hyph-utf8 for classical-latin

git-svn-id: svn://tug.org/texlive/trunk@34520 c570f23f-e606-0410-a88d-b1316a301751

2 files changed, 126 insertions, 30 deletions

diff --git a/Master/texmf-dist/source/generic/hyph-utf8/generate-webpage.rb b/Master/texmf-dist/source/generic/hyph-utf8/generate-webpage.rb
index c2fcbd7f657..490342c3bcc 100644
--- a/Master/texmf-dist/source/generic/hyph-utf8/generate-webpage.rb
+++ b/Master/texmf-dist/source/generic/hyph-utf8/generate-webpage.rb
@@ -10,20 +10,36 @@ $ctan_url = "http://www.ctan.org/tex-archive/language/hyph-utf8/tex/generic/hyph
 # TODO - make this a bit less hard-coded
 $path_tex_generic="../../../tex/generic"
 
+language_default = Language.new({
+	"code"      => "(default)",
+	"name"      => "english", "synonyms" => ["usenglish", "USenglish", "american"],
+	"hyphenmin" => [2,3],
+	"encoding"  => "ascii",
+	"type"      => "dictionary",
+	"authors"   => [ "donald_knuth" ],
+	"licence"   => "",
+})
+
 $l = Languages.new
+# add english to the list
+$l["default"] = language_default
 # TODO: should be singleton
 languages = $l.list.sort{|a,b| a.name <=> b.name}
 
+$a = Authors.new
+
 language_grouping = {
+	'english' => ['default', 'en-gb', 'en-us'],
+	'latin' => ['la', 'la-x-classic'],
 	'norwegian' => ['nb', 'nn'],
 	'german' => ['de-1901', 'de-1996','de-ch-1901'],
-	'mongolian' => ['mn-cyrl', 'mn-cyrl-x-2a'],
+	'mongolian' => ['mn-cyrl', 'mn-cyrl-x-lmc'],
 	'greek' => ['el-monoton', 'el-polyton'],
 	'ancientgreek' => ['grc', 'grc-x-ibycus'],
 	'chinese' => ['zh-latn-pinyin'],
 	# TODO - until someone tells what to do
 	#'serbian' => ['sr-latn', 'sr-cyrl'],
-	'serbian' => ['sh-latn'],
+	'serbian' => ['sh-latn', 'sh-cyrl'],
 }
 
 language_used_in_group = Hash.new
@@ -33,6 +49,9 @@ language_grouping.each_value do |group|
 	end
 end
 
+space_leading = "            "
+space_tr      = "  "
+
 # a hash with language name as key and array of languages as the value
 language_groups = Hash.new
 # single languages first
@@ -40,8 +59,6 @@ languages.each do |language|
 	# temporary remove cyrilic serbian until someone explains what is needed
 	if language.code == 'sr-cyrl' then
 		languages.delete(language)
-	elsif language.code == 'sh-latn' then
-		language.code = 'sr-latn'
 	elsif language_used_in_group[language.code] == nil then
 		language_groups[language.name] = [language]
 	end
@@ -58,12 +75,16 @@ language_groups.sort.each do |language_name,language_list|
 	first_line_printed = false
 	language_list.each do |language|
 		if language != nil then
+			puts "#{space_leading}<tr>"
+
+			line_content = ""
 			if not first_line_printed then
-				puts "<tr>\n\t<td><b>#{language_name.capitalize}</b></td>"
+				line_content = "<b>#{language_name.capitalize}</b>"
 				first_line_printed = true;
 			else
-				puts "<tr>\n\t<td>&nbsp;</td>"
+				line_content = "&nbsp;"
 			end
+			puts "#{space_leading}#{space_tr}<td>#{line_content}</td>"
 	
 			# synonyms
 			if language.synonyms != nil and language.synonyms.length > 0 then
@@ -71,7 +92,7 @@ language_groups.sort.each do |language_name,language_list|
 			else
 				synonyms=""
 			end
-			puts "\t<td>#{language.name}#{synonyms}</td>"
+			puts "#{space_leading}#{space_tr}<td>#{language.name}#{synonyms}</td>"
 	
