1# © 2016 and later: Unicode, Inc. and others. 2# License & terms of use: http://www.unicode.org/copyright.html 3# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml 4# 5# File: my_Zawgyi.txt 6# Generated from CLDR 7# 8 9# This transform converts Unicode Burmese text into Zawgyi font encoded 10# form. Zawgyi is a popular, non-standard encoding scheme in Myanmar 11# that uses the same code range as Myanmar Unicode but assigns different 12# characters or glyphs to some codepoints. In addition to character remapping, 13# context-based reordering of codepoints is needed to give readable 14# output when the output is displayed with a Zawgyi font such as 15# ZawgyiOne.ttf or ZawgyiOne2008.ttf. 16# 17# The transform is done in two main stages: 18# (1) Map all Unicode codepoints to their Zawgyi counterparts. 19# (2) Perform reordering. 20# Modern Burmese digits & Unicode code points. 21$nondigits = [^\u1040-\u1049]; 22$consonant = [\u1000-\u1021]; 23$narrowconsonant = [\u1001\u1002\u1004\u1005\u1007\u100b-\u100e\u1012\u1013\u1015-\u1017\u1019\u101d\u1020\u1025\u1026\u108f]; 24$wideconsonant = [\u1000\u1003\u1006\u1009\u100a\u100f\u1010\u1011\u1018\u101c\u101e\u101f\u1021]; 25$widenya = [\u100a\u106b]; 26$othernya = [\u1009\u106a]; 27$vowelsign = [\u102B-\u1030\u1032]; 28$vowelmedial = [\u102B-\u1030\u1032\u103c-\u103F]; 29$ukinzi = [\u1004\u101b\u105a]\u103A\u1039; 30$medialraZ = [\u103b\u107e-\u1084]; 31$lowsignZ = [\u102f\u1030\u1037\u103a\u103c\u103d\u1087-\u108a]; 32$highsignZ = [\u102d\u102e\u1032\u1036\u1039\u103d-\u103e\u1064]; 33$subscriptitem = [\u1060-\u1063\u1064-\u1068\u106c\u106d\u1070-\u107c\u1085\u1093\u1096]; 34$vowelsAndConsonants = [\u1000-\u102a]; 35#### Phase 0: CODEPOINT MAPPING FROM UNICODE TO ZAWGYI 36$ukinzi ($consonant) \u103B > $1 \u103A \u1064 ; 37$ukinzi ($consonant) \u102D \u1036 > $1 \u108e ; 38$ukinzi ($consonant) \u102D > $1 \u108b ; 39$ukinzi ($consonant) \u102E > $1 \u108C ; 40$ukinzi ($consonant) \u1036 > $1 \u108D ; 41$ukinzi ($consonant) \u1031 > $1 \u1031 \u1064 ; 42$ukinzi ($consonant) \u103B \u102D \u102F > $1 \u103A \u1033 \u108B ; 43$ukinzi ($consonant) \u103B \u102D > $1 \u103A \u108b ; 44$ukinzi ($consonant) \u103B \u102E \u102F > $1 \u103A \u108C \u1033 ; 45$ukinzi ($consonant) \u103B \u102E > $1 \u103A \u108C ; 46$ukinzi ($consonant) \u103B \u1036 > $1 \u103A \u108D ; 47$ukinzi ($consonant) \u103c > $1 \u103b \u1064; # Kinzi + medial ra 48$ukinzi \u102D > \u108B ; 49$ukinzi \u102E > \u108C ; 50$ukinzi \u1036 > \u108D ; 51$ukinzi ($consonant) > $1 \u1064 ; 52\u1025 ($vowelsign) \u1038 > \u106A $1 \u1038 ; 53\u1025 \u102f \u1036 > \u1025 \u1036 \u1033 ; 54\u102D \u1036 > \u108E ; 55# Some composed lower output 56\u103d \u103e > \u108a ; 57\u103e \u102f > \u1088 ; 58\u103E \u1030 > \u1089 ; 59\u103A > \u1039 ; 60\u103B > \u103A ; 61\u103C > \u103B ; 62\u103D > \u103C ; 63\u103E > \u103D ; 64\u103F > \u1086 ; 65([\u1019]) \u103e \u1030 > $1 \u103d \u1034; # A special case with signs. 