From 50f65a5ef0fe343ba54c547284043a3561cab734 Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Fri, 12 Sep 2025 09:28:10 +0100 Subject: [PATCH 1/8] Some more Unicode 17 --- Compose | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++++- Compose.md | 18 +++++----- README.md | 2 +- 3 files changed, 112 insertions(+), 11 deletions(-) diff --git a/Compose b/Compose index 1f04361..32e01a8 100644 --- a/Compose +++ b/Compose @@ -1040,6 +1040,8 @@ include "%L" : "Ꭓ" UA7B3 # LATIN CAPITAL LETTER CHI : "Ʀ" U01A6 # LATIN LETTER YR : "Ʒ" U01B7 # LATIN CAPITAL LETTER EZH + : "꟎" UA7CE # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE + : "꟏" UA7CF # LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE # various other letters @@ -1083,6 +1085,7 @@ include "%L" : "ꟙ" UA7D9 # LATIN SMALL LETTER SIGMOID S : "Ꟗ" UA7D6 # LATIN CAPITAL LETTER MIDDLE SCOTS S : "ꟗ" UA7D7 # LATIN SMALL LETTER MIDDLE SCOTS S + <2> : "꟒" UA7D2 # LATIN CAPITAL LETTER DOUBLE THORN <2> : "ꟓ" UA7D3 # LATIN SMALL LETTER DOUBLE THORN : "Ȣ" U0222 # LATIN CAPITAL LETTER OU (conflicts with Ū, use -U or U-) : "ȣ" U0223 # LATIN SMALL LETTER OU (conflicts with ū, use -u or u-) @@ -1092,6 +1095,7 @@ include "%L" : "ꝩ" UA769 # LATIN SMALL LETTER VEND (not ideal, but vn=ň is taken) : "Ƿ" U01F7 # LATIN CAPITAL LETTER WYNN : "ƿ" U01BF # LATIN LETTER WYNN + <2> : "꟔" UA7D4 # LATIN CAPITAL LETTER DOUBLE WYNN <2> : "ꟕ" UA7D5 # LATIN SMALL LETTER DOUBLE WYNN : "ꭐ" UAB50 # LATIN SMALL LETTER UI : "ꭑ" UAB51 # LATIN SMALL LETTER TURNED UI @@ -1652,6 +1656,7 @@ include "%L"

: "ᴾ" U1D3E # MODIFIER LETTER CAPITAL P : "ꟴ" UA7F4 # MODIFIER LETTER CAPITAL Q : "ᴿ" U1D3F # MODIFIER LETTER CAPITAL R + : "꟱" UA7F1 # MODIFIER LETTER CAPITAL S : "ᵀ" U1D40 # MODIFIER LETTER CAPITAL T : "ᵁ" U1D41 # MODIFIER LETTER CAPITAL U : "ⱽ" U2C7D # MODIFIER LETTER CAPITAL V @@ -4353,6 +4358,7 @@ include "%L" : "ݨ" U0768 # ARABIC LETTER NOON WITH SMALL TAH : "ݩ" U0769 # ARABIC LETTER NOON WITH SMALL V : "ࢉ" U0889 # ARABIC LETTER NOON WITH INVERTED SMALL V + : "࢏" U088F # ARABIC LETTER NOON WITH RING ABOVE : "ۿ" U06FF # ARABIC LETTER HEH WITH INVERTED V : "ۀ" U06C0 # ARABIC LETTER HEH WITH YEH ABOVE @@ -8796,6 +8802,8 @@ include "%L" : "ೱ" U0CF1 # KANNADA SIGN JIHVAMULIYA : "ೲ" U0CF2 # KANNADA SIGN UPADHMANIYA + : "೜" U0CDC # KANNADA ARCHAIC SHRII + # Numerals <0> : "೦" U0CE6 # KANNADA DIGIT ZERO @@ -10647,6 +10655,14 @@ include "%L" : "𑆎" U1118E # SHARADA LETTER AI : "𑆏" U1118F # SHARADA LETTER O : "𑆐" U11190 # SHARADA LETTER AU + : "𑭠" U11B60 # SHARADA VOWEL SIGN OE + : "𑭡" U11B61 # SHARADA VOWEL SIGN OOE + : "𑭢" U11B62 # SHARADA VOWEL SIGN UE + : "𑭣" U11B63 # SHARADA VOWEL SIGN UUE + : "𑭤" U11B64 # SHARADA VOWEL SIGN SHORT E + : "𑭥" U11B65 # SHARADA VOWEL SIGN SHORT O + : "𑭦" U11B66 # SHARADA VOWEL SIGN CANDRA E + : "𑭧" U11B67 # SHARADA VOWEL SIGN CANDRA O # Dependent vowels @@ -11126,6 +11142,8 @@ include "%L" : "ఽ" U0C3D # TELUGU SIGN AVAGRAHA : "౷" U0C77 # TELUGU SIGN SIDDHAM + : "౜" U0C5C # TELUGU ARCHAIC SHRII + # Numerals <0> : "౦" U0C66 # TELUGU DIGIT ZERO @@ -13482,6 +13500,60 @@ include "%L" : "ᙆ" U1646 # CANADIAN SYLLABICS CARRIER Z : "ᙇ" U1647 # CANADIAN SYLLABICS CARRIER INITIAL Z +# (b/B = Beria) + + : "𖺠" U16EA0 # BERIA ERFE CAPITAL LETTER ARKAB + : "𖺡" U16EA1 # BERIA ERFE CAPITAL LETTER BASIGNA + : "𖺢" U16EA2 # BERIA ERFE CAPITAL LETTER DARBAI + : "𖺣" U16EA3 # BERIA ERFE CAPITAL LETTER EH + : "𖺤" U16EA4 # BERIA ERFE CAPITAL LETTER FITKO + : "𖺥" U16EA5 # BERIA ERFE CAPITAL LETTER GOWAY + : "𖺦" U16EA6 # BERIA ERFE CAPITAL LETTER HIRDEABO + : "𖺧" U16EA7 # BERIA ERFE CAPITAL LETTER I + : "𖺨" U16EA8 # BERIA ERFE CAPITAL LETTER DJAI + : "𖺩" U16EA9 # BERIA ERFE CAPITAL LETTER KOBO + : "𖺪" U16EAA # BERIA ERFE CAPITAL LETTER LAKKO + : "𖺫" U16EAB # BERIA ERFE CAPITAL LETTER MERI + : "𖺬" U16EAC # BERIA ERFE CAPITAL LETTER NINI + : "𖺭" U16EAD # BERIA ERFE CAPITAL LETTER GNA + : "𖺮" U16EAE # BERIA ERFE CAPITAL LETTER NGAY + : "𖺯" U16EAF # BERIA ERFE CAPITAL LETTER OI +

: "𖺰" U16EB0 # BERIA ERFE CAPITAL LETTER PI + : "𖺱" U16EB1 # BERIA ERFE CAPITAL LETTER ERIGO + : "𖺲" U16EB2 # BERIA ERFE CAPITAL LETTER ERIGO TAMURA + : "𖺳" U16EB3 # BERIA ERFE CAPITAL LETTER SERI + : "𖺴" U16EB4 # BERIA ERFE CAPITAL LETTER SHEP + : "𖺵" U16EB5 # BERIA ERFE CAPITAL LETTER TATASOUE + : "𖺶" U16EB6 # BERIA ERFE CAPITAL LETTER UI + : "𖺷" U16EB7 # BERIA ERFE CAPITAL LETTER WASSE + : "𖺸" U16EB8 # BERIA ERFE CAPITAL LETTER AY + + : "𖺻" U16EBB # BERIA ERFE SMALL LETTER ARKAB + : "𖺼" U16EBC # BERIA ERFE SMALL LETTER BASIGNA + : "𖺽" U16EBD # BERIA ERFE SMALL LETTER DARBAI + : "𖺾" U16EBE # BERIA ERFE SMALL LETTER EH + : "𖺿" U16EBF # BERIA ERFE SMALL LETTER FITKO + : "𖻀" U16EC0 # BERIA ERFE SMALL LETTER GOWAY + : "𖻁" U16EC1 # BERIA ERFE SMALL LETTER HIRDEABO + : "𖻂" U16EC2 # BERIA ERFE SMALL LETTER I + : "𖻃" U16EC3 # BERIA ERFE SMALL LETTER DJAI + : "𖻄" U16EC4 # BERIA ERFE SMALL LETTER KOBO + : "𖻅" U16EC5 # BERIA ERFE SMALL LETTER LAKKO + : "𖻆" U16EC6 # BERIA ERFE SMALL LETTER MERI + : "𖻇" U16EC7 # BERIA ERFE SMALL LETTER NINI + : "𖻈" U16EC8 # BERIA ERFE SMALL LETTER GNA + : "𖻉" U16EC9 # BERIA ERFE SMALL LETTER NGAY + : "𖻊" U16ECA # BERIA ERFE SMALL LETTER OI +

: "𖻋" U16ECB # BERIA ERFE SMALL LETTER PI + : "𖻌" U16ECC # BERIA ERFE SMALL LETTER ERIGO + : "𖻍" U16ECD # BERIA ERFE SMALL LETTER ERIGO TAMURA + : "𖻎" U16ECE # BERIA ERFE SMALL LETTER SERI + : "𖻏" U16ECF # BERIA ERFE SMALL LETTER SHEP + : "𖻐" U16ED0 # BERIA ERFE SMALL LETTER TATASOUE + : "𖻑" U16ED1 # BERIA ERFE SMALL LETTER UI + : "𖻒" U16ED2 # BERIA ERFE SMALL LETTER WASSE + : "𖻓" U16ED3 # BERIA ERFE SMALL LETTER AY + # (c = Carrier Syllabics) see https://www.ydli.org/dakinfo/dulkwah.htm : "ᐁ" U1401 # CANADIAN SYLLABICS E @@ -15976,7 +16048,7 @@ include "%L" # (g) Greek (and other nearby scripts) # ######################################## -# covers Coptic, Cypriot, Elbasan, Gothic, Linear B, Lycian, Todhri & Vithkuqi +# covers Coptic, Cypriot, Elbasan, Gothic, Linear B, Lycian, Sidetic, Todhri & Vithkuqi : "Α" U0391 # GREEK CAPITAL LETTER ALPHA : "Β" U0392 # GREEK CAPITAL LETTER BETA @@ -16636,6 +16708,35 @@ include "%L" : "𐊛" U1029B # LYCIAN LETTER H : "𐊜" U1029C # LYCIAN LETTER X +# (s = Sidetic) + + : "𐥀" U10940 # SIDETIC LETTER N01 + : "𐥁" U10941 # SIDETIC LETTER N02 + : "𐥂" U10942 # SIDETIC LETTER N03 + : "𐥃" U10943 # SIDETIC LETTER N04 + : "𐥄" U10944 # SIDETIC LETTER N05 + : "𐥅" U10945 # SIDETIC LETTER N06 + : "𐥆" U10946 # SIDETIC LETTER N07 +

: "𐥇" U10947 # SIDETIC LETTER N08 + : "𐥈" U10948 # SIDETIC LETTER N09 (d2) + : "𐥉" U10949 # SIDETIC LETTER N10 + : "𐥊" U1094A # SIDETIC LETTER N11 + : "𐥋" U1094B # SIDETIC LETTER N12 + <8> : "𐥌" U1094C # SIDETIC LETTER N13 (θ) + : "𐥍" U1094D # SIDETIC LETTER N14 + : "𐥎" U1094E # SIDETIC LETTER N15 (s2) + : "𐥏" U1094F # SIDETIC LETTER N16 + : "𐥐" U10950 # SIDETIC LETTER N17 + : "𐥑" U10951 # SIDETIC LETTER N18 (𐌣) + : "𐥒" U10952 # SIDETIC LETTER N19 + : "𐥓" U10953 # SIDETIC LETTER N20 (χ) + : "𐥔" U10954 # SIDETIC LETTER N21 + : "𐥕" U10955 # SIDETIC LETTER N22 + : "𐥖" U10956 # SIDETIC LETTER N23 + : "𐥗" U10957 # SIDETIC LETTER N24 + : "𐥘" U10958 # SIDETIC LETTER N25 + : "𐥙" U10959 # SIDETIC LETTER N26 + # (p/P = Coptic) (not the best abbreviation, but think gp = egyptian)