 	#		if language.use_old_patterns == false then
 			if language.use_new_loader == true then
@@ -82,7 +103,7 @@ language_groups.sort.each do |language_name,language_list|
 				code = language.code
 			end
 			
-			puts "\t<td>#{code}</td>"
+			puts "#{space_leading}#{space_tr}<td>#{code}</td>"
 	
 			# lefthyphenmin/righthyphenmin
 			if language.hyphenmin == nil or language.hyphenmin.length == 0 then
@@ -95,7 +116,7 @@ language_groups.sort.each do |language_name,language_list|
 				lmin = language.hyphenmin[0]
 				rmin = language.hyphenmin[1]
 			end
-			puts "\t<td>(#{lmin},#{rmin})</td>"
+			puts "#{space_leading}#{space_tr}<td>(#{lmin},#{rmin})</td>"
 			# which file to use
 			if language.use_new_loader then
 				file = "loadhyph-#{language.code}.tex"
@@ -108,8 +129,27 @@ language_groups.sort.each do |language_name,language_list|
 			else
 				encoding = language.encoding.upcase
 			end
-			puts "\t<td>#{encoding}</td>"
-			puts "</tr>\n"
+			puts "#{space_leading}#{space_tr}<td>#{encoding}</td>"
+
+			# licence
+			licence = language.licence
+			puts "#{space_leading}#{space_tr}<td>#{licence}</td>"
+
+			authors = []
+			if language.authors != nil then
+				language.authors.each do |a|
+					author = $a[a]
+					if author != nil then
+						authors.push("#{author.name} #{author.surname}")
+					else
+						puts "author is nil!!!"
+					end
+				end
+			end
+			puts "#{space_leading}#{space_tr}<td>#{authors.join('<br/>')}</td>"
+
+			# finish the language definition
+			puts "#{space_leading}</tr>\n"
 		end
 	end
 end
diff --git a/Master/texmf-dist/source/generic/hyph-utf8/languages.rb b/Master/texmf-dist/source/generic/hyph-utf8/languages.rb
index d53bfadd26b..8f9bed23feb 100644
--- a/Master/texmf-dist/source/generic/hyph-utf8/languages.rb
+++ b/Master/texmf-dist/source/generic/hyph-utf8/languages.rb
@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 class Author
-	def intialize(name,surname,email,contacted1,contacted2)
+	def initialize(name,surname,email,contacted1,contacted2)
 		@name       = name
 		@surname    = surname
 		@email      = email
@@ -33,7 +33,10 @@ class Language
 		@description_s = language_hash["description_s"]
 		@description_l = language_hash["description_l"]
 		@version       = language_hash["version"]
-		
+
+		@licence = language_hash["licence"]
+		@authors = language_hash["authors"]
+
 		if @synonyms==nil then @synonyms = [] end
 	end
 
@@ -109,15 +112,21 @@ class Language
 	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
 	# this hack is needed for Serbian
 	attr_writer :code
 end
 
