diff options
Diffstat (limited to 'Master/texmf-dist/source/generic')
5 files changed, 328 insertions, 4 deletions
diff --git a/Master/texmf-dist/source/generic/hyph-utf8/data/encodings/l7x.dat b/Master/texmf-dist/source/generic/hyph-utf8/data/encodings/l7x.dat new file mode 100644 index 00000000000..c3e9fa08903 --- /dev/null +++ b/Master/texmf-dist/source/generic/hyph-utf8/data/encodings/l7x.dat @@ -0,0 +1,256 @@ +0x00 U+0060 grave +0x01 U+00B4 acute +0x02 U+02C6 circumflex +0x03 U+02DC tilde +0x04 U+00A8 dieresis +0x05 U+02DD hungarumlaut +0x06 U+02DA ring +0x07 U+02C7 caron +0x08 U+02D8 breve +0x09 U+00AF macron +0x0A U+02D9 dotaccent +0x0B U+00B8 cedilla +0x0C U+02DB ogonek +0x0D U+201A quotesinglbase +0x0E U+2039 guilsinglleft +0x0F U+203A guilsinglright +0x10 U+201C quotedblleft +0x11 U+201D quotedblright +0x12 U+201E quotedblbase +0x13 U+00AB guillemotleft +0x14 U+00BB guillemotright +0x15 U+2013 endash +0x16 U+2014 emdash +0x17 U+200B cwm +0x18 U+.... perthousandzero +0x19 U+0131 1 dotlessi +0x1A U+0237 1 dotlessj +0x1B U+FB00 ff +0x1C U+FB01 fi +0x1D U+FB02 fl +0x1E U+FB03 ffi +0x1F U+FB04 ffl +0x20 U+0020 space +0x21 U+0021 exclam +0x22 U+0022 quotedbl +0x23 U+0023 numbersign +0x24 U+0024 dollar +0x25 U+0025 percent +0x26 U+0026 ampersand +0x27 U+2019 quoteright +0x28 U+0028 parenleft +0x29 U+0029 parenright +0x2A U+002A asterisk +0x2B U+002B plus +0x2C U+002C comma +0x2D U+002D hyphen +0x2E U+002E period +0x2F U+002F slash +0x30 U+0030 zero +0x31 U+0031 one +0x32 U+0032 two +0x33 U+0033 three +0x34 U+0034 four +0x35 U+0035 five +0x36 U+0036 six +0x37 U+0037 seven +0x38 U+0038 eight +0x39 U+0039 nine +0x3A U+003A colon +0x3B U+003B semicolon +0x3C U+003C less +0x3D U+003D equal +0x3E U+003E greater +0x3F U+003F question +0x40 U+0040 at +0x41 U+0041 A +0x42 U+0042 B +0x43 U+0043 C +0x44 U+0044 D +0x45 U+0045 E +0x46 U+0046 F +0x47 U+0047 G +0x48 U+0048 H +0x49 U+0049 I +0x4A U+004A J +0x4B U+004B K +0x4C U+004C L +0x4D U+004D M +0x4E U+004E N +0x4F U+004F O +0x50 U+0050 P +0x51 U+0051 Q +0x52 U+0052 R +0x53 U+0053 S +0x54 U+0054 T +0x55 U+0055 U +0x56 U+0056 V +0x57 U+0057 W +0x58 U+0058 X +0x59 U+0059 Y +0x5A U+005A Z +0x5B U+005B bracketleft +0x5C U+005C backslash +0x5D U+005D bracketright +0x5E U+005E asciicircum +0x5F U+005F underscore +0x60 U+2018 quoteleft +0x61 U+0061 a +0x62 U+0062 b +0x63 U+0063 c +0x64 U+0064 d +0x65 U+0065 e +0x66 U+0066 f +0x67 U+0067 g +0x68 U+0068 h +0x69 U+0069 i +0x6A U+006A j +0x6B U+006B k +0x6C U+006C l +0x6D U+006D m +0x6E U+006E n +0x6F U+006F o +0x70 U+0070 p +0x71 U+0071 q +0x72 U+0072 r +0x73 U+0073 s +0x74 U+0074 t +0x75 U+0075 u +0x76 U+0076 v +0x77 U+0077 w +0x78 U+0078 x +0x79 U+0079 y +0x7A U+007A z +0x7B U+007B braceleft +0x7C U+007C bar +0x7D U+007D braceright +0x7E U+007E asciitilde +0x7F U+.... .notdef +0x80 U+20AC Euro +0x81 U+.... .notdef +0x82 U+201A quotesinglbase +0x83 U+0192 florin +0x84 U+201E quotedblbase +0x85 U+2026 ellipsis +0x86 U+2020 dagger +0x87 U+2021 daggerdbl +0x88 U+.... .notdef +0x89 U+2030 perthousand +0x8A U+.... .notdef +0x8B U+2039 guilsinglleft +0x8C U+0152 OE +0x8D U+00A8 dieresis +0x8E U+02C7 caron +0x8F U+00B8 cedilla +0x90 U+.... .notdef +0x91 U+2018 quoteleft +0x92 U+2019 quoteright +0x93 U+201C quotedblleft +0x94 U+201D quotedblright +0x95 U+2022 bullet +0x96 U+2013 endash +0x97 U+2014 emdash +0x98 U+.... .notdef +0x99 U+2122 trademark +0x9A U+.... .notdef +0x9B U+203A guilsinglright +0x9C U+0153 1 oe +0x9D U+00AF macron +0x9E U+02DB ogonek +0x9F U+.... .notdef +0xA0 U+0020 space +0xA1 U+201D quotedblright +0xA2 U+00A2 cent +0xA3 U+00A3 sterling +0xA4 U+00A4 currency +0xA5 U+201E quotedblbase +0xA6 U+00A6 brokenbar +0xA7 U+00A7 section +0xA8 U+00D8 Oslash +0xA9 U+00A9 copyright +0xAA U+0156 Rcommaaccent +0xAB U+00AB guillemotleft +0xAC U+00AC logicalnot +0xAD U+002D hyphen +0xAE U+00AE registered +0xAF U+00C6 AE +0xB0 U+00B0 degree +0xB1 U+00B1 plusminus +0xB2 U+00B2 twosuperior +0xB3 U+00B3 threesuperior +0xB4 U+201C quotedblleft +0xB5 U+00B5 mu +0xB6 U+00B6 paragraph +0xB7 U+00B7 periodcentered +0xB8 U+00F8 1 oslash +0xB9 U+00B9 onesuperior +0xBA U+0157 1 rcommaaccent +0xBB U+00BB guillemotright +0xBC U+00BC onequarter +0xBD U+00BD onehalf +0xBE U+00BE threequarters +0xBF U+00E6 1 ae +0xC0 U+0104 Aogonek +0xC1 U+012E Iogonek +0xC2 U+0100 Amacron +0xC3 U+0106 Cacute +0xC4 U+00C4 Adieresis +0xC5 U+00C5 Aring +0xC6 U+0118 Eogonek +0xC7 U+0112 Emacron +0xC8 U+010C Ccaron +0xC9 U+00C9 Eacute +0xCA U+0179 Zacute +0xCB U+0116 Edotaccent +0xCC U+0122 Gcommaaccent +0xCD U+0136 Kcommaaccent +0xCE U+012A Imacron +0xCF U+013B Lcommaaccent +0xD0 U+0160 Scaron +0xD1 U+0143 Nacute +0xD2 U+0145 Ncommaaccent +0xD3 U+00D3 Oacute +0xD4 U+014C Omacron +0xD5 U+00D5 Otilde +0xD6 U+00D6 Odieresis +0xD7 U+00D7 multiply +0xD8 U+0172 Uogonek +0xD9 U+0141 Lslash +0xDA U+015A Sacute +0xDB U+016A Umacron +0xDC U+00DC Udieresis +0xDD U+017B Zdotaccent +0xDE U+017D Zcaron +0xDF U+00DF 1 germandbls +0xE0 U+0105 1 aogonek +0xE1 U+012F 1 iogonek +0xE2 U+0101 1 amacron +0xE3 U+0107 1 cacute +0xE4 U+00E4 1 adieresis +0xE5 U+00E5 1 aring +0xE6 U+0119 1 eogonek +0xE7 U+0113 1 emacron +0xE8 U+010D 1 ccaron +0xE9 U+00E9 1 eacute +0xEA U+017A 1 zacute +0xEB U+0117 1 edotaccent +0xEC U+0123 1 gcommaaccent +0xED U+0137 1 kcommaaccent +0xEE U+012B 1 imacron +0xEF U+013C 1 lcommaaccent +0xF0 U+0161 1 scaron +0xF1 U+0144 1 nacute +0xF2 U+0146 1 ncommaaccent +0xF3 U+00F3 1 oacute +0xF4 U+014D 1 omacron +0xF5 U+00F5 1 otilde +0xF6 U+00F6 1 odieresis +0xF7 U+00F7 divide +0xF8 U+0173 1 uogonek +0xF9 U+0142 1 lslash +0xFA U+015B 1 sacute +0xFB U+016B 1 umacron +0xFC U+00FC 1 udieresis +0xFD U+017C 1 zdotaccent +0xFE U+017E 1 zcaron +0xFF U+2019 quoteright diff --git a/Master/texmf-dist/source/generic/hyph-utf8/generate-converters.rb b/Master/texmf-dist/source/generic/hyph-utf8/generate-converters.rb index 0449a12bc7c..bdc920181f9 100644 --- a/Master/texmf-dist/source/generic/hyph-utf8/generate-converters.rb +++ b/Master/texmf-dist/source/generic/hyph-utf8/generate-converters.rb @@ -1,7 +1,7 @@ #!/usr/bin/env ruby $encoding_data_dir = "data/encodings" -$encodings = ["ec", "qx", "t2a", "lmc", "il2", "il3"] +$encodings = ["ec", "qx", "t2a", "lmc", "il2", "il3", "l7x"] $output_data_dir = "../../../tex/generic/hyph-utf8/conversions" diff --git a/Master/texmf-dist/source/generic/hyph-utf8/generate-lua-tables-for-docs.rb b/Master/texmf-dist/source/generic/hyph-utf8/generate-lua-tables-for-docs.rb new file mode 100644 index 00000000000..d135392142f --- /dev/null +++ b/Master/texmf-dist/source/generic/hyph-utf8/generate-lua-tables-for-docs.rb @@ -0,0 +1,21 @@ +#!/usr/bin/env ruby + +# this file auto-generates data for docs for hyphenation patterns - to be improved + +load 'languages.rb' +$package_name="hyph-utf8" + +# TODO - make this a bit less hard-coded +$path_doc="../../../doc/generic/#{$package_name}" + +# TODO: should be singleton +languages = Languages.new.list + +puts "languages = {" +languages.each do |language| + puts "\t{" + puts "\t\t code = '#{language.code}'," + puts "\t\t name = '#{language.name}'," + puts "\t}," +end +puts "}" 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 