]> git.saurik.com Git - apple/icu.git/blame - icuSources/data/translit/Latin_ASCII.txt
ICU-62107.0.1.tar.gz
[apple/icu.git] / icuSources / data / translit / Latin_ASCII.txt
CommitLineData
f3c0d7a5
A
1# © 2016 and later: Unicode, Inc. and others.
2# License & terms of use: http://www.unicode.org/copyright.html#License
3#
729e4ab9 4# File: Latin_ASCII.txt
f3c0d7a5 5# Generated from CLDR
729e4ab9 6#
2ca993e8
A
7
8# This handles only Latin, Common, and IDEOGRAPHIC NUMBER ZERO (Han).
9#
729e4ab9 10:: [[:Latin:][:Common:][:Inherited:][〇]] ;
2ca993e8
A
11#
12# Don't want NFKD, because that would convert things like superscripts and
13# subscripts, which we do not want. So the individual transforms below
14# include an appropriate subset of the NFKD ones.
f3c0d7a5 15# Here we remove accents from Latin characters or digits. We then recompose to permit rules
2ca993e8
A
16# such as mapping NOT EQUAL TO to an ASCII equivalent e.g. "!=" if we choose to.
17#
729e4ab9 18:: NFD() ;
f3c0d7a5 19[[:Latin:][0-9]] { [:Mn:]+ → ; # maps to nothing; remove all Mn following Latin letter/digit
729e4ab9 20:: NFC() ;
2ca993e8
A
21#
22# Some of the following mappings (noted) are from CLDR ‹character-fallback› data.
23# (Note, here "‹character-fallback›" uses U+2039/U+203A to avoid XML issues)
24#
25# Latin letters and IPA
26#
729e4ab9
A
27Æ → AE ; # 00C6;LATIN CAPITAL LETTER AE (from ‹character-fallback›)
28Ð → D ; # 00D0;LATIN CAPITAL LETTER ETH
29Ø → O ; # 00D8;LATIN CAPITAL LETTER O WITH STROKE
30Þ → TH ; # 00DE;LATIN CAPITAL LETTER THORN
31ß → ss ; # 00DF;LATIN SMALL LETTER SHARP S (from ‹character-fallback›)
32æ → ae ; # 00E6;LATIN SMALL LETTER AE (from ‹character-fallback›)
33ð → d ; # 00F0;LATIN SMALL LETTER ETH
34ø → o ; # 00F8;LATIN SMALL LETTER O WITH STROKE
35þ → th ; # 00FE;LATIN SMALL LETTER THORN
36Đ → D ; # 0110;LATIN CAPITAL LETTER D WITH STROKE
37đ → d ; # 0111;LATIN SMALL LETTER D WITH STROKE
38Ħ → H ; # 0126;LATIN CAPITAL LETTER H WITH STROKE
2ca993e8 39ħ → h ; # 0126;LATIN SMALL LETTER H WITH STROKE
729e4ab9
A
40ı → i ; # 0131;LATIN SMALL LETTER DOTLESS I
41IJ → IJ ; # 0132;LATIN CAPITAL LIGATURE IJ (compat)
42ij → ij ; # 0133;LATIN SMALL LIGATURE IJ (compat)
43ĸ → q ; # 0138;LATIN SMALL LETTER KRA (collates with q in DUCET)
44Ŀ → L ; # 013F;LATIN CAPITAL LETTER L WITH MIDDLE DOT (compat)
45ŀ → l ; # 0140;LATIN SMALL LETTER L WITH MIDDLE DOT (compat)
46Ł → L ; # 0141;LATIN CAPITAL LETTER L WITH STROKE
47ł → l ; # 0142;LATIN SMALL LETTER L WITH STROKE
48ʼn → \'n ; # 0149;LATIN SMALL LETTER N PRECEDED BY APOSTROPHE (from ‹character-fallback›)
49Ŋ → N ; # 014A;LATIN CAPITAL LETTER ENG
50ŋ → n ; # 014B;LATIN SMALL LETTER ENG
51Œ → OE ; # 0152;LATIN CAPITAL LIGATURE OE (from ‹character-fallback›)
52œ → oe ; # 0153;LATIN SMALL LIGATURE OE (from ‹character-fallback›)
53Ŧ → T ; # 0166;LATIN CAPITAL LETTER T WITH STROKE
54ŧ → t ; # 0167;LATIN SMALL LETTER T WITH STROKE
55ſ → s ; # 017F;LATIN SMALL LETTER LONG S (compat)
56ƀ → b ; # 0180;LATIN SMALL LETTER B WITH STROKE
57Ɓ → B ; # 0181;LATIN CAPITAL LETTER B WITH HOOK
58Ƃ → B ; # 0182;LATIN CAPITAL LETTER B WITH TOPBAR
59ƃ → b ; # 0183;LATIN SMALL LETTER B WITH TOPBAR
60Ƈ → C ; # 0187;LATIN CAPITAL LETTER C WITH HOOK
61ƈ → c ; # 0188;LATIN SMALL LETTER C WITH HOOK
62Ɖ → D ; # 0189;LATIN CAPITAL LETTER AFRICAN D
63Ɗ → D ; # 018A;LATIN CAPITAL LETTER D WITH HOOK
64Ƌ → D ; # 018B;LATIN CAPITAL LETTER D WITH TOPBAR
65ƌ → d ; # 018C;LATIN SMALL LETTER D WITH TOPBAR
66Ɛ → E ; # 0190;LATIN CAPITAL LETTER OPEN E
67Ƒ → F ; # 0191;LATIN CAPITAL LETTER F WITH HOOK
68ƒ → f ; # 0192;LATIN SMALL LETTER F WITH HOOK
69Ɠ → G ; # 0193;LATIN CAPITAL LETTER G WITH HOOK
70ƕ → hv ; # 0195;LATIN SMALL LETTER HV
71Ɩ → I ; # 0196;LATIN CAPITAL LETTER IOTA
72Ɨ → I ; # 0197;LATIN CAPITAL LETTER I WITH STROKE
73Ƙ → K ; # 0198;LATIN CAPITAL LETTER K WITH HOOK
74ƙ → k ; # 0199;LATIN SMALL LETTER K WITH HOOK
75ƚ → l ; # 019A;LATIN SMALL LETTER L WITH BAR
76Ɲ → N ; # 019D;LATIN CAPITAL LETTER N WITH LEFT HOOK
77ƞ → n ; # 019E;LATIN SMALL LETTER N WITH LONG RIGHT LEG
78Ƣ → OI ; # 01A2;LATIN CAPITAL LETTER OI
79ƣ → oi ; # 01A3;LATIN SMALL LETTER OI
80Ƥ → P ; # 01A4;LATIN CAPITAL LETTER P WITH HOOK
81ƥ → p ; # 01A5;LATIN SMALL LETTER P WITH HOOK
82ƫ → t ; # 01AB;LATIN SMALL LETTER T WITH PALATAL HOOK
83Ƭ → T ; # 01AC;LATIN CAPITAL LETTER T WITH HOOK
84ƭ → t ; # 01AD;LATIN SMALL LETTER T WITH HOOK
85Ʈ → T ; # 01AE;LATIN CAPITAL LETTER T WITH RETROFLEX HOOK
86Ʋ → V ; # 01B2;LATIN CAPITAL LETTER V WITH HOOK
87Ƴ → Y ; # 01B3;LATIN CAPITAL LETTER Y WITH HOOK
88ƴ → y ; # 01B4;LATIN SMALL LETTER Y WITH HOOK
89Ƶ → Z ; # 01B5;LATIN CAPITAL LETTER Z WITH STROKE
90ƶ → z ; # 01B6;LATIN SMALL LETTER Z WITH STROKE
91DŽ → DZ ; # 01C4;LATIN CAPITAL LETTER DZ WITH CARON (compat)
92Dž → Dz ; # 01C5;LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON (compat)
93dž → dz ; # 01C6;LATIN SMALL LETTER DZ WITH CARON (compat)
94LJ → LJ ; # 01C7;LATIN CAPITAL LETTER LJ (compat)
95Lj → Lj ; # 01C8;LATIN CAPITAL LETTER L WITH SMALL LETTER J (compat)
