scuffed-code/icu4c/source/data/translit/Latin_ASCII.txt
2016-06-15 18:58:17 +00:00

771 lines
39 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# ***************************************************************************
# Copyright (C) 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# *
# * Copyright (C) 2004-2016, International Business Machines
# * Corporation; Unicode, Inc.; and others. All Rights Reserved.
# *
# ***************************************************************************
# File: Latin_ASCII.txt
# Generated from CLDR
#
# This handles only Latin, Common, and IDEOGRAPHIC NUMBER ZERO (Han).
#
:: [[:Latin:][:Common:][:Inherited:][]] ;
#
# Don't want NFKD, because that would convert things like superscripts and
# subscripts, which we do not want. So the individual transforms below
# include an appropriate subset of the NFKD ones.
# Here we remove accents from Latin characters. We then recompose to permit rules
# such as mapping NOT EQUAL TO to an ASCII equivalent e.g. "!=" if we choose to.
#
:: NFD() ;
[:Latin:] { [:Mn:]+ → ; # maps to nothing; remove all Mn following Latin letter
:: NFC() ;
#
# Some of the following mappings (noted) are from CLDR character-fallback data.
# (Note, here "character-fallback" uses U+2039/U+203A to avoid XML issues)
#
# Latin letters and IPA
#
Æ → AE ; # 00C6;LATIN CAPITAL LETTER AE (from character-fallback)
Ð → D ; # 00D0;LATIN CAPITAL LETTER ETH
Ø → O ; # 00D8;LATIN CAPITAL LETTER O WITH STROKE
Þ → TH ; # 00DE;LATIN CAPITAL LETTER THORN
ß → ss ; # 00DF;LATIN SMALL LETTER SHARP S (from character-fallback)
æ → ae ; # 00E6;LATIN SMALL LETTER AE (from character-fallback)
ð → d ; # 00F0;LATIN SMALL LETTER ETH
ø → o ; # 00F8;LATIN SMALL LETTER O WITH STROKE
þ → th ; # 00FE;LATIN SMALL LETTER THORN
Đ → D ; # 0110;LATIN CAPITAL LETTER D WITH STROKE
đ → d ; # 0111;LATIN SMALL LETTER D WITH STROKE
Ħ → H ; # 0126;LATIN CAPITAL LETTER H WITH STROKE
ħ → h ; # 0126;LATIN SMALL LETTER H WITH STROKE
ı → i ; # 0131;LATIN SMALL LETTER DOTLESS I
IJ → IJ ; # 0132;LATIN CAPITAL LIGATURE IJ (compat)
ij → ij ; # 0133;LATIN SMALL LIGATURE IJ (compat)
ĸ → q ; # 0138;LATIN SMALL LETTER KRA (collates with q in DUCET)
Ŀ → L ; # 013F;LATIN CAPITAL LETTER L WITH MIDDLE DOT (compat)
ŀ → l ; # 0140;LATIN SMALL LETTER L WITH MIDDLE DOT (compat)
Ł → L ; # 0141;LATIN CAPITAL LETTER L WITH STROKE
ł → l ; # 0142;LATIN SMALL LETTER L WITH STROKE
ʼn → \'n ; # 0149;LATIN SMALL LETTER N PRECEDED BY APOSTROPHE (from character-fallback)
Ŋ → N ; # 014A;LATIN CAPITAL LETTER ENG
ŋ → n ; # 014B;LATIN SMALL LETTER ENG
Œ → OE ; # 0152;LATIN CAPITAL LIGATURE OE (from character-fallback)
œ → oe ; # 0153;LATIN SMALL LIGATURE OE (from character-fallback)
Ŧ → T ; # 0166;LATIN CAPITAL LETTER T WITH STROKE
ŧ → t ; # 0167;LATIN SMALL LETTER T WITH STROKE
ſ → s ; # 017F;LATIN SMALL LETTER LONG S (compat)
ƀ → b ; # 0180;LATIN SMALL LETTER B WITH STROKE
Ɓ → B ; # 0181;LATIN CAPITAL LETTER B WITH HOOK
Ƃ → B ; # 0182;LATIN CAPITAL LETTER B WITH TOPBAR
ƃ → b ; # 0183;LATIN SMALL LETTER B WITH TOPBAR
Ƈ → C ; # 0187;LATIN CAPITAL LETTER C WITH HOOK
ƈ → c ; # 0188;LATIN SMALL LETTER C WITH HOOK
Ɖ → D ; # 0189;LATIN CAPITAL LETTER AFRICAN D
Ɗ → D ; # 018A;LATIN CAPITAL LETTER D WITH HOOK
Ƌ → D ; # 018B;LATIN CAPITAL LETTER D WITH TOPBAR
ƌ → d ; # 018C;LATIN SMALL LETTER D WITH TOPBAR
Ɛ → E ; # 0190;LATIN CAPITAL LETTER OPEN E
Ƒ → F ; # 0191;LATIN CAPITAL LETTER F WITH HOOK
ƒ → f ; # 0192;LATIN SMALL LETTER F WITH HOOK
Ɠ → G ; # 0193;LATIN CAPITAL LETTER G WITH HOOK
ƕ → hv ; # 0195;LATIN SMALL LETTER HV
Ɩ → I ; # 0196;LATIN CAPITAL LETTER IOTA
Ɨ → I ; # 0197;LATIN CAPITAL LETTER I WITH STROKE
Ƙ → K ; # 0198;LATIN CAPITAL LETTER K WITH HOOK
ƙ → k ; # 0199;LATIN SMALL LETTER K WITH HOOK
ƚ → l ; # 019A;LATIN SMALL LETTER L WITH BAR
Ɲ → N ; # 019D;LATIN CAPITAL LETTER N WITH LEFT HOOK
ƞ → n ; # 019E;LATIN SMALL LETTER N WITH LONG RIGHT LEG
Ƣ → OI ; # 01A2;LATIN CAPITAL LETTER OI
ƣ → oi ; # 01A3;LATIN SMALL LETTER OI
Ƥ → P ; # 01A4;LATIN CAPITAL LETTER P WITH HOOK
ƥ → p ; # 01A5;LATIN SMALL LETTER P WITH HOOK
ƫ → t ; # 01AB;LATIN SMALL LETTER T WITH PALATAL HOOK
Ƭ → T ; # 01AC;LATIN CAPITAL LETTER T WITH HOOK
ƭ → t ; # 01AD;LATIN SMALL LETTER T WITH HOOK
Ʈ → T ; # 01AE;LATIN CAPITAL LETTER T WITH RETROFLEX HOOK
Ʋ → V ; # 01B2;LATIN CAPITAL LETTER V WITH HOOK
Ƴ → Y ; # 01B3;LATIN CAPITAL LETTER Y WITH HOOK
ƴ → y ; # 01B4;LATIN SMALL LETTER Y WITH HOOK
Ƶ → Z ; # 01B5;LATIN CAPITAL LETTER Z WITH STROKE
ƶ → z ; # 01B6;LATIN SMALL LETTER Z WITH STROKE
DŽ → DZ ; # 01C4;LATIN CAPITAL LETTER DZ WITH CARON (compat)
Dž → Dz ; # 01C5;LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON (compat)
