ICU-66108.tar.gz

[apple/icu.git] / icuSources / data / translit / Latin_ASCII.txt

diff --git a/icuSources/data/translit/Latin_ASCII.txt b/icuSources/data/translit/Latin_ASCII.txt
index 19bdb42dce18196f67d3dcda5f70dc8ae1ee194a..686e441cc32076943cf2a602ccb1ec9c2c2cadeb 100644 (file)
--- a/icuSources/data/translit/Latin_ASCII.txt
+++ b/icuSources/data/translit/Latin_ASCII.txt
@@ -1,16 +1,29 @@
-# ***************************************************************************
-# *
-# *  Copyright (C) 2004-2015, International Business Machines
-# *  Corporation; Unicode, Inc.; and others.  All Rights Reserved.
-# *
-# ***************************************************************************
+# © 2016 and later: Unicode, Inc. and others.
+# License & terms of use: http://www.unicode.org/copyright.html#License
+#

 # File: Latin_ASCII.txt
 # File: Latin_ASCII.txt

-# Generated from CLDR 
+# Generated from CLDR
+#
+
+# This handles only Latin, Common, and IDEOGRAPHIC NUMBER ZERO (Han).

 #
 :: [[:Latin:][:Common:][:Inherited:][〇]] ;
 #
 :: [[:Latin:][:Common:][:Inherited:][〇]] ;

+#
+# 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 or digits. We then recompose to permit rules
+# such as mapping NOT EQUAL TO to an ASCII equivalent e.g. "!=" if we choose to.
+#

 :: NFD() ;
 :: NFD() ;

-[:Latin:] { [:Mn:]+ → ; # maps to nothing; remove all Mn following Latin letter
+[[:Latin:][0-9]] { [:Mn:]+ → ; # maps to nothing; remove all Mn following Latin letter/digit

 :: NFC() ;
 :: 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
 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


@@ -23,7 +36,7 @@
 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
 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 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)
 ı → i ; # 0131;LATIN SMALL LETTER DOTLESS I
 IJ → IJ ; # 0132;LATIN CAPITAL LIGATURE IJ (compat)
 ij → ij ; # 0133;LATIN SMALL LIGATURE IJ (compat)


@@ -158,13 +171,6 @@
 ʦ → ts ; # 02A6;LATIN SMALL LETTER TS DIGRAPH
 ʪ → ls ; # 02AA;LATIN SMALL LETTER LS DIGRAPH
 ʫ → lz ; # 02AB;LATIN SMALL LETTER LZ DIGRAPH
 ʦ → ts ; # 02A6;LATIN SMALL LETTER TS DIGRAPH
 ʪ → ls ; # 02AA;LATIN SMALL LETTER LS DIGRAPH
 ʫ → lz ; # 02AB;LATIN SMALL LETTER LZ DIGRAPH

-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
-ʾ → 2 ; # 02BE;MODIFIER LETTER RIGHT HALF RING (transliteration for Arabic hamza)
-ʿ → 3 ; # 02BF;MODIFIER LETTER LEFT HALF RING (transliteration for Arabic ain)

 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
 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


@@ -229,6 +235,106 @@
 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
 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