96lj → lj ; # 01C9;LATIN SMALL LETTER LJ (compat)
97NJ → NJ ; # 01CA;LATIN CAPITAL LETTER NJ (compat)
98Nj → Nj ; # 01CB;LATIN CAPITAL LETTER N WITH SMALL LETTER J (compat)
99nj → nj ; # 01CC;LATIN SMALL LETTER NJ (compat)
100Ǥ → G ; # 01E4;LATIN CAPITAL LETTER G WITH STROKE
101ǥ → g ; # 01E5;LATIN SMALL LETTER G WITH STROKE
102DZ → DZ ; # 01F1;LATIN CAPITAL LETTER DZ (compat)
103Dz → Dz ; # 01F2;LATIN CAPITAL LETTER D WITH SMALL LETTER Z (compat)
104dz → dz ; # 01F3;LATIN SMALL LETTER DZ (compat)
105ȡ → d ; # 0221;LATIN SMALL LETTER D WITH CURL
106Ȥ → Z ; # 0224;LATIN CAPITAL LETTER Z WITH HOOK
107ȥ → z ; # 0225;LATIN SMALL LETTER Z WITH HOOK
108ȴ → l ; # 0234;LATIN SMALL LETTER L WITH CURL
109ȵ → n ; # 0235;LATIN SMALL LETTER N WITH CURL
110ȶ → t ; # 0236;LATIN SMALL LETTER T WITH CURL
111ȷ → j ; # 0237;LATIN SMALL LETTER DOTLESS J
112ȸ → db ; # 0238;LATIN SMALL LETTER DB DIGRAPH
113ȹ → qp ; # 0239;LATIN SMALL LETTER QP DIGRAPH
114Ⱥ → A ; # 023A;LATIN CAPITAL LETTER A WITH STROKE
115Ȼ → C ; # 023B;LATIN CAPITAL LETTER C WITH STROKE
116ȼ → c ; # 023C;LATIN SMALL LETTER C WITH STROKE
117Ƚ → L ; # 023D;LATIN CAPITAL LETTER L WITH BAR
118Ⱦ → T ; # 023E;LATIN CAPITAL LETTER T WITH DIAGONAL STROKE
119ȿ → s ; # 023F;LATIN SMALL LETTER S WITH SWASH TAIL
120ɀ → z ; # 0240;LATIN SMALL LETTER Z WITH SWASH TAIL
121Ƀ → B ; # 0243;LATIN CAPITAL LETTER B WITH STROKE
122Ʉ → U ; # 0244;LATIN CAPITAL LETTER U BAR
123Ɇ → E ; # 0246;LATIN CAPITAL LETTER E WITH STROKE
124ɇ → e ; # 0247;LATIN SMALL LETTER E WITH STROKE
125Ɉ → J ; # 0248;LATIN CAPITAL LETTER J WITH STROKE
126ɉ → j ; # 0249;LATIN SMALL LETTER J WITH STROKE
127Ɍ → R ; # 024C;LATIN CAPITAL LETTER R WITH STROKE
128ɍ → r ; # 024D;LATIN SMALL LETTER R WITH STROKE
129Ɏ → Y ; # 024E;LATIN CAPITAL LETTER Y WITH STROKE
130ɏ → y ; # 024F;LATIN SMALL LETTER Y WITH STROKE
131ɓ → b ; # 0253;LATIN SMALL LETTER B WITH HOOK
132ɕ → c ; # 0255;LATIN SMALL LETTER C WITH CURL
133ɖ → d ; # 0256;LATIN SMALL LETTER D WITH TAIL
134ɗ → d ; # 0257;LATIN SMALL LETTER D WITH HOOK
135ɛ → e ; # 025B;LATIN SMALL LETTER OPEN E
136ɟ → j ; # 025F;LATIN SMALL LETTER DOTLESS J WITH STROKE
137ɠ → g ; # 0260;LATIN SMALL LETTER G WITH HOOK
138ɡ → g ; # 0261;LATIN SMALL LETTER SCRIPT G
139ɢ → G ; # 0262;LATIN LETTER SMALL CAPITAL G
140ɦ → h ; # 0266;LATIN SMALL LETTER H WITH HOOK
141ɧ → h ; # 0267;LATIN SMALL LETTER HENG WITH HOOK
142ɨ → i ; # 0268;LATIN SMALL LETTER I WITH STROKE
143ɪ → I ; # 026A;LATIN LETTER SMALL CAPITAL I
144ɫ → l ; # 026B;LATIN SMALL LETTER L WITH MIDDLE TILDE
145ɬ → l ; # 026C;LATIN SMALL LETTER L WITH BELT
146ɭ → l ; # 026D;LATIN SMALL LETTER L WITH RETROFLEX HOOK
147ɱ → m ; # 0271;LATIN SMALL LETTER M WITH HOOK
148ɲ → n ; # 0272;LATIN SMALL LETTER N WITH LEFT HOOK
149ɳ → n ; # 0273;LATIN SMALL LETTER N WITH RETROFLEX HOOK
150ɴ → N ; # 0274;LATIN LETTER SMALL CAPITAL N
151ɶ → OE ; # 0276;LATIN LETTER SMALL CAPITAL OE
152ɼ → r ; # 027C;LATIN SMALL LETTER R WITH LONG LEG
153ɽ → r ; # 027D;LATIN SMALL LETTER R WITH TAIL
154ɾ → r ; # 027E;LATIN SMALL LETTER R WITH FISHHOOK
155ʀ → R ; # 0280;LATIN LETTER SMALL CAPITAL R
156ʂ → s ; # 0282;LATIN SMALL LETTER S WITH HOOK
157ʈ → t ; # 0288;LATIN SMALL LETTER T WITH RETROFLEX HOOK
158ʉ → u ; # 0289;LATIN SMALL LETTER U BAR
159ʋ → v ; # 028B;LATIN SMALL LETTER V WITH HOOK
160ʏ → Y ; # 028F;LATIN LETTER SMALL CAPITAL Y
161ʐ → z ; # 0290;LATIN SMALL LETTER Z WITH RETROFLEX HOOK
162ʑ → z ; # 0291;LATIN SMALL LETTER Z WITH CURL
163ʙ → B ; # 0299;LATIN LETTER SMALL CAPITAL B
164ʛ → G ; # 029B;LATIN LETTER SMALL CAPITAL G WITH HOOK
165ʜ → H ; # 029C;LATIN LETTER SMALL CAPITAL H
166ʝ → j ; # 029D;LATIN SMALL LETTER J WITH CROSSED-TAIL
167ʟ → L ; # 029F;LATIN LETTER SMALL CAPITAL L
168ʠ → q ; # 02A0;LATIN SMALL LETTER Q WITH HOOK
169ʣ → dz ; # 02A3;LATIN SMALL LETTER DZ DIGRAPH
170ʥ → dz ; # 02A5;LATIN SMALL LETTER DZ DIGRAPH WITH CURL
171ʦ → ts ; # 02A6;LATIN SMALL LETTER TS DIGRAPH
172ʪ → ls ; # 02AA;LATIN SMALL LETTER LS DIGRAPH
173ʫ → lz ; # 02AB;LATIN SMALL LETTER LZ DIGRAPH
174ᴀ → A ; # 1D00;LATIN LETTER SMALL CAPITAL A
175ᴁ → AE ; # 1D01;LATIN LETTER SMALL CAPITAL AE
176ᴃ → B ; # 1D03;LATIN LETTER SMALL CAPITAL BARRED B
177ᴄ → C ; # 1D04;LATIN LETTER SMALL CAPITAL C
178ᴅ → D ; # 1D05;LATIN LETTER SMALL CAPITAL D
179ᴆ → D ; # 1D06;LATIN LETTER SMALL CAPITAL ETH
180ᴇ → E ; # 1D07;LATIN LETTER SMALL CAPITAL E
181ᴊ → J ; # 1D0A;LATIN LETTER SMALL CAPITAL J
182ᴋ → K ; # 1D0B;LATIN LETTER SMALL CAPITAL K
183ᴌ → L ; # 1D0C;LATIN LETTER SMALL CAPITAL L WITH STROKE
184ᴍ → M ; # 1D0D;LATIN LETTER SMALL CAPITAL M
185ᴏ → O ; # 1D0F;LATIN LETTER SMALL CAPITAL O
186ᴘ → P ; # 1D18;LATIN LETTER SMALL CAPITAL P
187ᴛ → T ; # 1D1B;LATIN LETTER SMALL CAPITAL T
188ᴜ → U ; # 1D1C;LATIN LETTER SMALL CAPITAL U
189ᴠ → V ; # 1D20;LATIN LETTER SMALL CAPITAL V
190ᴡ → W ; # 1D21;LATIN LETTER SMALL CAPITAL W
191ᴢ → Z ; # 1D22;LATIN LETTER SMALL CAPITAL Z
192ᵫ → ue ; # 1D6B;LATIN SMALL LETTER UE
193ᵬ → b ; # 1D6C;LATIN SMALL LETTER B WITH MIDDLE TILDE
