mirror of
https://git.lyx.org/repos/lyx.git
synced 2024-12-23 05:25:26 +00:00
UserGuide.lyx: revise the description of the encodings
git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@26587 a592a061-630c-0410-9148-cb99ea01b6c8
This commit is contained in:
Uwe Stöhr
parent
82f1cb7463
commit
ac1598df31
@ -36959,10 +36959,9 @@ Customization
|
||||
\begin_layout Standard
|
||||
If you use the option
|
||||
\family sans
|
||||
use language's default encoding
|
||||
Language Default
|
||||
\family default
|
||||
, LyX determines the encoding of a portion of text from the language of
|
||||
this text.
|
||||
, LyX determines the encoding of a text part from the language of this text.
|
||||
If the document contains text in more than one language you may get more
|
||||
than one encoding in the LaTeX file.
|
||||
If you do not use this option then the complete document will always use
|
||||
@ -37003,7 +37002,7 @@ LyX also supports Unicode output, which is particularly useful if you need
|
||||
so it is not uncommon that a file with lots of Unicode symbols works fine
|
||||
with
|
||||
\family sans
|
||||
use language's default encoding
|
||||
Language Default
|
||||
\family default
|
||||
(when LyX uses it's list of known LaTeX-commands), but does not work with
|
||||
a fixed utf8 encoding (when the list of known LaTeX-commands is not used,
|
||||
@ -37015,13 +37014,21 @@ Here is a list with the important encodings:
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
LaTeX
|
||||
Language
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
default Same as
|
||||
Default
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(no
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
inputenc) Same as
|
||||
\family sans
|
||||
use language's default encoding
|
||||
Language Default
|
||||
\family default
|
||||
, but the LaTeX-package
|
||||
\series bold
|
||||
@ -37038,155 +37045,457 @@ LaTeX-packages ! inputenc
|
||||
\end_inset
|
||||
|
||||
is not used.
|
||||
When using this, you probably need to load some other packages manually
|
||||
When using this, you probably need to load some additional packages manually
|
||||
in the preamble and specify the used encoding for text parts in foreign
|
||||
languages in TeX code.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
armscii8 encoding for Armenian
|
||||
ASCII the ASCII encoding, covers only plain English (7-bit ASCII).
|
||||
LyX converts all other characters into LaTeX commands, which may result
|
||||
in a big file when lots of LaTeX-commands are needed.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
ascii the ASCII encoding, covers only plain English, may result in a big
|
||||
file because lots of LaTeX-commands may be needed
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
cp1250 MS Windows code page for latin2
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
cp1251 MS Windows code page for Cyrillic
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
cp1252 MS Windows code page for latin1
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
cp1255 MS Windows code page for Hebrew, superset of the ISO-8859-8 encoding
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
cp1256 MS Windows code page for Arabic and Farsi
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
cp1257 MS Windows code page for Estonian, Latvian, and Lithuanian, the ISO-8859-
|
||||
13 encoding that is a superset of the ISO-8859-4 encoding
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
iso88595 the ISO-8859-5 encoding, covers Belorussian, Bulgarian, Macedonian,
|
||||
Serbian, and Ukrainian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
iso-8859-7 the ISO-8859-7 encoding, covers Greek
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
8859-8 the ISO-8859-8 encoding, covers Hebrew
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
koi8-r standard Cyrillic especially for Russian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
koi8-u Cyrillic for Ukrainian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
latin1 the ISO-8859-1 encoding, covers the languages Albanian, Catalan,
|
||||
Danish, Dutch, English, Faroese, Finnish, French, Galician, German, Icelandic,
|
||||
Irish, Italian, Norwegian, Portuguese, Spanish, and Swedish; should be
|
||||
replaced by latin9
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
latin2 the ISO-8859-2 encoding, covers Albanian, Croatian, Czech, German,
|
||||
Hungarian, Polish, Romanian, Slovak, and Slovenian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
latin3 the ISO-8859-3 encoding, covers Esperanto, Galician, Maltese, and
|
||||
Turkish
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
latin4 the ISO-8859-4 encoding, covers Estonian, Latvian, and Lithuanian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
latin5 the ISO-8859-9 encoding, covers Turkish, like the ISO-8859-1 encoding
|
||||
where the Icelandic letters are replaced by Turkish ones
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
latin9 the ISO-8859-15 encoding, like the ISO-8859-1 encoding, but with
|
||||
the euro currency sign, the
|
||||
\begin_inset ERT
|
||||
status collapsed
|
||||
|
||||
\begin_layout Plain Layout
|
||||
|
||||
|
||||
\backslash
|
||||
oe
|
||||
\end_layout
|
||||
|
||||
Arabic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
-ligature and some characters used for French and Finnish; latin9 should
|
||||
be the replacement for latin1
|
||||
(CP
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
1256) MS Windows code page for Arabic and Farsi
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
pt154 Cyrillic for Kazakh
|
||||
Arabic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-6) for Arabic and Farsi