dž → dz ; # 01C6;LATIN SMALL LETTER DZ WITH CARON (compat)
LJ → LJ ; # 01C7;LATIN CAPITAL LETTER LJ (compat)
Lj → Lj ; # 01C8;LATIN CAPITAL LETTER L WITH SMALL LETTER J (compat)
lj → lj ; # 01C9;LATIN SMALL LETTER LJ (compat)
NJ → NJ ; # 01CA;LATIN CAPITAL LETTER NJ (compat)
Nj → Nj ; # 01CB;LATIN CAPITAL LETTER N WITH SMALL LETTER J (compat)
nj → nj ; # 01CC;LATIN SMALL LETTER NJ (compat)
Ǥ → G ; # 01E4;LATIN CAPITAL LETTER G WITH STROKE
ǥ → g ; # 01E5;LATIN SMALL LETTER G WITH STROKE
DZ → DZ ; # 01F1;LATIN CAPITAL LETTER DZ (compat)
Dz → Dz ; # 01F2;LATIN CAPITAL LETTER D WITH SMALL LETTER Z (compat)
dz → dz ; # 01F3;LATIN SMALL LETTER DZ (compat)
ȡ → d ; # 0221;LATIN SMALL LETTER D WITH CURL
Ȥ → Z ; # 0224;LATIN CAPITAL LETTER Z WITH HOOK
ȥ → z ; # 0225;LATIN SMALL LETTER Z WITH HOOK
ȴ → l ; # 0234;LATIN SMALL LETTER L WITH CURL
ȵ → n ; # 0235;LATIN SMALL LETTER N WITH CURL
ȶ → t ; # 0236;LATIN SMALL LETTER T WITH CURL
ȷ → j ; # 0237;LATIN SMALL LETTER DOTLESS J
ȸ → db ; # 0238;LATIN SMALL LETTER DB DIGRAPH
ȹ → qp ; # 0239;LATIN SMALL LETTER QP DIGRAPH
Ⱥ → A ; # 023A;LATIN CAPITAL LETTER A WITH STROKE
Ȼ → C ; # 023B;LATIN CAPITAL LETTER C WITH STROKE
ȼ → c ; # 023C;LATIN SMALL LETTER C WITH STROKE
Ƚ → L ; # 023D;LATIN CAPITAL LETTER L WITH BAR
Ⱦ → T ; # 023E;LATIN CAPITAL LETTER T WITH DIAGONAL STROKE
ȿ → s ; # 023F;LATIN SMALL LETTER S WITH SWASH TAIL
ɀ → z ; # 0240;LATIN SMALL LETTER Z WITH SWASH TAIL
Ƀ → B ; # 0243;LATIN CAPITAL LETTER B WITH STROKE
Ʉ → U ; # 0244;LATIN CAPITAL LETTER U BAR
Ɇ → E ; # 0246;LATIN CAPITAL LETTER E WITH STROKE
ɇ → e ; # 0247;LATIN SMALL LETTER E WITH STROKE
Ɉ → J ; # 0248;LATIN CAPITAL LETTER J WITH STROKE
ɉ → j ; # 0249;LATIN SMALL LETTER J WITH STROKE
Ɍ → R ; # 024C;LATIN CAPITAL LETTER R WITH STROKE
ɍ → r ; # 024D;LATIN SMALL LETTER R WITH STROKE
Ɏ → Y ; # 024E;LATIN CAPITAL LETTER Y WITH STROKE
ɏ → y ; # 024F;LATIN SMALL LETTER Y WITH STROKE
ɓ → b ; # 0253;LATIN SMALL LETTER B WITH HOOK
ɕ → c ; # 0255;LATIN SMALL LETTER C WITH CURL
ɖ → d ; # 0256;LATIN SMALL LETTER D WITH TAIL
ɗ → d ; # 0257;LATIN SMALL LETTER D WITH HOOK
ɛ → e ; # 025B;LATIN SMALL LETTER OPEN E
ɟ → j ; # 025F;LATIN SMALL LETTER DOTLESS J WITH STROKE
ɠ → g ; # 0260;LATIN SMALL LETTER G WITH HOOK
ɡ → g ; # 0261;LATIN SMALL LETTER SCRIPT G
ɢ → G ; # 0262;LATIN LETTER SMALL CAPITAL G
ɦ → h ; # 0266;LATIN SMALL LETTER H WITH HOOK
ɧ → h ; # 0267;LATIN SMALL LETTER HENG WITH HOOK
ɨ → i ; # 0268;LATIN SMALL LETTER I WITH STROKE
ɪ → I ; # 026A;LATIN LETTER SMALL CAPITAL I
ɫ → l ; # 026B;LATIN SMALL LETTER L WITH MIDDLE TILDE
ɬ → l ; # 026C;LATIN SMALL LETTER L WITH BELT
ɭ → l ; # 026D;LATIN SMALL LETTER L WITH RETROFLEX HOOK
ɱ → m ; # 0271;LATIN SMALL LETTER M WITH HOOK
ɲ → n ; # 0272;LATIN SMALL LETTER N WITH LEFT HOOK
ɳ → n ; # 0273;LATIN SMALL LETTER N WITH RETROFLEX HOOK
ɴ → N ; # 0274;LATIN LETTER SMALL CAPITAL N
ɶ → OE ; # 0276;LATIN LETTER SMALL CAPITAL OE
ɼ → r ; # 027C;LATIN SMALL LETTER R WITH LONG LEG
ɽ → r ; # 027D;LATIN SMALL LETTER R WITH TAIL
ɾ → r ; # 027E;LATIN SMALL LETTER R WITH FISHHOOK
ʀ → R ; # 0280;LATIN LETTER SMALL CAPITAL R
ʂ → s ; # 0282;LATIN SMALL LETTER S WITH HOOK
ʈ → t ; # 0288;LATIN SMALL LETTER T WITH RETROFLEX HOOK
ʉ → u ; # 0289;LATIN SMALL LETTER U BAR
ʋ → v ; # 028B;LATIN SMALL LETTER V WITH HOOK
ʏ → Y ; # 028F;LATIN LETTER SMALL CAPITAL Y
ʐ → z ; # 0290;LATIN SMALL LETTER Z WITH RETROFLEX HOOK
ʑ → z ; # 0291;LATIN SMALL LETTER Z WITH CURL
ʙ → B ; # 0299;LATIN LETTER SMALL CAPITAL B
ʛ → G ; # 029B;LATIN LETTER SMALL CAPITAL G WITH HOOK
ʜ → H ; # 029C;LATIN LETTER SMALL CAPITAL H
ʝ → j ; # 029D;LATIN SMALL LETTER J WITH CROSSED-TAIL
ʟ → L ; # 029F;LATIN LETTER SMALL CAPITAL L
ʠ → q ; # 02A0;LATIN SMALL LETTER Q WITH HOOK
ʣ → dz ; # 02A3;LATIN SMALL LETTER DZ DIGRAPH
ʥ → dz ; # 02A5;LATIN SMALL LETTER DZ DIGRAPH WITH CURL
ʦ → ts ; # 02A6;LATIN SMALL LETTER TS DIGRAPH
ʪ → ls ; # 02AA;LATIN SMALL LETTER LS DIGRAPH
ʫ → lz ; # 02AB;LATIN SMALL LETTER LZ DIGRAPH
ᴀ → A ; # 1D00;LATIN LETTER SMALL CAPITAL A
ᴁ → AE ; # 1D01;LATIN LETTER SMALL CAPITAL AE
ᴃ → B ; # 1D03;LATIN LETTER SMALL CAPITAL BARRED B
→ C ; # 1D04;LATIN LETTER SMALL CAPITAL C
ᴅ → D ; # 1D05;LATIN LETTER SMALL CAPITAL D
ᴆ → D ; # 1D06;LATIN LETTER SMALL CAPITAL ETH
ᴇ → E ; # 1D07;LATIN LETTER SMALL CAPITAL E
ᴊ → J ; # 1D0A;LATIN LETTER SMALL CAPITAL J
ᴋ → K ; # 1D0B;LATIN LETTER SMALL CAPITAL K
ᴌ → L ; # 1D0C;LATIN LETTER SMALL CAPITAL L WITH STROKE
ᴍ → M ; # 1D0D;LATIN LETTER SMALL CAPITAL M
→ O ; # 1D0F;LATIN LETTER SMALL CAPITAL O
ᴘ → P ; # 1D18;LATIN LETTER SMALL CAPITAL P
ᴛ → T ; # 1D1B;LATIN LETTER SMALL CAPITAL T
