summaryrefslogtreecommitdiff
path: root/tex/context/base/char-ini.lua
diff options
context:
space:
mode:
Diffstat (limited to 'tex/context/base/char-ini.lua')
-rw-r--r--tex/context/base/char-ini.lua381
1 files changed, 199 insertions, 182 deletions
diff --git a/tex/context/base/char-ini.lua b/tex/context/base/char-ini.lua
index 6b6900ecd..bb7cce997 100644
--- a/tex/context/base/char-ini.lua
+++ b/tex/context/base/char-ini.lua
@@ -127,188 +127,190 @@ end )
--~ setmetatable(data,{ __index = function(t,k) return "" end }) -- quite old, obsolete
-characters.blocks = allocate {
- ["aegeannumbers"] = { 0x10100, 0x1013F, "Aegean Numbers" },
- ["alphabeticpresentationforms"] = { 0x0FB00, 0x0FB4F, "Alphabetic Presentation Forms" },
- ["ancientgreekmusicalnotation"] = { 0x1D200, 0x1D24F, "Ancient Greek Musical Notation" },
- ["ancientgreeknumbers"] = { 0x10140, 0x1018F, "Ancient Greek Numbers" },
- ["ancientsymbols"] = { 0x10190, 0x101CF, "Ancient Symbols" },
- ["arabic"] = { 0x00600, 0x006FF, "Arabic" },
- ["arabicpresentationformsa"] = { 0x0FB50, 0x0FDFF, "Arabic Presentation Forms-A" },
- ["arabicpresentationformsb"] = { 0x0FE70, 0x0FEFF, "Arabic Presentation Forms-B" },
- ["arabicsupplement"] = { 0x00750, 0x0077F, "Arabic Supplement" },
- ["armenian"] = { 0x00530, 0x0058F, "Armenian" },
- ["arrows"] = { 0x02190, 0x021FF, "Arrows" },
- ["balinese"] = { 0x01B00, 0x01B7F, "Balinese" },
- ["basiclatin"] = { 0x00000, 0x0007F, "Basic Latin" },
- ["bengali"] = { 0x00980, 0x009FF, "Bengali" },
- ["blockelements"] = { 0x02580, 0x0259F, "Block Elements" },
- ["bopomofo"] = { 0x03100, 0x0312F, "Bopomofo" },
- ["bopomofoextended"] = { 0x031A0, 0x031BF, "Bopomofo Extended" },
- ["boxdrawing"] = { 0x02500, 0x0257F, "Box Drawing" },
- ["braillepatterns"] = { 0x02800, 0x028FF, "Braille Patterns" },
- ["buginese"] = { 0x01A00, 0x01A1F, "Buginese" },
- ["buhid"] = { 0x01740, 0x0175F, "Buhid" },
- ["byzantinemusicalsymbols"] = { 0x1D000, 0x1D0FF, "Byzantine Musical Symbols" },
- ["carian"] = { 0x102A0, 0x102DF, "Carian" },
- ["cham"] = { 0x0AA00, 0x0AA5F, "Cham" },
- ["cherokee"] = { 0x013A0, 0x013FF, "Cherokee" },
- ["cjkcompatibility"] = { 0x03300, 0x033FF, "CJK Compatibility" },
- ["cjkcompatibilityforms"] = { 0x0FE30, 0x0FE4F, "CJK Compatibility Forms" },
- ["cjkcompatibilityideographs"] = { 0x0F900, 0x0FAFF, "CJK Compatibility Ideographs" },
- ["cjkcompatibilityideographssupplement"] = { 0x2F800, 0x2FA1F, "CJK Compatibility Ideographs Supplement" },
- ["cjkradicalssupplement"] = { 0x02E80, 0x02EFF, "CJK Radicals Supplement" },
- ["cjkstrokes"] = { 0x031C0, 0x031EF, "CJK Strokes" },
- ["cjksymbolsandpunctuation"] = { 0x03000, 0x0303F, "CJK Symbols and Punctuation" },
- ["cjkunifiedideographs"] = { 0x04E00, 0x09FFF, "CJK Unified Ideographs" },
- ["cjkunifiedideographsextensiona"] = { 0x03400, 0x04DBF, "CJK Unified Ideographs Extension A" },
- ["cjkunifiedideographsextensionb"] = { 0x20000, 0x2A6DF, "CJK Unified Ideographs Extension B" },
- ["combiningdiacriticalmarks"] = { 0x00300, 0x0036F, "Combining Diacritical Marks" },
- ["combiningdiacriticalmarksforsymbols"] = { 0x020D0, 0x020FF, "Combining Diacritical Marks for Symbols" },
- ["combiningdiacriticalmarkssupplement"] = { 0x01DC0, 0x01DFF, "Combining Diacritical Marks Supplement" },
- ["combininghalfmarks"] = { 0x0FE20, 0x0FE2F, "Combining Half Marks" },
- ["controlpictures"] = { 0x02400, 0x0243F, "Control Pictures" },
- ["coptic"] = { 0x02C80, 0x02CFF, "Coptic" },
- ["countingrodnumerals"] = { 0x1D360, 0x1D37F, "Counting Rod Numerals" },
- ["cuneiform"] = { 0x12000, 0x123FF, "Cuneiform" },
- ["cuneiformnumbersandpunctuation"] = { 0x12400, 0x1247F, "Cuneiform Numbers and Punctuation" },
- ["currencysymbols"] = { 0x020A0, 0x020CF, "Currency Symbols" },
- ["cypriotsyllabary"] = { 0x10800, 0x1083F, "Cypriot Syllabary" },