66\u102B \u103A > \u105A ; 67\u1039 \u1010 \u103d > \u1096 ; # Very special case 68\u1039 \u1000 > \u1060 ; 69\u1039 \u1001 > \u1061 ; 70\u1039 \u1002 > \u1062 ; 71\u1039 \u1003 > \u1063 ; 72\u1039 \u1005 > \u1065 ; 73\u1039 \u1006 > \u1067 ; 74\u1039 \u1007 > \u1068 ; 75\u1039 \u1008 > \u1069 ; 76\u1039 \u100B > \u106C ; 77\u1039 \u100C > \u106D ; 78\u1039 \u100D > \u106E ; 79\u100d \u1039 \u100E > \u106F ; 80\u1039 \u100E > \u106F ; 81\u1039 \u100F > \u1070 ; 82\u1039 \u1010 > \u1072 ; 83\u1039 \u1011 > \u1074 ; 84\u1039 \u1012 > \u1075 ; 85\u1039 \u1013 > \u1076 ; 86\u1039 \u1014 > \u1077 ; 87\u1039 \u1015 > \u1078 ; 88\u1039 \u1016 > \u1079 ; 89\u1039 \u1017 > \u107A ; 90\u1039 \u1018 > \u1093 ; 91\u1039 \u1019 > \u107C ; 92\u1039 \u101C > \u1085 ; 93\u100d\u1039\u100D > \u106E ; 94\u100F\u1039\u100D > \u1091 ; 95\u100B\u1039\u100C > \u1092 ; 96\u100B\u1039\u100B > \u1097 ; 97\u104E\u1004\u103A\u1038 > \u104E ; 98#### PHASE 1: Everything is now in Zawgyi code points. REORDERING RULES. 99::Null; 100# E Vowel + medial ra. Move the e vowel 101($consonant) \u103b \u1031 > \u1031 \u103b $1 ; 102($consonant) \u103b > \u103b $1 ; 103($consonant) \u103d \u1031 \u1037 > \u1031 $1 \u1094 \u103D ; 104($consonant) (\u108a) \u1031 > \u1031 $1 $2 ; 105($consonant) ([\u103a\u103d\u103e]+) \u1031 > \u1031 $1 $2 ; 106# Ra + kinzi 107($consonant) \u1064 \u103b > \u103b $1 \u1064 ; 108# E vowel plus medials 109($consonant) ([\u103a\u103c-\u103d]) \u1031 > \u1031 $1 $2 ; 110# No medials intervening. 111($vowelsAndConsonants) \u1031 > \u1031 $1 ; 112# Handle Na with lower modifiers. 113\u1014 ($subscriptitem) > \u108f $1 ; 114\u1014 ($lowsignZ) ($highsignZ) \u1037 > \u108f $1 $2 \u1094; 115\u1014 ($highsignZ) ($lowsignZ) \u1037 > \u108f $1 $2 \u1094; 116\u1014 ($highsignZ) \u1037 > \u1014 $1 \u1094; 117# Two medials 118\u103a \u103c > \u107d \u103c; 119# a special case 120\u1014 \u1032 \u1037 > \u1014 \u1032 \u1094; 121\u1014 \u1037 > \u1014 \u1094; 122\u1014 \u1032 ($lowsignZ) \u1037 > \u108f $1 \u1032 \u1094; 123\u1014 ($highsignZ) ($lowsignZ) > \u108f $1 $2; 124\u1014 ($lowsignZ) ($highsignZ) > \u108f $1 $2; 125\u1014 ($lowsignZ) \u1037 > \u108f $1 \u1094; 126\u1014 ($lowsignZ) > \u108f $1; 127# Move 1037 dot to right with other descenders. 128($lowsignZ) ($highsignZ*) \u1037 > $1 $2 \u1094; 129($nondigits) \u1040 ([\u102B-\u103F]) > $1 \u101D $2; 130# Handle lack of 104E ၎ MYANMAR SYMBOL AFOREMENTIONED 131($nondigits) \u104e > $1 \u1044; 132\u1031 \u1040 ($nondigits) > \u1031 \u101D $1; 133\u1009 \u103A > \u1025 \u103A; 134\u1025 \u102E > \u1026; 135\u1037 \u103A > \u103A \u1037; 136([\u102B\u102C\u102F\u1030]) ([\u102D\u102E\u1032]) > $2 $1; 137# Medial plus vowel sign U 138($medialraZ) ($consonant) \u102f > $1 $2 \u1033; 139## Phase 2: Further adjustments 140::Null; 141# Handle consonant, subscripted consonant, medial ra 142($narrowconsonant) ($subscriptitem) ($highsignZ) $medialraZ > \u1083 $1 $2 $3 ; 143($wideconsonant) ($subscriptitem) ($highsignZ) $medialraZ > \u1084 $1 $2 ; 144($narrowconsonant) ($subscriptitem) $medialraZ > \u1081 $1 $2 ; 145($wideconsonant) ($subscriptitem) $medialraZ > \u1082 $1 $2 ; 146\u103c \u1094 > \u103c \u1095 ; 147# Medial ra variations, context dependent 148$medialraZ ($narrowconsonant) \u102d \u103d \u102f > \u107f $1 \u102d \u1087 \u1083 ; 