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 +1,81 @@
|
|
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.org 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) 1998
|
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
|
+
// for S-JIS encoding, obeserve characteristic:
|
39
|
+
// 1, kana character (or hankaku?) often have hight frequency of appereance
|
40
|
+
// 2, kana character often exist in group
|
41
|
+
// 3, certain combination of kana is never used in japanese language
|
42
|
+
|
43
|
+
#ifndef nsSJISProber_h__
|
44
|
+
#define nsSJISProber_h__
|
45
|
+
|
46
|
+
#include "nsCharSetProber.h"
|
47
|
+
#include "nsCodingStateMachine.h"
|
48
|
+
#include "JpCntx.h"
|
49
|
+
#include "CharDistribution.h"
|
50
|
+
|
51
|
+
|
52
|
+
class nsSJISProber: public nsCharSetProber {
|
53
|
+
public:
|
54
|
+
nsSJISProber(PRBool aIsPreferredLanguage)
|
55
|
+
:mIsPreferredLanguage(aIsPreferredLanguage)
|
56
|
+
{mCodingSM = new nsCodingStateMachine(&SJISSMModel);
|
57
|
+
Reset();}
|
58
|
+
virtual ~nsSJISProber(void){delete mCodingSM;}
|
59
|
+
nsProbingState HandleData(const char* aBuf, PRUint32 aLen);
|
60
|
+
const char* GetCharSetName() {return "SHIFT_JIS";}
|
61
|
+
const char* GetLanguage() {return "ja";}
|
62
|
+
nsProbingState GetState(void) {return mState;}
|
63
|
+
void Reset(void);
|
64
|
+
float GetConfidence(void);
|
65
|
+
void SetOpion() {}
|
66
|
+
|
67
|
+
protected:
|
68
|
+
nsCodingStateMachine* mCodingSM;
|
69
|
+
nsProbingState mState;
|
70
|
+
|
71
|
+
SJISContextAnalysis mContextAnalyser;
|
72
|
+
SJISDistributionAnalysis mDistributionAnalyser;
|
73
|
+
|
74
|
+
char mLastChar[2];
|
75
|
+
PRBool mIsPreferredLanguage;
|
76
|
+
|
77
|
+
};
|
78
|
+
|
79
|
+
|
80
|
+
#endif /* nsSJISProber_h__ */
|
81
|
+
|
@@ -0,0 +1,87 @@
|
|
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.org 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) 1998
|
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 "nsUTF8Prober.h"
|
39
|
+
|
40
|
+
void nsUTF8Prober::Reset(void)
|
41
|
+
{
|
42
|
+
mCodingSM->Reset();
|
43
|
+
mNumOfMBChar = 0;
|
44
|
+
mState = eDetecting;
|
45
|
+
}
|
46
|
+
|
47
|
+
nsProbingState nsUTF8Prober::HandleData(const char* aBuf, PRUint32 aLen)
|
48
|
+
{
|
49
|
+
PRUint32 codingState;
|
50
|
+
|
51
|
+
for (PRUint32 i = 0; i < aLen; i++)
|
52
|
+
{
|
53
|
+
codingState = mCodingSM->NextState(aBuf[i]);
|
54
|
+
if (codingState == eItsMe)
|
55
|
+
{
|
56
|
+
mState = eFoundIt;
|
57
|
+
break;
|
58
|
+
}
|
59
|
+
if (codingState == eStart)
|
60
|
+
{
|
61
|
+
if (mCodingSM->GetCurrentCharLen() >= 2)
|
62
|
+
mNumOfMBChar++;
|
63
|
+
}
|
64
|
+
}
|
65
|
+
|
66
|
+
if (mState == eDetecting)
|
67
|
+
if (GetConfidence() > SHORTCUT_THRESHOLD)
