summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/source/generic/hyph-utf8
diff options
context:
space:
mode:
authorMojca Miklavec <mojca.miklavec@gmail.com>2011-06-22 09:20:34 +0000
committerMojca Miklavec <mojca.miklavec@gmail.com>2011-06-22 09:20:34 +0000
commit08668e5eadb0f42ff99bbaf3a0d7fdff3649dfab (patch)
tree8fe3c0a4bb736af248cbd364a1b33663cf853e32 /Master/texmf-dist/source/generic/hyph-utf8
parent3ded90c611331926683e61f74fd37b68eb28089a (diff)
Update hyph-utf8 (SVN #580) and package descriptions.
- complete descriptions for tlpsrc files - updated Hungarian patterns - change language tag for Pinyin (zh-latn -> zh-latn-pinyin) - remove trailing spaces from patterns, change line terminators for Spanish - fix typos in documentation - update unicode module in ruby: different character set for uppercase letters in Greek and German git-svn-id: svn://tug.org/texlive/trunk@23085 c570f23f-e606-0410-a88d-b1316a301751
Diffstat (limited to 'Master/texmf-dist/source/generic/hyph-utf8')
-rw-r--r--Master/texmf-dist/source/generic/hyph-utf8/generate-pattern-loaders.rb4
-rw-r--r--Master/texmf-dist/source/generic/hyph-utf8/generate-tl-files.rb7
-rw-r--r--Master/texmf-dist/source/generic/hyph-utf8/generate-webpage.rb2
-rw-r--r--Master/texmf-dist/source/generic/hyph-utf8/languages.rb729
4 files changed, 629 insertions, 113 deletions
diff --git a/Master/texmf-dist/source/generic/hyph-utf8/generate-pattern-loaders.rb b/Master/texmf-dist/source/generic/hyph-utf8/generate-pattern-loaders.rb
index 12d40429359..590a989cf43 100644
--- a/Master/texmf-dist/source/generic/hyph-utf8/generate-pattern-loaders.rb
+++ b/Master/texmf-dist/source/generic/hyph-utf8/generate-pattern-loaders.rb
@@ -82,7 +82,7 @@ text_patterns_quote = " \\input hyph-quote-#{language.code}.tex"
###########
lccodes_common = []
-if language.code == 'af' or language.code == 'it' or language.code == 'fr' or language.code == 'uk' or language.code == 'zh-latn' then
+if language.code == 'af' or language.code == 'it' or language.code == 'fr' or language.code == 'uk' or language.code == 'zh-latn-pinyin' then
lccodes_common.push("\\lccode`\\'=`\\'")
end
if language.code == 'af' or language.code == 'pt' or language.code == 'tk' or language.code == 'ru' or language.code == 'uk' then
@@ -206,7 +206,7 @@ end
file.puts(text_if_native_utf)
file.puts(text_engine_utf8)
file.puts(text_patterns_utf8)
- if language.code == 'af' or language.code == 'it' or language.code == 'fr' or language.code == 'uk' or language.code == 'zh-latn' then
+ if language.code == 'af' or language.code == 'it' or language.code == 'fr' or language.code == 'uk' or language.code == 'zh-latn-pinyin' then
file.puts(text_patterns_quote)
end
file.puts('\else')
diff --git a/Master/texmf-dist/source/generic/hyph-utf8/generate-tl-files.rb b/Master/texmf-dist/source/generic/hyph-utf8/generate-tl-files.rb
index f3f19863968..a6096297022 100644
--- a/Master/texmf-dist/source/generic/hyph-utf8/generate-tl-files.rb
+++ b/Master/texmf-dist/source/generic/hyph-utf8/generate-tl-files.rb
@@ -26,7 +26,7 @@ language_grouping = {
'mongolian' => ['mn-cyrl', 'mn-cyrl-x-lmc'],
'greek' => ['el-monoton', 'el-polyton'],
'ancientgreek' => ['grc', 'grc-x-ibycus'],
- 'chinese' => ['zh-latn'],
+ 'chinese' => ['zh-latn-pinyin'],
'indic' => ['as', 'bn', 'gu', 'hi', 'kn', 'ml', 'mr', 'or', 'pa', 'ta', 'te'],
'serbian' => ['sh-latn', 'sh-cyrl'],
}
@@ -95,8 +95,11 @@ language_groups.sort.each do |language_name,language_list|
end
language_list.each do |language|
if language.description_s != nil then
- $file_tlpsrc.puts "shortdesc #{language.description_s}"
+ $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}"
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 5086adf728f..c2fcbd7f657 100644
--- a/Master/texmf-dist/source/generic/hyph-utf8/generate-webpage.rb
+++ b/Master/texmf-dist/source/generic/hyph-utf8/generate-webpage.rb
@@ -20,7 +20,7 @@ language_grouping = {
'mongolian' => ['mn-cyrl', 'mn-cyrl-x-2a'],
'greek' => ['el-monoton', 'el-polyton'],
'ancientgreek' => ['grc', 'grc-x-ibycus'],
- 'chinese' => ['zh-latn'],
+ 'chinese' => ['zh-latn-pinyin'],
# TODO - until someone tells what to do
#'serbian' => ['sr-latn', 'sr-cyrl'],
'serbian' => ['sh-latn'],
diff --git a/Master/texmf-dist/source/generic/hyph-utf8/languages.rb b/Master/texmf-dist/source/generic/hyph-utf8/languages.rb
index 4064edb2618..fad3d02665d 100644
--- a/Master/texmf-dist/source/generic/hyph-utf8/languages.rb
+++ b/Master/texmf-dist/source/generic/hyph-utf8/languages.rb
@@ -31,6 +31,7 @@ class Language
@description_s = language_hash["description_s"]
