\ProvidesLanguage{english}
%\fi
%\ProvidesFile{english.dtx}
[2012/08/20 v3.3p English support from the babel system]
%\iffalse
%% File 'english.dtx'
%% Babel package for LaTeX version 2e
%% Copyright (C) 1989 - 2005
%% by Johannes Braams, TeXniek
%
%% Please report errors to: J.L. Braams
%% babel at braams.cistron.nl
%
% This file is part of the babel system, it provides the source
% code for the English language definition file.
%<*filedriver>
\documentclass{ltxdoc}
\newcommand*\TeXhax{\TeX hax}
\newcommand*\babel{\textsf{babel}}
\newcommand*\langvar{$\langle \mathit lang \rangle$}
\newcommand*\note[1]{}
\newcommand*\Lopt[1]{\textsf{#1}}
\newcommand*\file[1]{\texttt{#1}}
\begin{document}
\DocInput{english.dtx}
\end{document}
%
%\fi
% \GetFileInfo{english.dtx}
%
% \changes{english-2.0a}{1990/04/02}{Added checking of format}
% \changes{english-2.1}{1990/04/24}{Reflect changes in babel 2.1}
% \changes{english-2.1a}{1990/05/14}{Incorporated Nico's comments}
% \changes{english-2.1b}{1990/05/14}{merged \file{USenglish.sty} into
% this file}
% \changes{english-2.1c}{1990/05/22}{fixed typo in definition for
% american language found by Werenfried Spit (nspit@fys.ruu.nl)}
% \changes{english-2.1d}{1990/07/16}{Fixed some typos}
% \changes{english-3.0}{1991/04/23}{Modified for babel 3.0}
% \changes{english-3.0a}{1991/05/29}{Removed bug found by van der Meer}
% \changes{english-3.0c}{1991/07/15}{Renamed \file{babel.sty} in
% \file{babel.com}}
% \changes{english-3.1}{1991/11/05}{Rewrote parts of the code to use
% the new features of babel version 3.1}
% \changes{english-3.3}{1994/02/08}{Update or \LaTeXe}
% \changes{english-3.3c}{1994/06/26}{Removed the use of \cs{filedate}
% and moved the identification after the loading of
% \file{babel.def}}
% \changes{english-3.3g}{1996/07/10}{Replaced \cs{undefined} with
% \cs{@undefined} and \cs{empty} with \cs{@empty} for consistency
% with \LaTeX}
% \changes{english-3.3h}{1996/10/10}{Moved the definition of
% \cs{atcatcode} right to the beginning.}
%
% \section{The English language}
%
% The file \file{\filename}\footnote{The file described in this
% section has version number \fileversion\ and was last revised on
% \filedate.} defines all the language definition macros for the
% English language as well as for the American and Australian
% version of this language. For the Australian version the British
% hyphenation patterns will be used, if available, for the Canadian
% variant the American patterns are selected.
%
% For this language currently no special definitions are needed or
% available.
%
% \StopEventually{}
%
% The macro |\LdfInit| takes care of preventing that this file is
% loaded more than once, checking the category code of the
% \texttt{@} sign, etc.
% \changes{english-3.3h}{1996/11/02}{Now use \cs{LdfInit} to perform
% initial checks}
% \begin{macrocode}
%<*code>
\LdfInit\CurrentOption{date\CurrentOption}
% \end{macrocode}
%
% When this file is read as an option, i.e. by the |\usepackage|
% command, \texttt{english} could be an `unknown' language in which
% case we have to make it known. So we check for the existence of
% |\l@english| to see whether we have to do something here.
%
% \changes{english-3.0}{1991/04/23}{Now use \cs{adddialect} if
% language undefined}
% \changes{english-3.0d}{1991/10/22}{removed use of \cs{@ifundefined}}
% \changes{english-3.3c}{1994/06/26}{Now use \cs{@nopatterns} to
% produce the warning}
% \changes{english-3.3g}{1996/07/10}{Allow british as the name of the
% UK patterns}
% \changes{english-3.3j}{2000/01/21}{Also allow american english
% hyphenation patterns to be used for `english'}
% We allow for the british english patterns to be loaded as either
% `british', or `UKenglish'. When neither of those is
% known we try to define |\l@english| as an alias for |\l@american|
% or |\l@USenglish|.
% \changes{english-3.3k}{2001/02/07}{Added support for canadian}
% \changes{english-3.3n}{2004/06/12}{Added support for australian and
% newzealand}
% \begin{macrocode}
\ifx\l@english\@undefined
\ifx\l@UKenglish\@undefined
\ifx\l@british\@undefined
\ifx\l@american\@undefined
\ifx\l@USenglish\@undefined
\ifx\l@canadian\@undefined
\ifx\l@australian\@undefined
\ifx\l@newzealand\@undefined
\@nopatterns{English}
\adddialect\l@english0
\else
\let\l@english\l@newzealand
\fi
\else
\let\l@english\l@australian
\fi
\else
\let\l@english\l@canadian
\fi
\else
\let\l@english\l@USenglish
\fi
\else
\let\l@english\l@american
\fi
\else
\let\l@english\l@british
\fi
\else
\let\l@english\l@UKenglish
\fi
\fi
% \end{macrocode}
% Because we allow `british' to be used as the babel option we need
% to make sure that it will be recognised by |\selectlanguage|. In
% the code above we have made sure that |\l@english| was defined.
% Now we want to make sure that |\l@british| and |\l@UKenglish| are
% defined as well. When either of them is we make them equal to
% each other, when neither is we fall back to the default,
% |\l@english|.
% \changes{english-3.3o}{2004/06/14}{Make sure that british patterns
% are used if they were loaded}
% \begin{macrocode}
\ifx\l@british\@undefined
\ifx\l@UKenglish\@undefined
\adddialect\l@british\l@english
\adddialect\l@UKenglish\l@english
\else
\let\l@british\l@UKenglish
\fi
\else
\let\l@UKenglish\l@british
\fi
% \end{macrocode}
% `American' is a version of `English' which can have its own
% hyphenation patterns. The default english patterns are in fact
% for american english. We allow for the patterns to be loaded as
% `english' `american' or `USenglish'.
% \changes{english-3.0}{1990/04/23}{Now use \cs{adddialect} for
% american}
% \changes{english-3.0b}{1991/06/06}{Removed \cs{global} definitions}
% \changes{english-3.3d}{1995/02/01}{Only define american as a
% dialect when no separate patterns have been loaded}
% \changes{english-3.3g}{1996/07/10}{Allow USenglish as the name of
% the american patterns}
% \begin{macrocode}
\ifx\l@american\@undefined
\ifx\l@USenglish\@undefined
% \end{macrocode}
% When the patterns are not know as `american' or `USenglish' we
% add a ``dialect''.
% \begin{macrocode}
\adddialect\l@american\l@english
\else
\let\l@american\l@USenglish
\fi
\else
% \end{macrocode}
% Make sure that USenglish is known, even if the patterns were
% loaded as `american'.
% \changes{english-3.3j}{2000/01/21}{Ensure that \cs{l@USenglish} is
% alway defined}
% \changes{english-3.3l}{2001/04/15}{Added missing backslash}
% \begin{macrocode}
\ifx\l@USenglish\@undefined
\let\l@USenglish\l@american
\fi
\fi
% \end{macrocode}
%
% \changes{english-3.3k}{2001/02/07}{Added support for canadian}
% `Canadian' english spelling is a hybrid of British and American
% spelling. Although so far no special `translations' have been
% reported we allow this file to be loaded by the option
% \Lopt{candian} as well.
% \begin{macrocode}
\ifx\l@canadian\@undefined
\adddialect\l@canadian\l@american
\fi
% \end{macrocode}
%
% \changes{english-3.3n}{2004/06/12}{Added support for australian and
% newzealand}
% `Australian' and `New Zealand' english spelling seem to be the
% same as British spelling. Although so far no special
% `translations' have been reported we allow this file to be loaded
% by the options \Lopt{australian} and \Lopt{newzealand} as well.
% \begin{macrocode}
\ifx\l@australian\@undefined
\adddialect\l@australian\l@british
\fi
\ifx\l@newzealand\@undefined
\adddialect\l@newzealand\l@british
\fi
% \end{macrocode}
%
% \begin{macro}{\englishhyphenmins}
% \changes{english-3.3m}{2003/11/17}{Added default for setting of
% hyphenmin parameters}
% This macro is used to store the correct values of the hyphenation
% parameters |\lefthyphenmin| and |\righthyphenmin|.
% \begin{macrocode}
\providehyphenmins{\CurrentOption}{\tw@\thr@@}
% \end{macrocode}
% \end{macro}
%
% The next step consists of defining commands to switch to (and
% from) the English language.
% \begin{macro}{\captionsenglish}
% The macro |\captionsenglish| defines all strings used
% in the four standard document classes provided with \LaTeX.
% \changes{english-3.0b}{1991/06/06}{Removed \cs{global} definitions}
% \changes{english-3.0b}{1991/06/06}{\cs{pagename} should be
% \cs{headpagename}}
% \changes{english-3.1a}{1991/11/11}{added \cs{seename} and
% \cs{alsoname}}
% \changes{english-3.1b}{1992/01/26}{added \cs{prefacename}}
% \changes{english-3.2}{1993/07/15}{\cs{headpagename} should be
% \cs{pagename}}
% \changes{english-3.3e}{1995/07/04}{Added \cs{proofname} for
% AMS-\LaTeX}
% \changes{english-3.3g}{1996/07/10}{Construct control sequence on the
% fly}
% \changes{english-3.3j}{2000/09/19}{Added \cs{glossaryname}}
% \begin{macrocode}
\@namedef{captions\CurrentOption}{%
\def\prefacename{Preface}%
\def\refname{References}%
\def\abstractname{Abstract}%
\def\bibname{Bibliography}%
\def\chaptername{Chapter}%
\def\appendixname{Appendix}%
\def\contentsname{Contents}%
\def\listfigurename{List of Figures}%
\def\listtablename{List of Tables}%
\def\indexname{Index}%
\def\figurename{Figure}%
\def\tablename{Table}%
\def\partname{Part}%
\def\enclname{encl}%
\def\ccname{cc}%
\def\headtoname{To}%
\def\pagename{Page}%
\def\seename{see}%
\def\alsoname{see also}%
\def\proofname{Proof}%
\def\glossaryname{Glossary}%
}
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\dateenglish}
% In order to define |\today| correctly we need to know whether it
% should be `english', `australian', or `american'. We can find
% this out by checking the value of |\CurrentOption|.