d92627cf2fc..6ed311e5a10 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 @@ -97,6 +97,11 @@ languages.each do |language| file.puts(" \\lccode`'=`'\\lccode`’=`’\\lccode`ʼ=`ʼ\\lccode`᾽=`᾽\\lccode`᾿=`᾿") end file.puts(" \\input hyph-#{language.code}.tex") + # russian and ukrainian exceptions - hacks with dashes + if language.code == 'ru' or language.code == 'uk' then + file.puts(' % Additional patterns with hyphen/dash: a hack to prevent breaking after hyphen, but not before.') + file.puts(" \\input exhyph-#{language.code}.tex") + end file.puts('\else') file.puts(" \\message{#{language.message}}") # explain why we are still using the old patterns diff --git a/Master/texmf-dist/source/generic/hyph-utf8/languages.rb b/Master/texmf-dist/source/generic/hyph-utf8/languages.rb index 7fa06916868..71031e53aa9 100644 --- a/Master/texmf-dist/source/generic/hyph-utf8/languages.rb +++ b/Master/texmf-dist/source/generic/hyph-utf8/languages.rb @@ -20,6 +20,27 @@ class Language attr_reader :use_new_loader, :use_old_patterns, :use_old_patterns_comment, :filename_old_patterns, :code, :name, :synonyms, :hyphenmin, :encoding, :exceptions, :message end + +authors = { + "peter_heslin" => { + "name" => "Peter", + "surname" => "Heslin", + "tried_to_contact" => false, + }, + "dimitrios_filippou" => { + "name" => "Dimitrios", + "surname" => "Filippou", + "email" => "dfilipp{at}hotmail{dot}com", + "contact" => true, + "cooperate" => true, + }, + "claudio_beccari" => { + "name" => "Claudio", + "email" => "claudio.beccari@polito.it", + } + +} + # "use_new_loader" # => true - create a new file and use that one # => false - use "filename_old_patterns" in language.dat @@ -84,6 +105,8 @@ class Languages < Hash "encoding" => nil, "exceptions" => false, "message" => "Ancient Greek Hyphenation Patterns for Ibycus encoding (v3.0)", + + "authors" => ["peter_heslin"], }, # ---------------------------- # languages using old patterns @@ -104,7 +127,9 @@ class Languages < Hash "encoding" => nil, "exceptions" => true, # "message" => "Polytonic Greek Hyphenation Patterns", - "message" => "Hyphenation patterns for multi-accent (polytonic) Modern Greek" + "message" => "Hyphenation patterns for multi-accent (polytonic) Modern Greek", + + "authors" => ["dimitrios_filippou"], }, # monogreek xu-grmhyph4.tex { @@ -118,7 +143,9 @@ class Languages < Hash "encoding" => nil, "exceptions" => true, # "message" => "Monotonic Greek Hyphenation Patterns", - "message" => "Hyphenation patterns for uni-accent (monotonic) Modern Greek" + "message" => "Hyphenation patterns for uni-accent (monotonic) Modern Greek", + + "authors" => ["dimitrios_filippou"], }, # ancientgreek xu-grahyph4.tex { @@ -131,7 +158,9 @@ class Languages < Hash "hyphenmin" => [1,1], # polyglosia "encoding" => nil, "exceptions" => false, - "message" => "Hyphenation patterns for Ancient Greek" + "message" => "Hyphenation patterns for Ancient Greek", + + "authors" => ["dimitrios_filippou"], }, # coptic xu-copthyph.tex { @@ -145,6 +174,8 @@ class Languages < Hash "encoding" => nil, "exceptions" => false, "message" => "Coptic Hyphenation Patterns", + + "authors" => ["claudio_beccari"], }, # german xu-dehypht.tex { @@ -454,6 +485,17 @@ class Languages < Hash "exceptions" => false, "message" => "Latin Hyphenation Patterns", }, +# lithuanian +{ + "code" => "lt", + "name" => "lithuanian", + "use_new_loader" => true, + "use_old_patterns" => false, + "hyphenmin" => [2,2], + "encoding" => "l7x", + "exceptions" => false, + "message" => "Lithuanian Hyphenation Patterns", +}, # dutch nehyph96.tex { "code" => "nl", |