cldr-transforms 46.0.0-BETA2

package/transforms/Any-Accents.txt

@@ -0,0 +1,270 @@
+
+:: NFD (NFC) ;
+# to do: make reversible
+# define special conversion characters.
+# variants of this could use different characters, or set one or the other to null.
+$pre = \← ;
+$post = \→ ;
+# Provide keyboard equivalents for common diacritics used in transliteration
+$pre \` $post ↔ ̀ ; # COMBINING GRAVE ACCENT
+$pre \' $post ↔ ́ ; # COMBINING ACUTE ACCENT
+$pre \^ $post ↔ ̂ ; # COMBINING CIRCUMFLEX ACCENT
+$pre \~ $post ↔ ̃ ; # COMBINING TILDE
+$pre \- $post ↔ ̄ ; # COMBINING MACRON
+$pre \" $post ↔ ̈ ; # COMBINING DIAERESIS
+$pre \* $post ↔ ̊ ; # COMBINING RING ABOVE
+$pre \, $post ↔ ̧ ; # COMBINING CEDILLA
+$pre '/' $post ↔ ̸ ; # COMBINING LONG SOLIDUS OVERLAY
+$pre \. $post ↔ ̣ ; # COMBINING DOT BELOW
+# Combine common characters
+$pre AE $post ↔ Æ ; # LATIN CAPITAL LETTER AE
+$pre ae $post ↔ æ ; # LATIN SMALL LETTER AE
+$pre D $post ↔ Ð ; # LATIN CAPITAL LETTER ETH
+$pre d $post ↔ ð ; # LATIN SMALL LETTER ETH
+$pre O'/' $post ↔ Ø ; # LATIN CAPITAL LETTER O WITH STROKE
+$pre o'/' $post ↔ ø ; # LATIN SMALL LETTER O WITH STROKE
+$pre TH $post ↔ Þ ; # LATIN CAPITAL LETTER THORN
+$pre th $post ↔ þ ; # LATIN SMALL LETTER THORN
+$pre OE $post ↔ Œ ; # LATIN CAPITAL LIGATURE OE
+$pre oe $post ↔ œ ; # LATIN SMALL LIGATURE OE
+$pre ss $post ↔ ß ; # LATIN SMALL LETTER SHARP S
+$pre NG $post ↔ Ŋ ; # LATIN CAPITAL LETTER ENG
+$pre ng $post ↔ ŋ ; # LATIN SMALL LETTER ENG
+$pre T $post ↔ Θ ; # THETA
+$pre t $post ↔ θ ; # THETA
+$pre SH $post ↔ Ʃ ; # LATIN CAPITAL LETTER ESH
+$pre sh $post ↔ ʃ ; # LATIN SMALL LETTER ESH
+$pre ZH $post ↔ Ʒ ; # LATIN CAPITAL LETTER EZH
+$pre zh $post ↔ ʒ ; # LATIN SMALL LETTER EZH
+$pre U $post ↔ Ʊ ; # LATIN CAPITAL LETTER UPSILON
+$pre u $post ↔ ʊ ; # LATIN SMALL LETTER UPSILON
+$pre A $post ↔ Ə ; # LATIN CAPITAL LETTER SCHWA
+$pre a $post ↔ ə ; # LATIN SMALL LETTER SCHWA
+$pre O $post ↔ Ɔ ; # LATIN CAPITAL LETTER OPEN O
+$pre o $post ↔ ɔ ; # LATIN SMALL LETTER OPEN O
+$pre E $post ↔ Ɛ ; # LATIN CAPITAL LETTER OPEN E
+$pre e $post ↔ ɛ ; # LATIN SMALL LETTER OPEN E
+# three that don't have uppercases
+$pre '?' $post ↔ ʔ ; # LATIN LETTER GLOTTAL STOP
+$pre i $post ↔ ɪ ; # LATIN LETTER SMALL CAPITAL I
+$pre v $post ↔ ʌ ; # LATIN SMALL LETTER TURNED V
+# Additional Characters that may be added in the future
+# $pre XXX $post ↔ ̆ ; # COMBINING BREVE
+# $pre XXX $post ↔ ̇ ; # COMBINING DOT ABOVE
+# $pre XXX $post ↔ ̉ ; # COMBINING HOOK ABOVE
+# $pre XXX $post ↔ ̋ ; # COMBINING DOUBLE ACUTE ACCENT
+# $pre XXX $post ↔ ̌ ; # COMBINING CARON
+# $pre XXX $post ↔ ̏ ; # COMBINING DOUBLE GRAVE ACCENT
+# $pre XXX $post ↔ ̑ ; # COMBINING INVERTED BREVE
+# $pre XXX $post ↔ ̓ ; # COMBINING COMMA ABOVE
+# $pre XXX $post ↔ ̔ ; # COMBINING REVERSED COMMA ABOVE
+# $pre XXX $post ↔ ̛ ; # COMBINING HORN