149$medialraZ ($wideconsonant) \u102d \u103d \u102f > \u1080 $1 \u102d \u1087 \u1083 ; 150$medialraZ ($narrowconsonant) ($lowsignZ) ($highsignZ) > \u1083 $1 $2 $3 ; 151$medialraZ ($wideconsonant) ($lowsignZ) ($highsignZ) > \u1084 $1 $2 $3 ; 152$medialraZ ($narrowconsonant) ($highsignZ) > \u107f $1 $2 ; 153$medialraZ ($wideconsonant) ($highsignZ) > \u1080 $1 $2 ; 154$medialraZ ($narrowconsonant) \u1030 > \u103b $1 \u1034 ; 155$medialraZ ($wideconsonant) \u1030 > \u107e $1 \u1034 ; 156$medialraZ ($narrowconsonant) (\u102f) > \u103b $1 \u1033 ; 157$medialraZ ($wideconsonant) (\u102f) > \u107e $1 \u1033 ; 158$medialraZ ($narrowconsonant) ($lowsignZ) > \u1081 $1 $2 ; 159$medialraZ ($wideconsonant) ($lowsignZ) > \u1082 $1 $2 ; 160$medialraZ ($widenya) > \u1082 $1 ; 161$medialraZ ($othernya) > \u103b \u106a ; 162$medialraZ ($narrowconsonant) > \u103b $1 ; 163$medialraZ ($wideconsonant) > \u107e $1 ; 164\u1009 ($lowsignZ) > \u106a $1; 165\u100A ($lowsignZ)> \u106B $1 ; ## NYA and NNYA 166\u103d \u102d > \u102d \u103d; 167\u103a ($highsignZ) \u102f [\u1037\u1094\u1095] > \u103a $1 \u1033 \u1095; 168\u103a \u102f [\u1037\u1094\u1095] > \u103a \u1033 \u1095; 169\u103a \u102f > \u103a \u1033; 170# Kinzi combo 171\u1064 \u102e > \u108c ; 172##### Phase 3 173::Null; 174([\u103C\u103D\u103E]+) \u103B > \u103B $1; 175([\u103D\u103E]+) \u103C > \u103C $1; 176\u103E\u103D > \u103D\u103E ; 177\u1037 ([\u102D-\u1030\u1032\u1036]) > $1 \u1037; 178($consonant) ([\u102B-\u1032\u1036\u103B-\u103E]) \u103A ($consonant)> $1 \u103A $2 $3; 179# Combine vowel and consonant signs 180\u103d \u102f > \u1088; 181\u1033 \u1094 > \u1033 \u1095; # Wider spacing on lower dot 182($medialraZ) ($consonant) ($highsignZ) \u102f > $1 $2 $3 \u1033; 183##### Phase 4. More reorderings of medials 184::Null; 185([\u103D\u103E]) \u103C > \u103C $1; 186\u103E\u103D > \u103D\u103E ; 187\u1038 ($vowelmedial) > $1 \u1038; 188\u1038 ([\u1036\u1037\u103A]) > $1 \u1038; 189\u1036 \u102f > \u102f \u1036; 190\u103a ([\u1064\u108b-\u108e]) \u102d \u102f > \u103a $1 \u102d \u1033; 191\u103a \u102d \u102f > \u103a \u102d \u1033; 192#### Phase 5 193::Null; 194($consonant) \u103B \u103A > $1 \u103A \u103B; 195([\u103C\u103D\u103E]) \u103B > \u103B $1; 196([\u103D\u103E]) \u103C > \u103C $1; 197\u103E\u103D > \u103D\u103E ; 198([\u102D-\u1030\u1032]) \u103A ($consonant) \u103A > $1 $2 \u103A; 199\u102D \u103A > \u102D; 200\u102E \u103A > \u102E; 201\u102F \u103A > \u102F; 202\u102D \u102E > \u102E; 203\u102F \u1030 > \u102F; 204\u102B \u102B+ > \u102B; 205\u102C \u102C+ > \u102C; 206\u102D \u102D+ > \u102D; 207\u102E \u102E+ > \u102E; 208\u102F \u102F+ > \u102F; 209\u1030 \u1030+ > \u1030; 210\u1031 \u1031+ > \u1031; 211\u1032 \u1032+ > \u1032; 212\u1036 \u1036+ > \u1036; 213\u103A \u103A+ > \u103A; 214\u103B \u103B+ > \u103B; 215\u103C \u103C+ > \u103C; 216\u103D \u103D+ > \u103D; 217\u103E \u103E+ > \u103E; 218# Visually identical orderings - standardize 219\u102f \u102D > \u102D \u102f ; 220\u102f \u1036 > \u1036 \u102f ; 221\u1039 \u1037 > \u1037 \u1039 ; 222\u103c \u1032 > \u1032 \u103c ; 223\u103c \u102e > \u102e \u103c ; 224\u103d \u1088 > \u1088 ; 225 226