cldr-segments-full 43.0.0 → 44.0.0-BETA2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +32 -39
- package/bower.json +2 -2
- package/package.json +2 -2
- package/segments/de/suppressions.json +1 -1
- package/segments/el/suppressions.json +1 -1
- package/segments/en/suppressions.json +1 -1
- package/segments/es/suppressions.json +1 -1
- package/segments/fi/suppressions.json +2 -2
- package/segments/fr/suppressions.json +1 -1
- package/segments/it/suppressions.json +1 -1
- package/segments/ja/suppressions.json +5 -5
- package/segments/pt/suppressions.json +1 -1
- package/segments/ru/suppressions.json +1 -1
- package/segments/sv/suppressions.json +2 -2
- package/segments/und/suppressions.json +171 -114
- package/segments/zh/suppressions.json +3 -3
- package/segments/zh-Hant/suppressions.json +3 -3
package/LICENSE
CHANGED
|
@@ -1,46 +1,39 @@
|
|
|
1
|
-
|
|
1
|
+
UNICODE LICENSE V3
|
|
2
2
|
|
|
3
|
-
|
|
4
|
-
for definitions of Unicode Inc.’s Data Files and Software.
|
|
3
|
+
COPYRIGHT AND PERMISSION NOTICE
|
|
5
4
|
|
|
6
|
-
|
|
7
|
-
BY DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING UNICODE INC.'S
|
|
8
|
-
DATA FILES ("DATA FILES"), AND/OR SOFTWARE ("SOFTWARE"),
|
|
9
|
-
YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
|
|
10
|
-
TERMS AND CONDITIONS OF THIS AGREEMENT.
|
|
11
|
-
IF YOU DO NOT AGREE, DO NOT DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE
|
|
12
|
-
THE DATA FILES OR SOFTWARE.
|
|
5
|
+
Copyright © 2004-2023 Unicode, Inc.
|
|
13
6
|
|
|
14
|
-
|
|
7
|
+
NOTICE TO USER: Carefully read the following legal agreement. BY
|
|
8
|
+
DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING DATA FILES, AND/OR
|
|
9
|
+
SOFTWARE, YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
|
|
10
|
+
TERMS AND CONDITIONS OF THIS AGREEMENT. IF YOU DO NOT AGREE, DO NOT
|
|
11
|
+
DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE THE DATA FILES OR SOFTWARE.
|
|
15
12
|
|
|
16
|
-
|
|
17
|
-
|
|
13
|
+
Permission is hereby granted, free of charge, to any person obtaining a
|
|
14
|
+
copy of data files and any associated documentation (the "Data Files") or
|
|
15
|
+
software and any associated documentation (the "Software") to deal in the
|
|
16
|
+
Data Files or Software without restriction, including without limitation
|
|
17
|
+
the rights to use, copy, modify, merge, publish, distribute, and/or sell
|
|
18
|
+
copies of the Data Files or Software, and to permit persons to whom the
|
|
19
|
+
Data Files or Software are furnished to do so, provided that either (a)
|
|
20
|
+
this copyright and permission notice appear with all copies of the Data
|
|
21
|
+
Files or Software, or (b) this copyright and permission notice appear in
|
|
22
|
+
associated Documentation.
|
|
18
23
|
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
without restriction, including without limitation the rights to use,
|
|
24
|
-
copy, modify, merge, publish, distribute, and/or sell copies of
|
|
25
|
-
the Data Files or Software, and to permit persons to whom the Data Files
|
|
26
|
-
or Software are furnished to do so, provided that either
|
|
27
|
-
(a) this copyright and permission notice appear with all copies
|
|
28
|
-
of the Data Files or Software, or
|
|
29
|
-
(b) this copyright and permission notice appear in associated
|
|
30
|
-
Documentation.
|
|
24
|
+
THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
|
|
25
|
+
KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
26
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
|
|
27
|
+
THIRD PARTY RIGHTS.
|
|
31
28
|
|
|
32
|
-
|
|
33
|
-
ANY
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
IN
|
|
37
|
-
|
|
38
|
-
DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
|
|
39
|
-
DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
|
|
40
|
-
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
|
|
41
|
-
PERFORMANCE OF THE DATA FILES OR SOFTWARE.
|
|
29
|
+
IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE
|
|
30
|
+
BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES,
|
|
31
|
+
OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
|
|
32
|
+
WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
|
|
33
|
+
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE DATA
|
|
34
|
+
FILES OR SOFTWARE.
|
|
42
35
|
|
|
43
|
-
Except as contained in this notice, the name of a copyright holder
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
36
|
+
Except as contained in this notice, the name of a copyright holder shall
|
|
37
|
+
not be used in advertising or otherwise to promote the sale, use or other
|
|
38
|
+
dealings in these Data Files or Software without prior written
|
|
39
|
+
authorization of the copyright holder.
