source/data/translit/InterIndic_Latin.txt - Issue 2440913002: Update ICU to 58.1

Unified Diff: source/data/translit/InterIndic_Latin.txt

Issue 2440913002: Update ICU to 58.1

Patch Set: Created 4 years, 2 months ago

Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.

Jump to:

View side-by-side diff with in-line comments

Index: source/data/translit/InterIndic_Latin.txt

diff --git a/source/data/translit/InterIndic_Latin.txt b/source/data/translit/InterIndic_Latin.txt

index 0c85a5a446b786726ceed38b6da529cd9b6bd5af..13cd64a7211cd99b3eff533b82208c7ec9f79a83 100644

--- a/source/data/translit/InterIndic_Latin.txt

+++ b/source/data/translit/InterIndic_Latin.txt

@@ -1,15 +1,18 @@

-# ***************************************************************************

-# *

-# ***************************************************************************

+# License & terms of use: http://www.unicode.org/copyright.html#License

# File: InterIndic_Latin.txt

-# Generated from CLDR

+# Generated from CLDR

+# InterIndic-Latin

+#\u0E00 reserved

+#consonants

$chandrabindu=\uE001;

$anusvara=\uE002;

$visarga=\uE003;

+#\u0E004 reserved

+# w←vowel→ represents the stand-alone form

$wa=\uE005;

$waa=\uE006;

$wi=\uE007;

@@ -64,8 +67,11 @@ $sha=\uE036;

$ssa=\uE037;

$sa=\uE038;

$ha=\uE039;

+#\u093A Reserved

+#\u093B Reserved

$nukta=\uE03C;

$avagraha=\uE03D; # SIGN AVAGRAHA

+# ←vowel→ represents the dependent form

$aa=\uE03E;

$i=\uE03F;

$ii=\uE040;

@@ -82,6 +88,8 @@ $so=\uE04A; # VOWEL SIGN SHORT O

$o=\uE04B; # ो

$au=\uE04C;

$virama=\uE04D;

+# \u094E Reserved

+# \u094F Reserved

$om=\uE050; # OM

\uE051→; # UNMAPPED STRESS SIGN UDATTA

\uE052→; # UNMAPPED STRESS SIGN ANUDATTA

@@ -90,6 +98,7 @@ $om=\uE050; # OM

$lm = \uE055;# Telugu Length Mark

$ailm=\uE056;# AI Length Mark

$aulm=\uE057;# AU Length Mark

+#urdu compatibity forms

$uka=\uE058;

$ukha=\uE059;

$ugha=\uE05A;

@@ -114,14 +123,21 @@ $six=\uE06C; # DIGIT SIX

$seven=\uE06D; # DIGIT SEVEN

$eight=\uE06E; # DIGIT EIGHT

$nine=\uE06F; # DIGIT NINE

+# Glottal stop

$dgs=\uE082;

+#Khanda-ta

$kta=\uE083;

$depVowelAbove=[\uE03E-\uE040\uE045-\uE04C];

$depVowelBelow=[\uE041-\uE044];

+# $x was originally called '§'; $z was '%'

$x=[$aa$ai$au$ii$i$uu$u$rrh$rh$lh$llh$e$o$se$ce$so$co];

$z=[bcdfghjklmnpqrstvwxyz];

$vowels=[aeiour\u0304\u0325\u0306];

$forceIndependentMatra = [^[[:L:][\u0300-\u034C]]];

+######################################################################

+# convert from Native letters to Latin letters

+######################################################################

+#transliterations for anusvara

$anusvara} [$ka$kha$ga$gha$nga] → n\u0307;

$anusvara} [$ca$cha$ja$jha$nya] → n\u0304;

$anusvara} [$tta$ttha$dda$ddha$nna] → n\u0323;

@@ -129,6 +145,7 @@ $anusvara} [$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;

@@ -186,6 +203,7 @@ $ela → l\u0331a;

$uya}$x → y\u0307;

$uya$virama → y\u0307;

$uya → y\u0307a;

+# normal consonants

$ka$virama}$ha→k'';

$ka}$x→k;

$ka$virama→k;

@@ -312,6 +330,7 @@ $sa$virama}$ssa→s'';

$sa$virama}$sa→s'';

$sa}$x→s;

$sa$virama→s;

+#for gurmukhi

$sa$nukta}$x→s\u0301;

$sa$nukta$virama→s\u0301;

$sa$nukta→s\u0301a;

@@ -325,6 +344,7 @@ $ssa→s\u0323a;

$ha}$x→h;

$ha$virama→h;

$ha→ha;

+# dependent vowels (should never occur except following consonants)

$forceIndependentMatra{$aa → \u0314a\u0304;

$forceIndependentMatra{$ai → \u0314ai;

$forceIndependentMatra{$au → \u0314au;

@@ -338,6 +358,7 @@ $forceIndependentMatra{$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;

@@ -357,10 +378,12 @@ $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;

+#dependent vowels when following independent vowels. Generally Illegal only for roundtripping

$waa} $x → a\u0304\u0314;

$wai} $x → ai\u0314;

$wau} $x → au\u0314;

@@ -375,11 +398,13 @@ $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;

+# independent vowels when preceeded by vowels

$vowels{$waa → ''a\u0304;

$vowels{$wai → ''ai;

$vowels{$wau → ''au;

@@ -394,10 +419,12 @@ $vowels{$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;

+# independent vowels (otherwise)

$waa → a\u0304;

$wai → ai;

$wau → au;

@@ -412,15 +439,18 @@ $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;

+#stress marks

$avagraha → \u0315;

$chandrabindu$anusvara→\u0303;

$chandrabindu → m\u0310;

$visarga→h\u0323;

+#numbers

$zero → 0;

$one → 1;

$two → 2;

@@ -439,9 +469,11 @@ $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;

@@ -460,3 +492,4 @@ $doubleDanda→'.';

\uE07F→; # URA

\uE080→; # EK ONKAR

\uE004→; # DEVANAGARI VOWEL SIGN SHORT A

« no previous file with comments | « source/data/translit/InterIndic_Kannada.txt ('k') | source/data/translit/InterIndic_Malayalam.txt » ('j') | no next file with comments »