@chr33s/pdf-codepoints 5.0.0
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.md +21 -0
- package/README.md +81 -0
- package/data/ArabicShaping.txt +894 -0
- package/data/Blocks.txt +336 -0
- package/data/CaseFolding.txt +1581 -0
- package/data/CompositionExclusions.txt +208 -0
- package/data/DerivedNormalizationProps.txt +9803 -0
- package/data/EastAsianWidth.txt +2473 -0
- package/data/IndicPositionalCategory.txt +755 -0
- package/data/IndicSyllabicCategory.txt +1286 -0
- package/data/PropertyValueAliases.txt +1541 -0
- package/data/Scripts.txt +2837 -0
- package/data/SpecialCasing.txt +281 -0
- package/data/UnicodeData.txt +32840 -0
- package/data/extracted/DerivedNumericValues.txt +2537 -0
- package/dist/index.d.ts +5 -0
- package/dist/index.js +6 -0
- package/dist/index.js.map +1 -0
- package/dist/parser.d.ts +35 -0
- package/dist/parser.js +308 -0
- package/dist/parser.js.map +1 -0
- package/package.json +40 -0
- package/scripts/update-data.ts +64 -0
- package/src/index.ts +7 -0
- package/src/parser.ts +428 -0
- package/test/parser.test.ts +77 -0
- package/tsconfig.json +10 -0
- package/tsconfig.typecheck.json +14 -0
- package/vitest.config.ts +8 -0
|
@@ -0,0 +1,1541 @@
|
|
|
1
|
+
# PropertyValueAliases-12.0.0.txt
|
|
2
|
+
# Date: 2019-02-19, 05:01:57 GMT
|
|
3
|
+
# © 2019 Unicode®, Inc.
|
|
4
|
+
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
|
|
5
|
+
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
|
6
|
+
#
|
|
7
|
+
# Unicode Character Database
|
|
8
|
+
# For documentation, see http://www.unicode.org/reports/tr44/
|
|
9
|
+
#
|
|
10
|
+
# This file contains aliases for property values used in the UCD.
|
|
11
|
+
# These names can be used for XML formats of UCD data, for regular-expression
|
|
12
|
+
# property tests, and other programmatic textual descriptions of Unicode data.
|
|
13
|
+
#
|
|
14
|
+
# The names may be translated in appropriate environments, and additional
|
|
15
|
+
# aliases may be useful.
|
|
16
|
+
#
|
|
17
|
+
# FORMAT
|
|
18
|
+
#
|
|
19
|
+
# Each line describes a property value name.
|
|
20
|
+
# This consists of three or more fields, separated by semicolons.
|
|
21
|
+
#
|
|
22
|
+
# First Field: The first field describes the property for which that
|
|
23
|
+
# property value name is used.
|
|
24
|
+
#
|
|
25
|
+
# Second Field: The second field is the short name for the property value.
|
|
26
|
+
# It is typically an abbreviation, but in a number of cases it is simply
|
|
27
|
+
# a duplicate of the "long name" in the third field.
|
|
28
|
+
#
|
|
29
|
+
# Third Field: The third field is the long name for the property value,
|
|
30
|
+
# typically the formal name used in documentation about the property value.
|
|
31
|
+
#
|
|
32
|
+
# In the case of Canonical_Combining_Class (ccc), there are 4 fields:
|
|
33
|
+
# The second field is numeric, the third is the short name, and the fourth is the long name.
|
|
34
|
+
#
|
|
35
|
+
# The above are the preferred aliases. Other aliases may be listed in additional fields.
|
|
36
|
+
#
|
|
37
|
+
# Loose matching should be applied to all property names and property values, with
|
|
38
|
+
# the exception of String Property values. With loose matching of property names and
|
|
39
|
+
# values, the case distinctions, whitespace, hyphens, and '_' are ignored.
|
|
40
|
+
# For Numeric Property values, numeric equivalence is applied: thus "01.00"
|