|
package/bower.json
CHANGED
package/package.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "cldr-segments-full",
|
|
3
|
-
"version": "
|
|
3
|
+
"version": "44.0.0-BETA2",
|
|
4
4
|
"peerDependencies": {
|
|
5
|
-
"cldr-core": "
|
|
5
|
+
"cldr-core": "44.0.0-BETA2"
|
|
6
6
|
},
|
|
7
7
|
"description": "Text Segmentation data (all locales)",
|
|
8
8
|
"homepage": "https://cldr.unicode.org",
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"segments": {
|
|
3
3
|
"identity": {
|
|
4
4
|
"version": {
|
|
5
|
-
"_cldrVersion": "
|
|
5
|
+
"_cldrVersion": "44"
|
|
6
6
|
},
|
|
7
7
|
"language": "fi"
|
|
8
8
|
},
|
|
@@ -10,7 +10,7 @@
|
|
|
10
10
|
"WordBreak": {
|
|
11
11
|
"variables": [
|
|
12
12
|
{
|
|
13
|
-
"$MidLetter": "
|
|
13
|
+
"$MidLetter": "\\p{Word_Break=MidLetter}"
|
|
14
14
|
}
|
|
15
15
|
]
|
|
16
16
|
}
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"segments": {
|
|
3
3
|
"identity": {
|
|
4
4
|
"version": {
|
|
5
|
-
"_cldrVersion": "
|
|
5
|
+
"_cldrVersion": "44"
|
|
6
6
|
},
|
|
7
7
|
"language": "ja"
|
|
8
8
|
},
|
|
@@ -10,23 +10,23 @@
|
|
|
10
10
|
"LineBreak": {
|
|
11
11
|
"variables": [
|
|
12
12
|
{
|
|
13
|
-
"$ID": "[[
|
|
13
|
+
"$ID": "[[\\p{Line_Break=Ideographic}] [$CJ]]"
|
|
14
14
|
},
|
|
15
15
|
{
|
|
16
|
-
"$NS": "
|
|
16
|
+
"$NS": "\\p{Line_Break=Nonstarter}"
|
|
17
17
|
}
|
|
18
18
|
]
|
|
19
19
|
},
|
|
20
20
|
"WordBreak": {
|
|
21
21
|
"variables": [
|
|
22
22
|
{
|
|
23
|
-
"$Hiragana": "
|
|
23
|
+
"$Hiragana": "\\p{Hiragana}"
|
|
24
24
|
},
|
|
25
25
|
{
|
|
26
26
|
"$Hiragana": "($Hiragana $FE*)"
|
|
27
27
|
},
|
|
28
28
|
{
|
|
29
|
-
"$Ideographic": "[[
|
|
29
|
+
"$Ideographic": "[[\\p{Ideographic}] [\\u3005 \\u3007 \\u303B]]"
|
|
30
30
|
},
|
|
31
31
|
{
|
|
32
32
|
"$Ideographic": "($Ideographic $FE*)"
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"segments": {
|
|
3
3
|
"identity": {
|
|
4
4
|
"version": {
|
|
5
|
-
"_cldrVersion": "
|
|
5
|
+
"_cldrVersion": "44"
|
|
6
6
|
},
|
|
7
7
|
"language": "sv"
|
|
8
8
|
},
|
|
@@ -10,7 +10,7 @@
|
|
|
10
10
|
"WordBreak": {
|
|
11
11
|
"variables": [
|
|
12
12
|
{
|
|
13
|
-
"$MidLetter": "
|
|
13
|
+
"$MidLetter": "\\p{Word_Break=MidLetter}"
|
|
14
14
|
}
|
|
15
15
|
]
|
|
16
16
|
}
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"segments": {
|
|
3
3
|
"identity": {
|
|
4
4
|
"version": {
|
|
5
|
-
"_cldrVersion": "
|
|
5
|
+
"_cldrVersion": "44"
|
|
6
6
|
},
|
|
7
7
|
"language": "root"
|
|
8
8
|
},
|
|
@@ -10,55 +10,58 @@
|
|
|
10
10
|
"GraphemeClusterBreak": {
|
|
11
11
|
"variables": [
|
|
12
12
|
{
|
|
13
|
-