|
68
|
+
mState = eFoundIt;
|
69
|
+
return mState;
|
70
|
+
}
|
71
|
+
|
72
|
+
#define ONE_CHAR_PROB (float)0.50
|
73
|
+
|
74
|
+
float nsUTF8Prober::GetConfidence(void)
|
75
|
+
{
|
76
|
+
float unlike = (float)0.99;
|
77
|
+
|
78
|
+
if (mNumOfMBChar < 6)
|
79
|
+
{
|
80
|
+
for (PRUint32 i = 0; i < mNumOfMBChar; i++)
|
81
|
+
unlike *= ONE_CHAR_PROB;
|
82
|
+
return (float)1.0 - unlike;
|
83
|
+
}
|
84
|
+
else
|
85
|
+
return (float)0.99;
|
86
|
+
}
|
87
|
+
|
@@ -0,0 +1,66 @@
|
|
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.org 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) 1998
|
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 nsUTF8Prober_h__
|
39
|
+
#define nsUTF8Prober_h__
|
40
|
+
|
41
|
+
#include <cstddef>
|
42
|
+
#include "nsCharSetProber.h"
|
43
|
+
#include "nsCodingStateMachine.h"
|
44
|
+
|
45
|
+
class nsUTF8Prober: public nsCharSetProber {
|
46
|
+
public:
|
47
|
+
nsUTF8Prober(){mNumOfMBChar = 0;
|
48
|
+
mCodingSM = new nsCodingStateMachine(&UTF8SMModel);
|
49
|
+
Reset(); }
|
50
|
+
virtual ~nsUTF8Prober(){delete mCodingSM;}
|
51
|
+
nsProbingState HandleData(const char* aBuf, PRUint32 aLen);
|
52
|
+
const char* GetCharSetName() {return "UTF-8";}
|
53
|
+
const char* GetLanguage() {return NULL;}
|
54
|
+
nsProbingState GetState(void) {return mState;}
|
55
|
+
void Reset(void);
|
56
|
+
float GetConfidence(void);
|
57
|
+
void SetOpion() {}
|
58
|
+
|
59
|
+
protected:
|
60
|
+
nsCodingStateMachine* mCodingSM;
|
61
|
+
nsProbingState mState;
|
62
|
+
PRUint32 mNumOfMBChar;
|
63
|
+
};
|
64
|
+
|
65
|
+
#endif /* nsUTF8Prober_h__ */
|
66
|
+
|
@@ -0,0 +1,339 @@
|
|
1
|
+
/* -*- Mode: C++; tab-width: 2; 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 "nscore.h"
|
40
|
+
|
41
|
+
#include "nsUniversalDetector.h"
|
42
|
+
|
43
|
+
#include "nsMBCSGroupProber.h"
|
44
|
+
#include "nsSBCSGroupProber.h"
|
45
|
+
#include "nsEscCharsetProber.h"
|
46
|
+
#include "nsLatin1Prober.h"
|
47
|
+
|
48
|
+
nsUniversalDetector::nsUniversalDetector(PRUint32 aLanguageFilter)
|
49
|
+
{
|
50
|
+
mNbspFound = PR_FALSE;
|
51
|
+
mDone = PR_FALSE;
|
52
|
+
mBestGuess = -1; //illegal value as signal
|
53
|
+
mInTag = PR_FALSE;
|
54
|
+
mEscCharSetProber = nsnull;
|
55
|
+
|
56
|
+
mStart = PR_TRUE;
|
57
|
+
mDetectedCharset = nsnull;
|
58
|
+
mGotData = PR_FALSE;
|
59
|
+
mInputState = ePureAscii;
|
60
|
+
mLastChar = '\0';
|
61
|
+
mLanguageFilter = aLanguageFilter;
|
62
|
+
|
63
|
+
PRUint32 i;
|
64
|
+
for (i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
|
65
|
+
mCharSetProbers[i] = nsnull;
|
66
|
+
}
|
67
|
+
|
68
|
+
nsUniversalDetector::~nsUniversalDetector()
|
69
|
+
{
|
70
|
+
