mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-08 06:53:45 +00:00
ICU-4220 Remove whitespace that is difficult to remove programatically.
X-SVN-Rev: 17287
This commit is contained in:
parent
b53e510acd
commit
ebcb00caff
1 changed files with 185 additions and 185 deletions
|
@ -1,5 +1,5 @@
|
|||
#--------------------------------------------------------------------
|
||||
# Copyright (c) 1999-2004, International Business Machines
|
||||
# Copyright (c) 1999-2005, International Business Machines
|
||||
# Corporation and others. All Rights Reserved.
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
|
@ -58,7 +58,7 @@
|
|||
$vva=\ue081;
|
||||
$rra=\ue031;
|
||||
$la=\ue032;
|
||||
$lla=\ue033;
|
||||
$lla=\ue033;
|
||||
$ela=\ue034; #compatibility
|
||||
$va=\ue035;
|
||||
$sha=\ue036;
|
||||
|
@ -77,14 +77,14 @@
|
|||
$uu=\ue042;
|
||||
$rh=\ue043;
|
||||
$lh=\ue044;
|
||||
$ce=\ue045; #VOWEL SIGN CANDRA E
|
||||
$ce=\ue045; #VOWEL SIGN CANDRA E
|
||||
$se=\ue046; #VOWEL SIGN SHORT E
|
||||
$e=\ue047;
|
||||
$ai=\ue048;
|
||||
$co=\ue049; # VOWEL SIGN CANDRA O
|
||||
$so=\ue04a; # VOWEL SIGN SHORT O
|
||||
$o=\ue04b; # \u094b
|
||||
$au=\ue04c;
|
||||
$au=\ue04c;
|
||||
$virama=\ue04d;
|
||||
# \u094e Reserved
|
||||
# \u094f Reserved
|
||||
|
@ -93,9 +93,9 @@
|
|||
\ue052>; # UNMAPPED STRESS SIGN ANUDATTA
|
||||
\ue053>; # UNMAPPED GRAVE ACCENT
|
||||
\ue054>; # UNMAPPED ACUTE ACCENT
|
||||
$lm = \ue055;# Telugu Length Mark
|
||||
$ailm=\ue056;# AI Length Mark
|
||||
$aulm=\ue057;# AU Length Mark
|
||||
$lm = \ue055;# Telugu Length Mark
|
||||
$ailm=\ue056;# AI Length Mark
|
||||
$aulm=\ue057;# AU Length Mark
|
||||
#urdu compatibity forms
|
||||
$uka=\ue058;
|
||||
$ukha=\ue059;
|
||||
|
@ -121,7 +121,7 @@
|
|||
$seven=\ue06d; # DIGIT SEVEN
|
||||
$eight=\ue06e; # DIGIT EIGHT
|
||||
$nine=\ue06f; # DIGIT NINE
|
||||
|
||||
|
||||
# Glottal stop
|
||||
$dgs=\ue082;
|
||||
#Khanda-ta
|
||||
|
@ -141,73 +141,73 @@
|
|||
$anusvara} [$ka$kha$ga$gha$nga] > n\u0307;
|
||||
$anusvara} [$ca$cha$ja$jha$nya] > n\u0304;
|
||||
$anusvara} [$tta$ttha$dda$ddha$nna] > n\u0323;
|
||||
$anusvara} [$ta$tha$da$dha$na] > n ;
|
||||
$anusvara} [$pa$pha$ba$bha$ma] > m ;
|
||||
$anusvara} [$ya$ra$lla$la$va$ssa$sha$sa$ha] > n ;
|
||||
$anusvara} [$ta$tha$da$dha$na] > n;
|
||||
$anusvara} [$pa$pha$ba$bha$ma] > m;
|
||||
$anusvara} [$ya$ra$lla$la$va$ssa$sha$sa$ha] > n;
|
||||
$anusvara> m\u0307;
|
||||
|
||||
# Urdu compatibility
|
||||