+# $pre XXX $post ↔ ̤ ; # COMBINING DIAERESIS BELOW
+# $pre XXX $post ↔ ̥ ; # COMBINING RING BELOW
+# $pre XXX $post ↔ ̦ ; # COMBINING COMMA BELOW
+# $pre XXX $post ↔ ̨ ; # COMBINING OGONEK
+# $pre XXX $post ↔ ̭ ; # COMBINING CIRCUMFLEX ACCENT BELOW
+# $pre XXX $post ↔ ̮ ; # COMBINING BREVE BELOW
+# $pre XXX $post ↔ ̰ ; # COMBINING TILDE BELOW
+# $pre XXX $post ↔ ̱ ; # COMBINING MACRON BELOW
+# $pre YYY $post ↔ ª ; # FEMININE ORDINAL INDICATOR
+# $pre YYY $post ↔ º ; # MASCULINE ORDINAL INDICATOR
+# $pre YYY $post ↔ Đ ; # LATIN CAPITAL LETTER D WITH STROKE
+# $pre YYY $post ↔ đ ; # LATIN SMALL LETTER D WITH STROKE
+# $pre YYY $post ↔ Ħ ; # LATIN CAPITAL LETTER H WITH STROKE
+# $pre YYY $post ↔ ħ ; # LATIN SMALL LETTER H WITH STROKE
+# $pre YYY $post ↔ ı ; # LATIN SMALL LETTER DOTLESS I
+# $pre YYY $post ↔ ĸ ; # LATIN SMALL LETTER KRA
+# $pre YYY $post ↔ Ŀ ; # LATIN CAPITAL LETTER L WITH MIDDLE DOT
+# $pre YYY $post ↔ ŀ ; # LATIN SMALL LETTER L WITH MIDDLE DOT
+# $pre YYY $post ↔ Ł ; # LATIN CAPITAL LETTER L WITH STROKE
+# $pre YYY $post ↔ ł ; # LATIN SMALL LETTER L WITH STROKE
+# $pre YYY $post ↔ ʼn ; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
+# $pre YYY $post ↔ Ŧ ; # LATIN CAPITAL LETTER T WITH STROKE
+# $pre YYY $post ↔ ŧ ; # LATIN SMALL LETTER T WITH STROKE
+# $pre YYY $post ↔ ſ ; # LATIN SMALL LETTER LONG S
+# $pre YYY $post ↔ ƀ ; # LATIN SMALL LETTER B WITH STROKE
+# $pre YYY $post ↔ Ɓ ; # LATIN CAPITAL LETTER B WITH HOOK
+# $pre YYY $post ↔ Ƃ ; # LATIN CAPITAL LETTER B WITH TOPBAR
+# $pre YYY $post ↔ ƃ ; # LATIN SMALL LETTER B WITH TOPBAR
+# $pre YYY $post ↔ Ƅ ; # LATIN CAPITAL LETTER TONE SIX
+# $pre YYY $post ↔ ƅ ; # LATIN SMALL LETTER TONE SIX
+# $pre YYY $post ↔ Ƈ ; # LATIN CAPITAL LETTER C WITH HOOK
+# $pre YYY $post ↔ ƈ ; # LATIN SMALL LETTER C WITH HOOK
+# $pre YYY $post ↔ Ɖ ; # LATIN CAPITAL LETTER AFRICAN D
+# $pre YYY $post ↔ Ɗ ; # LATIN CAPITAL LETTER D WITH HOOK
+# $pre YYY $post ↔ Ƌ ; # LATIN CAPITAL LETTER D WITH TOPBAR
+# $pre YYY $post ↔ ƌ ; # LATIN SMALL LETTER D WITH TOPBAR
+# $pre YYY $post ↔ ƍ ; # LATIN SMALL LETTER TURNED DELTA
+# $pre YYY $post ↔ Ǝ ; # LATIN CAPITAL LETTER REVERSED E
+# $pre YYY $post ↔ Ƒ ; # LATIN CAPITAL LETTER F WITH HOOK
+# $pre YYY $post ↔ ƒ ; # LATIN SMALL LETTER F WITH HOOK
+# $pre YYY $post ↔ Ɠ ; # LATIN CAPITAL LETTER G WITH HOOK
+# $pre YYY $post ↔ Ɣ ; # LATIN CAPITAL LETTER GAMMA
+# $pre YYY $post ↔ ƕ ; # LATIN SMALL LETTER HV
+# $pre YYY $post ↔ Ɩ ; # LATIN CAPITAL LETTER IOTA
+# $pre YYY $post ↔ Ɨ ; # LATIN CAPITAL LETTER I WITH STROKE
+# $pre YYY $post ↔ Ƙ ; # LATIN CAPITAL LETTER K WITH HOOK
+# $pre YYY $post ↔ ƙ ; # LATIN SMALL LETTER K WITH HOOK
+# $pre YYY $post ↔ ƚ ; # LATIN SMALL LETTER L WITH BAR
+# $pre YYY $post ↔ ƛ ; # LATIN SMALL LETTER LAMBDA WITH STROKE
+# $pre YYY $post ↔ Ɯ ; # LATIN CAPITAL LETTER TURNED M