+# Latin extended C and D (later addition)
+Ⱡ → L ; # 2C60;LATIN CAPITAL LETTER L WITH DOUBLE BAR
+ⱡ → l ; # 2C61;LATIN SMALL LETTER L WITH DOUBLE BAR
+Ɫ → L ; # 2C62;LATIN CAPITAL LETTER L WITH MIDDLE TILDE
+Ᵽ → P ; # 2C63;LATIN CAPITAL LETTER P WITH STROKE
+Ɽ → R ; # 2C64;LATIN CAPITAL LETTER R WITH TAIL
+ⱥ → a ; # 2C65;LATIN SMALL LETTER A WITH STROKE
+ⱦ → t ; # 2C66;LATIN SMALL LETTER T WITH DIAGONAL STROKE
+Ⱨ → H ; # 2C67;LATIN CAPITAL LETTER H WITH DESCENDER
+ⱨ → h ; # 2C68;LATIN SMALL LETTER H WITH DESCENDER
+Ⱪ → K ; # 2C69;LATIN CAPITAL LETTER K WITH DESCENDER
+ⱪ → k ; # 2C6A;LATIN SMALL LETTER K WITH DESCENDER
+Ⱬ → Z ; # 2C6B;LATIN CAPITAL LETTER Z WITH DESCENDER
+ⱬ → z ; # 2C6C;LATIN SMALL LETTER Z WITH DESCENDER
+Ɱ → M ; # 2C6E;LATIN CAPITAL LETTER M WITH HOOK
+ⱱ → v ; # 2C71;LATIN SMALL LETTER V WITH RIGHT HOOK
+Ⱳ → W ; # 2C72;LATIN CAPITAL LETTER W WITH HOOK
+ⱳ → w ; # 2C73;LATIN SMALL LETTER W WITH HOOK
+ⱴ → v ; # 2C74;LATIN SMALL LETTER V WITH CURL
+ⱸ → e ; # 2C78;LATIN SMALL LETTER E WITH NOTCH
+ⱺ → o ; # 2C7A;LATIN SMALL LETTER O WITH LOW RING INSIDE
+Ȿ → S ; # 2C7E;LATIN CAPITAL LETTER S WITH SWASH TAIL
+Ɀ → Z ; # 2C7F;LATIN CAPITAL LETTER Z WITH SWASH TAIL
+ꜰ → F ; # A730;LATIN LETTER SMALL CAPITAL F
+ꜱ → S ; # A731;LATIN LETTER SMALL CAPITAL S
+Ꜳ → AA ; # A732;LATIN CAPITAL LETTER AA
+ꜳ → aa ; # A733;LATIN SMALL LETTER AA
+Ꜵ → AO ; # A734;LATIN CAPITAL LETTER AO
+ꜵ → ao ; # A735;LATIN SMALL LETTER AO
+Ꜷ → AU ; # A736;LATIN CAPITAL LETTER AU
+ꜷ → au ; # A737;LATIN SMALL LETTER AU
+Ꜹ → AV ; # A738;LATIN CAPITAL LETTER AV
+ꜹ → av ; # A739;LATIN SMALL LETTER AV
+Ꜻ → AV ; # A73A;LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR
+ꜻ → av ; # A73B;LATIN SMALL LETTER AV WITH HORIZONTAL BAR
+Ꜽ → AY ; # A73C;LATIN CAPITAL LETTER AY
+ꜽ → ay ; # A73D;LATIN SMALL LETTER AY
+Ꝁ → K ; # A740;LATIN CAPITAL LETTER K WITH STROKE
+ꝁ → k ; # A741;LATIN SMALL LETTER K WITH STROKE
+Ꝃ → K ; # A742;LATIN CAPITAL LETTER K WITH DIAGONAL STROKE
+ꝃ → k ; # A743;LATIN SMALL LETTER K WITH DIAGONAL STROKE
+Ꝅ → K ; # A744;LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE
+ꝅ → k ; # A745;LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE
+Ꝇ → L ; # A746;LATIN CAPITAL LETTER BROKEN L
+ꝇ → l ; # A747;LATIN SMALL LETTER BROKEN L
+Ꝉ → L ; # A748;LATIN CAPITAL LETTER L WITH HIGH STROKE
+ꝉ → l ; # A749;LATIN SMALL LETTER L WITH HIGH STROKE
+Ꝋ → O ; # A74A;LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY
+ꝋ → o ; # A74B;LATIN SMALL LETTER O WITH LONG STROKE OVERLAY
+Ꝍ → O ; # A74C;LATIN CAPITAL LETTER O WITH LOOP
+ꝍ → o ; # A74D;LATIN SMALL LETTER O WITH LOOP
+Ꝏ → OO ; # A74E;LATIN CAPITAL LETTER OO
+ꝏ → oo ; # A74F;LATIN SMALL LETTER OO