$ya$nukta}$x > y\u0307 ;
|
||||
$ya$nukta$virama > y\u0307 ;
|
||||
$ya$nukta > y\u0307a ;
|
||||
$ya$nukta}$x > y\u0307;
|
||||
$ya$nukta$virama > y\u0307;
|
||||
$ya$nukta > y\u0307a;
|
||||
|
||||
$la$nukta }$x > l\u0331 ;
|
||||
$la$nukta$virama > l\u0331 ;
|
||||
$la$nukta > l\u0331a ;
|
||||
$la$nukta }$x > l\u0331;
|
||||
$la$nukta$virama > l\u0331;
|
||||
$la$nukta > l\u0331a;
|
||||
|
||||
$na$nukta }$x > n\u0331 ;
|
||||
$na$nukta$virama > n\u0331 ;
|
||||
$na$nukta > n\u0331a ;
|
||||
$na$nukta }$x > n\u0331;
|
||||
$na$nukta$virama > n\u0331;
|
||||
$na$nukta > n\u0331a;
|
||||
|
||||
$ena }$x > n\u0331 ;
|
||||
$ena$virama > n\u0331 ;
|
||||
$ena > n\u0331a ;
|
||||
$uka > qa ;
|
||||
$ka$nukta }$x > q ;
|
||||
$ka$nukta$virama > q ;
|
||||
$ka$nukta > qa ;
|
||||
$kha$nukta }$x > k\u0331h\u0331 ;
|
||||
$kha$nukta$virama > k\u0331h\u0331 ;
|
||||
$kha$nukta > k\u0331h\u0331a ;
|
||||
$ena }$x > n\u0331;
|
||||
$ena$virama > n\u0331;
|
||||
$ena > n\u0331a;
|
||||
$uka > qa;
|
||||
$ka$nukta }$x > q;
|
||||
$ka$nukta$virama > q;
|
||||
$ka$nukta > qa;
|
||||
$kha$nukta }$x > k\u0331h\u0331;
|
||||
$kha$nukta$virama > k\u0331h\u0331;
|
||||
$kha$nukta > k\u0331h\u0331a;
|
||||
$ukha$virama > k\u0331h\u0331;
|
||||
$ukha > k\u0331h\u0331a;
|
||||
$ugha > g\u0307a ;
|
||||
$ga$nukta }$x > g\u0307 ;
|
||||
$ga$nukta$virama > g\u0307 ;
|
||||
$ga$nukta > g\u0307a ;
|
||||
|
||||
$ujha > za ;
|
||||
$ja$nukta }$x > z ;
|
||||
$ja$nukta$virama > z ;
|
||||
$ja$nukta > za ;
|
||||
$ddha$nukta}$x > r\u0323h ;
|
||||
$ddha$nukta$virama > r\u0323h ;
|
||||
$ugha > g\u0307a;
|
||||
$ga$nukta }$x > g\u0307;
|
||||
$ga$nukta$virama > g\u0307;
|
||||
$ga$nukta > g\u0307a;
|
||||
|
||||
$ujha > za;
|
||||
$ja$nukta }$x > z;
|
||||
$ja$nukta$virama > z;
|
||||
$ja$nukta > za;
|
||||
$ddha$nukta}$x > r\u0323h;
|
||||
$ddha$nukta$virama > r\u0323h;
|
||||
$ddha$nukta > r\u0323ha;
|
||||
|
||||
$uddha}$x > r\u0323 ;
|
||||
$uddha$virama > r\u0323 ;
|
||||
$uddha}$x > r\u0323;
|
||||
$uddha$virama > r\u0323;
|
||||
$uddha > r\u0323a;
|
||||
|
||||
$udha > r\u0323a ;
|
||||
$dda$nukta}$x > r\u0323 ;
|
||||
$dda$nukta$virama > r\u0323 ;
|
||||
$dda$nukta > r\u0323a ;
|
||||
$pha$nukta }$x > f ;
|
||||
$pha$nukta$virama > f ;
|
||||
$pha$nukta > fa ;
|
||||
$ufa }$x > f ;
|
||||
$ufa$virama > f ;
|
||||
$ufa > fa ;
|
||||
|
||||
$udha > r\u0323a;
|
||||
$dda$nukta}$x > r\u0323;
|
||||
$dda$nukta$virama > r\u0323;
|
||||