for (PRInt32 i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
|
71
|
+
delete mCharSetProbers[i];
|
72
|
+
|
73
|
+
delete mEscCharSetProber;
|
74
|
+
}
|
75
|
+
|
76
|
+
void
|
77
|
+
nsUniversalDetector::Reset()
|
78
|
+
{
|
79
|
+
mNbspFound = PR_FALSE;
|
80
|
+
mDone = PR_FALSE;
|
81
|
+
mBestGuess = -1; //illegal value as signal
|
82
|
+
mInTag = PR_FALSE;
|
83
|
+
|
84
|
+
mStart = PR_TRUE;
|
85
|
+
mDetectedCharset = nsnull;
|
86
|
+
mGotData = PR_FALSE;
|
87
|
+
mInputState = ePureAscii;
|
88
|
+
mLastChar = '\0';
|
89
|
+
|
90
|
+
if (mEscCharSetProber)
|
91
|
+
mEscCharSetProber->Reset();
|
92
|
+
|
93
|
+
PRUint32 i;
|
94
|
+
for (i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
|
95
|
+
if (mCharSetProbers[i])
|
96
|
+
mCharSetProbers[i]->Reset();
|
97
|
+
}
|
98
|
+
|
99
|
+
//---------------------------------------------------------------------
|
100
|
+
#define SHORTCUT_THRESHOLD (float)0.95
|
101
|
+
#define MINIMUM_THRESHOLD (float)0.20
|
102
|
+
|
103
|
+
nsresult nsUniversalDetector::HandleData(const char* aBuf, PRUint32 aLen)
|
104
|
+
{
|
105
|
+
if(mDone)
|
106
|
+
return NS_OK;
|
107
|
+
|
108
|
+
if (aLen > 0)
|
109
|
+
mGotData = PR_TRUE;
|
110
|
+
|
111
|
+
/* If the data starts with BOM, we know it is UTF. */
|
112
|
+
if (mStart)
|
113
|
+
{
|
114
|
+
mStart = PR_FALSE;
|
115
|
+
if (aLen > 2)
|
116
|
+
{
|
117
|
+
switch (aBuf[0])
|
118
|
+
{
|
119
|
+
case '\xEF':
|
120
|
+
if (('\xBB' == aBuf[1]) && ('\xBF' == aBuf[2]))
|
121
|
+
/* EF BB BF: UTF-8 encoded BOM. */
|
122
|
+
mDetectedCharset = "UTF-8";
|
123
|
+
break;
|
124
|
+
case '\xFE':
|
125
|
+
if ('\xFF' == aBuf[1])
|
126
|
+
/* FE FF: UTF-16, big endian BOM. */
|
127
|
+
mDetectedCharset = "UTF-16";
|
128
|
+
break;
|
129
|
+
case '\xFF':
|
130
|
+
if ('\xFE' == aBuf[1])
|
131
|
+
{
|
132
|
+
if (aLen > 3 &&
|
133
|
+
aBuf[2] == '\x00' &&
|
134
|
+
aBuf[3] == '\x00')
|
135
|
+
{
|
136
|
+
/* FF FE 00 00: UTF-32 (LE). */
|
137
|
+
mDetectedCharset = "UTF-32";
|
138
|
+
}
|
139
|
+
else
|
140
|
+
{
|
141
|
+
/* FF FE: UTF-16, little endian BOM. */
|
142
|
+
mDetectedCharset = "UTF-16";
|
143
|
+
}
|
144
|
+
}
|
145
|
+
break;
|
146
|
+
case '\x00':
|
147
|
+
if (aLen > 3 &&
|
148
|
+
aBuf[1] == '\x00' &&
|
149
|
+
aBuf[2] == '\xFE' &&
|
150
|
+
aBuf[3] == '\xFF')
|
151
|
+
{
|
152
|
+
/* 00 00 FE FF: UTF-32 (BE). */
|
153
|
+
mDetectedCharset = "UTF-32";
|
154
|
+
}
|
155
|
+
break;
|
156
|
+
}
|
157
|
+
}
|
158
|
+
|
159
|
+
if (mDetectedCharset)
|
160
|
+
{
|
161
|
+
mDone = PR_TRUE;
|
162
|
+
return NS_OK;
|
163
|
+
}
|
164
|
+
}
|
165
|
+
|
166
|
+
PRUint32 i;
|
167
|
+
for (i = 0; i < aLen; i++)
|
168
|
+
{
|
169
|
+
/* If every other character is ASCII or 0xA0, we don't run charset
|
170
|
+
* probers.