"$CR": "
|
|
13
|
+
"$CR": "\\p{Grapheme_Cluster_Break=CR}"
|
|
14
14
|
},
|
|
15
15
|
{
|
|
16
|
-
"$LF": "
|
|
16
|
+
"$LF": "\\p{Grapheme_Cluster_Break=LF}"
|
|
17
17
|
},
|
|
18
18
|
{
|
|
19
|
-
"$Control": "
|
|
19
|
+
"$Control": "\\p{Grapheme_Cluster_Break=Control}"
|
|
20
20
|
},
|
|
21
21
|
{
|
|
22
|
-
"$Extend": "
|
|
22
|
+
"$Extend": "\\p{Grapheme_Cluster_Break=Extend}"
|
|
23
23
|
},
|
|
24
24
|
{
|
|
25
|
-
"$ZWJ": "
|
|
25
|
+
"$ZWJ": "\\p{Grapheme_Cluster_Break=ZWJ}"
|
|
26
26
|
},
|
|
27
27
|
{
|
|
28
|
-
"$RI": "
|
|
28
|
+
"$RI": "\\p{Grapheme_Cluster_Break=Regional_Indicator}"
|
|
29
29
|
},
|
|
30
30
|
{
|
|
31
|
-
"$Prepend": "
|
|
31
|
+
"$Prepend": "\\p{Grapheme_Cluster_Break=Prepend}"
|
|
32
32
|
},
|
|
33
33
|
{
|
|
34
|
-
"$SpacingMark": "
|
|
34
|
+
"$SpacingMark": "\\p{Grapheme_Cluster_Break=SpacingMark}"
|
|
35
35
|
},
|
|
36
36
|
{
|
|
37
|
-
"$L": "
|
|
37
|
+
"$L": "\\p{Grapheme_Cluster_Break=L}"
|
|
38
38
|
},
|
|
39
39
|
{
|
|
40
|
-
"$V": "
|
|
40
|
+
"$V": "\\p{Grapheme_Cluster_Break=V}"
|
|
41
41
|
},
|
|
42
42
|
{
|
|
43
|
-
"$T": "
|
|
43
|
+
"$T": "\\p{Grapheme_Cluster_Break=T}"
|
|
44
44
|
},
|
|
45
45
|
{
|
|
46
|
-
"$LV": "
|
|
46
|
+
"$LV": "\\p{Grapheme_Cluster_Break=LV}"
|
|
47
47
|
},
|
|
48
48
|
{
|
|
49
|
-
"$LVT": "
|
|
49
|
+
"$LVT": "\\p{Grapheme_Cluster_Break=LVT}"
|
|
50
50
|
},
|
|
51
51
|
{
|
|
52
|
-
"$
|
|
52
|
+
"$ConjunctLinkingScripts": "[\\p{Gujr}\\p{sc=Telu}\\p{sc=Mlym}\\p{sc=Orya}\\p{sc=Beng}\\p{sc=Deva}]"
|
|
53
53
|
},
|
|
54
54
|
{
|
|
55
|
-
"$
|
|
55
|
+
"$ConjunctLinker": "\\p{Indic_Conjunct_Break=Linker}"
|
|
56
56
|
},
|
|
57
57
|
{
|
|
58
|
-
"$
|
|
58
|
+
"$LinkingConsonant": "\\p{Indic_Conjunct_Break=Consonant}"
|
|
59
59
|
},
|
|
60
60
|
{
|
|
61
|
-
"$
|
|
61
|
+
"$ExtPict": "\\p{Extended_Pictographic}"
|
|
62
|
+
},
|
|
63
|
+
{
|
|
64
|
+
"$ExtCccZwj": "[\\p{Indic_Conjunct_Break=Linker}\\p{Indic_Conjunct_Break=Extend}]"
|
|
62
65
|
}
|
|
63
66
|
],
|
|
64
67
|
"segmentRules": {
|
|
@@ -71,7 +74,7 @@
|
|
|
71
74
|
"9": " × ($Extend | $ZWJ) ",
|
|
72
75
|
"9.1": " × $SpacingMark ",
|
|
73
76
|
"9.2": " $Prepend × ",
|
|
74
|
-
"9.3": " $LinkingConsonant $ExtCccZwj* $
|
|
77
|
+
"9.3": " $LinkingConsonant $ExtCccZwj* $ConjunctLinker $ExtCccZwj* × $LinkingConsonant ",
|
|
75
78
|
"11": " $ExtPict $Extend* $ZWJ × $ExtPict ",
|
|
76
79
|
"12": " ^ ($RI $RI)* $RI × $RI ",
|
|
77
80
|
"13": " [^$RI] ($RI $RI)* $RI × $RI "
|
|
@@ -80,145 +83,175 @@
|
|
|
80
83
|
"LineBreak": {
|
|
81
84
|
"variables": [
|
|
82
85
|
{
|
|
83
|
-
"$AI": "
|
|
86
|
+
"$AI": "\\p{Line_Break=Ambiguous}"