+# $pre YYY $post ↔ Ɲ ; # LATIN CAPITAL LETTER N WITH LEFT HOOK
+# $pre YYY $post ↔ ƞ ; # LATIN SMALL LETTER N WITH LONG RIGHT LEG
+# $pre YYY $post ↔ Ɵ ; # LATIN CAPITAL LETTER O WITH MIDDLE TILDE
+# $pre YYY $post ↔ Ƣ ; # LATIN CAPITAL LETTER OI
+# $pre YYY $post ↔ ƣ ; # LATIN SMALL LETTER OI
+# $pre YYY $post ↔ Ƥ ; # LATIN CAPITAL LETTER P WITH HOOK
+# $pre YYY $post ↔ ƥ ; # LATIN SMALL LETTER P WITH HOOK
+# $pre YYY $post ↔ Ʀ ; # LATIN LETTER YR
+# $pre YYY $post ↔ Ƨ ; # LATIN CAPITAL LETTER TONE TWO
+# $pre YYY $post ↔ ƨ ; # LATIN SMALL LETTER TONE TWO
+# $pre YYY $post ↔ ƪ ; # LATIN LETTER REVERSED ESH LOOP
+# $pre YYY $post ↔ ƫ ; # LATIN SMALL LETTER T WITH PALATAL HOOK
+# $pre YYY $post ↔ Ƭ ; # LATIN CAPITAL LETTER T WITH HOOK
+# $pre YYY $post ↔ ƭ ; # LATIN SMALL LETTER T WITH HOOK
+# $pre YYY $post ↔ Ʈ ; # LATIN CAPITAL LETTER T WITH RETROFLEX HOOK
+# $pre YYY $post ↔ Ʋ ; # LATIN CAPITAL LETTER V WITH HOOK
+# $pre YYY $post ↔ Ƴ ; # LATIN CAPITAL LETTER Y WITH HOOK
+# $pre YYY $post ↔ ƴ ; # LATIN SMALL LETTER Y WITH HOOK
+# $pre YYY $post ↔ Ƶ ; # LATIN CAPITAL LETTER Z WITH STROKE
+# $pre YYY $post ↔ ƶ ; # LATIN SMALL LETTER Z WITH STROKE
+# $pre YYY $post ↔ Ƹ ; # LATIN CAPITAL LETTER EZH REVERSED
+# $pre YYY $post ↔ ƹ ; # LATIN SMALL LETTER EZH REVERSED
+# $pre YYY $post ↔ ƺ ; # LATIN SMALL LETTER EZH WITH TAIL
+# $pre YYY $post ↔ ƻ ; # LATIN LETTER TWO WITH STROKE
+# $pre YYY $post ↔ Ƽ ; # LATIN CAPITAL LETTER TONE FIVE
+# $pre YYY $post ↔ ƽ ; # LATIN SMALL LETTER TONE FIVE
+# $pre YYY $post ↔ ƾ ; # LATIN LETTER INVERTED GLOTTAL STOP WITH STROKE
+# $pre YYY $post ↔ ƿ ; # LATIN LETTER WYNN
+# $pre YYY $post ↔ ǀ ; # LATIN LETTER DENTAL CLICK
+# $pre YYY $post ↔ ǁ ; # LATIN LETTER LATERAL CLICK
+# $pre YYY $post ↔ ǂ ; # LATIN LETTER ALVEOLAR CLICK
+# $pre YYY $post ↔ ǃ ; # LATIN LETTER RETROFLEX CLICK
+# $pre YYY $post ↔ DŽ ; # LATIN CAPITAL LETTER DZ WITH CARON
+# $pre YYY $post ↔ Dž ; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
+# $pre YYY $post ↔ dž ; # LATIN SMALL LETTER DZ WITH CARON
+# $pre YYY $post ↔ LJ ; # LATIN CAPITAL LETTER LJ
+# $pre YYY $post ↔ Lj ; # LATIN CAPITAL LETTER L WITH SMALL LETTER J
+# $pre YYY $post ↔ lj ; # LATIN SMALL LETTER LJ
+# $pre YYY $post ↔ NJ ; # LATIN CAPITAL LETTER NJ
+# $pre YYY $post ↔ Nj ; # LATIN CAPITAL LETTER N WITH SMALL LETTER J
+# $pre YYY $post ↔ nj ; # LATIN SMALL LETTER NJ
+# $pre YYY $post ↔ ǝ ; # LATIN SMALL LETTER TURNED E
+# $pre YYY $post ↔ Ǥ ; # LATIN CAPITAL LETTER G WITH STROKE
+# $pre YYY $post ↔ ǥ ; # LATIN SMALL LETTER G WITH STROKE
+# $pre YYY $post ↔ DZ ; # LATIN CAPITAL LETTER DZ
+# $pre YYY $post ↔ Dz ; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z
+# $pre YYY $post ↔ dz ; # LATIN SMALL LETTER DZ
+# $pre YYY $post ↔ Ƕ ; # LATIN CAPITAL LETTER HWAIR
+# $pre YYY $post ↔ Ƿ ; # LATIN CAPITAL LETTER WYNN
+# $pre YYY $post ↔ Ȝ ; # LATIN CAPITAL LETTER YOGH
