X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=lib%2Fencodings;h=c43f63802863a0a600b1489870f30d91f0aa0775;hb=0984e113171297e402c88ce048e9ccf1fb3d3619;hp=b05138119f6c7df0096b74eca2160066b87906ff;hpb=0c265078904d636985f8c990b7bfa833adc3edbe;p=lyx.git

diff --git a/lib/encodings b/lib/encodings
index b05138119f..c43f638028 100644
--- a/lib/encodings
+++ b/lib/encodings
@@ -1,125 +1,254 @@
 # FIXME: Have a look at the encodings known by the inputenc package and add
 # missing ones. Caution: File format change!
 
-# Note that you can only add single byte encodings to this file without
-# changing some C++ code.
-# The only multibyte encoding that is currently supported is utf8, and this
-# support is hardcoded to the iconv name "UTF-8".
-
-# Order of names: LyX name LaTeX name iconv name
-
-Encoding utf8 utf8 UTF-8
+# Note that you can only add singlebyte encodings to this file.
+# LyX does not support the output of multibyte encodings (e.g. utf16).
+# It does support singlebyte encodings with variable width (e.g. utf8).
+# These are marked with the "variable" keyword.
+# Fixed width encodings are marked with the "fixed" keyword.
+# The code points of TeX control characters like {, } and \ can occur in the
+# second byte of some variable width encodings. These encodings must not be
+# set as document encodings and are marked with the "variableunsafe" keyword.
+# They are only needed for proper tex2lyx import.
+
+# Most encodings require loading a latex package such as "inputenc" or "CJK".
+# There is no "japanese" latex package, rather this keyword indicates to LyX
+# to switch the buffer format and use platex instead of standard (pdf)latex.
+# In this case, TeX control characters in high bytes is not a problem.
+# The invocation is platex -kanji=<LaTeX name>
+
+# 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 <LyX name> <LaTeX name> <GUI name> <iconv name> <width> <package> End
+
+# LyX name:    Name used by the file format and in lib/languages. Must be unique!
+# LaTeX name:  Used in the latex export or passed to platex as command-line switch.
+# GUI name:    Displayed in document settings.
+# iconv name:  Used by iconv.
+# width:       One of fixed, variable, or variableunsafe (see above).
+# package:     One of none, inputenc, CJK, or japanese (see above).
+
+# 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
+# (<LaTeX name>.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.
+
+# inputenc's standard utf8 support:
+Encoding utf8 utf8 "Unicode (utf8)" 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 UTF-8
+Encoding utf8x utf8x "Unicode (ucs-extended) (utf8x)" UTF-8 variable inputenc
+End
+
+# from http://www.ctan.org/pkg/armtex
+Encoding armscii8 armscii8 "Armenian (ArmSCII8)" ARMSCII-8 fixed inputenc
+End
+
+Encoding iso8859-1 latin1 "Western European (ISO 8859-1)" ISO-8859-1 fixed inputenc
+End
+
+Encoding iso8859-2 latin2 "Central European (ISO 8859-2)" ISO-8859-2 fixed inputenc
+End
+
+Encoding iso8859-3 latin3 "South European (ISO 8859-3)" ISO-8859-3 fixed inputenc
+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
+
+# from http://www.ctan.org/pkg/arabi
+Encoding iso8859-6 8859-6 "Arabic (ISO 8859-6)" ISO-8859-6 fixed inputenc
+End
+
+# from http://www.ctan.org/pkg/greek-inputenc
+Encoding iso8859-7 iso-8859-7 "Greek (ISO 8859-7)" ISO-8859-7 fixed inputenc
+End
+
+Encoding iso8859-8 8859-8 "Hebrew (ISO 8859-8)" ISO-8859-8 fixed inputenc
+End
+
+Encoding iso8859-9 latin5 "Turkish (ISO 8859-9)" ISO-8859-9 fixed inputenc
+End
+
+Encoding iso8859-13 latin7 "Baltic (ISO 8859-13)" ISO-8859-13 fixed inputenc
 End
 