- ["cyrillic"] = { 0x00400, 0x004FF, "Cyrillic" },
- ["cyrillicextendeda"] = { 0x02DE0, 0x02DFF, "Cyrillic Extended-A" },
- ["cyrillicextendedb"] = { 0x0A640, 0x0A69F, "Cyrillic Extended-B" },
- ["cyrillicsupplement"] = { 0x00500, 0x0052F, "Cyrillic Supplement" },
- ["deseret"] = { 0x10400, 0x1044F, "Deseret" },
- ["devanagari"] = { 0x00900, 0x0097F, "Devanagari" },
- ["dingbats"] = { 0x02700, 0x027BF, "Dingbats" },
- ["dominotiles"] = { 0x1F030, 0x1F09F, "Domino Tiles" },
- ["enclosedalphanumerics"] = { 0x02460, 0x024FF, "Enclosed Alphanumerics" },
- ["enclosedcjklettersandmonths"] = { 0x03200, 0x032FF, "Enclosed CJK Letters and Months" },
- ["ethiopic"] = { 0x01200, 0x0137F, "Ethiopic" },
- ["ethiopicextended"] = { 0x02D80, 0x02DDF, "Ethiopic Extended" },
- ["ethiopicsupplement"] = { 0x01380, 0x0139F, "Ethiopic Supplement" },
- ["generalpunctuation"] = { 0x02000, 0x0206F, "General Punctuation" },
- ["geometricshapes"] = { 0x025A0, 0x025FF, "Geometric Shapes" },
- ["georgian"] = { 0x010A0, 0x010FF, "Georgian" },
- ["georgiansupplement"] = { 0x02D00, 0x02D2F, "Georgian Supplement" },
- ["glagolitic"] = { 0x02C00, 0x02C5F, "Glagolitic" },
- ["gothic"] = { 0x10330, 0x1034F, "Gothic" },
- ["greekandcoptic"] = { 0x00370, 0x003FF, "Greek and Coptic" },
- ["greekextended"] = { 0x01F00, 0x01FFF, "Greek Extended" },
- ["gujarati"] = { 0x00A80, 0x00AFF, "Gujarati" },
- ["gurmukhi"] = { 0x00A00, 0x00A7F, "Gurmukhi" },
- ["halfwidthandfullwidthforms"] = { 0x0FF00, 0x0FFEF, "Halfwidth and Fullwidth Forms" },
- ["hangulcompatibilityjamo"] = { 0x03130, 0x0318F, "Hangul Compatibility Jamo" },
- ["hanguljamo"] = { 0x01100, 0x011FF, "Hangul Jamo" },
- ["hangulsyllables"] = { 0x0AC00, 0x0D7AF, "Hangul Syllables" },
- ["hanunoo"] = { 0x01720, 0x0173F, "Hanunoo" },
- ["hebrew"] = { 0x00590, 0x005FF, "Hebrew" },
- ["highprivateusesurrogates"] = { 0x0DB80, 0x0DBFF, "High Private Use Surrogates" },
- ["highsurrogates"] = { 0x0D800, 0x0DB7F, "High Surrogates" },
- ["hiragana"] = { 0x03040, 0x0309F, "Hiragana" },
- ["ideographicdescriptioncharacters"] = { 0x02FF0, 0x02FFF, "Ideographic Description Characters" },
- ["ipaextensions"] = { 0x00250, 0x02AF, "IPA Extensions" },
- ["kanbun"] = { 0x03190, 0x0319F, "Kanbun" },
- ["kangxiradicals"] = { 0x02F00, 0x02FDF, "Kangxi Radicals" },
- ["kannada"] = { 0x00C80, 0x00CFF, "Kannada" },
- ["katakana"] = { 0x030A0, 0x030FF, "Katakana" },
- ["katakanaphoneticextensions"] = { 0x031F0, 0x031FF, "Katakana Phonetic Extensions" },
- ["kayahli"] = { 0x0A900, 0x0A92F, "Kayah Li" },
- ["kharoshthi"] = { 0x10A00, 0x10A5F, "Kharoshthi" },
- ["khmer"] = { 0x01780, 0x017FF, "Khmer" },
- ["khmersymbols"] = { 0x019E0, 0x019FF, "Khmer Symbols" },
- ["lao"] = { 0x00E80, 0x00EFF, "Lao" },
- ["latinextendeda"] = { 0x00100, 0x0017F, "Latin Extended-A" },
- ["latinextendedadditional"] = { 0x01E00, 0x01EFF, "Latin Extended Additional" },
- ["latinextendedb"] = { 0x00180, 0x0024F, "Latin Extended-B" },
- ["latinextendedc"] = { 0x02C60, 0x02C7F, "Latin Extended-C" },
- ["latinextendedd"] = { 0x0A720, 0x0A7FF, "Latin Extended-D" },
- ["latinsupplement"] = { 0x00080, 0x000FF, "Latin-1 Supplement" },
- ["lepcha"] = { 0x01C00, 0x01C4F, "Lepcha" },
- ["letterlikesymbols"] = { 0x02100, 0x0214F, "Letterlike Symbols" },
- ["limbu"] = { 0x01900, 0x0194F, "Limbu" },
- ["linearbideograms"] = { 0x10080, 0x100FF, "Linear B Ideograms" },
- ["linearbsyllabary"] = { 0x10000, 0x1007F, "Linear B Syllabary" },
- ["lowsurrogates"] = { 0x0DC00, 0x0DFFF, "Low Surrogates" },
- ["lycian"] = { 0x10280, 0x1029F, "Lycian" },
- ["lydian"] = { 0x10920, 0x1093F, "Lydian" },
- ["mahjongtiles"] = { 0x1F000, 0x1F02F, "Mahjong Tiles" },
- ["malayalam"] = { 0x00D00, 0x00D7F, "Malayalam" },
