X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=lib%2Fencodings;h=ca47cf18220d68275c1c7a4983781ecbb86ac1ba;hb=992fe6561ed1eb1fb0e212ab50e1c37e1b5756b9;hp=75ae8f3d0dccb2016ecf337ede1c42234263aae9;hpb=ad767b159d2755525c917ff4c660c935cf807a8d;p=lyx.git diff --git a/lib/encodings b/lib/encodings index 75ae8f3d0d..ca47cf1822 100644 --- a/lib/encodings +++ b/lib/encodings @@ -17,6 +17,12 @@ # In this case, TeX control characters in high bytes is not a problem. # The invocation is platex -kanji= +# The set of "iconv" supported encodings is system dependent. + +# For Gnu libiconv, supported encodings are listed at +# https://www.gnu.org/software/libiconv/ +# and available via the `iconv --list` command. + # Syntax: Encoding End # LyX name: Name used by the file format and in lib/languages. Must be unique! @@ -26,17 +32,30 @@ # width: One of fixed, variable, or variableunsafe (see above). # package: One of none, inputenc, CJK, or japanese (see above). -# encodings used by inputenc.sty +# Encodings used with inputenc.sty +# ================================ + +# "inputenc" is a base LaTeX package that provides an extensible framework +# for conversion of a document encoding into an "LaTeX Internal Character +# Representation" (LICR) and a set of encoding definitions +# (.def files). Additional encoding definitions are provided by +# several language support packages. +# +# The following encodings from http://www.ctan.org/pkg/latex-cyrillic are +# not included, because they are not widely used and lack iconv support: +# ctt, dbk, isoir111, koi8-ru, lcyenc, maccyr, macukr, mik, mls, mnk, mos, +# and pt254. -Encoding utf8 utf8 "Unicode (utf8)" UTF-8 variable inputenc +# inputenc's standard utf8 support: +Encoding utf8 utf8 "Default" UTF-8 variable inputenc End -# This one is used by many CJK packages. utf8 is supposed to be the successor, -# but does not have all features of utf8x yet. -Encoding utf8x utf8x "Unicode (ucs-extended) (utf8x)" UTF-8 variable inputenc +# extended utf8 support from the "ucs" package: +# Larger set of supported characters but conflicts with some packages. +Encoding utf8x utf8x "Extended [ucs] (utf8x)" UTF-8 variable inputenc End -# This encoding is used to typeset Armenian using the armTeX package +# from http://www.ctan.org/pkg/armtex Encoding armscii8 armscii8 "Armenian (ArmSCII8)" ARMSCII-8 fixed inputenc End @@ -52,14 +71,15 @@ End Encoding iso8859-4 latin4 "Baltic (ISO 8859-4)" ISO-8859-4 fixed inputenc End +# from http://www.ctan.org/pkg/latex-cyrillic Encoding iso8859-5 iso88595 "Cyrillic (ISO 8859-5)" ISO-8859-5 fixed inputenc End -# Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/ +# from http://www.ctan.org/pkg/arabi Encoding iso8859-6 8859-6 "Arabic (ISO 8859-6)" ISO-8859-6 fixed inputenc End -# Not standard, see http://ctan.org/tex-archive/language/greek/greek-inputenc +# from http://www.ctan.org/pkg/greek-inputenc Encoding iso8859-7 iso-8859-7 "Greek (ISO 8859-7)" ISO-8859-7 fixed inputenc End @@ -69,8 +89,7 @@ End Encoding iso8859-9 latin5 "Turkish (ISO 8859-9)" ISO-8859-9 fixed inputenc End -# Not standard, see http://www.vtex.lt/tex/littex/index.html -Encoding iso8859-13 l7xenc "Baltic (ISO 8859-13)" ISO-8859-13 fixed inputenc +Encoding iso8859-13 latin7 "Baltic (ISO 8859-13)" ISO-8859-13 fixed inputenc End Encoding iso8859-15 latin9 "Western European (ISO 8859-15)" ISO-8859-15 fixed inputenc @@ -85,7 +104,7 @@ End Encoding cp437 cp437 "DOS (CP 437)" CP437 fixed inputenc End -# cp437, but on position 225 is sz instead of beta +# like