% \changes{english-3.3j}{2000/01/21}{Make sure that the value of
% \cs{today} is correct for both options `american' and
% `USenglish'}
% \changes{english-3.3n}{2004/06/12}{Added support for `Australian'
% and `Newzealand'}
% \changes{english-3.3o}{2004/06/14}{Explicitly choose the UK form of
% date}
% \changes{english-3.9a}{2012/08/20}{Warning if `english' is used with
% other options}
% \begin{macrocode}
\def\bbl@tempa{british}
\ifx\CurrentOption\bbl@tempa\def\bbl@tempb{UK}\fi
\def\bbl@tempa{UKenglish}
\ifx\CurrentOption\bbl@tempa\def\bbl@tempb{UK}\fi
\def\bbl@tempa{american}
\ifx\CurrentOption\bbl@tempa\def\bbl@tempb{US}\fi
\def\bbl@tempa{USenglish}
\ifx\CurrentOption\bbl@tempa\def\bbl@tempb{US}\fi
\def\bbl@tempa{canadian}
\ifx\CurrentOption\bbl@tempa\def\bbl@tempb{US}\fi
\def\bbl@tempa{australian}
\ifx\CurrentOption\bbl@tempa\def\bbl@tempb{AU}\fi
\def\bbl@tempa{newzealand}
\ifx\CurrentOption\bbl@tempa\def\bbl@tempb{AU}\fi
\def\bbl@tempa{english}
\ifx\CurrentOption\bbl@tempa
\AtEndOfPackage{\@nameuse{bbl@englishwarning}}
\else
\edef\bbl@englishwarning{%
\let\noexpand\bbl@englishwarning\relax
\noexpand\PackageWarning{Babel}{%
The package option `english' should not be used\noexpand\MessageBreak
with a more specific one (like `\CurrentOption')}}
\fi
% \end{macrocode}
%
% The macro |\dateenglish| redefines the command |\today| to
% produce English dates.
% \changes{english-3.0b}{1991/06/06}{Removed \cs{global} definitions}
% \changes{english-3.3g}{1996/07/10}{Construct control sequence on the
% fly}
% \changes{english-3.3i}{1997/10/01}{Use \cs{edef} to define \cs{today}
% to save memory}
% \changes{english-3.3i}{1998/03/28}{use \cs{def} instead of
% \cs{edef}}
% \begin{macrocode}
\def\bbl@tempa{UK}
\ifx\bbl@tempa\bbl@tempb
\@namedef{date\CurrentOption}{%
\def\today{\ifcase\day\or
1st\or 2nd\or 3rd\or 4th\or 5th\or
6th\or 7th\or 8th\or 9th\or 10th\or
11th\or 12th\or 13th\or 14th\or 15th\or
16th\or 17th\or 18th\or 19th\or 20th\or
21st\or 22nd\or 23rd\or 24th\or 25th\or
26th\or 27th\or 28th\or 29th\or 30th\or
31st\fi~\ifcase\month\or
January\or February\or March\or April\or May\or June\or
July\or August\or September\or October\or November\or
December\fi\space \number\year}}
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\dateaustralian}
% Now, test for `australian' or `american'.
% \changes{english-3.3n}{2004/06/12}{Add australian date}
% \begin{macrocode}
\else
% \end{macrocode}
%
% The macro |\dateaustralian| redefines the command |\today| to
% produce Australian resp.\ New Zealand dates.
% \begin{macrocode}
\def\bbl@tempa{AU}
\ifx\bbl@tempa\bbl@tempb
\@namedef{date\CurrentOption}{%
\def\today{\number\day~\ifcase\month\or
January\or February\or March\or April\or May\or June\or
July\or August\or September\or October\or November\or
December\fi\space \number\year}}
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\dateamerican}
% The macro |\dateamerican| redefines the command |\today| to
% produce American dates.
% \changes{english-3.0b}{1991/06/06}{Removed \cs{global} definitions}
% \changes{english-3.3i}{1997/10/01}{Use \cs{edef} to define
% \cs{today} to save memory}
% \changes{english-3.3i}{1998/03/28}{use \cs{def} instead of
% \cs{edef}}
% \begin{macrocode}
\else
\@namedef{date\CurrentOption}{%
\def\today{\ifcase\month\or
January\or February\or March\or April\or May\or June\or
July\or August\or September\or October\or November\or
December\fi \space\number\day, \number\year}}
\fi
\fi
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\extrasenglish}
% \begin{macro}{\noextrasenglish}
% The macro |\extrasenglish| will perform all the extra definitions
% needed for the English language. The macro |\noextrasenglish| is
% used to cancel the actions of |\extrasenglish|. For the moment
% these macros are empty but they are defined for compatibility
% with the other language definition files.
%
% \changes{english-3.3g}{1996/07/10}{Construct control sequences on
% the fly}
% \begin{macrocode}
\@namedef{extras\CurrentOption}{}
\@namedef{noextras\CurrentOption}{}
% \end{macrocode}
% \end{macro}
% \end{macro}
%
% The macro |\ldf@finish| takes care of looking for a
% configuration file, setting the main language to be switched on
% at |\begin{document}| and resetting the category code of
% \texttt{@} to its original value.
% \changes{english-3.3h}{1996/11/02}{Now use \cs{ldf@finish} to wrap
% up}
% \begin{macrocode}
\ldf@finish\CurrentOption
%
% \end{macrocode}
%
% \Finale
%%
%% \CharacterTable
%% {Upper-case \A\B\C\D\E\F\G\H\I\J\K\L\M\N\O\P\Q\R\S\T\U\V\W\X\Y\Z
%% Lower-case \a\b\c\d\e\f\g\h\i\j\k\l\m\n\o\p\q\r\s\t\u\v\w\x\y\z
%% Digits \0\1\2\3\4\5\6\7\8\9
%% Exclamation \! Double quote \" Hash (number) \#
%% Dollar \$ Percent \% Ampersand \&
%% Acute accent \' Left paren \( Right paren \)
%% Asterisk \* Plus \+ Comma \,
%% Minus \- Point \. Solidus \/
%% Colon \: Semicolon \; Less than \<
%% Equals \= Greater than \> Question mark \?
%% Commercial at \@ Left bracket \[ Backslash \\
%% Right bracket \] Circumflex \^ Underscore \_
%% Grave accent \` Left brace \{ Vertical bar \|
%% Right brace \} Tilde \~}
%%
\endinput
#!/usr/bin/env ruby
# encoding: utf-8
# this file auto-generates tlpsrc files for hyphenation patterns - to be improved
load 'languages.rb'
$package_name="hyph-utf8"
# TODO - make this a bit less hard-coded
$path_tex_generic=File.expand_path("../../../tex/generic")
$path_TL=File.expand_path("../../../../TL")
$path_language_dat="#{$path_TL}/texmf-dist/tex/generic/config"
# hyphen-foo.tlpsrc for TeX Live
$path_tlpsrc="#{$path_TL}/tlpkg/tlpsrc"
$path_txt="#{$path_tex_generic}/#{$package_name}/patterns/txt"
$l = Languages.new
# TODO: should be singleton
languages = $l.list.sort{|a,b| a.name <=> b.name}
language_grouping = {
'english' => ['en-gb', 'en-us'],
'norwegian' => ['nb', 'nn'],
'german' => ['de-1901', 'de-1996', 'de-ch-1901'],
'mongolian' => ['mn-cyrl', 'mn-cyrl-x-lmc'],
'greek' => ['el-monoton', 'el-polyton'],
'ancientgreek' => ['grc', 'grc-x-ibycus'],
'chinese' => ['zh-latn-pinyin'],
'indic' => ['as', 'bn', 'gu', 'hi', 'kn', 'ml', 'mr', 'or', 'pa', 'ta', 'te'],
'serbian' => ['sh-latn', 'sh-cyrl'],
'latin' => ['la', 'la-x-classic', 'la-x-liturgic'],
}
language_used_in_group = Hash.new
language_grouping.each_value do |group|
group.each do |code|
language_used_in_group[code] = true
end
end
# a hash with language name as key and array of languages as the value
language_groups = Hash.new
# single languages first
languages.each do |language|
# temporary remove cyrilic serbian until someone explains what is needed
if language.code == 'sr-cyrl' or language.code == 'en-us' then
# ignore the language
elsif language_used_in_group[language.code] == nil then
language_groups[language.name] = [language]
end
if language.code == 'sh-latn' then
language.code = 'sr-latn'
elsif language.code == 'sh-cyrl' then
language.code = 'sr-cyrl'
end
end
# then groups of languages
language_grouping.each do |name,group|
language_groups[name] = []
group.each do |code|
language_groups[name].push($l[code])
end
end
# languages.each do |language|
# if language.hyphenmin == nil then
# lmin = ''
# rmin = ''
# else
# lmin = language.hyphenmin[0]
# rmin = language.hyphenmin[1]
# end
# puts "#{language.name}: #{lmin} #{rmin}"
# end
#--------#
# TLPSRC #
#--------#
language_groups.sort.each do |language_name,language_list|
files_path_hyph8 = "tex/generic/hyph-utf8"
files_run = []
files_doc = []
files_src = []
$file_tlpsrc = File.open("#{$path_tlpsrc}/hyphen-#{language_name}.tlpsrc", 'w')
puts "generating #{$path_tlpsrc}/hyphen-#{language_name}.tlpsrc"
#$file_tlpsrc.puts "name hyphen-#{language_name}"
$file_tlpsrc.puts "category TLCore"
$file_tlpsrc.puts "depend hyphen-base"
$file_tlpsrc.puts "depend hyph-utf8"
# external dependencies for Russian and Ukrainian (until we implement the new functionality at least)
if language_name == "russian" then
$file_tlpsrc.puts "depend ruhyphen"
elsif language_name == "ukrainian" then
$file_tlpsrc.puts "depend ukrhyph"
elsif language_name == "norwegian" then
files_run.push("#{files_path_hyph8}/patterns/tex/hyph-no.tex")
end
language_list.each do |language|
if language.description_s != nil then
$file_tlpsrc.puts "shortdesc #{language.description_s}."
$file_tlpsrc.puts "longdesc #{language.description_l.join("\nlongdesc ")}"
# if language.version != nil then
# $file_tlpsrc.puts "catalogue-version #{language.version}"
# end
end
name = "name=#{language.name}"
# synonyms
if language.synonyms != nil and language.synonyms.length > 0 then
synonyms=" synonyms=#{language.synonyms.join(',')}"
else
synonyms=""
end
# lefthyphenmin/righthyphenmin
if language.hyphenmin == nil or language.hyphenmin.length == 0 then
lmin = ''
rmin = ''
elsif language.filename_old_patterns == "zerohyph.tex" then
lmin = ''
rmin = ''
else
lmin = language.hyphenmin[0]
rmin = language.hyphenmin[1]
end
hyphenmins = "lefthyphenmin=#{lmin} \\\n\trighthyphenmin=#{rmin}"
# which file to use
file = ""
file_patterns = ""
file_exceptions = ""
if language.use_new_loader then
file = "file=loadhyph-#{language.code}.tex"
files_run.push("#{files_path_hyph8}/loadhyph/loadhyph-#{language.code}.tex")
if language.has_quotes then
files_run.push("#{files_path_hyph8}/patterns/quote/hyph-quote-#{language.code}.tex")
end
if language.code == "mn-cyrl-x-lmc" then
files_run.push("#{files_path_hyph8}/patterns/tex/hyph-#{language.code}.tex")
files_run.push("#{files_path_hyph8}/patterns/ptex/hyph-#{language.code}.#{language.encoding}.tex")
# we skip the mongolian language for luatex files
else
if language.code == "sr-latn" or language.code == "sr-cyrl" then
code = language.code.gsub(/sr/, "sh")
filename_pat = "hyph-sh-latn.pat.txt,hyph-sh-cyrl.pat.txt"
filename_hyp = "hyph-sh-latn.hyp.txt,hyph-sh-cyrl.hyp.txt"
files_run.push("#{files_path_hyph8}/patterns/tex/hyph-#{code}.tex")
files_run.push("#{files_path_hyph8}/patterns/ptex/hyph-#{code}.#{language.encoding}.tex")
# duplicate entries (will be removed later)
files_run.push("#{files_path_hyph8}/patterns/tex/hyph-sr-cyrl.tex")
['chr', 'pat', 'hyp', 'lic'].each do |t|
files_run.push("#{files_path_hyph8}/patterns/txt/hyph-#{code}.#{t}.txt")
# duplicate entries (will be removed later)
files_run.push("#{files_path_hyph8}/patterns/txt/hyph-sr-cyrl.#{t}.txt")
end
else
filename_pat = "hyph-#{language.code}.pat.txt"
filename_hyp = "hyph-#{language.code}.hyp.txt"
files_run.push("#{files_path_hyph8}/patterns/tex/hyph-#{language.code}.tex")
if language.encoding != nil and language.encoding != "ascii" then
files_run.push("#{files_path_hyph8}/patterns/ptex/hyph-#{language.code}.#{language.encoding}.tex")
elsif language.code == "cop" then
files_run.push("#{files_path_hyph8}/patterns/tex-8bit/#{language.filename_old_patterns}")
# files_run.push("#{files_path_hyph8}/patterns/tex-8bit/copthyph.tex")
end
['chr', 'pat', 'hyp', 'lic'].each do |t|
files_run.push("#{files_path_hyph8}/patterns/txt/hyph-#{language.code}.#{t}.txt")
end
# check for existance of patterns and exceptions
if !File::exists?( "#{$path_txt}/#{filename_pat}" ) then
puts "some problem with #{$path_txt}/#{filename_pat}!!!"