+# $pre YYY $post ↔ ȝ ; # LATIN SMALL LETTER YOGH
+# $pre YYY $post ↔ Ȣ ; # LATIN CAPITAL LETTER OU
+# $pre YYY $post ↔ ȣ ; # LATIN SMALL LETTER OU
+# $pre YYY $post ↔ Ȥ ; # LATIN CAPITAL LETTER Z WITH HOOK
+# $pre YYY $post ↔ ȥ ; # LATIN SMALL LETTER Z WITH HOOK
+# $pre YYY $post ↔ ɐ ; # LATIN SMALL LETTER TURNED A
+# $pre YYY $post ↔ ɑ ; # LATIN SMALL LETTER ALPHA
+# $pre YYY $post ↔ ɒ ; # LATIN SMALL LETTER TURNED ALPHA
+# $pre YYY $post ↔ ɓ ; # LATIN SMALL LETTER B WITH HOOK
+# $pre YYY $post ↔ ɕ ; # LATIN SMALL LETTER C WITH CURL
+# $pre YYY $post ↔ ɖ ; # LATIN SMALL LETTER D WITH TAIL
+# $pre YYY $post ↔ ɗ ; # LATIN SMALL LETTER D WITH HOOK
+# $pre YYY $post ↔ ɘ ; # LATIN SMALL LETTER REVERSED E
+# $pre YYY $post ↔ ɚ ; # LATIN SMALL LETTER SCHWA WITH HOOK
+# $pre YYY $post ↔ ɜ ; # LATIN SMALL LETTER REVERSED OPEN E
+# $pre YYY $post ↔ ɝ ; # LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
+# $pre YYY $post ↔ ɞ ; # LATIN SMALL LETTER CLOSED REVERSED OPEN E
+# $pre YYY $post ↔ ɟ ; # LATIN SMALL LETTER DOTLESS J WITH STROKE
+# $pre YYY $post ↔ ɠ ; # LATIN SMALL LETTER G WITH HOOK
+# $pre YYY $post ↔ ɡ ; # LATIN SMALL LETTER SCRIPT G
+# $pre YYY $post ↔ ɢ ; # LATIN LETTER SMALL CAPITAL G
+# $pre YYY $post ↔ ɣ ; # LATIN SMALL LETTER GAMMA
+# $pre YYY $post ↔ ɤ ; # LATIN SMALL LETTER RAMS HORN
+# $pre YYY $post ↔ ɥ ; # LATIN SMALL LETTER TURNED H
+# $pre YYY $post ↔ ɦ ; # LATIN SMALL LETTER H WITH HOOK
+# $pre YYY $post ↔ ɧ ; # LATIN SMALL LETTER HENG WITH HOOK
+# $pre YYY $post ↔ ɨ ; # LATIN SMALL LETTER I WITH STROKE
+# $pre YYY $post ↔ ɩ ; # LATIN SMALL LETTER IOTA
+# $pre YYY $post ↔ ɫ ; # LATIN SMALL LETTER L WITH MIDDLE TILDE
+# $pre YYY $post ↔ ɬ ; # LATIN SMALL LETTER L WITH BELT
+# $pre YYY $post ↔ ɭ ; # LATIN SMALL LETTER L WITH RETROFLEX HOOK
+# $pre YYY $post ↔ ɮ ; # LATIN SMALL LETTER LEZH
+# $pre YYY $post ↔ ɯ ; # LATIN SMALL LETTER TURNED M
+# $pre YYY $post ↔ ɰ ; # LATIN SMALL LETTER TURNED M WITH LONG LEG
+# $pre YYY $post ↔ ɱ ; # LATIN SMALL LETTER M WITH HOOK
+# $pre YYY $post ↔ ɲ ; # LATIN SMALL LETTER N WITH LEFT HOOK
+# $pre YYY $post ↔ ɳ ; # LATIN SMALL LETTER N WITH RETROFLEX HOOK
+# $pre YYY $post ↔ ɴ ; # LATIN LETTER SMALL CAPITAL N
+# $pre YYY $post ↔ ɵ ; # LATIN SMALL LETTER BARRED O
+# $pre YYY $post ↔ ɶ ; # LATIN LETTER SMALL CAPITAL OE
+# $pre YYY $post ↔ ɷ ; # LATIN SMALL LETTER CLOSED OMEGA
+# $pre YYY $post ↔ ɸ ; # LATIN SMALL LETTER PHI
+# $pre YYY $post ↔ ɹ ; # LATIN SMALL LETTER TURNED R
+# $pre YYY $post ↔ ɺ ; # LATIN SMALL LETTER TURNED R WITH LONG LEG
+# $pre YYY $post ↔ ɻ ; # LATIN SMALL LETTER TURNED R WITH HOOK
+# $pre YYY $post ↔ ɼ ; # LATIN SMALL LETTER R WITH LONG LEG
+# $pre YYY $post ↔ ɽ ; # LATIN SMALL LETTER R WITH TAIL
+# $pre YYY $post ↔ ɾ ; # LATIN SMALL LETTER R WITH FISHHOOK
+# $pre YYY $post ↔ ɿ ; # LATIN SMALL LETTER REVERSED R WITH FISHHOOK