@description_l = language_hash["description_l"]
+ @version = language_hash["version"]
if @synonyms==nil then @synonyms = [] end
end
@@ -106,14 +107,14 @@ 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
+ attr_reader :description_s, :description_l, :version
# this hack is needed for Serbian
attr_writer :code
end
authors = {
- "peter_heslin" => ["Peter", "Heslin", "", 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],
"juan_aguirregabiria" => ["Juan M.", "Aguirregabiria", "juanmari{dot}aguirregabiria{at}ehu.es", true, true],
@@ -139,6 +140,44 @@ authors = {
"ole_michael_selberg" => ["Ole Michael", "Selberg", nil, false, false],
"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],
+ "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],
+ "vytas_statulevicius" => ["Vytas", "Statulevičius", "vytas{at}vtex{dot}nl", false, false],
+ "sigitas_tolusis" => ["Sigitas", "Tolusis", "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],
+ "terry_mart" => ["Terry", "Mart", "mart{at}kph{dot}uni-mainz{dot}de", false, false],
+ "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"],
+ "kevin_p_scannell" => ["Kevin P.", "Scannell", "scanell{at}slu{dot}edu", false, false],
+ "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
+ "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],
+ "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
+ "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],
+ "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...
}
@@ -182,6 +221,7 @@ class Languages < Hash
# TODO
"description_s" => "(No) Arabic hyphenation patterns",
"description_l" => [
+ #......................................................................#
"Prevent hyphenation in Arabic.",
],
},
@@ -201,6 +241,7 @@ class Languages < Hash
# TODO
"description_s" => "(No) Persian hyphenation patterns",
"description_l" => [
+ #......................................................................#
"Prevent hyphenation in Persian.",
],
},
@@ -220,11 +261,12 @@ class Languages < Hash
"message" => "Ancient Greek hyphenation patterns for Ibycus encoding (v3.0)",
# "authors" => ["peter_heslin"],
+ "version" => 3.0,
},
# ----------------------------
# languages using old patterns
# ----------------------------
-# greek xu-grphyph4.tex
+# greek
# =polygreek
{
"code" => "el-polyton",
@@ -236,15 +278,28 @@ class Languages < Hash
# 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], # polyglosia
+ "hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => true,
-# "message" => "Polytonic Greek hyphenation patterns",
"message" => "Hyphenation patterns for multi-accent (polytonic) Modern Greek",
-
- # "authors" => ["dimitrios_filippou"],
-},
-# monogreek xu-grmhyph4.tex
+
+ "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",
@@ -252,13 +307,33 @@ class Languages < Hash
"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], # polyglosia
+ "hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => true,
-# "message" => "Monotonic Greek hyphenation patterns",
"message" => "Hyphenation patterns for uni-accent (monotonic) Modern Greek",
-
- # "authors" => ["dimitrios_filippou"],
+
+ "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
{
@@ -268,21 +343,32 @@ class Languages < Hash
"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], # polyglosia
+ "hyphenmin" => [1,1], # polyglossia
"encoding" => nil,
"exceptions" => false,
"message" => "Hyphenation patterns for Ancient Greek",
"version" => "5.0",
- "last_modified" => "2008-05-27",
+ "last_modified" => "2008-06-06",
"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",
- # TODO: please help me rewrite this
"description_l" => [
- "Hyphenation patterns for Ancient Greek language in UTF-8 encoding",
- "as well as in ASCII-based LGR encoding of babel for 8-bit engines.",
+ #......................................................................#
+ "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
@@ -293,7 +379,7 @@ class Languages < Hash
"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], # polyglosia TODO: no documentation found
+ "hyphenmin" => [1,1], # polyglossia TODO: no documentation found
"encoding" => nil,
"exceptions" => false,
"message" => "Coptic hyphenation patterns",
@@ -302,16 +388,17 @@ class Languages < Hash
"last_modified" => "2004-10-03",
"type" => "rules",
"authors" => [ "claudio_beccari" ],
- "licence" => "LPPL", # TODO: check; catalogue says so
+ "licence" => "LPPL",
"description_s" => "Coptic hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Coptic language in UTF-8 encoding",
