
* x-mac-hebrew defines similar additional code points but with a different
|
96
|
+
* mapping.
|
97
|
+
*
|
98
|
+
* As far as an average Hebrew text with no diacritics is concerned, all four
|
99
|
+
* charsets are identical with respect to code points. Meaning that for the
|
100
|
+
* main Hebrew alphabet, all four map the same values to all 27 Hebrew letters
|
101
|
+
* (including final letters).
|
102
|
+
*
|
103
|
+
* The dominant difference between these charsets is their directionality.
|
104
|
+
* "Visual" directionality means that the text is ordered as if the renderer is
|
105
|
+
* not aware of a BIDI rendering algorithm. The renderer sees the text and
|
106
|
+
* draws it from left to right. The text itself when ordered naturally is read
|
107
|
+
* backwards. A buffer of Visual Hebrew generally looks like so:
|
108
|
+
* "[last word of first line spelled backwards] [whole line ordered backwards
|
109
|
+
* and spelled backwards] [first word of first line spelled backwards]
|
110
|
+
* [end of line] [last word of second line] ... etc' "
|
111
|
+
* adding punctuation marks, numbers and English text to visual text is
|
112
|
+
* naturally also "visual" and from left to right.
|
113
|
+
*
|
114
|
+
* "Logical" directionality means the text is ordered "naturally" according to
|
115
|
+
* the order it is read. It is the responsibility of the renderer to display
|
116
|
+
* the text from right to left. A BIDI algorithm is used to place general
|
117
|
+
* punctuation marks, numbers and English text in the text.
|
118
|
+
*
|
119
|
+
* Texts in x-mac-hebrew are almost impossible to find on the Internet. From
|
120
|
+
* what little evidence I could find, it seems that its general directionality
|
121
|
+
* is Logical.
|
122
|
+
*
|
123
|
+
* To sum up all of the above, the Hebrew probing mechanism knows about two
|
124
|
+
* charsets:
|
125
|
+
* Visual Hebrew - "ISO-8859-8" - backwards text - Words and sentences are
|
126
|
+
* backwards while line order is natural. For charset recognition purposes
|
127
|
+
* the line order is unimportant (In fact, for this implementation, even
|
128
|
+
* word order is unimportant).
|
129
|
+
* Logical Hebrew - "windows-1255" - normal, naturally ordered text.
|
130
|
+
*
|
131
|
+
* "ISO-8859-8-I" is a subset of windows-1255 and doesn't need to be
|
132
|
+
* specifically identified.
|
133
|
+
* "x-mac-hebrew" is also identified as windows-1255. A text in x-mac-hebrew
|
134
|
+
* that contain special punctuation marks or diacritics is displayed with
|
135
|
+
* some unconverted characters showing as question marks. This problem might
|
136
|
+
* be corrected using another model prober for x-mac-hebrew. Due to the fact
|
137
|
+
* that x-mac-hebrew texts are so rare, writing another model prober isn't
|
138
|
+
* worth the effort and performance hit.
|
139
|
+
*
|
140
|
+
* *** The Prober ***
|
141
|
+
*
|
142
|
+
* The prober is divided between two nsSBCharSetProbers and an nsHebrewProber,
|
143
|
+
* all of which are managed, created, fed data, inquired and deleted by the
|
144
|
+
* nsSBCSGroupProber. The two nsSBCharSetProbers identify that the text is in
|
145
|
+
* fact some kind of Hebrew, Logical or Visual. The final decision about which
|
146
|
+
* one is it is made by the nsHebrewProber by combining final-letter scores
|
147
|
+
* with the scores of the two nsSBCharSetProbers to produce a final answer.
|
148
|
+
*
|
149
|
+
* The nsSBCSGroupProber is responsible for stripping the original text of HTML
|
150
|
+
* tags, English characters, numbers, low-ASCII punctuation characters, spaces
|
151
|
+
* and new lines. It reduces any sequence of such characters to a single space.