$dda$nukta > r\u0323a;
|
||||
$pha$nukta }$x > f;
|
||||
$pha$nukta$virama > f;
|
||||
$pha$nukta > fa;
|
||||
$ufa }$x > f;
|
||||
$ufa$virama > f;
|
||||
$ufa > fa;
|
||||
|
||||
$ra$nukta}$x > r\u0331;
|
||||
$ra$nukta$virama > r\u0331;
|
||||
$ra$nukta > r\u0331a;
|
||||
$lla$nukta}$x > l\u0331;
|
||||
$lla$nukta$virama > l\u0331;
|
||||
$lla$nukta$virama > l\u0331;
|
||||
$lla$nukta > l\u0331a;
|
||||
|
||||
$ela}$x > l\u0331;
|
||||
$ela$virama > l\u0331;
|
||||
$ela$virama > l\u0331;
|
||||
$ela > l\u0331a;
|
||||
|
||||
$uya}$x > y\u0307;
|
||||
|
@ -234,7 +234,7 @@
|
|||
|
||||
$nga}$x>n\u0307;
|
||||
$nga$virama>n\u0307;
|
||||
$nga>n\u0307a ;
|
||||
$nga>n\u0307a;
|
||||
$ca$virama}$ha>c'';
|
||||
$ca}$x>c;
|
||||
$ca$virama>c;
|
||||
|
@ -252,9 +252,9 @@
|
|||
$jha$virama>jh;
|
||||
$jha>jha;
|
||||
|
||||
$nya }$x>n\u0303 ;
|
||||
$nya }$x>n\u0303;
|
||||
$nya$virama>n\u0303;
|
||||
$nya > n\u0303a ;
|
||||
$nya > n\u0303a;
|
||||
|
||||
|
||||
$tta$virama}$ha>t\u0323'';
|
||||
|
@ -274,9 +274,9 @@
|
|||
$ddha$virama>d\u0323h;
|
||||
$ddha>d\u0323ha;
|
||||
|
||||
$nna}$x>n\u0323 ;
|
||||
$nna}$x>n\u0323;
|
||||
$nna$virama>n\u0323;
|
||||
$nna>n\u0323a ;
|
||||
$nna>n\u0323a;
|
||||
|
||||
|
||||
$ta$virama}$ha>t'';
|
||||
|
@ -338,7 +338,7 @@
|
|||
$vva$virama}$ha>w\u0307'';
|
||||
$vva}$x>w\u0307;
|
||||
$vva$virama>w\u0307;
|
||||
$vva>w\u0307a;
|
||||
$vva>w\u0307a;
|
||||
$rra$virama}$ha>r\u0331'';
|
||||
$rra}$x>r\u0331;
|
||||
$rra$virama>r\u0331;
|
||||
|
@ -379,108 +379,108 @@
|
|||
$ha>ha;
|
||||
|
||||
# dependent vowels (should never occur except following consonants)
|
||||
$forceIndependentMatra{$aa > \u0314a\u0304 ;
|
||||
$forceIndependentMatra{$ai > \u0314ai ;
|
||||
$forceIndependentMatra{$au > \u0314au ;
|
||||
$forceIndependentMatra{$ii > \u0314i\u0304 ;
|
||||
$forceIndependentMatra{$i > \u0314i ;
|
||||
$forceIndependentMatra{$uu > \u0314u\u0304 ;
|
||||
$forceIndependentMatra{$u > \u0314u ;
|
||||
$forceIndependentMatra{$rrh > \u0314r\u0325\u0304 ;
|
||||
$forceIndependentMatra{$rh > \u0314r\u0325 ;
|
||||
$forceIndependentMatra{$llh > \u0314l\u0325\u0304 ;
|
||||
$forceIndependentMatra{$lh > \u0314l\u0325 ;
|
||||
$forceIndependentMatra{$e > \u0314e\u0304 ;
|
||||
$forceIndependentMatra{$o > \u0314o\u0304 ;
|
||||
$forceIndependentMatra{$aa > \u0314a\u0304;
|
||||
$forceIndependentMatra{$ai > \u0314ai;
|
||||
$forceIndependentMatra{$au > \u0314au;
|
||||
$forceIndependentMatra{$ii > \u0314i\u0304;