end
if !File::exists?( "#{$path_txt}/#{filename_hyp}" ) then
puts "some problem with #{$path_txt}/#{filename_hyp}!!!"
end
end
file_patterns = "file_patterns=#{filename_pat}"
if File::size?( "#{$path_txt}/#{filename_hyp}" ) != nil then
file_exceptions = "file_exceptions=#{filename_hyp}"
# TODO: nasty workaround
elsif language.code == "sr-latn" or language.code == "sr-cyrl" then
file_exceptions = "file_exceptions=#{filename_hyp}"
else
file_exceptions = "file_exceptions="
# puts "> #{filename_hyp} is empty"
end
end
else
file = "file=#{language.filename_old_patterns}"
if language.code == 'ar' or language.code == 'fa' then
file = file + " \\\n\tfile_patterns="
elsif language.code == 'grc-x-ibycus' then
# TODO: fix this
file = file + " \\\n\tluaspecial=\"disabled:8-bit only\""
end
end
$file_tlpsrc.puts "execute AddHyphen \\\n\t#{name}#{synonyms} \\"
$file_tlpsrc.print "\t#{hyphenmins} \\\n\t#{file}"
if file_patterns + file_exceptions != ""
$file_tlpsrc.print " \\\n\t#{file_patterns} \\\n\t#{file_exceptions}"
end
if language.code == "mn-cyrl-x-lmc" then
$file_tlpsrc.print " \\\n\tluaspecial=\"disabled:only for 8bit montex with lmc encoding\""
end
# end-of-line
$file_tlpsrc.puts
# add sources
if ['es', 'eu', 'gl', 'hy', 'mul-ethi', 'tk', 'tr'].include?(language.code) then
files_src.push("source/generic/hyph-utf8/languages/#{language.code}")
end
# add documentation
if ['bg', 'es', 'hu', 'sa'].include?(language.code) then
files_doc.push("doc/generic/hyph-utf8/#{language.code}")
end
end
if language_name != "russian" and language_name != "ukrainian" then
language_list.each do |language|
if language.use_old_patterns and language.filename_old_patterns != "zerohyph.tex" and language.filename_old_patterns != "copthyph.tex" then
files_run.push("tex/generic/hyphen/#{language.filename_old_patterns}")
end
end
end
# documeentation
if language_name == "greek" then
files_doc.push("doc/generic/elhyphen")
elsif language_name == "hungarian" then
files_doc.push("doc/generic/huhyphen")
elsif language_name == "german" then
files_run.push("tex/generic/hyphen/dehyphtex.tex")
files_run.push("tex/generic/hyphen/ghyphen.README")
end
files_doc.sort.each do |f|
$file_tlpsrc.puts "docpattern d texmf-dist/#{f}"
end
files_src.sort.each do |f|
$file_tlpsrc.puts "srcpattern d texmf-dist/#{f}"
end
files_run.sort.uniq.each do |f|
$file_tlpsrc.puts "runpattern f texmf-dist/#{f}"
end
$file_tlpsrc.close
end
#--------------#
# language.dat #
#--------------#
$file_language_dat = File.open("#{$path_language_dat}/language.dat", "w")
language_groups.sort.each do |language_name,language_list|
language_list.each do |language|
if language.use_new_loader then
$file_language_dat.puts "#{language.name}\tloadhyph-#{language.code}.tex"
else
$file_language_dat.puts "#{language.name}\t#{language.filename_old_patterns}"
end
# synonyms
if language.synonyms != nil then
language.synonyms.each do |synonym|
$file_language_dat.puts "=#{synonym}"
end
end
end
end
$file_language_dat.close
#!/usr/bin/env ruby
require File.expand_path(File.join(File.dirname(__FILE__), 'hyph-utf8'))
# this file generates patterns for pTeX out of the plain ones
# use 'gem install unicode' if unicode is missing on your computer
# require 'jcode'
# require 'rubygems'
# require 'unicode'
load 'languages.rb'
$path_root=File.expand_path("../../..")
$path_ptex="#{$path_root}/tex/generic/hyph-utf8/patterns/ptex"
# load encodings
encodings_list = ["ascii", "ec", "qx", "t2a", "lmc", "il2", "il3", "l7x", "t8m", "lth"]
encodings = Hash.new
encodings_list.each do |encoding_name|
encodings[encoding_name] = HyphEncoding.new(encoding_name)
end
$l = Languages.new
# TODO: should be singleton
languages = $l.list.sort{|a,b| a.name <=> b.name}
language_codes = Hash.new
languages.each do |language|
language_codes[language.code] = language.code
end
languages.sort{|x,y| x.code <=> y.code }.each do |language|
encoding = nil
if language.use_new_loader then
if language.encoding == nil or language_codes[language.code] == nil
include_language = false
puts "(skipping #{language.code} # encoding)"
elsif language.encoding == 'ascii'
include_language = false
puts "(skipping #{language.code} # ascii)"
else
include_language = true
encoding = encodings[language.encoding]
end
else
include_language = false
puts "(skipping #{language.code} # loader)"
end
code = language_codes[language.code]
if include_language
puts ">> generating #{code} (#{language.name})"
file_ptex = File.open("#{$path_ptex}/hyph-#{code}.#{language.encoding}.tex", "w")
patterns = language.get_patterns
exceptions = language.get_exceptions
if code == 'nn' or code == 'nb'
patterns = $l['no'].get_patterns
end
characters = patterns.join('').gsub(/[.0-9]/,'').unpack('U*').sort.uniq
if language.encoding != 'ascii' then
patterns = encoding.convert_to_escaped_characters(patterns)
exceptions = encoding.convert_to_escaped_characters(exceptions)
end
file_ptex.puts("% pTeX-friendly hyphenation patterns")
file_ptex.puts("%")
file_ptex.puts("% language: #{language.name} (#{language.code})")
file_ptex.puts("% encoding: #{language.encoding}")
file_ptex.puts("%")
file_ptex.puts("% This file has been auto-generated from hyph-#{language.code}.tex")
file_ptex.puts("% with a script [texmf]/scripts/generic/hyph-utf8/generate-ptex-patterns.rb")
file_ptex.puts("% See the original file for details about author, licence etc.")
file_ptex.puts("%")
file_ptex.puts("\\bgroup")
# setting lccodes for letters
characters.each do |c|
if (c == 0x01FD or c == 0x0301) and language.code == 'la-x-liturgic'
# skip
elsif c >= 128 then
code = encoding.unicode_characters[c].code_enc
file_ptex.puts sprintf("\\lccode\"%02X=\"%02X", code, code)
end
end
# patterns
if patterns.length > 0 then
file_ptex.puts("\\patterns{\n#{patterns.join("\n")}\n}")
end
# exceptions
if exceptions.length > 0 then
file_ptex.puts("\\hyphenation{\n#{exceptions.join("\n")}\n}")
end
file_ptex.puts("\\egroup")
file_ptex.close
end
end
#!/usr/bin/env ruby
# encoding: utf-8
# this file auto-generates loaders for hyphenation patterns - to be improved
load 'languages.rb'
$package_name="hyph-utf8"
# TODO - make this a bit less hard-coded
$path_tex_generic=File.expand_path("../../../tex/generic")
$path_loadhyph="#{$path_tex_generic}/#{$package_name}/loadhyph"
# TODO: should be singleton
languages = Languages.new.list
#text_if_native_utf = "\input pattern-loader.tex\n\\ifNativeUtfEightPatterns"
languages.each do |language|
string_enc = (language.encoding == nil) ? "" : language.encoding.upcase + " "
################
# Header texts #
################
# a message about auto-generation
# TODO: write a more comprehensive one
text_header =
"% filename: loadhyph-#{language.code}.tex
% language: #{language.name}
%
% Loader for hyphenation patterns, generated by
% source/generic/hyph-utf8/generate-pattern-loaders.rb
% See also http://tug.org/tex-hyphen
%
% Copyright 2008-2016 TeX Users Group.
% You may freely use, modify and/or distribute this file.
% (But consider adapting the scripts if you need modifications.)
%
% Once it turns out that more than a simple definition is needed,
% these lines may be moved to a separate file.
