1 # FIXME: Have a look at the encodings known by the inputenc package and add
2 # missing ones. Caution: File format change!
4 # Note that you can only add singlebyte encodings to this file.
5 # LyX does not support the output of multibyte encodings (e.g. utf16).
6 # It does support singlebyte encodings with variable width (e.g. utf8).
7 # These are marked with the "variable" keyword.
8 # Fixed width encodings are marked with the "fixed" keyword.
9 # The code points of TeX control characters like {, } and \ can occur in the
10 # second byte of some variable width encodings. These encodings must not be
11 # set as document encodings and are marked with the "variableunsafe" keyword.
12 # They are only needed for proper tex2lyx import.
14 # Most encodings require loading a latex package such as "inputenc" or "CJK".
15 # There is no "japanese" latex package, rather this keyword indicates to LyX
16 # to switch the buffer format and use platex instead of standard (pdf)latex.
17 # In this case, TeX control characters in high bytes is not a problem.
18 # The invocation is platex -kanji=<LaTeX name>
20 # Syntax: Encoding <LyX name> <LaTeX name> <GUI name> <iconv name> <width> <package> End
22 # LyX name: Name used by the file format and in lib/languages. Must be unique!
23 # LaTeX name: Used in the latex export or passed to platex as command-line switch.
24 # GUI name: Displayed in document settings.
25 # iconv name: Used by iconv.
26 # width: One of fixed, variable, or variableunsafe (see above).
27 # package: One of none, inputenc, CJK, or japanese (see above).
29 # encodings used by inputenc.sty
31 Encoding utf8 utf8 "Unicode (utf8)" UTF-8 variable inputenc
34 # This one is used by many CJK packages. utf8 is supposed to be the successor,
35 # but does not have all features of utf8x yet.
36 Encoding utf8x utf8x "Unicode (ucs-extended) (utf8x)" UTF-8 variable inputenc
39 # This encoding is used to typeset Armenian using the armTeX package
40 Encoding armscii8 armscii8 "Armenian (ArmSCII8)" ARMSCII-8 fixed inputenc
43 Encoding iso8859-1 latin1 "Western European (ISO 8859-1)" ISO-8859-1 fixed inputenc
46 Encoding iso8859-2 latin2 "Central European (ISO 8859-2)" ISO-8859-2 fixed inputenc
49 Encoding iso8859-3 latin3 "South European (ISO 8859-3)" ISO-8859-3 fixed inputenc
52 Encoding iso8859-4 latin4 "Baltic (ISO 8859-4)" ISO-8859-4 fixed inputenc
55 Encoding iso8859-5 iso88595 "Cyrillic (ISO 8859-5)" ISO-8859-5 fixed inputenc
58 # Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/
59 Encoding iso8859-6 8859-6 "Arabic (ISO 8859-6)" ISO-8859-6 fixed inputenc
62 # Not standard, see http://ctan.org/tex-archive/language/greek/greek-inputenc
63 Encoding iso8859-7 iso-8859-7 "Greek (ISO 8859-7)" ISO-8859-7 fixed inputenc
66 Encoding iso8859-8 8859-8 "Hebrew (ISO 8859-8)" ISO-8859-8 fixed inputenc
69 Encoding iso8859-9 latin5 "Turkish (ISO 8859-9)" ISO-8859-9 fixed inputenc
72 Encoding iso8859-13 latin7 "Baltic (ISO 8859-13)" ISO-8859-13 fixed inputenc
75 Encoding iso8859-15 latin9 "Western European (ISO 8859-15)" ISO-8859-15 fixed inputenc
78 Encoding iso8859-16 latin10 "South-Eastern European (ISO 8859-16)" ISO-8859-16 fixed inputenc
81 Encoding applemac applemac "Western European (Macintosh Roman)" Macintosh fixed inputenc
84 Encoding cp437 cp437 "DOS (CP 437)" CP437 fixed inputenc
87 # cp437, but on position 225 is sz instead of beta
88 Encoding cp437de cp437de "DOS-de (CP 437-de)" CP437 fixed inputenc
91 Encoding cp850 cp850 "Western European (CP 850)" CP850 fixed inputenc
94 Encoding cp852 cp852 "Central European (CP 852)" CP852 fixed inputenc
97 Encoding cp855 cp855 "Cyrillic (CP 855)" CP855 fixed inputenc
100 # TODO: not supported by iconv (2.24 on Debian)
101 Encoding cp858 cp858 "Western European (CP 858)" CP858 fixed inputenc
104 Encoding cp862 cp862 "Hebrew (CP 862)" CP862 fixed inputenc