|
152
|
+
* The buffer fed to each prober in the SBCS group prober is pure text in
|
153
|
+
* high-ASCII.
|
154
|
+
* The two nsSBCharSetProbers (model probers) share the same language model:
|
155
|
+
* Win1255Model.
|
156
|
+
* The first nsSBCharSetProber uses the model normally as any other
|
157
|
+
* nsSBCharSetProber does, to recognize windows-1255, upon which this model was
|
158
|
+
* built. The second nsSBCharSetProber is told to make the pair-of-letter
|
159
|
+
* lookup in the language model backwards. This in practice exactly simulates
|
160
|
+
* a visual Hebrew model using the windows-1255 logical Hebrew model.
|
161
|
+
*
|
162
|
+
* The nsHebrewProber is not using any language model. All it does is look for
|
163
|
+
* final-letter evidence suggesting the text is either logical Hebrew or visual
|
164
|
+
* Hebrew. Disjointed from the model probers, the results of the nsHebrewProber
|
165
|
+
* alone are meaningless. nsHebrewProber always returns 0.00 as confidence
|
166
|
+
* since it never identifies a charset by itself. Instead, the pointer to the
|
167
|
+
* nsHebrewProber is passed to the model probers as a helper "Name Prober".
|
168
|
+
* When the Group prober receives a positive identification from any prober,
|
169
|
+
* it asks for the name of the charset identified. If the prober queried is a
|
170
|
+
* Hebrew model prober, the model prober forwards the call to the
|
171
|
+
* nsHebrewProber to make the final decision. In the nsHebrewProber, the
|
172
|
+
* decision is made according to the final-letters scores maintained and Both
|
173
|
+
* model probers scores. The answer is returned in the form of the name of the
|
174
|
+
* charset identified, either "windows-1255" or "ISO-8859-8".
|
175
|
+
*
|
176
|
+
*/
|
177
|
+
#endif /* nsHebrewProber_h__ */
|
@@ -0,0 +1,182 @@
|
|
1
|
+
/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
|
2
|
+
/* ***** BEGIN LICENSE BLOCK *****
|
3
|
+
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
|
4
|
+
*
|
5
|
+
* The contents of this file are subject to the Mozilla Public License Version
|
6
|
+
* 1.1 (the "License"); you may not use this file except in compliance with
|
7
|
+
* the License. You may obtain a copy of the License at
|
8
|
+
* http://www.mozilla.org/MPL/
|
9
|
+
*
|
10
|
+
* Software distributed under the License is distributed on an "AS IS" basis,
|
11
|
+
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
|
12
|
+
* for the specific language governing rights and limitations under the
|
13
|
+
* License.
|
14
|
+
*
|
15
|
+
* The Original Code is Mozilla Universal charset detector code.
|
16
|
+
*
|
17
|
+
* The Initial Developer of the Original Code is
|
18
|
+
* Netscape Communications Corporation.
|
19
|
+
* Portions created by the Initial Developer are Copyright (C) 2001
|
20
|
+
* the Initial Developer. All Rights Reserved.
|
21
|
+
*
|
22
|
+
* Contributor(s):
|
23
|
+
* Shy Shalom <shooshX@gmail.com>
|
24
|
+
*
|
25
|
+
* Alternatively, the contents of this file may be used under the terms of
|
26
|
+
* either the GNU General Public License Version 2 or later (the "GPL"), or
|
27
|
+
* the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
|
28
|
+
* in which case the provisions of the GPL or the LGPL are applicable instead
|
29
|
+
* of those above. If you wish to allow use of your version of this file only
|
30
|
+
* under the terms of either the GPL or the LGPL, and not to allow others to
|
31
|
+
* use your version of this file under the terms of the MPL, indicate your
|
32
|
+
* decision by deleting the provisions above and replace them with the notice
|
33
|
+
* and other provisions required by the GPL or the LGPL. If you do not delete
|
34
|
+
* the provisions above, a recipient may use your version of this file under
|
35
|
+
* the terms of any one of the MPL, the GPL or the LGPL.