+# $pre YYY $post ↔ ʀ ; # LATIN LETTER SMALL CAPITAL R
+# $pre YYY $post ↔ ʁ ; # LATIN LETTER SMALL CAPITAL INVERTED R
+# $pre YYY $post ↔ ʂ ; # LATIN SMALL LETTER S WITH HOOK
+# $pre YYY $post ↔ ʄ ; # LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK
+# $pre YYY $post ↔ ʅ ; # LATIN SMALL LETTER SQUAT REVERSED ESH
+# $pre YYY $post ↔ ʆ ; # LATIN SMALL LETTER ESH WITH CURL
+# $pre YYY $post ↔ ʇ ; # LATIN SMALL LETTER TURNED T
+# $pre YYY $post ↔ ʈ ; # LATIN SMALL LETTER T WITH RETROFLEX HOOK
+# $pre YYY $post ↔ ʉ ; # LATIN SMALL LETTER U BAR
+# $pre YYY $post ↔ ʋ ; # LATIN SMALL LETTER V WITH HOOK
+# $pre YYY $post ↔ ʍ ; # LATIN SMALL LETTER TURNED W
+# $pre YYY $post ↔ ʎ ; # LATIN SMALL LETTER TURNED Y
+# $pre YYY $post ↔ ʏ ; # LATIN LETTER SMALL CAPITAL Y
+# $pre YYY $post ↔ ʐ ; # LATIN SMALL LETTER Z WITH RETROFLEX HOOK
+# $pre YYY $post ↔ ʑ ; # LATIN SMALL LETTER Z WITH CURL
+# $pre YYY $post ↔ ʓ ; # LATIN SMALL LETTER EZH WITH CURL
+# $pre YYY $post ↔ ʔ ; # LATIN LETTER GLOTTAL STOP
+# $pre YYY $post ↔ ʕ ; # LATIN LETTER PHARYNGEAL VOICED FRICATIVE
+# $pre YYY $post ↔ ʖ ; # LATIN LETTER INVERTED GLOTTAL STOP
+# $pre YYY $post ↔ ʗ ; # LATIN LETTER STRETCHED C
+# $pre YYY $post ↔ ʘ ; # LATIN LETTER BILABIAL CLICK
+# $pre YYY $post ↔ ʙ ; # LATIN LETTER SMALL CAPITAL B
+# $pre YYY $post ↔ ʚ ; # LATIN SMALL LETTER CLOSED OPEN E
+# $pre YYY $post ↔ ʛ ; # LATIN LETTER SMALL CAPITAL G WITH HOOK
+# $pre YYY $post ↔ ʜ ; # LATIN LETTER SMALL CAPITAL H
+# $pre YYY $post ↔ ʝ ; # LATIN SMALL LETTER J WITH CROSSED-TAIL
+# $pre YYY $post ↔ ʞ ; # LATIN SMALL LETTER TURNED K
+# $pre YYY $post ↔ ʟ ; # LATIN LETTER SMALL CAPITAL L
+# $pre YYY $post ↔ ʠ ; # LATIN SMALL LETTER Q WITH HOOK
+# $pre YYY $post ↔ ʡ ; # LATIN LETTER GLOTTAL STOP WITH STROKE
+# $pre YYY $post ↔ ʢ ; # LATIN LETTER REVERSED GLOTTAL STOP WITH STROKE
+# $pre YYY $post ↔ ʣ ; # LATIN SMALL LETTER DZ DIGRAPH
+# $pre YYY $post ↔ ʤ ; # LATIN SMALL LETTER DEZH DIGRAPH
+# $pre YYY $post ↔ ʥ ; # LATIN SMALL LETTER DZ DIGRAPH WITH CURL
+# $pre YYY $post ↔ ʦ ; # LATIN SMALL LETTER TS DIGRAPH
+# $pre YYY $post ↔ ʧ ; # LATIN SMALL LETTER TESH DIGRAPH
+# $pre YYY $post ↔ ʨ ; # LATIN SMALL LETTER TC DIGRAPH WITH CURL
+# $pre YYY $post ↔ ʩ ; # LATIN SMALL LETTER FENG DIGRAPH
+# $pre YYY $post ↔ ʪ ; # LATIN SMALL LETTER LS DIGRAPH
+# $pre YYY $post ↔ ʫ ; # LATIN SMALL LETTER LZ DIGRAPH
+# $pre YYY $post ↔ ʬ ; # LATIN LETTER BILABIAL PERCUSSIVE
+# $pre YYY $post ↔ ʭ ; # LATIN LETTER BIDENTAL PERCUSSIVE
+# $pre YYY $post ↔ ʰ ; # MODIFIER LETTER SMALL H
+# $pre YYY $post ↔ ʱ ; # MODIFIER LETTER SMALL H WITH HOOK
+# $pre YYY $post ↔ ʲ ; # MODIFIER LETTER SMALL J
+# $pre YYY $post ↔ ʳ ; # MODIFIER LETTER SMALL R
+# $pre YYY $post ↔ ʴ ; # MODIFIER LETTER SMALL TURNED R
+# $pre YYY $post ↔ ʵ ; # MODIFIER LETTER SMALL TURNED R WITH HOOK