194ᵭ → d ; # 1D6D;LATIN SMALL LETTER D WITH MIDDLE TILDE
195ᵮ → f ; # 1D6E;LATIN SMALL LETTER F WITH MIDDLE TILDE
196ᵯ → m ; # 1D6F;LATIN SMALL LETTER M WITH MIDDLE TILDE
197ᵰ → n ; # 1D70;LATIN SMALL LETTER N WITH MIDDLE TILDE
198ᵱ → p ; # 1D71;LATIN SMALL LETTER P WITH MIDDLE TILDE
199ᵲ → r ; # 1D72;LATIN SMALL LETTER R WITH MIDDLE TILDE
200ᵳ → r ; # 1D73;LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE
201ᵴ → s ; # 1D74;LATIN SMALL LETTER S WITH MIDDLE TILDE
202ᵵ → t ; # 1D75;LATIN SMALL LETTER T WITH MIDDLE TILDE
203ᵶ → z ; # 1D76;LATIN SMALL LETTER Z WITH MIDDLE TILDE
204ᵺ → th ; # 1D7A;LATIN SMALL LETTER TH WITH STRIKETHROUGH
205ᵻ → I ; # 1D7B;LATIN SMALL CAPITAL LETTER I WITH STROKE
206ᵽ → p ; # 1D7D;LATIN SMALL LETTER P WITH STROKE
207ᵾ → U ; # 1D7E;LATIN SMALL CAPITAL LETTER U WITH STROKE
208ᶀ → b ; # 1D80;LATIN SMALL LETTER B WITH PALATAL HOOK
209ᶁ → d ; # 1D81;LATIN SMALL LETTER D WITH PALATAL HOOK
210ᶂ → f ; # 1D82;LATIN SMALL LETTER F WITH PALATAL HOOK
211ᶃ → g ; # 1D83;LATIN SMALL LETTER G WITH PALATAL HOOK
212ᶄ → k ; # 1D84;LATIN SMALL LETTER K WITH PALATAL HOOK
213ᶅ → l ; # 1D85;LATIN SMALL LETTER L WITH PALATAL HOOK
214ᶆ → m ; # 1D86;LATIN SMALL LETTER M WITH PALATAL HOOK
215ᶇ → n ; # 1D87;LATIN SMALL LETTER N WITH PALATAL HOOK
216ᶈ → p ; # 1D88;LATIN SMALL LETTER P WITH PALATAL HOOK
217ᶉ → r ; # 1D89;LATIN SMALL LETTER R WITH PALATAL HOOK
218ᶊ → s ; # 1D8A;LATIN SMALL LETTER S WITH PALATAL HOOK
219ᶌ → v ; # 1D8C;LATIN SMALL LETTER V WITH PALATAL HOOK
220ᶍ → x ; # 1D8D;LATIN SMALL LETTER X WITH PALATAL HOOK
221ᶎ → z ; # 1D8E;LATIN SMALL LETTER Z WITH PALATAL HOOK
222ᶏ → a ; # 1D8F;LATIN SMALL LETTER A WITH RETROFLEX HOOK
223ᶑ → d ; # 1D91;LATIN SMALL LETTER D WITH HOOK AND TAIL
224ᶒ → e ; # 1D92;LATIN SMALL LETTER E WITH RETROFLEX HOOK
225ᶓ → e ; # 1D93;LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK
226ᶖ → i ; # 1D96;LATIN SMALL LETTER I WITH RETROFLEX HOOK
227ᶙ → u ; # 1D99;LATIN SMALL LETTER U WITH RETROFLEX HOOK
228ẚ → a ; # 1E9A;LATIN SMALL LETTER A WITH RIGHT HALF RING
229ẜ → s ; # 1E9C;LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE
230ẝ → s ; # 1E9D;LATIN SMALL LETTER LONG S WITH HIGH STROKE
231ẞ → SS ; # 1E9E;LATIN CAPITAL LETTER SHARP S
232Ỻ → LL ; # 1EFA;LATIN CAPITAL LETTER MIDDLE-WELSH LL
233ỻ → ll ; # 1EFB;LATIN SMALL LETTER MIDDLE-WELSH LL
234Ỽ → V ; # 1EFC;LATIN CAPITAL LETTER MIDDLE-WELSH V
235ỽ → v ; # 1EFD;LATIN SMALL LETTER MIDDLE-WELSH V
236Ỿ → Y ; # 1EFE;LATIN CAPITAL LETTER Y WITH LOOP
237ỿ → y ; # 1EFF;LATIN SMALL LETTER Y WITH LOOP
2ca993e8 238# Presentation forms
729e4ab9
A
239ff → ff ; # FB00;LATIN SMALL LIGATURE FF (compat)
240fi → fi ; # FB01;LATIN SMALL LIGATURE FI (compat)
241fl → fl ; # FB02;LATIN SMALL LIGATURE FL (compat)
242ffi → ffi ; # FB03;LATIN SMALL LIGATURE FFI (compat)
243ffl → ffl ; # FB04;LATIN SMALL LIGATURE FFL (compat)
244ſt → st ; # FB05;LATIN SMALL LIGATURE LONG S T (compat)
245st → st ; # FB06;LATIN SMALL LIGATURE ST (compat)
2ca993e8 246# Fullwidth
729e4ab9
A
247A → A ; # FF21;FULLWIDTH LATIN CAPITAL LETTER A (compat)
248B → B ; # FF22;FULLWIDTH LATIN CAPITAL LETTER B (compat)
249C → C ; # FF23;FULLWIDTH LATIN CAPITAL LETTER C (compat)
250D → D ; # FF24;FULLWIDTH LATIN CAPITAL LETTER D (compat)
251E → E ; # FF25;FULLWIDTH LATIN CAPITAL LETTER E (compat)
252F → F ; # FF26;FULLWIDTH LATIN CAPITAL LETTER F (compat)
253G → G ; # FF27;FULLWIDTH LATIN CAPITAL LETTER G (compat)
254H → H ; # FF28;FULLWIDTH LATIN CAPITAL LETTER H (compat)
255I → I ; # FF29;FULLWIDTH LATIN CAPITAL LETTER I (compat)
256J → J ; # FF2A;FULLWIDTH LATIN CAPITAL LETTER J (compat)
257K → K ; # FF2B;FULLWIDTH LATIN CAPITAL LETTER K (compat)
258L → L ; # FF2C;FULLWIDTH LATIN CAPITAL LETTER L (compat)
259M → M ; # FF2D;FULLWIDTH LATIN CAPITAL LETTER M (compat)
260N → N ; # FF2E;FULLWIDTH LATIN CAPITAL LETTER N (compat)
261O → O ; # FF2F;FULLWIDTH LATIN CAPITAL LETTER O (compat)
262P → P ; # FF30;FULLWIDTH LATIN CAPITAL LETTER P (compat)
263Q → Q ; # FF31;FULLWIDTH LATIN CAPITAL LETTER Q (compat)
264R → R ; # FF32;FULLWIDTH LATIN CAPITAL LETTER R (compat)
265S → S ; # FF33;FULLWIDTH LATIN CAPITAL LETTER S (compat)
266T → T ; # FF34;FULLWIDTH LATIN CAPITAL LETTER T (compat)
267U → U ; # FF35;FULLWIDTH LATIN CAPITAL LETTER U (compat)
268V → V ; # FF36;FULLWIDTH LATIN CAPITAL LETTER V (compat)
269W → W ; # FF37;FULLWIDTH LATIN CAPITAL LETTER W (compat)
270X → X ; # FF38;FULLWIDTH LATIN CAPITAL LETTER X (compat)
271Y → Y ; # FF39;FULLWIDTH LATIN CAPITAL LETTER Y (compat)
272Z → Z ; # FF3A;FULLWIDTH LATIN CAPITAL LETTER Z (compat)
273a → a ; # FF41;FULLWIDTH LATIN SMALL LETTER A (compat)
274b → b ; # FF42;FULLWIDTH LATIN SMALL LETTER B (compat)
275c → c ; # FF43;FULLWIDTH LATIN SMALL LETTER C (compat)
276d → d ; # FF44;FULLWIDTH LATIN SMALL LETTER D (compat)
277e → e ; # FF45;FULLWIDTH LATIN SMALL LETTER E (compat)
278f → f ; # FF46;FULLWIDTH LATIN SMALL LETTER F (compat)
279g → g ; # FF47;FULLWIDTH LATIN SMALL LETTER G (compat)
280h → h ; # FF48;FULLWIDTH LATIN SMALL LETTER H (compat)
