xref: /aosp_15_r20/external/cldr/common/transforms/Myanmar-Latin.xml (revision 912701f9769bb47905792267661f0baf2b85bed5)

<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
<!-- Copyright © 2020 Unicode, Inc.
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
For terms of use, see http://www.unicode.org/copyright.html -->
<supplementalData>
	<version number="$Revision$" />
	<transforms>
		<transform source="my" target="my_Latn" direction="forward" draft="contributed" alias="Burmese-Latin Myanmar-Latin my-Latn-t-my">
			<tRule><![CDATA[
# Author: Arne Mauser, Moe Aung Naing
# Description: Myanmar Romanization

$consonants = [\u1000-\u1021];

# Character combinations: "1 consonant 5 vowels"
# ($consonants) ြောင့် > | $1 yount;
($consonants) \u103C\u1031\u102C\u1004\u103A\u1037 > | $1 yount;

# ($consonants) ျောင့် > | $1 yount;
($consonants)  \u103B\u1031\u102C\u1004\u103A\u1037 > | $1 yount;

# ($consonants) ြောင်း > | $1 yaungg;
($consonants) \u103C\u1031\u102C\u1004\u103A\u1038 > | $1 yaungg;

# ($consonants) ျောင်း > | $1 yaungg;
($consonants) \u103B\u1031\u102C\u1004\u103A\u1038  > | $1 yaungg;



#  Character combinations: "1 consonant 4 vowels"
# ိုင်း > ine;
 \u102D\u102F\u1004\u103A\u1038 > ine;

# ($consonants) ြောင် > | $1 yaung;
($consonants) \u103C\u1031\u102C\u1004\u103A  > | $1 yaung;

# ($consonants) ျောင် > | $1 yaung;
($consonants) \u103B\u1031\u102C\u1004\u103A  > | $1 yaung;



#  Character combinations: "1 consonant 3 vowels"
# ောက် > out; # 1c3v
\u1031\u102C\u1000\u103A > out;

# ေါက် > out; # 1c3v
\u1031\u102B\u1000\u103A > out;

# ိုက် > ite; # 1c3v
\u102D\u102F\u1000\u103A > ite;

# ိုင် > ine; # 1c3v
\u102D\u102F\u1004\u103A > ine;

# ိုယ် > o; # 1c3v
\u102D\u102F\u101A\u103A > o;

# ျင်း > yinn;
\u103B\u1004\u103A\u1038 > yinn;

# ျိန် > yane;
\u103B\u102D\u1014\u103A > yane;

# ($consonants) ောင်း > | $1 aungg;
($consonants) \u1031\u102C\u1004\u103A\u1038 > | $1 aungg;

# ($consonants) ေါင်း > | $1 aungg;
($consonants) \u1031\u102B\u1004\u103A\u1038 > | $1 aungg;

# ($consonants) ောင် > | $1 aung;
($consonants) \u1031\u102C\u1004\u103A > | $1 aung;

# ($consonants) ေါင် >  | $1 aung;
($consonants) \u1031\u102B\u1004\u103A > | $1 aung;

# ($consonants) ြင့် > | $1 yint;
($consonants) \u103C\u1004\u103A\u1037 > | $1 yint;

# ($consonants) ြင်း > | $1 yinn;
($consonants) \u103C\u1004\u103A\u1038 > | $1 yinn;

# ($consonants) ြင် > | $1 yin;
($consonants) \u103C\u1004\u103A > | $1 yin;

# ($consonants) ျင့် > | $1 yint;
($consonants) \u103B\u1004\u103A\u1037 > | $1 yint;

# ($consonants) ျင်း > | $1 yinn;
($consonants) \u103B\u1004\u103A\u1038 > | $1 yinn;

# ($consonants) ျင် > | $1 yin;
($consonants) \u103B\u1004\u103A > | $1 yin;

# ($consonants) ြစ် > | $1 yit;
($consonants) \u103C\u1005\u103A > | $1 yit;

# ($consonants) ျစ် > | $1 yit;
($consonants)  \u103B\u1005\u103A > | $1 yit;

