Module:Unicode chart/display: Difference between revisions

Revision as of 21:09, 18 September 2019

Latest revision as of 03:40, 17 September 2022

(8 intermediate revisions by 2 users not shown)

Line 1:

--[[-----------------

return {

Values that look like meaningless pass-through assignments actually have the purpose of forcing a dashed box

on printable characters that otherwise would not be identified as needing one. This avoids setting up a second config table for the box status.

The character U+1F3F7 LABEL actually looks like the tags in the Tags block. At least according to the standard. Reality will vary by font. See:

* https://www.unicode.org/charts/PDF/U1F300.pdf

* https://www.unicode.org/charts/PDF/UE0000.pdf

--]]-----------------

local display = {

-- Basic Latin

[0x0000] = "NUL",

Line 70 ⟶ 81:

[0x00A0] = "NB SP",

[0x00AD] = "SHY -",

-- Latin Extended-A

-- Latin Extended-B

-- IPA Extensions

-- Spacing Modifier Letters

-- Combining Diacritical Marks

[0x034F] = "CGJ ◌",

-- Greek and Coptic

-- Cyrillic

-- Cyrillic Supplement

-- Armenian

-- Hebrew

-- Arabic

[0x0600] = mw.ustring.char(0x0600),

[0x0601] = mw.ustring.char(0x0601),

[0x0602] = mw.ustring.char(0x0602),

[0x0603] = mw.ustring.char(0x0603),

[0x0604] = mw.ustring.char(0x0604),

[0x0605] = mw.ustring.char(0x0605),

[0x061C] = "ALM",

[0x06DD] = mw.ustring.char(0x06DD),

-- Syriac

[0x070F] = mw.ustring.char(0x070F).." SAM",

-- Arabic SupplementExtended-B

[0x0890] = mw.ustring.char(0x0890),

[0x0891] = mw.ustring.char(0x0891),

-- Thaana

-- NKo

-- Samaritan

-- Mandaic

-- Syriac Supplement

-- Arabic Extended-A

[0x08E2] = mw.ustring.char(0x08E2),

-- Devanagari

-- Bengali

-- Gurmukhi

-- Gujarati

-- Oriya

-- Tamil

-- Telugu

-- Kannada

[0x0CF1] = mw.ustring.char(0x0CF1),

[0x0CF2] = mw.ustring.char(0x0CF2),

-- Malayalam

[0x0D4E] = mw.ustring.char(0x0D4E),

-- Sinhala

-- Thai

-- Lao

-- Tibetan

[0x0F0C] = mw.ustring.char(0x0F0C).." NB",

-- Myanmar

[0x1039] = mw.ustring.char(0x1039),

-- Georgian

-- Hangul Jamo

[0x115F] = "HC F",

[0x1160] = "HJ F",

-- Ethiopic

-- Ethiopic Supplement

-- Cherokee

-- Unified Canadian Aboriginal Syllabics

-- Ogham

[0x1680] = mw.ustring.char(0x1680),

-- Runic

-- Tagalog

-- Hanunoo

-- Buhid

-- Tagbanwa

-- Khmer

[0x17B4] = "KIV AQ",

[0x17B5] = "KIV AA",

[0x17D2] = mw.ustring.char(0x17D2),

-- Mongolian

[0x180B] = "FV S1",

[0x180C] = "FV S2",

-- Unified Canadian Aboriginal Syllabics Extended

[0x180D] = "FV S3",

[0x180E] = "MV S",

-- Limbu

[0x180F] = "FV S4",

-- Tai Le

-- New Tai Lue

-- Khmer Symbols

-- Buginese

-- Tai Tham

[0x1A60] = mw.ustring.char(0x1A60),

-- Combining Diacritical Marks Extended

-- Balinese

-- Sundanese

[0x1BAB] = mw.ustring.char(0x1BAB),

-- Batak

-- Lepcha

-- Ol Chiki

-- Cyrillic Extended-C

-- Georgian Extended

-- Sundanese Supplement

-- Vedic Extensions

[0x1CF5] = mw.ustring.char(0x1CF5),

[0x1CF6] = mw.ustring.char(0x1CF6),

-- Phonetic Extensions

-- Phonetic Extensions Supplement

-- Combining Diacritical Marks Supplement

-- Latin Extended Additional

-- Greek Extended

-- General Punctuation

[0x2000] = "NQ SP",

Line 235 ⟶ 157:

[0x202F] = "NNB SP",

[0x205F] = "MM SP",

[0x2060] = "WJ",

[0x2061] = "<i>ƒ</i><small>()</small>",

[0x2062] = "✕",

[0x2063] = ",",

[0x2064] = "+",

[0x2066] = "LRI",

[0x2067] = "RLI",

[0x2068] = "FSI",

[0x2069] = "PDI",

[0x206A] = "I SS",

[0x206B] = "A SS",

Line 245 ⟶ 172:

[0x206E] = "NA DS",

[0x206F] = "NO DS",

-- Superscripts and Subscripts

-- Currency Symbols

-- Combining Diacritical Marks for Symbols

-- Letterlike Symbols

-- Number Forms

-- Arrows

-- Mathematical Operators

-- Miscellaneous Technical

-- Control Pictures

-- Optical Character Recognition

-- Enclosed Alphanumerics

-- Box Drawing

-- Block Elements

-- Geometric Shapes

-- Miscellaneous Symbols

-- Dingbats

-- Miscellaneous Mathematical Symbols-A

-- Supplemental Arrows-A

-- Braille Patterns

-- Supplemental Arrows-B

-- Miscellaneous Mathematical Symbols-B

-- Supplemental Mathematical Operators

-- Miscellaneous Symbols and Arrows

-- Glagolitic

-- Latin Extended-C

-- Coptic

-- Georgian Supplement

-- Tifinagh

[0x2D7F] = mw.ustring.char(0x2D7F),

-- Ethiopic Extended

-- Cyrillic Extended-A

-- Supplemental Punctuation

[0x2E3A] = "2M"..mw.ustring.char(0x2E3A),

[0x2E3B] = "3M"..mw.ustring.char(0x2E3B),

-- CJK Radicals Supplement

-- Kangxi Radicals

-- Ideographic Description Characters

-- CJK Symbols and Punctuation

[0x3000] = "ID SP", --whitespace anyway

[0x303E] = mw.ustring.char(0x303E),

-- Hiragana

-- Katakana

-- Bopomofo

-- Hangul Compatibility Jamo

[0x3164] = "HF",

-- Kanbun

-- Bopomofo Extended

-- CJK Strokes

-- Katakana Phonetic Extensions

-- Enclosed CJK Letters and Months

-- CJK Compatibility

-- CJK Unified Ideographs Extension A

-- Yijing Hexagram Symbols

-- CJK Unified Ideographs

-- Yi Syllables

-- Yi Radicals

-- Lisu

-- Vai

-- Cyrillic Extended-B

-- Bamum

-- Modifier Tone Letters

-- Latin Extended-D

-- Syloti Nagri

-- Common Indic Number Forms

-- Phags-pa

-- Saurashtra

-- Devanagari Extended

-- Kayah Li

-- Rejang

-- Hangul Jamo Extended-A

-- Javanese

-- Myanmar Extended-B

-- Cham

-- Myanmar Extended-A

-- Tai Viet

-- Meetei Mayek Extensions

[0xAAF6] = mw.ustring.char(0xAAF6),

-- Ethiopic Extended-A

-- Latin Extended-E

-- Cherokee Supplement

-- Meetei Mayek

-- Hangul Syllables

-- Hangul Jamo Extended-B

-- High Surrogates

-- High Private Use Surrogates

-- Low Surrogates

-- Private Use Area

-- CJK Compatibility Ideographs

-- Alphabetic Presentation Forms

-- Arabic Presentation Forms-A

-- Variation Selectors

[0xFE00] = "VS 1",

[0xFE01] = "VS 2",

-- Vertical Forms

[0xFE02] = "VS 3",

[0xFE03] = "VS 4",

-- Combining Half Marks

[0xFE04] = "VS 5",