+# $pre YYY $post ↔ ʶ ; # MODIFIER LETTER SMALL CAPITAL INVERTED R
+# $pre YYY $post ↔ ʷ ; # MODIFIER LETTER SMALL W
+# $pre YYY $post ↔ ʸ ; # MODIFIER LETTER SMALL Y
+# $pre YYY $post ↔ ˠ ; # MODIFIER LETTER SMALL GAMMA
+# $pre YYY $post ↔ ˡ ; # MODIFIER LETTER SMALL L
+# $pre YYY $post ↔ ˢ ; # MODIFIER LETTER SMALL S
+# $pre YYY $post ↔ ˣ ; # MODIFIER LETTER SMALL X
+# $pre YYY $post ↔ ˤ ; # MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
+# $pre YYY $post ↔ ẚ ; # LATIN SMALL LETTER A WITH RIGHT HALF RING
+# $pre YYY $post ↔ ⁿ ; # SUPERSCRIPT LATIN SMALL LETTER N
+:: NFC (NFD) ;
+

package/transforms/Any-Publishing.json

@@ -0,0 +1,9 @@
+{
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-t-s0-publish",
+  "_aliasBcp47": "und-t-d0-publish",
+  "_source": "Any",
+  "_direction": "both",
+  "_target": "Publishing",
+  "_rulesFile": "Any-Publishing.txt"
+}

package/transforms/Any-Publishing.txt

@@ -0,0 +1,63 @@
+
+# Variables
+$single = \' ;
+$space = ' ' ;
+$double = \";
+$back = \` ;
+$tab = \u0008 ;
+$makeRight = [[:Z:][:Ps:][:Pi:]$] ;
+# fix UNIX quotes
+$back $back → “ ;
+$back → ‘ ;
+# fix typewriter quotes, by context
+$makeRight {$double} ↔ “ ;
+$double ↔ ” ;
+$makeRight {$single} ↔ ‘ ;
+$single ↔ ’;
+$space {$space} → ;
+'<--->' ↔ '⟷';
+'<---' ↔ '⟵';
+'--->' ↔ '⟶';
+'<-->' ↔ '↔';
+'<--' ↔ '←';
+'-->' ↔ '→';
+'<-/->' ↔ '↮';
+'<-/-' ↔ '↚';
+'-/->' ↔ '↛';
+'<===>' ↔ '⟺';
+'<===' ↔ '⟸';
+'===>' ↔ '⟹';
+'<==>' ↔ '⇔';
+'<==' ↔ '⇐';
+'==>' ↔ '⇒';
+'!=' ↔ ≠;
+'<=' ↔ ≤;
+'>=' ↔ ≥;
+'+-' ↔ ±;
+'-+' ↔ ∓;
+'~=' ↔ ≅;
+'--' ↔ —;
+'...' ↔ …;
+\(C\) ↔ ©;
+\(c\) → ©;
+\(R\) ↔ ®;
+\(r\) → ®;
+\(TM\) ↔ ™;
+\(tm\) → ™;
+{c\/o} ↔ ℅;
+[^0-9] {1\/2} [^0-9] ↔ ½;
+[^0-9] {1\/3} [^0-9] ↔ ⅓;
+[^0-9] {2\/3} [^0-9] ↔ ⅔;
+[^0-9] {1\/4} [^0-9] ↔ ¼;
+[^0-9] {3\/4} [^0-9] ↔ ¾;
+[^0-9] {1\/5} [^0-9] ↔ ⅕;
+[^0-9] {2\/5} [^0-9] ↔ ⅖;
+[^0-9] {3\/5} [^0-9] ↔ ⅗;
+[^0-9] {4\/5} [^0-9] ↔ ⅘;
+[^0-9] {1\/6} [^0-9] ↔ ⅙;
+[^0-9] {5\/6} [^0-9] ↔ ⅚;
+[^0-9] {1\/8} [^0-9] ↔ ⅛;
+[^0-9] {3\/8} [^0-9] ↔ ⅜;
+[^0-9] {5\/8} [^0-9] ↔ ⅝;
+[^0-9] {7\/8} [^0-9] ↔ ⅞;
+

package/transforms/Arabic-Latin-BGN.json

@@ -0,0 +1,9 @@
+{
+  "_visibility": "external",
+  "_alias": "Arabic-Latin/BGN",
+  "_aliasBcp47": "ar-Latn-t-ar-m0-bgn",
+  "_source": "ar",
+  "_direction": "forward",
+  "_target": "ar_Latn",
+  "_rulesFile": "Arabic-Latin-BGN.txt"
+}

package/transforms/Arabic-Latin-BGN.txt

@@ -0,0 +1,205 @@
+
+#
+########################################################################
+# BGN/PCGN 1956 System
+#
+# This system was adopted by the BGN in 1946 and by the PCGN
+# in 1956 and has been applied in the systematic romanization
+# of geographic names in Bahrain, Egypt, Iraq, Jordan,
+# Kuwait, Lebanon, Libya, Oman, Qatar, Saudi Arabia, Sudan,
+# Syria, Tunisia, the United Arab Emirates, and Yemen, all
+# of which has been covered by published BGN engineers.