281i → i ; # FF49;FULLWIDTH LATIN SMALL LETTER I (compat)
282j → j ; # FF4A;FULLWIDTH LATIN SMALL LETTER J (compat)
283k → k ; # FF4B;FULLWIDTH LATIN SMALL LETTER K (compat)
284l → l ; # FF4C;FULLWIDTH LATIN SMALL LETTER L (compat)
285m → m ; # FF4D;FULLWIDTH LATIN SMALL LETTER M (compat)
286n → n ; # FF4E;FULLWIDTH LATIN SMALL LETTER N (compat)
287o → o ; # FF4F;FULLWIDTH LATIN SMALL LETTER O (compat)
288p → p ; # FF50;FULLWIDTH LATIN SMALL LETTER P (compat)
289q → q ; # FF51;FULLWIDTH LATIN SMALL LETTER Q (compat)
290r → r ; # FF52;FULLWIDTH LATIN SMALL LETTER R (compat)
291s → s ; # FF53;FULLWIDTH LATIN SMALL LETTER S (compat)
292t → t ; # FF54;FULLWIDTH LATIN SMALL LETTER T (compat)
293u → u ; # FF55;FULLWIDTH LATIN SMALL LETTER U (compat)
294v → v ; # FF56;FULLWIDTH LATIN SMALL LETTER V (compat)
295w → w ; # FF57;FULLWIDTH LATIN SMALL LETTER W (compat)
296x → x ; # FF58;FULLWIDTH LATIN SMALL LETTER X (compat)
297y → y ; # FF59;FULLWIDTH LATIN SMALL LETTER Y (compat)
298z → z ; # FF5A;FULLWIDTH LATIN SMALL LETTER Z (compat)
2ca993e8
A
299#
300# Currency and letterlike
301#
729e4ab9
A
302© → '(C)' ; # 00A9;COPYRIGHT SIGN (from ‹character-fallback›)
303® → '(R)' ; # 00AE;REGISTERED SIGN (from ‹character-fallback›)
304₠ → CE ; # 20A0;EURO-CURRENCY SIGN (from ‹character-fallback›)
305₢ → Cr ; # 20A2;CRUZEIRO SIGN (from ‹character-fallback›)
306₣ → 'Fr.' ; # 20A3;FRENCH FRANC SIGN (from ‹character-fallback›)
307₤ → 'L.' ; # 20A4;LIRA SIGN (from ‹character-fallback›)
308₧ → Pts ; # 20A7;PESETA SIGN (from ‹character-fallback›)
57a6839d 309₺ → TL ; # 20BA;TURKISH LIRA SIGN (from ‹character-fallback›)
729e4ab9
A
310₹ → Rs ; # 20B9;INDIAN RUPEE SIGN (from ‹character-fallback›)
311℀ → 'a/c' ; # 2100;ACCOUNT OF (compat)
312℁ → 'a/s' ; # 2101;ADDRESSED TO THE SUBJECT (compat)
313ℂ → C ; # 2102;DOUBLE-STRUCK CAPITAL C (compat)
314℅ → 'c/o' ; # 2105;CARE OF (compat)
315℆ → 'c/u' ; # 2106;CADA UNA (compat)
316ℊ → g ; # 210A;SCRIPT SMALL G (compat)
317ℋ → H ; # 210B;SCRIPT CAPITAL H (compat)
318ℌ → x ; # 210C;BLACK-LETTER CAPITAL H (compat)
319ℍ → H ; # 210D;DOUBLE-STRUCK CAPITAL H (compat)
320ℎ → h ; # 210E;PLANCK CONSTANT (compat)
321ℐ → I ; # 2110;SCRIPT CAPITAL I (compat)
322ℑ → I ; # 2111;BLACK-LETTER CAPITAL I (compat)
323ℒ → L ; # 2112;SCRIPT CAPITAL L (compat)
324ℓ → l ; # 2113;SCRIPT SMALL L (compat)
325ℕ → N ; # 2115;DOUBLE-STRUCK CAPITAL N (compat)
326№ → No ; # 2116;NUMERO SIGN (compat)
327ℙ → P ; # 2119;DOUBLE-STRUCK CAPITAL P (compat)
328ℚ → Q ; # 211A;DOUBLE-STRUCK CAPITAL Q (compat)
329ℛ → R ; # 211B;SCRIPT CAPITAL R (compat)
330ℜ → R ; # 211C;BLACK-LETTER CAPITAL R (compat)
331ℝ → R ; # 211D;DOUBLE-STRUCK CAPITAL R (compat)
332℞ → Rx ; # 211E;PRESCRIPTION TAKE (from ‹character-fallback›)
333℡ → TEL ; # 2121;TELEPHONE SIGN (compat)
334ℤ → Z ; # 2124;DOUBLE-STRUCK CAPITAL Z (compat)
335ℨ → Z ; # 2128;BLACK-LETTER CAPITAL Z (compat)
336ℬ → B ; # 212C;SCRIPT CAPITAL B (compat)
337ℭ → C ; # 212D;BLACK-LETTER CAPITAL C (compat)
338ℯ → e ; # 212F;SCRIPT SMALL E (compat)
339ℰ → E ; # 2130;SCRIPT CAPITAL E (compat)
340ℱ → F ; # 2131;SCRIPT CAPITAL F (compat)
341ℳ → M ; # 2133;SCRIPT CAPITAL M (compat)
342ℴ → o ; # 2134;SCRIPT SMALL O (compat)
343ℹ → i ; # 2139;INFORMATION SOURCE (compat)
344℻ → FAX ; # 213B;FACSIMILE SIGN (compat)
345ⅅ → D ; # 2145;DOUBLE-STRUCK ITALIC CAPITAL D (compat)
346ⅆ → d ; # 2146;DOUBLE-STRUCK ITALIC SMALL D (compat)
347ⅇ → e ; # 2147;DOUBLE-STRUCK ITALIC SMALL E (compat)
348ⅈ → i ; # 2148;DOUBLE-STRUCK ITALIC SMALL I (compat)
349ⅉ → j ; # 2149;DOUBLE-STRUCK ITALIC SMALL J (compat)
2ca993e8
A
350#
351# Squared Latin
352#
729e4ab9
A
353㍱ → hPa ; # 3371;SQUARE HPA (compat)
354㍲ → da ; # 3372;SQUARE DA (compat)
355㍳ → AU ; # 3373;SQUARE AU (compat)
356㍴ → bar ; # 3374;SQUARE BAR (compat)
357㍵ → oV ; # 3375;SQUARE OV (compat)
358㍶ → pc ; # 3376;SQUARE PC (compat)
359㍷ → dm ; # 3377;SQUARE DM (compat)
360㍺ → IU ; # 337A;SQUARE IU (compat)
361㎀ → pA ; # 3380;SQUARE PA AMPS (compat)
362㎁ → nA ; # 3381;SQUARE NA (compat)
363㎃ → mA ; # 3383;SQUARE MA (compat)
364㎄ → kA ; # 3384;SQUARE KA (compat)
365㎅ → KB ; # 3385;SQUARE KB (compat)
366㎆ → MB ; # 3386;SQUARE MB (compat)
367㎇ → GB ; # 3387;SQUARE GB (compat)
368㎈ → cal ; # 3388;SQUARE CAL (compat)
369㎉ → kcal ; # 3389;SQUARE KCAL (compat)
370㎊ → pF ; # 338A;SQUARE PF (compat)
371㎋ → nF ; # 338B;SQUARE NF (compat)
372㎎ → mg ; # 338E;SQUARE MG (compat)
373㎏ → kg ; # 338F;SQUARE KG (compat)
374㎐ → Hz ; # 3390;SQUARE HZ (compat)
375㎑ → kHz ; # 3391;SQUARE KHZ (compat)
376㎒ → MHz ; # 3392;SQUARE MHZ (compat)
377㎓ → GHz ; # 3393;SQUARE GHZ (compat)
378㎔ → THz ; # 3394;SQUARE THZ (compat)
379㎙ → fm ; # 3399;SQUARE FM (compat)
380㎚ → nm ; # 339A;SQUARE NM (compat)
381㎜ → mm ; # 339C;SQUARE MM (compat)
382㎝ → cm ; # 339D;SQUARE CM (compat)
383㎞ → km ; # 339E;SQUARE KM (compat)
384㎧ → 'm/s' ; # 33A7;SQUARE M OVER S (compat) (from ‹character-fallback›)
385㎩ → Pa ; # 33A9;SQUARE PA (compat)
386㎪ → kPa ; # 33AA;SQUARE KPA (compat)