# ($consonants) ြည် > | $1 yi;
($consonants) \u103C\u100A\u103A > | $1 yi;

# ($consonants) ြန် > | $1 yan;
($consonants) \u103C\u1014\u103A > | $1 yan;

# ($consonants) ြန်း > | $1 yann;
($consonants) \u103C\u1014\u103A\u1038 > | $1 yann;

# ($consonants) ျန်း > | $1 yann;
($consonants) \u103B\u1014\u103A\u1038 > | $1 yann;

# ိမ်း > aim;
\u102D\u1019\u103A\u1038 > aim;

# ိန်း > ein;
\u102D\u1014\u103A\u1038 > ein;



#  Character combinations: "4 vowels"
# ျိုး > yoe;
\u103B\u102D\u102F\u1038 > yoe;

# ($consonants) ြော် > | $1 yaw;
($consonants) \u103C\u1031\u102C\u103A > | $1 yaw;

# ($consonants) ျော် > | $1 yaw;
($consonants) \u103B\u1031\u102C\u103A > | $1 yaw;



# Character combinations: "1 consonant 2 vowels"
# ဦး > u;
\u1025\u102E\u1038 > u;  # this is a misspelling of \u1026

# ွက် > wat;
\u103D\u1000\u103A > wat;

# ွင် > win;
\u103D\u1004\u103A > win;

# န်း > ann;
\u1014\u103A\u1038 > ann;

# န့် > ant;
\u1014\u103A\u1037 > ant;

# င်း > inn;
\u1004\u103A\u1038 > inn;

# င့် > int;
\u1004\u103A\u1037 > int;

# ည်း > ee;
\u100A\u103A\u1038 > ee;

# ည့် > eet; # 1c2v
\u100A\u103A\u1037 > eet;

# ိတ် > ate; # 1c2v
\u102D\u1010\u103A > ate;

# ုတ် > ote; # 1c2v
\u102F\u1010\u103A > ote;

# ုန် > one; # 1c2v
\u102F\u1014\u103A > one;

# ုပ် > ote; # 1c2v
\u102F\u1015\u103A > ote;

# ိမ် > aim; # 1c2v
\u102D\u1019\u103A > ain;

# ိန် > ein;
\u102D\u1014\u103A > ein;

# ယ့် > ae; # 1c2v
\u101A\u103A\u1037 > ae;

# သျှ > sh; # 1c2v
\u101E\u103B\u103E > sh;

# လျှ > sh; # 1c2v
\u101C\u103B\u103E > sh;

# ရွှ > shw; # 1c2v
\u101B\u103D\u103E > shw;

# ြတ် > yat;
\u103C\u1010\u103A > yat;

# ျတ် > yat;
\u103B\u1010\u103A > yat;

# ြက်  > yet;
\u103C\u1000\103A > yet;

# ျက် > yet;
\u103B\u1000\u103A > yet;

# ျင် > yin;
\u103B\u1004\u103A > yin;

# ြင် > yin;
\u103C\u1004\u103A > yin;




#  Character combinations: "3 vowels"
# ော့ > ot;
\u1031\u102C\u1037 > ot;

# ေါ့ > ot;
\u1031\u102B\u1037 > ot;

# ော် > aw;
\u1031\u102C\u103A > aw;

# ေါ် > aw;
\u1031\u102B\u103A > aw;

# ို့ > hoet; # 3v
\u102D\u102F\u1037 > hoet;

# ိုး > oe;
\u102D\u102F\u1038 > oe;

# ုံး > one; # 3v
\u102F\u1036\u1038 > one;

# ျား > yarr;
\u103B\u102C\u1038 > yarr;

# ြား > yarr;
\u103C\u102C\u1038 > yarr;

# ြီး > yee;
\u103C\u102E\u1038 > yee;

# ($consonants) ြော  > | $1 yaww;
($consonants) \u103C\u1031\u102C > | $1 yaww;

# ($consonants) ျော  > | $1 yaww;
($consonants) \u103B\u1031\u102C > | $1 yaww;

# ွား > warr;
\u103D\u102C\u1038 > warr;

# ွေ့ > wae;
\u103D\u1031\u1037 > wae;




#  Character combinations: "1 consonant 1 vowel"
#က် > at;
\u1000\u103A > at;

# င် > in;
\u1004\u103A > in;

# စ် > it;
\u1005\u103A > it;

# ဥ် > in;
\u1009\u103A > in;
\u1025\u103A > in;  # \u1025 is a misspelling of \u1009

# ည် > i;
\u100A\u103A > i;

# ပ် > ut;
\u1015\u103A > ut;

# ယ် > al;
\u101A\u103A > al;