|
|
87
|
+
},
|
|
88
|
+
{
|
|
89
|
+
"$AK": "\\p{Line_Break=Aksara}"
|
|
84
90
|
},
|
|
85
91
|
{
|
|
86
|
-
"$AL": "
|
|
92
|
+
"$AL": "\\p{Line_Break=Alphabetic}"
|
|
87
93
|
},
|
|
88
94
|
{
|
|
89
|
-
"$
|
|
95
|
+
"$AP": "\\p{Line_Break=Aksara_Prebase}"
|
|
90
96
|
},
|
|
91
97
|
{
|
|
92
|
-
"$
|
|
98
|
+
"$AS": "\\p{Line_Break=Aksara_Start}"
|
|
93
99
|
},
|
|
94
100
|
{
|
|
95
|
-
"$
|
|
101
|
+
"$B2": "\\p{Line_Break=Break_Both}"
|
|
96
102
|
},
|
|
97
103
|
{
|
|
98
|
-
"$
|
|
104
|
+
"$BA": "\\p{Line_Break=Break_After}"
|
|
99
105
|
},
|
|
100
106
|
{
|
|
101
|
-
"$
|
|
107
|
+
"$BB": "\\p{Line_Break=Break_Before}"
|
|
102
108
|
},
|
|
103
109
|
{
|
|
104
|
-
"$
|
|
110
|
+
"$BK": "\\p{Line_Break=Mandatory_Break}"
|
|
105
111
|
},
|
|
106
112
|
{
|
|
107
|
-
"$
|
|
113
|
+
"$CB": "\\p{Line_Break=Contingent_Break}"
|
|
108
114
|
},
|
|
109
115
|
{
|
|
110
|
-
"$
|
|
116
|
+
"$CL": "\\p{Line_Break=Close_Punctuation}"
|
|
111
117
|
},
|
|
112
118
|
{
|
|
113
|
-
"$
|
|
119
|
+
"$CP": "\\p{Line_Break=CP}"
|
|
114
120
|
},
|
|
115
121
|
{
|
|
116
|
-
"$
|
|
122
|
+
"$CM1": "\\p{Line_Break=Combining_Mark}"
|
|
117
123
|
},
|
|
118
124
|
{
|
|
119
|
-
"$
|
|
125
|
+
"$CR": "\\p{Line_Break=Carriage_Return}"
|
|
120
126
|
},
|
|
121
127
|
{
|
|
122
|
-
"$
|
|
128
|
+
"$EX": "\\p{Line_Break=Exclamation}"
|
|
123
129
|
},
|
|
124
130
|
{
|
|
125
|
-
"$
|
|
131
|
+
"$GL": "\\p{Line_Break=Glue}"
|
|
126
132
|
},
|
|
127
133
|
{
|
|
128
|
-
"$
|
|
134
|
+
"$H2": "\\p{Line_Break=H2}"
|
|
129
135
|
},
|
|
130
136
|
{
|
|
131
|
-
"$
|
|
137
|
+
"$H3": "\\p{Line_Break=H3}"
|
|
132
138
|
},
|
|
133
139
|
{
|
|
134
|
-
"$
|
|
140
|
+
"$HL": "\\p{Line_Break=HL}"
|
|
135
141
|
},
|
|
136
142
|
{
|
|
137
|
-
"$
|
|
143
|
+
"$HY": "\\p{Line_Break=Hyphen}"
|
|
138
144
|
},
|
|
139
145
|
{
|
|
140
|
-
"$
|
|
146
|
+
"$ID": "\\p{Line_Break=Ideographic}"
|
|
141
147
|
},
|
|
142
148
|
{
|
|
143
|
-
"$
|
|
149
|
+
"$IN": "\\p{Line_Break=Inseparable}"
|
|
144
150
|
},
|
|
145
151
|
{
|
|
146
|
-
"$
|
|
152
|
+
"$IS": "\\p{Line_Break=Infix_Numeric}"
|
|
147
153
|
},
|
|
148
154
|
{
|
|
149
|
-
"$
|
|
155
|
+
"$JL": "\\p{Line_Break=JL}"
|
|
150
156
|
},
|
|
151
157
|
{
|
|
152
|
-
"$
|
|
158
|
+
"$JT": "\\p{Line_Break=JT}"
|
|
153
159
|
},
|
|
154
160
|
{
|
|
155
|
-
"$
|
|
161
|
+
"$JV": "\\p{Line_Break=JV}"
|
|
156
162
|
},
|
|
157
163
|
{
|
|
158
|
-
"$
|
|
164
|
+
"$LF": "\\p{Line_Break=Line_Feed}"
|
|
159
165
|
},
|
|
160
166
|
{
|
|
161
|
-
"$
|
|
167
|
+
"$NL": "\\p{Line_Break=Next_Line}"
|
|
162
168
|
},
|
|
163
169
|
{
|
|
164
|
-
"$
|
|
170
|
+