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
utf8 Unicode utf8 based on the LaTeX-package
|
||||
Armenian
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ArmSCII8) for Armenian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Baltic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CP
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
1257) MS Windows code page for Estonian, Latvian, and Lithuanian, the same
|
||||
as the ISO-8859-13 encoding
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Baltic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-13) for Estonian, Latvian, and Lithuanian, a superset of the ISO-8859-4
|
||||
encoding
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Baltic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-4) (latin 4) for Estonian, Latvian, and Lithuanian, a subset of the
|
||||
ISO-8859-13 encoding
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Central
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
European
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CP
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
1250) MS Windows code page for ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-2 (latin2)
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Central
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
European
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-2) (latin 2) covers Albanian, Croatian, Czech, German, Hungarian, Polish,
|
||||
Romanian, Slovak, and Slovenian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Chinese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(simplified)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(EUC-CN) for simplified Chinese, used especially on UNIX OSes, since 2001
|
||||
this encoding is officially replaced by the encoding GB18030, as GB18030
|
||||
is not available for LaTeX you should try to use the encoding Unicode
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(utf8)
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Chinese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(simplified)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(GBK) for simplified Chinese, is the same as the Windows code page CP 936
|
||||
except of the Euro currency sign, since 2001 this encoding is officially
|
||||
replaced by the encoding GB18030, as GB18030 is not available for LaTeX
|
||||
you should try to use the encoding Unicode
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(utf8)
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Chinese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(simplified)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(EUC-TW) for traditional Chinese
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Cyrillic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CP
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
1251) MS Windows code page for Cyrillic
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Cyrillic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-5) covers Belorussian, Bulgarian, Macedonian, Serbian, and Ukrainian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Cyrillic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(KOI8-R) standard Cyrillic especially for Russian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Cyrillic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(KOI8-U) Cyrillic for Ukrainian
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Cyrillic
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(pt
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
154) Cyrillic for Kazakh
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Greek
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-7) for Greek
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Hebrew
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CP
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
1255) MS Windows code page for Hebrew, a superset of the ISO-8859-8 encoding
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Hebrew
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-8) for Hebrew
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Japanese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(EUC-JP) EUC-JP encoding for Japanese, uses the LaTeX-package
|
||||
\series bold
|
||||
inputenc
|
||||
CJK
|
||||
\series default
|
||||
|
||||
\begin_inset Index
|
||||
status collapsed
|
||||
|
||||
\begin_layout Plain Layout
|
||||
LaTeX-packages ! inputenc
|
||||
LaTeX-packages ! CJK
|
||||
\end_layout
|
||||
|
||||
\end_inset
|
||||
|
||||
.
|
||||
Currently only a limited range of characters (mainly for Latin scripts)
|
||||
is supported.
|
||||
, when using this, set the document language to
|
||||
\family sans
|
||||
Japanese (CJK)
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
utf8x Unicode utf8 based on the LaTeX package
|
||||
Japanese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(JIS) JIS encoding for Japanese, uses the LaTeX-package
|
||||
\series bold
|
||||
ucs
|
||||
CJK
|
||||
\series default
|
||||
, when using this, set the document language to
|
||||
\family sans
|
||||
Japanese (CJK)
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Japanese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(non-CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(EUC-JP) EUC-JP encoding for Japanese, uses the LaTeX-package
|
||||
\series bold
|
||||
japanese
|
||||
\series default
|
||||
|
||||
\begin_inset Index
|
||||
status collapsed
|
||||
|
||||
\begin_layout Plain Layout
|
||||
LaTeX-packages ! ucs
|
||||
LaTeX-packages ! japanese
|
||||
\end_layout
|
||||
|
||||
\end_inset
|
||||
|
||||
(comprehensive, including Latin, Greek, Cyrillic and CJK scripts).