+Ꝑ → P ; # A750;LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER
+ꝑ → p ; # A751;LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER
+Ꝓ → P ; # A752;LATIN CAPITAL LETTER P WITH FLOURISH
+ꝓ → p ; # A753;LATIN SMALL LETTER P WITH FLOURISH
+Ꝕ → P ; # A754;LATIN CAPITAL LETTER P WITH SQUIRREL TAIL
+ꝕ → p ; # A755;LATIN SMALL LETTER P WITH SQUIRREL TAIL
+Ꝗ → Q ; # A756;LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER
+ꝗ → q ; # A757;LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER
+Ꝙ → Q ; # A758;LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE
+ꝙ → q ; # A759;LATIN SMALL LETTER Q WITH DIAGONAL STROKE
+Ꝟ → V ; # A75E;LATIN CAPITAL LETTER V WITH DIAGONAL STROKE
+ꝟ → v ; # A75F;LATIN SMALL LETTER V WITH DIAGONAL STROKE
+Ꝡ → VY ; # A760;LATIN CAPITAL LETTER VY
+ꝡ → vy ; # A761;LATIN SMALL LETTER VY
+Ꝥ → TH ; # A764;LATIN CAPITAL LETTER THORN WITH STROKE
+ꝥ → th ; # A765;LATIN SMALL LETTER THORN WITH STROKE
+Ꝧ → TH ; # A766;LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER
+ꝧ → th ; # A767;LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER
+ꝱ → d ; # A771;LATIN SMALL LETTER DUM
+ꝲ → l ; # A772;LATIN SMALL LETTER LUM
+ꝳ → m ; # A773;LATIN SMALL LETTER MUM
+ꝴ → n ; # A774;LATIN SMALL LETTER NUM
+ꝵ → r ; # A775;LATIN SMALL LETTER RUM
+ꝶ → R ; # A776;LATIN LETTER SMALL CAPITAL RUM
+ꝷ → t ; # A777;LATIN SMALL LETTER TUM
+Ꝺ → D ; # A779;LATIN CAPITAL LETTER INSULAR D
+ꝺ → d ; # A77A;LATIN SMALL LETTER INSULAR D
+Ꝼ → F ; # A77B;LATIN CAPITAL LETTER INSULAR F
+ꝼ → f ; # A77C;LATIN SMALL LETTER INSULAR F
+Ꞇ → T ; # A786;LATIN CAPITAL LETTER INSULAR T
+ꞇ → t ; # A787;LATIN SMALL LETTER INSULAR T
+Ꞑ → N ; # A790;LATIN CAPITAL LETTER N WITH DESCENDER
+ꞑ → n ; # A791;LATIN SMALL LETTER N WITH DESCENDER
+Ꞓ → C ; # A792;LATIN CAPITAL LETTER C WITH BAR
+ꞓ → c ; # A793;LATIN SMALL LETTER C WITH BAR
+Ꞡ → G ; # A7A0;LATIN CAPITAL LETTER G WITH OBLIQUE STROKE
+ꞡ → g ; # A7A1;LATIN SMALL LETTER G WITH OBLIQUE STROKE
+Ꞣ → K ; # A7A2;LATIN CAPITAL LETTER K WITH OBLIQUE STROKE
+ꞣ → k ; # A7A3;LATIN SMALL LETTER K WITH OBLIQUE STROKE
+Ꞥ → N ; # A7A4;LATIN CAPITAL LETTER N WITH OBLIQUE STROKE
+ꞥ → n ; # A7A5;LATIN SMALL LETTER N WITH OBLIQUE STROKE
+Ꞧ → R ; # A7A6;LATIN CAPITAL LETTER R WITH OBLIQUE STROKE
+ꞧ → r ; # A7A7;LATIN SMALL LETTER R WITH OBLIQUE STROKE
+Ꞩ → S ; # A7A8;LATIN CAPITAL LETTER S WITH OBLIQUE STROKE
+ꞩ → s ; # A7A9;LATIN SMALL LETTER S WITH OBLIQUE STROKE
+Ɦ → H ; # A7AA;LATIN CAPITAL LETTER H WITH HOOK
+# 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)
 ff → ff ; # FB00;LATIN SMALL LIGATURE FF (compat)
 fi → fi ; # FB01;LATIN SMALL LIGATURE FI (compat)
 fl → fl ; # FB02;LATIN SMALL LIGATURE FL (compat)