cp437, but on position 225 is sz instead of beta Encoding cp437de cp437de "DOS-de (CP 437-de)" CP437 fixed inputenc End @@ -95,9 +114,12 @@ End Encoding cp852 cp852 "Central European (CP 852)" CP852 fixed inputenc End +# from http://www.ctan.org/pkg/latex-cyrillic Encoding cp855 cp855 "Cyrillic (CP 855)" CP855 fixed inputenc End +# Gnu iconv only supports cp858, if configured with "--enable-extra-encodings" +# (see https://www.gnu.org/software/libiconv/) Encoding cp858 cp858 "Western European (CP 858)" CP858 fixed inputenc End @@ -107,12 +129,14 @@ End Encoding cp865 cp865 "Nordic languages (CP 865)" CP865 fixed inputenc End +# from http://www.ctan.org/pkg/latex-cyrillic Encoding cp866 cp866 "Cyrillic (CP 866)" CP866 fixed inputenc End Encoding cp1250 cp1250 "Central European (CP 1250)" CP1250 fixed inputenc End +# from http://www.ctan.org/pkg/latex-cyrillic Encoding cp1251 cp1251 "Cyrillic (CP 1251)" CP1251 fixed inputenc End @@ -123,25 +147,30 @@ End Encoding cp1255 cp1255 "Hebrew (CP 1255)" CP1255 fixed inputenc End -# Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/ +# from http://www.ctan.org/pkg/arabi Encoding cp1256 cp1256 "Arabic (CP 1256)" CP1256 fixed inputenc End Encoding cp1257 cp1257 "Baltic (CP 1257)" CP1257 fixed inputenc End +# from http://www.ctan.org/pkg/latex-cyrillic Encoding koi8-r koi8-r "Cyrillic (KOI8-R)" KOI8-R fixed inputenc End +# from http://www.ctan.org/pkg/latex-cyrillic Encoding koi8-u koi8-u "Cyrillic (KOI8-U)" KOI8-U fixed inputenc End +# from http://www.ctan.org/pkg/latex-cyrillic Encoding pt154 pt154 "Cyrillic (pt 154)" PT154 fixed inputenc End -Encoding pt254 pt254 "Cyrillic (pt 254)" PT254 fixed inputenc +# from https://ctan.org/pkg/babel-thai +Encoding tis620-0 tis620 "Thai (TIS 620-0)" TIS620-0 fixed inputenc End + # encodings used by CJK.sty # The following encodings that are supported by the CJK package are not @@ -183,7 +212,7 @@ Encoding euc-kr KS "Korean (EUC-KR)" EUC-KR variable CJK End # The CJK package has yet another name for utf8... -Encoding utf8-cjk UTF8 "Unicode (CJK) (utf8)" UTF-8 variable CJK +Encoding utf8-cjk UTF8 "Extended [CJK] (Chinese/Japanese/Korean)" UTF-8 variable CJK End # For traditional chinese @@ -204,21 +233,21 @@ Encoding jis-platex jis "Japanese (pLaTeX) (JIS)" ISO-2022-JP variable japanese End Encoding shift-jis-platex sjis "Japanese (pLaTeX) (SJIS)" CP932 variable japanese End -Encoding utf8-platex utf8 "Japanese (pLaTeX) (UTF8)" UTF-8 variable japanese +Encoding utf8-platex utf8 "Extended [pLaTeX] (Japanese)" UTF-8 variable japanese End -# This one needs hardcoded support, since the inputenc package does not know -# tis620-0, and thailatex sets up babel directly to use tis620-0, so the -# LaTeX name is never output to .tex files (but needed for the hardcoded -# tis620-0 support). -Encoding tis620-0 tis620-0 "Thai (TIS 620-0)" TIS620-0 fixed none -End - -# A plain utf8 encoding that does not use the inputenc package. -# Such an encoding is required for XeTeX. -Encoding utf8-plain utf8-plain "Unicode (XeTeX) (utf8)" UTF-8 variable none +# A plain utf8 encoding that does not use the inputenc package +# nor the LyX-added conversions in lib/unicodesymbols. +# Such an encoding is required for XeTeX and LuaTeX. +Encoding utf8-plain utf8-plain "Direct" UTF-8 variable none End # Pure 7bit ASCII encoding (partially hardcoded in LyX) Encoding ascii ascii "ASCII" ascii fixed none End + +# Semantic encodings + +# Inherit encoding of the context (used by verbatim) +Encoding inherit inherit "" "" fixed none +End