%"
text_if_native_utf =
'% Test for pTeX
\\ifx\\kanjiskip\\undefined
% Test for native UTF-8 (which gets only a single argument)
% That\'s Tau (as in Taco or ΤΕΧ, Tau-Epsilon-Chi), a 2-byte UTF-8 character
\\def\\testengine#1#2!{\\def\\secondarg{#2}}\\testengine Τ!\\relax
\\ifx\\secondarg\\empty'
comment_engine_utf8 = "% Unicode-aware engine (such as XeTeX or LuaTeX) only sees a single (2-byte) argument"
comment_engine_8bit = "% 8-bit engine (such as TeX or pdfTeX)"
comment_engine_ptex = "% pTeX"
text_engine_ascii = ["% ASCII patterns - no additional support is needed",
"\\message{ASCII #{language.message}}",
"\\input hyph-#{language.code}.tex"]
text_engine_utf8 = [" #{comment_engine_utf8}",
" \\message{UTF-8 #{language.message}}"]
text_engine_8bit = [" #{comment_engine_8bit}",
" \\message{#{string_enc}#{language.message}}"]
text_engine_ptex = [" #{comment_engine_ptex}",
" \\message{#{string_enc}#{language.message}}"]
text_engine_8bit_no = [" #{comment_engine_8bit}",
" \\message{No #{language.message} - only for Unicode engines}",
" %\\input zerohyph.tex"]
text_engine_ptex_no = [" #{comment_engine_ptex}",
" \\message{No #{language.message} - only for Unicode engines}",
" %\\input zerohyph.tex"]
text_patterns = " \\input hyph-#{language.code}.tex"
text_patterns_ptex = " \\input hyph-#{language.code}.#{language.encoding}.tex"
text_patterns_old = " \\input #{language.filename_old_patterns}"
text_patterns_conv = " \\input conv-utf8-#{language.encoding}.tex"
text_patterns_utf8 = text_patterns
text_patterns_quote = " \\input hyph-quote-#{language.code}.tex"
###########
# lccodes #
###########
lccodes_common = []
if language.has_quotes then
lccodes_common.push("\\lccode`\\'=`\\'")
end
if language.has_dashes then
lccodes_common.push("\\lccode`\\-=`\\-")
end
if ['sh-latn', 'sh-cyrl'].include?(language.code) then
text_patterns_utf8 = [" \\input hyph-sh-latn.tex",
" \\input hyph-sh-cyrl.tex"]
text_engine_utf8 = [" #{comment_engine_utf8}",
" \\message{UTF-8 Serbian hyphenation patterns}",
" % We load both scripts at the same time to simplify usage"]
end
if language.use_new_loader then
if language.code == 'sh-latn' then
filename = "#{$path_loadhyph}/loadhyph-sr-latn.tex"
elsif language.code == 'sh-cyrl' then
filename = "#{$path_loadhyph}/loadhyph-sr-cyrl.tex"
else
filename = "#{$path_loadhyph}/loadhyph-#{language.code}.tex"
end
puts "generating '#{filename}'"
File.open(filename, "w") do |file|
file.puts text_header
file.puts('\begingroup')
if lccodes_common.length > 0 then
file.puts lccodes_common.join("\n")
end
########################################
# GROUP nr. 1 - ONLY USABLE WITH UTF-8 #
########################################
# some special cases first
#
# some languages (sanskrit) are useless in 8-bit engines; we only want to load them for UTF engines
# TODO - maybe consider doing something similar for ibycus
if ['cu', 'sa','as','bn','gu','hi','hy','kn','lo','mul-ethi','ml','mr','or','pa','ta','te'].include?(language.code) then
file.puts(text_if_native_utf)
file.puts(text_engine_utf8)
# lccodes
if language.code == 'mul-ethi' then
file.puts(' % Set \lccode for Ethiopian word space.')
file.puts(' \lccode"1361="1361')
file.puts(' \lccode"1362="1362')
elsif language.code == "cu" then
file.puts(' % fix lccodes for some characters (they were recently included in Unicode)')
file.puts(' \lccode"1C82="1C82 % sharp o in lowercase "uk"')
['1DF6', '1DF7', '1DF8', '1DF9', 'A69E', '1C86', 'A67E', 'FE2E', 'FE2F'].each do |l|
file.puts(" \\lccode\"#{l}=\"#{l}")
end
elsif language.code != 'lo' then
file.puts(' % Set \lccode for ZWNJ and ZWJ.')
file.puts(' \lccode"200C="200C')
file.puts(' \lccode"200D="200D')
if language.code == 'sa' then
file.puts(' % Set \lccode for KANNADA SIGN JIHVAMULIYA and KANNADA SIGN UPADHMANIYA.')
file.puts(' \lccode"0CF1="0CF1')
file.puts(' \lccode"0CF2="0CF2')
end
end
file.puts(text_patterns)
file.puts('\else')
file.puts(text_engine_8bit_no)
file.puts('\fi\else')
file.puts(text_engine_ptex_no)
file.puts('\fi')
#######################
# GROUP nr. 2 - ASCII #
#######################
elsif ['it', 'pms', 'rm'].include?(language.code)
file.puts(text_if_native_utf)
file.puts(text_engine_utf8)
file.puts(text_patterns)
file.puts(text_patterns_quote)
file.puts('\else')
file.puts(text_engine_8bit)
file.puts(text_patterns)
file.puts('\fi\else')
file.puts(text_engine_ptex)
file.puts(text_patterns)
file.puts('\fi')
# for ASCII encoding, we don't load any special support files, but simply load everything
elsif language.encoding == 'ascii' then
file.puts(text_engine_ascii)
####################################
# GROUP nr. 3 - different patterns #
####################################
# when lanugage uses old patterns for 8-bit engines, load two different patterns rather than using the converter
elsif language.use_old_patterns then
file.puts(text_if_native_utf)
file.puts(text_engine_utf8)
# some catcodes for XeTeX
if language.code == 'grc' or language.code.slice(0,2) == 'el' then
file.puts(" \\lccode`'=`'\\lccode`’=`’\\lccode`ʼ=`ʼ\\lccode`᾽=`᾽\\lccode`᾿=`᾿")
end
file.puts(text_patterns)
if language.code == 'uk' then
file.puts(text_patterns_quote)
end
file.puts('\else')
file.puts(text_engine_8bit)
# explain why we are still using the old patterns
if language.use_old_patterns_comment != nil then
file.puts(" % #{language.use_old_patterns_comment}")
else
puts "Missing comment for #{language.name}"
file.puts(' % we still load old patterns for 8-bit TeX')
end
file.puts(text_patterns_old)
file.puts('\fi\else')
file.puts(text_engine_ptex)
# greek, coptic
if language.encoding == nil then
file.puts(text_patterns_old)
else
file.puts(text_patterns_ptex)
end
file.puts('\fi')
#########################
# GROUP nr. 4 - regular #
#########################
else
file.puts(text_if_native_utf)
file.puts(text_engine_utf8)
file.puts(text_patterns_utf8)
if language.has_quotes
file.puts(text_patterns_quote)
end
file.puts('\else')
file.puts(text_engine_8bit)
if ['la-x-liturgic'].include?(language.code) then
file.puts(text_patterns_ptex)
else
file.puts(text_patterns_conv)
file.puts(text_patterns)
end
file.puts('\fi\else')
file.puts(text_engine_ptex)
file.puts(text_patterns_ptex)
file.puts('\fi')
end
#######
# end #
#######
file.puts('\endgroup')
end
end
end
#!/usr/bin/env ruby
require File.expand_path(File.join(File.dirname(__FILE__), 'hyph-utf8'))
$encoding_data_dir = "data/encodings"
# $encodings = ["ec", "qx", "t2a", "lmc", "il2", "il3", "l7x", "t8m", "lth"]
$encodings = ["t8m", "lth"]
$path_root=File.expand_path("../../..")
$output_data_dir = "#{$path_root}/tex/generic/hyph-utf8/conversions"
$encodings.each do |encoding|
# load encoding
e = HyphEncoding.new(encoding)
# open file
file_out = File.open("#{$output_data_dir}#{File::Separator}conv-utf8-#{encoding}.tex", "w")
# copyright notice
file_out.puts "% conv-utf8-#{encoding}.tex"
file_out.puts "%"
file_out.puts "% Conversion from UTF-8 to #{encoding.upcase},"
file_out.puts "% used before loading hyphenation patterns for 8-bit TeX engines."
file_out.puts "%"
file_out.puts "% This file is part of hyph-utf8 package and autogenerated."
file_out.puts "% See http://tug.org/tex-hyphen"
file_out.puts "%"
file_out.puts "% Copyright 2008-2015 TeX Users Group."
file_out.puts "% You may freely use, modify and/or distribute this file."
file_out.puts "% (But consider adapting the scripts if you need modifications.)"
file_out.puts
# macro to get mapping unicode -> font encoding & error message if screwed up
file_out.puts '% macros adapted from ConTeXt MKII; see unic-ini.mkii'
file_out.puts '\def\unicodechar#1{%'
file_out.puts ' \ifcsname unichar@\number#1\endcsname'
file_out.puts ' \csname unichar@\number#1\endcsname'
file_out.puts ' \else'
file_out.puts ' \errmessage{Unicode character [#1] not in encoding.}%'
file_out.puts ' \fi}'
# minimal and maximal lenght of characters in the encoding (until now just 2 & 3)
unicode_characters_array = e.unicode_characters.sort
length_min = unicode_characters_array.first[1].bytes.size
length_max = unicode_characters_array.last[1].bytes.size
# only output the necessary macros for transforming UTF-8 -> Unicode number
if length_min <= 2 and length_max >= 2 then
file_out.puts '\def\utftwouniglyph#1#2%'
file_out.puts ' {\expandafter\unicodechar\expandafter'
file_out.puts ' {\the\numexpr64*(#1-192)+`#2-128\relax}}'
end
if length_min <= 3 and length_max >= 3 then
file_out.puts '\def\utfthreeuniglyph#1#2#3%'
file_out.puts ' {\expandafter\unicodechar\expandafter'
file_out.puts ' {\the\numexpr4096*(#1-224)+64*(`#2-128)+`#3-128\relax}}'
end
if length_min <= 4 and length_max >= 4 then
file_out.puts '\def\utffouruniglyph#1#2#3#4%'
file_out.puts ' {\expandafter\unicodechar\expandafter'
file_out.puts ' {\the\numexpr262144*(#1-240)+4096*(`#2-128)+64*(`#3-128)+`#4-128\relax}}'
end
# macro to store mapping unicode -> font encoding
file_out.puts
file_out.puts '\def\addunichar #1 #2 {\expandafter\def\csname unichar@\number#1\endcsname{#2}}'
file_out.puts
file_out.puts '% \addunichar "unicode_code - ^^font_encoding_code'
# all unicode characters in the encoding
e.unicode_characters.sort.each do |code,c|
file_out.puts sprintf("\\addunichar \"%04X ^^%02x \\lccode\"%02X=\"%02X %% %s - %s",
c.code_uni, c.code_enc, c.code_enc, c.code_enc, [c.code_uni].pack('U'), c.name)
end
file_out.puts
# make all the possible first characters active
# output the definition into file
e.unicode_characters_first_byte.sort.each do |first_byte_code,chars|
byte = first_byte_code.hex
size = chars[0].bytes.size
# 2-byte: 0b11000000 <= byte < 0b11100000
if size == 2 then
str = "two"
# 3-byte: 0b11100000 <= byte < 0b11110000
elsif size == 3 then
str = "three"
# 4-byte: 0b11110000 <= byte < 0b11111000
elsif size == 4 then
str = "four"
end
file_out.puts sprintf("\\catcode\"%02X=\\active \\def^^%02x{\\utf%suniglyph{\"%02X}}", byte, byte, str, byte)
end
file_out.close
end
$encodings = ["ec", "qx", "t2a", "lmc", "il2", "il3", "l7x"]
$encodings.each do |encoding|
# load encoding
e = HyphEncoding.new(encoding)
# open file
file_out = File.open("#{$output_data_dir}#{File::Separator}conv-utf8-#{encoding}.tex", "w")
# copyright notice
file_out.puts "% conv-utf8-#{encoding}.tex"
file_out.puts "%"
file_out.puts "% Conversion from UTF-8 to #{encoding.upcase},"
file_out.puts "% used before loading hyphenation patterns for 8-bit TeX engines."
file_out.puts "%"
file_out.puts "% This file is part of hyph-utf8 package and autogenerated."
file_out.puts "% See http://tug.org/tex-hyphen"
file_out.puts "%"
file_out.puts "% Copyright 2008-2015 TeX Users Group."
file_out.puts "% You may freely use, modify and/or distribute this file."
file_out.puts "% (But consider adapting the scripts if you need modifications.)"