: "Ⲁ" U2C80 # COPTIC CAPITAL LETTER ALFA diff --git a/Compose.md b/Compose.md index 9424590..dfa16cb 100644 --- a/Compose.md +++ b/Compose.md @@ -3,7 +3,7 @@ > Link: https://github.com/Udzu/xcompose/blob/master/Compose -This repo also hosts my personal .XCompose file, which contains over 48 000 memorable compose key sequences. To use them, copy all or parts of the config into your ~/.XCompose file. You can browse the sequences either directly in the config or using the [xcompose](https://github.com/Udzu/xcompose/) utility. Note that the shortcuts for Hangul syllables and logograms are in separate files. +This repo also hosts my personal .XCompose file, which contains over 49 000 memorable compose key sequences. To use them, copy all or parts of the config into your ~/.XCompose file. You can browse the sequences either directly in the config or using the [xcompose](https://github.com/Udzu/xcompose/) utility. Note that the shortcuts for Hangul syllables and logograms are in separate files. The file aims for memorability and consistency. As a result, a small number of the rules here conflict with the default system rules, with workarounds given in the comments (e.g. \'s usefulness for subscripting often interferes with its system use for macrons, for which \ works equally well as an alternative). @@ -19,25 +19,25 @@ The file aims for memorability and consistency. As a result, a small number of t * **Combining diacritics** (190): ń n̊ n̫ m͡n Zǎ̺̣͆̚l⃪ğ̶̍ö̱̰̥̂̃ etc * **Control characters** (272): RLI PDI ZWJ VS16 etc -### Latin script characters (2763) +### Latin script characters (2768) * **International Phonetic Alphabet** (143): ⫽ˈɹɛ.dɪt⫽ [aɪ̯ pʰiː eɪ̯] etc -* **Latin script letters** (514): Ƿ Ȝ ␢ ȵ etc +* **Latin script letters** (518): Ƿ Ȝ ␢ ȵ etc * **Mathematical alphanumerics** (796): 𝐀 𝐴 𝑨 A 𝗔 𝘈 𝘼 𝒜 𝓐 𝔄 𝕬 𝙰 𝔸 𜳖 etc * **Enclosed alphanumerics** (293): ⓼ 🅛 🆛 ⒜ ⒓ etc -* **Superscripts and subscripts** (310): ᵃ ᴬ ₐ ᴀ ◌ͣ etc +* **Superscripts and subscripts** (311): ᵃ ᴬ ₐ ᴀ ◌ͣ etc * **Multigraphs and ligatures** (392): ʣ ㏈ etc * **Letter games** (315): ʇᴉppǝɹ ɟibbɘר டωᓀᓀ·–⟝ etc -### Non-Latin script characters (36172) -* **Arabic**, Old North Arabian, Old South Arabian, Avestan, Chorasmian, Hatran, Mandaic, Manichaean, Nabatean, Old Persian, Osmanya, Inscriptional Pahlavi, Psalter Pahlavi, Inscriptional Parthian, Hanifi Rohingya, Old Sogdian, Sogdian, Syriac, Neo-Tifinagh, Thaana, Old Uyghur & Yezidi (2267): ⁧رِيدِتْ⁩, ⁧𐪇𐪕𐪉⁩, ⁧𐬭𐬈𐬛𐬌𐬙⁩, ⁧𐩧𐩵𐩩⁩, ⁧𐿂𐾴𐾺𐿄⁩, ⁧𐣣𐣣𐣩𐣵⁩, ⁧ࡓࡏࡃࡉࡕ⁩, ⁧𐫡𐫅𐫏𐫤⁩, ⁧𐢛𐢅𐢍𐢞⁩, 𐎼𐎡𐎮𐎡𐎫, 𐒇𐒗𐒆𐒘𐒂, ⁧𐭥𐭣𐭩𐭲⁩, ⁧𐮅𐮃𐮈𐮑⁩, ⁧𐴌𐴠𐴊𐴞𐴃⁩, ⁧𐭓𐭃𐭉𐭕⁩, ⁧𐼘𐼘𐼊𐼚⁩, ⁧𐽀𐼲𐼷𐽂⁩, ⁧ܪܕ݁ܝܬ݁⁩, ⵔⴻⴷⴷⵉⵜ, ⁧ރެދިތް⁩, ⁧𐽾𐽲𐽶𐾀⁩, ⁧𐺎𐺩𐺋𐺨𐺕⁩ etc +### Non-Latin script characters (36259) +* **Arabic**, Old North Arabian, Old South Arabian, Avestan, Chorasmian, Hatran, Mandaic, Manichaean, Nabatean, Old Persian, Osmanya, Inscriptional Pahlavi, Psalter Pahlavi, Inscriptional Parthian, Hanifi Rohingya, Old Sogdian, Sogdian, Syriac, Neo-Tifinagh, Thaana, Old Uyghur & Yezidi (2268): ⁧رِيدِتْ⁩, ⁧𐪇𐪕𐪉⁩, ⁧𐬭𐬈𐬛𐬌𐬙⁩, ⁧𐩧𐩵𐩩⁩, ⁧𐿂𐾴𐾺𐿄⁩, ⁧𐣣𐣣𐣩𐣵⁩, ⁧ࡓࡏࡃࡉࡕ⁩, ⁧𐫡𐫅𐫏𐫤⁩, ⁧𐢛𐢅𐢍𐢞⁩, 𐎼𐎡𐎮𐎡𐎫, 𐒇𐒗𐒆𐒘𐒂, ⁧𐭥𐭣𐭩𐭲⁩, ⁧𐮅𐮃𐮈𐮑⁩, ⁧𐴌𐴠𐴊𐴞𐴃⁩, ⁧𐭓𐭃𐭉𐭕⁩, ⁧𐼘𐼘𐼊𐼚⁩, ⁧𐽀𐼲𐼷𐽂⁩, ⁧ܪܕ݁ܝܬ݁⁩, ⵔⴻⴷⴷⵉⵜ, ⁧ރެދިތް⁩, ⁧𐽾𐽲𐽶𐾀⁩, ⁧𐺎𐺩𐺋𐺨𐺕⁩ etc * **Armenian** (95): Րեդդիտ etc -* **Brahmic scripts**: Ahom, Bengali, Bhaiksuki, Brahmi, Burmese, Chakma, Devanagari, Dives Akuru, Dogra, Grantha, Gujala Gondi, Gujarati, Gurmukhi, Gurung Khema, Kaithi, Kannada, Kawi, Kharoshthi, Khojki, Khudawadi, Kirat Rai, Lepcha, Limbu, Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meitei, Modi, Multani, Nandinagari, Newa, Odia, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Sylheti Nagri, Takri, Tamil, Telugu, Tigalari, Tirhuta (3608): 𑜍𑜦𑜔𑜢𑜌𑜫, রেডিট, 𑰨𑰸𑰠𑰰𑰞, 𑀭𑁂𑀟𑀺𑀝, ရေဍိဋ္, 𑄢𑄬𑄘𑄨𑄖𑄳, रेडिट, 𑤧𑤵𑤞𑤱𑤜𑤽, 𑠤𑠳𑠜𑠭𑠚, 𑌰𑍇𑌧𑌿𑌥, 𑶈𑶐𑵹𑶋𑵴𑶗, રેડિટ, ਰੇਡਿਟ, 𖄛𖄣𖄓𖄟𖄑, 𑂩𑂵𑂡𑂱𑂟, ರೆಡಿತ್, ⁧𐨪𐨅𐨢𐨁𐨠⁩, 𑈦𑈰𑈝𑈭𑈚, 𑋙𑋥𑋐𑋡𑋎, 𖵝𖵧𖵕𖵤𖵓, ᰛᰬᰌᰧᰳ, ᤖᤧᤍᤡᤳ, 𑅭𑅓𑅦𑅑𑅟, രെഡിട്, 𑲊𑲳𑱼𑲱𑱻, 𑴦𑴺𑴞𑴲𑴜, ꯔꯦꯗꯤꯠ, 𑘨𑘹𑘠𑘱𑘞, 𑊢𑊃𑊙𑊁𑊗, 𑧈𑧚𑧀𑧒𑦾, 𑐬𑐾𑐢𑐶𑐠, ରେଡିଟ, ꢬꢾꢞꢶꢜ, 𑆫𑆼𑆣𑆴𑆡, 𑖨𑖸𑖠𑖰𑖞, රෙඩිට්, ꠞꠦꠗꠤꠕ, 𑚤𑚲𑚜𑚮𑚚, ரெடிட், రెడిట్, 𑎬𑏂𑎤𑎹𑎢, 𑒩𑒺𑒡𑒱𑒟 etc +* **Brahmic scripts**: Ahom, Bengali, Bhaiksuki, Brahmi, Burmese, Chakma, Devanagari, Dives Akuru, Dogra, Grantha, Gujala Gondi, Gujarati, Gurmukhi, Gurung Khema, Kaithi, Kannada, Kawi, Kharoshthi, Khojki, Khudawadi, Kirat Rai, Lepcha, Limbu, Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meitei, Modi, Multani, Nandinagari, Newa, Odia, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Sylheti Nagri, Takri, Tamil, Telugu, Tigalari, Tirhuta (3618): 𑜍𑜦𑜔𑜢𑜌𑜫, রেডিট, 𑰨𑰸𑰠𑰰𑰞, 𑀭𑁂𑀟𑀺𑀝, ရေဍိဋ္, 𑄢𑄬𑄘𑄨𑄖𑄳, रेडिट, 𑤧𑤵𑤞𑤱𑤜𑤽, 𑠤𑠳𑠜𑠭𑠚, 𑌰𑍇𑌧𑌿𑌥, 𑶈𑶐𑵹𑶋𑵴𑶗, રેડિટ, ਰੇਡਿਟ, 𖄛𖄣𖄓𖄟𖄑, 𑂩𑂵𑂡𑂱𑂟, ರೆಡಿತ್, ⁧𐨪𐨅𐨢𐨁𐨠⁩, 𑈦𑈰𑈝𑈭𑈚, 𑋙𑋥𑋐𑋡𑋎, 𖵝𖵧𖵕𖵤𖵓, ᰛᰬᰌᰧᰳ, ᤖᤧᤍᤡᤳ, 𑅭𑅓𑅦𑅑𑅟, രെഡിട്, 𑲊𑲳𑱼𑲱𑱻, 𑴦𑴺𑴞𑴲𑴜, ꯔꯦꯗꯤꯠ, 𑘨𑘹𑘠𑘱𑘞, 𑊢𑊃𑊙𑊁𑊗, 𑧈𑧚𑧀𑧒𑦾, 𑐬𑐾𑐢𑐶𑐠, ରେଡିଟ, ꢬꢾꢞꢶꢜ, 𑆫𑆼𑆣𑆴𑆡, 𑖨𑖸𑖠𑖰𑖞, රෙඩිට්, ꠞꠦꠗꠤꠕ, 𑚤𑚲𑚜𑚮𑚚, ரெடிட், రెడిట్, 𑎬𑏂𑎤𑎹𑎢, 𑒩𑒺𑒡𑒱𑒟 etc * **Braille**, UEB (272): ⠗⠫⠙⠊⠞ etc -* **ConScripts**: Carrier, Cherokee, Cree, Deseret, Inuktitut, Kayah Li, Mefeidrin, Mundari Bani, Mru, Nyiakeng Puachue Hmong, Ol Chiki, Old Onal, Osage, Pahawh Hmong, Pau Cin Hau, Shavian, Sloan-Duployan, Sora Sompeng, Sunuwar, Tangsa, Toto, Wancho & Warang Citi (2279): ᘥᑔᐪ, ᎴᏗᏛ, ᕃᑎᑦ, 𐐡𐐇𐐔𐐆𐐓, ᕃᑎᑦ, ꤚꤢꤧꤘꤤꤒ, 𖹜𖹯𖹹𖹹𖹫𖹨, 𞓣𞓤𞓡𞓚𞓝, 𖩓𖩘𖩅𖩊𖩀, 𞄣𞄪𞄏𞄦𞄃, ᱨᱮᱫᱫᱤᱛ, 𞗧𞗨𞗠𞗜𞗝, 𐒴𐓟𐓵𐓣𐓰, 𖬡𖬉𖬰𖬞𖬰𖬃𖬰𖬧𖬵, 𑫒𑫖𑫄𑫗𑫎, 𐑮𐑧𐑛𐑦𐑑, 𛰋𛱌𛰍, 𑃝𑃣𑃔𑃤𑃑, 𑯄𑯂𑯀𑯃𑯁, 𖪲𖪔𖪱𖪏𖪰, 𞊟𞊦𞊓𞊡𞊒, 𞋗𞋛𞋄𞋜𞋋, 𑢼𑣈𑣔𑣂𑣕 etc +* **ConScripts**: Beria, Carrier, Cherokee, Cree, Deseret, Inuktitut, Kayah Li, Mefeidrin, Mundari Bani, Mru, Nyiakeng Puachue Hmong, Ol Chiki, Old Onal, Osage, Pahawh Hmong, Pau Cin Hau, Shavian, Sloan-Duployan, Sora Sompeng, Sunuwar, Tangsa, Toto, Wancho & Warang Citi (2329): 𖺱𖺾𖺽𖻂𖻐, ᘥᑔᐪ, ᎴᏗᏛ, ᕃᑎᑦ, 𐐡𐐇𐐔𐐆𐐓, ᕃᑎᑦ, ꤚꤢꤧꤘꤤꤒ, 𖹜𖹯𖹹𖹹𖹫𖹨, 𞓣𞓤𞓡𞓚𞓝, 𖩓𖩘𖩅𖩊𖩀, 𞄣𞄪𞄏𞄦𞄃, ᱨᱮᱫᱫᱤᱛ, 