-Encoding iso8859-1 latin1 ISO-8859-1
+Encoding iso8859-15 latin9 "Western European (ISO 8859-15)" ISO-8859-15 fixed inputenc
 End
 
-Encoding iso8859-2 latin2 ISO-8859-2
+Encoding iso8859-16 latin10 "South-Eastern European (ISO 8859-16)" ISO-8859-16 fixed inputenc
 End
 
-Encoding iso8859-3 latin3 ISO-8859-3
+Encoding applemac applemac "Western European (Macintosh Roman)" Macintosh fixed inputenc
 End
 
-Encoding iso8859-4 latin4 ISO-8859-4
+Encoding cp437 cp437 "DOS (CP 437)" CP437 fixed inputenc
 End
 
-Encoding iso8859-5 iso88595 ISO-8859-5
+# like cp437, but on position 225 is sz instead of beta
+Encoding cp437de cp437de "DOS-de (CP 437-de)" CP437 fixed inputenc
 End
 
-# Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/
-Encoding iso8859-6 8859-6 ISO-8859-6
+Encoding cp850 cp850 "Western European (CP 850)" CP850 fixed inputenc
 End
 
-Encoding iso8859-7 iso-8859-7 ISO-8859-7
+Encoding cp852 cp852 "Central European (CP 852)" CP852 fixed inputenc
 End
 
-Encoding iso8859-8 8859-8 ISO-8859-8
+# from http://www.ctan.org/pkg/latex-cyrillic
+Encoding cp855 cp855 "Cyrillic (CP 855)" CP855 fixed inputenc
 End
 
-Encoding iso8859-9 latin5 ISO-8859-9
+# 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
 
-# Not standard, see http://www.vtex.lt/tex/littex/index.html
-Encoding iso8859-13 l7xenc ISO-8859-13
+Encoding cp862 cp862 "Hebrew (CP 862)" CP862 fixed inputenc
 End
 
-Encoding iso8859-15 latin9 ISO-8859-15
+Encoding cp865 cp865 "Nordic languages (CP 865)" CP865 fixed inputenc
 End
 
-Encoding iso8859-16 latin10 ISO-8859-16
+# from http://www.ctan.org/pkg/latex-cyrillic
+Encoding cp866 cp866 "Cyrillic (CP 866)" CP866 fixed inputenc
 End
 
-Encoding cp437 cp437 CP437
+Encoding cp1250 cp1250 "Central European (CP 1250)" CP1250 fixed inputenc
 End
 
-# cp437, but on position 225 is sz instead of beta
-Encoding cp437de cp437de CP437
+# from http://www.ctan.org/pkg/latex-cyrillic
+Encoding cp1251 cp1251 "Cyrillic (CP 1251)" CP1251 fixed inputenc
 End
 
-Encoding cp850 cp850 CP850
+# "ansinew" is harcoded as a synonym of this (see Encodings::fromLaTeXName)
+Encoding cp1252 cp1252 "Western European (CP 1252)" CP1252 fixed inputenc
 End
 
-Encoding cp852 cp852 CP852
+Encoding cp1255 cp1255 "Hebrew (CP 1255)" CP1255 fixed inputenc
 End
 
-Encoding cp855 cp855 CP855
+# from http://www.ctan.org/pkg/arabi
+Encoding cp1256 cp1256 "Arabic (CP 1256)" CP1256 fixed inputenc
 End
 
-Encoding cp858 cp858 CP858
+Encoding cp1257 cp1257 "Baltic (CP 1257)" CP1257 fixed inputenc
 End
 
-Encoding cp862 cp862 CP862
+# from http://www.ctan.org/pkg/latex-cyrillic
+Encoding koi8-r koi8-r "Cyrillic (KOI8-R)" KOI8-R fixed inputenc
 End
 