+#
+# Originally prepared by Michael Everson <everson@evertype.com>
+########################################################################
+#
+# MINIMAL FILTER: Arabic-Latin
+#
+:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىيًٌٍَُِّْ٠١٢٣٤٥٦٧٨٩ٱ]] ;
+:: NFKD (NFC) ;
+#
+#
+########################################################################
+#
+########################################################################
+#
+# Define All Transformation Variables
+#
+########################################################################
+#
+$alef = ’;
+$ayin = ‘;
+$disambig =  ̱ ;
+#
+#
+# Use this $wordBoundary until bug 2034 is fixed in ICU:
+# http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest
+#
+$wordBoundary =  [^[:L:][:M:][:N:]] ;
+#
+#
+########################################################################
+# non-letters
+[:Nd:]{٫}[:Nd:] ↔ [:Nd:]{','}[:Nd:] ; # ARABIC DECIMAL SEPARATOR
+[:Nd:]{٬}[:Nd:] ↔ [:Nd:]{'.'}[:Nd:] ; # ARABIC THOUSANDS SEPARATOR
+٫ ↔ ',' $disambig ; # ARABIC DECIMAL SEPARATOR
+٬ ↔ '.' $disambig ; # ARABIC THOUSANDS SEPARATOR
+#  ٭ ↔ ; # ARABIC FIVE POINTED STAR // no need to transliterate
+، ↔ ',' ; # ARABIC COMMA
+؛ ↔ ';' ; # ARABIC SEMICOLON
+؟ ↔ '?' ; # ARABIC QUESTION MARK
+٪ ↔ '%' ; # ARABIC PERCENT SIGN
+۰ ↔ 0 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ZERO
+۱ ↔ 1 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ONE
+۲ ↔ 2 $disambig ; # EXTENDED ARABIC-INDIC DIGIT TWO
+۳ ↔ 3 $disambig ; # EXTENDED ARABIC-INDIC DIGIT THREE
+۴ ↔ 4 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FOUR
+۵ ↔ 5 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FIVE
+۶ ↔ 6 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SIX
+۷ ↔ 7 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SEVEN
+۸ ↔ 8 $disambig ; # EXTENDED ARABIC-INDIC DIGIT EIGHT
+۹ ↔ 9 $disambig ; # EXTENDED ARABIC-INDIC DIGIT NINE
+٠ ↔ 0 ; # ARABIC-INDIC DIGIT ZERO
+١ ↔ 1 ; # ARABIC-INDIC DIGIT ONE
+٢ ↔ 2 ; # ARABIC-INDIC DIGIT TWO
+٣ ↔ 3 ; # ARABIC-INDIC DIGIT THREE
+٤ ↔ 4 ; # ARABIC-INDIC DIGIT FOUR
+٥ ↔ 5 ; # ARABIC-INDIC DIGIT FIVE
+٦ ↔ 6 ; # ARABIC-INDIC DIGIT SIX
+٧ ↔ 7 ; # ARABIC-INDIC DIGIT SEVEN
+٨ ↔ 8 ; # ARABIC-INDIC DIGIT EIGHT
+٩ ↔ 9 ; # ARABIC-INDIC DIGIT NINE
+#
+########################################################################
+#
+# Rules moved to front to avoid masking
+#
+########################################################################
+#
+########################################################################
+#
+# BGN Page 8 Rule 5
+#
+# The character sequences ت , كه , ته , and سه may be romanized t·h, k·h,
+# d·h, and s·h in order to differentiate those romanizations from the
+# digraphs th, kh, dh, and sh.
+#
+########################################################################
+#
+ته → t·h ; # ARABIC LETTER TEH + HEH
+كه → k·h ; # ARABIC LETTER KAF + HEH
+ده → d·h ; # ARABIC LETTER DAL + HEH
+سه → s·h ; # ARABIC LETTER SEEN + HEH
+#
+#
+########################################################################
+#
+# End Rule 5
+#
+########################################################################
+########################################################################
+#
+#
+# BGN Page 8 Rule 9
+#
+# Doubles consonant sounds are represented in Arabic script by placing
+# a shaddah ( ّ ) over a consonant character. In romanization the letter
+# should be doubled. [The remainder of this rule deals with the definite
+# article and is lexical.]