𞗧𞗨𞗠𞗜𞗝, 𐒴𐓟𐓵𐓣𐓰, 𖬡𖬉𖬰𖬞𖬰𖬃𖬰𖬧𖬵, 𑫒𑫖𑫄𑫗𑫎, 𐑮𐑧𐑛𐑦𐑑, 𛰋𛱌𛰍, 𑃝𑃣𑃔𑃤𑃑, 𑯄𑯂𑯀𑯃𑯁, 𖪲𖪔𖪱𖪏𖪰, 𞊟𞊦𞊓𞊡𞊒, 𞋗𞋛𞋄𞋜𞋋, 𑢼𑣈𑣔𑣂𑣕 etc * **Cyrillic**, Glagolitic & Old Permic (680): Ре́ддит, Ⱃⰵδδιτ, 𐍠𐍔𐍓𐍓𐍙𐍢 etc * **Geʽez**, Adlam, Bamum, Bassa Vah, Garay, Mende Kikakui, Meroitic Cursive & Hieroglyphic, NKo & Vai (2074): ሬዲተ, ⁧𞤈𞤫𞤣𞤭𞤼⁩, ꚥꛤꛤ꛱, 𖫦𖫬𖫗𖫭𖫡, ⁧𐵞𐵩𐵺𐵋𐵽⁩, ⁧𞠺𞠾𞡊⁩, ⁧𐦫𐦪𐦷𐦢𐦴⁩, ⁧𐦎𐦁𐦝𐦂𐦘⁩, ⁧ߙߍߘߘߌߕ⁩, ꗸꔹꗋ etc * **Georgian** & Caucasian Albanian (227): რედდიტ, ႰႤႣႣႨႲ, 𐕙𐔴𐔳𐔳𐔼𐔸 etc -* **Greek**, Coptic, Cypriot, Elbasan, Gothic, Linear B, Lycian, Todhri & Vithkuqi (1221): Ρέντιτ, Ⲣⲉⲇⲇⲓⲧ, ⁧𐠤𐠯𐠮⁩, 𐔙𐔇𐔄𐔍𐔝, 𐍂𐌴𐌳𐌳𐌹𐍄, 𐀩𐀇𐀵, 𐊕𐊁𐊅𐊅𐊆𐊗, 𐗝𐗉𐗆𐗒𐗢, 𐖊𐖞𐖜𐖜𐖥𐖵 etc +* **Greek**, Coptic, Cypriot, Elbasan, Gothic, Linear B, Lycian, Sidetic, Todhri & Vithkuqi (1247): Ρέντιτ, Ⲣⲉⲇⲇⲓⲧ, ⁧𐠤𐠯𐠮⁩, 𐔙𐔇𐔄𐔍𐔝, 𐍂𐌴𐌳𐌳𐌹𐍄, 𐀩𐀇𐀵, 𐊕𐊁𐊅𐊅𐊆𐊗, ⁧𐥔𐥁𐥋𐥂𐥊⁩, 𐗝𐗉𐗆𐗒𐗢, 𐖊𐖞𐖜𐖜𐖥𐖵 etc * **Hebrew**, Aramaic, Elymaic, Lydian, Palmyrene, Phoenician, Samaritan & Ugaritic (372): ⁧רֶדִיט⁩, ⁧𐡓𐡃𐡉𐡕⁩, ⁧𐿳𐿣𐿵⁩, ⁧𐤭𐤤𐤣𐤣𐤦𐤯⁩, ⁧𐡴𐡣𐡩𐡶⁩, ⁧𐤓𐤃𐤕⁩, ⁧ࠓࠝࠃࠪࠕ⁩, 𐎗𐎄𐎚 etc * **Japanese** (mostly kana) (916): 「レディット」 etc * **Kawi Scripts**: Balinese, Batak, Baybayin, Buginese, Buhid, Hanunoo, Javanese, Old Kawi, Makasar, Rejang, Sundanese & Tagbanwa (583): ᬭᬾᬤᬶᬢ᭄, ᯒᯧᯑᯪᯖ᯲, ᜍᜒᜇᜒᜆ᜔, ᨑᨙᨉᨗ, ᝍᝒᝇᝒ, ᜭᜲᜧᜲᜦ᜴, ꦫꦺꦢꦶꦠ, 𑼬𑼾𑼤𑼶𑼢, 𑻭𑻵𑻧𑻳, ꤽꥉꤴꥇꤳ, ᮛᮨᮓᮤᮒ᮪, ᝮᝲᝧᝲ, etc diff --git a/README.md b/README.md index 3ef3f3a..40cb3c9 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ Simple utilities to help configure X11 compose key sequences. -> The repo also hosts a very extensive [.XCompose file](Compose) with over 48 000 new sequences; [more details here](Compose.md). +> The repo also hosts a very extensive [.XCompose file](Compose) with over 49 000 new sequences; [more details here](Compose.md). ## Installation From 8081ca3235e27d086483ddac74d92e3507149010 Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Tue, 16 Sep 2025 16:48:57 +0100 Subject: [PATCH 2/8] More --- Compose | 130 ++++++++++++++++++++++++++++++++++++++++++++++------- Compose.md | 14 +++--- 2 files changed, 120 insertions(+), 24 deletions(-) diff --git a/Compose b/Compose index 32e01a8..0dbd027 100644 --- a/Compose +++ b/Compose @@ -300,12 +300,40 @@ include "%L" <2> : "᪼" U1ABC # COMBINING DOUBLE PARENTHESES ABOVE : "᫁" U1AC1 # COMBINING LEFT PARENTHESIS ABOVE LEFT (conflicts with ˘, use ␣() : "᫂" U1AC2 # COMBINING RIGHT PARENTHESIS ABOVE RIGHT - : "᫅" U1AC5 # COMBINING SQUARE BRACKETS ABOVE + : "᫅" U1AC5 # COMBINING SQUARE BRACKETS ABOVE : "᫆" U1AC6 # COMBINING NUMBER SIGN ABOVE : "᫇" U1AC7 # COMBINING INVERTED DOUBLE ARCH ABOVE (for ◌ᷓ use a[Return]) : "᫈" U1AC8 # COMBINING PLUS SIGN ABOVE : "᫉" U1AC9 # COMBINING DOUBLE PLUS SIGN ABOVE (conflicts with useless #) + : "᫏" U1ACF # COMBINING DOUBLE CARON + : "᫐" U1AD0 # COMBINING VERTICAL-LINE-ACUTE + : "᫑" U1AD1 # COMBINING GRAVE-VERTICAL-LINE + : "᫒" U1AD2 # COMBINING VERTICAL-LINE-GRAVE + : "᫓" U1AD3 # COMBINING ACUTE-VERTICAL-LINE + : "᫔" U1AD4 # COMBINING VERTICAL-LINE-MACRON + : "᫕" U1AD5 # COMBINING MACRON-VERTICAL-LINE + : "᫖" U1AD6 # COMBINING VERTICAL-LINE-ACUTE-GRAVE + : "᫖" U1AD6 # COMBINING VERTICAL-LINE-ACUTE-GRAVE + : "᫗" U1AD7 # COMBINING VERTICAL-LINE-GRAVE-ACUTE + : "᫗" U1AD7 # COMBINING VERTICAL-LINE-GRAVE-ACUTE + : "᫘" U1AD8 # COMBINING MACRON-ACUTE-GRAVE + : "᫘" U1AD8 # COMBINING MACRON-ACUTE-GRAVE + : "᫙" U1AD9 # COMBINING SHARP SIGN + : "᫚" U1ADA # COMBINING FLAT SIGN + : "᫛" U1ADB # COMBINING DOWN TACK ABOVE + : "᫜" U1ADC # COMBINING DIAERESIS WITH RAISED LEFT DOT : "᫋" U1ACB # COMBINING TRIPLE ACUTE ACCENT (not ideal, but ''' and 3' are taken) + : "᫠" U1AE0 # COMBINING LEFT TACK ABOVE + : "᫡" U1AE1 # COMBINING RIGHT TACK ABOVE (conflicts with Ť, use vT) + : "᫢" U1AE2 # COMBINING MINUS SIGN ABOVE + : "᫣" U1AE3 # COMBINING INVERTED BRIDGE ABOVE + : "᫤" U1AE4 # COMBINING SQUARE ABOVE + : "᫥" U1AE5 # COMBINING SEAGULL ABOVE + : "᫧" U1AE7 # COMBINING DOUBLE ARCH ABOVE + : "᫨" U1AE8 # COMBINING EQUALS SIGN ABOVE + : "᫩" U1AE9 # COMBINING LEFT ANGLE CENTRED ABOVE + : "᫩" U1AE9 # COMBINING LEFT ANGLE CENTRED ABOVE + : "᫪" U1AEA # COMBINING UPWARDS ARROW ABOVE : "᷀" U1DC0 # COMBINING DOTTED GRAVE ACCENT : "᷁" U1DC1 # COMBINING DOTTED ACUTE ACCENT : "᷄" U1DC4 # COMBINING MACRON-ACUTE (conflicts with ⍘, use [Return]_' defined below) @@ -396,6 +424,9 @@ include "%L" : "᫃" U1AC3 # COMBINING LEFT PARENTHESIS BELOW LEFT (conflicts with ¯, use -^) : "᫄" U1AC4 # COMBINING RIGHT PARENTHESIS BELOW RIGHT (conflicts with ¯, use -^) : "᫊" U1ACA # COMBINING DOUBLE PLUS SIGN BELOW (conflicts with ¯, use -^) + : "᫝" U1ADD # COMBINING DOT-AND-RING BELOW (conflicts with ȱ, use -.o or _.o␣) + : "ȱ" U0231 # LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON (overrides, alternatively -.o) + : "᫦" U1AE6 # COMBINING DOUBLE ARCH BELOW : "᷏" U1DCF # COMBINING ZIGZAG BELOW : "᷐" U1DD0 # COMBINING IS BELOW (conflicts with ¯, use -^) : "᷹" U1DF9 # COMBINING WIDE INVERTED BRIDGE BELOW (conflicts with ¯, use -^) @@ -436,6 +467,7 @@ include "%L" <2> : "͢" U0362 # COMBINING DOUBLE RIGHTWARDS ARROW BELOW <2> : "᷼" U1DFC # COMBINING DOUBLE INVERTED BREVE BELOW (alternatively __([Return]) <2> : "᷍" U1DCD # COMBINING DOUBLE CIRCUMFLEX ABOVE (conflicts with ², use ^2) + <2> : "᫫" U1AEB # COMBINING DOUBLE RIGHTWARDS ARROW ABOVE (conflicts with ², use ^2) <2> : "︠" UFE20 # COMBINING LIGATURE LEFT HALF <2> : "︡" UFE21 # COMBINING LIGATURE RIGHT HALF @@ -1218,6 +1250,7 @@ include "%L" : "ƚ" U019A # LATIN SMALL LETTER L WITH BAR (conflicts with £, use l-) : "Ꝉ" UA748 # LATIN CAPITAL LETTER L WITH HIGH STROKE : "ꝉ" UA749 # LATIN SMALL LETTER L WITH HIGH STROKE + : "ȱ" U0231 # LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON

: "ꝑ" UA751 # LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER

: "Ꝑ" UA750 # LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER

: "Ᵽ" U2C63 # LATIN CAPITAL LETTER P WITH STROKE @@ -1806,7 +1839,7 @@ include "%L" : "ⱼ" U2C7C # LATIN SUBSCRIPT SMALL LETTER J : "ₖ" U2096 # LATIN SUBSCRIPT SMALL LETTER K : "ₗ" U2097 # LATIN SUBSCRIPT SMALL LETTER L - : "ₘ" U2098 # LATIN SUBSCRIPT SMALL LETTER M + : "ₘ" U2098 # LATIN SUBSCRIPT SMALL LETTER M : "ₙ" U2099 # LATIN SUBSCRIPT SMALL LETTER N : "ₒ" U2092 # LATIN SUBSCRIPT SMALL LETTER O (conflicts with ō, use -o)

: "ₚ" U209A # LATIN SUBSCRIPT SMALL LETTER P @@ -4142,6 +4175,7 @@ include "%L" : "ࣻ" U08FB # ARABIC DOUBLE RIGHT ARROWHEAD ABOVE (conflicts with ą) : "ࣼ" U08FC # ARABIC DOUBLE RIGHT ARROWHEAD ABOVE WITH DOT (conflicts with ą) : "ࣽ" U08FD # ARABIC RIGHT ARROWHEAD ABOVE WITH DOT (conflicts with ą) + : "𐻺" U10EFA # ARABIC DOUBLE VERTICAL BAR BELOW (conflicts with ą) : "﮲" UFBB2 # ARABIC SYMBOL DOT ABOVE (conflicts with ą) (for ۔ use a;..) : "﮳" UFBB3 # ARABIC SYMBOL DOT BELOW (conflicts with ą) @@ -4410,6 +4444,7 @@ include "%L" <2> : "ࢨ" U08A8 # ARABIC LETTER YEH WITH TWO DOTS BELOW AND HAMZA ABOVE : "ࢩ" U08A9 # ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE : "ࢺ" U08BA # ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE + : "𐻇" U10EC7 # ARABIC LETTER YEH WITH FOUR DOTS BELOW

: "ࢷ" U08B7 # ARABIC LETTER PEH WITH SMALL MEEM ABOVE

: "ࢾ" U08BE # ARABIC LETTER PEH WITH SMALL V @@ -4501,6 +4536,7 @@ include "%L" : "ٖ" U0656 # ARABIC SUBSCRIPT ALEF : "ۣ" U06E3 # ARABIC SMALL LOW SEEN : "ۭ" U06ED # ARABIC SMALL LOW MEEM + : "𐻻" U10EFB # ARABIC SMALL LOW NOON : "ࣙ" U08D9 # ARABIC SMALL LOW NOON WITH KASRA : "࣓" U08D3 # ARABIC SMALL LOW WAW : "࣓" U08D3 # ARABIC SMALL LOW WAW @@ -12602,7 +12638,7 @@ include "%L" # (C) ConScripts # ################## -# covers Canadian Aboriginal Syllabics (including Carrier, Cree & Inuktitut shortcuts), Cherokee, Deseret, +# covers Beria, Canadian Aboriginal Syllabics (including Carrier, Cree & Inuktitut shortcuts), Cherokee, Deseret, # Kayah Li, Medefeidrin, Mru, Nag Mundari, Nyiakeng Puachue Hmong, Ol Chiki, Old Onal, Osage, Pahawh Hmong, # Pau Cin Hau, Shavian, Sora Sompeng, Sunuwar, Tangsa, Toto, Wancho & Warang Citi @@ -15889,6 +15925,66 @@ include "%L" <8> : "𖫈" U16AC8 # TANGSA DIGIT EIGHT <9> : "𖫉" U16AC9 # TANGSA DIGIT NINE +# (TS = Tolong Siki) + + : "𑶰" U11DB0 # TOLONG SIKI LETTER I + : "𑶱" U11DB1 # TOLONG SIKI LETTER E + : "𑶲" U11DB2 # TOLONG SIKI LETTER U + : "𑶳" U11DB3 # TOLONG SIKI LETTER O + : "𑶴" U11DB4 # TOLONG SIKI LETTER A + : "𑶵" U11DB5 # TOLONG SIKI LETTER AA + +