-Encoding cp865 cp865 CP865
+# from http://www.ctan.org/pkg/latex-cyrillic
+Encoding koi8-u koi8-u "Cyrillic (KOI8-U)" KOI8-U fixed inputenc
 End
 
-Encoding cp866 cp866 CP866
+# from http://www.ctan.org/pkg/latex-cyrillic
+Encoding pt154 pt154 "Cyrillic (pt 154)" PT154 fixed inputenc
 End
 
-Encoding cp1250 cp1250 CP1250
+# encodings used by CJK.sty
+
+# The following encodings that are supported by the CJK package are not
+# included here, because they are not widely used and lack proper iconv support:
+# Bg5+, GBt
+# See the NOTES file of libiconv for details.
+
+# For traditional chinese
+Encoding big5 Bg5 "Chinese (traditional) (Big5)" BIG5 variableunsafe CJK
 End
 
-Encoding cp1251 cp1251 CP1251
+# For japanese
+# We use CP932 and not SJIS, since it is a super set of SJIS except that it
+# translates SJIS 0x5c to U+005C (REVERSE SOLIDUS aka backslash) instead of
+# U+00A5 (YEN SIGN). Strictly speaking this is wrong, but there is a long
+# standing confusion which translation is correct, and using CP932 is also
+# consistent with the SJIS example file <texmf>/doc/latex/cjk/examples/SJIS.tex
+# of the CJK package. The CP932 extensions over SJIS do not matter here.
+Encoding shift-jis SJIS "Japanese (CJK) (SJIS)" CP932 variableunsafe CJK
+End
+
+# The following encodings need hardcoded support of the encodable unicode
+# range, but are known by iconv:
+
+# For simplified chinese
+Encoding euc-cn GB "Chinese (simplified) (EUC-CN)" EUC-CN variable CJK
 End
 
-Encoding cp1252 cp1252 CP1252
+# For simplified chinese
+Encoding gbk GBK "Chinese (simplified) (GBK)" GBK variable CJK
 End
 
-Encoding cp1255 cp1255 CP1255
+# For japanese
+Encoding jis JIS "Japanese (CJK) (JIS)" ISO-2022-JP variable CJK
 End
 
-# Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/
-Encoding cp1256 cp1256 CP1256
+# For korean
+Encoding euc-kr KS "Korean (EUC-KR)" EUC-KR variable CJK
 End
 
-Encoding cp1257 cp1257 CP1257
+# The CJK package has yet another name for utf8...
+Encoding utf8-cjk UTF8 "Unicode (CJK) (utf8)" UTF-8 variable CJK
 End
 
-Encoding koi8 koi8-r KOI8-R
+# For traditional chinese
+Encoding euc-tw EUC-TW "Chinese (traditional) (EUC-TW)" EUC-TW variable CJK
 End
 
-Encoding koi8-u koi8-u KOI8-U
+# For japanese
+Encoding euc-jp EUC-JP "Japanese (CJK) (EUC-JP)" EUC-JP variable CJK
+End
+
+# encodings that do not use a package
+
+# Traditional Japanese TeX programs require the japanese package.
+# that is incompatible with CJK and inputenc.
+Encoding euc-jp-platex euc "Japanese (pLaTeX) (EUC-JP)" EUC-JP variable japanese
+End
+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
 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 value
-# for inputenc is never output to .tex files (but needed for the hardcoded
+# 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 TIS620-0
+Encoding tis620-0 tis620-0 "Thai (TIS 620-0)" TIS620-0 fixed none
 End
 
-Encoding pt154 pt154 PT154
+# 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
 End
 
-Encoding pt254 pt254 PT254
+# Pure 7bit ASCII encoding (partially hardcoded in LyX)
+Encoding ascii ascii "ASCII" ascii fixed none
 End
 
-# Pure 7bit ASCII encoding (partially hardcoded in LyX)
-Encoding ascii ascii ascii
+# Semantic encodings
+
+# Inherit encoding of the context (used by verbatim)
+Encoding inherit inherit "" "" fixed none
 End