+ #......................................................................#
+ "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 xu-dehypht.tex
+# german
{
"code" => "de-1901",
"name" => "german",
@@ -323,8 +410,34 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "German hyphenation patterns (traditional orthography)",
-},
-# ngerman xu-dehyphn.tex
+
+ "version" => nil,
+ "last_modified" => "2011-06-01", # 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",
@@ -336,19 +449,43 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "German hyphenation patterns (reformed orthography)",
+
+ "version" => nil,
+ "last_modified" => "2011-06-01", # 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", # TODO: how is it going to be called
+ "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" => nil,
+ "last_modified" => "2011-06-01", # 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 xu-ruhyphen.tex
+# russian
{
"code" => "ru",
"name" => "russian",
@@ -360,8 +497,24 @@ class Languages < Hash
"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 xu-ukrhyph.tex
+# ukrainian
{
"code" => "uk",
"name" => "ukrainian",
@@ -373,6 +526,22 @@ class Languages < Hash
"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
@@ -397,10 +566,11 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Afrikaans hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Afrikaans language in T1/EC and UTF-8 encoding.",
- "(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.",
+ #......................................................................#
+ "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
@@ -422,7 +592,8 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Catalan hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Catalan language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Catalan in T1/EC and UTF-8 encodings.",
],
},
# czech
@@ -453,9 +624,10 @@ class Languages < Hash
"licence" => "GPL",
"description_s" => "Czech hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Czech language in T1/EC and UTF-8 encoding.",
- "Original patterns 'czhyphen' are still distributed in 'csplain' package",
- "and loaded with ISO Latin 2 encoding (IL2).",
+ #......................................................................#
+ "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
],
},
@@ -480,9 +652,10 @@ class Languages < Hash
"licence" => "GPL",
"description_s" => "Slovak hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Slovak language in T1/EC and UTF-8 encoding.",
- "Original patterns 'skhyphen' are still distributed in 'csplain' package",
- "and loaded with ISO Latin 2 encoding (IL2).",
+ #......................................................................#
+ "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
],
},
@@ -505,7 +678,8 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Welsh hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Welsh language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Welsh in T1/EC and UTF-8 encodings.",
],
},
# danish
@@ -528,7 +702,8 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Danish hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Danish language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Danish in T1/EC and UTF-8 encodings.",
],
},
# esperanto
@@ -550,10 +725,15 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Esperanto hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Esperanto language in UTF-8 and ISO Latin 3 (IL3) encoding.",
- "Note that TeX distributions usually don't ship any suitable fonts in that encoding,",
- "so unless you create your own font support or want to use MlTeX,",
- "using native UTF-8 engines is highly recommended.",
+ #......................................................................#
+ "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
@@ -576,7 +756,8 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Spanish hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Spanish language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Spanish in T1/EC and UTF-8 encodings.",
],
},
# basque
@@ -598,11 +779,12 @@ class Languages < Hash
"licence" => "other-free", # "public-check",
"description_s" => "Basque hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Basque language in T1/EC and UTF-8 encoding.",
- "Generating scripts for these rule-based patterns is included in hyph-utf8."
+ #......................................................................#
+ "Hyphenation patterns for Basque in T1/EC and UTF-8 encodings.",
+ # "Generating scripts for these rule-based patterns is included in hyph-utf8."
