You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
226 lines
8.7 KiB
226 lines
8.7 KiB
# © 2016 and later: Unicode, Inc. and others.
|
|
# License & terms of use: http://www.unicode.org/copyright.html
|
|
# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
|
|
#
|
|
# File: my_Zawgyi.txt
|
|
# Generated from CLDR
|
|
#
|
|
|
|
# This transform converts Unicode Burmese text into Zawgyi font encoded
|
|
# form. Zawgyi is a popular, non-standard encoding scheme in Myanmar
|
|
# that uses the same code range as Myanmar Unicode but assigns different
|
|
# characters or glyphs to some codepoints. In addition to character remapping,
|
|
# context-based reordering of codepoints is needed to give readable
|
|
# output when the output is displayed with a Zawgyi font such as
|
|
# ZawgyiOne.ttf or ZawgyiOne2008.ttf.
|
|
#
|
|
# The transform is done in two main stages:
|
|
# (1) Map all Unicode codepoints to their Zawgyi counterparts.
|
|
# (2) Perform reordering.
|
|
# Modern Burmese digits & Unicode code points.
|
|
$nondigits = [^\u1040-\u1049];
|
|
$consonant = [\u1000-\u1021];
|
|
$narrowconsonant = [\u1001\u1002\u1004\u1005\u1007\u100b-\u100e\u1012\u1013\u1015-\u1017\u1019\u101d\u1020\u1025\u1026\u108f];
|
|
$wideconsonant = [\u1000\u1003\u1006\u1009\u100a\u100f\u1010\u1011\u1018\u101c\u101e\u101f\u1021];
|
|
$widenya = [\u100a\u106b];
|
|
$othernya = [\u1009\u106a];
|
|
$vowelsign = [\u102B-\u1030\u1032];
|
|
$vowelmedial = [\u102B-\u1030\u1032\u103c-\u103F];
|
|
$ukinzi = [\u1004\u101b\u105a]\u103A\u1039;
|
|
$medialraZ = [\u103b\u107e-\u1084];
|
|
$lowsignZ = [\u102f\u1030\u1037\u103a\u103c\u103d\u1087-\u108a];
|
|
$highsignZ = [\u102d\u102e\u1032\u1036\u1039\u103d-\u103e\u1064];
|
|
$subscriptitem = [\u1060-\u1063\u1064-\u1068\u106c\u106d\u1070-\u107c\u1085\u1093\u1096];
|
|
$vowelsAndConsonants = [\u1000-\u102a];
|
|
#### Phase 0: CODEPOINT MAPPING FROM UNICODE TO ZAWGYI
|
|
$ukinzi ($consonant) \u103B > $1 \u103A \u1064 ;
|
|
$ukinzi ($consonant) \u102D \u1036 > $1 \u108e ;
|
|
$ukinzi ($consonant) \u102D > $1 \u108b ;
|
|
$ukinzi ($consonant) \u102E > $1 \u108C ;
|
|
$ukinzi ($consonant) \u1036 > $1 \u108D ;
|
|
$ukinzi ($consonant) \u1031 > $1 \u1031 \u1064 ;
|
|
$ukinzi ($consonant) \u103B \u102D \u102F > $1 \u103A \u1033 \u108B ;
|
|
$ukinzi ($consonant) \u103B \u102D > $1 \u103A \u108b ;
|
|
$ukinzi ($consonant) \u103B \u102E \u102F > $1 \u103A \u108C \u1033 ;
|
|
$ukinzi ($consonant) \u103B \u102E > $1 \u103A \u108C ;
|
|
$ukinzi ($consonant) \u103B \u1036 > $1 \u103A \u108D ;
|
|
$ukinzi ($consonant) \u103c > $1 \u103b \u1064; # Kinzi + medial ra
|
|
$ukinzi \u102D > \u108B ;
|
|
$ukinzi \u102E > \u108C ;
|
|
$ukinzi \u1036 > \u108D ;
|
|
$ukinzi ($consonant) > $1 \u1064 ;
|
|
\u1025 ($vowelsign) \u1038 > \u106A $1 \u1038 ;
|
|
\u1025 \u102f \u1036 > \u1025 \u1036 \u1033 ;
|
|
\u102D \u1036 > \u108E ;
|
|
# Some composed lower output
|
|
\u103d \u103e > \u108a ;
|
|
\u103e \u102f > \u1088 ;
|
|
\u103E \u1030 > \u1089 ;
|
|
\u103A > \u1039 ;
|
|
\u103B > \u103A ;
|
|
\u103C > \u103B ;
|
|
\u103D > \u103C ;
|
|
\u103E > \u103D ;
|
|
\u103F > \u1086 ;
|
|
([\u1019]) \u103e \u1030 > $1 \u103d \u1034; # A special case with signs.
