1 # © 2016 and later: Unicode, Inc. and others.
2 # License & terms of use: http://www.unicode.org/copyright.html#License
4 # File: Latin_InterIndic.txt
16 # w←vowel→ represents the stand-alone form
25 $wce=\uE00D; # LETTER CANDRA E
26 $wse=\uE00E; # LETTER SHORT E
27 $we=\uE00F; # ए LETTER E
29 $wco=\uE011; # LETTER CANDRA O
30 $wso=\uE012; # LETTER SHORT O
31 $wo=\uE013; # ओ LETTER O
53 $ena=\uE029; #compatibility
64 $ela=\uE034; #compatibility
74 $avagraha=\uE03D; # SIGN AVAGRAHA
75 # ←vowel→ represents the dependent form
83 $ce=\uE045; #VOWEL SIGN CANDRA E
84 $se=\uE046; #VOWEL SIGN SHORT E
87 $co=\uE049; # VOWEL SIGN CANDRA O
88 $so=\uE04A; # VOWEL SIGN SHORT O
95 # \u0951→; # UNMAPPED STRESS SIGN UDATTA
96 # \u0952→; # UNMAPPED STRESS SIGN ANUDATTA
97 # \u0953→; # UNMAPPED GRAVE ACCENT
98 # \u0954→; # UNMAPPED ACUTE ACCENT
99 $lm = \uE055;# Telugu Length Mark
100 $ailm=\uE056;# AI Length Mark
101 $aulm=\uE057;# AU Length Mark
102 #urdu compatibity forms
117 $zero=\uE066; # DIGIT ZERO
118 $one=\uE067; # DIGIT ONE
119 $two=\uE068; # DIGIT TWO
120 $three=\uE069; # DIGIT THREE
121 $four=\uE06A; # DIGIT FOUR
122 $five=\uE06B; # DIGIT FIVE
123 $six=\uE06C; # DIGIT SIX
124 $seven=\uE06D; # DIGIT SEVEN
125 $eight=\uE06E; # DIGIT EIGHT
126 $nine=\uE06F; # DIGIT NINE
128 # For all other scripts
147 # ॰→; # nothing in Latin maps to InterIndic ABBREVIATION SIGN
148 $depVowelAbove=[\uE03E-\uE040\uE045-\uE04C];
149 $depVowelBelow=[\uE041-\uE044];
150 $endThing=[$danda$doubleDanda];
151 # $x was originally called '§'; $z was '%'
152 $x=[$virama$aa$ai$au$ii$i$uu$u$rrh$rh$lh$e$o$se$ce$so$co];
153 $z=[bcdfghjklmnpqrstvwxyz];
154 $consonants=[[$ka-$ha]$z[क-ह][ক-হ][ਕ-ਹ][ક-હ][କ-ହ][க-ஹ][క-హ][ಕ-ಹ][ക-ഹ]];
156 \u0303→$chandrabindu$anusvara;
157 m\u0310→$chandrabindu;
160 # convert to independent forms at start of word or syllable:
161 # dependent forms for roundtrip
170 \u0314r\u0325\u0304→$rrh;
172 \u0314l\u0325\u0304→$llh;
182 # preceeded by consonants
183 $consonants{ a\u0304→$aa;
187 $consonants{ i\u0304→$ii;
189 $consonants{ u\u0304→$uu;
191 $consonants{ r\u0325\u0304→$rrh;
192 $consonants{ r\u0325a→$rh;
193 $consonants{ r\u0325→$rh;
194 $consonants{ l\u0325\u0304→$llh;
196 $consonants{ l\u0325→$lh;
197 $consonants{ e\u0304→$e;
198 $consonants{ o\u0304→$o;
199 $consonants{ e\u0306→$ce;
200 $consonants{ o\u0306→$co;
203 # e.g. keai -→ {ka}{e}{wai}; k'ai -→ {ka}{wai}; (ai) -→ ({wai})
225 n}r\u0325 → $na|$virama;
226 n}l\u0325 → $na|$virama;
228 n\u0307}[kg] → $anusvara;
229 n\u0307}n\u0307 → $anusvara;
230 n\u0304}[cj] → $anusvara;
231 n\u0304}n\u0303 → $anusvara;
232 n\u0323}[tdn]\u0323 → $anusvara;
235 n}[ylvshr] → $anusvara;
239 k\u0331h\u0331→$ukha |$virama;
240 g\u0307→ $ugha | $virama;
245 y\u0307→$uya|$virama;
246 l\u0331→$ela|$virama;
247 n\u0331→$ena|$virama;
248 n\u0307→$nga|$virama;
249 n\u0303→$nya|$virama;
250 n\u0323→$nna|$virama;
251 t\u0323h→$ttha|$virama;
252 t\u0323→$tta|$virama;
253 r\u0323h→$udha|$virama;
254 r\u0323→$uddha|$virama;
255 d\u0323h→$ddha|$virama;
256 d\u0323→$dda|$virama;
279 r\u0331→$rra|$virama;
281 l\u0323→$lla|$virama;
284 w\u0307→$vva|$virama;
288 s\u0323→$ssa|$virama;
289 s\u0301→$sha|$virama;
293 $danda'.'→$doubleDanda;
294 $depVowelAbove{'~'→$anusvara;
295 $depVowelBelow{'~'→$chandrabindu;
296 # convert to dependent forms after consonant with no vowel:
297 # e.g. kai -→ {ka}{virama}ai -→ {ka}{ai}
309 $virama r\u0325\u0304→$rrh;
311 $virama r\u0325a→$rh;
313 $virama l\u0325\u0304→$llh;
323 # otherwise convert independent forms when separated by ': k'ai -→ {ka}{virama}{wai}
325 $virama''a\u0304→$waa;
329 $virama''i\u0304→$wii;
332 $virama''u\u0304→$wuu;
335 $virama''r\u0325\u0304→$wrr;
337 $virama''r\u0325→$wr;
338 $virama''l\u0325\u0304→$wll;
340 $virama''l\u0325→$wl;
341 $virama''e\u0304→$we;
342 $virama''o\u0304→$wo;
344 $virama''e\u0306→$wce;
345 $virama''o\u0306→$wco;
356 ''r\u0325\u0304→$wrr;
358 ''l\u0325\u0304→$wll;
367 $virama } [$z] → $virama;
368 $virama } ' ' → $virama ;
370 ʔ→$dgs; # Glottal Stop