],
},
-# french xu-frhyph.tex
+# french
# =patois
# =francais
{
@@ -615,8 +797,21 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "French hyphenation patterns (V2.12, 2002/12/11)",
+
+ "version" => "2.12",
+ "last_modified" => "2002-12-11",
+ "type" => "rules",
+ "authors" => ["rene_bastian", "daniel_flipo", "bernard_gaulle"],
+ # TODO for Arthur: recreate mailing-list
+ # "email" => ["cesure-l{at}gutenberg{dot}eu{dot}org"],
+ "licence" => "other-free", # Knuthian type
+ "description_s" => "French hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for French in T1/EC and UTF-8 encodings.",
+ ]
},
-# galician xu-glhyph.tex
+# galician
{
"code" => "gl",
"name" => "galician",
@@ -627,6 +822,18 @@ class Languages < Hash
"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
{
@@ -647,10 +854,11 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Estonian hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Estonian language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Estonian in T1/EC and UTF-8 encodings.",
],
},
-# finnish fihyph.tex
+# finnish
{
"code" => "fi",
"name" => "finnish",
@@ -661,6 +869,17 @@ class Languages < Hash
"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
{
@@ -681,20 +900,35 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Croatian hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Croatian language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Croatian in T1/EC and UTF-8 encodings.",
],
},
-# hungarian xu-huhyphn.tex
+# hungarian
{
"code" => "hu",
"name" => "hungarian",
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "huhyphn.tex",
- "hyphenmin" => [2,2], # polyglosia
+ "hyphenmin" => [2,2], # polyglossia
"encoding" => "ec",
"exceptions" => false,
- "message" => "Hungarian hyphenation patterns (v20031107)",
+ "message" => "Hungarian hyphenation patterns (v20090612)",
+
+ # https://github.com/nagybence/huhyphn/
+ "version" => nil,
+ "last_modified" => "2009-06-12",
+ "type" => "dictionary",
+ "authors" => ["bence_nagy"],
+ "licence" => "GPL",
+ "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 <sahak at mit dot edu>
@@ -708,8 +942,20 @@ class Languages < Hash
"encoding" => nil,
"exceptions" => false,
"message" => "Armenian hyphenation patterns",
+
+ "version" => nil,
+ "last_modified" => "2010-05",
+ "type" => "rules",
+ "authors" => ["sahak_petrosyan"],
+ "licence" => "LPGL",
+ "description_s" => "Armenian hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Armenian for Unicode engines.",
+ # "Auto-generated from a script included in hyph-utf8.",
+ ],
},
-# interlingua iahyphen.tex
+# interlingua
{
"code" => "ia",
"name" => "interlingua",
@@ -720,8 +966,19 @@ class Languages < Hash
"encoding" => "ascii",
"exceptions" => true,
"message" => "Hyphenation patterns for Interlingua",
+
+ "version" => "0.2c",
+ "last_modified" => "2005-06-28",
+ "type" => "dictionary",
+ "authors" => ["peter_kleiweg"],
+ "licence" => "LPPL", # TODO Status maintained
+ "description_s" => "Interlingua hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Interlingua in ASCII encoding.",
+ ],
},
-# indonesian inhyph.tex
+# indonesian
{
"code" => "id",
"name" => "indonesian",
@@ -732,8 +989,20 @@ class Languages < Hash
"encoding" => "ascii",
"exceptions" => true,
"message" => "Indonesian hyphenation patterns",
+
+ "version" => "1.3",
+ "last_modified" => "1997-09-19",
+ "type" => "rules",
+ "authors" => ["joerg_knappen", "terry_mart"],
+ "licence" => "GPL",
+ "description_s" => "Indonesian hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Indonesian (Bahasa Indonesia) in ASCII",
+ "encoding. They are probably also usable for Malay (Bahasa Melayu).",
+ ],
},
-# icelandic icehyph.tex
+# icelandic
{
"code" => "is",
"name" => "icelandic",
@@ -744,8 +1013,20 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "Icelandic hyphenation patterns",
+
+ "version" => nil,
+ "last_modified" => "2004-03-02",
+ "type" => "dictionary",
+ # TODO: I'm not sure that the last two names are relevant, I don't find the source of Marteinn Sverrisson
+ "authors" => ["jorgen_pind", "marteinn_sverrisson", "kristinn_gylfason"],
+ "licence" => "LPPL",
+ "description_s" => "Icelandic hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Icelandic in T1/EC and UTF-8 encodings.",
+ ],
},
-# irish gahyph.tex
+# irish
{
"code" => "ga",
"name" => "irish",
@@ -756,8 +1037,21 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => true,
"message" => "Irish hyphenation patterns",
+
+ "version" => "1.0",
+ "last_modified" => "2004-01-22",
+ "type" => "dictionary",
+ "authors" => ["kevin_p_scannell"],
+ "licence" => "GPL",
+ "description_s" => "Irish hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Irish (Gaeilge) in T1/EC and UTF-8 encodings.",
+ "Visit http://borel.slu.edu/fleiscin/index.html for more information.",
+ # TODO: I'm slightly reluctant to put URL here
+ ],
},
-# italian ithyph.tex
+# italian
{
"code" => "it",
"name" => "italian",
@@ -768,6 +1062,23 @@ class Languages < Hash
"encoding" => "ascii",
"exceptions" => false,
"message" => "Italian hyphenation patterns",
+
+ "version" => "4.8h",
+ "last_modified" => "2010-05-24",
+ "type" => "rules", # TODO: we might want to check that, but it seems unlikely that patgen was used
+ "authors" => ["claudio_beccari"],
+ "licence" => "LGPL",
+ "description_s" => "Italian hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Italian in ASCII encoding.",
+ # supposed to be ...