@@ -236,6 +342,7 @@
 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)
 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 → A ; # FF21;FULLWIDTH LATIN CAPITAL LETTER A (compat)
 Ｂ → B ; # FF22;FULLWIDTH LATIN CAPITAL LETTER B (compat)
 Ｃ → C ; # FF23;FULLWIDTH LATIN CAPITAL LETTER C (compat)
 Ａ → A ; # FF21;FULLWIDTH LATIN CAPITAL LETTER A (compat)
 Ｂ → B ; # FF22;FULLWIDTH LATIN CAPITAL LETTER B (compat)
 Ｃ → C ; # FF23;FULLWIDTH LATIN CAPITAL LETTER C (compat)


@@ -288,6 +395,9 @@
 ｘ → x ; # FF58;FULLWIDTH LATIN SMALL LETTER X (compat)
 ｙ → y ; # FF59;FULLWIDTH LATIN SMALL LETTER Y (compat)
 ｚ → z ; # FF5A;FULLWIDTH LATIN SMALL LETTER Z (compat)
 ｘ → x ; # FF58;FULLWIDTH LATIN SMALL LETTER X (compat)
 ｙ → y ; # FF59;FULLWIDTH LATIN SMALL LETTER Y (compat)
 ｚ → 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›)
 © → '(C)' ; # 00A9;COPYRIGHT SIGN (from ‹character-fallback›)
 ® → '(R)' ; # 00AE;REGISTERED SIGN (from ‹character-fallback›)
 ₠ → CE ; # 20A0;EURO-CURRENCY SIGN (from ‹character-fallback›)


@@ -313,6 +423,8 @@
 ℓ → l ; # 2113;SCRIPT SMALL L (compat)
 ℕ → N ; # 2115;DOUBLE-STRUCK CAPITAL N (compat)
 № → No ; # 2116;NUMERO SIGN (compat)
 ℓ → l ; # 2113;SCRIPT SMALL L (compat)
 ℕ → N ; # 2115;DOUBLE-STRUCK CAPITAL N (compat)
 № → No ; # 2116;NUMERO SIGN (compat)

+℗ → '(P)' ; # 2117;SOUND RECORDING COPYRIGHT (later addition)
+℘ → P ; # 2118;SCRIPT CAPITAL P (later addition)

 ℙ → P ; # 2119;DOUBLE-STRUCK CAPITAL P (compat)
 ℚ → Q ; # 211A;DOUBLE-STRUCK CAPITAL Q (compat)
 ℛ → R ; # 211B;SCRIPT CAPITAL R (compat)
 ℙ → P ; # 2119;DOUBLE-STRUCK CAPITAL P (compat)
 ℚ → Q ; # 211A;DOUBLE-STRUCK CAPITAL Q (compat)
 ℛ → R ; # 211B;SCRIPT CAPITAL R (compat)


@@ -336,6 +448,9 @@
 ⅇ → e ; # 2147;DOUBLE-STRUCK ITALIC SMALL E (compat)
 ⅈ → i ; # 2148;DOUBLE-STRUCK ITALIC SMALL I (compat)
 ⅉ → j ; # 2149;DOUBLE-STRUCK ITALIC SMALL J (compat)
 ⅇ → e ; # 2147;DOUBLE-STRUCK ITALIC SMALL E (compat)
 ⅈ → i ; # 2148;DOUBLE-STRUCK ITALIC SMALL I (compat)
 ⅉ → 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)
 ㍱ → hPa ; # 3371;SQUARE HPA (compat)
 ㍲ → da ; # 3372;SQUARE DA (compat)
 ㍳ → AU ; # 3373;SQUARE AU (compat)


@@ -417,6 +532,9 @@
 ㏝ → 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›)
 ㏝ → 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)
 ⒜ → '(a)' ; # 249C;PARENTHESIZED LATIN SMALL LETTER A (compat)
 ⒝ → '(b)' ; # 249D;PARENTHESIZED LATIN SMALL LETTER B (compat)
 ⒞ → '(c)' ; # 249E;PARENTHESIZED LATIN SMALL LETTER C (compat)