file_out.puts "%"
e.unicode_characters_first_byte.sort.each do |first_byte_code,chars|
# sorting all the second characters alphabetically
chars.sort!{|x,y| x.code_uni <=> y.code_uni }
# make all the possible first characters active
# output the definition into file
file_out.puts sprintf("\\catcode\"%02X=\\active", first_byte_code.hex)
end
file_out.puts "%"
e.unicode_characters_first_byte.sort.each do |first_byte_code,chars|
first_byte_code = first_byte_code.hex
size = chars[0].bytes.size
if size != 2 then
throw "The encoding #{encoding} uses more than two bytes to encode characters"
else
file_out.puts sprintf("\\def^^%02x#1{%", first_byte_code)
string_fi = ""
for i in 1..(chars.size)
uni_character = chars[i-1]
enc_byte = uni_character.code_enc
enc_byte = [ uni_character.code_enc ].pack('c').unpack('H2')
ux_code = sprintf("U+%04X", uni_character.code_uni)
file_out.puts sprintf("\t\\ifx#1^^%02x^^%02x\\else %% %s - U+%04X - %s", uni_character.bytes[1], uni_character.code_enc, [uni_character.code_uni].pack('U'), uni_character.code_uni, uni_character.name)
string_fi = string_fi + "\\fi"
end
# at least three bytes
end
file_out.puts "\t\\errmessage{Hyphenation pattern file corrupted or #{encoding} encoding not supported!}"
file_out.puts string_fi + "}"
end
file_out.puts '%'
file_out.puts '% ensure all the chars above have valid \lccode values'
file_out.puts '%'
e.lowercase_characters.each do |character|
code = [ character.code_enc ].pack("c").unpack("H2").first.upcase
# \lccode"FF="FF
ux_code = sprintf("U+%04X", character.code_uni)
file_out.puts "\\lccode\"#{code}=\"#{code} % #{[character.code_uni].pack('U')} - #{ux_code} - #{character.name}"
end
file_out.puts
file_out.close
end
#!/usr/bin/env ruby
# encoding: utf-8
# this file generates plain patterns (one-per-line) out of TeX source
# use 'gem install unicode' if unicode is missing on your computer
require 'unicode'
load 'languages.rb'
$path_root=File.expand_path("../../..")
$path_plain="#{$path_root}/tex/generic/hyph-utf8/patterns/txt"
$path_quote="#{$path_root}/tex/generic/hyph-utf8/patterns/quote"
$path_TL=File.expand_path("../../../../TL")
$path_language_dat_lua="#{$path_root}/tex/luatex/hyph-utf8/config"
$l = Languages.new
# TODO: should be singleton
languages = $l.list.sort{|a,b| a.name <=> b.name}
# TODO: we should rewrite this
# not using: eo, el
# todo: mn, no!, sa, sh
# codes = ['bg', 'ca', 'cs', 'cy', 'da', 'de-1901', 'de-1996', 'de-ch-1901', 'en-gb', 'en-us', 'es', 'et', 'eu', 'fi', 'fr', 'ga', 'gl', 'hr', 'hsb', 'hu', 'ia', 'id', 'is', 'it', 'kmr', 'la', 'lt', 'lv', 'nl', 'no', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'sr-cyrl', 'sv', 'tr', 'uk']
language_codes = Hash.new
languages.each do |language|
language_codes[language.code] = language.code
end
language_codes['mn-cyrl-x-lmc'] = nil
# language_codes['sh-latn'] = nil
# language_codes['sh-cyrl'] = nil
# language_codes['sr-cyrl'] = nil
# $file_language_dat_lua = File.open("#{$path_language_dat_lua}/language.dat.lua", "w")
# $file_language_dat_lua.puts "return {\n"
languages.sort{|x,y| x.code <=> y.code }.each do |language|
if language.use_new_loader or language.code == 'en-us' then
include_language = true
else
include_language = false
puts "(skipping #{language.code})"
end
code = language_codes[language.code]
if code == nil
include_language = false
end
if code == 'en_US'
include_language = true
end
if include_language
puts "generating #{code}"
$file_pat = File.open("#{$path_plain}/hyph-#{code}.pat.txt", 'w')
$file_hyp = File.open("#{$path_plain}/hyph-#{code}.hyp.txt", 'w')
$file_let = File.open("#{$path_plain}/hyph-#{code}.chr.txt", 'w')
$file_inf = File.open("#{$path_plain}/hyph-#{code}.lic.txt", 'w')
patterns = language.get_patterns
exceptions = language.get_exceptions
patterns_quote = Array.new
if code == 'nn' or code == 'nb'
patterns = ""
patterns = $l['no'].get_patterns
end
characters_indexes = patterns.join('').gsub(/[.0-9]/,'').unpack('U*').sort.uniq
# patterns
patterns.each do |pattern|
$file_pat.puts pattern
if pattern =~ /'/ then
if code != "grc" and code != "el-monoton" and code != "el-polyton" then
pattern_with_quote = pattern.gsub(/'/,"’")
$file_pat.puts pattern_with_quote
patterns_quote.push(pattern_with_quote)
end
end
end
# exceptions
if exceptions != ""
$file_hyp.puts exceptions
end
# letters
characters_indexes.each do |c|
ch = [c].pack('U')
$file_let.puts ch + Unicode.upcase(ch)
if ch == "'" and code != "grc" and code != "el-monoton" and code != "el-polyton" then
$file_let.puts "’’"
end
end
# licence and readme
# $file_inf.puts "#{language.message}\n\n(more info about the licence to be added later)\n\n"
$file_inf.puts language.get_comments_and_licence
$file_pat.close
$file_hyp.close
$file_let.close
$file_inf.close
if patterns_quote.length > 0
f = File.open("#{$path_quote}/hyph-quote-#{code}.tex", 'w')
f.puts "\\bgroup\n\\lccode`\\’=`\\’\n\\patterns{\n#{patterns_quote.join("\n")}\n}\n\\egroup\n"
f.close
end
# $file_language_dat_lua.puts "\t[\"#{language.name}\"]={"
# $file_language_dat_lua.puts "\t\tloader=\"loadhyph-#{language.code}.tex\","
# $file_language_dat_lua.puts "\t\tcode=\"#{code}\","
# if language.hyphenmin == nil or language.hyphenmin.length == 0 then
# lmin = ''
# rmin = ''
# else
# lmin = language.hyphenmin[0]
# rmin = language.hyphenmin[1]
# end
# $file_language_dat_lua.puts "\t\tlefthyphenmin=#{lmin},"
# $file_language_dat_lua.puts "\t\trighthyphenmin=#{rmin},"
# if language.synonyms.length > 0
# $file_language_dat_lua.puts "\t\tsynonyms={\"#{language.synonyms.join('","')}\"},"
# else
# $file_language_dat_lua.puts "\t\tsynonyms={},"
# end
# $file_language_dat_lua.puts "\t},\n"
end
end
# $file_language_dat_lua.puts "}\n"
# $file_language_dat_lua.close
# this is a Unicode character represented in some particular encoding
class UnicodeCharacter
# unicode code
# code in that particular encoding
# character name (like 'eacute')
def initialize(code_uni, code_enc, name)
@code_uni = code_uni
@code_enc = code_enc
@bytes = [code_uni].pack('U').unpack('C*')
@name = name
end
attr_reader :code_uni, :code_enc, :bytes, :name
end
class UnicodeCharacters < Hash
# a hash based on the first character
def add_new_character_first_byte(code_uni, code_enc, name)
first_byte = [code_uni].pack('U').unpack('H2').first
if self[first_byte] == nil then
self[first_byte] = Array.new
end
self[first_byte].push(UnicodeCharacter.new(code_uni, code_enc, name))
end
# a hash based on the whole unicode codepoint
def add_new_character(code_uni, code_enc, name)
self[code_uni] = UnicodeCharacter.new(code_uni, code_enc, name)
end
end
class HyphEncoding
def initialize(encoding_name)
@encoding_name = encoding_name
@unicode_characters_first_byte = UnicodeCharacters.new
@unicode_characters = UnicodeCharacters.new
@lowercase_characters = Array.new
if encoding_name != 'ascii' then
read_data
end
end
def convert_to_escaped_characters(str)
if str.kind_of?(Array) then
str.each_index do |i|
str[i] = convert_string_to_escaped_characters(str[i])
end
elsif str.kind_of?(String) then
str = convert_string_to_escaped_characters(str)
end
return str
end
attr_reader :encoding_name, :unicode_characters, :unicode_characters_first_byte, :lowercase_characters
def convert_string_to_escaped_characters(str)
skip_this_string = false
characters = str.unpack('U*')
new_string = Array.new(characters.length)
characters.each_index do |i|
c = characters[i] # character code on position i
# check if unicode entry with that number exists
uc = @unicode_characters[c]
if uc == nil then
if c < 128 then
new_string[i] = [c].pack('U')
elsif c == 8217 # ’
new_string[i] = "'"
elsif (c == 0x01FD or c == 0x0301) and @encoding_name == 'ec'
skip_this_string = true
new_string[i] = sprintf("[U+%04X]", c)
else
puts sprintf("There must be an error: character U+%04X in string '%s' is not ASCII or %s.", c, str, @encoding_name.upcase)
end
# an unicode character
else
new_string[i] = sprintf("^^%x", uc.code_enc)
end
end
if skip_this_string
new_string.unshift("% ")
end
return new_string.join('')
end
private
def read_data
# fetch the characters
encoding_data_dir = File.expand_path("data/encodings")
filename = "#{encoding_data_dir}/#{@encoding_name}.dat"
if File.exists?(filename) then
File.open(filename).grep(/^0x(\w+)\tU\+(\w+)\t(\d*)\t([_a-zA-Z0-9\.]*)$/) do |line|
# puts line
code_enc = $1.hex
code_uni = $2.hex
if $3.length > 0
type = $3.to_i
else
type = 0
end
name = $4
if type == 1 then
@unicode_characters_first_byte.add_new_character_first_byte(code_uni, code_enc, name)
@unicode_characters.add_new_character(code_uni, code_enc, name)
@lowercase_characters.push(UnicodeCharacter.new(code_uni, code_enc, name))
end
@lowercase_characters.sort!{|x,y| x.code_enc <=> y.code_enc}
end
else
# TODO: throw an error
puts "Invalid encoding name '#{@encoding_name}'."
puts "File '#{filename}' doesn't exist."
end
end
end
generate-converters.rb
======================
INPUT:
- source/generic/hyph-utf8/data/encodings/*.dat
OUTPUT:
- tex/generic/hyph-utf8/conversions/conv-utf8-*.dat
Auto-generates conversions from UTF-8 to some particular encoding.
Needs to be run only in case that a new encoding is added or an old encoding is fixed.
generate-pattern-loaders.rb
===========================
INPUT:
- language.rb with data
OUTPUT:
- tex/generic/hyph-utf8/loadhyph/loadhyph-*.tex
Auto-generates pattern loaders for languages that should be used in TeX Live or other distros.
Needs to be run when a new language is added, a bug needs to be fixed or a strategy is changed.
generate-tl-files.rb
====================
Has been used once for the very first TL script generation.
Out-of-date and not maintaned; will probably be removed.
generate-webpage.rb
===================
Used to generated webpage with language overview.
languages.rb
============
Database with language information used for almost every script.
Needs some clean-up and some updates.
languages/eu/generate_patterns_eu.rb
====================================
Generator for patterns for Basque.
Author: Juan M. Aguirregabiria, adapted by Mojca Miklavec
languages/gl
============
Generator for patterns for Galician.
Author: Javier A. Múgica
languages/tr/generate_patterns_tr.rb
====================================
Generator for patterns for Turkish.
Author: See file, modified by Mojca Miklavec
contributed/make-exhyph.pl
==========================
Imported script for hack related to breaking compound words.