"$NS": "\\p{Line_Break=Nonstarter}"
|
|
165
171
|
},
|
|
166
172
|
{
|
|
167
|
-
"$
|
|
173
|
+
"$NU": "\\p{Line_Break=Numeric}"
|
|
168
174
|
},
|
|
169
175
|
{
|
|
170
|
-
"$
|
|
176
|
+
"$OP": "\\p{Line_Break=Open_Punctuation}"
|
|
171
177
|
},
|
|
172
178
|
{
|
|
173
|
-
"$PO": "
|
|
179
|
+
"$PO": "\\p{Line_Break=Postfix_Numeric}"
|
|
174
180
|
},
|
|
175
181
|
{
|
|
176
|
-
"$PR": "
|
|
182
|
+
"$PR": "\\p{Line_Break=Prefix_Numeric}"
|
|
177
183
|
},
|
|
178
184
|
{
|
|
179
|
-
"$QU": "
|
|
185
|
+
"$QU": "\\p{Line_Break=Quotation}"
|
|
180
186
|
},
|
|
181
187
|
{
|
|
182
|
-
"$SA": "
|
|
188
|
+
"$SA": "\\p{Line_Break=Complex_Context}"
|
|
183
189
|
},
|
|
184
190
|
{
|
|
185
|
-
"$SG": "
|
|
191
|
+
"$SG": "\\p{Line_Break=Surrogate}"
|
|
186
192
|
},
|
|
187
193
|
{
|
|
188
|
-
"$SP": "
|
|
194
|
+
"$SP": "\\p{Line_Break=Space}"
|
|
189
195
|
},
|
|
190
196
|
{
|
|
191
|
-
"$SY": "
|
|
197
|
+
"$SY": "\\p{Line_Break=Break_Symbols}"
|
|
192
198
|
},
|
|
193
199
|
{
|
|
194
|
-
"$
|
|
200
|
+
"$VF": "\\p{Line_Break=Virama_Final}"
|
|
195
201
|
},
|
|
196
202
|
{
|
|
197
|
-
"$
|
|
203
|
+
"$VI": "\\p{Line_Break=Virama}"
|
|
198
204
|
},
|
|
199
205
|
{
|
|
200
|
-
"$
|
|
206
|
+
"$WJ": "\\p{Line_Break=Word_Joiner}"
|
|
201
207
|
},
|
|
202
208
|
{
|
|
203
|
-
"$
|
|
209
|
+
"$XX": "\\p{Line_Break=Unknown}"
|
|
204
210
|
},
|
|
205
211
|
{
|
|
206
|
-
"$
|
|
212
|
+
"$ZW": "\\p{Line_Break=ZWSpace}"
|
|
207
213
|
},
|
|
208
214
|
{
|
|
209
|
-
"$
|
|
215
|
+
"$CJ": "\\p{Line_Break=Conditional_Japanese_Starter}"
|
|
210
216
|
},
|
|
211
217
|
{
|
|
212
|
-
"$
|
|
218
|
+
"$RI": "\\p{Line_Break=Regional_Indicator}"
|
|
213
219
|
},
|
|
214
220
|
{
|
|
215
|
-
"$
|
|
221
|
+
"$EB": "\\p{Line_Break=E_Base}"
|
|
216
222
|
},
|
|
217
223
|
{
|
|
218
|
-
"$
|
|
224
|
+
"$EM": "\\p{Line_Break=E_Modifier}"
|
|
219
225
|
},
|
|
220
226
|
{
|
|
221
|
-
"$
|
|
227
|
+
"$ZWJ_O": "\\p{Line_Break=ZWJ}"
|
|
228
|
+
},
|
|
229
|
+
{
|
|
230
|
+
"$ZWJ": "\\p{Line_Break=ZWJ}"
|
|
231
|
+
},
|
|
232
|
+
{
|
|
233
|
+
"$QU_Pi": "[$QU & \\p{gc=Pi}]"
|
|
234
|
+
},
|
|
235
|
+
{
|
|
236
|
+
"$QU_Pf": "[$QU & \\p{gc=Pf}]"
|
|
237
|
+
},
|
|
238
|
+
{
|
|
239
|
+
"$DottedCircle": "◌"
|
|
240
|
+
},
|
|
241
|
+
{
|
|
242
|
+
"$CP30": "[$CP-[\\p{ea=F}\\p{ea=W}\\p{ea=H}]]"
|
|
243
|
+
},
|
|
244
|
+
{
|
|
245
|
+
"$OP30": "[$OP-[\\p{ea=F}\\p{ea=W}\\p{ea=H}]]"
|
|
246
|
+
},
|
|
247
|
+
{
|
|
248
|
+
"$ExtPictUnassigned": "[\\p{Extended_Pictographic}&\\p{gc=Cn}]"
|
|
249
|
+
},
|
|
250
|
+
{
|
|
251
|
+
"$sot": "^"
|
|
252
|
+
},
|
|
253
|
+
{
|
|
254
|
+
"$eot": "(?!.)"