387㎫ → MPa ; # 33AB;SQUARE MPA (compat)
388㎬ → GPa ; # 33AC;SQUARE GPA (compat)
389㎭ → rad ; # 33AD;SQUARE RAD (compat)
390㎮ → 'rad/s' ; # 33AE;SQUARE RAD OVER S (compat) (from ‹character-fallback›)
391㎰ → ps ; # 33B0;SQUARE PS (compat)
392㎱ → ns ; # 33B1;SQUARE NS (compat)
393㎳ → ms ; # 33B3;SQUARE MS (compat)
394㎴ → pV ; # 33B4;SQUARE PV (compat)
395㎵ → nV ; # 33B5;SQUARE NV (compat)
396㎷ → mV ; # 33B7;SQUARE MV (compat)
397㎸ → kV ; # 33B8;SQUARE KV (compat)
398㎹ → MV ; # 33B9;SQUARE MV MEGA (compat)
399㎺ → pW ; # 33BA;SQUARE PW (compat)
400㎻ → nW ; # 33BB;SQUARE NW (compat)
401㎽ → mW ; # 33BD;SQUARE MW (compat)
402㎾ → kW ; # 33BE;SQUARE KW (compat)
403㎿ → MW ; # 33BF;SQUARE MW MEGA (compat)
404㏂ → 'a.m.' ; # 33C2;SQUARE AM (compat)
405㏃ → Bq ; # 33C3;SQUARE BQ (compat)
406㏄ → cc ; # 33C4;SQUARE CC (compat) (from ‹character-fallback›, adj)
407㏅ → cd ; # 33C5;SQUARE CD (compat)
408㏆ → 'C/kg' ; # 33C6;SQUARE C OVER KG (compat) (from ‹character-fallback›)
409㏇ → 'Co.' ; # 33C7;SQUARE CO (compat)
410㏈ → dB ; # 33C8;SQUARE DB (compat)
411㏉ → Gy ; # 33C9;SQUARE GY (compat)
412㏊ → ha ; # 33CA;SQUARE HA (compat)
413㏋ → HP ; # 33CB;SQUARE HP (compat)
414㏌ → in ; # 33CC;SQUARE IN (compat)
415㏍ → KK ; # 33CD;SQUARE KK (compat)
416㏎ → KM ; # 33CE;SQUARE KM CAPITAL (compat)
417㏏ → kt ; # 33CF;SQUARE KT (compat)
418㏐ → lm ; # 33D0;SQUARE LM (compat)
419㏑ → ln ; # 33D1;SQUARE LN (compat)
420㏒ → log ; # 33D2;SQUARE LOG (compat)
421㏓ → lx ; # 33D3;SQUARE LX (compat)
422㏔ → mb ; # 33D4;SQUARE MB SMALL (compat)
423㏕ → mil ; # 33D5;SQUARE MIL (compat)
424㏖ → mol ; # 33D6;SQUARE MOL (compat)
425㏗ → pH ; # 33D7;SQUARE PH (compat) (from ‹character-fallback›)
426㏘ → 'p.m.' ; # 33D8;SQUARE PM (compat)
427㏙ → PPM ; # 33D9;SQUARE PPM (compat)
428㏚ → PR ; # 33DA;SQUARE PR (compat)
429㏛ → sr ; # 33DB;SQUARE SR (compat)
430㏜ → Sv ; # 33DC;SQUARE SV (compat)
431㏝ → Wb ; # 33DD;SQUARE WB (compat)
432㏞ → 'V/m' ; # 33DE;SQUARE V OVER M (compat) (from ‹character-fallback›)
433㏟ → 'A/m' ; # 33DF;SQUARE A OVER M (compat) (from ‹character-fallback›)
2ca993e8
A
434#
435# Enclosed Latin
436#
729e4ab9
A
437⒜ → '(a)' ; # 249C;PARENTHESIZED LATIN SMALL LETTER A (compat)
438⒝ → '(b)' ; # 249D;PARENTHESIZED LATIN SMALL LETTER B (compat)
439⒞ → '(c)' ; # 249E;PARENTHESIZED LATIN SMALL LETTER C (compat)
440⒟ → '(d)' ; # 249F;PARENTHESIZED LATIN SMALL LETTER D (compat)
441⒠ → '(e)' ; # 24A0;PARENTHESIZED LATIN SMALL LETTER E (compat)
442⒡ → '(f)' ; # 24A1;PARENTHESIZED LATIN SMALL LETTER F (compat)
443⒢ → '(g)' ; # 24A2;PARENTHESIZED LATIN SMALL LETTER G (compat)
444⒣ → '(h)' ; # 24A3;PARENTHESIZED LATIN SMALL LETTER H (compat)
445⒤ → '(i)' ; # 24A4;PARENTHESIZED LATIN SMALL LETTER I (compat)
446⒥ → '(j)' ; # 24A5;PARENTHESIZED LATIN SMALL LETTER J (compat)
447⒦ → '(k)' ; # 24A6;PARENTHESIZED LATIN SMALL LETTER K (compat)
448⒧ → '(l)' ; # 24A7;PARENTHESIZED LATIN SMALL LETTER L (compat)
449⒨ → '(m)' ; # 24A8;PARENTHESIZED LATIN SMALL LETTER M (compat)
450⒩ → '(n)' ; # 24A9;PARENTHESIZED LATIN SMALL LETTER N (compat)
451⒪ → '(o)' ; # 24AA;PARENTHESIZED LATIN SMALL LETTER O (compat)
452⒫ → '(p)' ; # 24AB;PARENTHESIZED LATIN SMALL LETTER P (compat)
453⒬ → '(q)' ; # 24AC;PARENTHESIZED LATIN SMALL LETTER Q (compat)
454⒭ → '(r)' ; # 24AD;PARENTHESIZED LATIN SMALL LETTER R (compat)
455⒮ → '(s)' ; # 24AE;PARENTHESIZED LATIN SMALL LETTER S (compat)
456⒯ → '(t)' ; # 24AF;PARENTHESIZED LATIN SMALL LETTER T (compat)
457⒰ → '(u)' ; # 24B0;PARENTHESIZED LATIN SMALL LETTER U (compat)
458⒱ → '(v)' ; # 24B1;PARENTHESIZED LATIN SMALL LETTER V (compat)
459⒲ → '(w)' ; # 24B2;PARENTHESIZED LATIN SMALL LETTER W (compat)
460⒳ → '(x)' ; # 24B3;PARENTHESIZED LATIN SMALL LETTER X (compat)
461⒴ → '(y)' ; # 24B4;PARENTHESIZED LATIN SMALL LETTER Y (compat)
462⒵ → '(z)' ; # 24B5;PARENTHESIZED LATIN SMALL LETTER Z (compat)
2ca993e8
A
463#
464# Roman numerals
465#
729e4ab9
A
466Ⅰ → I ; # 2160;ROMAN NUMERAL ONE (compat)
467Ⅱ → II ; # 2161;ROMAN NUMERAL TWO (compat)
468Ⅲ → III ; # 2162;ROMAN NUMERAL THREE (compat)
469Ⅳ → IV ; # 2163;ROMAN NUMERAL FOUR (compat)
470Ⅴ → V ; # 2164;ROMAN NUMERAL FIVE (compat)
471Ⅵ → VI ; # 2165;ROMAN NUMERAL SIX (compat)
472Ⅶ → VII ; # 2166;ROMAN NUMERAL SEVEN (compat)
473Ⅷ → VIII ; # 2167;ROMAN NUMERAL EIGHT (compat)
474Ⅸ → IX ; # 2168;ROMAN NUMERAL NINE (compat)
475Ⅹ → X ; # 2169;ROMAN NUMERAL TEN (compat)
476Ⅺ → XI ; # 216A;ROMAN NUMERAL ELEVEN (compat)
477Ⅻ → XII ; # 216B;ROMAN NUMERAL TWELVE (compat)
478Ⅼ → L ; # 216C;ROMAN NUMERAL FIFTY (compat)
479Ⅽ → C ; # 216D;ROMAN NUMERAL ONE HUNDRED (compat)
480Ⅾ → D ; # 216E;ROMAN NUMERAL FIVE HUNDRED (compat)
481Ⅿ → M ; # 216F;ROMAN NUMERAL ONE THOUSAND (compat)
482ⅰ → i ; # 2170;SMALL ROMAN NUMERAL ONE (compat)
483ⅱ → ii ; # 2171;SMALL ROMAN NUMERAL TWO (compat)
484ⅲ → iii ; # 2172;SMALL ROMAN NUMERAL THREE (compat)
485ⅳ → iv ; # 2173;SMALL ROMAN NUMERAL FOUR (compat)
486ⅴ → v ; # 2174;SMALL ROMAN NUMERAL FIVE (compat)
487ⅵ → vi ; # 2175;SMALL ROMAN NUMERAL SIX (compat)
488ⅶ → vii ; # 2176;SMALL ROMAN NUMERAL SEVEN (compat)