- ["mathematicalalphanumericsymbols"] = { 0x1D400, 0x1D7FF, "Mathematical Alphanumeric Symbols" },
- ["mathematicaloperators"] = { 0x02200, 0x022FF, "Mathematical Operators" },
- ["miscellaneousmathematicalsymbolsa"] = { 0x027C0, 0x027EF, "Miscellaneous Mathematical Symbols-A" },
- ["miscellaneousmathematicalsymbolsb"] = { 0x02980, 0x029FF, "Miscellaneous Mathematical Symbols-B" },
- ["miscellaneoussymbols"] = { 0x02600, 0x026FF, "Miscellaneous Symbols" },
- ["miscellaneoussymbolsandarrows"] = { 0x02B00, 0x02BFF, "Miscellaneous Symbols and Arrows" },
- ["miscellaneoustechnical"] = { 0x02300, 0x023FF, "Miscellaneous Technical" },
- ["modifiertoneletters"] = { 0x0A700, 0x0A71F, "Modifier Tone Letters" },
- ["mongolian"] = { 0x01800, 0x018AF, "Mongolian" },
- ["musicalsymbols"] = { 0x1D100, 0x1D1FF, "Musical Symbols" },
- ["myanmar"] = { 0x01000, 0x0109F, "Myanmar" },
- ["newtailue"] = { 0x01980, 0x019DF, "New Tai Lue" },
- ["nko"] = { 0x007C0, 0x007FF, "NKo" },
- ["numberforms"] = { 0x02150, 0x0218F, "Number Forms" },
- ["ogham"] = { 0x01680, 0x0169F, "Ogham" },
- ["olchiki"] = { 0x01C50, 0x01C7F, "Ol Chiki" },
- ["olditalic"] = { 0x10300, 0x1032F, "Old Italic" },
- ["oldpersian"] = { 0x103A0, 0x103DF, "Old Persian" },
- ["opticalcharacterrecognition"] = { 0x02440, 0x0245F, "Optical Character Recognition" },
- ["oriya"] = { 0x00B00, 0x00B7F, "Oriya" },
- ["osmanya"] = { 0x10480, 0x104AF, "Osmanya" },
- ["phagspa"] = { 0x0A840, 0x0A87F, "Phags-pa" },
- ["phaistosdisc"] = { 0x101D0, 0x101FF, "Phaistos Disc" },
- ["phoenician"] = { 0x10900, 0x1091F, "Phoenician" },
- ["phoneticextensions"] = { 0x01D00, 0x01D7F, "Phonetic Extensions" },
- ["phoneticextensionssupplement"] = { 0x01D80, 0x01DBF, "Phonetic Extensions Supplement" },
- ["privateusearea"] = { 0x0E000, 0x0F8FF, "Private Use Area" },
- ["rejang"] = { 0x0A930, 0x0A95F, "Rejang" },
- ["runic"] = { 0x016A0, 0x016FF, "Runic" },
- ["saurashtra"] = { 0x0A880, 0x0A8DF, "Saurashtra" },
- ["shavian"] = { 0x10450, 0x1047F, "Shavian" },
- ["sinhala"] = { 0x00D80, 0x00DFF, "Sinhala" },
- ["smallformvariants"] = { 0x0FE50, 0x0FE6F, "Small Form Variants" },
- ["spacingmodifierletters"] = { 0x002B0, 0x002FF, "Spacing Modifier Letters" },
- ["specials"] = { 0x0FFF0, 0x0FFFF, "Specials" },
- ["sundanese"] = { 0x01B80, 0x01BBF, "Sundanese" },
- ["superscriptsandsubscripts"] = { 0x02070, 0x0209F, "Superscripts and Subscripts" },
- ["supplementalarrowsa"] = { 0x027F0, 0x027FF, "Supplemental Arrows-A" },
- ["supplementalarrowsb"] = { 0x02900, 0x0297F, "Supplemental Arrows-B" },
- ["supplementalmathematicaloperators"] = { 0x02A00, 0x02AFF, "Supplemental Mathematical Operators" },
- ["supplementalpunctuation"] = { 0x02E00, 0x02E7F, "Supplemental Punctuation" },
- ["supplementaryprivateuseareaa"] = { 0xF0000, 0xFFFFF, "Supplementary Private Use Area-A" },
- ["supplementaryprivateuseareab"] = { 0x100000,0x10FFFF,"Supplementary Private Use Area-B" },
- ["sylotinagri"] = { 0x0A800, 0x0A82F, "Syloti Nagri" },
- ["syriac"] = { 0x00700, 0x0074F, "Syriac" },
- ["tagalog"] = { 0x01700, 0x0171F, "Tagalog" },
- ["tagbanwa"] = { 0x01760, 0x0177F, "Tagbanwa" },
- ["tags"] = { 0xE0000, 0xE007F, "Tags" },
- ["taile"] = { 0x01950, 0x0197F, "Tai Le" },
- ["taixuanjingsymbols"] = { 0x1D300, 0x1D35F, "Tai Xuan Jing Symbols" },
- ["tamil"] = { 0x00B80, 0x00BFF, "Tamil" },
- ["telugu"] = { 0x00C00, 0x00C7F, "Telugu" },
- ["thaana"] = { 0x00780, 0x007BF, "Thaana" },
- ["thai"] = { 0x00E00, 0x00E7F, "Thai" },
- ["tibetan"] = { 0x00F00, 0x00FFF, "Tibetan" },
- ["tifinagh"] = { 0x02D30, 0x02D7F, "Tifinagh" },
- ["ugaritic"] = { 0x10380, 0x1039F, "Ugaritic" },
- ["unifiedcanadianaboriginalsyllabics"] = { 0x01400, 0x0167F, "Unified Canadian Aboriginal Syllabics" },
- ["vai"] = { 0x0A500, 0x0A63F, "Vai" },
- ["variationselectors"] = { 0x0FE00, 0x0FE0F, "Variation Selectors" },