|
|
\u102B \u103A > \u105A ;
|
|
\u1039 \u1010 \u103d > \u1096 ; # Very special case
|
|
\u1039 \u1000 > \u1060 ;
|
|
\u1039 \u1001 > \u1061 ;
|
|
\u1039 \u1002 > \u1062 ;
|
|
\u1039 \u1003 > \u1063 ;
|
|
\u1039 \u1005 > \u1065 ;
|
|
\u1039 \u1006 > \u1067 ;
|
|
\u1039 \u1007 > \u1068 ;
|
|
\u1039 \u1008 > \u1069 ;
|
|
\u1039 \u100B > \u106C ;
|
|
\u1039 \u100C > \u106D ;
|
|
\u1039 \u100D > \u106E ;
|
|
\u100d \u1039 \u100E > \u106F ;
|
|
\u1039 \u100E > \u106F ;
|
|
\u1039 \u100F > \u1070 ;
|
|
\u1039 \u1010 > \u1072 ;
|
|
\u1039 \u1011 > \u1074 ;
|
|
\u1039 \u1012 > \u1075 ;
|
|
\u1039 \u1013 > \u1076 ;
|
|
\u1039 \u1014 > \u1077 ;
|
|
\u1039 \u1015 > \u1078 ;
|
|
\u1039 \u1016 > \u1079 ;
|
|
\u1039 \u1017 > \u107A ;
|
|
\u1039 \u1018 > \u1093 ;
|
|
\u1039 \u1019 > \u107C ;
|
|
\u1039 \u101C > \u1085 ;
|
|
\u100d\u1039\u100D > \u106E ;
|
|
\u100F\u1039\u100D > \u1091 ;
|
|
\u100B\u1039\u100C > \u1092 ;
|
|
\u100B\u1039\u100B > \u1097 ;
|
|
\u104E\u1004\u103A\u1038 > \u104E ;
|
|
#### PHASE 1: Everything is now in Zawgyi code points. REORDERING RULES.
|
|
::Null;
|
|
# E Vowel + medial ra. Move the e vowel
|
|
($consonant) \u103b \u1031 > \u1031 \u103b $1 ;
|
|
($consonant) \u103b > \u103b $1 ;
|
|
($consonant) \u103d \u1031 \u1037 > \u1031 $1 \u1094 \u103D ;
|
|
($consonant) (\u108a) \u1031 > \u1031 $1 $2 ;
|
|
($consonant) ([\u103a\u103d\u103e]+) \u1031 > \u1031 $1 $2 ;
|
|
# Ra + kinzi
|
|
($consonant) \u1064 \u103b > \u103b $1 \u1064 ;
|
|
# E vowel plus medials
|
|
($consonant) ([\u103a\u103c-\u103d]) \u1031 > \u1031 $1 $2 ;
|
|
# No medials intervening.
|
|
($vowelsAndConsonants) \u1031 > \u1031 $1 ;