: "𑶶" U11DB6 # TOLONG SIKI LETTER P +

: "𑶷" U11DB7 # TOLONG SIKI LETTER PH + : "𑶸" U11DB8 # TOLONG SIKI LETTER B + : "𑶹" U11DB9 # TOLONG SIKI LETTER BH + : "𑶺" U11DBA # TOLONG SIKI LETTER M + : "𑶻" U11DBB # TOLONG SIKI LETTER T + : "𑶼" U11DBC # TOLONG SIKI LETTER TH + : "𑶽" U11DBD # TOLONG SIKI LETTER D + : "𑶾" U11DBE # TOLONG SIKI LETTER DH + : "𑶿" U11DBF # TOLONG SIKI LETTER N + : "𑷀" U11DC0 # TOLONG SIKI LETTER TT + : "𑷁" U11DC1 # TOLONG SIKI LETTER TTH + : "𑷂" U11DC2 # TOLONG SIKI LETTER DD + : "𑷃" U11DC3 # TOLONG SIKI LETTER DDH + : "𑷄" U11DC4 # TOLONG SIKI LETTER NN + : "𑷅" U11DC5 # TOLONG SIKI LETTER C + : "𑷆" U11DC6 # TOLONG SIKI LETTER CH + : "𑷇" U11DC7 # TOLONG SIKI LETTER J + : "𑷈" U11DC8 # TOLONG SIKI LETTER JH + : "𑷉" U11DC9 # TOLONG SIKI LETTER NY + : "𑷊" U11DCA # TOLONG SIKI LETTER K + : "𑷋" U11DCB # TOLONG SIKI LETTER KH + : "𑷌" U11DCC # TOLONG SIKI LETTER G + : "𑷍" U11DCD # TOLONG SIKI LETTER GH + : "𑷎" U11DCE # TOLONG SIKI LETTER NG + : "𑷏" U11DCF # TOLONG SIKI LETTER Y + : "𑷐" U11DD0 # TOLONG SIKI LETTER R + : "𑷑" U11DD1 # TOLONG SIKI LETTER L + : "𑷒" U11DD2 # TOLONG SIKI LETTER V + : "𑷓" U11DD3 # TOLONG SIKI LETTER NNY + : "𑷔" U11DD4 # TOLONG SIKI LETTER S + : "𑷕" U11DD5 # TOLONG SIKI LETTER H + : "𑷖" U11DD6 # TOLONG SIKI LETTER X + : "𑷗" U11DD7 # TOLONG SIKI LETTER RR + : "𑷘" U11DD8 # TOLONG SIKI LETTER RRH + + : "𑷙" U11DD9 # TOLONG SIKI SIGN SELA + : "𑷚" U11DDA # TOLONG SIKI SIGN HECAKA + : "𑷛" U11DDB # TOLONG SIKI UNGGA + + <0> : "𑷠" U11DE0 # TOLONG SIKI DIGIT ZERO + <1> : "𑷡" U11DE1 # TOLONG SIKI DIGIT ONE + <2> : "𑷢" U11DE2 # TOLONG SIKI DIGIT TWO + <3> : "𑷣" U11DE3 # TOLONG SIKI DIGIT THREE + <4> : "𑷤" U11DE4 # TOLONG SIKI DIGIT FOUR + <5> : "𑷥" U11DE5 # TOLONG SIKI DIGIT FIVE + <6> : "𑷦" U11DE6 # TOLONG SIKI DIGIT SIX + <7> : "𑷧" U11DE7 # TOLONG SIKI DIGIT SEVEN + <8> : "𑷨" U11DE8 # TOLONG SIKI DIGIT EIGHT + <9> : "𑷩" U11DE9 # TOLONG SIKI DIGIT NINE + # (w = Wancho) : "𞋀" U1E2C0 # WANCHO LETTER AA @@ -32162,20 +32258,20 @@ include "Logograms" # Rectangles [ ] and ellipses ( ) - <0> : "▭" U25AD # WHITE RECTANGLE - <1> : "▬" U25AC # BLACK RECTANGLE - : "⌧" U2327 # X IN A RECTANGLE BOX - : "⮹" U2BB9 # UP ARROWHEAD IN A RECTANGLE BOX - : "⃢" U20E2 # COMBINING ENCLOSING SCREEN - <0> : "▯" U25AF # WHITE VERTICAL RECTANGLE - <1> : "▮" U25AE # BLACK VERTICAL RECTANGLE - : "𜸆" U1CE06 # WHITE VERTICAL RECTANGLE WITH HORIZONTAL BAR - - <0> : "⬭" U2B2D # WHITE HORIZONTAL ELLIPSE (conflicts with ˘, use ␣() - <1> : "⬬" U2B2C # BLACK HORIZONTAL ELLIPSE (conflicts with ˘, use ␣() - <2> : "𜸋𜸌" U1CE0B U1CE0C # WHITE ELLIPSE (TWO CHARACTERS) (conflicts with ˘, use ␣() - <0> : "⬯" U2B2F # WHITE VERTICAL ELLIPSE (conflicts with ˘, use ␣() - <1> : "⬮" U2B2E # BLACK VERTICAL ELLIPSE (conflicts with ˘, use ␣() + <0> : "▭" U25AD # WHITE RECTANGLE + <1> : "▬" U25AC # BLACK RECTANGLE + : "⌧" U2327 # X IN A RECTANGLE BOX + : "⮹" U2BB9 # UP ARROWHEAD IN A RECTANGLE BOX + : "⃢" U20E2 # COMBINING ENCLOSING SCREEN + <0> : "▯" U25AF # WHITE VERTICAL RECTANGLE + <1> : "▮" U25AE # BLACK VERTICAL RECTANGLE + : "𜸆" U1CE06 # WHITE VERTICAL RECTANGLE WITH HORIZONTAL BAR + + <0> : "⬭" U2B2D # WHITE HORIZONTAL ELLIPSE + <1> : "⬬" U2B2C # BLACK HORIZONTAL ELLIPSE + <2> : "𜸋𜸌" U1CE0B U1CE0C # WHITE ELLIPSE (TWO CHARACTERS) + <0> : "⬯" U2B2F # WHITE VERTICAL ELLIPSE + <1> : "⬮" U2B2E # BLACK VERTICAL ELLIPSE # Other shapes: [TAB] + 2 letter shape + code (note this shares a namespace with arrows) diff --git a/Compose.md b/Compose.md index dfa16cb..81a2028 100644 --- a/Compose.md +++ b/Compose.md @@ -9,31 +9,31 @@ The file aims for memorability and consistency. As a result, a small number of t ## Table of contents and examples -### Common script characters (666) +### Common script characters (694) * **Spaces** (15): NBSP MMSP ZWSP etc * **Dashes** (13): – — ⁓ ⸻ etc * **Brackets** (62): ⟨ ⟦ ⸨ ⌈ ⫽ etc * **Bullets** (11): • ‣ ⁃ ◉ etc * **General punctuation** (72): ⁁ ⁂ ⸎ etc * **Currency symbols** (31): ₱ ₿ ₪ etc -* **Combining diacritics** (190): ń n̊ n̫ m͡n Zǎ̺̣͆̚l⃪ğ̶̍ö̱̰̥̂̃ etc +* **Combining diacritics** (218): ń n̊ n̫ m͡n Zǎ̺̣͆̚l⃪ğ̶̍ö̱̰̥̂̃ etc * **Control characters** (272): RLI PDI ZWJ VS16 etc -### Latin script characters (2768) +### Latin script characters (2769) * **International Phonetic Alphabet** (143): ⫽ˈɹɛ.dɪt⫽ [aɪ̯ pʰiː eɪ̯] etc -* **Latin script letters** (518): Ƿ Ȝ ␢ ȵ etc +* **Latin script letters** (519): Ƿ Ȝ ␢ ȵ etc * **Mathematical alphanumerics** (796): 𝐀 𝐴 𝑨 A 𝗔 𝘈 𝘼 𝒜 𝓐 𝔄 𝕬 𝙰 𝔸 𜳖 etc * **Enclosed alphanumerics** (293): ⓼ 🅛 🆛 ⒜ ⒓ etc * **Superscripts and subscripts** (311): ᵃ ᴬ ₐ ᴀ ◌ͣ etc * **Multigraphs and ligatures** (392): ʣ ㏈ etc * **Letter games** (315): ʇᴉppǝɹ ɟibbɘר டωᓀᓀ·–⟝ etc -### Non-Latin script characters (36259) -* **Arabic**, Old North Arabian, Old South Arabian, Avestan, Chorasmian, Hatran, Mandaic, Manichaean, Nabatean, Old Persian, Osmanya, Inscriptional Pahlavi, Psalter Pahlavi, Inscriptional Parthian, Hanifi Rohingya, Old Sogdian, Sogdian, Syriac, Neo-Tifinagh, Thaana, Old Uyghur & Yezidi (2268): ⁧رِيدِتْ⁩, ⁧𐪇𐪕𐪉⁩, ⁧𐬭𐬈𐬛𐬌𐬙⁩, ⁧𐩧𐩵𐩩⁩, ⁧𐿂𐾴𐾺𐿄⁩, ⁧𐣣𐣣𐣩𐣵⁩, ⁧ࡓࡏࡃࡉࡕ⁩, ⁧𐫡𐫅𐫏𐫤⁩, ⁧𐢛𐢅𐢍𐢞⁩, 𐎼𐎡𐎮𐎡𐎫, 𐒇𐒗𐒆𐒘𐒂, ⁧𐭥𐭣𐭩𐭲⁩, ⁧𐮅𐮃𐮈𐮑⁩, ⁧𐴌𐴠𐴊𐴞𐴃⁩, ⁧𐭓𐭃𐭉𐭕⁩, ⁧𐼘𐼘𐼊𐼚⁩, ⁧𐽀𐼲𐼷𐽂⁩, ⁧ܪܕ݁ܝܬ݁⁩, ⵔⴻⴷⴷⵉⵜ, ⁧ރެދިތް⁩, ⁧𐽾𐽲𐽶𐾀⁩, ⁧𐺎𐺩𐺋𐺨𐺕⁩ etc +### Non-Latin script characters (36316) +* **Arabic**, Old North Arabian, Old South Arabian, Avestan, Chorasmian, Hatran, Mandaic, Manichaean, Nabatean, Old Persian, Osmanya, Inscriptional Pahlavi, Psalter Pahlavi, Inscriptional Parthian, Hanifi Rohingya, Old Sogdian, Sogdian, Syriac, Neo-Tifinagh, Thaana, Old Uyghur & Yezidi (2271): ⁧رِيدِتْ⁩, ⁧𐪇𐪕𐪉⁩, ⁧𐬭𐬈𐬛𐬌𐬙⁩, ⁧𐩧𐩵𐩩⁩, ⁧𐿂𐾴𐾺𐿄⁩, ⁧𐣣𐣣𐣩𐣵⁩, ⁧ࡓࡏࡃࡉࡕ⁩, ⁧𐫡𐫅𐫏𐫤⁩, ⁧𐢛𐢅𐢍𐢞⁩, 𐎼𐎡𐎮𐎡𐎫, 𐒇𐒗𐒆𐒘𐒂, ⁧𐭥𐭣𐭩𐭲⁩, ⁧𐮅𐮃𐮈𐮑⁩, ⁧𐴌𐴠𐴊𐴞𐴃⁩, ⁧𐭓𐭃𐭉𐭕⁩, ⁧𐼘𐼘𐼊𐼚⁩, ⁧𐽀𐼲𐼷𐽂⁩, ⁧ܪܕ݁ܝܬ݁⁩, ⵔⴻⴷⴷⵉⵜ, ⁧ރެދިތް⁩, ⁧𐽾𐽲𐽶𐾀⁩, ⁧𐺎𐺩𐺋𐺨𐺕⁩ etc * **Armenian** (95): Րեդդիտ etc * **Brahmic scripts**: Ahom, Bengali, Bhaiksuki, Brahmi, Burmese, Chakma, Devanagari, Dives Akuru, Dogra, Grantha, Gujala Gondi, Gujarati, Gurmukhi, Gurung Khema, Kaithi, Kannada, Kawi, Kharoshthi, Khojki, Khudawadi, Kirat Rai, Lepcha, Limbu, Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meitei, Modi, Multani, Nandinagari, Newa, Odia, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Sylheti Nagri, Takri, Tamil, Telugu, Tigalari, Tirhuta (3618): 𑜍𑜦𑜔𑜢𑜌𑜫, রেডিট, 𑰨𑰸𑰠𑰰𑰞, 𑀭𑁂𑀟𑀺𑀝, ရေဍိဋ္, 𑄢𑄬𑄘𑄨𑄖𑄳, रेडिट, 𑤧𑤵𑤞𑤱𑤜𑤽, 𑠤𑠳𑠜𑠭𑠚, 𑌰𑍇𑌧𑌿𑌥, 𑶈𑶐𑵹𑶋𑵴𑶗, રેડિટ, ਰੇਡਿਟ, 𖄛𖄣𖄓𖄟𖄑, 𑂩𑂵𑂡𑂱𑂟, ರೆಡಿತ್, ⁧𐨪𐨅𐨢𐨁𐨠⁩, 𑈦𑈰𑈝𑈭𑈚, 𑋙𑋥𑋐𑋡𑋎, 𖵝𖵧𖵕𖵤𖵓, ᰛᰬᰌᰧᰳ, ᤖᤧᤍᤡᤳ, 𑅭𑅓𑅦𑅑𑅟, രെഡിട്, 𑲊𑲳𑱼𑲱𑱻, 𑴦𑴺𑴞𑴲𑴜, ꯔꯦꯗꯤꯠ, 𑘨𑘹𑘠𑘱𑘞, 𑊢𑊃𑊙𑊁𑊗, 𑧈𑧚𑧀𑧒𑦾, 𑐬𑐾𑐢𑐶𑐠, ରେଡିଟ, ꢬꢾꢞꢶꢜ, 𑆫𑆼𑆣𑆴𑆡, 𑖨𑖸𑖠𑖰𑖞, රෙඩිට්, ꠞꠦꠗꠤꠕ, 𑚤𑚲𑚜𑚮𑚚, ரெடிட், రెడిట్, 𑎬𑏂𑎤𑎹𑎢, 𑒩𑒺𑒡𑒱𑒟 etc * **Braille**, UEB (272): ⠗⠫⠙⠊⠞ etc -* **ConScripts**: Beria, Carrier, Cherokee, Cree, Deseret, Inuktitut, Kayah Li, Mefeidrin, Mundari Bani, Mru, Nyiakeng Puachue Hmong, Ol Chiki, Old Onal, Osage, Pahawh Hmong, Pau Cin Hau, Shavian, Sloan-Duployan, Sora Sompeng, Sunuwar, Tangsa, Toto, Wancho & Warang Citi (2329): 𖺱𖺾𖺽𖻂𖻐, ᘥᑔᐪ, ᎴᏗᏛ, ᕃᑎᑦ, 𐐡𐐇𐐔𐐆𐐓, ᕃᑎᑦ, ꤚꤢꤧꤘꤤꤒ, 𖹜𖹯𖹹𖹹𖹫𖹨, 𞓣𞓤𞓡𞓚𞓝, 𖩓𖩘𖩅𖩊𖩀, 𞄣𞄪𞄏𞄦𞄃, ᱨᱮᱫᱫᱤᱛ, 𞗧𞗨𞗠𞗜𞗝, 𐒴𐓟𐓵𐓣𐓰, 𖬡𖬉𖬰𖬞𖬰𖬃𖬰𖬧𖬵, 𑫒𑫖𑫄𑫗𑫎, 𐑮𐑧𐑛𐑦𐑑, 𛰋𛱌𛰍, 𑃝𑃣𑃔𑃤𑃑, 𑯄𑯂𑯀𑯃𑯁, 𖪲𖪔𖪱𖪏𖪰, 𞊟𞊦𞊓𞊡𞊒, 𞋗𞋛𞋄𞋜𞋋, 𑢼𑣈𑣔𑣂𑣕 etc +* **ConScripts**: Beria, Carrier, Cherokee, Cree, Deseret, Inuktitut, Kayah Li, Mefeidrin, Mundari Bani, Mru, Nyiakeng Puachue Hmong, Ol Chiki, Old Onal, Osage, Pahawh Hmong, Pau Cin Hau, Shavian, Sloan-Duployan, Sora Sompeng, Sunuwar, Tangsa, Tolong Siki, Toto, Wancho & Warang Citi (2383): 𖺱𖺾𖺽𖻂𖻐, ᘥᑔᐪ, ᎴᏗᏛ, ᕃᑎᑦ, 𐐡𐐇𐐔𐐆𐐓, ᕃᑎᑦ, ꤚꤢꤧꤘꤤꤒ, 𖹜𖹯𖹹𖹹𖹫𖹨, 𞓣𞓤𞓡𞓚𞓝, 𖩓𖩘𖩅𖩊𖩀, 𞄣𞄪𞄏𞄦𞄃, ᱨᱮᱫᱫᱤᱛ, 𞗧𞗨𞗠𞗜𞗝, 𐒴𐓟𐓵𐓣𐓰, 𖬡𖬉𖬰𖬞𖬰𖬃𖬰𖬧𖬵, 𑫒𑫖𑫄𑫗𑫎, 𐑮𐑧𐑛𐑦𐑑, 𛰋𛱌𛰍, 𑃝𑃣𑃔𑃤𑃑, 𑯄𑯂𑯀𑯃𑯁, 𖪲𖪔𖪱𖪏𖪰, 𑷐𑶱𑶽𑶰𑶻, 𞊟𞊦𞊓𞊡𞊒, 𞋗𞋛𞋄𞋜𞋋, 𑢼𑣈𑣔𑣂𑣕 etc * **Cyrillic**, Glagolitic & Old Permic (680): Ре́ддит, Ⱃⰵδδιτ, 𐍠𐍔𐍓𐍓𐍙𐍢 etc * **Geʽez**, Adlam, Bamum, Bassa Vah, Garay, Mende Kikakui, Meroitic Cursive & Hieroglyphic, NKo & Vai (2074): ሬዲተ, ⁧𞤈𞤫𞤣𞤭𞤼⁩, ꚥꛤꛤ꛱, 𖫦𖫬𖫗𖫭𖫡, ⁧𐵞𐵩𐵺𐵋𐵽⁩, ⁧𞠺𞠾𞡊⁩, ⁧𐦫𐦪𐦷𐦢𐦴⁩, ⁧𐦎𐦁𐦝𐦂𐦘⁩, ⁧ߙߍߘߘߌߕ⁩, ꗸꔹꗋ etc * **Georgian** & Caucasian Albanian (227): რედდიტ, ႰႤႣႣႨႲ, 𐕙𐔴𐔳𐔳𐔼𐔸 etc From d0eb9f0e6365c6457b7e625b03419fadc1d4f516 Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Tue, 16 Sep 2025 21:49:55 +0100 Subject: [PATCH 3/8] Tai Yo --- Compose | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++---- Compose.md | 4 ++-- 2 files changed, 68 insertions(+), 6 deletions(-) diff --git a/Compose b/Compose index 0dbd027..1e7c306 100644 --- a/Compose +++ b/Compose @@ -12640,7 +12640,7 @@ include "%L" # covers Beria, Canadian Aboriginal Syllabics (including Carrier, Cree & Inuktitut shortcuts), Cherokee, Deseret, # Kayah Li, Medefeidrin, Mru, Nag Mundari, Nyiakeng Puachue Hmong, Ol Chiki, Old Onal, Osage, Pahawh Hmong, -# Pau Cin Hau, Shavian, Sora Sompeng, Sunuwar, Tangsa, Toto, Wancho & Warang Citi +# Pau Cin Hau, Shavian, Sora Sompeng, Sunuwar, Tangsa, Tolong Siki, Toto, Wancho & Warang Citi # (AS = Canadian Aboriginal Syllabics) @@ -22061,9 +22061,9 @@ include "HangulSyllables" : "𝪋" U1DA8B # SIGNWRITING PARENTHESIS : "𝪋𝪤" U1DA8B U1DA44 # SIGNWRITING CLOSE PARENTHESIS -######################################################## -# (t) Thai (and Cham, Khmer, Lao, Tai Tham & Tai Viet) # -######################################################## +################################################################ +# (t) Thai (and Cham, Khmer, Lao, Tai Tham, Tai Viet & Tai Yo) # +################################################################ # (based on ISO 11940) @@ -22777,6 +22777,68 @@ include "HangulSyllables" : "꫞" UAADE # TAI VIET SYMBOL HO HOI : "꫟" UAADF # TAI VIET SYMBOL KOI KOI +# (Y = Tai Yo) + + : "𞛀" U1E6C0 # TAI YO LETTER LOW KO + : "𞛁" U1E6C1 # TAI YO LETTER HIGH KO + : "𞛂" U1E6C2 # TAI YO LETTER LOW KHO + : "𞛃" U1E6C3 # TAI YO LETTER HIGH KHO + : "𞛄" U1E6C4 # TAI YO LETTER GO + : "𞛅" U1E6C5 # TAI YO LETTER NGO + : "𞛆" U1E6C6 # TAI YO LETTER CO + : "𞛇" U1E6C7 # TAI YO LETTER LOW XO + : "𞛈" U1E6C8 # TAI YO LETTER HIGH XO + : "𞛉" U1E6C9 # TAI YO LETTER LOW NYO + : "𞛊" U1E6CA # TAI YO LETTER HIGH NYO + : "𞛋" U1E6CB # TAI YO LETTER DO + : "𞛌" U1E6CC # TAI YO LETTER LOW TO + : "𞛍" U1E6CD # TAI YO LETTER HIGH TO + : "𞛎" U1E6CE # TAI YO LETTER THO + : "𞛏" U1E6CF # TAI YO LETTER NO + : "𞛐" U1E6D0 # TAI YO LETTER BO +