489ⅷ → viii ; # 2177;SMALL ROMAN NUMERAL EIGHT (compat)
490ⅸ → ix ; # 2178;SMALL ROMAN NUMERAL NINE (compat)
491ⅹ → x ; # 2179;SMALL ROMAN NUMERAL TEN (compat)
492ⅺ → xi ; # 217A;SMALL ROMAN NUMERAL ELEVEN (compat)
493ⅻ → xii ; # 217B;SMALL ROMAN NUMERAL TWELVE (compat)
494ⅼ → l ; # 217C;SMALL ROMAN NUMERAL FIFTY (compat)
495ⅽ → c ; # 217D;SMALL ROMAN NUMERAL ONE HUNDRED (compat)
496ⅾ → d ; # 217E;SMALL ROMAN NUMERAL FIVE HUNDRED (compat)
497ⅿ → m ; # 217F;SMALL ROMAN NUMERAL ONE THOUSAND (compat)
2ca993e8
A
498#
499# Fractions
500#
729e4ab9
A
501¼ → ' 1/4' ; # 00BC;VULGAR FRACTION ONE QUARTER (from ‹character-fallback›)
502½ → ' 1/2' ; # 00BD;VULGAR FRACTION ONE HALF (from ‹character-fallback›)
503¾ → ' 3/4' ; # 00BE;VULGAR FRACTION THREE QUARTERS (from ‹character-fallback›)
504⅓ → ' 1/3' ; # 2153;VULGAR FRACTION ONE THIRD (from ‹character-fallback›)
505⅔ → ' 2/3' ; # 2154;VULGAR FRACTION TWO THIRDS (from ‹character-fallback›)
506⅕ → ' 1/5' ; # 2155;VULGAR FRACTION ONE FIFTH (from ‹character-fallback›)
507⅖ → ' 2/5' ; # 2156;VULGAR FRACTION TWO FIFTHS (from ‹character-fallback›)
508⅗ → ' 3/5' ; # 2157;VULGAR FRACTION THREE FIFTHS (from ‹character-fallback›)
509⅘ → ' 4/5' ; # 2158;VULGAR FRACTION FOUR FIFTHS (from ‹character-fallback›)
510⅙ → ' 1/6' ; # 2159;VULGAR FRACTION ONE SIXTH (from ‹character-fallback›)
511⅚ → ' 5/6' ; # 215A;VULGAR FRACTION FIVE SIXTHS (from ‹character-fallback›)
512⅛ → ' 1/8' ; # 215B;VULGAR FRACTION ONE EIGHTH (from ‹character-fallback›)
513⅜ → ' 3/8' ; # 215C;VULGAR FRACTION THREE EIGHTHS (from ‹character-fallback›)
514⅝ → ' 5/8' ; # 215D;VULGAR FRACTION FIVE EIGHTHS (from ‹character-fallback›)
515⅞ → ' 7/8' ; # 215E;VULGAR FRACTION SEVEN EIGHTHS (from ‹character-fallback›)
516⅟ → ' 1/' ; # 215F;FRACTION NUMERATOR ONE (from ‹character-fallback›)
2ca993e8
A
517#
518# Enclosed numeric
519#
729e4ab9
A
520⑴ → '(1)' ; # 2474;PARENTHESIZED DIGIT ONE (compat)
521⑵ → '(2)' ; # 2475;PARENTHESIZED DIGIT TWO (compat)
522⑶ → '(3)' ; # 2476;PARENTHESIZED DIGIT THREE (compat)
523⑷ → '(4)' ; # 2477;PARENTHESIZED DIGIT FOUR (compat)
524⑸ → '(5)' ; # 2478;PARENTHESIZED DIGIT FIVE (compat)
525⑹ → '(6)' ; # 2479;PARENTHESIZED DIGIT SIX (compat)
526⑺ → '(7)' ; # 247A;PARENTHESIZED DIGIT SEVEN (compat)
527⑻ → '(8)' ; # 247B;PARENTHESIZED DIGIT EIGHT (compat)
528⑼ → '(9)' ; # 247C;PARENTHESIZED DIGIT NINE (compat)
529⑽ → '(10)' ; # 247D;PARENTHESIZED NUMBER TEN (compat)
530⑾ → '(11)' ; # 247E;PARENTHESIZED NUMBER ELEVEN (compat)
531⑿ → '(12)' ; # 247F;PARENTHESIZED NUMBER TWELVE (compat)
532⒀ → '(13)' ; # 2480;PARENTHESIZED NUMBER THIRTEEN (compat)
533⒁ → '(14)' ; # 2481;PARENTHESIZED NUMBER FOURTEEN (compat)
534⒂ → '(15)' ; # 2482;PARENTHESIZED NUMBER FIFTEEN (compat)
535⒃ → '(16)' ; # 2483;PARENTHESIZED NUMBER SIXTEEN (compat)
536⒄ → '(17)' ; # 2484;PARENTHESIZED NUMBER SEVENTEEN (compat)
537⒅ → '(18)' ; # 2485;PARENTHESIZED NUMBER EIGHTEEN (compat)
538⒆ → '(19)' ; # 2486;PARENTHESIZED NUMBER NINETEEN (compat)
539⒇ → '(20)' ; # 2487;PARENTHESIZED NUMBER TWENTY (compat)
540⒈ → '1.' ; # 2488;DIGIT ONE FULL STOP (compat)
541⒉ → '2.' ; # 2489;DIGIT TWO FULL STOP (compat)
542⒊ → '3.' ; # 248A;DIGIT THREE FULL STOP (compat)
543⒋ → '4.' ; # 248B;DIGIT FOUR FULL STOP (compat)
544⒌ → '5.' ; # 248C;DIGIT FIVE FULL STOP (compat)
545⒍ → '6.' ; # 248D;DIGIT SIX FULL STOP (compat)
546⒎ → '7.' ; # 248E;DIGIT SEVEN FULL STOP (compat)
547⒏ → '8.' ; # 248F;DIGIT EIGHT FULL STOP (compat)
548⒐ → '9.' ; # 2490;DIGIT NINE FULL STOP (compat)
549⒑ → '10.' ; # 2491;NUMBER TEN FULL STOP (compat)
550⒒ → '11.' ; # 2492;NUMBER ELEVEN FULL STOP (compat)
551⒓ → '12.' ; # 2493;NUMBER TWELVE FULL STOP (compat)
552⒔ → '13.' ; # 2494;NUMBER THIRTEEN FULL STOP (compat)
553⒕ → '14.' ; # 2495;NUMBER FOURTEEN FULL STOP (compat)
554⒖ → '15.' ; # 2496;NUMBER FIFTEEN FULL STOP (compat)
555⒗ → '16.' ; # 2497;NUMBER SIXTEEN FULL STOP (compat)
556⒘ → '17.' ; # 2498;NUMBER SEVENTEEN FULL STOP (compat)
557⒙ → '18.' ; # 2499;NUMBER EIGHTEEN FULL STOP (compat)
558⒚ → '19.' ; # 249A;NUMBER NINETEEN FULL STOP (compat)
559⒛ → '20.' ; # 249B;NUMBER TWENTY FULL STOP (compat)
2ca993e8
A
560#
561# Other numeric (ideographic and fullwidth)
562#
729e4ab9
A
563〇 → 0 ; # 3007;IDEOGRAPHIC NUMBER ZERO
5640 → 0 ; # FF10;FULLWIDTH DIGIT ZERO (compat)
5651 → 1 ; # FF11;FULLWIDTH DIGIT ONE (compat)
5662 → 2 ; # FF12;FULLWIDTH DIGIT TWO (compat)
5673 → 3 ; # FF13;FULLWIDTH DIGIT THREE (compat)
5684 → 4 ; # FF14;FULLWIDTH DIGIT FOUR (compat)
5695 → 5 ; # FF15;FULLWIDTH DIGIT FIVE (compat)
5706 → 6 ; # FF16;FULLWIDTH DIGIT SIX (compat)
5717 → 7 ; # FF17;FULLWIDTH DIGIT SEVEN (compat)
5728 → 8 ; # FF18;FULLWIDTH DIGIT EIGHT (compat)
5739 → 9 ; # FF19;FULLWIDTH DIGIT NINE (compat)
2ca993e8
A
574#
575# Spaces
576#
729e4ab9
A
577\u00A0 → ' ' ; # 00A0;NO-BREAK SPACE
578\u2002 → ' ' ; # 2002;EN SPACE (compat)
579\u2003 → ' ' ; # 2003;EM SPACE (compat)
580\u2004 → ' ' ; # 2004;THREE-PER-EM SPACE (compat)
581\u2005 → ' ' ; # 2005;FOUR-PER-EM SPACE (compat)