+ "Compliant with the Recommendation UNI 6461 on hyphenation",
+ "issued by the Italian Standards Institution",
+ "(Ente Nazionale di Unificazione UNI).",
+ # "Implements Recommendation UNI 6461 issued by the Italian Standards Institution",
+ # "(Ente Nazionale di Unificazione UNI).",
+ ],
},
# kurmanji
{
@@ -780,6 +1091,19 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "Kurmanji hyphenation patterns (v. 1.0 2009/06/29 JKn and MSh)",
+
+ "version" => "1.0",
+ "last_modified" => "2009-06-29",
+ "type" => "dictionary",
+ "authors" => ["joerg_knappen", "medeni_shemde"],
+ "licence" => "LPPL", # Status: maintained!
+ "description_s" => "Kurmanji hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Kurmanji (Northern Kurdish) as spoken in",
+ "Turkey and by the Kurdish diaspora in Europe, in T1/EC and UTF-8",
+ "encodings."
+ ],
},
# latin
{
@@ -801,10 +1125,11 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Latin hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Latin language in T1/EC and UTF-8 encoding,",
+ #......................................................................#
+ "Hyphenation patterns for Latin in T1/EC and UTF-8 encodings,",
"mainly in modern spelling (u when u is needed and v when v is needed),",
"medieval spelling with the ligatures \\ae and \\oe and the (uncial)",
- "lowercase 'v' written as a 'u' is also supported. Apparently",
+ "lowercase 'v' written as a 'u' is also supported. Apparently",
"there is no conflict between the patterns of modern Latin and",
"those of medieval Latin.",
],
@@ -819,6 +1144,20 @@ class Languages < Hash
"encoding" => "l7x",
"exceptions" => false,
"message" => "Lithuanian hyphenation patterns",
+
+ "version" => nil,
+ "last_modified" => "2002-11-20", # 1992-03-04, for the content?
+ "authors" => ["vytas_statulevicius", "yannis_haralambous", "sigitas_tolusis"],
+ # "licence" => "LPPL",
+ "description_s" => "Lithuanian hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Lithuanian in L7X and UTF-8 encodings.",
+ # "Designed for \\lefthyphenmin and \\righthyphenmin set to 2.",
+ "\\lefthyphenmin and \\righthyphenmin have to be at least 2.",
+ # "Changing them to 1 according to grammatical rules from 1997",
+ # "would require to review and maybe rebuild the patterns."
+ ],
},
# latvian
{
@@ -830,8 +1169,19 @@ class Languages < Hash
"encoding" => "l7x",
"exceptions" => false,
"message" => "Latvian hyphenation patterns",
+
+ "version" => "0.3",
+ "last_modified" => "2005-09-14",
+ "type" => "dictionary",
+ "authors" => ["janis_vilims"],
+ "licence" => "LGPL",
+ "description_s" => "Latvian hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Latvian in L7X and UTF-8 encodings.",
+ ],
},
-# dutch nehyph96.tex
+# dutch
{
"code" => "nl",
"name" => "dutch",
@@ -844,8 +1194,23 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => true,
"message" => "Dutch hyphenation patterns",
+
+ "version" => "1.1",
+ "last_modified" => "1996-11",
+ "type" => "dictionary",
+ "authors" => ["piet_tutelaers"],
+ "licence" => "LPPL",
+ "description_s" => "Dutch hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Dutch in T1/EC and UTF-8 encodings.",
+ # "\\lefthyphenmin and \\righthyphenmin must both be > 1.",
+ "These patterns don't handle cases like 'menuutje' > 'menu-tje',",
+ "and don't hyphenate words that have different hyphenations according",
+ "to their meaning."