- ["variationselectorssupplement"] = { 0xE0100, 0xE01EF, "Variation Selectors Supplement" },
- ["verticalforms"] = { 0x0FE10, 0x0FE1F, "Vertical Forms" },
- ["yijinghexagramsymbols"] = { 0x04DC0, 0x04DFF, "Yijing Hexagram Symbols" },
- ["yiradicals"] = { 0x0A490, 0x0A4CF, "Yi Radicals" },
- ["yisyllables"] = { 0x0A000, 0x0A48F, "Yi Syllables" },
+local blocks = allocate {
+ ["aegeannumbers"] = { first = 0x10100, last = 0x1013F, description = "Aegean Numbers" },
+ ["alphabeticpresentationforms"] = { first = 0x0FB00, last = 0x0FB4F, description = "Alphabetic Presentation Forms" },
+ ["ancientgreekmusicalnotation"] = { first = 0x1D200, last = 0x1D24F, description = "Ancient Greek Musical Notation" },
+ ["ancientgreeknumbers"] = { first = 0x10140, last = 0x1018F, description = "Ancient Greek Numbers" },
+ ["ancientsymbols"] = { first = 0x10190, last = 0x101CF, description = "Ancient Symbols" },
+ ["arabic"] = { first = 0x00600, last = 0x006FF, description = "Arabic" },
+ ["arabicpresentationformsa"] = { first = 0x0FB50, last = 0x0FDFF, description = "Arabic Presentation Forms-A" },
+ ["arabicpresentationformsb"] = { first = 0x0FE70, last = 0x0FEFF, description = "Arabic Presentation Forms-B" },
+ ["arabicsupplement"] = { first = 0x00750, last = 0x0077F, description = "Arabic Supplement" },
+ ["armenian"] = { first = 0x00530, last = 0x0058F, description = "Armenian" },
+ ["arrows"] = { first = 0x02190, last = 0x021FF, description = "Arrows" },
+ ["balinese"] = { first = 0x01B00, last = 0x01B7F, description = "Balinese" },
+ ["basiclatin"] = { first = 0x00000, last = 0x0007F, description = "Basic Latin" },
+ ["bengali"] = { first = 0x00980, last = 0x009FF, description = "Bengali" },
+ ["blockelements"] = { first = 0x02580, last = 0x0259F, description = "Block Elements" },
+ ["bopomofo"] = { first = 0x03100, last = 0x0312F, description = "Bopomofo" },
+ ["bopomofoextended"] = { first = 0x031A0, last = 0x031BF, description = "Bopomofo Extended" },
+ ["boxdrawing"] = { first = 0x02500, last = 0x0257F, description = "Box Drawing" },
+ ["braillepatterns"] = { first = 0x02800, last = 0x028FF, description = "Braille Patterns" },
+ ["buginese"] = { first = 0x01A00, last = 0x01A1F, description = "Buginese" },
+ ["buhid"] = { first = 0x01740, last = 0x0175F, description = "Buhid" },
+ ["byzantinemusicalsymbols"] = { first = 0x1D000, last = 0x1D0FF, description = "Byzantine Musical Symbols" },
+ ["carian"] = { first = 0x102A0, last = 0x102DF, description = "Carian" },
+ ["cham"] = { first = 0x0AA00, last = 0x0AA5F, description = "Cham" },
+ ["cherokee"] = { first = 0x013A0, last = 0x013FF, description = "Cherokee" },
+ ["cjkcompatibility"] = { first = 0x03300, last = 0x033FF, description = "CJK Compatibility" },
+ ["cjkcompatibilityforms"] = { first = 0x0FE30, last = 0x0FE4F, description = "CJK Compatibility Forms" },
+ ["cjkcompatibilityideographs"] = { first = 0x0F900, last = 0x0FAFF, description = "CJK Compatibility Ideographs" },
+ ["cjkcompatibilityideographssupplement"] = { first = 0x2F800, last = 0x2FA1F, description = "CJK Compatibility Ideographs Supplement" },
+ ["cjkradicalssupplement"] = { first = 0x02E80, last = 0x02EFF, description = "CJK Radicals Supplement" },
+ ["cjkstrokes"] = { first = 0x031C0, last = 0x031EF, description = "CJK Strokes" },
+ ["cjksymbolsandpunctuation"] = { first = 0x03000, last = 0x0303F, description = "CJK Symbols and Punctuation" },
+ ["cjkunifiedideographs"] = { first = 0x04E00, last = 0x09FFF, description = "CJK Unified Ideographs" },
+ ["cjkunifiedideographsextensiona"] = { first = 0x03400, last = 0x04DBF, description = "CJK Unified Ideographs Extension A" },
+ ["cjkunifiedideographsextensionb"] = { first = 0x20000, last = 0x2A6DF, description = "CJK Unified Ideographs Extension B" },