+#
+########################################################################
+#
+بّ → bb ; # ARABIC LETTER BEH + SHADDA
+تّ → tt ; # ARABIC LETTER TEH + SHADDA
+ثّ → thth ; # ARABIC LETTER THEH + SHADDA
+جّ → jj ; # ARABIC LETTER JEEM + SHADDA
+حّ → ḥḥ ; # ARABIC LETTER HAH + SHADDA
+خّ → khkh ; # ARABIC LETTER KHAH + SHADDA
+دّ → dd ; # ARABIC LETTER DAL + SHADDA
+ذّ → dhdh ; # ARABIC LETTER THAL + SHADDA
+رّ → rr ; # ARABIC LETTER REH + SHADDA
+زّ → zz ; # ARABIC LETTER ZAIN + SHADDA
+سّ → ss ; # ARABIC LETTER SEEN + SHADDA
+شّ → shsh ; # ARABIC LETTER SHEEN + SHADDA
+صّ → ṣṣ ; # ARABIC LETTER SAD + SHADDA
+ضّ → ḍḍ ; # ARABIC LETTER DAD + SHADDA
+طّ → ṭṭ ; # ARABIC LETTER TAH + SHADDA
+ظّ → ẓẓ ; # ARABIC LETTER ZAH + SHADDA
+عّ → $ayin $ayin ; # ARABIC LETTER AIN + SHADDA
+غّ → ghgh ; # ARABIC LETTER GHAIN + SHADDA
+فّ → ff ; # ARABIC LETTER FEH + SHADDA
+قّ → qq ; # ARABIC LETTER QAF + SHADDA
+كّ → kk ; # ARABIC LETTER KAF + SHADDA
+لّ → ll ; # ARABIC LETTER LAM + SHADDA
+مّ → mm ; # ARABIC LETTER MEEM + SHADDA
+نّ → nn ; # ARABIC LETTER NOON + SHADDA
+هّ → hh ; # ARABIC LETTER HEH + SHADDA
+وّ → ww ; # ARABIC LETTER WAW + SHADDA
+ىّ → yy ; # ARABIC LETTER YEH + SHADDA
+#
+#
+########################################################################
+#
+# End Rule 9
+#
+########################################################################
+#
+########################################################################
+#
+# Start of Transformations
+#
+########################################################################
+#
+$wordBoundary{ء →  ; # ARABIC LETTER HAMZA
+ء → $alef ; # ARABIC LETTER HAMZA
+$wordBoundary{ا →  ; # ARABIC LETTER ALEF
+ٱ → $alef ; # ARABIC LETTER ALEF WASLA
+$wordBoundary{آ → ā ; # ARABIC LETTER ALEF WITH MADDA ABOVE
+آ → $alef ā ; # ARABIC LETTER ALEF WITH MADDA ABOVE
+ب → b ; # ARABIC LETTER BEH
+ت → t ; # ARABIC LETTER TEH
+ة → h ; # ARABIC LETTER TEH MARBUTA
+ث → th ; # ARABIC LETTER THEH
+ج → j ; # ARABIC LETTER JEEM
+ح → ḩ ; # ARABIC LETTER HAH
+خ → kh ; # ARABIC LETTER KHAH
+د → d ; # ARABIC LETTER DAL
+ذ → dh ; # ARABIC LETTER THAL
+ر → r ; # ARABIC LETTER REH
+ز → z ; # ARABIC LETTER ZAIN
+س → s ; # ARABIC LETTER SEEN
+ش → sh ; # ARABIC LETTER SHEEN
+ص → ş ; # ARABIC LETTER SAD
+ض → ḑ ; # ARABIC LETTER DAD
+ط → ţ ; # ARABIC LETTER TAH
+ظ → z̧ ; # ARABIC LETTER ZAH
+ع → $ayin ; # ARABIC LETTER AIN
+غ → gh ; # ARABIC LETTER GHAIN
+ف → f ; # ARABIC LETTER FEH
+ق → q ; # ARABIC LETTER QAF
+ک ↔ k $disambig ; # ARABIC LETTER KEHEH
+ك ↔ k ; # ARABIC LETTER KAF
+ل → l ; # ARABIC LETTER LAM
+م → m ; # ARABIC LETTER MEEM
+ن → n ; # ARABIC LETTER NOON
+ه → h ; # ARABIC LETTER HEH
+و → w ; # ARABIC LETTER WAW
+ى → y ; # ARABIC LETTER YEH
+َا → ā ; # ARABIC FATHA + ALEF
+َى → á ; # ARABIC FATHA + ALEF MAKSURA
+َيْ → ay ; # ARABIC FATHA + YEH + SUKUN
+َوْ → aw ; # ARABIC FATHA + WAW + SUKUN
+َ → a ; # ARABIC FATHA
+ِي → ī ; # ARABIC KASRA + YEH
+ِ → i ; # ARABIC KASRA
+ُو → ū ; # ARABIC DAMMA + WAW
+ُ → u ; # ARABIC DAMMA
+ْ →  ; # ARABIC SUKUN
+ً → aⁿ ; # ARABIC FATHATAN
+ٍ → iⁿ ; # ARABIC KASRATAN
+ٌ → uⁿ ; # ARABIC DAMMATAN
+::NFC (NFD) ;
+#
+#
+########################################################################
+

package/transforms/Arabic-Latin.json

@@ -0,0 +1,11 @@
+{
+  "_backwardAlias": "Latin-Arabic",
+  "_visibility": "external",
+  "_backwardAliasBcp47": "und-Arab-t-und-latn",
+  "_alias": "Arabic-Latin",
+  "_aliasBcp47": "und-Latn-t-und-arab",
+  "_source": "Arab",
+  "_direction": "both",
+  "_target": "Latn",
+  "_rulesFile": "Arabic-Latin.txt"
+}