+ ],
},
-# polish xu-plhyph.tex
+# polish
{
"code" => "pl",
"name" => "polish",
@@ -857,8 +1222,20 @@ class Languages < Hash
"encoding" => "qx",
"exceptions" => true,
"message" => "Polish hyphenation patterns",
+
+ "version" => "3.0a",
+ "last_modified" => "1995-06-17",
+ "type" => "dictionary",
+ "authors" => ["hanna_kolodziejska", "boguslaw_jackowski", "marek_rycko"],
+ "licence" => "public", # TODO Knuthian type
+ "description_s" => "Polish hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Polish in QX and UTF-8 encodings.",
+ "These patterns are also used by Polish TeX formats MeX and LaMeX.",
+ ],
},
-# portuguese pthyph.tex
+# portuguese
# =portuges
{
"code" => "pt",
@@ -870,10 +1247,21 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => true,
"message" => "Portuguese hyphenation patterns",
+
+ "version" => "1.0",
+ "last_modified" => "1996-07-21",
+ "type" => "rules", # TODO: we could create a generating script
+ "authors" => ["pedro_j_de_rezende", "j_joao_dias_almeida"],
+ "licence" => "LPPL",
+ "description_s" => "Portuguese hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Portuguese in T1/EC and UTF-8 encodings.",
+ ],
},
-# pinyin xu-pyhyph.tex
+# pinyin
{
- "code" => "zh-latn",
+ "code" => "zh-latn-pinyin",
"name" => "pinyin",
"use_new_loader" => true,
"use_old_patterns" => false,
@@ -882,8 +1270,20 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "Hyphenation patterns for unaccented pinyin syllables (CJK 4.8.0)",
+
+ "version" => "4.8.0",
+ "last_modified" => "2008-05-22",
+ "type" => "rules", # TODO: we could create a generating script
+ "authors" => ["werner_lemberg"],
+ "licence" => "GPL",
+ "description_s" => "Chinese pinyin hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for unaccented transliterated Mandarin Chinese",
+ "(pinyin) in T1/EC and UTF-8 encodings.",
+ ],
},
-# romanian xu-rohyphen.tex
+# romanian
{
"code" => "ro",
"name" => "romanian",
@@ -894,6 +1294,20 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "Romanian hyphenation patterns", # : `rohyphen' 1.1 <29.10.1996>
+
+ "version" => "1.1R",
+ "last_modified" => "1996-11-07",
+ "type" => "dictionary",
+ "authors" => ["adrian_rezus"],
+ "description_s" => "Romanian hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Romanian in T1/EC and UTF-8 encodings.",
+ "The UTF-8 patterns use U+0219 for the character 's with comma accent'",
+ "and U+021B for 't with comma accent', but we may consider using U+015F",
+ "and U+0163 as well in the future.",
+ # "Generated by PatGen2-output hyphen-level 9.",
+ ],
},
# slovenian
# =slovene
@@ -915,10 +1329,11 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Slovenian hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Slovenian language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Slovenian in T1/EC and UTF-8 encodings.",
],
},
-# uppersorbian xu-sorhyph.tex
+# uppersorbian
{
"code" => "hsb",
"name" => "uppersorbian",
@@ -931,8 +1346,19 @@ class Languages < Hash
"message" => "Upper Sorbian hyphenation patterns (E. Werner)",
# \message{Hyphenation patterns for Upper Sorbian, E. Werner}
# \message{Completely new revision 1997, March 22}
+
+ "version" => nil,
+ "last_modified" => "1997-03-22",
+ "authors" => ["eduard_werner"],
+ "type" => "dictionary",
+ "licence" => "LPPL",
+ "description_s" => "Upper Sorbian hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Upper Sorbian in T1/EC and UTF-8 encodings.",
+ ],
},
-# swedish svhyph.tex
+# swedish
{
"code" => "sv",
"name" => "swedish",
@@ -943,6 +1369,18 @@ class Languages < Hash
"encoding" => "ec",
"exceptions" => false,
"message" => "Swedish hyphenation patterns (Jan Michael Rynning, 1994-03-03)",
+
+ # "version" => "1994-03-03", # that is what author used in message
+ "version" => nil,
+ "last_modified" => "1994-03-03",
+ "type" => "dictionary",
+ "authors" => ["jan_michael_rynning"],
+ "licence" => "LPPL",
+ "description_s" => "Swedish hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Swedish in T1/EC and UTF-8 encodings.",
+ ],
},
# turkmen
{
@@ -958,12 +1396,13 @@ class Languages < Hash
"version" => "0.1",
"last_modified" => "2010-03-16",
- "type" => "rules",
+ "type" => "dictionary",
"authors" => [ "nazar_annagurban" ],
"licence" => "public",
"description_s" => "Turkmen hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Turkmen language in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Turkmen in T1/EC and UTF-8 encodings.",
],
},
# turkish
@@ -973,12 +1412,33 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"filename_old_patterns" => "tkhyph.tex",
- "hyphenmin" => [2,2], # polyglosia
+ "hyphenmin" => [2,2], # polyglossia
"encoding" => "ec",
"exceptions" => false,
"message" => "Turkish hyphenation patterns",
+
+ "version" => nil,
+ "last_modified" => "2008-06-28",
+ "type" => "rules",
+ "authors" => ["pierre_mackay", "h_turgut_uyar", "s_ekin_kocabas", "mojca_miklavec"],
+ "licence" => "public-ask", # TODO
+ "description_s" => "Turkish hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for Turkish in T1/EC and UTF-8 encodings.",
+ # "Auto-generated from a script included in the distribution.",
+ "The patterns for Turkish were first produced for the Ottoman Texts",
+ "Project in 1987 and were suitable for both Modern Turkish and Ottoman",
+ "Turkish in Latin script, however the required character set didn't fit",
+ "into EC encoding, so support for Ottoman Turkish had to be dropped to",
+ "keep compatibility with 8-bit engines.",
+ ]
},
-# ukenglish ukhyphen.tex
+
+
+
+
+# ukenglish
{
"code" => "en-gb",
"name" => "ukenglish", "synonyms" => ["british", "UKenglish"],
@@ -989,8 +1449,31 @@ class Languages < Hash
"encoding" => "ascii",
"exceptions" => true,
"message" => "Hyphenation patterns for British English",
+
+ "version" => "1.0a", # FIXME a much older comment says 2.0?