|
||||
$forceIndependentMatra{$i > \u0314i;
|
||||
$forceIndependentMatra{$uu > \u0314u\u0304;
|
||||
$forceIndependentMatra{$u > \u0314u;
|
||||
$forceIndependentMatra{$rrh > \u0314r\u0325\u0304;
|
||||
$forceIndependentMatra{$rh > \u0314r\u0325;
|
||||
$forceIndependentMatra{$llh > \u0314l\u0325\u0304;
|
||||
$forceIndependentMatra{$lh > \u0314l\u0325;
|
||||
$forceIndependentMatra{$e > \u0314e\u0304;
|
||||
$forceIndependentMatra{$o > \u0314o\u0304;
|
||||
#extra vowels
|
||||
$forceIndependentMatra{$ce > \u0314e\u0306 ;
|
||||
$forceIndependentMatra{$co > \u0314o\u0306 ;
|
||||
$forceIndependentMatra{$se > \u0314e ;
|
||||
$forceIndependentMatra{$so > \u0314o ;
|
||||
$forceIndependentMatra{$ce > \u0314e\u0306;
|
||||
$forceIndependentMatra{$co > \u0314o\u0306;
|
||||
$forceIndependentMatra{$se > \u0314e;
|
||||
$forceIndependentMatra{$so > \u0314o;
|
||||
$forceIndependentMatra{$nukta >; # Nukta cannot appear independently or as first character
|
||||
$forceIndependentMatra{$virama >; # Virama cannot appear independently or as first character
|
||||
$aa > a\u0304 ;
|
||||
$ai > ai ;
|
||||
$au > au ;
|
||||
$ii > i\u0304 ;
|
||||
$i > i ;
|
||||
$uu > u\u0304 ;
|
||||
$u > u ;
|
||||
$rrh > r\u0325\u0304 ;
|
||||
$rh > r\u0325 ;
|
||||
$llh > l\u0325\u0304 ;
|
||||
$lh > l\u0325 ;
|
||||
$e > e\u0304 ;
|
||||
$o > o\u0304 ;
|
||||
$aa > a\u0304;
|
||||
$ai > ai;
|
||||
$au > au;
|
||||
$ii > i\u0304;
|
||||
$i > i;
|
||||
$uu > u\u0304;
|
||||
$u > u;
|
||||
$rrh > r\u0325\u0304;
|
||||
$rh > r\u0325;
|
||||
$llh > l\u0325\u0304;
|
||||
$lh > l\u0325;
|
||||
$e > e\u0304;
|
||||
$o > o\u0304;
|
||||
#extra vowels
|
||||
$ce > e\u0306 ;
|
||||
$co > o\u0306 ;
|
||||
$se > e ;
|
||||
$so > o ;
|
||||
$ce > e\u0306;
|
||||
$co > o\u0306;
|
||||
$se > e;
|
||||
$so > o;
|
||||
#dependent vowels when following independent vowels. Generally Illegal only for roundtripping
|
||||
$waa} $x > a\u0304\u0314 ;
|
||||
$wai} $x > ai\u0314 ;
|
||||
$wau} $x > au\u0314 ;
|
||||
$wii} $x > i\u0304\u0314 ;
|
||||
$wi } $x > i\u0314 ;
|
||||
$wuu} $x > u\u0304\u0314 ;
|
||||
$wu } $x > u\u0314 ;
|
||||
$wrr} $x > r\u0325\u0304\u0314 ;
|
||||
$wr } $x > r\u0325\u0314 ;
|
||||
$wll} $x > l\u0325\u0304\u0314 ;
|
||||
$wl } $x > l\u0325\u0314 ;
|
||||
$we } $x > e\u0304\u0314 ;
|
||||
$wo } $x > o\u0304\u0314 ;
|
||||
$wa } $x > a\u0314 ;
|
||||
$waa} $x > a\u0304\u0314;
|
||||
$wai} $x > ai\u0314;
|
||||
$wau} $x > au\u0314;
|
||||