→ U ; # 1D1C;LATIN LETTER SMALL CAPITAL U
→ V ; # 1D20;LATIN LETTER SMALL CAPITAL V
→ W ; # 1D21;LATIN LETTER SMALL CAPITAL W
→ Z ; # 1D22;LATIN LETTER SMALL CAPITAL Z
ᵫ → ue ; # 1D6B;LATIN SMALL LETTER UE
ᵬ → b ; # 1D6C;LATIN SMALL LETTER B WITH MIDDLE TILDE
ᵭ → d ; # 1D6D;LATIN SMALL LETTER D WITH MIDDLE TILDE
ᵮ → f ; # 1D6E;LATIN SMALL LETTER F WITH MIDDLE TILDE
ᵯ → m ; # 1D6F;LATIN SMALL LETTER M WITH MIDDLE TILDE
ᵰ → n ; # 1D70;LATIN SMALL LETTER N WITH MIDDLE TILDE
ᵱ → p ; # 1D71;LATIN SMALL LETTER P WITH MIDDLE TILDE
ᵲ → r ; # 1D72;LATIN SMALL LETTER R WITH MIDDLE TILDE
ᵳ → r ; # 1D73;LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE
ᵴ → s ; # 1D74;LATIN SMALL LETTER S WITH MIDDLE TILDE
ᵵ → t ; # 1D75;LATIN SMALL LETTER T WITH MIDDLE TILDE
ᵶ → z ; # 1D76;LATIN SMALL LETTER Z WITH MIDDLE TILDE
ᵺ → th ; # 1D7A;LATIN SMALL LETTER TH WITH STRIKETHROUGH
ᵻ → I ; # 1D7B;LATIN SMALL CAPITAL LETTER I WITH STROKE
ᵽ → p ; # 1D7D;LATIN SMALL LETTER P WITH STROKE
ᵾ → U ; # 1D7E;LATIN SMALL CAPITAL LETTER U WITH STROKE
ᶀ → b ; # 1D80;LATIN SMALL LETTER B WITH PALATAL HOOK
ᶁ → d ; # 1D81;LATIN SMALL LETTER D WITH PALATAL HOOK
ᶂ → f ; # 1D82;LATIN SMALL LETTER F WITH PALATAL HOOK
→ g ; # 1D83;LATIN SMALL LETTER G WITH PALATAL HOOK
ᶄ → k ; # 1D84;LATIN SMALL LETTER K WITH PALATAL HOOK
ᶅ → l ; # 1D85;LATIN SMALL LETTER L WITH PALATAL HOOK
ᶆ → m ; # 1D86;LATIN SMALL LETTER M WITH PALATAL HOOK
ᶇ → n ; # 1D87;LATIN SMALL LETTER N WITH PALATAL HOOK
ᶈ → p ; # 1D88;LATIN SMALL LETTER P WITH PALATAL HOOK
ᶉ → r ; # 1D89;LATIN SMALL LETTER R WITH PALATAL HOOK
ᶊ → s ; # 1D8A;LATIN SMALL LETTER S WITH PALATAL HOOK
→ v ; # 1D8C;LATIN SMALL LETTER V WITH PALATAL HOOK
ᶍ → x ; # 1D8D;LATIN SMALL LETTER X WITH PALATAL HOOK
ᶎ → z ; # 1D8E;LATIN SMALL LETTER Z WITH PALATAL HOOK
ᶏ → a ; # 1D8F;LATIN SMALL LETTER A WITH RETROFLEX HOOK
ᶑ → d ; # 1D91;LATIN SMALL LETTER D WITH HOOK AND TAIL
ᶒ → e ; # 1D92;LATIN SMALL LETTER E WITH RETROFLEX HOOK
ᶓ → e ; # 1D93;LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK
ᶖ → i ; # 1D96;LATIN SMALL LETTER I WITH RETROFLEX HOOK
ᶙ → u ; # 1D99;LATIN SMALL LETTER U WITH RETROFLEX HOOK
ẚ → a ; # 1E9A;LATIN SMALL LETTER A WITH RIGHT HALF RING
ẜ → s ; # 1E9C;LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE
→ s ; # 1E9D;LATIN SMALL LETTER LONG S WITH HIGH STROKE
ẞ → SS ; # 1E9E;LATIN CAPITAL LETTER SHARP S
Ỻ → LL ; # 1EFA;LATIN CAPITAL LETTER MIDDLE-WELSH LL
ỻ → ll ; # 1EFB;LATIN SMALL LETTER MIDDLE-WELSH LL
Ỽ → V ; # 1EFC;LATIN CAPITAL LETTER MIDDLE-WELSH V
ỽ → v ; # 1EFD;LATIN SMALL LETTER MIDDLE-WELSH V
Ỿ → Y ; # 1EFE;LATIN CAPITAL LETTER Y WITH LOOP
ỿ → y ; # 1EFF;LATIN SMALL LETTER Y WITH LOOP
# Presentation forms
ff → ff ; # FB00;LATIN SMALL LIGATURE FF (compat)
fi → fi ; # FB01;LATIN SMALL LIGATURE FI (compat)
fl → fl ; # FB02;LATIN SMALL LIGATURE FL (compat)
ffi → ffi ; # FB03;LATIN SMALL LIGATURE FFI (compat)
ffl → ffl ; # FB04;LATIN SMALL LIGATURE FFL (compat)
ſt → st ; # FB05;LATIN SMALL LIGATURE LONG S T (compat)
st → st ; # FB06;LATIN SMALL LIGATURE ST (compat)
# Fullwidth
→ A ; # FF21;FULLWIDTH LATIN CAPITAL LETTER A (compat)
→ B ; # FF22;FULLWIDTH LATIN CAPITAL LETTER B (compat)
→ C ; # FF23;FULLWIDTH LATIN CAPITAL LETTER C (compat)
→ D ; # FF24;FULLWIDTH LATIN CAPITAL LETTER D (compat)
→ E ; # FF25;FULLWIDTH LATIN CAPITAL LETTER E (compat)
→ F ; # FF26;FULLWIDTH LATIN CAPITAL LETTER F (compat)
→ G ; # FF27;FULLWIDTH LATIN CAPITAL LETTER G (compat)
→ H ; # FF28;FULLWIDTH LATIN CAPITAL LETTER H (compat)
→ I ; # FF29;FULLWIDTH LATIN CAPITAL LETTER I (compat)
→ J ; # FF2A;FULLWIDTH LATIN CAPITAL LETTER J (compat)
→ K ; # FF2B;FULLWIDTH LATIN CAPITAL LETTER K (compat)
→ L ; # FF2C;FULLWIDTH LATIN CAPITAL LETTER L (compat)
→ M ; # FF2D;FULLWIDTH LATIN CAPITAL LETTER M (compat)
→ N ; # FF2E;FULLWIDTH LATIN CAPITAL LETTER N (compat)
→ O ; # FF2F;FULLWIDTH LATIN CAPITAL LETTER O (compat)
→ P ; # FF30;FULLWIDTH LATIN CAPITAL LETTER P (compat)
→ Q ; # FF31;FULLWIDTH LATIN CAPITAL LETTER Q (compat)
→ R ; # FF32;FULLWIDTH LATIN CAPITAL LETTER R (compat)
→ S ; # FF33;FULLWIDTH LATIN CAPITAL LETTER S (compat)
→ T ; # FF34;FULLWIDTH LATIN CAPITAL LETTER T (compat)
→ U ; # FF35;FULLWIDTH LATIN CAPITAL LETTER U (compat)
→ V ; # FF36;FULLWIDTH LATIN CAPITAL LETTER V (compat)
→ W ; # FF37;FULLWIDTH LATIN CAPITAL LETTER W (compat)
→ X ; # FF38;FULLWIDTH LATIN CAPITAL LETTER X (compat)
→ Y ; # FF39;FULLWIDTH LATIN CAPITAL LETTER Y (compat)
→ Z ; # FF3A;FULLWIDTH LATIN CAPITAL LETTER Z (compat)
→ a ; # FF41;FULLWIDTH LATIN SMALL LETTER A (compat)
→ b ; # FF42;FULLWIDTH LATIN SMALL LETTER B (compat)
