lyx_mirror/autotests/export/latex/languages/en-th_utf8.lyx

461 lines
7.2 KiB
Plaintext
Raw Normal View History

#LyX 2.4 created this file. For more info see https://www.lyx.org/
\lyxformat 573
\begin_document
\begin_header
\save_transient_properties true
\origin unavailable
\textclass article
\use_default_options true
\maintain_unincluded_children false
\language english
\language_package default
\inputencoding utf8
\fontencoding auto
\font_roman "lmodern" "Norasi"
\font_sans "default" "Garuda"
\font_typewriter "default" "Tlwg Mono"
\font_math "auto" "auto"
\font_default_family default
\use_non_tex_fonts false
\font_sc false
\font_osf false
\font_sf_scale 100 100
\font_tt_scale 100 100
\use_microtype false
\use_dash_ligatures true
\graphics default
\default_output_format default
\output_sync 0
\bibtex_command default
\index_command default
\float_placement class
\float_alignment class
\paperfontsize default
\spacing single
\use_hyperref false
\papersize default
\use_geometry false
\use_package amsmath 1
\use_package amssymb 1
\use_package cancel 1
\use_package esint 1
\use_package mathdots 1
\use_package mathtools 1
\use_package mhchem 1
\use_package stackrel 1
\use_package stmaryrd 1
\use_package undertilde 1
\cite_engine basic
\cite_engine_type default
\biblio_style plain
\use_bibtopic false
\use_indices false
\paperorientation portrait
\suppress_date false
\justification true
\use_refstyle 1
\use_minted 0
\index Index
\shortcut idx
\color #008000
\end_index
\secnumdepth 3
\tocdepth 3
\paragraph_separation indent
\paragraph_indentation default
\is_math_indent 0
\math_numbering_side default
\quotes_style english
\dynamic_quotes 0
\papercolumns 1
\papersides 1
\paperpagestyle default
\tablestyle default
\tracking_changes false
\output_changes false
\html_math_output 0
\html_css_as_file 0
\html_be_strict false
\end_header
\begin_body
\begin_layout Subsection*
Test workaround for Thai language
\end_layout
\begin_layout Standard
Up to version 2013/03/31 v1.8, Babels “thai.ldf” changes character categories
and the definitions for up-/dowcasing of letters (catcode, uccode, lccode)
\series bold
globally
\series default
.
As a result, high bit characters come out wrong in the output.
UTF8 encoded characters are not parsed but interpreted as byte (=character)
sequences:
\end_layout
\begin_layout Quotation
\backslash
languagename
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
languagename
\end_layout
\end_inset
\end_layout
\begin_layout Quotation
\backslash
familydefault
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
familydefault
\end_layout
\end_inset
\end_layout
\begin_layout Quotation
\backslash
f@encoding
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
makeatletter
\backslash
f@encoding
\backslash
makeatother
\end_layout
\end_inset
\end_layout
\begin_layout Standard
and the
\emph on
Latin supplement
\emph default
characters are written
\end_layout
\begin_layout Quotation
A0   ¡ ¢ £ ¤ ¥ ¦ § ¨ © ª « ¬ ® ¯
\end_layout
\begin_layout Quotation
B0 ° ± ² ³ ´ µ ¶ · ¸ ¹ º » ¼ ½ ¾ ¿
\end_layout
\begin_layout Quotation
C0 À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï
\end_layout
\begin_layout Quotation
D0 Ð Ñ Ò Ó Ô Õ Ö × Ø Ù Ú Û Ü Ý Þ ß
\end_layout
\begin_layout Quotation
E0 à á â ã ä å æ ç è é ê ë ì í î ï
\end_layout
\begin_layout Quotation
F0 ð ñ ò ó ô õ ö ÷ ø ù ú û ü ý þ ÿ
\end_layout
\begin_layout Itemize
catcode 11 or 12 means, the characters are directly passed to the font and
come out wrong when the T1 font encoding differs from latin9.