|
||||
, when using this, set the document language to
|
||||
\family sans
|
||||
Japanese
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
UTF8 Unicode utf8 with the LaTeX-package
|
||||
Japanese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(non-CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(JIS) JIS encoding for Japanese, uses the LaTeX-package
|
||||
\series bold
|
||||
japanese
|
||||
\series default
|
||||
, when using this, set the document language to
|
||||
\family sans
|
||||
Japanese
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Japanese
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(non-CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(SJIS) SJIS encoding for Japanese, uses the LaTeX-package
|
||||
\series bold
|
||||
japanese
|
||||
\series default
|
||||
, when using this, set the document language to
|
||||
\family sans
|
||||
Japanese
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Korean
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(EUC-KR) for Korean
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Southern
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
European
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-3) (latin 3) covers Esperanto, Galician, Maltese, and Turkish
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
South-Eastern
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
European
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-16) (latin 10) covers Albanian, Croatian, Finnish, French, German,
|
||||
Hungarian, Irish Gaelic, Italian, Polish, Romanian, Slovenian, is designed
|
||||
to cover many languages and characters with diacritics
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Thai
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(TIS
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
620-0) for Thai
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Turkish
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-9) (latin 5) for Turkish, is like the ISO-8859-1 encoding where the
|
||||
Icelandic letters are replaced by Turkish ones
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Unicode
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CJK)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(utf8) Unicode utf8 with the LaTeX-package
|
||||
\series bold
|
||||
CJK
|
||||
\series default
|
||||
@ -37204,7 +37513,15 @@ LaTeX-packages ! CJK
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
utf8-plain Unicode utf8 to be used with
|
||||
Unicode
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(XeTeX)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(utf8) Unicode utf8 to be used with
|
||||
\family sans
|
||||
XeTeX
|
||||
\family default
|
||||
@ -37232,6 +37549,112 @@ key "XeTeX"
|
||||
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Unicode
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ucs-extended)
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(utf8x) Unicode utf8 based on the LaTeX package
|
||||
\series bold
|
||||
ucs
|
||||
\series default
|
||||
|
||||
\begin_inset Index
|
||||
status collapsed
|
||||
|
||||
\begin_layout Plain Layout
|
||||
LaTeX-packages ! ucs
|
||||
\end_layout
|
||||
|
||||
\end_inset
|
||||
|
||||
(comprehensive, including Latin, Greek, Cyrillic and CJK scripts).
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Unicode
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(utf8) Unicode utf8 based on the LaTeX-package
|
||||
\series bold
|
||||
inputenc
|
||||
\series default
|
||||
|
||||
\begin_inset Index
|
||||
status collapsed
|
||||
|
||||
\begin_layout Plain Layout
|
||||
LaTeX-packages ! inputenc
|
||||
\end_layout
|
||||
|
||||
\end_inset
|
||||
|
||||
.
|
||||
Currently only a limited range of characters (mainly for Latin scripts)
|
||||
is supported.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Western
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
European
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(CP
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
1252) MS Windows code page for ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-1 (latin1)
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Western
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
European
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-1) (latin 1) covers the languages Albanian, Catalan, Danish, Dutch,
|
||||
English, Faroese, Finnish, French, Galician, German, Icelandic, Irish,
|
||||
Italian, Norwegian, Portuguese, Spanish, and Swedish; better use the ISO-8859-1
|
||||
5 encoding instead
|
||||
\end_layout
|
||||
|
||||
\begin_layout Description
|
||||
Western
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
European
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
(ISO
|
||||
\begin_inset space ~
|
||||
\end_inset
|
||||
|
||||
8859-15) (latin 9) like the ISO-8859-1 encoding, but with the Euro currency
|
||||
sign, the œ-ligature and some characters used for French and Finnish
|
||||
\end_layout
|
||||
|
||||
\begin_layout Subsubsection
|
||||
Numbering & TOC
|
||||
\end_layout
|
||||
|
||||
Loading…
Reference in New Issue
Block a user