$wii} $x > i\u0304\u0314;
|
||||
$wi } $x > i\u0314;
|
||||
$wuu} $x > u\u0304\u0314;
|
||||
$wu } $x > u\u0314;
|
||||
$wrr} $x > r\u0325\u0304\u0314;
|
||||
$wr } $x > r\u0325\u0314;
|
||||
$wll} $x > l\u0325\u0304\u0314;
|
||||
$wl } $x > l\u0325\u0314;
|
||||
$we } $x > e\u0304\u0314;
|
||||
$wo } $x > o\u0304\u0314;
|
||||
$wa } $x > a\u0314;
|
||||
#extra vowels
|
||||
$wce} $x > e\u0306\u0314 ;
|
||||
$wco} $x > o\u0306\u0314 ;
|
||||
$wse} $x > e\u0314 ;
|
||||
$wso} $x > o\u0314 ;
|
||||
$om} $x > ''om\u0314 ;
|
||||
|
||||
$wce} $x > e\u0306\u0314;
|
||||
$wco} $x > o\u0306\u0314;
|
||||
$wse} $x > e\u0314;
|
||||
$wso} $x > o\u0314;
|
||||
$om} $x > ''om\u0314;
|
||||
|
||||
# independent vowels when preceeded by vowels
|
||||
$vowels{$waa > ''a\u0304 ;
|
||||
$vowels{$wai > ''ai ;
|
||||
$vowels{$wau > ''au ;
|
||||
$vowels{$wii > ''i\u0304 ;
|
||||
$vowels{$wi > ''i ;
|
||||
$vowels{$wuu > ''u\u0304 ;
|
||||
$vowels{$wu > ''u ;
|
||||
$vowels{$wrr > ''r\u0325\u0304 ;
|
||||
$vowels{$wr > ''r\u0325 ;
|
||||
$vowels{$wll > ''l\u0325\u0304 ;
|
||||
$vowels{$wl > ''l\u0325 ;
|
||||
$vowels{$we > ''e\u0304 ;
|
||||
$vowels{$wo > ''o\u0304 ;
|
||||
$vowels{$wa > ''a ;
|
||||
$vowels{$waa > ''a\u0304;
|
||||
$vowels{$wai > ''ai;
|
||||
$vowels{$wau > ''au;
|
||||
$vowels{$wii > ''i\u0304;
|
||||
$vowels{$wi > ''i;
|
||||
$vowels{$wuu > ''u\u0304;
|
||||
$vowels{$wu > ''u;
|
||||
$vowels{$wrr > ''r\u0325\u0304;
|
||||
$vowels{$wr > ''r\u0325;
|
||||
$vowels{$wll > ''l\u0325\u0304;
|
||||
$vowels{$wl > ''l\u0325;
|
||||
$vowels{$we > ''e\u0304;
|
||||
$vowels{$wo > ''o\u0304;
|
||||
$vowels{$wa > ''a;
|
||||
#extra vowels
|
||||
$vowels{$wce > ''e\u0306 ;
|
||||
$vowels{$wco > ''o\u0306 ;
|
||||
$vowels{$wse > ''e ;
|
||||
$vowels{$wso > ''o ;
|
||||
$vowels{$wce > ''e\u0306;
|
||||
$vowels{$wco > ''o\u0306;
|
||||
$vowels{$wse > ''e;
|
||||
$vowels{$wso > ''o;
|
||||
|
||||
# independent vowels (otherwise)
|
||||
$waa > a\u0304 ;
|
||||
$wai > ai ;
|
||||
$wau > au ;
|
||||
$wii > i\u0304 ;
|
||||
$wi > i ;
|
||||
$wuu > u\u0304 ;
|
||||
$wu > u ;
|
||||
$wrr > r\u0325\u0304 ;
|
||||
$wr > r\u0325 ;
|
||||
$wll > l\u0325\u0304 ;
|
||||
$wl > l\u0325 ;
|
||||
$we > e\u0304 ;
|
||||
$wo > o\u0304 ;
|
||||
$wa > a ;
|
||||
$waa > a\u0304;
|
||||
$wai > ai;
|
||||
$wau > au;
|
||||
$wii > i\u0304;
|
||||
$wi > i;
|
||||
$wuu > u\u0304;
|
||||
$wu > u;
|
||||
$wrr > r\u0325\u0304;
|
||||
$wr > r\u0325;
|
||||
$wll > l\u0325\u0304;