→ c ; # FF43;FULLWIDTH LATIN SMALL LETTER C (compat)
→ d ; # FF44;FULLWIDTH LATIN SMALL LETTER D (compat)
→ e ; # FF45;FULLWIDTH LATIN SMALL LETTER E (compat)
→ f ; # FF46;FULLWIDTH LATIN SMALL LETTER F (compat)
→ g ; # FF47;FULLWIDTH LATIN SMALL LETTER G (compat)
→ h ; # FF48;FULLWIDTH LATIN SMALL LETTER H (compat)
→ i ; # FF49;FULLWIDTH LATIN SMALL LETTER I (compat)
→ j ; # FF4A;FULLWIDTH LATIN SMALL LETTER J (compat)
→ k ; # FF4B;FULLWIDTH LATIN SMALL LETTER K (compat)
→ l ; # FF4C;FULLWIDTH LATIN SMALL LETTER L (compat)
→ m ; # FF4D;FULLWIDTH LATIN SMALL LETTER M (compat)
→ n ; # FF4E;FULLWIDTH LATIN SMALL LETTER N (compat)
→ o ; # FF4F;FULLWIDTH LATIN SMALL LETTER O (compat)
→ p ; # FF50;FULLWIDTH LATIN SMALL LETTER P (compat)
→ q ; # FF51;FULLWIDTH LATIN SMALL LETTER Q (compat)
→ r ; # FF52;FULLWIDTH LATIN SMALL LETTER R (compat)
→ s ; # FF53;FULLWIDTH LATIN SMALL LETTER S (compat)
→ t ; # FF54;FULLWIDTH LATIN SMALL LETTER T (compat)
→ u ; # FF55;FULLWIDTH LATIN SMALL LETTER U (compat)
→ v ; # FF56;FULLWIDTH LATIN SMALL LETTER V (compat)
→ w ; # FF57;FULLWIDTH LATIN SMALL LETTER W (compat)
→ x ; # FF58;FULLWIDTH LATIN SMALL LETTER X (compat)
→ y ; # FF59;FULLWIDTH LATIN SMALL LETTER Y (compat)
→ z ; # FF5A;FULLWIDTH LATIN SMALL LETTER Z (compat)
#
# Currency and letterlike
#
© → '(C)' ; # 00A9;COPYRIGHT SIGN (from character-fallback)
® → '(R)' ; # 00AE;REGISTERED SIGN (from character-fallback)
₠ → CE ; # 20A0;EURO-CURRENCY SIGN (from character-fallback)
₢ → Cr ; # 20A2;CRUZEIRO SIGN (from character-fallback)
₣ → 'Fr.' ; # 20A3;FRENCH FRANC SIGN (from character-fallback)
₤ → 'L.' ; # 20A4;LIRA SIGN (from character-fallback)
₧ → Pts ; # 20A7;PESETA SIGN (from character-fallback)
₺ → TL ; # 20BA;TURKISH LIRA SIGN (from character-fallback)
₹ → Rs ; # 20B9;INDIAN RUPEE SIGN (from character-fallback)
℀ → 'a/c' ; # 2100;ACCOUNT OF (compat)
℁ → 'a/s' ; # 2101;ADDRESSED TO THE SUBJECT (compat)
→ C ; # 2102;DOUBLE-STRUCK CAPITAL C (compat)
℅ → 'c/o' ; # 2105;CARE OF (compat)
℆ → 'c/u' ; # 2106;CADA UNA (compat)
→ g ; # 210A;SCRIPT SMALL G (compat)
→ H ; # 210B;SCRIPT CAPITAL H (compat)
→ x ; # 210C;BLACK-LETTER CAPITAL H (compat)
→ H ; # 210D;DOUBLE-STRUCK CAPITAL H (compat)
→ h ; # 210E;PLANCK CONSTANT (compat)
→ I ; # 2110;SCRIPT CAPITAL I (compat)
→ I ; # 2111;BLACK-LETTER CAPITAL I (compat)
→ L ; # 2112;SCRIPT CAPITAL L (compat)
→ l ; # 2113;SCRIPT SMALL L (compat)
→ N ; # 2115;DOUBLE-STRUCK CAPITAL N (compat)
№ → No ; # 2116;NUMERO SIGN (compat)
→ P ; # 2119;DOUBLE-STRUCK CAPITAL P (compat)
→ Q ; # 211A;DOUBLE-STRUCK CAPITAL Q (compat)
→ R ; # 211B;SCRIPT CAPITAL R (compat)
→ R ; # 211C;BLACK-LETTER CAPITAL R (compat)
→ R ; # 211D;DOUBLE-STRUCK CAPITAL R (compat)
℞ → Rx ; # 211E;PRESCRIPTION TAKE (from character-fallback)
℡ → TEL ; # 2121;TELEPHONE SIGN (compat)
→ Z ; # 2124;DOUBLE-STRUCK CAPITAL Z (compat)
→ Z ; # 2128;BLACK-LETTER CAPITAL Z (compat)
→ B ; # 212C;SCRIPT CAPITAL B (compat)
→ C ; # 212D;BLACK-LETTER CAPITAL C (compat)
→ e ; # 212F;SCRIPT SMALL E (compat)
→ E ; # 2130;SCRIPT CAPITAL E (compat)
→ F ; # 2131;SCRIPT CAPITAL F (compat)
→ M ; # 2133;SCRIPT CAPITAL M (compat)
→ o ; # 2134;SCRIPT SMALL O (compat)
→ i ; # 2139;INFORMATION SOURCE (compat)
℻ → FAX ; # 213B;FACSIMILE SIGN (compat)
→ D ; # 2145;DOUBLE-STRUCK ITALIC CAPITAL D (compat)
→ d ; # 2146;DOUBLE-STRUCK ITALIC SMALL D (compat)
→ e ; # 2147;DOUBLE-STRUCK ITALIC SMALL E (compat)
→ i ; # 2148;DOUBLE-STRUCK ITALIC SMALL I (compat)
→ j ; # 2149;DOUBLE-STRUCK ITALIC SMALL J (compat)
#
# Squared Latin
#
㍱ → hPa ; # 3371;SQUARE HPA (compat)
㍲ → da ; # 3372;SQUARE DA (compat)
㍳ → AU ; # 3373;SQUARE AU (compat)
㍴ → bar ; # 3374;SQUARE BAR (compat)
㍵ → oV ; # 3375;SQUARE OV (compat)
㍶ → pc ; # 3376;SQUARE PC (compat)
㍷ → dm ; # 3377;SQUARE DM (compat)
㍺ → IU ; # 337A;SQUARE IU (compat)
㎀ → pA ; # 3380;SQUARE PA AMPS (compat)
㎁ → nA ; # 3381;SQUARE NA (compat)
㎃ → mA ; # 3383;SQUARE MA (compat)
㎄ → kA ; # 3384;SQUARE KA (compat)
㎅ → KB ; # 3385;SQUARE KB (compat)
㎆ → MB ; # 3386;SQUARE MB (compat)
㎇ → GB ; # 3387;SQUARE GB (compat)
㎈ → cal ; # 3388;SQUARE CAL (compat)
㎉ → kcal ; # 3389;SQUARE KCAL (compat)
㎊ → pF ; # 338A;SQUARE PF (compat)
㎋ → nF ; # 338B;SQUARE NF (compat)
㎎ → mg ; # 338E;SQUARE MG (compat)
㎏ → kg ; # 338F;SQUARE KG (compat)
㎐ → Hz ; # 3390;SQUARE HZ (compat)
㎑ → kHz ; # 3391;SQUARE KHZ (compat)
㎒ → MHz ; # 3392;SQUARE MHZ (compat)
㎓ → GHz ; # 3393;SQUARE GHZ (compat)
㎔ → THz ; # 3394;SQUARE THZ (compat)
㎙ → fm ; # 3399;SQUARE FM (compat)
㎚ → nm ; # 339A;SQUARE NM (compat)
㎜ → mm ; # 339C;SQUARE MM (compat)
㎝ → cm ; # 339D;SQUARE CM (compat)
㎞ → km ; # 339E;SQUARE KM (compat)