582\u2006 → ' ' ; # 2006;SIX-PER-EM SPACE (compat)
583\u2007 → ' ' ; # 2007;FIGURE SPACE (compat)
584\u2008 → ' ' ; # 2008;PUNCTUATION SPACE (compat)
585\u2009 → ' ' ; # 2009;THIN SPACE (compat)
586\u200A → ' ' ; # 200A;HAIR SPACE (compat)
587\u205F → ' ' ; # 205F;MEDIUM MATHEMATICAL SPACE (compat)
588\u3000 → ' ' ; # 3000;IDEOGRAPHIC SPACE (from ‹character-fallback›)
2ca993e8
A
589#
590# Quotes, apostrophes
591#
592ʹ → \' ; # 02B9;MODIFIER LETTER PRIME
593ʺ → \" ; # 02BA;MODIFIER LETTER DOUBLE PRIME
594ʻ → \' ; # 02BB;MODIFIER LETTER TURNED COMMA
595ʼ → \' ; # 02BC;MODIFIER LETTER APOSTROPHE
596ʽ → \' ; # 02BD;MODIFIER LETTER REVERSED COMMA
597ˈ → \' ; # 02C8;MODIFIER LETTER VERTICAL LINE
598ˋ → '`' ; # 02CB;MODIFIER LETTER GRAVE ACCENT
729e4ab9
A
599‘ → \' ; # 2018;LEFT SINGLE QUOTATION MARK (from ‹character-fallback›)
600’ → \' ; # 2019;RIGHT SINGLE QUOTATION MARK (from ‹character-fallback›)
601‚ → ',' ; # 201A;SINGLE LOW-9 QUOTATION MARK (from ‹character-fallback›)
602‛ → \' ; # 201B;SINGLE HIGH-REVERSED-9 QUOTATION MARK (from ‹character-fallback›)
603“ → \" ; # 201C;LEFT DOUBLE QUOTATION MARK (from ‹character-fallback›)
604” → \" ; # 201D;RIGHT DOUBLE QUOTATION MARK (from ‹character-fallback›)
605„ → ',,' ; # 201E;DOUBLE LOW-9 QUOTATION MARK (from ‹character-fallback›)
606‟ → \" ; # 201F;DOUBLE HIGH-REVERSED-9 QUOTATION MARK (from ‹character-fallback›)
607′ → \' ; # 2032;PRIME
608″ → \" ; # 2033;DOUBLE PRIME
609〝 → \" ; # 301D;REVERSED DOUBLE PRIME QUOTATION MARK
610〞 → \" ; # 301E;DOUBLE PRIME QUOTATION MARK
611" → \" ; # FF02;FULLWIDTH QUOTATION MARK (compat)
612' → \' ; # FF07;FULLWIDTH APOSTROPHE (compat)
613« → '<<' ; # 00AB;LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (from ‹character-fallback›)
614» → '>>' ; # 00BB;RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (from ‹character-fallback›)
615‹ → '<' ; # 2039;SINGLE LEFT-POINTING ANGLE QUOTATION MARK
616› → '>' ; # 203A;SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
2ca993e8
A
617#
618# Dashes, hyphens...
619#
729e4ab9
A
620\u00AD → '-' ; # 00AD;SOFT HYPHEN (from ‹character-fallback›)
621‐ → '-' ; # 2010;HYPHEN (from ‹character-fallback›)
622‑ → '-' ; # 2011;NON-BREAKING HYPHEN (from ‹character-fallback›)
623‒ → '-' ; # 2012;FIGURE DASH (from ‹character-fallback›)
624– → '-' ; # 2013;EN DASH (from ‹character-fallback›)
625— → '-' ; # 2014;EM DASH (from ‹character-fallback›)
626― → '-' ; # 2015;HORIZONTAL BAR (from ‹character-fallback›)
627︱ → '-' ; # FE31;PRESENTATION FORM FOR VERTICAL EM DASH (compat)
628︲ → '-' ; # FE32;PRESENTATION FORM FOR VERTICAL EN DASH (compat)
629﹘ → '-' ; # FE58;SMALL EM DASH (compat)
630﹣ → '-' ; # FE63;SMALL HYPHEN-MINUS (compat)
631- → '-' ; # FF0D;FULLWIDTH HYPHEN-MINUS (compat)
2ca993e8
A
632#
633# Other misc punctuation and symbols
634#
635˂ → '<' ; # 02C2;MODIFIER LETTER LEFT ARROWHEAD
636˃ → '>' ; # 02C3;MODIFIER LETTER RIGHT ARROWHEAD
637˄ → '^' ; # 02C4;MODIFIER LETTER UP ARROWHEAD
638ˆ → '^' ; # 02C6;MODIFIER LETTER CIRCUMFLEX ACCENT
639ː → ':' ; # 02D0;MODIFIER LETTER TRIANGULAR COLON
640˜ → '~' ; # 02DC;SMALL TILDE
729e4ab9
A
641‖ → '||' ; # 2016;DOUBLE VERTICAL LINE
642․ → '.' ; # 2024;ONE DOT LEADER (compat)
643‥ → '..' ; # 2025;TWO DOT LEADER (compat)
644… → '...' ; # 2026;HORIZONTAL ELLIPSIS (compat)
645‼ → '!!' ; # 203C;DOUBLE EXCLAMATION MARK (compat)
646⁄ → '/' ; # 2044;FRACTION SLASH (from ‹character-fallback›)
647⁅ → '[' ; # 2045;LEFT SQUARE BRACKET WITH QUILL
648⁆ → ']' ; # 2046;RIGHT SQUARE BRACKET WITH QUILL
649⁇ → '??' ; # 2047;DOUBLE QUESTION MARK (compat)
650⁈ → '?!' ; # 2048;QUESTION EXCLAMATION MARK (compat)
651⁉ → '!?' ; # 2049;EXCLAMATION QUESTION MARK (compat)
652⁎ → '*' ; # 204E;LOW ASTERISK
2ca993e8 653# CJK
729e4ab9
A
654、 → ',' ; # 3001;IDEOGRAPHIC COMMA
655。 → '.' ; # 3002;IDEOGRAPHIC FULL STOP
656〈 → '<' ; # 3008;LEFT ANGLE BRACKET
657〉 → '>' ; # 3009;RIGHT ANGLE BRACKET
658《 → '<<' ; # 300A;LEFT DOUBLE ANGLE BRACKET
659》 → '>>' ; # 300B;RIGHT DOUBLE ANGLE BRACKET
660〔 → '[' ; # 3014;LEFT TORTOISE SHELL BRACKET
661〕 → ']' ; # 3015;RIGHT TORTOISE SHELL BRACKET
662〘 → '[' ; # 3018;LEFT WHITE TORTOISE SHELL BRACKET
663〙 → ']' ; # 3019;RIGHT WHITE TORTOISE SHELL BRACKET
664〚 → '[' ; # 301A;LEFT WHITE SQUARE BRACKET
665〛 → ']' ; # 301B;RIGHT WHITE SQUARE BRACKET
2ca993e8 666# Vertical and small forms
729e4ab9
A
667︐ → ',' ; # FE10;PRESENTATION FORM FOR VERTICAL COMMA (compat)
668︑ → ',' ; # FE11;PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA (compat)
669︒ → '.' ; # FE12;PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP (compat)
670︓ → ':' ; # FE13;PRESENTATION FORM FOR VERTICAL COLON (compat)
671︔ → ';' ; # FE14;PRESENTATION FORM FOR VERTICAL SEMICOLON (compat)
672︕ → '!' ; # FE15;PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (compat)
673︖ → '?' ; # FE16;PRESENTATION FORM FOR VERTICAL QUESTION MARK (compat)
674︙ → '...' ; # FE19;PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (compat)
675︰ → '..' ; # FE30;PRESENTATION FORM FOR VERTICAL TWO DOT LEADER (compat)