|
||||
$wl > l\u0325;
|
||||
$we > e\u0304;
|
||||
$wo > o\u0304;
|
||||
$wa > a;
|
||||
#extra vowels
|
||||
$wce > e\u0306 ;
|
||||
$wco > o\u0306 ;
|
||||
$wse > e ;
|
||||
$wso > o ;
|
||||
$om > ''om ;
|
||||
$wce > e\u0306;
|
||||
$wco > o\u0306;
|
||||
$wse > e;
|
||||
$wso > o;
|
||||
$om > ''om;
|
||||
|
||||
#stress marks
|
||||
$avagraha > \u0315;
|
||||
|
@ -488,17 +488,17 @@
|
|||
$chandrabindu > m\u0310;
|
||||
$visarga>h\u0323;
|
||||
#numbers
|
||||
$zero > 0;
|
||||
$one > 1;
|
||||
$two > 2;
|
||||
$zero > 0;
|
||||
$one > 1;
|
||||
$two > 2;
|
||||
$three > 3;
|
||||
$four > 4;
|
||||
$five > 5;
|
||||
$six > 6;
|
||||
$four > 4;
|
||||
$five > 5;
|
||||
$six > 6;
|
||||
$seven > 7;
|
||||
$eight > 8;
|
||||
$nine > 9;
|
||||
$lm >;
|
||||
$lm >;
|
||||
$ailm >;
|
||||
$aulm >;
|
||||
|
||||
|
@ -506,30 +506,30 @@
|
|||
$kta>t\u0331;
|
||||
$danda>'.';
|
||||
$doubleDanda>'.';
|
||||
|
||||
|
||||
\ue070>; # ABBREVIATION SIGN
|
||||
# LETTER RA WITH MIDDLE DIAGONAL
|
||||
\ue071}$x>ra;
|
||||
\ue071$virama>r;
|
||||
\ue071>ra;
|
||||
# LETTER RA WITH LOWER DIAGONAL
|
||||
\ue072}$x>ra;
|
||||
\ue072$virama>r;
|
||||
\ue072>ra;
|
||||
|
||||
\ue073>; # RUPEE MARK
|
||||
\ue074>; # RUPEE SIGN
|
||||
\ue075>; # CURRENCY NUMERATOR ONE
|
||||
\ue076>; # CURRENCY NUMERATOR TWO
|
||||
\ue077>; # CURRENCY NUMERATOR THREE
|
||||
\ue078>; # CURRENCY NUMERATOR FOUR
|
||||
\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
\ue07A>; # CURRENCY DENOMINATOR SIXTEEN
|
||||
\ue07B>; # ISSHAR
|
||||
\uE07C>; # TIPPI
|
||||
\uE07D>; # ADDAK
|
||||
\uE07E>; # IRI
|
||||
\uE07F>; # URA
|
||||
\uE080>; # EK ONKAR
|
||||
\uE004>; # DEVANAGARI VOWEL SIGN SHORT A
|
||||
|
||||
\ue071}$x>ra;
|
||||
\ue071$virama>r;
|
||||
\ue071>ra;
|
||||
# LETTER RA WITH LOWER DIAGONAL
|
||||
\ue072}$x>ra;
|
||||
\ue072$virama>r;
|
||||
\ue072>ra;
|
||||
|
||||
\ue073>; # RUPEE MARK
|
||||
\ue074>; # RUPEE SIGN
|
||||
\ue075>; # CURRENCY NUMERATOR ONE
|
||||
\ue076>; # CURRENCY NUMERATOR TWO
|
||||
\ue077>; # CURRENCY NUMERATOR THREE
|
||||
\ue078>; # CURRENCY NUMERATOR FOUR
|
||||
\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR
|
||||
\ue07A>; # CURRENCY DENOMINATOR SIXTEEN
|
||||
\ue07B>; # ISSHAR
|
||||
\uE07C>; # TIPPI
|
||||
\uE07D>; # ADDAK
|
||||
\uE07E>; # IRI
|
||||
\uE07F>; # URA
|
||||
\uE080>; # EK ONKAR
|
||||
\uE004>; # DEVANAGARI VOWEL SIGN SHORT A
|
||||
|
||||
|
|
Loading…
Add table
Reference in a new issue