㎧ → 'm/s' ; # 33A7;SQUARE M OVER S (compat) (from character-fallback)
㎩ → Pa ; # 33A9;SQUARE PA (compat)
㎪ → kPa ; # 33AA;SQUARE KPA (compat)
㎫ → MPa ; # 33AB;SQUARE MPA (compat)
㎬ → GPa ; # 33AC;SQUARE GPA (compat)
㎭ → rad ; # 33AD;SQUARE RAD (compat)
㎮ → 'rad/s' ; # 33AE;SQUARE RAD OVER S (compat) (from character-fallback)
㎰ → ps ; # 33B0;SQUARE PS (compat)
㎱ → ns ; # 33B1;SQUARE NS (compat)
㎳ → ms ; # 33B3;SQUARE MS (compat)
㎴ → pV ; # 33B4;SQUARE PV (compat)
㎵ → nV ; # 33B5;SQUARE NV (compat)
㎷ → mV ; # 33B7;SQUARE MV (compat)
㎸ → kV ; # 33B8;SQUARE KV (compat)
㎹ → MV ; # 33B9;SQUARE MV MEGA (compat)
㎺ → pW ; # 33BA;SQUARE PW (compat)
㎻ → nW ; # 33BB;SQUARE NW (compat)
㎽ → mW ; # 33BD;SQUARE MW (compat)
㎾ → kW ; # 33BE;SQUARE KW (compat)
㎿ → MW ; # 33BF;SQUARE MW MEGA (compat)
㏂ → 'a.m.' ; # 33C2;SQUARE AM (compat)
㏃ → Bq ; # 33C3;SQUARE BQ (compat)
㏄ → cc ; # 33C4;SQUARE CC (compat) (from character-fallback, adj)
㏅ → cd ; # 33C5;SQUARE CD (compat)
㏆ → 'C/kg' ; # 33C6;SQUARE C OVER KG (compat) (from character-fallback)
㏇ → 'Co.' ; # 33C7;SQUARE CO (compat)
㏈ → dB ; # 33C8;SQUARE DB (compat)
㏉ → Gy ; # 33C9;SQUARE GY (compat)
㏊ → ha ; # 33CA;SQUARE HA (compat)
㏋ → HP ; # 33CB;SQUARE HP (compat)
㏌ → in ; # 33CC;SQUARE IN (compat)
㏍ → KK ; # 33CD;SQUARE KK (compat)
㏎ → KM ; # 33CE;SQUARE KM CAPITAL (compat)
㏏ → kt ; # 33CF;SQUARE KT (compat)
㏐ → lm ; # 33D0;SQUARE LM (compat)
㏑ → ln ; # 33D1;SQUARE LN (compat)
㏒ → log ; # 33D2;SQUARE LOG (compat)
㏓ → lx ; # 33D3;SQUARE LX (compat)
㏔ → mb ; # 33D4;SQUARE MB SMALL (compat)
㏕ → mil ; # 33D5;SQUARE MIL (compat)
㏖ → mol ; # 33D6;SQUARE MOL (compat)
㏗ → pH ; # 33D7;SQUARE PH (compat) (from character-fallback)
㏘ → 'p.m.' ; # 33D8;SQUARE PM (compat)
㏙ → PPM ; # 33D9;SQUARE PPM (compat)
㏚ → PR ; # 33DA;SQUARE PR (compat)
㏛ → sr ; # 33DB;SQUARE SR (compat)
㏜ → Sv ; # 33DC;SQUARE SV (compat)
㏝ → Wb ; # 33DD;SQUARE WB (compat)
㏞ → 'V/m' ; # 33DE;SQUARE V OVER M (compat) (from character-fallback)
㏟ → 'A/m' ; # 33DF;SQUARE A OVER M (compat) (from character-fallback)
#
# Enclosed Latin
#
⒜ → '(a)' ; # 249C;PARENTHESIZED LATIN SMALL LETTER A (compat)
⒝ → '(b)' ; # 249D;PARENTHESIZED LATIN SMALL LETTER B (compat)
⒞ → '(c)' ; # 249E;PARENTHESIZED LATIN SMALL LETTER C (compat)
⒟ → '(d)' ; # 249F;PARENTHESIZED LATIN SMALL LETTER D (compat)
⒠ → '(e)' ; # 24A0;PARENTHESIZED LATIN SMALL LETTER E (compat)
⒡ → '(f)' ; # 24A1;PARENTHESIZED LATIN SMALL LETTER F (compat)
⒢ → '(g)' ; # 24A2;PARENTHESIZED LATIN SMALL LETTER G (compat)
⒣ → '(h)' ; # 24A3;PARENTHESIZED LATIN SMALL LETTER H (compat)
⒤ → '(i)' ; # 24A4;PARENTHESIZED LATIN SMALL LETTER I (compat)
⒥ → '(j)' ; # 24A5;PARENTHESIZED LATIN SMALL LETTER J (compat)
⒦ → '(k)' ; # 24A6;PARENTHESIZED LATIN SMALL LETTER K (compat)
⒧ → '(l)' ; # 24A7;PARENTHESIZED LATIN SMALL LETTER L (compat)
⒨ → '(m)' ; # 24A8;PARENTHESIZED LATIN SMALL LETTER M (compat)
⒩ → '(n)' ; # 24A9;PARENTHESIZED LATIN SMALL LETTER N (compat)
⒪ → '(o)' ; # 24AA;PARENTHESIZED LATIN SMALL LETTER O (compat)
⒫ → '(p)' ; # 24AB;PARENTHESIZED LATIN SMALL LETTER P (compat)
⒬ → '(q)' ; # 24AC;PARENTHESIZED LATIN SMALL LETTER Q (compat)
⒭ → '(r)' ; # 24AD;PARENTHESIZED LATIN SMALL LETTER R (compat)
⒮ → '(s)' ; # 24AE;PARENTHESIZED LATIN SMALL LETTER S (compat)
⒯ → '(t)' ; # 24AF;PARENTHESIZED LATIN SMALL LETTER T (compat)
⒰ → '(u)' ; # 24B0;PARENTHESIZED LATIN SMALL LETTER U (compat)
⒱ → '(v)' ; # 24B1;PARENTHESIZED LATIN SMALL LETTER V (compat)
⒲ → '(w)' ; # 24B2;PARENTHESIZED LATIN SMALL LETTER W (compat)
⒳ → '(x)' ; # 24B3;PARENTHESIZED LATIN SMALL LETTER X (compat)
⒴ → '(y)' ; # 24B4;PARENTHESIZED LATIN SMALL LETTER Y (compat)
⒵ → '(z)' ; # 24B5;PARENTHESIZED LATIN SMALL LETTER Z (compat)
#
# Roman numerals
#
→ I ; # 2160;ROMAN NUMERAL ONE (compat)
Ⅱ → II ; # 2161;ROMAN NUMERAL TWO (compat)
Ⅲ → III ; # 2162;ROMAN NUMERAL THREE (compat)
Ⅳ → IV ; # 2163;ROMAN NUMERAL FOUR (compat)
→ V ; # 2164;ROMAN NUMERAL FIVE (compat)
Ⅵ → VI ; # 2165;ROMAN NUMERAL SIX (compat)
Ⅶ → VII ; # 2166;ROMAN NUMERAL SEVEN (compat)
Ⅷ → VIII ; # 2167;ROMAN NUMERAL EIGHT (compat)
Ⅸ → IX ; # 2168;ROMAN NUMERAL NINE (compat)
→ X ; # 2169;ROMAN NUMERAL TEN (compat)
Ⅺ → XI ; # 216A;ROMAN NUMERAL ELEVEN (compat)
Ⅻ → XII ; # 216B;ROMAN NUMERAL TWELVE (compat)
→ L ; # 216C;ROMAN NUMERAL FIFTY (compat)
→ C ; # 216D;ROMAN NUMERAL ONE HUNDRED (compat)
→ D ; # 216E;ROMAN NUMERAL FIVE HUNDRED (compat)
→ M ; # 216F;ROMAN NUMERAL ONE THOUSAND (compat)
→ i ; # 2170;SMALL ROMAN NUMERAL ONE (compat)
ⅱ → ii ; # 2171;SMALL ROMAN NUMERAL TWO (compat)
ⅲ → iii ; # 2172;SMALL ROMAN NUMERAL THREE (compat)