# -*- coding: utf-8 -*-
class Author
def initialize(name,surname,email,contacted1,contacted2)
@name = name
@surname = surname
@email = email
# this mostly means if email has been recently checked
@contacted1 = contacted1
# this means if we made more cooperation with author,
# exchanging patches etc.
@contacted2 = contacted2
end
attr_reader :name, :surname, :email
end
class Language
def initialize(language_hash)
@use_new_loader = language_hash["use_new_loader"]
@use_old_patterns = language_hash["use_old_patterns"]
@use_old_patterns_comment = language_hash["use_old_patterns_comment"]
@filename_old_patterns = language_hash["filename_old_patterns"]
@filename_old_patterns_other = language_hash["filename_old_patterns_other"]
@code = language_hash["code"]
@name = language_hash["name"]
@synonyms = language_hash["synonyms"]
@hyphenmin = language_hash["hyphenmin"]
@encoding = language_hash["encoding"]
@exceptions = language_hash["exceptions"]
@message = language_hash["message"]
@description_s = language_hash["description_s"]
@description_l = language_hash["description_l"]
@version = language_hash["version"]
@licence = language_hash["licence"]
@authors = language_hash["authors"]
@has_quotes = false
@has_dashes = false
if @synonyms==nil then @synonyms = [] end
end
def set_quotes
@has_quotes = true
end
def set_dashes
@has_dashes = true
end
# TODO: simplify this (reduce duplication)
def get_exceptions
if @exceptions1 == nil
filename = "../../../tex/generic/hyph-utf8/patterns/tex/hyph-#{@code}.tex";
lines = IO.readlines(filename, '.').join("")
exceptions = lines.gsub(/%.*/,'');
if (exceptions.index('\hyphenation') != nil)
@exceptions1 = exceptions.gsub(/.*\\hyphenation\s*\{(.*?)\}.*/m,'\1').
gsub(/\s+/m,"\n").
gsub(/^\s*/m,'').
gsub(/\s*$/m,'').
split("\n")
else
@exceptions1 = ""
end
end
return @exceptions1
end
def get_patterns
if @patterns == nil
filename = "../../../tex/generic/hyph-utf8/patterns/tex/hyph-#{@code}.tex"
lines = IO.readlines(filename, '.').join("")
@patterns = lines.gsub(/%.*/,'').
gsub(/.*\\patterns\s*\{(.*?)\}.*/m,'\1').
gsub(/\s+/m,"\n").
gsub(/^\s*/m,'').
gsub(/\s*$/m,'').
split("\n")
if @code == 'eo' then
@patterns = lines.gsub(/%.*/,'').
gsub(/.*\\patterns\s*\{(.*)\}.*/m,'\1').
#
gsub(/\\adj\{(.*?)\}/m,'\1a. \1aj. \1ajn. \1an. \1e.').
gsub(/\\nom\{(.*?)\}/m,'\1a. \1aj. \1ajn. \1an. \1e. \1o. \1oj. \1ojn. \1on.').
gsub(/\\ver\{(.*?)\}/m,'\1as. \1i. \1is. \1os. \1u. \1us.').
#
gsub(/\s+/m,"\n").
gsub(/^\s*/m,'').
gsub(/\s*$/m,'').
split("\n")
end
end
return @patterns
end
def get_comments_and_licence
if @comments_and_licence == nil then
filename = File.expand_path("../../../tex/generic/hyph-utf8/patterns/tex/hyph-#{@code}.tex");
lines = IO.readlines(filename, '.').join("")
@comments_and_licence = lines.
gsub(/(.*)\\patterns.*/m,'\1')
end
return @comments_and_licence
end
# def lc_characters
# if @lc_characters == nil
# lc_characters = Hash.new
# p = self.patterns
# p.each do |pattern|
# end
# end
# return @lc_characters
# end
attr_reader :use_new_loader, :use_old_patterns, :use_old_patterns_comment, :filename_old_patterns
attr_reader :code, :name, :synonyms, :hyphenmin, :encoding, :exceptions, :message
attr_reader :description_s, :description_l, :version
attr_reader :licence, :authors
attr_reader :has_quotes, :has_dashes
# this hack is needed for Serbian
attr_writer :code
end
class Authors < Hash
@@list = []
def initialize
authors = {
#authors = {
"donald_knuth" => ["Donald", "Knuth", nil, false, false],
"peter_heslin" => ["Peter", "Heslin", nil, false, false],
"dimitrios_filippou" => ["Dimitrios", "Filippou", "dimitrios{dot}filippou{at}riotinto{dot}com", true, true],
"claudio_beccari" => ["Claudio", "Beccari","claudio{dot}beccari{at}gmail{dot}com", true, true],
"juan_aguirregabiria" => ["Juan M.", "Aguirregabiria", "juanmari{dot}aguirregabiria{at}ehu.es", true, true],
"igor_marinovic" => ["Igor", "Marinović", "marinowski{at}gmail.com", true, true],
"tilla_fick" => ["Tilla", "Fick", "fick{dot}tilla{at}gmail{dot}com", true, true],
"chris_swanepoel" => ["Chris", "Swanepoel", "cj{at}swanepoel{dot}net", true, true],
"matjaz_vrecko" => ["Matjaž", "VreÄko", "matjaz{at}mg-soft{dot}si", true, true],
"goncal_badenes" => ["Gonçal", "Badenes", "g{dot}badenes{at}ieee.org", false, false],
"pavel_sevecek" => ["Pavel", "Å eveÄek", "pavel{at}lingea{dot}cz", false, false],
# email doesn't work
"jana_chlebikova" => ["Jana", "ChlebÃková", "chlebikj{at}dcs{dot}fmph{dot}uniba{dot}sk", false, false],
"yannis_haralambous" => ["Yannis", "Haralambous", "yannis{dot}haralambous{at}telecom-bretagne{dot}eu", true, false],
"frank_jensen" => ["Frank", "Jensen", "frank{dot}jensen{at}hugin{dot}com", true, true],
"sergei_pokrovsky" => ["Sergei", "Pokrovsky", "sergio{dot}pokrovskij{at}gmail{dot}com", true, true],
"javier_bezos" => ["Javier", "Bezos", "jbezos{at}tex-tipografia{dot}com", true, true],
"een_saar" => ["Enn", "Saar", "saar{at}aai{dot}ee", false, false],
"dejan_muhamedagic" => ["Dejan", "Muhamedagić", "dejan{at}hello-penguin{dot}com", true, true],
"brian_wilson" => ["Brian", "Wilson", "bountonw{at}gmail{dot}com", true, true],
"arthur_reutenauer" => ["Arthur", "Reutenauer", "arthur{dot}reutenauer{at}normalesup{dot}org", true, true],
"mojca_miklavec" => ["Mojca", "Miklavec", "mojca{dot}miklavec{dot}lists{at}gmail{dot}com", true, true],
"santhosh_thottingal" => ["Santhosh", "Thottingal", "santhosh{dot}thottingal{at}gmail{dot}com>", true, true],
# email doesn't work
"yves_codet" => ["Yves", "Codet", "ycodet{at}club-internet{dot}fr", true, true],
"rune_kleveland" => ["Rune", "Kleveland", nil, false, false],
# email doesn't work
"ole_michael_selberg" => ["Ole Michael", "Selberg", "o{dot}m{dot}selberg{at}c2i{dot}net", true, true],
"dorjgotov_batmunkh" => ["Dorjgotov", "Batmunkh", "bataak{at}gmail{dot}com", true, true],
"nazar_annagurban" => ["Nazar", "Annagurban", "nazartm{at}gmail{dot}com", false, false],
"jan_michael_rynning" => ["Jan Michael", "Rynning", nil, false, false],
"eduard_werner" => ["Eduard", "Werner", "edi{dot}werner{at}gmx{dot}de", false, false],
"werner_lemberg" => ["Werner", "Lemberg", "wl{at}gnu{dot}org", true, true],
# email doesn't work
"pedro_j_de_rezende" => ["Pedro J.", "de Rezende", "rezende{at}ddc{dot}unicamp{dot}br", false, false],
"j_joao_dias_almeida" => ["J. Joao", "Dias Almeida", "jj{at}di{dot}uminho{dot}pt"],
# email doesn't work
"piet_tutelaers" => ["Piet", "Tutelaers", "p{dot}t{dot}h{dot}tutelaers{at}tue{dot}nl", false, false],
"vytas_statulevicius" => ["Vytas", "StatuleviÄius", "vytas{at}vtex{dot}nl", false, false],
"sigitas_tolusis" => ["Sigitas", "Tolušis", "sigitas{at}vtex{dot}lt", false, false],
"janis_vilims" => ["Janis", "Vilims", "jvilims{at}apollo{dot}lv", false, false],
"joerg_knappen" => ["Jörg", "Knappen", "jknappen{at}web{dot}de", true, true],
"medeni_shemde" => ["Medeni", "Shemdê", nil, false, false],
"terry_mart" => ["Terry", "Mart", "mart{at}kph{dot}uni-mainz{dot}de", false, false],
# email doesn't work
"jorgen_pind" => ["Jorgen", "Pind", "jorgen{at}lexis{dot}hi{dot}is", false, false],
"marteinn_sverrisson" => ["Marteinn", "Sverrisson", nil, false, false],
# email doesn't work
"kristinn_gylfason" => ["Kristinn", "Gylfason", "kristgy{at}ieee{dot}org", false, false],
# email doesn't work
"kevin_p_scannell" => ["Kevin P.", "Scannell", "scanell{at}slu{dot}edu", false, false],
# email doesn't work
"peter_kleiweg" => ["Peter", "Kleiweg", "p{dot}c{dot}c{dot}kleiweg{at}rug{dot}nl", false, false],
"hanna_kolodziejska" => ["Hanna", "Kołodziejska", nil, false, false],
"boguslaw_jackowski" => ["Bogusław", "Jackowski", nil, true, true],
"marek_rycko" => ["Marek", "Ryćko", nil, false, false],
"vladimir_volovich" => ["Vladimir", "Volovich", nil, true, true], # TODO add e-mail address
"alexander_i_lebedev" => ["Alexander I.", "Lebedev", "swan{at}scon155{dot}phys{dot}msu{dot}su", false, false], # Not sure were 'I' belongs
# first email doesn't work
"maksym_polyakov" => ["Maksym", "Polyakov", "polyama{at}auburn{dot}edu", false, false], # Second e-mail address in ukrhypmp.tex: mpoliak@i.com.ua
"adrian_rezus" => ["Adrian", "Rezus", "adriaan{at}\{sci,cs\}{dot}kun{dot}nl", false, false],
# email doesn't work
"sahak_petrosyan" => ["Sahak", "Petrosyan", "sahak{at}mit{dot}edu", true, true], # I think "true, true" is right. Arthur
"dominik_wujastyk" => ["Dominik", "Wujastyk", "wujastyk{at}gmail{dot}com", false, false],
"graham_toal" => ["Graham", "Toal", nil, false, false],
"donald_e_knuth" => ["Donald E.", "Knuth", nil, false, false], # Don doesn't use e-mail ;-)
"gerard_d_c_kuiken" => ["Gerard D.C.", "Kuiken", nil, false, false],
"pierre_mackay" => ["P. A.", "MacKay", nil, true, true],
"h_turgut_uyar" => ["H. Turgut", "Uyar", "uyar{at}itu{dot}edu{tr}", true, true],
# email doesn't work
"s_ekin_kocabas" => ["S. Ekin", "Kocabas", "kocabas{at}stanford{dot}edu", true, true],
"bence_nagy" => ["Bence", "Nagy", "nagybence{at}tipogral{dot}hu", true, true],
"kauko_saarinen" => ["Kauko", "Saarinen", nil, false, false],
"fred_karlsson" => ["Fred", "Karlsson", nil, false, false],
"rene_bastian" => ["René", "Bastian", nil, false, false], # TODO make contact
"daniel_flipo" => ["Daniel", "Flipo", nil, false, false], # TODO make contact
"bernard_gaulle" => ["Bernard", "Gaulle", nil, false, false], # Deceased...