|
36
|
+
*
|
37
|
+
* ***** END LICENSE BLOCK ***** */
|
38
|
+
|
39
|
+
#include "nsLatin1Prober.h"
|
40
|
+
#include "prmem.h"
|
41
|
+
#include <stdio.h>
|
42
|
+
|
43
|
+
#define UDF 0 // undefined
|
44
|
+
#define OTH 1 //other
|
45
|
+
#define ASC 2 // ascii capital letter
|
46
|
+
#define ASS 3 // ascii small letter
|
47
|
+
#define ACV 4 // accent capital vowel
|
48
|
+
#define ACO 5 // accent capital other
|
49
|
+
#define ASV 6 // accent small vowel
|
50
|
+
#define ASO 7 // accent small other
|
51
|
+
#define CLASS_NUM 8 // total classes
|
52
|
+
|
53
|
+
static const unsigned char Latin1_CharToClass[] =
|
54
|
+
{
|
55
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 00 - 07
|
56
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 08 - 0F
|
57
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 10 - 17
|
58
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 18 - 1F
|
59
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 20 - 27
|
60
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 28 - 2F
|
61
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 30 - 37
|
62
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 38 - 3F
|
63
|
+
OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC, // 40 - 47
|
64
|
+
ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, // 48 - 4F
|
65
|
+
ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC, // 50 - 57
|
66
|
+
ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH, // 58 - 5F
|
67
|
+
OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS, // 60 - 67
|
68
|
+
ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, // 68 - 6F
|
69
|
+
ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS, // 70 - 77
|
70
|
+
ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH, // 78 - 7F
|
71
|
+
OTH, UDF, OTH, ASO, OTH, OTH, OTH, OTH, // 80 - 87
|
72
|
+
OTH, OTH, ACO, OTH, ACO, UDF, ACO, UDF, // 88 - 8F
|
73
|
+
UDF, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // 90 - 97
|
74
|
+
OTH, OTH, ASO, OTH, ASO, UDF, ASO, ACO, // 98 - 9F
|
75
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // A0 - A7
|
76
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // A8 - AF
|
77
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // B0 - B7
|
78
|
+
OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH, // B8 - BF
|
79
|
+
ACV, ACV, ACV, ACV, ACV, ACV, ACO, ACO, // C0 - C7
|
80
|
+
ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV, // C8 - CF
|
81
|
+
ACO, ACO, ACV, ACV, ACV, ACV, ACV, OTH, // D0 - D7
|
82
|
+
ACV, ACV, ACV, ACV, ACV, ACO, ACO, ACO, // D8 - DF
|
83
|
+
ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASO, // E0 - E7
|
84
|
+
ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV, // E8 - EF
|
85
|
+
ASO, ASO, ASV, ASV, ASV, ASV, ASV, OTH, // F0 - F7