: "𞛑" U1E6D1 # TAI YO LETTER LOW PO +

: "𞛒" U1E6D2 # TAI YO LETTER HIGH PO +

: "𞛓" U1E6D3 # TAI YO LETTER PHO + : "𞛔" U1E6D4 # TAI YO LETTER LOW FO + : "𞛕" U1E6D5 # TAI YO LETTER HIGH FO + : "𞛖" U1E6D6 # TAI YO LETTER MO + : "𞛗" U1E6D7 # TAI YO LETTER YO + : "𞛘" U1E6D8 # TAI YO LETTER LO + : "𞛙" U1E6D9 # TAI YO LETTER VO + : "𞛚" U1E6DA # TAI YO LETTER LOW HO + : "𞛛" U1E6DB # TAI YO LETTER HIGH HO + : "𞛜" U1E6DC # TAI YO LETTER QO + : "𞛜" U1E6DC # TAI YO LETTER QO + : "𞛝" U1E6DD # TAI YO LETTER LOW KVO + : "𞛞" U1E6DE # TAI YO LETTER HIGH KVO + + : "𞛠" U1E6E0 # TAI YO LETTER AA + : "𞛡" U1E6E1 # TAI YO LETTER I + : "𞛢" U1E6E2 # TAI YO LETTER UE + : "𞛣" U1E6E3 # TAI YO SIGN UE + : "𞛤" U1E6E4 # TAI YO LETTER U + : "𞛥" U1E6E5 # TAI YO LETTER AE + : "𞛦" U1E6E6 # TAI YO SIGN AU + : "𞛧" U1E6E7 # TAI YO LETTER O + : "𞛨" U1E6E8 # TAI YO LETTER E + : "𞛩" U1E6E9 # TAI YO LETTER IA + : "𞛪" U1E6EA # TAI YO LETTER UEA + : "𞛫" U1E6EB # TAI YO LETTER UA + : "𞛬" U1E6EC # TAI YO LETTER OO + : "𞛭" U1E6ED # TAI YO LETTER AUE + + : "𞛮" U1E6EE # TAI YO SIGN AY + : "𞛯" U1E6EF # TAI YO SIGN ANG + : "𞛰" U1E6F0 # TAI YO LETTER AN + : "𞛱" U1E6F1 # TAI YO LETTER AM + : "𞛲" U1E6F2 # TAI YO LETTER AK + : "𞛳" U1E6F3 # TAI YO LETTER AT +

: "𞛴" U1E6F4 # TAI YO LETTER AP + : "𞛵" U1E6F5 # TAI YO SIGN OM + + : "𞛾" U1E6FE # TAI YO SYMBOL MUEANG + : "𞛿" U1E6FF # TAI YO XAM LAI + ################################################## # (z) Zhuyin/Bopomofo (and other nearby scripts) # ################################################## diff --git a/Compose.md b/Compose.md index 81a2028..8458624 100644 --- a/Compose.md +++ b/Compose.md @@ -28,7 +28,7 @@ The file aims for memorability and consistency. As a result, a small number of t * **Multigraphs and ligatures** (392): ʣ ㏈ etc * **Letter games** (315): ʇᴉppǝɹ ɟibbɘר டωᓀᓀ·–⟝ etc -### Non-Latin script characters (36316) +### Non-Latin script characters (36371) * **Arabic**, Old North Arabian, Old South Arabian, Avestan, Chorasmian, Hatran, Mandaic, Manichaean, Nabatean, Old Persian, Osmanya, Inscriptional Pahlavi, Psalter Pahlavi, Inscriptional Parthian, Hanifi Rohingya, Old Sogdian, Sogdian, Syriac, Neo-Tifinagh, Thaana, Old Uyghur & Yezidi (2271): ⁧رِيدِتْ⁩, ⁧𐪇𐪕𐪉⁩, ⁧𐬭𐬈𐬛𐬌𐬙⁩, ⁧𐩧𐩵𐩩⁩, ⁧𐿂𐾴𐾺𐿄⁩, ⁧𐣣𐣣𐣩𐣵⁩, ⁧ࡓࡏࡃࡉࡕ⁩, ⁧𐫡𐫅𐫏𐫤⁩, ⁧𐢛𐢅𐢍𐢞⁩, 𐎼𐎡𐎮𐎡𐎫, 𐒇𐒗𐒆𐒘𐒂, ⁧𐭥𐭣𐭩𐭲⁩, ⁧𐮅𐮃𐮈𐮑⁩, ⁧𐴌𐴠𐴊𐴞𐴃⁩, ⁧𐭓𐭃𐭉𐭕⁩, ⁧𐼘𐼘𐼊𐼚⁩, ⁧𐽀𐼲𐼷𐽂⁩, ⁧ܪܕ݁ܝܬ݁⁩, ⵔⴻⴷⴷⵉⵜ, ⁧ރެދިތް⁩, ⁧𐽾𐽲𐽶𐾀⁩, ⁧𐺎𐺩𐺋𐺨𐺕⁩ etc * **Armenian** (95): Րեդդիտ etc * **Brahmic scripts**: Ahom, Bengali, Bhaiksuki, Brahmi, Burmese, Chakma, Devanagari, Dives Akuru, Dogra, Grantha, Gujala Gondi, Gujarati, Gurmukhi, Gurung Khema, Kaithi, Kannada, Kawi, Kharoshthi, Khojki, Khudawadi, Kirat Rai, Lepcha, Limbu, Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meitei, Modi, Multani, Nandinagari, Newa, Odia, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Sylheti Nagri, Takri, Tamil, Telugu, Tigalari, Tirhuta (3618): 𑜍𑜦𑜔𑜢𑜌𑜫, রেডিট, 𑰨𑰸𑰠𑰰𑰞, 𑀭𑁂𑀟𑀺𑀝, ရေဍိဋ္, 𑄢𑄬𑄘𑄨𑄖𑄳, रेडिट, 𑤧𑤵𑤞𑤱𑤜𑤽, 𑠤𑠳𑠜𑠭𑠚, 𑌰𑍇𑌧𑌿𑌥, 𑶈𑶐𑵹𑶋𑵴𑶗, રેડિટ, ਰੇਡਿਟ, 𖄛𖄣𖄓𖄟𖄑, 𑂩𑂵𑂡𑂱𑂟, ರೆಡಿತ್, ⁧𐨪𐨅𐨢𐨁𐨠⁩, 𑈦𑈰𑈝𑈭𑈚, 𑋙𑋥𑋐𑋡𑋎, 𖵝𖵧𖵕𖵤𖵓, ᰛᰬᰌᰧᰳ, ᤖᤧᤍᤡᤳ, 𑅭𑅓𑅦𑅑𑅟, രെഡിട്, 𑲊𑲳𑱼𑲱𑱻, 𑴦𑴺𑴞𑴲𑴜, ꯔꯦꯗꯤꯠ, 𑘨𑘹𑘠𑘱𑘞, 𑊢𑊃𑊙𑊁𑊗, 𑧈𑧚𑧀𑧒𑦾, 𑐬𑐾𑐢𑐶𑐠, ରେଡିଟ, ꢬꢾꢞꢶꢜ, 𑆫𑆼𑆣𑆴𑆡, 𑖨𑖸𑖠𑖰𑖞, රෙඩිට්, ꠞꠦꠗꠤꠕ, 𑚤𑚲𑚜𑚮𑚚, ரெடிட், రెడిట్, 𑎬𑏂𑎤𑎹𑎢, 𑒩𑒺𑒡𑒱𑒟 etc @@ -45,7 +45,7 @@ The file aims for memorability and consistency. As a result, a small number of t * **International Morse Code** (76): ·-· · -·· -·· ·· - etc * **Old Italic**, Carian, Ogham, Old Hungarian, Runic & Old Turkic (405): 𐌓𐌄𐌃𐌃𐌉𐌕, 𐊥𐊺𐊢𐊢𐊹𐊭, ᚏᚓᚇᚔᚈ, ⁧𐲢𐳉𐳇𐳇𐳐𐳦⁩, ᚱᛖᛞᛞᛁᛏ, ⁧𐰺𐰅𐰑𐰃𐱃⁩ etc * **Sutton SignWriting** (673): 𝧿𝨾𝡇𝪜𝪡𝦈𝪪 etc -* **Thai**, Cham, Khmer, Lao, Tai Tham & Tai Viet (596): เรดดิต, ꨣꨮꨖꨪꩅ, រេទិត, ເຣັດິຕ, ᩁᩮᨯᩥᨲ, ꪧꪵꪒꪲꪒ etc +* **Thai**, Cham, Khmer, Lao, Tai Tham, Tai Viet & Tai Yo (651): เรดดิต, ꨣꨮꨖꨪꩅ, រេទិត, ເຣັດິຕ, ᩁᩮᨯᩥᨲ, ꪧꪵꪒꪲꪒ, 𞛘𞛨𞛋𞛡 etc * **Zhuyin**, Fraser, Mongolian, New Tai Lue, Nüshu, ʼPhags-pa, Pollard, Soyombo, Tai LeTibetan, Yi, Zanabazar Square (3104): ㄏㄨㄥˊㄉㄧˊ, ꓡꓯꓓꓲꓔ, ᠷᠡᠳᠢᠲ, ᦜᦵᦡᦲᧆ, 𛋝𛆒, ꡘꡠꡊꡞꡈ, 𖼖𖽝𖼋𖽡𖼊, 𑩼𑩔𑩩𑩑𑪍, ᥘᥦᥖᥤᥖ, རེཌིཊ྄, ꏒꄶ, 𑨫𑨄𑨜𑨁𑨚𑨴 etc * **Logograms/undeciphered**: Anatolian Hieroglyphs, Cuneiform, Cypro-Minoan, Egyptian Hieroglyphs, Linear A&B, Phaistos Disc (4835): 𔐅 𒆛 𒿌 𓀁 𐙞 𐇑 etc * Language names (150): 🇯🇵 日本語 🇮🇷 ⁧فارس⁩ 🇻🇳 Tiếng Việt etc From 70f9baf3dc36cf9912581020e40cd1a21bcf4946 Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Fri, 3 Oct 2025 12:18:45 +0100 Subject: [PATCH 4/8] Arabic --- Compose | 12 +++++++++--- Compose.md | 4 ++-- 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/Compose b/Compose index 1e7c306..e62f92b 100644 --- a/Compose +++ b/Compose @@ -4566,10 +4566,13 @@ include "%L" : "ؑ" U0611 # ARABIC SIGN ALAYHE ASSALLAM : "﵇" UFD47 # ARABIC LIGATURE ALAYHI AS-SALAAM + : "﵈" UFD48 # ARABIC LIGATURE ALAYHIM AS-SALAAM + <2> : "﵉" UFD49 # ARABIC LIGATURE ALAYHIMAA AS-SALAAM + : "﵍" UFD4D # ARABIC LIGATURE ALAYHAA AS-SALAAM : "﵊" UFD4A # ARABIC LIGATURE ALAYHI AS-SALAATU WAS-SALAAM - : "﵈" UFD48 # ARABIC LIGATURE ALAYHIM AS-SALAAM - <2> : "﵉" UFD49 # ARABIC LIGATURE ALAYHIMAA AS-SALAAM - : "﵍" UFD4D # ARABIC LIGATURE ALAYHAA AS-SALAAM + : "𐻑" U10ED1 # ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM + : "𐻒" U10ED2 # ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM + <2> : "𐻓" U10ED3 # ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM : "ؓ" U0613 # ARABIC SIGN RADI ALLAHOU ANHU : "﵁" UFD41 # ARABIC LIGATURE RADI ALLAAHU ANH @@ -30129,6 +30132,7 @@ include "Logograms" : "😗" U1F617 # KISSING FACE (MWAH) (use :x for 😙) : "🤓" U1F913 # NERD FACE : "🙂‍↔️" U1F642 U200D U2194 UFE0F # HEAD SHAKING HORIZONTALLY EMOJI (NO!) (use -1 for 👎) + : "😮" U1F62E # FACE WITH OPEN MOUTH (OH!) (alternatively :O) : "🫢" U1FAE2 # FACE WITH OPEN EYES AND HAND OVER MOUTH (OH NO!)