"theppitak_karoonboonyanan" => ["Theppitak", "Karoonboonyanan", "theppitak{at}gmail{dot}com", true, true],
"levan_shoshiashvili" => ["Levan", "Shoshiashvili", "shoshia{at}hotmail{dot}com", true, true],
# email doesn't work
"javier_mugica" => ["Javier", "Múgica", "javier{at}digi21{dot}eu", true, true],
"georgi_boshnakov" => ["Georgi", "Boshnakov", "georgi{dot}boshnakov{at}manchester{dot}ac{dot}uk", true, true],
"mike_kroutikov" => ["Mike", "Kroutikov", "pgmmpk{at}gmail{dot}com", true, true],
"aleksandr_andreev" => ["Aleksandr", "Andreev", "", true, true],
}
#
authors.each do |a|
author = Author.new(a[1][0], a[1][1], a[1][2], a[1][3], a[1][4])
@@list.push(author)
self[a[0]] = author
end
end
end
# "use_new_loader"
# => true - create a new file and use that one
# => false - use "filename_old_patterns" in language.dat
# "filename_old_patterns"
# => [string] - the name used in language.dat if "use_new_loader" is false
# "eightbitfilename"
# => [string] - if set, load another file for 8-bit engines
# "code"
# => [string] - used in filenames, needs to conform to the standard
# "name"
# => [string] -
# "synonyms" => [],
# "hyphenmin" => [],
# "encoding" => nil,
# "exceptions" => false,
# "message" => nil,
class Languages < Hash
@@list = []
def initialize
languages = [
# --------------------------------------
# languages with no hyphenation patterns
# --------------------------------------
# arabic
{
"code" => "ar",
"name" => "arabic",
"use_new_loader" => false,
"use_old_patterns" => false,
"filename_old_patterns" => "zerohyph.tex",
# "hyphenmin" => [], # not needed
"encoding" => nil,
"exceptions" => false,
"message" => nil,
# TODO
"description_s" => "(No) Arabic hyphenation patterns",
"description_l" => [
#......................................................................#
"Prevent hyphenation in Arabic.",
],
},
# farsi
# =persian
{
"code" => "fa",
"name" => "farsi", "synonyms" => ["persian"],
"use_new_loader" => false,
"use_old_patterns" => false,
"filename_old_patterns" => "zerohyph.tex",
# "hyphenmin" => [], # not needed
"encoding" => nil,
"exceptions" => false,
"message" => nil,
# TODO
"description_s" => "(No) Persian hyphenation patterns",
"description_l" => [
#......................................................................#
"Prevent hyphenation in Persian.",
],
},
# -------------------------------
# special patterns, not converted
# -------------------------------
# ibycus ibyhyph.tex
{
"code" => "grc-x-ibycus",
"name" => "ibycus",
"use_new_loader" => false,
"use_old_patterns" => true,
"filename_old_patterns" => "ibyhyph.tex",
"hyphenmin" => [2,2],
"encoding" => nil,
"exceptions" => false,
"message" => "Ancient Greek hyphenation patterns for Ibycus encoding (v3.0)",
# "authors" => ["peter_heslin"],
"version" => 3.0,
},
# ----------------------------
# languages using old patterns
# ----------------------------
# greek
# =polygreek
{
"code" => "el-polyton",
"name" => "greek", "synonyms" => ["polygreek"],
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Old patterns work in a different way, one-to-one conversion from UTF-8 is not possible.",
"filename_old_patterns" => "grphyph5.tex",
# left/right hyphen min for Greek can be as low as one (1),
# but for aesthetic reasons keep them at 2/2.
# Dimitrios Filippou
"hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => true,
"message" => "Hyphenation patterns for multi-accent (polytonic) Modern Greek",
"version" => "5.0",
"last_modified" => "2008-06-06",
"type" => "rules",
"authors" => ["dimitrios_filippou"],
"licence" => "LPPL",
# "description_s" => "Polytonic Modern Greek hyphenation patterns",
# # #.....................................................................#
# "description_l" => [
# #......................................................................#
# "Hyphenation patterns for Modern Greek in polytonic spelling.",
# "The pattern file used for 8-bit engines is grphyph5.tex that is",
# "not part of hyph-utf8. Patterns in UTF-8 use two code positions for",
# "each of the vowels with acute accent (a.k.a tonos, oxia), e.g.,",
# "U+03AC, U+1F71 for alpha.",
# ],
},
# monogreek
{
"code" => "el-monoton",
"name" => "monogreek",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Old patterns work in a different way, one-to-one conversion from UTF-8 is not possible.",
"filename_old_patterns" => "grmhyph5.tex",
"hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => true,
"message" => "Hyphenation patterns for uni-accent (monotonic) Modern Greek",
"version" => "5.0",
"last_modified" => "2008-06-06",
"type" => "rules",
"authors" => ["dimitrios_filippou"],
"licence" => "LPPL",
# "description_s" => "Monotonic Modern Greek hyphenation patterns",
# "description_l" => [
# #......................................................................#
# "Hyphenation patterns for Modern Greek in monotonic spelling.",
# "The pattern file used for 8-bit engines is grmhyph5.tex, in Babel's LGR encoding,",
# "that is not part of hyph-utf8.",
# "Patterns in UTF-8 use two code positions for each of the vowels with acute accent",
# "(a.k.a tonos, oxia), e.g., U+03AD, U+1F73 for epsilon.",
# ],
"description_s" => "Modern Greek hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Modern Greek in monotonic and polytonic",
"spelling in LGR and UTF-8 encodings. Patterns in UTF-8 use two code",
"positions for each of the vowels with acute accent (a.k.a tonos,",
"oxia), e.g., U+03AC, U+1F71 for alpha.",
],
},
# ancientgreek
{
"code" => "grc",
"name" => "ancientgreek",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Old patterns work in a different way, one-to-one conversion from UTF-8 is not possible.",
"filename_old_patterns" => "grahyph5.tex",
"hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => false,
"message" => "Hyphenation patterns for Ancient Greek",
"version" => "5.0",
"last_modified" => "2016-05-12",
"type" => "rules",
"authors" => ["dimitrios_filippou"],
"licence" => "LPPL",
# "description_s" => "Ancient Greek hyphenation patterns",
# "description_l" => [
# #......................................................................#
# "Hyphenation patterns for Ancient Greek.",
# "The pattern file used for 8-bit engines is grahyph5.tex, in Babel's LGR encoding,",
# "that is not part of hyph-utf8.",
# "Patterns in UTF-8 use two code positions for each of the vowels with acute accent",
# "(a.k.a tonos, oxia), e.g., U+03AE, U+1F75 for eta.",
# ],
"description_s" => "Ancient Greek hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Ancient Greek in LGR and UTF-8 encodings,",
"including support for (obsolete) Ibycus font encoding.",
"Patterns in UTF-8 use two code positions for each of the vowels with",
"acute accent (a.k.a tonos, oxia), e.g., U+03AE, U+1F75 for eta.",
],
},
# coptic
{
"code" => "cop",
"name" => "coptic",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "TODO: automatic conversion could be done, but was too complicated; leave for later.",
"filename_old_patterns" => "copthyph.tex",
"hyphenmin" => [1,1], # polyglossia TODO: no documentation found
"encoding" => nil,
"exceptions" => false,
"message" => "Coptic hyphenation patterns",
"version" => nil,
"last_modified" => "2004-10-03",
"type" => "rules",
"authors" => [ "claudio_beccari" ],
"licence" => "LPPL",
"description_s" => "Coptic hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Coptic in UTF-8 encoding",
"as well as in ASCII-based encoding for 8-bit engines.",
"The latter can only be used with special Coptic fonts (like CBcoptic).",
"The patterns are considered experimental.",
],
},
# german
{
"code" => "de-1901",
"name" => "german",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Kept for the sake of backward compatibility, but newer and better patterns by WL are available.",
"filename_old_patterns" => "dehypht.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "German hyphenation patterns (traditional orthography)",
"version" => "0.40",
"last_modified" => "2014-05-21", # For the active project
"type" => "dictionary",
"authors" => ["werner_lemberg"],
"licence" => "LPPL",
# "description_s" => "German hyphenation patterns in traditional spelling",
# "description_l" => [
# "Hyphenation patterns for German in traditional spelling, in T1/EC and UTF-8 encoding.",
# "Patterns encoded in UTF-8 are provided by a separate package.",
# ],
"description_s" => "German hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for German in T1/EC and UTF-8 encodings,",
"for traditional and reformed spelling, including Swiss German.",
"The package includes the latest patterns from dehyph-exptl",
"(known to TeX under names 'german', 'ngerman' and 'swissgerman'),",
"however 8-bit engines still load old versions of patterns",
"for 'german' and 'ngerman' for backward-compatibility reasons.",
"Swiss German patterns are suitable for Swiss Standard German",
"(Hochdeutsch) not the Alemannic dialects spoken in Switzerland",
"(Schwyzerduetsch).",
"There are no known patterns for written Schwyzerduetsch.",
]
},
# ngerman
{
"code" => "de-1996",
"name" => "ngerman",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "Kept for the sake of backward compatibility, but newer and better patterns by WL are available.",
"filename_old_patterns" => "dehyphn.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "German hyphenation patterns (reformed orthography)",
"version" => "0.40",
"last_modified" => "2014-05-21", # For the active project
"type" => "dictionary",
"authors" => ["werner_lemberg"],
"licence" => "LPPL",
# "description_s" => "German hyphenation patterns in reformed spelling",
# "description_l" => [
# "Hyphenation patterns for German in reformed spelling, in T1/EC and UTF-8 encoding.",
# "Patterns encoded in UTF-8 are provided by a separate package.",
# ],
},
# swissgerman
{
"code" => "de-ch-1901",
"name" => "swissgerman",
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Swiss-German hyphenation patterns (traditional orthography)",
"version" => "0.40",
"last_modified" => "2014-05-21", # For the active project
"type" => "dictionary",
"authors" => ["werner_lemberg"],
"licence" => "LPPL",
# "description_l" => "German hyphenation patterns, traditional spelling in Switzerland.",
# "description_s" => [
# "Hyphenation patterns for German in traditional spelling as used in Switzerland, in T1/EC and UTF-8.",
# "These patterns are suitable for Standard German (Hochdeutsch), not the Alemannic dialects",
# "spoken in Switzerland (Schwyzerdütsch). There are no patterns for written Schwyzerdütsch",
# "we know of.",
# ],
},
# russian
{
"code" => "ru",
"name" => "russian",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "The old system allows choosing patterns and encodings manually. That mechanism needs to be implemented first in this package, so we still fall back on old system.",
"filename_old_patterns" => "ruhyphen.tex",
"hyphenmin" => [2,2],
"encoding" => "t2a",
"exceptions" => false,
"message" => "Russian hyphenation patterns",
"version" => nil,
"last_modified" => "2003-03-10", # Date of the patterns proper, not the support files
"type" => "dictionary",
"authors" => ["alexander_i_lebedev", "werner_lemberg", "vladimir_volovich"],
"licence" => "LPPL",
"description_s" => "Russian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Russian in T2A and UTF-8 encodings.",