# တ် > at;
\u1010\u103A > at;

# န် > an;
\u1014\u103A > an;

# ရှ > sh; # 1c1v
\u101B\u103E > sh;

#  Character combinations: "2 vowel"
# ြီ > ye;
\u103C\u102E > ye;

# ြု > yu;
\u103C\u102F > yu;

# ြေ > yay;
\u103C\u1031 > yay;

# ွေ > way;
\u103D\u1031 > way;

# ွဲ > wal;
\u103D\u1032 > wal;

# ှု > hu;
\u103E\u102F > hu;

# ူ့ > hu;
\u1030\u1037 > hu;

# ူး > uu;
\u1030\u1038 > uu;

# ါး > arr;
\u102B\u1038 > arr;

# ား > arr;
\u102C\u1038 > arr;

# ီး > ee;
\u102E\u1038 > ee;

# ေး > ayy;
\u1031\u1038 > ayy;

# ေ့ > ae;
\u1031\u1037 > ae;

# ဲ့ > ae;
\u1032\u1037 > ae;

# ော > aw;
\u1031\u102C > aw;

# ေါ > aw;
\u1031\u102B > aw;

# ို > o;
\u102D\u102F > o;

# ုံ > one;
\u102F\u1036 > one;

# ှာ > har;
\u103E\u102C > har;





# Character combinations: "1 vowel"

# ါ > ar;
\u102B > ar;

# ာ  > ar;
\u102C > ar;

# ိ > i;
\u102D > i;

# ီ  > e;
\u102E > e;

# ု  > u;
\u102F > u;

# ူ > uu;
\u1030 > uu;

# ေ  > ay;
\u1031 > ay;

# ဲ  > ell;
\u1032 > ell;

# ံ  > an;
\u1036 > an;

# ျ > ya;
\u103B > ya;

# ြ  > ya;
\u103C > ya;

#  ှ  > ha;
\u103E > ha;


# Modern Myanmar digits
\u1040 > 0 ;
\u1041 > 1 ;
\u1042 > 2 ;
\u1043 > 3 ;
\u1044 > 4 ;
\u1045 > 5 ;
\u1046 > 6 ;
\u1047 > 7 ;
\u1048 > 8 ;
\u1049 > 9 ;

# Myanmar Punctuation

\u104A > \, ; # MYANMAR SIGN LITTLE SECTION
\u104B > \. ; # MYANMAR SIGN SECTION
\u104C > ; # MYANMAR SYMBOL LOCATIVE
\u104D > ; # MYANMAR SYMBOL COMPLETED

# Inserting 'a' in between to consonants.

($consonants) ($consonants) > | $1 a $2 ;

# Consonant clusters
# က္က > kk ;
# က္ခ > khk ;
# ဂ္ဂ > gg ;
# ဂ္ဃ > ggh ;
# င်္ဂ > ngg ;

# Fundamental Burmese Consonants:
# က > k;
\u1000 > k;

# ခ > hk;
\u1001 > hk;

# ဂ > g;
\u1002 > g;

# ဃ > gh;
\u1003 > gh;

# င > ng;
\u1004 > ng;

# စ > hc;
\u1005 > hc;

# ဆ > s;
\u1006 > s;

# ဇ > j;
\u1007 > j;

# ဈ > jh;
\u1008 > jh;

# ဉ > ny;
\u1009 > ny;

# ည > ny;
\u100A > ny;

# ဋ > t;
\u100B > t;

# ဌ > ht;
\u100C > ht;

# ဍ > d;
\u100D > d;

# ဎ > dh;
\u100E > dh;

# ဏ > n;
\u100F > n;

# တ > t;
\u1010 > t;

# ထ > ht;
\u1011 > ht;

# ဒ > d;
\u1012 > d;

# ဓ > dh;
\u1013 > dh;

# န > n;
\u1014 > n;

# ပ > p;
\u1015 > p;

# ဖ > hp;
\u1016 > hp;

# ဗ > b;
\u1017 > b;

# ဘ > bh;
\u1018 > bh;

# မ > m;
\u1019 > m;

# ယ > y;
\u101A > y;

# ရ > r;
\u101B > r;

# လ > l;
\u101C > l;

# ဝ > w;
\u101D > w;

# သ > s;
\u101E > s;
ဿ > s; #https://www.eki.ee/wgrs/rom2_my.htm

# ဟ > h;
\u101F > h;

# ဠ > l;
\u1020 > l;

# အ > a;
\u1021 > a;

# ဣ > i;
\u1023 > i;

# ဤ > i;
\u1024 > i;

# ဥ > u;
\u1025 > u;

# ဦ > u;
\u1026 > u;

# ဧ > e;
\u1027 > e;

# ဩ > au;
\u1029 > au;

# ဪ > au;
\u102A > au;

# TODO: this character repeats the previous romanized letter
# း > ;
\u1038 > ;

# ့  > ;
\u1037 > ;

#  ်  > ;
\u103A > ;

# ၏ > eat ;
\u104F > eat;

# ္  > ;
\u1039 > ;

# Leftovers

\u103D > w;

::NFC(NFD);
			]]></tRule>
		</transform>
	</transforms>
</supplementalData>