|
|
# Handle Na with lower modifiers.
|
|
\u1014 ($subscriptitem) > \u108f $1 ;
|
|
\u1014 ($lowsignZ) ($highsignZ) \u1037 > \u108f $1 $2 \u1094;
|
|
\u1014 ($highsignZ) ($lowsignZ) \u1037 > \u108f $1 $2 \u1094;
|
|
\u1014 ($highsignZ) \u1037 > \u1014 $1 \u1094;
|
|
# Two medials
|
|
\u103a \u103c > \u107d \u103c;
|
|
# a special case
|
|
\u1014 \u1032 \u1037 > \u1014 \u1032 \u1094;
|
|
\u1014 \u1037 > \u1014 \u1094;
|
|
\u1014 \u1032 ($lowsignZ) \u1037 > \u108f $1 \u1032 \u1094;
|
|
\u1014 ($highsignZ) ($lowsignZ) > \u108f $1 $2;
|
|
\u1014 ($lowsignZ) ($highsignZ) > \u108f $1 $2;
|
|
\u1014 ($lowsignZ) \u1037 > \u108f $1 \u1094;
|
|
\u1014 ($lowsignZ) > \u108f $1;
|
|
# Move 1037 dot to right with other descenders.
|
|
($lowsignZ) ($highsignZ*) \u1037 > $1 $2 \u1094;
|
|
($nondigits) \u1040 ([\u102B-\u103F]) > $1 \u101D $2;
|
|
# Handle lack of 104E ၎ MYANMAR SYMBOL AFOREMENTIONED
|
|
($nondigits) \u104e > $1 \u1044;
|
|
\u1031 \u1040 ($nondigits) > \u1031 \u101D $1;
|
|
\u1009 \u103A > \u1025 \u103A;
|
|
\u1025 \u102E > \u1026;
|
|
\u1037 \u103A > \u103A \u1037;
|
|
([\u102B\u102C\u102F\u1030]) ([\u102D\u102E\u1032]) > $2 $1;
|
|
# Medial plus vowel sign U
|
|
($medialraZ) ($consonant) \u102f > $1 $2 \u1033;
|
|
## Phase 2: Further adjustments
|
|
::Null;
|
|
# Handle consonant, subscripted consonant, medial ra
|
|
($narrowconsonant) ($subscriptitem) ($highsignZ) $medialraZ > \u1083 $1 $2 $3 ;
|
|
($wideconsonant) ($subscriptitem) ($highsignZ) $medialraZ > \u1084 $1 $2 ;
|
|
($narrowconsonant) ($subscriptitem) $medialraZ > \u1081 $1 $2 ;
|
|
($wideconsonant) ($subscriptitem) $medialraZ > \u1082 $1 $2 ;
|
|
\u103c \u1094 > \u103c \u1095 ;
|
|
# Medial ra variations, context dependent
|
|
$medialraZ ($narrowconsonant) \u102d \u103d \u102f > \u107f $1 \u102d \u1087 \u1083 ;
|
|
$medialraZ ($wideconsonant) \u102d \u103d \u102f > \u1080 $1 \u102d \u1087 \u1083 ;
|
|
$medialraZ ($narrowconsonant) ($lowsignZ) ($highsignZ) > \u1083 $1 $2 $3 ;
|
|
$medialraZ ($wideconsonant) ($lowsignZ) ($highsignZ) > \u1084 $1 $2 $3 ;
|
|
$medialraZ ($narrowconsonant) ($highsignZ) > \u107f $1 $2 ;
|
|
$medialraZ ($wideconsonant) ($highsignZ) > \u1080 $1 $2 ;
|
|
$medialraZ ($narrowconsonant) \u1030 > \u103b $1 \u1034 ;
|
|
$medialraZ ($wideconsonant) \u1030 > \u107e $1 \u1034 ;
|
|
$medialraZ ($narrowconsonant) (\u102f) > \u103b $1 \u1033 ;
|
|
$medialraZ ($wideconsonant) (\u102f) > \u107e $1 \u1033 ;
|
|
$medialraZ ($narrowconsonant) ($lowsignZ) > \u1081 $1 $2 ;
|
|