+ "last_modified" => "2005-10-18",
+ "type" => "dictionary",
+ "authors" => ["dominik_wujastyk", "graham_toal"],
+ "licence" => "other-free", # TODO Knuth-like
+ # (This will be uncommented during reimplementation)
+ # "description_s" => "British English hyphenation patterns",
+ # "description_l" => [
+ # "Hyphenation patterns for British English in ASCII encoding.",
+ # ],
+
+ "description_s" => "English hyphenation patterns",
+ "description_l" => [
+ #......................................................................#
+ "Additional hyphenation patterns for American and British",
+ "English in ASCII encoding. The American English patterns",
+ "(usenglishmax) greatly extend the standard patterns from Knuth",
+ "to find many additional hyphenation points. British English",
+ "hyphenation is completely different from US English, so has its",
+ "own set of patterns.",
+ ],
},
-# US english
+# (US english)
+# usenglishmax
{
"code" => "en-us",
"name" => "usenglishmax",
@@ -1001,6 +1484,17 @@ class Languages < Hash
"encoding" => "ascii",
"exceptions" => true,
"message" => "Hyphenation patterns for American English",
+
+ "version" => nil,
+ "last_modified" => "1990-03-01", # 8-bit file also has version 2005-05-30.
+ "type" => "dictionary",
+ "authors" => ["donald_e_knuth", "gerard_d_c_kuiken"],
+ "licence" => "other-free",
+ # (This will be uncommented during reimplementation)
+ # "description_s" => "American English hyphenation patterns",
+ # "description_l" => [
+ # "Hyphenation patterns for American English in ASCII encoding.",
+ # ],
},
# US english
# {
@@ -1024,7 +1518,7 @@ class Languages < Hash
"filename_old_patterns" => "shhyphl.tex",
# It is allowed to leave one character at the end of the row.
# However, if you think that it is graphicaly not very
- # pleasent these patterns will work well with \lefthyphenmin=2.
+ # pleasant these patterns will work well with \lefthyphenmin=2.
# \lefthyphenmin=1 \righthyphenmin=2
"hyphenmin" => [2,2],
"encoding" => "ec",
@@ -1040,10 +1534,11 @@ class Languages < Hash
# for both scripts
"description_s" => "Serbian hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Serbian language in UTF-8 and 8-bit variant.",
- "For 8-bit TeX the patterns are available separately as 'serbian' in",
- "T1/EC encoding for Latin script and 'serbianc' in T2A encoding for",
- "Cyrillic script. UTF-8 engines should only use 'serbian'",
+ #......................................................................#
+ "Hyphenation patterns for Serbian in T1/EC, T2A and UTF-8 encodings.",
+ "For 8-bit engines the patterns are available separately as 'serbian'",
+ "in T1/EC encoding for Latin script and 'serbianc' in T2A encoding for",
+ "Cyrillic script. Unicode engines should only use 'serbian'",
"which has patterns in both scripts combined.",
],
},
@@ -1080,9 +1575,10 @@ class Languages < Hash
# for both
"description_s" => "Mongolian hyphenation patterns in Cyrillic script",
"description_l" => [
- "Hyphenation patterns for Mongolian language in T2A, LMC and UTF-8 encoding.",
- "LMC encoding is used in MonTeX. The package includes two sets of patterns",
- "that will hopefully be merged in future.",
+ #......................................................................#
+ "Hyphenation patterns for Mongolian in T2A, LMC and UTF-8 encodings.",
+ "LMC encoding is used in MonTeX. The package includes two sets of",
+ "patterns that will hopefully be merged in future.",
],
},
# mongolianlmc xu-mnhyph.tex (used to be mongolian)
@@ -1097,7 +1593,7 @@ class Languages < Hash
"exceptions" => false,
"message" => "Mongolian hyphenation patterns",
},
-# bulgarian xu-bghyphen.tex
+# bulgarian
{
"code" => "bg",
"name" => "bulgarian",
@@ -1116,7 +1612,8 @@ class Languages < Hash
"licence" => "LPPL",
"description_s" => "Bulgarian hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Bulgarian language in T2A and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Bulgarian in T2A and UTF-8 encodings.",
],
},
# sanskrit
@@ -1125,8 +1622,8 @@ class Languages < Hash
"name" => "sanskrit",
"use_new_loader" => true,
"use_old_patterns" => false,
- "hyphenmin" => [1,5], # polyglosia
- "encoding" => nil, # no patterns for 8-bit TeX
+ "hyphenmin" => [1,5], # polyglossia
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Sanskrit hyphenation patterns (v0.4, 2010/02/26)",