ⅳ → iv ; # 2173;SMALL ROMAN NUMERAL FOUR (compat)
→ v ; # 2174;SMALL ROMAN NUMERAL FIVE (compat)
ⅵ → vi ; # 2175;SMALL ROMAN NUMERAL SIX (compat)
ⅶ → vii ; # 2176;SMALL ROMAN NUMERAL SEVEN (compat)
ⅷ → viii ; # 2177;SMALL ROMAN NUMERAL EIGHT (compat)
ⅸ → ix ; # 2178;SMALL ROMAN NUMERAL NINE (compat)
→ x ; # 2179;SMALL ROMAN NUMERAL TEN (compat)
ⅺ → xi ; # 217A;SMALL ROMAN NUMERAL ELEVEN (compat)
ⅻ → xii ; # 217B;SMALL ROMAN NUMERAL TWELVE (compat)
→ l ; # 217C;SMALL ROMAN NUMERAL FIFTY (compat)
→ c ; # 217D;SMALL ROMAN NUMERAL ONE HUNDRED (compat)
→ d ; # 217E;SMALL ROMAN NUMERAL FIVE HUNDRED (compat)
ⅿ → m ; # 217F;SMALL ROMAN NUMERAL ONE THOUSAND (compat)
#
# Fractions
#
¼ → ' 1/4' ; # 00BC;VULGAR FRACTION ONE QUARTER (from character-fallback)
½ → ' 1/2' ; # 00BD;VULGAR FRACTION ONE HALF (from character-fallback)
¾ → ' 3/4' ; # 00BE;VULGAR FRACTION THREE QUARTERS (from character-fallback)
⅓ → ' 1/3' ; # 2153;VULGAR FRACTION ONE THIRD (from character-fallback)
⅔ → ' 2/3' ; # 2154;VULGAR FRACTION TWO THIRDS (from character-fallback)
⅕ → ' 1/5' ; # 2155;VULGAR FRACTION ONE FIFTH (from character-fallback)
⅖ → ' 2/5' ; # 2156;VULGAR FRACTION TWO FIFTHS (from character-fallback)
⅗ → ' 3/5' ; # 2157;VULGAR FRACTION THREE FIFTHS (from character-fallback)
⅘ → ' 4/5' ; # 2158;VULGAR FRACTION FOUR FIFTHS (from character-fallback)
⅙ → ' 1/6' ; # 2159;VULGAR FRACTION ONE SIXTH (from character-fallback)
⅚ → ' 5/6' ; # 215A;VULGAR FRACTION FIVE SIXTHS (from character-fallback)
⅛ → ' 1/8' ; # 215B;VULGAR FRACTION ONE EIGHTH (from character-fallback)
⅜ → ' 3/8' ; # 215C;VULGAR FRACTION THREE EIGHTHS (from character-fallback)
⅝ → ' 5/8' ; # 215D;VULGAR FRACTION FIVE EIGHTHS (from character-fallback)
⅞ → ' 7/8' ; # 215E;VULGAR FRACTION SEVEN EIGHTHS (from character-fallback)
⅟ → ' 1/' ; # 215F;FRACTION NUMERATOR ONE (from character-fallback)
#
# Enclosed numeric
#
⑴ → '(1)' ; # 2474;PARENTHESIZED DIGIT ONE (compat)
⑵ → '(2)' ; # 2475;PARENTHESIZED DIGIT TWO (compat)
⑶ → '(3)' ; # 2476;PARENTHESIZED DIGIT THREE (compat)
⑷ → '(4)' ; # 2477;PARENTHESIZED DIGIT FOUR (compat)
⑸ → '(5)' ; # 2478;PARENTHESIZED DIGIT FIVE (compat)
⑹ → '(6)' ; # 2479;PARENTHESIZED DIGIT SIX (compat)
⑺ → '(7)' ; # 247A;PARENTHESIZED DIGIT SEVEN (compat)
⑻ → '(8)' ; # 247B;PARENTHESIZED DIGIT EIGHT (compat)
⑼ → '(9)' ; # 247C;PARENTHESIZED DIGIT NINE (compat)
⑽ → '(10)' ; # 247D;PARENTHESIZED NUMBER TEN (compat)
⑾ → '(11)' ; # 247E;PARENTHESIZED NUMBER ELEVEN (compat)
⑿ → '(12)' ; # 247F;PARENTHESIZED NUMBER TWELVE (compat)
⒀ → '(13)' ; # 2480;PARENTHESIZED NUMBER THIRTEEN (compat)
⒁ → '(14)' ; # 2481;PARENTHESIZED NUMBER FOURTEEN (compat)
⒂ → '(15)' ; # 2482;PARENTHESIZED NUMBER FIFTEEN (compat)
⒃ → '(16)' ; # 2483;PARENTHESIZED NUMBER SIXTEEN (compat)
⒄ → '(17)' ; # 2484;PARENTHESIZED NUMBER SEVENTEEN (compat)
⒅ → '(18)' ; # 2485;PARENTHESIZED NUMBER EIGHTEEN (compat)
⒆ → '(19)' ; # 2486;PARENTHESIZED NUMBER NINETEEN (compat)
⒇ → '(20)' ; # 2487;PARENTHESIZED NUMBER TWENTY (compat)
⒈ → '1.' ; # 2488;DIGIT ONE FULL STOP (compat)
⒉ → '2.' ; # 2489;DIGIT TWO FULL STOP (compat)
⒊ → '3.' ; # 248A;DIGIT THREE FULL STOP (compat)
⒋ → '4.' ; # 248B;DIGIT FOUR FULL STOP (compat)
⒌ → '5.' ; # 248C;DIGIT FIVE FULL STOP (compat)
⒍ → '6.' ; # 248D;DIGIT SIX FULL STOP (compat)
⒎ → '7.' ; # 248E;DIGIT SEVEN FULL STOP (compat)
⒏ → '8.' ; # 248F;DIGIT EIGHT FULL STOP (compat)
⒐ → '9.' ; # 2490;DIGIT NINE FULL STOP (compat)
⒑ → '10.' ; # 2491;NUMBER TEN FULL STOP (compat)
⒒ → '11.' ; # 2492;NUMBER ELEVEN FULL STOP (compat)
⒓ → '12.' ; # 2493;NUMBER TWELVE FULL STOP (compat)
⒔ → '13.' ; # 2494;NUMBER THIRTEEN FULL STOP (compat)
⒕ → '14.' ; # 2495;NUMBER FOURTEEN FULL STOP (compat)
⒖ → '15.' ; # 2496;NUMBER FIFTEEN FULL STOP (compat)
⒗ → '16.' ; # 2497;NUMBER SIXTEEN FULL STOP (compat)
⒘ → '17.' ; # 2498;NUMBER SEVENTEEN FULL STOP (compat)
⒙ → '18.' ; # 2499;NUMBER EIGHTEEN FULL STOP (compat)
⒚ → '19.' ; # 249A;NUMBER NINETEEN FULL STOP (compat)
⒛ → '20.' ; # 249B;NUMBER TWENTY FULL STOP (compat)
#
# Other numeric (ideographic and fullwidth)
#
→ 0 ; # 3007;IDEOGRAPHIC NUMBER ZERO
→ 0 ; # FF10;FULLWIDTH DIGIT ZERO (compat)
→ 1 ; # FF11;FULLWIDTH DIGIT ONE (compat)
→ 2 ; # FF12;FULLWIDTH DIGIT TWO (compat)
→ 3 ; # FF13;FULLWIDTH DIGIT THREE (compat)
→ 4 ; # FF14;FULLWIDTH DIGIT FOUR (compat)
→ 5 ; # FF15;FULLWIDTH DIGIT FIVE (compat)
→ 6 ; # FF16;FULLWIDTH DIGIT SIX (compat)
→ 7 ; # FF17;FULLWIDTH DIGIT SEVEN (compat)
→ 8 ; # FF18;FULLWIDTH DIGIT EIGHT (compat)
→ 9 ; # FF19;FULLWIDTH DIGIT NINE (compat)
#
# Spaces
#
\u00A0 → ' ' ; # 00A0;NO-BREAK SPACE
\u2002 → ' ' ; # 2002;EN SPACE (compat)
\u2003 → ' ' ; # 2003;EM SPACE (compat)