+ ["combiningdiacriticalmarks"] = { first = 0x00300, last = 0x0036F, description = "Combining Diacritical Marks" },
+ ["combiningdiacriticalmarksforsymbols"] = { first = 0x020D0, last = 0x020FF, description = "Combining Diacritical Marks for Symbols" },
+ ["combiningdiacriticalmarkssupplement"] = { first = 0x01DC0, last = 0x01DFF, description = "Combining Diacritical Marks Supplement" },
+ ["combininghalfmarks"] = { first = 0x0FE20, last = 0x0FE2F, description = "Combining Half Marks" },
+ ["controlpictures"] = { first = 0x02400, last = 0x0243F, description = "Control Pictures" },
+ ["coptic"] = { first = 0x02C80, last = 0x02CFF, description = "Coptic" },
+ ["countingrodnumerals"] = { first = 0x1D360, last = 0x1D37F, description = "Counting Rod Numerals" },
+ ["cuneiform"] = { first = 0x12000, last = 0x123FF, description = "Cuneiform" },
+ ["cuneiformnumbersandpunctuation"] = { first = 0x12400, last = 0x1247F, description = "Cuneiform Numbers and Punctuation" },
+ ["currencysymbols"] = { first = 0x020A0, last = 0x020CF, description = "Currency Symbols" },
+ ["cypriotsyllabary"] = { first = 0x10800, last = 0x1083F, description = "Cypriot Syllabary" },
+ ["cyrillic"] = { first = 0x00400, last = 0x004FF, description = "Cyrillic" },
+ ["cyrillicextendeda"] = { first = 0x02DE0, last = 0x02DFF, description = "Cyrillic Extended-A" },
+ ["cyrillicextendedb"] = { first = 0x0A640, last = 0x0A69F, description = "Cyrillic Extended-B" },
+ ["cyrillicsupplement"] = { first = 0x00500, last = 0x0052F, description = "Cyrillic Supplement" },
+ ["deseret"] = { first = 0x10400, last = 0x1044F, description = "Deseret" },
+ ["devanagari"] = { first = 0x00900, last = 0x0097F, description = "Devanagari" },
+ ["dingbats"] = { first = 0x02700, last = 0x027BF, description = "Dingbats" },
+ ["dominotiles"] = { first = 0x1F030, last = 0x1F09F, description = "Domino Tiles" },
+ ["enclosedalphanumerics"] = { first = 0x02460, last = 0x024FF, description = "Enclosed Alphanumerics" },
+ ["enclosedcjklettersandmonths"] = { first = 0x03200, last = 0x032FF, description = "Enclosed CJK Letters and Months" },
+ ["ethiopic"] = { first = 0x01200, last = 0x0137F, description = "Ethiopic" },
+ ["ethiopicextended"] = { first = 0x02D80, last = 0x02DDF, description = "Ethiopic Extended" },
+ ["ethiopicsupplement"] = { first = 0x01380, last = 0x0139F, description = "Ethiopic Supplement" },
+ ["generalpunctuation"] = { first = 0x02000, last = 0x0206F, description = "General Punctuation" },
+ ["geometricshapes"] = { first = 0x025A0, last = 0x025FF, description = "Geometric Shapes" },
+ ["georgian"] = { first = 0x010A0, last = 0x010FF, description = "Georgian" },
+ ["georgiansupplement"] = { first = 0x02D00, last = 0x02D2F, description = "Georgian Supplement" },
+ ["glagolitic"] = { first = 0x02C00, last = 0x02C5F, description = "Glagolitic" },
+ ["gothic"] = { first = 0x10330, last = 0x1034F, description = "Gothic" },
+ ["greekandcoptic"] = { first = 0x00370, last = 0x003FF, description = "Greek and Coptic" },
+ ["greekextended"] = { first = 0x01F00, last = 0x01FFF, description = "Greek Extended" },
+ ["gujarati"] = { first = 0x00A80, last = 0x00AFF, description = "Gujarati" },
+ ["gurmukhi"] = { first = 0x00A00, last = 0x00A7F, description = "Gurmukhi" },
+ ["halfwidthandfullwidthforms"] = { first = 0x0FF00, last = 0x0FFEF, description = "Halfwidth and Fullwidth Forms" },
+ ["hangulcompatibilityjamo"] = { first = 0x03130, last = 0x0318F, description = "Hangul Compatibility Jamo" },
+ ["hanguljamo"] = { first = 0x01100, last = 0x011FF, description = "Hangul Jamo" },
+ ["hangulsyllables"] = { first = 0x0AC00, last = 0x0D7AF, description = "Hangul Syllables" },
+ ["hanunoo"] = { first = 0x01720, last = 0x0173F, description = "Hanunoo" },