: "🥳" U1F973 # FACE WITH PARTY HORN AND PARTY HAT (use yay for 🎉)

: "🫣" U1FAE3 # FACE WITH PEEKING EYE @@ -30330,6 +30334,7 @@ include "Logograms"

: "🥢" U1F962 # CHOPSTICKS (conflicts with ȟ, use vh) : "🥂" U1F942 # CLINKING GLASSES (conflicts with ľ, use vl) : "🍸" U1F378 # COCKTAIL GLASS (conflicts with ǒ, use vo) + : "☕" U2615 # HOT BEVERAGE (COFFEE) (alternatively tea) (conflicts with ǎ, use va) : "🍳" U1F373 # COOKING (conflicts with ǒ, use vo) (use chef for 🧑‍🍳) : "🍪" U1F36A # COOKIE (conflicts with ǒ, use vo) : "🍾" U1F37E # BOTTLE WITH POPPING CORK (conflicts with ǒ, use vo) @@ -30352,6 +30357,7 @@ include "Logograms"

: "🍏" U1F34F # GREEN APPLE : "🧄" U1F9C4 # GARLIC : "🍨" U1F368 # ICE CREAM (GELATO) + : "🍸" U1F378 # COCKTAIL GLASS (GIN) : "🫚" U1FADA # GINGER ROOT : "🥃" U1F943 # TUMBLER GLASS

: "🍇" U1F347 # GRAPES diff --git a/Compose.md b/Compose.md index 8458624..79c9c69 100644 --- a/Compose.md +++ b/Compose.md @@ -28,8 +28,8 @@ The file aims for memorability and consistency. As a result, a small number of t * **Multigraphs and ligatures** (392): ʣ ㏈ etc * **Letter games** (315): ʇᴉppǝɹ ɟibbɘר டωᓀᓀ·–⟝ etc -### Non-Latin script characters (36371) -* **Arabic**, Old North Arabian, Old South Arabian, Avestan, Chorasmian, Hatran, Mandaic, Manichaean, Nabatean, Old Persian, Osmanya, Inscriptional Pahlavi, Psalter Pahlavi, Inscriptional Parthian, Hanifi Rohingya, Old Sogdian, Sogdian, Syriac, Neo-Tifinagh, Thaana, Old Uyghur & Yezidi (2271): ⁧رِيدِتْ⁩, ⁧𐪇𐪕𐪉⁩, ⁧𐬭𐬈𐬛𐬌𐬙⁩, ⁧𐩧𐩵𐩩⁩, ⁧𐿂𐾴𐾺𐿄⁩, ⁧𐣣𐣣𐣩𐣵⁩, ⁧ࡓࡏࡃࡉࡕ⁩, ⁧𐫡𐫅𐫏𐫤⁩, ⁧𐢛𐢅𐢍𐢞⁩, 𐎼𐎡𐎮𐎡𐎫, 𐒇𐒗𐒆𐒘𐒂, ⁧𐭥𐭣𐭩𐭲⁩, ⁧𐮅𐮃𐮈𐮑⁩, ⁧𐴌𐴠𐴊𐴞𐴃⁩, ⁧𐭓𐭃𐭉𐭕⁩, ⁧𐼘𐼘𐼊𐼚⁩, ⁧𐽀𐼲𐼷𐽂⁩, ⁧ܪܕ݁ܝܬ݁⁩, ⵔⴻⴷⴷⵉⵜ, ⁧ރެދިތް⁩, ⁧𐽾𐽲𐽶𐾀⁩, ⁧𐺎𐺩𐺋𐺨𐺕⁩ etc +### Non-Latin script characters (36374) +* **Arabic**, Old North Arabian, Old South Arabian, Avestan, Chorasmian, Hatran, Mandaic, Manichaean, Nabatean, Old Persian, Osmanya, Inscriptional Pahlavi, Psalter Pahlavi, Inscriptional Parthian, Hanifi Rohingya, Old Sogdian, Sogdian, Syriac, Neo-Tifinagh, Thaana, Old Uyghur & Yezidi (2274): ⁧رِيدِتْ⁩, ⁧𐪇𐪕𐪉⁩, ⁧𐬭𐬈𐬛𐬌𐬙⁩, ⁧𐩧𐩵𐩩⁩, ⁧𐿂𐾴𐾺𐿄⁩, ⁧𐣣𐣣𐣩𐣵⁩, ⁧ࡓࡏࡃࡉࡕ⁩, ⁧𐫡𐫅𐫏𐫤⁩, ⁧𐢛𐢅𐢍𐢞⁩, 𐎼𐎡𐎮𐎡𐎫, 𐒇𐒗𐒆𐒘𐒂, ⁧𐭥𐭣𐭩𐭲⁩, ⁧𐮅𐮃𐮈𐮑⁩, ⁧𐴌𐴠𐴊𐴞𐴃⁩, ⁧𐭓𐭃𐭉𐭕⁩, ⁧𐼘𐼘𐼊𐼚⁩, ⁧𐽀𐼲𐼷𐽂⁩, ⁧ܪܕ݁ܝܬ݁⁩, ⵔⴻⴷⴷⵉⵜ, ⁧ރެދިތް⁩, ⁧𐽾𐽲𐽶𐾀⁩, ⁧𐺎𐺩𐺋𐺨𐺕⁩ etc * **Armenian** (95): Րեդդիտ etc * **Brahmic scripts**: Ahom, Bengali, Bhaiksuki, Brahmi, Burmese, Chakma, Devanagari, Dives Akuru, Dogra, Grantha, Gujala Gondi, Gujarati, Gurmukhi, Gurung Khema, Kaithi, Kannada, Kawi, Kharoshthi, Khojki, Khudawadi, Kirat Rai, Lepcha, Limbu, Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meitei, Modi, Multani, Nandinagari, Newa, Odia, Rejang, Saurashtra, Sharada, Siddham, Sinhala, Sylheti Nagri, Takri, Tamil, Telugu, Tigalari, Tirhuta (3618): 𑜍𑜦𑜔𑜢𑜌𑜫, রেডিট, 𑰨𑰸𑰠𑰰𑰞, 𑀭𑁂𑀟𑀺𑀝, ရေဍိဋ္, 𑄢𑄬𑄘𑄨𑄖𑄳, रेडिट, 𑤧𑤵𑤞𑤱𑤜𑤽, 𑠤𑠳𑠜𑠭𑠚, 𑌰𑍇𑌧𑌿𑌥, 𑶈𑶐𑵹𑶋𑵴𑶗, રેડિટ, ਰੇਡਿਟ, 𖄛𖄣𖄓𖄟𖄑, 𑂩𑂵𑂡𑂱𑂟, ರೆಡಿತ್, ⁧𐨪𐨅𐨢𐨁𐨠⁩, 𑈦𑈰𑈝𑈭𑈚, 𑋙𑋥𑋐𑋡𑋎, 𖵝𖵧𖵕𖵤𖵓, ᰛᰬᰌᰧᰳ, ᤖᤧᤍᤡᤳ, 𑅭𑅓𑅦𑅑𑅟, രെഡിട്, 𑲊𑲳𑱼𑲱𑱻, 𑴦𑴺𑴞𑴲𑴜, ꯔꯦꯗꯤꯠ, 𑘨𑘹𑘠𑘱𑘞, 𑊢𑊃𑊙𑊁𑊗, 𑧈𑧚𑧀𑧒𑦾, 𑐬𑐾𑐢𑐶𑐠, ରେଡିଟ, ꢬꢾꢞꢶꢜ, 𑆫𑆼𑆣𑆴𑆡, 𑖨𑖸𑖠𑖰𑖞, රෙඩිට්, ꠞꠦꠗꠤꠕ, 𑚤𑚲𑚜𑚮𑚚, ரெடிட், రెడిట్, 𑎬𑏂𑎤𑎹𑎢, 𑒩𑒺𑒡𑒱𑒟 etc * **Braille**, UEB (272): ⠗⠫⠙⠊⠞ etc From 8d587de02d702dedc1f2d9523afc3675a879fbdb Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Mon, 8 Dec 2025 11:11:44 +0000 Subject: [PATCH 5/8] A few emoji aliases --- Compose | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Compose b/Compose index e62f92b..0d8cad3 100644 --- a/Compose +++ b/Compose @@ -30094,6 +30094,7 @@ include "Logograms" : "👶" U1F476 # BABY (conflicts with ă, use ua) (use diaper or nappy for 🚼) : "😄" U1F604 # SMILING FACE WITH OPEN MOUTH AND SMILING EYES (BEAMY) (conflicts with ĕ, use ue) : "😳" U1F633 # FLUSHED FACE (BLUSH) + : "👻" U1F47B # GHOST (BOO!) : "🤡" U1F921 # CLOWN FACE (conflicts with ľ, use vl) : "🥶" U1F976 # FREEZING FACE (COLD) (conflicts with ǒ, use vo) : "😎" U1F60E # SMILING FACE WITH SUNGLASSES (COOL) (conflicts with ǒ, use vo) @@ -30134,6 +30135,9 @@ include "Logograms" : "🙂‍↔️" U1F642 U200D U2194 UFE0F # HEAD SHAKING HORIZONTALLY EMOJI (NO!) (use -1 for 👎) : "😮" U1F62E # FACE WITH OPEN MOUTH (OH!) (alternatively :O) : "🫢" U1FAE2 # FACE WITH OPEN EYES AND HAND OVER MOUTH (OH NO!) + : "👴" U1F474 # OLDER MAN + : "👵" U1F475 # OLDER WOMAN + : "🧓" U1F9D3 # OLDER ADULT