$medialraZ ($wideconsonant) ($lowsignZ) > \u1082 $1 $2 ;
|
|
$medialraZ ($widenya) > \u1082 $1 ;
|
|
$medialraZ ($othernya) > \u103b \u106a ;
|
|
$medialraZ ($narrowconsonant) > \u103b $1 ;
|
|
$medialraZ ($wideconsonant) > \u107e $1 ;
|
|
\u1009 ($lowsignZ) > \u106a $1;
|
|
\u100A ($lowsignZ)> \u106B $1 ; ## NYA and NNYA
|
|
\u103d \u102d > \u102d \u103d;
|
|
\u103a ($highsignZ) \u102f [\u1037\u1094\u1095] > \u103a $1 \u1033 \u1095;
|
|
\u103a \u102f [\u1037\u1094\u1095] > \u103a \u1033 \u1095;
|
|
\u103a \u102f > \u103a \u1033;
|
|
# Kinzi combo
|
|
\u1064 \u102e > \u108c ;
|
|
##### Phase 3
|
|
::Null;
|
|
([\u103C\u103D\u103E]+) \u103B > \u103B $1;
|
|
([\u103D\u103E]+) \u103C > \u103C $1;
|
|
\u103E\u103D > \u103D\u103E ;
|
|
\u1037 ([\u102D-\u1030\u1032\u1036]) > $1 \u1037;
|
|
($consonant) ([\u102B-\u1032\u1036\u103B-\u103E]) \u103A ($consonant)> $1 \u103A $2 $3;
|
|
# Combine vowel and consonant signs
|
|
\u103d \u102f > \u1088;
|
|
\u1033 \u1094 > \u1033 \u1095; # Wider spacing on lower dot
|
|
($medialraZ) ($consonant) ($highsignZ) \u102f > $1 $2 $3 \u1033;
|
|
##### Phase 4. More reorderings of medials
|
|
::Null;
|
|
([\u103D\u103E]) \u103C > \u103C $1;
|
|
\u103E\u103D > \u103D\u103E ;
|
|
\u1038 ($vowelmedial) > $1 \u1038;
|
|
\u1038 ([\u1036\u1037\u103A]) > $1 \u1038;
|
|
\u1036 \u102f > \u102f \u1036;
|
|
\u103a ([\u1064\u108b-\u108e]) \u102d \u102f > \u103a $1 \u102d \u1033;
|
|
\u103a \u102d \u102f > \u103a \u102d \u1033;
|
|
#### Phase 5
|
|
::Null;
|
|
($consonant) \u103B \u103A > $1 \u103A \u103B;
|
|
([\u103C\u103D\u103E]) \u103B > \u103B $1;
|
|
([\u103D\u103E]) \u103C > \u103C $1;
|
|
\u103E\u103D > \u103D\u103E ;
|
|
([\u102D-\u1030\u1032]) \u103A ($consonant) \u103A > $1 $2 \u103A;
|
|
\u102D \u103A > \u102D;
|
|
\u102E \u103A > \u102E;
|
|
\u102F \u103A > \u102F;
|
|
\u102D \u102E > \u102E;
|
|
\u102F \u1030 > \u102F;
|
|
\u102B \u102B+ > \u102B;
|
|
\u102C \u102C+ > \u102C;
|
|
\u102D \u102D+ > \u102D;
|
|
\u102E \u102E+ > \u102E;
|
|
\u102F \u102F+ > \u102F;
|
|
\u1030 \u1030+ > \u1030;
|
|
\u1031 \u1031+ > \u1031;
|
|
\u1032 \u1032+ > \u1032;
|
|
\u1036 \u1036+ > \u1036;
|
|
\u103A \u103A+ > \u103A;
|
|
\u103B \u103B+ > \u103B;
|
|
\u103C \u103C+ > \u103C;
|
|
\u103D \u103D+ > \u103D;
|
|
\u103E \u103E+ > \u103E;
|
|
# Visually identical orderings - standardize
|
|
\u102f \u102D > \u102D \u102f ;
|
|
\u102f \u1036 > \u1036 \u102f ;
|
|
\u1039 \u1037 > \u1037 \u1039 ;
|
|
\u103c \u1032 > \u1032 \u103c ;
|
|
\u103c \u102e > \u102e \u103c ;
|
|
\u103d \u1088 > \u1088 ;
|
|
|