+ ["hebrew"] = { first = 0x00590, last = 0x005FF, description = "Hebrew" },
+ ["highprivateusesurrogates"] = { first = 0x0DB80, last = 0x0DBFF, description = "High Private Use Surrogates" },
+ ["highsurrogates"] = { first = 0x0D800, last = 0x0DB7F, description = "High Surrogates" },
+ ["hiragana"] = { first = 0x03040, last = 0x0309F, description = "Hiragana" },
+ ["ideographicdescriptioncharacters"] = { first = 0x02FF0, last = 0x02FFF, description = "Ideographic Description Characters" },
+ ["ipaextensions"] = { first = 0x00250, last = 0x002AF, description = "IPA Extensions" },
+ ["kanbun"] = { first = 0x03190, last = 0x0319F, description = "Kanbun" },
+ ["kangxiradicals"] = { first = 0x02F00, last = 0x02FDF, description = "Kangxi Radicals" },
+ ["kannada"] = { first = 0x00C80, last = 0x00CFF, description = "Kannada" },
+ ["katakana"] = { first = 0x030A0, last = 0x030FF, description = "Katakana" },
+ ["katakanaphoneticextensions"] = { first = 0x031F0, last = 0x031FF, description = "Katakana Phonetic Extensions" },
+ ["kayahli"] = { first = 0x0A900, last = 0x0A92F, description = "Kayah Li" },
+ ["kharoshthi"] = { first = 0x10A00, last = 0x10A5F, description = "Kharoshthi" },
+ ["khmer"] = { first = 0x01780, last = 0x017FF, description = "Khmer" },
+ ["khmersymbols"] = { first = 0x019E0, last = 0x019FF, description = "Khmer Symbols" },
+ ["lao"] = { first = 0x00E80, last = 0x00EFF, description = "Lao" },
+ ["latinextendeda"] = { first = 0x00100, last = 0x0017F, description = "Latin Extended-A" },
+ ["latinextendedadditional"] = { first = 0x01E00, last = 0x01EFF, description = "Latin Extended Additional" },
+ ["latinextendedb"] = { first = 0x00180, last = 0x0024F, description = "Latin Extended-B" },
+ ["latinextendedc"] = { first = 0x02C60, last = 0x02C7F, description = "Latin Extended-C" },
+ ["latinextendedd"] = { first = 0x0A720, last = 0x0A7FF, description = "Latin Extended-D" },
+ ["latinsupplement"] = { first = 0x00080, last = 0x000FF, description = "Latin-1 Supplement" },
+ ["lepcha"] = { first = 0x01C00, last = 0x01C4F, description = "Lepcha" },
+ ["letterlikesymbols"] = { first = 0x02100, last = 0x0214F, description = "Letterlike Symbols" },
+ ["limbu"] = { first = 0x01900, last = 0x0194F, description = "Limbu" },
+ ["linearbideograms"] = { first = 0x10080, last = 0x100FF, description = "Linear B Ideograms" },
+ ["linearbsyllabary"] = { first = 0x10000, last = 0x1007F, description = "Linear B Syllabary" },
+ ["lowsurrogates"] = { first = 0x0DC00, last = 0x0DFFF, description = "Low Surrogates" },
+ ["lycian"] = { first = 0x10280, last = 0x1029F, description = "Lycian" },
+ ["lydian"] = { first = 0x10920, last = 0x1093F, description = "Lydian" },
+ ["mahjongtiles"] = { first = 0x1F000, last = 0x1F02F, description = "Mahjong Tiles" },
+ ["malayalam"] = { first = 0x00D00, last = 0x00D7F, description = "Malayalam" },
+ ["mathematicalalphanumericsymbols"] = { first = 0x1D400, last = 0x1D7FF, description = "Mathematical Alphanumeric Symbols" },
+ ["mathematicaloperators"] = { first = 0x02200, last = 0x022FF, description = "Mathematical Operators" },
+ ["miscellaneousmathematicalsymbolsa"] = { first = 0x027C0, last = 0x027EF, description = "Miscellaneous Mathematical Symbols-A" },
+ ["miscellaneousmathematicalsymbolsb"] = { first = 0x02980, last = 0x029FF, description = "Miscellaneous Mathematical Symbols-B" },
+ ["miscellaneoussymbols"] = { first = 0x02600, last = 0x026FF, description = "Miscellaneous Symbols" },
+ ["miscellaneoussymbolsandarrows"] = { first = 0x02B00, last = 0x02BFF, description = "Miscellaneous Symbols and Arrows" },
+ ["miscellaneoustechnical"] = { first = 0x02300, last = 0x023FF, description = "Miscellaneous Technical" },
+ ["modifiertoneletters"] = { first = 0x0A700, last = 0x0A71F, description = "Modifier Tone Letters" },