@@ -443,6 +561,9 @@
 ⒳ → '(x)' ; # 24B3;PARENTHESIZED LATIN SMALL LETTER X (compat)
 ⒴ → '(y)' ; # 24B4;PARENTHESIZED LATIN SMALL LETTER Y (compat)
 ⒵ → '(z)' ; # 24B5;PARENTHESIZED LATIN SMALL LETTER Z (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 → I ; # 2160;ROMAN NUMERAL ONE (compat)
 Ⅱ → II ; # 2161;ROMAN NUMERAL TWO (compat)
 Ⅲ → III ; # 2162;ROMAN NUMERAL THREE (compat)
 Ⅰ → I ; # 2160;ROMAN NUMERAL ONE (compat)
 Ⅱ → II ; # 2161;ROMAN NUMERAL TWO (compat)
 Ⅲ → III ; # 2162;ROMAN NUMERAL THREE (compat)


@@ -475,6 +596,9 @@
 ⅽ → c ; # 217D;SMALL ROMAN NUMERAL ONE HUNDRED (compat)
 ⅾ → d ; # 217E;SMALL ROMAN NUMERAL FIVE HUNDRED (compat)
 ⅿ → m ; # 217F;SMALL ROMAN NUMERAL ONE THOUSAND (compat)
 ⅽ → c ; # 217D;SMALL ROMAN NUMERAL ONE HUNDRED (compat)
 ⅾ → 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›)
 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›)


@@ -491,6 +615,9 @@
 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›)
 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)
 ⑴ → '(1)' ; # 2474;PARENTHESIZED DIGIT ONE (compat)
 ⑵ → '(2)' ; # 2475;PARENTHESIZED DIGIT TWO (compat)
 ⑶ → '(3)' ; # 2476;PARENTHESIZED DIGIT THREE (compat)


@@ -531,6 +658,9 @@
 ⒙ → '18.' ; # 2499;NUMBER EIGHTEEN FULL STOP (compat)
 ⒚ → '19.' ; # 249A;NUMBER NINETEEN FULL STOP (compat)
 ⒛ → '20.' ; # 249B;NUMBER TWENTY 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)
+#

 〇 → 0 ; # 3007;IDEOGRAPHIC NUMBER ZERO
 ０ → 0 ; # FF10;FULLWIDTH DIGIT ZERO (compat)
 １ → 1 ; # FF11;FULLWIDTH DIGIT ONE (compat)
 〇 → 0 ; # 3007;IDEOGRAPHIC NUMBER ZERO
 ０ → 0 ; # FF10;FULLWIDTH DIGIT ZERO (compat)
 １ → 1 ; # FF11;FULLWIDTH DIGIT ONE (compat)


@@ -542,6 +672,9 @@
 ７ → 7 ; # FF17;FULLWIDTH DIGIT SEVEN (compat)
 ８ → 8 ; # FF18;FULLWIDTH DIGIT EIGHT (compat)
 ９ → 9 ; # FF19;FULLWIDTH DIGIT NINE (compat)
 ７ → 7 ; # FF17;FULLWIDTH DIGIT SEVEN (compat)
 ８ → 8 ; # FF18;FULLWIDTH DIGIT EIGHT (compat)
 ９ → 9 ; # FF19;FULLWIDTH DIGIT NINE (compat)

+#
+# Spaces
+#

 \u00A0 → ' ' ; # 00A0;NO-BREAK SPACE
 \u2002 → ' ' ; # 2002;EN SPACE (compat)
 \u2003 → ' ' ; # 2003;EM SPACE (compat)
 \u00A0 → ' ' ; # 00A0;NO-BREAK SPACE
 \u2002 → ' ' ; # 2002;EN SPACE (compat)
 \u2003 → ' ' ; # 2003;EM SPACE (compat)


@@ -554,6 +687,16 @@
 \u200A → ' ' ; # 200A;HAIR SPACE (compat)
 \u205F → ' ' ; # 205F;MEDIUM MATHEMATICAL SPACE (compat)
 \u3000 → ' ' ; # 3000;IDEOGRAPHIC SPACE (from ‹character-fallback›)
 \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›)
 ‘ → \' ; # 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›)