107 Encoding cp865 cp865 "Nordic languages (CP 865)" CP865 fixed inputenc
110 Encoding cp866 cp866 "Cyrillic (CP 866)" CP866 fixed inputenc
113 Encoding cp1250 cp1250 "Central European (CP 1250)" CP1250 fixed inputenc
116 Encoding cp1251 cp1251 "Cyrillic (CP 1251)" CP1251 fixed inputenc
119 # "ansinew" is harcoded as a synonym of this (see Encodings::fromLaTeXName)
120 Encoding cp1252 cp1252 "Western European (CP 1252)" CP1252 fixed inputenc
123 Encoding cp1255 cp1255 "Hebrew (CP 1255)" CP1255 fixed inputenc
126 # Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/
127 Encoding cp1256 cp1256 "Arabic (CP 1256)" CP1256 fixed inputenc
130 Encoding cp1257 cp1257 "Baltic (CP 1257)" CP1257 fixed inputenc
133 Encoding koi8-r koi8-r "Cyrillic (KOI8-R)" KOI8-R fixed inputenc
136 Encoding koi8-u koi8-u "Cyrillic (KOI8-U)" KOI8-U fixed inputenc
139 Encoding pt154 pt154 "Cyrillic (pt 154)" PT154 fixed inputenc
142 # TODO: not supported by iconv (2.24 on Debian)
143 Encoding pt254 pt254 "Cyrillic (pt 254)" PT254 fixed inputenc
146 # encodings used by CJK.sty
148 # The following encodings that are supported by the CJK package are not
149 # included here, because they are not widely used and lack proper iconv support:
151 # See the NOTES file of libiconv for details.
153 # For traditional chinese
154 Encoding big5 Bg5 "Chinese (traditional) (Big5)" BIG5 variableunsafe CJK
158 # We use CP932 and not SJIS, since it is a super set of SJIS except that it
159 # translates SJIS 0x5c to U+005C (REVERSE SOLIDUS aka backslash) instead of
160 # U+00A5 (YEN SIGN). Strictly speaking this is wrong, but there is a long
161 # standing confusion which translation is correct, and using CP932 is also
162 # consistent with the SJIS example file <texmf>/doc/latex/cjk/examples/SJIS.tex
163 # of the CJK package. The CP932 extensions over SJIS do not matter here.
164 Encoding shift-jis SJIS "Japanese (CJK) (SJIS)" CP932 variableunsafe CJK
167 # The following encodings need hardcoded support of the encodable unicode
168 # range, but are known by iconv:
170 # For simplified chinese
171 Encoding euc-cn GB "Chinese (simplified) (EUC-CN)" EUC-CN variable CJK
174 # For simplified chinese
175 Encoding gbk GBK "Chinese (simplified) (GBK)" GBK variable CJK
179 Encoding jis JIS "Japanese (CJK) (JIS)" ISO-2022-JP variable CJK
183 Encoding euc-kr KS "Korean (EUC-KR)" EUC-KR variable CJK
186 # The CJK package has yet another name for utf8...
187 Encoding utf8-cjk UTF8 "Unicode (CJK) (utf8)" UTF-8 variable CJK
190 # For traditional chinese
191 Encoding euc-tw EUC-TW "Chinese (traditional) (EUC-TW)" EUC-TW variable CJK
195 Encoding euc-jp EUC-JP "Japanese (CJK) (EUC-JP)" EUC-JP variable CJK
198 # encodings that do not use a package
200 # Traditional Japanese TeX programs require the japanese package.
201 # that is incompatible with CJK and inputenc.
202 Encoding euc-jp-platex euc "Japanese (pLaTeX) (EUC-JP)" EUC-JP variable japanese
204 Encoding jis-platex jis "Japanese (pLaTeX) (JIS)" ISO-2022-JP variable japanese
206 Encoding shift-jis-platex sjis "Japanese (pLaTeX) (SJIS)" CP932 variable japanese
208 Encoding utf8-platex utf8 "Japanese (pLaTeX) (UTF8)" UTF-8 variable japanese
211 # This one needs hardcoded support, since the inputenc package does not know
212 # tis620-0, and thailatex sets up babel directly to use tis620-0, so the
213 # LaTeX name is never output to .tex files (but needed for the hardcoded
215 Encoding tis620-0 tis620-0 "Thai (TIS 620-0)" TIS620-0 fixed none
218 # A plain utf8 encoding that does not use the inputenc package.
219 # Such an encoding is required for XeTeX.
220 Encoding utf8-plain utf8-plain "Unicode (XeTeX) (utf8)" UTF-8 variable none
223 # Pure 7bit ASCII encoding (partially hardcoded in LyX)
224 Encoding ascii ascii "ASCII" ascii fixed none