676︵ → '(' ; # FE35;PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS (compat)
677︶ → ')' ; # FE36;PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS (compat)
678︷ → '{' ; # FE37;PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET (compat)
679︸ → '}' ; # FE38;PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET (compat)
680︹ → '[' ; # FE39;PRESENTATION FORM FOR VERTICAL LEFT TORTOISE SHELL BRACKET (compat)
681︺ → ']' ; # FE3A;PRESENTATION FORM FOR VERTICAL RIGHT TORTOISE SHELL BRACKET (compat)
682︽ → '<<' ; # FE3D;PRESENTATION FORM FOR VERTICAL LEFT DOUBLE ANGLE BRACKET (compat)
683︾ → '>>' ; # FE3E;PRESENTATION FORM FOR VERTICAL RIGHT DOUBLE ANGLE BRACKET (compat)
684︿ → '<' ; # FE3F;PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET (compat)
685﹀ → '>' ; # FE40;PRESENTATION FORM FOR VERTICAL RIGHT ANGLE BRACKET (compat)
686﹇ → '[' ; # FE47;PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET (compat)
687﹈ → ']' ; # FE48;PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET (compat)
688﹐ → ',' ; # FE50;SMALL COMMA (compat)
689﹑ → ',' ; # FE51;SMALL IDEOGRAPHIC COMMA (compat)
690﹒ → '.' ; # FE52;SMALL FULL STOP (compat)
691﹔ → ';' ; # FE54;SMALL SEMICOLON (compat)
692﹕ → ':' ; # FE55;SMALL COLON (compat)
693﹖ → '?' ; # FE56;SMALL QUESTION MARK (compat)
694﹗ → '!' ; # FE57;SMALL EXCLAMATION MARK (compat)
695﹙ → '(' ; # FE59;SMALL LEFT PARENTHESIS (compat)
696﹚ → ')' ; # FE5A;SMALL RIGHT PARENTHESIS (compat)
697﹛ → '{' ; # FE5B;SMALL LEFT CURLY BRACKET (compat)
698﹜ → '}' ; # FE5C;SMALL RIGHT CURLY BRACKET (compat)
699﹝ → '[' ; # FE5D;SMALL LEFT TORTOISE SHELL BRACKET (compat)
700﹞ → ']' ; # FE5E;SMALL RIGHT TORTOISE SHELL BRACKET (compat)
701﹟ → '#' ; # FE5F;SMALL NUMBER SIGN (compat)
702﹠ → '&' ; # FE60;SMALL AMPERSAND (compat)
703﹡ → '*' ; # FE61;SMALL ASTERISK (compat)
704﹢ → '+' ; # FE62;SMALL PLUS SIGN (compat)
705﹤ → '<' ; # FE64;SMALL LESS-THAN SIGN (compat)
706﹥ → '>' ; # FE65;SMALL GREATER-THAN SIGN (compat)
707﹦ → '=' ; # FE66;SMALL EQUALS SIGN (compat)
708﹨ → '\' ; # FE68;SMALL REVERSE SOLIDUS (compat)
709﹩ → '$' ; # FE69;SMALL DOLLAR SIGN (compat)
710﹪ → '%' ; # FE6A;SMALL PERCENT SIGN (compat)
711﹫ → '@' ; # FE6B;SMALL COMMERCIAL AT (compat)
2ca993e8 712# Fullwidth and halfwidth
729e4ab9
A
713! → '!' ; # FF01;FULLWIDTH EXCLAMATION MARK (compat)
714# → '#' ; # FF03;FULLWIDTH NUMBER SIGN (compat)
715$ → '$' ; # FF04;FULLWIDTH DOLLAR SIGN (compat)
716% → '%' ; # FF05;FULLWIDTH PERCENT SIGN (compat)
717& → '&' ; # FF06;FULLWIDTH AMPERSAND (compat)
718( → '(' ; # FF08;FULLWIDTH LEFT PARENTHESIS (compat)
719) → ')' ; # FF09;FULLWIDTH RIGHT PARENTHESIS (compat)
720* → '*' ; # FF0A;FULLWIDTH ASTERISK (compat)
721+ → '+' ; # FF0B;FULLWIDTH PLUS SIGN (compat)
722, → ',' ; # FF0C;FULLWIDTH COMMA (compat)
723. → '.' ; # FF0E;FULLWIDTH FULL STOP (compat)
724/ → '/' ; # FF0F;FULLWIDTH SOLIDUS (compat)
725: → ':' ; # FF1A;FULLWIDTH COLON (compat)
726; → ';' ; # FF1B;FULLWIDTH SEMICOLON (compat)
727< → '<' ; # FF1C;FULLWIDTH LESS-THAN SIGN (compat)
728= → '=' ; # FF1D;FULLWIDTH EQUALS SIGN (compat)
729> → '>' ; # FF1E;FULLWIDTH GREATER-THAN SIGN (compat)
730? → '?' ; # FF1F;FULLWIDTH QUESTION MARK (compat)
731@ → '@' ; # FF20;FULLWIDTH COMMERCIAL AT (compat)
732[ → '[' ; # FF3B;FULLWIDTH LEFT SQUARE BRACKET (compat)
733\ → '\' ; # FF3C;FULLWIDTH REVERSE SOLIDUS (compat)
734] → ']' ; # FF3D;FULLWIDTH RIGHT SQUARE BRACKET (compat)
735^ → '^' ; # FF3E;FULLWIDTH CIRCUMFLEX ACCENT (compat)
736_ → '_' ; # FF3F;FULLWIDTH LOW LINE (compat)
737` → '`' ; # FF40;FULLWIDTH GRAVE ACCENT (compat)
738{ → '{' ; # FF5B;FULLWIDTH LEFT CURLY BRACKET (compat)
739| → '|' ; # FF5C;FULLWIDTH VERTICAL LINE (compat)
740} → '}' ; # FF5D;FULLWIDTH RIGHT CURLY BRACKET (compat)
741~ → '~' ; # FF5E;FULLWIDTH TILDE (compat)
742⦅ → '((' ; # FF5F;FULLWIDTH LEFT WHITE PARENTHESIS (compat)(from ‹character-fallback›)
743⦆ → '))' ; # FF60;FULLWIDTH RIGHT WHITE PARENTHESIS (compat)(from ‹character-fallback›)
744。 → '.' ; # FF61;HALFWIDTH IDEOGRAPHIC FULL STOP (compat)
745、 → ',' ; # FF64;HALFWIDTH IDEOGRAPHIC COMMA (compat)
2ca993e8
A
746#
747# Other math operators (non-ASCII-range)
748#
729e4ab9
A
749× → '*' ; # 00D7;MULTIPLICATION SIGN
750÷ → '/' ; # 00F7;DIVISION SIGN
2ca993e8
A
751˖ → '+' ; # 02D6;MODIFIER LETTER PLUS SIGN
752˗ → '-' ; # 02D7;MODIFIER LETTER MINUS SIGN
729e4ab9
A
753− → '-' ; # 2212;MINUS SIGN (from ‹character-fallback›)
754∕ → '/' ; # 2215;DIVISION SLASH (from ‹character-fallback›)
755∖ → '\' ; # 2216;SET MINUS (from ‹character-fallback›)
756∣ → '|' ; # 2223;DIVIDES (from ‹character-fallback›)
757∥ → '||' ; # 2225;PARALLEL TO (from ‹character-fallback›)
758≪ → '<<' ; # 226A;MUCH LESS-THAN
759≫ → '>>' ; # 226B;MUCH GREATER-THAN
760⦅ → '((' ; # 2985;LEFT WHITE PARENTHESIS
761⦆ → '))' ; # 2986;RIGHT WHITE PARENTHESIS
762⩴ → '::=' ; # 2A74;DOUBLE COLON EQUAL (compat)
763⩵ → '==' ; # 2A75;TWO CONSECUTIVE EQUALS SIGNS (compat)
764⩶ → '===' ; # 2A76;THREE CONSECUTIVE EQUALS SIGNS (compat)
2ca993e8 765