@@ -572,6 +715,9 @@
 » → '>>' ; # 00BB;RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (from ‹character-fallback›)
 ‹ → '<' ; # 2039;SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 › → '>' ; # 203A;SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 » → '>>' ; # 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›)
 \u00AD → '-' ; # 00AD;SOFT HYPHEN (from ‹character-fallback›)
 ‐ → '-' ; # 2010;HYPHEN (from ‹character-fallback›)
 ‑ → '-' ; # 2011;NON-BREAKING HYPHEN (from ‹character-fallback›)


@@ -584,6 +730,15 @@
 ﹘ → '-' ; # FE58;SMALL EM DASH (compat)
 ﹣ → '-' ; # FE63;SMALL HYPHEN-MINUS (compat)
 － → '-' ; # FF0D;FULLWIDTH HYPHEN-MINUS (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)
 ‖ → '||' ; # 2016;DOUBLE VERTICAL LINE
 ․ → '.' ; # 2024;ONE DOT LEADER (compat)
 ‥ → '..' ; # 2025;TWO DOT LEADER (compat)


@@ -596,6 +751,7 @@
 ⁈ → '?!' ; # 2048;QUESTION EXCLAMATION MARK (compat)
 ⁉ → '!?' ; # 2049;EXCLAMATION QUESTION MARK (compat)
 ⁎ → '*' ; # 204E;LOW ASTERISK
 ⁈ → '?!' ; # 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
 、 → ',' ; # 3001;IDEOGRAPHIC COMMA
 。 → '.' ; # 3002;IDEOGRAPHIC FULL STOP
 〈 → '<' ; # 3008;LEFT ANGLE BRACKET


@@ -608,6 +764,7 @@
 〙 → ']' ; # 3019;RIGHT WHITE TORTOISE SHELL BRACKET
 〚 → '[' ; # 301A;LEFT WHITE SQUARE BRACKET
 〛 → ']' ; # 301B;RIGHT WHITE SQUARE 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)
 ︐ → ',' ; # FE10;PRESENTATION FORM FOR VERTICAL COMMA (compat)
 ︑ → ',' ; # FE11;PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA (compat)
 ︒ → '.' ; # FE12;PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP (compat)


@@ -653,6 +810,7 @@
 ﹩ → '$' ; # FE69;SMALL DOLLAR SIGN (compat)
 ﹪ → '%' ; # FE6A;SMALL PERCENT SIGN (compat)
 ﹫ → '@' ; # FE6B;SMALL COMMERCIAL AT (compat)
 ﹩ → '$' ; # 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)
 ＄ → '$' ; # FF04;FULLWIDTH DOLLAR SIGN (compat)
 ！ → '!' ; # FF01;FULLWIDTH EXCLAMATION MARK (compat)
 ＃ → '#' ; # FF03;FULLWIDTH NUMBER SIGN (compat)
 ＄ → '$' ; # FF04;FULLWIDTH DOLLAR SIGN (compat)


@@ -686,8 +844,13 @@
 ｠ → '))' ; # FF60;FULLWIDTH RIGHT WHITE PARENTHESIS (compat)(from ‹character-fallback›)
 ｡ → '.' ; # FF61;HALFWIDTH IDEOGRAPHIC FULL STOP (compat)
 ､ → ',' ; # FF64;HALFWIDTH IDEOGRAPHIC COMMA (compat)
 ｠ → '))' ; # 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
 × → '*' ; # 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›)
 − → '-' ; # 2212;MINUS SIGN (from ‹character-fallback›)
 ∕ → '/' ; # 2215;DIVISION SLASH (from ‹character-fallback›)
 ∖ → '\' ; # 2216;SET MINUS (from ‹character-fallback›)


@@ -700,3 +863,4 @@
 ⩴ → '::=' ; # 2A74;DOUBLE COLON EQUAL (compat)
 ⩵ → '==' ; # 2A75;TWO CONSECUTIVE EQUALS SIGNS (compat)
 ⩶ → '===' ; # 2A76;THREE CONSECUTIVE EQUALS SIGNS (compat)
 ⩴ → '::=' ; # 2A74;DOUBLE COLON EQUAL (compat)
 ⩵ → '==' ; # 2A75;TWO CONSECUTIVE EQUALS SIGNS (compat)
 ⩶ → '===' ; # 2A76;THREE CONSECUTIVE EQUALS SIGNS (compat)

+