-
-authors = {
+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", "dfilipp{at}hotmail{dot}com", true, true],
-	"claudio_beccari"     => ["Claudio", "Beccari","claudio{dot}beccari{at}polito{dot}it", true, true],
+	"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],
@@ -125,10 +134,11 @@ authors = {
 	"matjaz_vrecko"       => ["Matjaž", "Vrečko", "matjaz{at}mg-soft{dot}si", true, true],
 	"goncal_badenes"      => ["Gonçal", "Badenes", "g{dot}badenes{at}ieee.org", false, false],
 	"pavel_sevecek"       => ["Pavel", "Ševeček", "pavel{at}lingea{dot}cz", false, false],
+	# email doesn't work
 	"jana_chlebikova"     => ["Jana", "Chlebíková", "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 B.", "Pokrovsky", "pok{at}iis{dot}nsk{dot}su", false, false], # not sure where B. belongs
+	"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],
@@ -136,42 +146,53 @@ authors = {
 	"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"],
-	"piet_tutelaers"      => ["Piet", "Tutelaers", "P{dot}T{dot}H{dot}Tutelaers{at}tue{dot}nl", false, false],
+	# email doesn't work
+	"piet_tutelaers"      => ["Piet", "Tutelaers", "p{dot}t{dot}h{dot}tutelaers{at}tue{dot}nl", false, false],
 	"vytas_statulevicius" => ["Vytas", "Statulevičius", "vytas{at}vtex{dot}nl", false, false],
-	"sigitas_tolusis"     => ["Sigitas", "Tolusis", "sigitas{at}vtex{dot}lt", 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", "knappen{at}vkpmzd{dot}kph{dot}uni-mainz{dot}de", false, false], # TODO From id patterns; obviously there must be some more recent address for him
-	"medeni_semde"        => ["Medeni", "Shemdê", nil, 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],
-	"kristinn_gylfason"   => ["Kristinn", "Gylfason", "kristgy{at}ieee{dot}org"],
+	# 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", nil, false, false], # TODO Dominik is quite active on the XeTeX list, make contact with him
+	"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],
@@ -179,9 +200,20 @@ authors = {
 	"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" "thep{at}linux{dot}thai{dot}net", true, true],
+	"theppitak_karoonboonyanan" => ["Theppitak", "Karoonboonyanan", "thep{at}linux{dot}thai{dot}net", 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],
 }
+#
+		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"
@@ -1189,16 +1221,15 @@ class Languages < Hash
 	"name" => "latin",
 	"use_new_loader" => true,
 	"use_old_patterns" => false,
-	"use_old_patterns_comment" => "Old patterns support both EC & OT1 encodings at the same time.",
 	"filename_old_patterns" => "lahyph.tex",
 	"hyphenmin" => [2,2], # babel
 	"encoding" => "ec",
 	"exceptions" => false,
 	"message" => "Latin hyphenation patterns",
 
-	"version"       => "3.2",
-	"last_modified" => "2010-06-01",
-	"type"          => "dictionary",
+	"version"       => "3.2a",
+	"last_modified" => "2014-06-04", # patterns (behaviour) last modified on 2010-06-01
+	"type"          => "rules",
 	"authors"       => [ "claudio_beccari" ],
 	"licence"       => "LPPL",
 	"description_s" => "Latin hyphenation patterns",
@@ -1212,6 +1243,31 @@ class Languages < Hash
 		"those of medieval Latin.",
 	],
 },
+# classiclatin
+{
+	"code" => "la-x-classic",
+	"name" => "classiclatin",
+	"use_new_loader" => true,
+	"use_old_patterns" => false,
+	"filename_old_patterns" => nil,
+	"hyphenmin" => [2,2],
+	"encoding" => "ec",
+	"exceptions" => false,
+	"message" => "Classical Latin hyphenation patterns",
+
+	"version"       => "1.0",
+	"last_modified" => "2014-05-27",
+	"type"          => "rules",
+	"authors"       => [ "claudio_beccari" ],
+	"licence"       => "LPPL",
+	"description_s" => "Classical Latin hyphenation patterns",
+	"description_l" => [
+		#......................................................................#
+		"Hyphenation patterns for the Classical Latin in T1/EC and UTF-8",
+		"encodings. Classical Latin hyphenation patterns are different from",
+		"those of 'plain' Latin, the latter being more adapted to modern Latin.",
+	],
+},
 # lithuanian
 {
 	"code" => "lt",
@@ -1686,7 +1742,7 @@ class Languages < Hash
 	"version"       => "1.7",
 	"last_modified" => "2008-06",
 	"type"          => "pattern",
-	"authors"       => [ "" ],
+	"authors"       => [ "georgi_boshnakov" ],
 	"licence"       => "LPPL",
 	"description_s" => "Bulgarian hyphenation patterns",
 	"description_l" => [