@@ -1137,6 +1634,7 @@ class Languages < Hash
"licence" => nil,
"description_s" => "Sanskrit hyphenation patterns",
"description_l" => [
+ #......................................................................#
"Hyphenation patterns for Sanskrit and Prakrit in transliteration,",
"and in Devanagari, Bengali, Kannada, Malayalam and Telugu scripts",
"for Unicode engines.",
@@ -1171,7 +1669,9 @@ class Languages < Hash
"licence" => "free", # TODO
"description_s" => "Norwegian Bokmal and Nynorsk hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Norwegian Bokmal and Nynorsk in T1/EC and UTF-8 encoding.",
+ #......................................................................#
+ "Hyphenation patterns for Norwegian Bokmal and Nynorsk in T1/EC and",
+ "UTF-8 encodings.",
],
},
# nynorsk
@@ -1193,9 +1693,9 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
- "message" => "Assameze hyphenation patterns",
+ "message" => "Assamese hyphenation patterns",
# this is true for all Indic patterns
"version" => "0.5.3",
@@ -1205,9 +1705,10 @@ class Languages < Hash
"licence" => "LGPL",
"description_s" => "Indic hyphenation patterns",
"description_l" => [
- "Hyphenation patterns for Assameze, Bengali, Gujarati, Hindi,",
- "Kannada, Malayalam, Marathi, Oriya, Panjabi, Tamil and Telugu",
- "for Unicode engines.",
+ #......................................................................#
+ "Hyphenation patterns for Assamese, Bengali, Gujarati, Hindi, Kannada,",
+ "Malayalam, Marathi, Oriya, Panjabi, Tamil and Telugu for Unicode",
+ "engines.",
],
},
# bengali
@@ -1217,7 +1718,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Bengali hyphenation patterns",
},
@@ -1228,7 +1729,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Gujarati hyphenation patterns",
},
@@ -1239,7 +1740,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Hindi hyphenation patterns",
},
@@ -1250,7 +1751,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Kannada hyphenation patterns",
},
@@ -1261,7 +1762,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Malayalam hyphenation patterns",
},
@@ -1272,7 +1773,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Marathi hyphenation patterns",
},
@@ -1283,7 +1784,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Oriya hyphenation patterns",
},
@@ -1294,7 +1795,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Panjabi hyphenation patterns",
},
@@ -1305,7 +1806,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Tamil hyphenation patterns",
},
@@ -1316,7 +1817,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Telugu hyphenation patterns",
},
@@ -1327,7 +1828,7 @@ class Languages < Hash
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1], # TODO
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Lao hyphenation patterns",
@@ -1335,24 +1836,36 @@ class Languages < Hash
"last_modified" => "2010-05-19",
"type" => "rules",
"authors" => [ "brian_wilson", "arthur_reutenauer", "mojca_miklavec" ],
- "licence" => nil, # TODO
+ "licence" => "other-free",
"description_s" => "Lao hyphenation patterns",
"description_l" => [
+ #......................................................................#
"Hyphenation patterns for Lao language for Unicode engines.",
"Current version is experimental and gives bad results.",
- "Please wait for a new version.",
],
},
# pan-Ethiopic
{
"code" => "mul-ethi",
"name" => "ethiopic", "synonyms" => ["amharic", "geez"],
+ "version" => nil,
+ "last_modified" => "2011-01-10",
+ "authors" => ["arthur_reutenauer", "mojca_miklavec"],
+ "licence" => "public-ask", # TODO
"use_new_loader" => true,
"use_old_patterns" => false,
"hyphenmin" => [1,1],
- "encoding" => nil, # no patterns for 8-bit TeX
+ "encoding" => nil, # no patterns for 8-bit engines
"exceptions" => false,
"message" => "Pan-Ethiopic hyphenation patterns",
+ "description_s" => "Hyphenation patterns for Ethiopic scripts",
+ "description_l" => [
+ #......................................................................#
+ "Hyphenation patterns for languages written using the Ethiopic script",
+ "for Unicode engines. They are not supposed to be linguistically",
+ "relevant in all cases and should, for proper typography, be replaced",
+ "by files tailored to individual languages.",
+ ],
},
# dumylang -> dumyhyph.tex
# nohyphenation -> zerohyph.tex