[0xFE05] = "VS 6",

-- CJK Compatibility Forms

[0xFE06] = "VS 7",

[0xFE07] = "VS 8",

-- Small Form Variants

[0xFE08] = "VS 9",

[0xFE09] = "VS 10",

[0xFE0A] = "VS 11",

[0xFE0B] = "VS 12",

[0xFE0C] = "VS 13",

[0xFE0D] = "VS 14",

[0xFE0E] = "VS 15",

[0xFE0F] = "VS 16",

-- Arabic Presentation Forms-B

[0xFEFF] = "ZWN BSP",

-- Halfwidth and Fullwidth Forms

[0xFFA0] = "HW HF",

-- Specials

[0xFFF9] = "IA A",

[0xFFFA] = "IA S",

-- Linear B Syllabary

[0xFFFB] = "IA T",

[0xFFFC] = "OBJ",

-- Linear B Ideograms

-- Aegean Numbers

-- Ancient Greek Numbers

-- Ancient Symbols

-- Phaistos Disc

-- Lycian

-- Carian

-- Coptic Epact Numbers

-- Old Italic

-- Gothic

-- Old Permic

-- Ugaritic

-- Old Persian

-- Deseret

-- Shavian

-- Osmanya

-- Osage

-- Elbasan

-- Caucasian Albanian

-- Linear A

-- Cypriot Syllabary

-- Imperial Aramaic

-- Palmyrene

-- Nabataean

-- Hatran

-- Phoenician

-- Lydian

-- Meroitic Hieroglyphs

-- Meroitic Cursive

-- Kharoshthi

[0x10A3F] = mw.ustring.char(0x10A3F),

-- Old South Arabian

-- Old North Arabian

-- Manichaean

-- Avestan

-- Inscriptional Parthian

-- Inscriptional Pahlavi

-- Psalter Pahlavi

-- Old Turkic

-- Old Hungarian

-- Hanifi Rohingya

-- Rumi Numeral Symbols

-- Old Sogdian

-- Sogdian

-- Elymaic

-- Brahmi

[0x11003] = mw.ustring.char(0x11003),

[0x11004] = mw.ustring.char(0x11004),

[0x1107F] = "BNJ",

-- Kaithi

[0x110BD] = mw.ustring.char(0x110BD),

[0x110CD] = mw.ustring.char(0x110CD),

-- Sora Sompeng

-- Chakma

[0x11133] = mw.ustring.char(0x11133),

-- Mahajani

-- Sharada

[0x111C2] = mw.ustring.char(0x111C2),

[0x111C3] = mw.ustring.char(0x111C3),

-- Sinhala Archaic Numbers

-- Khojki

-- Multani

-- Khudawadi

-- Grantha

-- Newa

[0x11460] = mw.ustring.char(0x11460),

[0x11461] = mw.ustring.char(0x11461),

-- Tirhuta

-- Dives Akuru

[0x1193E] = mw.ustring.char(0x1193E),

-- Siddham

[0x1193F] = mw.ustring.char(0x1193F),

[0x11941] = mw.ustring.char(0x11941),

-- Modi

-- Mongolian Supplement

-- Takri

-- Ahom

-- Dogra

-- Warang Citi

-- Nandinagari

-- Zanabazar Square

[0x11A3A] = mw.ustring.char(0x11A3A),

[0x11A47] = mw.ustring.char(0x11A47),

-- Soyombo

[0x11A84] = mw.ustring.char(0x11A84),

[0x11A85] = mw.ustring.char(0x11A85),

-- Pau Cin Hau

[0x11A86] = mw.ustring.char(0x11A86),

[0x11A87] = mw.ustring.char(0x11A87),

-- Bhaiksuki

[0x11A88] = mw.ustring.char(0x11A88),

[0x11A89] = mw.ustring.char(0x11A89),

-- Marchen

[0x11A99] = mw.ustring.char(0x11A99),

-- Masaram Gondi

[0x11D45] = mw.ustring.char(0x11D45),

[0x11D46] = mw.ustring.char(0x11D46),

-- Gunjala Gondi

[0x11D97] = mw.ustring.char(0x11D97),

-- MakasarKawi