|
171
|
+
* 0xA0 (NBSP in a few charset) is apparently a rare exception
|
172
|
+
* of non-ASCII character often contained in nearly-ASCII text. */
|
173
|
+
if (aBuf[i] & '\x80' && aBuf[i] != '\xA0')
|
174
|
+
{
|
175
|
+
/* We got a non-ASCII byte (high-byte) */
|
176
|
+
if (mInputState != eHighbyte)
|
177
|
+
{
|
178
|
+
//adjust state
|
179
|
+
mInputState = eHighbyte;
|
180
|
+
|
181
|
+
//kill mEscCharSetProber if it is active
|
182
|
+
if (mEscCharSetProber) {
|
183
|
+
delete mEscCharSetProber;
|
184
|
+
mEscCharSetProber = nsnull;
|
185
|
+
}
|
186
|
+
|
187
|
+
//start multibyte and singlebyte charset prober
|
188
|
+
if (nsnull == mCharSetProbers[0])
|
189
|
+
{
|
190
|
+
mCharSetProbers[0] = new nsMBCSGroupProber(mLanguageFilter);
|
191
|
+
if (nsnull == mCharSetProbers[0])
|
192
|
+
return NS_ERROR_OUT_OF_MEMORY;
|
193
|
+
}
|
194
|
+
if (nsnull == mCharSetProbers[1] &&
|
195
|
+
(mLanguageFilter & NS_FILTER_NON_CJK))
|
196
|
+
{
|
197
|
+
mCharSetProbers[1] = new nsSBCSGroupProber;
|
198
|
+
if (nsnull == mCharSetProbers[1])
|
199
|
+
return NS_ERROR_OUT_OF_MEMORY;
|
200
|
+
}
|
201
|
+
if (nsnull == mCharSetProbers[2])
|
202
|
+
{
|
203
|
+
mCharSetProbers[2] = new nsLatin1Prober;
|
204
|
+
if (nsnull == mCharSetProbers[2])
|
205
|
+
return NS_ERROR_OUT_OF_MEMORY;
|
206
|
+
}
|
207
|
+
}
|
208
|
+
}
|
209
|
+
else
|
210
|
+
{
|
211
|
+
/* Just pure ASCII or NBSP so far. */
|
212
|
+
if (aBuf[i] == '\xA0')
|
213
|
+
{
|
214
|
+
/* ASCII with the only exception of NBSP seems quite common.
|
215
|
+
* I doubt it is really necessary to train a model here, so let's
|
216
|
+
* just make an exception.
|
217
|
+
*/
|
218
|
+
mNbspFound = PR_TRUE;
|
219
|
+
}
|
220
|
+
else if (mInputState == ePureAscii &&
|
221
|
+
(aBuf[i] == '\033' || (aBuf[i] == '{' && mLastChar == '~')))
|
222
|
+
{
|
223
|
+
/* We found an escape character or HZ "~{". */
|
224
|
+
mInputState = eEscAscii;
|
225
|
+
}
|
226
|
+
mLastChar = aBuf[i];
|
227
|
+
}
|
228
|
+
}
|
229
|
+
|
230
|
+
nsProbingState st;
|
231
|
+
switch (mInputState)
|
232
|
+
{
|
233
|
+
case eEscAscii:
|
234
|
+
if (nsnull == mEscCharSetProber) {
|
235
|
+
mEscCharSetProber = new nsEscCharSetProber(mLanguageFilter);
|
236
|
+
if (nsnull == mEscCharSetProber)
|
237
|
+
return NS_ERROR_OUT_OF_MEMORY;
|
238
|
+
}
|
239
|
+
st = mEscCharSetProber->HandleData(aBuf, aLen);
|
240
|
+
if (st == eFoundIt)
|
241
|
+
{
|
242
|
+
mDone = PR_TRUE;
|
243
|
+
mDetectedCharset = mEscCharSetProber->GetCharSetName();
|
244
|
+
}
|
245
|
+
break;
|
246
|
+