|
|
222
255
|
},
|
|
223
256
|
{
|
|
224
257
|
"$CM": "[$CM1 $ZWJ]"
|
|
@@ -248,14 +281,20 @@
|
|
|
248
281
|
"$Spec4_": "[^ $NU $CM]"
|
|
249
282
|
},
|
|
250
283
|
{
|
|
251
|
-
"$
|
|
284
|
+
"$AI": "($AI $X)"
|
|
252
285
|
},
|
|
253
286
|
{
|
|
254
|
-
"$
|
|
287
|
+
"$AK": "($AK $X)"
|
|
255
288
|
},
|
|
256
289
|
{
|
|
257
290
|
"$AL": "($AL $X)"
|
|
258
291
|
},
|
|
292
|
+
{
|
|
293
|
+
"$AP": "($AP $X)"
|
|
294
|
+
},
|
|
295
|
+
{
|
|
296
|
+
"$AS": "($AS $X)"
|
|
297
|
+
},
|
|
259
298
|
{
|
|
260
299
|
"$B2": "($B2 $X)"
|
|
261
300
|
},
|
|
@@ -274,9 +313,6 @@
|
|
|
274
313
|
{
|
|
275
314
|
"$CP": "($CP $X)"
|
|
276
315
|
},
|
|
277
|
-
{
|
|
278
|
-
"$CP30": "($CP30 $X)"
|
|
279
|
-
},
|
|
280
316
|
{
|
|
281
317
|
"$CM": "($CM $X)"
|
|
282
318
|
},
|
|
@@ -325,9 +361,6 @@
|
|
|
325
361
|
{
|
|
326
362
|
"$OP": "($OP $X)"
|
|
327
363
|
},
|
|
328
|
-
{
|
|
329
|
-
"$OP30": "($OP30 $X)"
|
|
330
|
-
},
|
|
331
364
|
{
|
|
332
365
|
"$PO": "($PO $X)"
|
|
333
366
|
},
|
|
@@ -346,6 +379,12 @@
|
|
|
346
379
|
{
|
|
347
380
|
"$SY": "($SY $X)"
|
|
348
381
|
},
|
|
382
|
+
{
|
|
383
|
+
"$VF": "($VF $X)"
|
|
384
|
+
},
|
|
385
|
+
{
|
|
386
|
+
"$VI": "($VI $X)"
|
|
387
|
+
},
|
|
349
388
|
{
|
|
350
389
|
"$WJ": "($WJ $X)"
|
|
351
390
|
},
|
|
@@ -364,6 +403,21 @@
|
|
|
364
403
|
{
|
|
365
404
|
"$ZWJ": "($ZWJ $X)"
|
|
366
405
|
},
|
|
406
|
+
{
|
|
407
|
+
"$QU_Pi": "($QU_Pi $X)"
|
|
408
|
+
},
|
|
409
|
+
{
|
|
410
|
+
"$QU_Pf": "($QU_Pf $X)"
|
|
411
|
+
},
|
|
412
|
+
{
|
|
413
|
+
"$DottedCircle": "($DottedCircle $X)"
|
|
414
|
+
},
|
|
415
|
+
{
|
|
416
|
+
"$CP30": "($CP30 $X)"
|
|
417
|
+
},
|
|
418
|
+
{
|
|
419
|
+
"$OP30": "($OP30 $X)"
|
|
420
|
+
},
|
|
367
421
|
{
|
|
368
422
|
"$AL": "($AL | ^ $CM | (?<=$Spec1_) $CM)"
|
|
369
423
|
}
|
|
@@ -391,7 +445,8 @@
|
|
|
391
445
|
"13.03": " $Spec4_ $CM+ × ($CL | $CP | $IS | $SY) ",
|
|
392
446
|
"13.04": " ^ $CM+ × ($CL | $CP | $IS | $SY) ",
|
|
393
447
|
"14": " $OP $SP* × ",
|
|
394
|
-
"15": " $QU $SP* ×
|
|
448
|
+
"15.11": " ( $sot | $BK | $CR | $LF | $NL | $OP | $QU | $GL | $SP | $ZW ) $QU_Pi $SP* × ",
|
|
449
|
+
"15.21": " × $QU_Pf ( $SP | $GL | $WJ | $CL | $QU | $CP | $EX | $IS | $SY | $BK | $CR | $LF | $NL | $ZW | $eot ) ",
|
|
395
450
|
"16": " ($CL | $CP) $SP* × $NS ",
|
|
396
451
|
"17": " $B2 $SP* × $B2 ",
|
|
397
452
|
"18": " $SP ÷ ",
|
|
@@ -399,14 +454,13 @@
|
|
|
399
454
|
"19.02": " $QU × ",
|
|
400
455
|
"20.01": " ÷ $CB ",
|
|
401
456
|
"20.02": " $CB ÷ ",
|
|
402
|
-
"20.09": " $Spec5_ $HY × $AL ",
|
|
403
457
|
"21.01": " × $BA ",
|
|
404
458
|
"21.02": " × $HY ",
|
|
405
459
|
"21.03": " × $NS ",
|
|
406
460
|
"21.04": " $BB × ",
|
|
407
461
|
"21.1": " $HL ($HY | $BA) × ",
|
|
408
462
|
"21.2": " $SY × $HL ",
|
|
409
|
-
"22
|
|
463
|
+
"22": " × $IN ",
|
|
410
464
|
"23.02": " ($AL | $HL) × $NU ",
|
|
411
465
|