\u2004 → ' ' ; # 2004;THREE-PER-EM SPACE (compat)
\u2005 → ' ' ; # 2005;FOUR-PER-EM SPACE (compat)
\u2006 → ' ' ; # 2006;SIX-PER-EM SPACE (compat)
\u2007 → ' ' ; # 2007;FIGURE SPACE (compat)
\u2008 → ' ' ; # 2008;PUNCTUATION SPACE (compat)
\u2009 → ' ' ; # 2009;THIN SPACE (compat)
\u200A → ' ' ; # 200A;HAIR SPACE (compat)
\u205F → ' ' ; # 205F;MEDIUM MATHEMATICAL SPACE (compat)
\u3000 → ' ' ; # 3000;IDEOGRAPHIC SPACE (from character-fallback)
#
# Quotes, apostrophes
#
ʹ → \' ; # 02B9;MODIFIER LETTER PRIME
ʺ → \" ; # 02BA;MODIFIER LETTER DOUBLE PRIME
ʻ → \' ; # 02BB;MODIFIER LETTER TURNED COMMA
ʼ → \' ; # 02BC;MODIFIER LETTER APOSTROPHE
ʽ → \' ; # 02BD;MODIFIER LETTER REVERSED COMMA
ˈ → \' ; # 02C8;MODIFIER LETTER VERTICAL LINE
ˋ → '`' ; # 02CB;MODIFIER LETTER GRAVE ACCENT
→ \' ; # 2018;LEFT SINGLE QUOTATION MARK (from character-fallback)
→ \' ; # 2019;RIGHT SINGLE QUOTATION MARK (from character-fallback)
→ ',' ; # 201A;SINGLE LOW-9 QUOTATION MARK (from character-fallback)
→ \' ; # 201B;SINGLE HIGH-REVERSED-9 QUOTATION MARK (from character-fallback)
“ → \" ; # 201C;LEFT DOUBLE QUOTATION MARK (from character-fallback)
” → \" ; # 201D;RIGHT DOUBLE QUOTATION MARK (from character-fallback)
„ → ',,' ; # 201E;DOUBLE LOW-9 QUOTATION MARK (from character-fallback)
‟ → \" ; # 201F;DOUBLE HIGH-REVERSED-9 QUOTATION MARK (from character-fallback)
→ \' ; # 2032;PRIME
″ → \" ; # 2033;DOUBLE PRIME
〝 → \" ; # 301D;REVERSED DOUBLE PRIME QUOTATION MARK
〞 → \" ; # 301E;DOUBLE PRIME QUOTATION MARK
→ \" ; # FF02;FULLWIDTH QUOTATION MARK (compat)
→ \' ; # FF07;FULLWIDTH APOSTROPHE (compat)
« → '<<' ; # 00AB;LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (from character-fallback)
» → '>>' ; # 00BB;RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (from character-fallback)
→ '<' ; # 2039;SINGLE LEFT-POINTING ANGLE QUOTATION MARK
→ '>' ; # 203A;SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
#
# Dashes, hyphens...
#
\u00AD → '-' ; # 00AD;SOFT HYPHEN (from character-fallback)
→ '-' ; # 2010;HYPHEN (from character-fallback)
→ '-' ; # 2011;NON-BREAKING HYPHEN (from character-fallback)
→ '-' ; # 2012;FIGURE DASH (from character-fallback)
→ '-' ; # 2013;EN DASH (from character-fallback)
— → '-' ; # 2014;EM DASH (from character-fallback)
― → '-' ; # 2015;HORIZONTAL BAR (from character-fallback)
︱ → '-' ; # FE31;PRESENTATION FORM FOR VERTICAL EM DASH (compat)
︲ → '-' ; # FE32;PRESENTATION FORM FOR VERTICAL EN DASH (compat)
→ '-' ; # FE58;SMALL EM DASH (compat)
﹣ → '-' ; # FE63;SMALL HYPHEN-MINUS (compat)
→ '-' ; # FF0D;FULLWIDTH HYPHEN-MINUS (compat)
#
# Other misc punctuation and symbols
#
˂ → '<' ; # 02C2;MODIFIER LETTER LEFT ARROWHEAD
˃ → '>' ; # 02C3;MODIFIER LETTER RIGHT ARROWHEAD
˄ → '^' ; # 02C4;MODIFIER LETTER UP ARROWHEAD
ˆ → '^' ; # 02C6;MODIFIER LETTER CIRCUMFLEX ACCENT
ː → ':' ; # 02D0;MODIFIER LETTER TRIANGULAR COLON
˜ → '~' ; # 02DC;SMALL TILDE
‖ → '||' ; # 2016;DOUBLE VERTICAL LINE
→ '.' ; # 2024;ONE DOT LEADER (compat)
‥ → '..' ; # 2025;TWO DOT LEADER (compat)
… → '...' ; # 2026;HORIZONTAL ELLIPSIS (compat)
‼ → '!!' ; # 203C;DOUBLE EXCLAMATION MARK (compat)
→ '/' ; # 2044;FRACTION SLASH (from character-fallback)
⁅ → '[' ; # 2045;LEFT SQUARE BRACKET WITH QUILL
⁆ → ']' ; # 2046;RIGHT SQUARE BRACKET WITH QUILL
⁇ → '??' ; # 2047;DOUBLE QUESTION MARK (compat)
⁈ → '?!' ; # 2048;QUESTION EXCLAMATION MARK (compat)
⁉ → '!?' ; # 2049;EXCLAMATION QUESTION MARK (compat)
→ '*' ; # 204E;LOW ASTERISK
# CJK
、 → ',' ; # 3001;IDEOGRAPHIC COMMA
。 → '.' ; # 3002;IDEOGRAPHIC FULL STOP
〈 → '<' ; # 3008;LEFT ANGLE BRACKET
〉 → '>' ; # 3009;RIGHT ANGLE BRACKET
《 → '<<' ; # 300A;LEFT DOUBLE ANGLE BRACKET
》 → '>>' ; # 300B;RIGHT DOUBLE ANGLE BRACKET
→ '[' ; # 3014;LEFT TORTOISE SHELL BRACKET
→ ']' ; # 3015;RIGHT TORTOISE SHELL BRACKET
〘 → '[' ; # 3018;LEFT WHITE TORTOISE SHELL BRACKET
〙 → ']' ; # 3019;RIGHT WHITE TORTOISE SHELL BRACKET
〚 → '[' ; # 301A;LEFT WHITE SQUARE BRACKET
〛 → ']' ; # 301B;RIGHT WHITE SQUARE BRACKET
# Vertical and small forms
︐ → ',' ; # FE10;PRESENTATION FORM FOR VERTICAL COMMA (compat)
︑ → ',' ; # FE11;PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA (compat)
︒ → '.' ; # FE12;PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP (compat)
︓ → ':' ; # FE13;PRESENTATION FORM FOR VERTICAL COLON (compat)
︔ → ';' ; # FE14;PRESENTATION FORM FOR VERTICAL SEMICOLON (compat)
︕ → '!' ; # FE15;PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (compat)
︖ → '?' ; # FE16;PRESENTATION FORM FOR VERTICAL QUESTION MARK (compat)
︙ → '...' ; # FE19;PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (compat)