[0x11F02] = mw.ustring.char(0x11F02),

[0x11F42] = mw.ustring.char(0x11F42),

-- Tamil Supplement

-- Cuneiform

-- Cuneiform Numbers and Punctuation

-- Early Dynastic Cuneiform

-- Egyptian Hieroglyphs

-- Egyptian Hieroglyph Format Controls

[0x13430] = mw.ustring.char(0x13430),

[0x13431] = mw.ustring.char(0x13431),

-- Anatolian Hieroglyphs

[0x13432] = mw.ustring.char(0x13432),

[0x13433] = mw.ustring.char(0x13433),

-- Bamum Supplement

[0x13434] = mw.ustring.char(0x13434),

[0x13435] = mw.ustring.char(0x13435),

-- Mro

[0x13436] = mw.ustring.char(0x13436),

[0x13437] = mw.ustring.char(0x13437),

-- Bassa Vah

[0x13438] = mw.ustring.char(0x13438),

[0x13439] = mw.ustring.char(0x13439),

-- Pahawh Hmong

[0x1343A] = mw.ustring.char(0x1343A),

[0x1343B] = mw.ustring.char(0x1343B),

-- Medefaidrin

[0x1343C] = mw.ustring.char(0x1343C),

[0x1343D] = mw.ustring.char(0x1343D),

[0x1343E] = mw.ustring.char(0x1343E),

[0x1343F] = mw.ustring.char(0x1343F),

[0x13440] = mw.ustring.char(0x13440),

[0x13441] = "FB",

[0x13442] = "HB",

[0x13447] = mw.ustring.char(0x13447),

[0x13448] = mw.ustring.char(0x13448),

[0x13449] = mw.ustring.char(0x13449),

[0x1344A] = mw.ustring.char(0x1344A),

[0x1344B] = mw.ustring.char(0x1344B),

[0x1344C] = mw.ustring.char(0x1344C),

[0x1344D] = mw.ustring.char(0x1344D),

[0x1344E] = mw.ustring.char(0x1344E),

[0x1344F] = mw.ustring.char(0x1344F),

[0x13450] = mw.ustring.char(0x13450),

[0x13451] = mw.ustring.char(0x13451),

[0x13452] = mw.ustring.char(0x13452),

[0x13453] = mw.ustring.char(0x13453),

[0x13454] = mw.ustring.char(0x13454),

[0x13455] = mw.ustring.char(0x13455),

-- Miao

[0x16F8F] = mw.ustring.char(0x16F8F),

[0x16F90] = mw.ustring.char(0x16F90),

[0x16F91] = mw.ustring.char(0x16F91),

[0x16F92] = mw.ustring.char(0x16F92),

-- Ideographic Symbols and Punctuation

[0x16FE4] = "KSS F",

-- Tangut

-- Tangut Components

-- Kana Supplement

-- Kana Extended-A

-- Small Kana Extension

-- Nushu

-- Duployan

[0x1BC9D] = "DT LS",

-- Shorthand Format Controls

[0x1BCA0] = mw.ustring.char(0x1BCA0),

[0x1BCA1] = mw.ustring.char(0x1BCA1),

-- Byzantine Musical Symbols

[0x1BCA2] = mw.ustring.char(0x1BCA2),

[0x1BCA3] = mw.ustring.char(0x1BCA3),

-- Musical Symbols

[0x1D159] = "NULL NOTE HEAD",

[0x1D173] = "BEGIN BEAM ",

[0x1D174] = "END BEAM",

[0x1D175] = "BEGIN TIE ",

[0x1D176] = "END TIE",

[0x1D177] = "BEGIN SLUR ",

[0x1D178] = "END SLUR",

[0x1D179] = "BEGIN PHR .",

[0x1D17A] = "END PHR.",

-- Ancient Greek Musical Notation

-- Mayan Numerals

-- Tai Xuan Jing Symbols

-- Counting Rod Numerals

-- Mathematical Alphanumeric Symbols

-- Sutton SignWriting

[0x1DA9B] = "SW F2",