"23.03": " $NU × ($AL | $HL) ",
|
|
412
466
|
"23.12": " $PR × ($ID | $EB | $EM) ",
|
|
@@ -421,14 +475,17 @@
|
|
|
421
475
|
"26.01": " $JL × $JL | $JV | $H2 | $H3 ",
|
|
422
476
|
"26.02": " $JV | $H2 × $JV | $JT ",
|
|
423
477
|
"26.03": " $JT | $H3 × $JT ",
|
|
424
|
-
"27.01": " $JL | $JV | $JT | $H2 | $H3 × $
|
|
425
|
-
"27.02": " $JL | $JV | $JT | $H2 | $H3
|
|
426
|
-
"27.03": " $PR × $JL | $JV | $JT | $H2 | $H3 ",
|
|
478
|
+
"27.01": " $JL | $JV | $JT | $H2 | $H3 × $PO ",
|
|
479
|
+
"27.02": " $PR × $JL | $JV | $JT | $H2 | $H3 ",
|
|
427
480
|
"28": " ($AL | $HL) × ($AL | $HL) ",
|
|
481
|
+
"28.11": " $AP × ($AK | $DottedCircle | $AS) ",
|
|
482
|
+
"28.12": " ($AK | $DottedCircle | $AS) × ($VF | $VI) ",
|
|
483
|
+
"28.13": " ($AK | $DottedCircle | $AS) $VI × ($AK | $DottedCircle) ",
|
|
484
|
+
"28.14": " ($AK | $DottedCircle | $AS) × ($AK | $DottedCircle | $AS) $VF ",
|
|
428
485
|
"29": " $IS × ($AL | $HL) ",
|
|
429
486
|
"30.01": " ($AL | $HL | $NU) × $OP30 ",
|
|
430
487
|
"30.02": " $CP30 × ($AL | $HL | $NU) ",
|
|
431
|
-
"30.11": "
|
|
488
|
+
"30.11": " $sot ($RI $RI)* $RI × $RI ",
|
|
432
489
|
"30.12": " [^$RI] ($RI $RI)* $RI × $RI ",
|
|
433
490
|
"30.13": " $RI ÷ $RI ",
|
|
434
491
|
"30.21": " $EB × $EM ",
|
|
@@ -438,46 +495,46 @@
|
|
|
438
495
|
"SentenceBreak": {
|
|
439
496
|
"variables": [
|
|
440
497
|
{
|
|
441
|
-
"$CR": "
|
|
498
|
+
"$CR": "\\p{Sentence_Break=CR}"
|
|
442
499
|
},
|
|
443
500
|
{
|
|
444
|
-
"$LF": "
|
|
501
|
+
"$LF": "\\p{Sentence_Break=LF}"
|
|
445
502
|
},
|
|
446
503
|
{
|
|
447
|
-
"$Extend": "
|
|
504
|
+
"$Extend": "\\p{Sentence_Break=Extend}"
|
|
448
505
|
},
|
|
449
506
|
{
|
|
450
|
-
"$Format": "
|
|
507
|
+
"$Format": "\\p{Sentence_Break=Format}"
|
|
451
508
|
},
|
|
452
509
|
{
|
|
453
|
-
"$Sep": "
|
|
510
|
+
"$Sep": "\\p{Sentence_Break=Sep}"
|
|
454
511
|
},
|
|
455
512
|
{
|
|
456
|
-
"$Sp": "
|
|
513
|
+
"$Sp": "\\p{Sentence_Break=Sp}"
|
|
457
514
|
},
|
|
458
515
|
{
|
|
459
|
-
"$Lower": "
|
|
516
|
+
"$Lower": "\\p{Sentence_Break=Lower}"
|
|
460
517
|
},
|
|
461
518
|
{
|
|
462
|
-
"$Upper": "
|
|
519
|
+
"$Upper": "\\p{Sentence_Break=Upper}"
|
|
463
520
|
},
|
|
464
521
|
{
|
|
465
|
-
"$OLetter": "
|
|
522
|
+
"$OLetter": "\\p{Sentence_Break=OLetter}"
|
|
466
523
|
},
|
|
467
524
|
{
|
|
468
|
-
"$Numeric": "
|
|
525
|
+
"$Numeric": "\\p{Sentence_Break=Numeric}"
|
|
469
526
|
},
|
|
470
527
|
{
|
|
471
|
-
"$ATerm": "
|
|
528
|
+
"$ATerm": "\\p{Sentence_Break=ATerm}"
|
|
472
529
|
},
|
|
473
530
|
{
|
|
474
|
-
"$STerm": "
|
|
531
|
+
"$STerm": "\\p{Sentence_Break=STerm}"
|
|
475
532
|
},
|
|
476
533
|
{
|
|
477
|
-
"$Close": "
|
|
534
|
+
"$Close": "\\p{Sentence_Break=Close}"
|
|
478
535
|
},
|
|
479
536
|
{
|
|
480
|
-
"$SContinue": "
|
|
537
|
+
"$SContinue": "\\p{Sentence_Break=SContinue}"
|
|
481
538
|
},
|
|
482
539
|
{
|
|
483
540
|
"$Any": "."