\end_layout
\begin_layout Itemize
uc/lccode changes prevent up/downcasing of high-bit characters
\begin_inset Newline newline
\end_inset
(lösen
\begin_inset Formula $→$
\end_inset
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
MakeUppercase{
\end_layout
\end_inset
lösen
\begin_inset ERT
status open
\begin_layout Plain Layout
}
\end_layout
\end_inset
, LÖSEN
\begin_inset Formula $→$
\end_inset
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
MakeLowercase{
\end_layout
\end_inset
LÖSEN
\begin_inset ERT
status open
\begin_layout Plain Layout
}
\end_layout
\end_inset
).
\end_layout
\begin_layout Standard
\lang thai
Setting the text language to Thai:
\end_layout
\begin_layout Quotation
\lang thai
\backslash
languagename
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
languagename
\end_layout
\end_inset
\end_layout
\begin_layout Quotation
\lang thai
\backslash
familydefault
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
familydefault
\end_layout
\end_inset
\end_layout
\begin_layout Quotation
\lang thai
\backslash
f@encoding
\begin_inset ERT
status open
\begin_layout Plain Layout
\backslash
makeatletter
\backslash
f@encoding
\backslash
makeatother
\end_layout
\end_inset
\end_layout
\begin_layout Standard
\lang thai
Non-ASCII characters are mis-represented because the bytes are passed to
the (Thai) font as-is:
\end_layout
\begin_layout Quotation
\lang thai
A0   ¡ ¢ £ ¤ ¥ ¦ § ¨ © ª « ¬ ® ¯
\end_layout
\begin_layout Quotation
\lang thai
B0 ° ± ² ³ ´ µ ¶ · ¸ ¹ º » ¼ ½ ¾ ¿
\end_layout
\begin_layout Quotation
\lang thai
C0 À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï
\end_layout
\begin_layout Quotation
\lang thai
D0
\begin_inset Note Note
status open
\begin_layout Plain Layout
\lang thai
Ð
\end_layout
\end_inset
Ñ Ò Ó Ô Õ Ö × Ø Ù Ú Û Ü Ý
\begin_inset Note Note
status open
\begin_layout Plain Layout
\lang thai
Þ
\end_layout
\end_inset
ß
\end_layout
\begin_layout Quotation
\lang thai
E0 à á â ã ä å æ ç è é ê ë ì í î ï
\end_layout
\begin_layout Quotation
\lang thai
F0
\begin_inset Note Note
status open
\begin_layout Plain Layout
\lang thai
ð
\end_layout
\end_inset
ñ ò ó ô õ ö ÷ ø ù ú û ü ý
\begin_inset Note Note
status open
\begin_layout Plain Layout
\lang thai
þ
\end_layout
\end_inset
ÿ
\end_layout
\begin_layout Standard
Example text in Thai.
Emphasizing works, if
\begin_inset Quotes eld
\end_inset
fonts-tlwg
\begin_inset Quotes erd
\end_inset
is loaded
\series bold
after
\series default
Babel:
\end_layout
\begin_layout Quote
\series bold
\lang thai
ภาษาไทย
\series default
หรือ
\emph on
ภาษาไทยกลาง
\emph default
เป็นภาษาราชการและภาษาประจำชาติของประเทศไทย ภาษาไทยเป็นภาษาในกลุ่มภาษาไท
ซึ่งเป็นกลุ่มย่อยของตระกูลภาษาไท-กะได สันนิษฐานว่า ภาษาในตระกูลนี้มีถิ่นกำเนิดจ
ากทางตอนใต้ของประเทศจีน และนักภาษาศาสตร์บางส่วนเสนอว่า ภาษาไทยน่าจะมีความเชื่อมโ
ยงกับตระกูลภาษาออสโตร-เอเชียติก ตระกูลภาษาออสโตรนีเซียน และตระกูลภาษาจีน-ทิเบต
\end_layout
\end_body
\end_document