: "🥳" U1F973 # FACE WITH PARTY HORN AND PARTY HAT (use yay for 🎉)

: "🫣" U1FAE3 # FACE WITH PEEKING EYE

: "☠️" U2620 UFE0F # SKULL AND CROSSBONES EMOJI @@ -31128,6 +31132,7 @@ include "Logograms" : "🛠️" U1F6E0 UFE0F # HAMMER AND WRENCH EMOJI (use toolb for 🧰) : "🔦" U1F526 # ELECTRIC TORCH

: "🪤" U1FAA4 # MOUSE TRAP + : "🗑️" U1F5D1 UFE0F # WASTEBASKET EMOJI (TRASH)

: "🔭" U1F52D # TELESCOPE : "🔓" U1F513 # OPEN LOCK : "⚱️" U26B1 UFE0F # FUNERAL URN EMOJI (use amphor for 🏺) From 61fac3688752af3c396f48af97e53c0ebbbd9cf2 Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Fri, 3 Jul 2026 13:04:03 +0100 Subject: [PATCH 6/8] A few aliases --- Compose | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Compose b/Compose index 0d8cad3..f560f6b 100644 --- a/Compose +++ b/Compose @@ -30055,6 +30055,7 @@ include "Logograms" : "🚈" U1F688 # LIGHT RAIL (LRT) : "🚙" U1F699 # RECREATIONAL VEHICLE (SUV) : "🛸" U1F6F8 # FLYING SAUCER (UFO) +

: "🚧" U1F6A7 # CONSTRUCTION SIGN (WIP) : "🏧" U1F3E7 # AUTOMATED TELLER MACHINE (conflicts with useless @) : "🧬" U1F9EC # DNA DOUBLE HELIX @@ -30094,7 +30095,7 @@ include "Logograms" : "👶" U1F476 # BABY (conflicts with ă, use ua) (use diaper or nappy for 🚼) : "😄" U1F604 # SMILING FACE WITH OPEN MOUTH AND SMILING EYES (BEAMY) (conflicts with ĕ, use ue) : "😳" U1F633 # FLUSHED FACE (BLUSH) - : "👻" U1F47B # GHOST (BOO!) + : "👻" U1F47B # GHOST (BOO!) (conflicts with ŏ, use uo) : "🤡" U1F921 # CLOWN FACE (conflicts with ľ, use vl) : "🥶" U1F976 # FREEZING FACE (COLD) (conflicts with ǒ, use vo) : "😎" U1F60E # SMILING FACE WITH SUNGLASSES (COOL) (conflicts with ǒ, use vo) @@ -30105,6 +30106,7 @@ include "Logograms" : "🤨" U1F928 # FACE WITH ONE EYEBROW RAISED (DOUBT) : "🤤" U1F924 # DROOLING FACE : "🥴" U1F974 # FACE WITH UNEVEN EYES AND WAVY MOUTH (DRUNK) + : "😳" U1F633 # FLUSHED FACE (EMBARRASSED) : "😨" U1F628 # FEARFUL FACE (use argh for 😱) : "(◕‿◕✿)" # FLOWER GIRL : "😦" U1F626 # FROWNING FACE WITH OPEN MOUTH (use :( for ☹️ and upset for 🙍) From a1eb4454e38b8aa968b9b5cd27f0bbef4878415b Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Fri, 3 Jul 2026 13:36:12 +0100 Subject: [PATCH 7/8] A few Unicode 18 musical symbols --- Compose | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/Compose b/Compose index f560f6b..799db59 100644 --- a/Compose +++ b/Compose @@ -34286,6 +34286,7 @@ include "Logograms" # rests : "𝄩" U1D129 # MUSICAL SYMBOL MULTIPLE MEASURE REST + : "𝇿" U1D1FF # MUSICAL SYMBOL LONGA REST (LONGA) : "𝄺" U1D13A # MUSICAL SYMBOL MULTI REST (BREVE) : "𝄻" U1D13B # MUSICAL SYMBOL WHOLE REST (SEMIBREVE) : "𝄼" U1D13C # MUSICAL SYMBOL HALF REST (MINIM) @@ -34303,6 +34304,9 @@ include "Logograms" <3> <2> : "𝅀" U1D140 # MUSICAL SYMBOL THIRTY-SECOND REST <6> <4> : "𝅁" U1D141 # MUSICAL SYMBOL SIXTY-FOURTH REST <1> <2> <8> : "𝅂" U1D142 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH REST + <2> <5> <6> : "𝉓" U1D253 # MUSICAL SYMBOL TWO HUNDRED FIFTY-SIXTH REST + <5> <1> <2> : "𝉔" U1D254 # MUSICAL SYMBOL FIVE HUNDRED TWELFTH REST + <1> <0> <2> <4> : "𝉕" U1D255 # MUSICAL SYMBOL ONE THOUSAND TWENTY-FOURTH REST : "𝅭" U1D16D # MUSICAL SYMBOL COMBINING AUGMENTATION DOT # accidentals and time signatures @@ -34321,6 +34325,19 @@ include "Logograms" <4> : "𝄳" U1D133 # MUSICAL SYMBOL QUARTER TONE FLAT <4> <4> : "𝄴" U1D134 # MUSICAL SYMBOL COMMON TIME <2> <2> : "𝄵" U1D135 # MUSICAL SYMBOL CUT TIME +# TODO: confirm Unicode 18 additions + <1> <4> : "𝇫" U1D1EB # MUSICAL SYMBOL HALF SHARP + <3> <4> : "𝇬" U1D1EC # MUSICAL SYMBOL ONE AND A HALF SHARP + <1> <4> : "𝇭" U1D1ED # MUSICAL SYMBOL REVERSED FLAT + <3> <4> : "𝇮" U1D1EE # MUSICAL SYMBOL REVERSED FLAT AND FLAT + <1> <4> : "𝇯" U1D1EF # MUSICAL SYMBOL HALF SHARP UP + <1> <4> : "𝇰" U1D1F0 # MUSICAL SYMBOL HALF SHARP DOWN + <3> <4> : "𝇱" U1D1F1 # MUSICAL SYMBOL ONE AND A HALF SHARP UP + <3> <4> : "𝇲" U1D1F2 # MUSICAL SYMBOL ONE AND A HALF SHARP DOWN + <1> <4> : "𝇳" U1D1F3 # MUSICAL SYMBOL REVERSED FLAT UP + <1> <4> : "𝇴" U1D1F4 # MUSICAL SYMBOL REVERSED FLAT DOWN + <3> <4> : "𝇵" U1D1F5 # MUSICAL SYMBOL REVERSED FLAT AND FLAT UP + <3> <4> : "𝇶" U1D1F6 # MUSICAL SYMBOL REVERSED FLAT AND FLAT DOWN # note heads : "𝅃" U1D143 # MUSICAL SYMBOL X NOTEHEAD @@ -34357,6 +34374,9 @@ include "Logograms" <3> : "𝅰" U1D170 # MUSICAL SYMBOL COMBINING FLAG-3 <4> : "𝅱" U1D171 # MUSICAL SYMBOL COMBINING FLAG-4 <5> : "𝅲" U1D172 # MUSICAL SYMBOL COMBINING FLAG-5 + <6> : "𝉐" U1D250 # MUSICAL SYMBOL COMBINING FLAG-6 + <7> : "𝉑" U1D251 # MUSICAL SYMBOL COMBINING FLAG-7 + <8> : "𝉒" U1D252 # MUSICAL SYMBOL COMBINING FLAG-8 # beams and slurs : "𝅳" U1D173 # MUSICAL SYMBOL BEGIN BEAM From de8f5ad54389597ae7104bb923cc344e6d8b66df Mon Sep 17 00:00:00 2001 From: Uri Granta Date: Fri, 3 Jul 2026 13:39:54 +0100 Subject: [PATCH 8/8] count --- Compose.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Compose.md b/Compose.md index 79c9c69..57f8ccd 100644 --- a/Compose.md +++ b/Compose.md @@ -50,14 +50,14 @@ The file aims for memorability and consistency. As a result, a small number of t * **Logograms/undeciphered**: Anatolian Hieroglyphs, Cuneiform, Cypro-Minoan, Egyptian Hieroglyphs, Linear A&B, Phaistos Disc (4835): 𔐅 𒆛 𒿌 𓀁 𐙞 𐇑 etc * Language names (150): 🇯🇵 日本語 🇮🇷 ⁧فارس⁩ 🇻🇳 Tiếng Việt etc -### Symbols (6327) +### Symbols (6346) * **Emoji** (1531): 😉 👌🏾 🇳🇿 🫡 👉🏼 💔 🤣 🤦🏽‍♀️ 🏳️‍⚧️ ✨ etc * **Sprites** (247): 🗫 🯅 ㋡ etc * **Math and science** (676): ρ(∂v⃗/∂t + (v⃗·∇)v) ∫πeⁱᶿ dθ etc. * **APL** (107): ⍟ ⍫ ⍉ etc * **Technical** (108): ⏻ ⎙ ⌘ etc * **Numerals** (403): 𝍸𝍷 𝍵 Ⅻ ↁ etc -* **Music** (578): 𝄞 𝅗𝅨𝅥 𝅃𝅥𝅮 𝆍𝆑𝆎 etc +* **Music** (597): 𝄞 𝅗𝅨𝅥 𝅃𝅥𝅮 𝆍𝆑𝆎 etc * **Games** (366): ♞c6 🩡 🂽 🁖 🀄︎ etc * **Astrology** (113): ♈ 🐉 🌒 ☿ ♇ etc * **Alchemical symbols** (116): 🜇 🜢 🝖 etc