|
|
@@ -539,61 +596,61 @@
|
|
|
539
596
|
"WordBreak": {
|
|
540
597
|
"variables": [
|
|
541
598
|
{
|
|
542
|
-
"$CR": "
|
|
599
|
+
"$CR": "\\p{Word_Break=CR}"
|
|
543
600
|
},
|
|
544
601
|
{
|
|
545
|
-
"$LF": "
|
|
602
|
+
"$LF": "\\p{Word_Break=LF}"
|
|
546
603
|
},
|
|
547
604
|
{
|
|
548
|
-
"$Newline": "
|
|
605
|
+
"$Newline": "\\p{Word_Break=Newline}"
|
|
549
606
|
},
|
|
550
607
|
{
|
|
551
|
-
"$Extend": "
|
|
608
|
+
"$Extend": "\\p{Word_Break=Extend}"
|
|
552
609
|
},
|
|
553
610
|
{
|
|
554
|
-
"$Format": "
|
|
611
|
+
"$Format": "[\\p{Word_Break=Format}]"
|
|
555
612
|
},
|
|
556
613
|
{
|
|
557
|
-
"$Katakana": "
|
|
614
|
+
"$Katakana": "\\p{Word_Break=Katakana}"
|
|
558
615
|
},
|
|
559
616
|
{
|
|
560
|
-
"$ALetter": "
|
|
617
|
+
"$ALetter": "\\p{Word_Break=ALetter}"
|
|
561
618
|
},
|
|
562
619
|
{
|
|
563
|
-
"$MidLetter": "[
|
|
620
|
+
"$MidLetter": "[\\p{Word_Break = MidLetter} - [\\: \\uFE55 \\uFF1A]]"
|
|
564
621
|
},
|
|
565
622
|
{
|
|
566
|
-
"$MidNum": "
|
|
623
|
+
"$MidNum": "\\p{Word_Break=MidNum}"
|
|
567
624
|
},
|
|
568
625
|
{
|
|
569
|
-
"$MidNumLet": "
|
|
626
|
+
"$MidNumLet": "\\p{Word_Break=MidNumLet}"
|
|
570
627
|
},
|
|
571
628
|
{
|
|
572
|
-
"$Numeric": "
|
|
629
|
+
"$Numeric": "\\p{Word_Break=Numeric}"
|
|
573
630
|
},
|
|
574
631
|
{
|
|
575
|
-
"$ExtendNumLet": "
|
|
632
|
+
"$ExtendNumLet": "\\p{Word_Break=ExtendNumLet}"
|
|
576
633
|
},
|
|
577
634
|
{
|
|
578
|
-
"$RI": "
|
|
635
|
+
"$RI": "\\p{Word_Break=Regional_Indicator}"
|
|
579
636
|
},
|
|
580
637
|
{
|
|
581
|
-
"$Hebrew_Letter": "
|
|
638
|
+
"$Hebrew_Letter": "\\p{Word_Break=Hebrew_Letter}"
|
|
582
639
|
},
|
|
583
640
|
{
|
|
584
|
-
"$Double_Quote": "
|
|
641
|
+
"$Double_Quote": "\\p{Word_Break=Double_Quote}"
|
|
585
642
|
},
|
|
586
643
|
{
|
|
587
|
-
"$Single_Quote": "
|
|
644
|
+
"$Single_Quote": "\\p{Word_Break=Single_Quote}"
|
|
588
645
|
},
|
|
589
646
|
{
|
|
590
|
-
"$ZWJ": "
|
|
647
|
+
"$ZWJ": "\\p{Word_Break=ZWJ}"
|
|
591
648
|
},
|
|
592
649
|
{
|
|
593
|
-
"$ExtPict": "
|
|
650
|
+
"$ExtPict": "\\p{Extended_Pictographic}"
|
|
594
651
|
},
|
|
595
652
|
{
|
|
596
|
-
"$WSegSpace": "
|
|
653
|
+
"$WSegSpace": "\\p{Word_Break=WSegSpace}"
|
|
597
654
|
},
|
|
598
655
|
{
|
|
599
656
|
"$AHLetter": "($ALetter | $Hebrew_Letter)"
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"segments": {
|
|
3
3
|
"identity": {
|
|
4
4
|
"version": {
|
|
5
|
-
"_cldrVersion": "
|
|
5
|
+
"_cldrVersion": "44"
|
|
6
6
|
},
|
|
7
7
|
"language": "zh"
|
|
8
8
|
},
|
|
@@ -10,10 +10,10 @@
|
|
|
10
10
|
"LineBreak": {
|
|
11
11
|
"variables": [
|
|
12
12
|
{
|
|
13
|
-
"$ID": "[[
|
|
13
|
+
"$ID": "[[\\p{Line_Break=Ideographic}] [$CJ]]"
|
|
14
14
|
},
|
|
15
15
|
{
|
|
16
|
-
"$NS": "
|
|
16
|
+
"$NS": "\\p{Line_Break=Nonstarter}"
|
|
17
17
|
}
|
|
18
18
|
]
|
|
19
19
|
}
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"segments": {
|
|
3
3
|
"identity": {
|
|
4
4
|
"version": {
|
|
5
|
-
"_cldrVersion": "
|
|
5
|
+
"_cldrVersion": "44"
|
|
6
6
|
},
|
|
7
7
|
"language": "zh",
|
|
8
8
|
"script": "Hant"
|
|
@@ -11,10 +11,10 @@
|
|
|
11
11
|
"LineBreak": {
|
|
12
12
|
"variables": [
|
|
13
13
|
{
|
|
14
|
-
"$ID": "[[
|
|
14
|
+
"$ID": "[[\\p{Line_Break=Ideographic}] [$CJ]]"
|
|
15
15
|
},
|
|
16
16
|
{
|
|
17
|
-
"$NS": "
|
|
17
|
+
"$NS": "\\p{Line_Break=Nonstarter}"
|
|
18
18
|
}
|
|
19
19
|
]
|
|
20
20
|
}
|