"For 8-bit engines, the 'ruhyphen' package provides a number of",
"different pattern sets, as well as different (8-bit) encodings, that",
"can be chosen at format-generation time. The UTF-8 version only",
"provides the default pattern set. A mechanism similar to the one used",
"for 8-bit patterns may be implemented in the future.",
],
},
# ukrainian
{
"code" => "uk",
"name" => "ukrainian",
"use_new_loader" => true,
"use_old_patterns" => true,
"use_old_patterns_comment" => "The old system allows choosing patterns and encodings manually. That mechanism needs to be implemented first in this package, so we still fall back on old system.",
"filename_old_patterns" => "ukrhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "t2a",
"exceptions" => false,
"message" => "Ukrainian hyphenation patterns",
"version" => nil,
"last_modified" => "2001-05-10", # Date of the patterns proper
# "type" => "rules", # TODO: it is not really clear
"authors" => ["maksym_polyakov", "werner_lemberg", "vladimir_volovich"],
"licence" => "LPPL",
"description_s" => "Ukrainian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Ukrainian in T2A and UTF-8 encodings.",
"For 8-bit engines, the 'ukrhyph' package provides a number of",
"different pattern sets, as well as different (8-bit) encodings, that",
"can be chosen at format-generation time. The UTF-8 version only",
"provides the default pattern set. A mechanism similar to the one used",
"for 8-bit patterns may be implemented in the future.",
],
},
# ----------------------------
# languages using new patterns
# ----------------------------
# afrikaans
{
"code" => "af",
"name" => "afrikaans",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => nil,
"hyphenmin" => [1,2], # in babel: 2,2
"encoding" => "ec",
"exceptions" => true,
"message" => "Afrikaans hyphenation patterns",
"version" => "1.0",
"last_modified" => "2013-10-08",
"type" => "dictionary",
"authors" => [ "tilla_fick", "chris_swanepoel" ],
"email" => [ "hyphen{at}rekenaar{dot}net" ],
"licence" => "LPPL",
"description_s" => "Afrikaans hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Afrikaans in T1/EC and UTF-8 encodings.",
"OpenOffice includes older patterns created by a different author,",
"but the patterns packaged with TeX are considered superior in quality.",
# "Word list used to generate patterns with opatgen might be released in future.",
],
},
# catalan
{
"code" => "ca",
"name" => "catalan",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "cahyph.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => true,
"message" => "Catalan hyphenation patterns",
"version" => "1.11",
"last_modified" => "2003-07-15",
"type" => "rules", # not only rules, also patgen, but it is a good approximation
"authors" => [ "goncal_badenes" ],
"licence" => "LPPL",
"description_s" => "Catalan hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Catalan in T1/EC and UTF-8 encodings.",
],
},
# czech
{
"code" => "cs",
"name" => "czech",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "czhyph.tex",
"filename_old_patterns_other" => ["czhyphen.tex","czhyphen.ex"],
# Both Czech and Slovak: \lefthyphenmin=2, \righthyphenmin=3
# Typographical rules allow \righthyphenmin=2 when typesetting in a
# narrow column (newspapers etc.).
# (used to be 2,2)
"hyphenmin" => [2,3],
"encoding" => "ec",
"exceptions" => true,
"message" => "Czech hyphenation patterns (Pavel Sevecek, v3, 1995)",
"version" => "3",
# guessing based on CTAN/macros/cstex/base/csplain.tar.gz:
# 1998-12-17 (patterns)
# 1995-08-23 (exceptions)
# but patterns claim 1995
"last_modified" => "1995", # todo: no date
"type" => "dictionary",
"authors" => [ "pavel_sevecek" ],
"licence" => "GPL",
"description_s" => "Czech hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Czech in T1/EC and UTF-8 encodings.",
"Original patterns 'czhyphen' are still distributed in the 'csplain'",
"package and loaded with ISO Latin 2 encoding (IL2).",
# however hyph-utf8 could also be used for that
],
},
# slovak
{
"code" => "sk",
"name" => "slovak",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "skhyph.tex",
"filename_old_patterns_other" => ["skhyphen.tex","skhyphen.ex"],
# see czech
"hyphenmin" => [2,3],
"encoding" => "ec",
"exceptions" => true,
"message" => "Slovak hyphenation patterns (Jana Chlebikova, 1992)",
"version" => "2",
"last_modified" => "1992-04-24",
"type" => "dictionary",
"authors" => [ "jana_chlebikova" ],
"licence" => "GPL",
"description_s" => "Slovak hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Slovak in T1/EC and UTF-8 encodings.",
"Original patterns 'skhyphen' are still distributed in the 'csplain'",
"package and loaded with ISO Latin 2 encoding (IL2).",
# however hyph-utf8 could also be used for that
],
},
# welsh
{
"code" => "cy",
"name" => "welsh",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "cyhyph.tex",
"hyphenmin" => [2,3],
"encoding" => "ec",
"exceptions" => false,
"message" => "Welsh hyphenation patterns",
"version" => nil,
"last_modified" => "1996",
"type" => "dictionary",
"authors" => [ "yannis_haralambous" ],
"licence" => "LPPL",
"description_s" => "Welsh hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Welsh in T1/EC and UTF-8 encodings.",
],
},
# danish
{
"code" => "da",
"name" => "danish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "dkhyph.tex",
"filename_old_patterns_other" => ["dkcommon.tex", "dkspecial.tex"],
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Danish hyphenation patterns",
"version" => nil,
"last_modified" => "2011-01-11",
"type" => "dictionary",
"authors" => [ "frank_jensen" ],
"licence" => "LPPL",
"description_s" => "Danish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Danish in T1/EC and UTF-8 encodings.",
],
},
# esperanto
{
"code" => "eo",
"name" => "esperanto",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "eohyph.tex",
"hyphenmin" => [2,2],
"encoding" => "il3", # TODO
"exceptions" => false,
"message" => "Esperanto hyphenation patterns",
"version" => nil,
"last_modified" => "1999-08-10",
"type" => "rules",
"authors" => [ "sergei_pokrovsky" ],
"licence" => "LPPL",
"description_s" => "Esperanto hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Esperanto ISO Latin 3 and UTF-8 encodings.",
"Note that TeX distributions don't ship any suitable fonts in Latin 3",
"encoding, so unless you create your own font support or want to use",
"MlTeX, using native Unicode engines is highly recommended.",
# "Hyphenation patterns for Esperanto ISO Latin 3 and UTF-8 encodings.",
# "Note that TeX distributions usually don't ship any suitable fonts in",
# "Latin 3 encoding, so unless you create your own font support or want",
# "to use MlTeX, using native UTF-8 engines is highly recommended.",
],
},
# spanish
# =espanol
{
"code" => "es",
"name" => "spanish", "synonyms" => ["espanol"],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "eshyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Spanish hyphenation patterns",
"version" => "4.7",
"last_modified" => "2015-11-12",
"type" => "dictionary",
"authors" => [ "javier_bezos" ],
"licence" => "MIT/X11",
"description_s" => "Spanish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Spanish in T1/EC and UTF-8 encodings.",
],
},
# basque
{
"code" => "eu",
"name" => "basque",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "bahyph.tex",
"hyphenmin" => [2,2], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Basque hyphenation patterns",
"version" => nil,
"last_modified" => "2008-06-26",
"type" => "rules",
"authors" => [ "juan_aguirregabiria" ],
"licence" => "other-free", # "public-check",
"description_s" => "Basque hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Basque in T1/EC and UTF-8 encodings.",
# "Generating scripts for these rule-based patterns is included in hyph-utf8."
],
},
# french
# =patois
# =francais
{
"code" => "fr",
"name" => "french", "synonyms" => ["patois","francais"],
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "frhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "French hyphenation patterns",
"version" => "2.13",
"last_modified" => "2016-05-12",
"type" => "rules",
"authors" => ["daniel_flipo", "bernard_gaulle", "arthur_reutenauer"],
"email" => ["cesure-l{at}gutenberg{dot}eu{dot}org"],
"licence" => "MIT",
"description_s" => "French hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for French in T1/EC and UTF-8 encodings.",
]
},
# galician
{
"code" => "gl",
"name" => "galician",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "glhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Galician hyphenation patterns",
"version" => "2.4",
"last_modified" => "2010-04-23",
"type" => "rules",
"authors" => ["javier_mugica"],
"licence" => "LPPL", # Status maintained
"description_s" => "Galician hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Galician in T1/EC and UTF-8 encodings.",
# "Generated automatically from the mkpattern utility.",
]
},
# estonian
{
"code" => "et",
"name" => "estonian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "ethyph.tex",
"hyphenmin" => [2,3], # babel
"encoding" => "ec",
"exceptions" => false,
"message" => "Estonian hyphenation patterns",
"version" => nil,
"last_modified" => "2004-04-13",
"type" => "dictionary",
"authors" => [ "een_saar" ],
"licence" => "LPPL|MIT", # Dual MIT-LPPL
"description_s" => "Estonian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Estonian in T1/EC and UTF-8 encodings.",
],
},
# finnish
{
"code" => "fi",
"name" => "finnish",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "fihyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Finnish hyphenation patterns",
"version" => "2.2",
"last_modified" => "1989-03-08",
"type" => "rules",
"authors" => ["kauko_saarinen", "fred_karlsson"],
"licence" => "other-free",
"description_s" => "Finnish hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Finnish in T1/EC and UTF-8 encodings.",
],
},
# croatian
{
"code" => "hr",
"name" => "croatian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "hrhyph.tex",
"hyphenmin" => [2,2],
"encoding" => "ec",
"exceptions" => false,
"message" => "Croatian hyphenation patterns",
"version" => nil,
"last_modified" => "1996-03-19",
"type" => "dictionary",
"authors" => [ "igor_marinovic" ],
"licence" => "LPPL",
"description_s" => "Croatian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Croatian in T1/EC and UTF-8 encodings.",
],
},
# hungarian
{
"code" => "hu",
"name" => "hungarian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "huhyphn.tex",
"hyphenmin" => [2,2], # polyglossia
"encoding" => "ec",
"exceptions" => false,
"message" => "Hungarian hyphenation patterns (v20110815)",
# https://github.com/nagybence/huhyphn/
"version" => "v20110815",
"last_modified" => "2011-08-15", # actually, it is "2009-06-12" or older for contents; we probably want to check/fix this
"type" => "dictionary",
"authors" => ["bence_nagy"],
"licence" => "MPL 1.1/GPL 2.0/LGPL 2.1", # TODO
"description_s" => "Hungarian hyphenation patterns",
"description_l" => [
#......................................................................#
"Hyphenation patterns for Hungarian in T1/EC and UTF-8 encodings.",
# TODO: same comment as for Irish: I'm slightly reluctant to put URL addresses here.
"From https://github.com/nagybence/huhyphn/."
],
},
# armenian
# Sahak Petrosyan