→ '..' ; # FE30;PRESENTATION FORM FOR VERTICAL TWO DOT LEADER (compat)
︵ → '(' ; # FE35;PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS (compat)
︶ → ')' ; # FE36;PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS (compat)
︷ → '{' ; # FE37;PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET (compat)
︸ → '}' ; # FE38;PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET (compat)
︹ → '[' ; # FE39;PRESENTATION FORM FOR VERTICAL LEFT TORTOISE SHELL BRACKET (compat)
︺ → ']' ; # FE3A;PRESENTATION FORM FOR VERTICAL RIGHT TORTOISE SHELL BRACKET (compat)
︽ → '<<' ; # FE3D;PRESENTATION FORM FOR VERTICAL LEFT DOUBLE ANGLE BRACKET (compat)
︾ → '>>' ; # FE3E;PRESENTATION FORM FOR VERTICAL RIGHT DOUBLE ANGLE BRACKET (compat)
︿ → '<' ; # FE3F;PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET (compat)
﹀ → '>' ; # FE40;PRESENTATION FORM FOR VERTICAL RIGHT ANGLE BRACKET (compat)
﹇ → '[' ; # FE47;PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET (compat)
﹈ → ']' ; # FE48;PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET (compat)
﹐ → ',' ; # FE50;SMALL COMMA (compat)
﹑ → ',' ; # FE51;SMALL IDEOGRAPHIC COMMA (compat)
﹒ → '.' ; # FE52;SMALL FULL STOP (compat)
﹔ → ';' ; # FE54;SMALL SEMICOLON (compat)
﹕ → ':' ; # FE55;SMALL COLON (compat)
﹖ → '?' ; # FE56;SMALL QUESTION MARK (compat)
﹗ → '!' ; # FE57;SMALL EXCLAMATION MARK (compat)
﹙ → '(' ; # FE59;SMALL LEFT PARENTHESIS (compat)
﹚ → ')' ; # FE5A;SMALL RIGHT PARENTHESIS (compat)
﹛ → '{' ; # FE5B;SMALL LEFT CURLY BRACKET (compat)
﹜ → '}' ; # FE5C;SMALL RIGHT CURLY BRACKET (compat)
﹝ → '[' ; # FE5D;SMALL LEFT TORTOISE SHELL BRACKET (compat)
﹞ → ']' ; # FE5E;SMALL RIGHT TORTOISE SHELL BRACKET (compat)
﹟ → '#' ; # FE5F;SMALL NUMBER SIGN (compat)
﹠ → '&' ; # FE60;SMALL AMPERSAND (compat)
﹡ → '*' ; # FE61;SMALL ASTERISK (compat)
﹢ → '+' ; # FE62;SMALL PLUS SIGN (compat)
﹤ → '<' ; # FE64;SMALL LESS-THAN SIGN (compat)
﹥ → '>' ; # FE65;SMALL GREATER-THAN SIGN (compat)
﹦ → '=' ; # FE66;SMALL EQUALS SIGN (compat)
→ '\' ; # FE68;SMALL REVERSE SOLIDUS (compat)
﹩ → '$' ; # FE69;SMALL DOLLAR SIGN (compat)
﹪ → '%' ; # FE6A;SMALL PERCENT SIGN (compat)
﹫ → '@' ; # FE6B;SMALL COMMERCIAL AT (compat)
# Fullwidth and halfwidth
→ '!' ; # FF01;FULLWIDTH EXCLAMATION MARK (compat)
→ '#' ; # FF03;FULLWIDTH NUMBER SIGN (compat)
→ '$' ; # FF04;FULLWIDTH DOLLAR SIGN (compat)
→ '%' ; # FF05;FULLWIDTH PERCENT SIGN (compat)
→ '&' ; # FF06;FULLWIDTH AMPERSAND (compat)
→ '(' ; # FF08;FULLWIDTH LEFT PARENTHESIS (compat)
→ ')' ; # FF09;FULLWIDTH RIGHT PARENTHESIS (compat)
→ '*' ; # FF0A;FULLWIDTH ASTERISK (compat)
→ '+' ; # FF0B;FULLWIDTH PLUS SIGN (compat)
→ ',' ; # FF0C;FULLWIDTH COMMA (compat)
→ '.' ; # FF0E;FULLWIDTH FULL STOP (compat)
→ '/' ; # FF0F;FULLWIDTH SOLIDUS (compat)
→ ':' ; # FF1A;FULLWIDTH COLON (compat)
→ ';' ; # FF1B;FULLWIDTH SEMICOLON (compat)
→ '<' ; # FF1C;FULLWIDTH LESS-THAN SIGN (compat)
→ '=' ; # FF1D;FULLWIDTH EQUALS SIGN (compat)
→ '>' ; # FF1E;FULLWIDTH GREATER-THAN SIGN (compat)
→ '?' ; # FF1F;FULLWIDTH QUESTION MARK (compat)
→ '@' ; # FF20;FULLWIDTH COMMERCIAL AT (compat)
→ '[' ; # FF3B;FULLWIDTH LEFT SQUARE BRACKET (compat)
→ '\' ; # FF3C;FULLWIDTH REVERSE SOLIDUS (compat)
→ ']' ; # FF3D;FULLWIDTH RIGHT SQUARE BRACKET (compat)
→ '^' ; # FF3E;FULLWIDTH CIRCUMFLEX ACCENT (compat)
_ → '_' ; # FF3F;FULLWIDTH LOW LINE (compat)
→ '`' ; # FF40;FULLWIDTH GRAVE ACCENT (compat)
→ '{' ; # FF5B;FULLWIDTH LEFT CURLY BRACKET (compat)
→ '|' ; # FF5C;FULLWIDTH VERTICAL LINE (compat)
→ '}' ; # FF5D;FULLWIDTH RIGHT CURLY BRACKET (compat)
→ '~' ; # FF5E;FULLWIDTH TILDE (compat)
⦅ → '((' ; # FF5F;FULLWIDTH LEFT WHITE PARENTHESIS (compat)(from character-fallback)
⦆ → '))' ; # FF60;FULLWIDTH RIGHT WHITE PARENTHESIS (compat)(from character-fallback)
。 → '.' ; # FF61;HALFWIDTH IDEOGRAPHIC FULL STOP (compat)
、 → ',' ; # FF64;HALFWIDTH IDEOGRAPHIC COMMA (compat)
#
# Other math operators (non-ASCII-range)
#
× → '*' ; # 00D7;MULTIPLICATION SIGN
÷ → '/' ; # 00F7;DIVISION SIGN
˖ → '+' ; # 02D6;MODIFIER LETTER PLUS SIGN
˗ → '-' ; # 02D7;MODIFIER LETTER MINUS SIGN
→ '-' ; # 2212;MINUS SIGN (from character-fallback)
→ '/' ; # 2215;DIVISION SLASH (from character-fallback)
→ '\' ; # 2216;SET MINUS (from character-fallback)
→ '|' ; # 2223;DIVIDES (from character-fallback)
∥ → '||' ; # 2225;PARALLEL TO (from character-fallback)
≪ → '<<' ; # 226A;MUCH LESS-THAN
≫ → '>>' ; # 226B;MUCH GREATER-THAN
⦅ → '((' ; # 2985;LEFT WHITE PARENTHESIS
⦆ → '))' ; # 2986;RIGHT WHITE PARENTHESIS
⩴ → '::=' ; # 2A74;DOUBLE COLON EQUAL (compat)
⩵ → '==' ; # 2A75;TWO CONSECUTIVE EQUALS SIGNS (compat)
⩶ → '===' ; # 2A76;THREE CONSECUTIVE EQUALS SIGNS (compat)