summaryrefslogtreecommitdiffstats
path: root/intl/icu/source/data/translit/my_Zawgyi.txt
blob: 52367557c641b93f9a71c39d45eea23351b181c6 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
# © 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 and 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\u103c\u103d\u1087-\u108a];
$highsignZ = [\u102d\u102e\u1032\u1036\u1039\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 > $1 \u103d \u1034;  # A special case with signs.
\u102B \u103A > \u105A ;
\u1039 \u1010 \u103d > \u1096 ; # Very special case
\u1039 \u1000 > \u1060 ;
\u1039 \u1001 > \u1061 ;
\u1039 \u1002 > \u1062 ;
\u1039 \u1003 > \u1063 ;
\u1039 \u1005 > \u1065 ;
\u1039 \u1006 > \u1067 ;
\u1039 \u1007 > \u1068 ;
\u1039 \u1008 > \u1069 ;
\u1039 \u100B > \u106C ;
\u1039 \u100C > \u106D ;
\u1039 \u100F > \u1070 ;
\u1039 \u1010 > \u1072 ;
\u1039 \u1011 > \u1074 ;
\u1039 \u1012 > \u1075 ;
\u1039 \u1013 > \u1076 ;
\u1039 \u1014 > \u1077 ;
\u1039 \u1015 > \u1078 ;
\u1039 \u1016 > \u1079 ;
\u1039 \u1017 > \u107A ;
\u1039 \u1018 > \u1093 ;
\u1039 \u1019 > \u107C ;
\u1039 \u101C > \u1085 ;
\u100d\u1039\u100D > \u106E ;
\u100d\u1039\u100E > \u106F ;
\u100F\u1039\u100D > \u1091 ;
\u100B\u1039\u100C > \u1092 ;
\u100B\u1039\u100B > \u1097 ;
\u104E\u1004\u103A\u1038 > \u104E ;
#### PHASE 1: Everything is now in Zawgyi code points. REORDERING RULES.
::Null;
# Handle Na with lower modifiers, medial ra.
\u1014 ($subscriptitem) ($highsignZ*) \u103b > \u103b \u108f $1 $2;
\u1014 \u103b ([\u103c\u103d]*) (\u1031*) > $2 \u103b \u108f $1;
# E Vowel + medial ra. Move the e vowel
($consonant) \u103b ([\u103c\u103d]*) \u1031 > \u1031 \u103b $1 $2;
($consonant) \u103b > \u103b $1 ;
($consonant) \u103d \u1031 \u1037 > \u1031 $1 \u1094 \u103D ;
($consonant) (\u108a) \u1031 > \u1031 $1 $2 ;
# Ra + kinzi
($consonant) \u1064 \u103b > \u103b $1 \u1064 ;
# E vowel plus medials
($consonant) ([\u103a\u103c-\u103d]+) \u1031 > \u1031 $1 $2 ;
# Handle consonant, subscripted consonant, medial ra
($consonant) ($subscriptitem) ($highsignZ*) \u103b > \u103b $1 $2 $3 ;
# No medials intervening.
($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 $1 \u1094;
# a special case
\u1014 \u1032 \u1037 > \u1014 \u1032 \u1094;
\u1014 \u1037 > \u1014 \u1094;
\u1014 \u1032 ($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;
## Phase 2: Further adjustments
::Null;
# Two medials
\u103a \u103c > \u103c \u107d;
\u103c \u1094 > \u103c \u1095 ;
# Medial ra variations, context dependent
$medialraZ ($narrowconsonant) ($subscriptitem) ($highsignZ) > \u1083 $1 $2 $3 ;
$medialraZ ($wideconsonant) ($subscriptitem) ($highsignZ) > \u1084 $1 $2 $3;
$medialraZ ($narrowconsonant) ($subscriptitem) > \u1081 $1 $2 ;
$medialraZ ($wideconsonant) ($subscriptitem) > \u1082 $1 $2 ;
$medialraZ ($narrowconsonant) ([\u103c\u108a]) ($highsignZ) > \u1083 $1 $2 $3 ;
$medialraZ ($wideconsonant) ([\u103c\u108a]) ($highsignZ) > \u1084 $1 $2 $3 ;
$medialraZ ($narrowconsonant) \u103d ($highsignZ) > \u107f $1 \u1087 $2;
$medialraZ ($wideconsonant) \u103d ($highsignZ) > \u1080 $1 \u1087 $2;
$medialraZ ($narrowconsonant) \u102f ($highsignZ) > \u107f $1 \u1033 $2;
$medialraZ ($wideconsonant) \u102f ($highsignZ) > \u1080 $1 \u1033 $2;
$medialraZ ($narrowconsonant) \u1030 ($highsignZ) > \u107f $1 \u1034 $2;
$medialraZ ($wideconsonant) \u1030 ($highsignZ) > \u1080 $1 \u1034 $2;
$medialraZ ($narrowconsonant) ($lowsignZ*) ($highsignZ) > \u107f $1 $2 $3;
$medialraZ ($wideconsonant) ($lowsignZ*) ($highsignZ) > \u1080 $1 $2 $3;
$medialraZ ($narrowconsonant) ([\u103c\u108a]) > \u1081 $1 $2 ;
$medialraZ ($wideconsonant) ([\u103c\u108a]) > \u1082 $1 $2 ;
$medialraZ ($narrowconsonant) \u103d > \u103b $1 \u1087;
$medialraZ ($wideconsonant) \u103d > \u107e $1 \u1087;
$medialraZ ($narrowconsonant) \u102f > \u103b $1 \u1033;
$medialraZ ($wideconsonant) \u102f > \u107e $1 \u1033;
$medialraZ ($narrowconsonant) \u1030 > \u103b $1 \u1034;
$medialraZ ($wideconsonant) \u1030 > \u107e $1 \u1034;
$medialraZ ($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;
\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) ($narrowconsonant) ($lowsignZ*) ($highsignZ*) \u102f > $1 $2 $3 $4 \u1033;
($medialraZ) ($wideconsonant) ($lowsignZ*) ($highsignZ*) \u102f > $1 $2 $3 $4 \u1033;
($medialraZ) ($narrowconsonant) ($lowsignZ*) ($highsignZ*) \u1030 > $1 $2 $3 $4 \u1034;
($medialraZ) ($wideconsonant) ($lowsignZ*) ($highsignZ*) \u1030 > $1 $2 $3 $4 \u1034;
##### 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;
\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\u1033]) \u102D > \u102D $1 ;
([\u102f\u1033]) \u1036 > \u1036 $1 ;
\u1037 \u1039 > \u1039 \u1037;
\u1032 \u103c > \u103c \u1032 ;
\u102e \u103c > \u103c \u102e ;
\u103d \u1088 > \u1088 ;