|
86
|
+
ASV, ASV, ASV, ASV, ASV, ASO, ASO, ASO, // F8 - FF
|
87
|
+
};
|
88
|
+
|
89
|
+
|
90
|
+
/* 0 : illegal
|
91
|
+
1 : very unlikely
|
92
|
+
2 : normal
|
93
|
+
3 : very likely
|
94
|
+
*/
|
95
|
+
static const unsigned char Latin1ClassModel[] =
|
96
|
+
{
|
97
|
+
/* UDF OTH ASC ASS ACV ACO ASV ASO */
|
98
|
+
/*UDF*/ 0, 0, 0, 0, 0, 0, 0, 0,
|
99
|
+
/*OTH*/ 0, 3, 3, 3, 3, 3, 3, 3,
|
100
|
+
/*ASC*/ 0, 3, 3, 3, 3, 3, 3, 3,
|
101
|
+
/*ASS*/ 0, 3, 3, 3, 1, 1, 3, 3,
|
102
|
+
/*ACV*/ 0, 3, 3, 3, 1, 2, 1, 2,
|
103
|
+
/*ACO*/ 0, 3, 3, 3, 3, 3, 3, 3,
|
104
|
+
/*ASV*/ 0, 3, 1, 3, 1, 1, 1, 3,
|
105
|
+
/*ASO*/ 0, 3, 1, 3, 1, 1, 3, 3,
|
106
|
+
};
|
107
|
+
|
108
|
+
void nsLatin1Prober::Reset(void)
|
109
|
+
{
|
110
|
+
mState = eDetecting;
|
111
|
+
mLastCharClass = OTH;
|
112
|
+
for (int i = 0; i < FREQ_CAT_NUM; i++)
|
113
|
+
mFreqCounter[i] = 0;
|
114
|
+
}
|
115
|
+
|
116
|
+
|
117
|
+
nsProbingState nsLatin1Prober::HandleData(const char* aBuf, PRUint32 aLen)
|
118
|
+
{
|
119
|
+
char *newBuf1 = 0;
|
120
|
+
PRUint32 newLen1 = 0;
|
121
|
+
|
122
|
+
if (!FilterWithEnglishLetters(aBuf, aLen, &newBuf1, newLen1)) {
|
123
|
+
newBuf1 = (char*)aBuf;
|
124
|
+
newLen1 = aLen;
|
125
|
+
}
|
126
|
+
|
127
|
+
unsigned char charClass;
|
128
|
+
unsigned char freq;
|
129
|
+
for (PRUint32 i = 0; i < newLen1; i++)
|
130
|
+
{
|
131
|
+
charClass = Latin1_CharToClass[(unsigned char)newBuf1[i]];
|
132
|
+
freq = Latin1ClassModel[mLastCharClass*CLASS_NUM + charClass];
|
133
|
+
if (freq == 0) {
|
134
|
+
mState = eNotMe;
|
135
|
+
break;
|
136
|
+
}
|
137
|
+
mFreqCounter[freq]++;
|
138
|
+
mLastCharClass = charClass;
|
139
|
+
}
|
140
|
+
|
141
|
+
if (newBuf1 != aBuf)
|
142
|
+
PR_FREEIF(newBuf1);
|
143
|
+
|
144
|
+
return mState;
|
145
|
+
}
|
146
|
+
|
147
|
+
float nsLatin1Prober::GetConfidence(void)
|
148
|
+
{
|
149
|
+
if (mState == eNotMe)
|
150
|
+
return 0.01f;
|
151
|
+
|
152
|
+
float confidence;
|
153
|
+
PRUint32 total = 0;
|
154
|
+
for (PRInt32 i = 0; i < FREQ_CAT_NUM; i++)
|
155
|
+
total += mFreqCounter[i];
|
156
|
+
|
157
|
+
if(!total)
|
158
|
+
confidence = 0.0f;
|
159
|
+
else
|
160
|
+
{
|
161
|
+
confidence = mFreqCounter[3]*1.0f / total;
|
162
|
+
confidence -= mFreqCounter[1]*20.0f/total;
|
163
|
+
}
|
164
|
+
|
165
|
+
if (confidence < 0.0f)
|
166
|
+
confidence = 0.0f;
|
167
|
+
|
168
|
+
// lower the confidence of latin1 so that other more accurate detector
|
169
|
+
// can take priority.
|
170
|
+
confidence *= 0.50f;
|
171
|
+
|
172
|
+
return confidence;
|
173
|
+
}
|
174
|
+
|
175
|
+
#ifdef DEBUG_chardet
|
176
|
+
void nsLatin1Prober::DumpStatus()
|
177
|
+
{
|
178
|
+
printf(" Latin1Prober: %1.3f [%s]\r\n", GetConfidence(), GetCharSetName());
|
179
|
+
}
|
180
|
+
#endif
|
181
|
+
|
182
|
+
|