+ ["mongolian"] = { first = 0x01800, last = 0x018AF, description = "Mongolian" },
+ ["musicalsymbols"] = { first = 0x1D100, last = 0x1D1FF, description = "Musical Symbols" },
+ ["myanmar"] = { first = 0x01000, last = 0x0109F, description = "Myanmar" },
+ ["newtailue"] = { first = 0x01980, last = 0x019DF, description = "New Tai Lue" },
+ ["nko"] = { first = 0x007C0, last = 0x007FF, description = "NKo" },
+ ["numberforms"] = { first = 0x02150, last = 0x0218F, description = "Number Forms" },
+ ["ogham"] = { first = 0x01680, last = 0x0169F, description = "Ogham" },
+ ["olchiki"] = { first = 0x01C50, last = 0x01C7F, description = "Ol Chiki" },
+ ["olditalic"] = { first = 0x10300, last = 0x1032F, description = "Old Italic" },
+ ["oldpersian"] = { first = 0x103A0, last = 0x103DF, description = "Old Persian" },
+ ["opticalcharacterrecognition"] = { first = 0x02440, last = 0x0245F, description = "Optical Character Recognition" },
+ ["oriya"] = { first = 0x00B00, last = 0x00B7F, description = "Oriya" },
+ ["osmanya"] = { first = 0x10480, last = 0x104AF, description = "Osmanya" },
+ ["phagspa"] = { first = 0x0A840, last = 0x0A87F, description = "Phags-pa" },
+ ["phaistosdisc"] = { first = 0x101D0, last = 0x101FF, description = "Phaistos Disc" },
+ ["phoenician"] = { first = 0x10900, last = 0x1091F, description = "Phoenician" },
+ ["phoneticextensions"] = { first = 0x01D00, last = 0x01D7F, description = "Phonetic Extensions" },
+ ["phoneticextensionssupplement"] = { first = 0x01D80, last = 0x01DBF, description = "Phonetic Extensions Supplement" },
+ ["privateusearea"] = { first = 0x0E000, last = 0x0F8FF, description = "Private Use Area" },
+ ["rejang"] = { first = 0x0A930, last = 0x0A95F, description = "Rejang" },
+ ["runic"] = { first = 0x016A0, last = 0x016FF, description = "Runic" },
+ ["saurashtra"] = { first = 0x0A880, last = 0x0A8DF, description = "Saurashtra" },
+ ["shavian"] = { first = 0x10450, last = 0x1047F, description = "Shavian" },
+ ["sinhala"] = { first = 0x00D80, last = 0x00DFF, description = "Sinhala" },
+ ["smallformvariants"] = { first = 0x0FE50, last = 0x0FE6F, description = "Small Form Variants" },
+ ["spacingmodifierletters"] = { first = 0x002B0, last = 0x002FF, description = "Spacing Modifier Letters" },
+ ["specials"] = { first = 0x0FFF0, last = 0x0FFFF, description = "Specials" },
+ ["sundanese"] = { first = 0x01B80, last = 0x01BBF, description = "Sundanese" },
+ ["superscriptsandsubscripts"] = { first = 0x02070, last = 0x0209F, description = "Superscripts and Subscripts" },
+ ["supplementalarrowsa"] = { first = 0x027F0, last = 0x027FF, description = "Supplemental Arrows-A" },
+ ["supplementalarrowsb"] = { first = 0x02900, last = 0x0297F, description = "Supplemental Arrows-B" },
+ ["supplementalmathematicaloperators"] = { first = 0x02A00, last = 0x02AFF, description = "Supplemental Mathematical Operators" },
+ ["supplementalpunctuation"] = { first = 0x02E00, last = 0x02E7F, description = "Supplemental Punctuation" },
+ ["supplementaryprivateuseareaa"] = { first = 0xF0000, last = 0xFFFFF, description = "Supplementary Private Use Area-A" },
+ ["supplementaryprivateuseareab"] = { first = 0x100000,last = 0x10FFFF,description = "Supplementary Private Use Area-B" },
+ ["sylotinagri"] = { first = 0x0A800, last = 0x0A82F, description = "Syloti Nagri" },
+ ["syriac"] = { first = 0x00700, last = 0x0074F, description = "Syriac" },
+ ["tagalog"] = { first = 0x01700, last = 0x0171F, description = "Tagalog" },
+ ["tagbanwa"] = { first = 0x01760, last = 0x0177F, description = "Tagbanwa" },
+ ["tags"] = { first = 0xE0000, last = 0xE007F, description = "Tags" },
+ ["taile"] = { first = 0x01950, last = 0x0197F, description = "Tai Le" },
+ ["taixuanjingsymbols"] = { first = 0x1D300, last = 0x1D35F, description = "Tai Xuan Jing Symbols" },