case eHighbyte:
|
247
|
+
for (i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
|
248
|
+
{
|
249
|
+
if (mCharSetProbers[i])
|
250
|
+
{
|
251
|
+
st = mCharSetProbers[i]->HandleData(aBuf, aLen);
|
252
|
+
if (st == eFoundIt)
|
253
|
+
{
|
254
|
+
mDone = PR_TRUE;
|
255
|
+
mDetectedCharset = mCharSetProbers[i]->GetCharSetName();
|
256
|
+
return NS_OK;
|
257
|
+
}
|
258
|
+
}
|
259
|
+
}
|
260
|
+
break;
|
261
|
+
|
262
|
+
default:
|
263
|
+
break;
|
264
|
+
}
|
265
|
+
return NS_OK;
|
266
|
+
}
|
267
|
+
|
268
|
+
|
269
|
+
//---------------------------------------------------------------------
|
270
|
+
void nsUniversalDetector::DataEnd()
|
271
|
+
{
|
272
|
+
if (!mGotData)
|
273
|
+
{
|
274
|
+
// we haven't got any data yet, return immediately
|
275
|
+
// caller program sometimes call DataEnd before anything has been sent to detector
|
276
|
+
return;
|
277
|
+
}
|
278
|
+
|
279
|
+
if (! mDetectedCharset)
|
280
|
+
{
|
281
|
+
switch (mInputState)
|
282
|
+
{
|
283
|
+
case eEscAscii:
|
284
|
+
case ePureAscii:
|
285
|
+
if (mNbspFound)
|
286
|
+
{
|
287
|
+
/* ISO-8859-1 is a good result candidate for ASCII + NBSP.
|
288
|
+
* (though it could have been any ISO-8859 encoding). */
|
289
|
+
mDetectedCharset = "ISO-8859-1";
|
290
|
+
}
|
291
|
+
else
|
292
|
+
{
|
293
|
+
/* ASCII with the ESC character (or the sequence "~{") is still
|
294
|
+
* ASCII until proven otherwise. */
|
295
|
+
mDetectedCharset = "ASCII";
|
296
|
+
}
|
297
|
+
default:
|
298
|
+
break;
|
299
|
+
}
|
300
|
+
}
|
301
|
+
|
302
|
+
if (mDetectedCharset)
|
303
|
+
{
|
304
|
+
/* These cases are limited enough that we are always confident
|
305
|
+
* when finding them.
|
306
|
+
*/
|
307
|
+
mDone = PR_TRUE;
|
308
|
+
Report(mDetectedCharset, NULL, 1.0);
|
309
|
+
return;
|
310
|
+
}
|
311
|
+
|
312
|
+
switch (mInputState)
|
313
|
+
{
|
314
|
+
case eHighbyte:
|
315
|
+
{
|
316
|
+
float proberConfidence;
|
317
|
+
|
318
|
+
for (PRInt32 i = 0; i < NUM_OF_CHARSET_PROBERS; i++)
|
319
|
+
{
|
320
|
+
if (mCharSetProbers[i])
|
321
|
+
{
|
322
|
+
proberConfidence = mCharSetProbers[i]->GetConfidence();
|
323
|
+
|
324
|
+
if (proberConfidence > MINIMUM_THRESHOLD)
|
325
|
+
/* Only report what we are confident in. */
|
326
|
+
Report(mCharSetProbers[i]->GetCharSetName(),
|
327
|
+
mCharSetProbers[i]->GetLanguage(),
|
328
|
+
proberConfidence);
|
329
|
+
}
|
330
|
+
}
|
331
|
+
}
|
332
|
+
break;
|
333
|
+
case eEscAscii:
|
334
|
+
break;
|
335
|
+
default:
|
336
|
+
;
|
337
|
+
}
|
338
|
+
return;
|
339
|
+
}
|