[0x1DA9C] = "SW F3",

-- Glagolitic Supplement

[0x1DA9D] = "SW F4",

[0x1DA9E] = "SW F5",

-- Nyiakeng Puachue Hmong

[0x1DA9F] = "SW F6",

[0x1DAA1] = "SW R2",

-- Wancho

[0x1DAA2] = "SW R3",

[0x1DAA3] = "SW R4",

-- Mende Kikakui

[0x1DAA4] = "SW R5",

[0x1DAA5] = "SW R6",

-- Adlam

[0x1DAA6] = "SW R7",

[0x1DAA7] = "SW R8",

-- Indic Siyaq Numbers

[0x1DAA8] = "SW R9",

[0x1DAA9] = "SW R10",

-- Ottoman Siyaq Numbers

[0x1DAAA] = "SW R11",

[0x1DAAB] = "SW R12",

-- Arabic Mathematical Alphabetic Symbols

[0x1DAAC] = "SW R13",

[0x1DAAD] = "SW R14",

-- Mahjong Tiles

[0x1DAAE] = "SW R15",

[0x1DAAF] = "SW R16",

-- Domino Tiles

-- Playing Cards

-- Enclosed Alphanumeric Supplement

[0x1F1E6] = mw.ustring.char(0x1F1E6),

[0x1F1E7] = mw.ustring.char(0x1F1E7),

-- Enclosed Ideographic Supplement

[0x1F1E8] = mw.ustring.char(0x1F1E8),

[0x1F1E9] = mw.ustring.char(0x1F1E9),

-- Miscellaneous Symbols and Pictographs

[0x1F1EA] = mw.ustring.char(0x1F1EA),

[0x1F1EB] = mw.ustring.char(0x1F1EB),

-- Emoticons

[0x1F1EC] = mw.ustring.char(0x1F1EC),

[0x1F1ED] = mw.ustring.char(0x1F1ED),

-- Ornamental Dingbats

[0x1F1EE] = mw.ustring.char(0x1F1EE),

[0x1F1EF] = mw.ustring.char(0x1F1EF),

-- Transport and Map Symbols

[0x1F1F0] = mw.ustring.char(0x1F1F0),

[0x1F1F1] = mw.ustring.char(0x1F1F1),

-- Alchemical Symbols

[0x1F1F2] = mw.ustring.char(0x1F1F2),

[0x1F1F3] = mw.ustring.char(0x1F1F3),

-- Geometric Shapes Extended

[0x1F1F4] = mw.ustring.char(0x1F1F4),

[0x1F1F5] = mw.ustring.char(0x1F1F5),

-- Supplemental Arrows-C

[0x1F1F6] = mw.ustring.char(0x1F1F6),

[0x1F1F7] = mw.ustring.char(0x1F1F7),

-- Supplemental Symbols and Pictographs

[0x1F1F8] = mw.ustring.char(0x1F1F8),

[0x1F1F9] = mw.ustring.char(0x1F1F9),

-- Chess Symbols

[0x1F1FA] = mw.ustring.char(0x1F1FA),

[0x1F1FB] = mw.ustring.char(0x1F1FB),

-- Symbols and Pictographs Extended-A

[0x1F1FC] = mw.ustring.char(0x1F1FC),

[0x1F1FD] = mw.ustring.char(0x1F1FD),

-- CJK Unified Ideographs Extension B

[0x1F1FE] = mw.ustring.char(0x1F1FE),

[0x1F1FF] = mw.ustring.char(0x1F1FF),

-- CJK Unified Ideographs Extension C

}

-- CJK Unified Ideographs Extension D

-- CJK Unified Ideographs Extension E

-- CJK Unified Ideographs Extension F

-- CJK Compatibility Ideographs Supplement

-- Tags

local tag = ' '..mw.ustring.char(0x1F3F7)

display[0xE0001] = "BEGIN"..tag

display[0xE0020] = "SP"..tag

for n = 0xE0021,0xE007F do display[n] = (string.char(n-0xE0000)..tag) end

-- Variation Selectors Supplement

for n = 0xE0100,0x0E01EF do display[n] = "VS "..(n-0xE00EF) end

return display

-- Supplementary Private Use Area-A

-- Supplementary Private Use Area-B

}

-- {{list-stub}}