+ ["tamil"] = { first = 0x00B80, last = 0x00BFF, description = "Tamil" },
+ ["telugu"] = { first = 0x00C00, last = 0x00C7F, description = "Telugu" },
+ ["thaana"] = { first = 0x00780, last = 0x007BF, description = "Thaana" },
+ ["thai"] = { first = 0x00E00, last = 0x00E7F, description = "Thai" },
+ ["tibetan"] = { first = 0x00F00, last = 0x00FFF, description = "Tibetan" },
+ ["tifinagh"] = { first = 0x02D30, last = 0x02D7F, description = "Tifinagh" },
+ ["ugaritic"] = { first = 0x10380, last = 0x1039F, description = "Ugaritic" },
+ ["unifiedcanadianaboriginalsyllabics"] = { first = 0x01400, last = 0x0167F, description = "Unified Canadian Aboriginal Syllabics" },
+ ["vai"] = { first = 0x0A500, last = 0x0A63F, description = "Vai" },
+ ["variationselectors"] = { first = 0x0FE00, last = 0x0FE0F, description = "Variation Selectors" },
+ ["variationselectorssupplement"] = { first = 0xE0100, last = 0xE01EF, description = "Variation Selectors Supplement" },
+ ["verticalforms"] = { first = 0x0FE10, last = 0x0FE1F, description = "Vertical Forms" },
+ ["yijinghexagramsymbols"] = { first = 0x04DC0, last = 0x04DFF, description = "Yijing Hexagram Symbols" },
+ ["yiradicals"] = { first = 0x0A490, last = 0x0A4CF, description = "Yi Radicals" },
+ ["yisyllables"] = { first = 0x0A000, last = 0x0A48F, description = "Yi Syllables" },
}
-setmetatable(characters.blocks, { __index = function(t,k)
+characters.blocks = blocks
+
+setmetatable(blocks, { __index = function(t,k)
return k and rawget(t,lower(gsub(k,"[^a-zA-Z]","")))
end } )
function characters.getrange(name) -- used in font fallback definitions (name or range)
- local range = characters.blocks[name]
+ local range = blocks[name]
if range then
- return range[1], range[2], range[3]
+ return range.first, range.last, range.description
end
name = gsub(name,'"',"0x") -- goodie: tex hex notation
local start, stop = match(name,"^(.-)[%-%:](.-)$")
@@ -506,11 +508,26 @@ function characters.define(tobelettered, tobeactivated) -- catcodetables
local contextname = chr.contextname
if contextname then
local category = chr.category
+--~ if is_character[category] then
+--~ if chr.unicodeslot < 128 then
+--~ texprint(ctxcatcodes,format("\\chardef\\%s=%s",contextname,u))
+--~ else
+--~ texprint(ctxcatcodes,format("\\let\\%s=%s",contextname,utfchar(u)))
+--~ end
+--~ elseif is_command[category] then
+--~ texsprint("{\\catcode",u,"=13\\unexpanded\\gdef ",utfchar(u),"{\\"..contextname,"}}") -- no texprint
+--~ a = a + 1
+--~ activated[a] = u
+--~ end
if is_character[category] then
if chr.unicodeslot < 128 then
- texprint(ctxcatcodes,format("\\chardef\\%s=%s",contextname,u))
+ if is_letter[category] then
+ texprint(ctxcatcodes,format("\\def\\%s{%s}",contextname,utfchar(u)))
+ else
+ texprint(ctxcatcodes,format("\\chardef\\%s=%s",contextname,u))
+ end
else
- texprint(ctxcatcodes,format("\\let\\%s=%s",contextname,utfchar(u)))
+ texprint(ctxcatcodes,format("\\def\\%s{%s}",contextname,utfchar(u)))
end
elseif is_command[category] then
texsprint("{\\catcode",u,"=13\\unexpanded\\gdef ",utfchar(u),"{\\"..contextname,"}}") -- no texprint
@@ -522,9 +539,9 @@ function characters.define(tobelettered, tobeactivated) -- catcodetables
end
if tobelettered then -- shared
- local saved = tex.catcodetable
- for i=1,#tobelettered do
- tex.catcodetable = tobelettered[i]
+ local saved = tex.catcodetable
+ for i=1,#tobelettered do
+ tex.catcodetable = tobelettered[i]
if trace_defining then
report_defining("defining letters (global, shared)")
end
@@ -541,8 +558,8 @@ function characters.define(tobelettered, tobeactivated) -- catcodetables
end
texsetcatcode(0x200C,11) -- non-joiner
texsetcatcode(0x200D,11) -- joiner
- end
- tex.catcodetable = saved
+ end
+ tex.catcodetable = saved
end
local nofactivated = #tobeactivated