|
41
|
+
# is equivalent to "1".
|
|
42
|
+
#
|
|
43
|
+
# NOTE: Property value names are NOT unique across properties. For example:
|
|
44
|
+
#
|
|
45
|
+
# AL means Arabic Letter for the Bidi_Class property, and
|
|
46
|
+
# AL means Above_Left for the Canonical_Combining_Class property, and
|
|
47
|
+
# AL means Alphabetic for the Line_Break property.
|
|
48
|
+
#
|
|
49
|
+
# In addition, some property names may be the same as some property value names.
|
|
50
|
+
# For example:
|
|
51
|
+
#
|
|
52
|
+
# sc means the Script property, and
|
|
53
|
+
# Sc means the General_Category property value Currency_Symbol (Sc)
|
|
54
|
+
#
|
|
55
|
+
# The combination of property value and property name is, however, unique.
|
|
56
|
+
#
|
|
57
|
+
# For more information, see UAX #44, Unicode Character Database, and
|
|
58
|
+
# UTS #18, Unicode Regular Expressions.
|
|
59
|
+
# ================================================
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
# ASCII_Hex_Digit (AHex)
|
|
63
|
+
|
|
64
|
+
AHex; N ; No ; F ; False
|
|
65
|
+
AHex; Y ; Yes ; T ; True
|
|
66
|
+
|
|
67
|
+
# Age (age)
|
|
68
|
+
|
|
69
|
+
age; 1.1 ; V1_1
|
|
70
|
+
age; 2.0 ; V2_0
|
|
71
|
+
age; 2.1 ; V2_1
|
|
72
|
+
age; 3.0 ; V3_0
|
|
73
|
+
age; 3.1 ; V3_1
|
|
74
|
+
age; 3.2 ; V3_2
|
|
75
|
+
age; 4.0 ; V4_0
|
|
76
|
+
age; 4.1 ; V4_1
|
|
77
|
+
age; 5.0 ; V5_0
|
|
78
|
+
age; 5.1 ; V5_1
|
|
79
|
+
age; 5.2 ; V5_2
|
|
80
|
+
age; 6.0 ; V6_0
|
|
81
|
+
age; 6.1 ; V6_1
|
|
82
|
+
age; 6.2 ; V6_2
|
|
83
|
+
age; 6.3 ; V6_3
|
|
84
|
+
age; 7.0 ; V7_0
|
|
85
|
+
age; 8.0 ; V8_0
|
|
86
|
+
age; 9.0 ; V9_0
|
|
87
|
+
age; 10.0 ; V10_0
|
|
88
|
+
age; 11.0 ; V11_0
|
|
89
|
+
age; 12.0 ; V12_0
|
|
90
|
+
age; NA ; Unassigned
|
|
91
|
+
|
|
92
|
+
# Alphabetic (Alpha)
|
|
93
|
+
|
|
94
|
+
Alpha; N ; No ; F ; False
|
|
95
|
+
Alpha; Y ; Yes ; T ; True
|
|
96
|
+
|
|
97
|
+
# Bidi_Class (bc)
|
|
98
|
+
|
|
99
|
+
bc ; AL ; Arabic_Letter
|
|
100
|
+
bc ; AN ; Arabic_Number
|
|
101
|
+
bc ; B ; Paragraph_Separator
|
|
102
|
+
bc ; BN ; Boundary_Neutral
|
|
103
|
+
bc ; CS ; Common_Separator
|
|
104
|
+
bc ; EN ; European_Number
|
|
105
|
+
bc ; ES ; European_Separator
|
|
106
|
+
bc ; ET ; European_Terminator
|
|
107
|
+
bc ; FSI ; First_Strong_Isolate
|
|
108
|
+
bc ; L ; Left_To_Right
|
|
109
|
+
bc ; LRE ; Left_To_Right_Embedding
|
|
110
|
+
bc ; LRI ; Left_To_Right_Isolate
|
|
111
|
+
bc ; LRO ; Left_To_Right_Override
|
|
112
|
+
bc ; NSM ; Nonspacing_Mark
|
|
113
|
+
bc ; ON ; Other_Neutral
|
|
114
|
+
bc ; PDF ; Pop_Directional_Format
|
|
115
|
+
bc ; PDI ; Pop_Directional_Isolate
|
|
116
|
+
bc ; R ; Right_To_Left
|
|
117
|
+
bc ; RLE ; Right_To_Left_Embedding
|
|
118
|
+
bc ; RLI ; Right_To_Left_Isolate
|
|
119
|
+
bc ; RLO ; Right_To_Left_Override
|
|
120
|
+
bc ; S ; Segment_Separator
|
|
121
|
+
bc ; WS ; White_Space
|
|
122
|
+
|
|
123
|
+
# Bidi_Control (Bidi_C)
|
|
124
|
+
|
|
125
|
+
Bidi_C; N ; No ; F ; False
|
|
126
|
+
Bidi_C; Y ; Yes ; T ; True
|
|
127
|
+
|
|
128
|
+
# Bidi_Mirrored (Bidi_M)
|
|
129
|
+
|
|
130
|
+
Bidi_M; N ; No ; F ; False
|
|
131
|
+
Bidi_M; Y ; Yes ; T ; True
|
|
132
|
+
|
|
133
|
+
# Bidi_Mirroring_Glyph (bmg)
|
|
134
|
+
|
|
135
|
+
# @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; <none>
|
|
136
|
+
|
|
137
|
+
# Bidi_Paired_Bracket (bpb)
|
|
138
|
+
|
|
139
|
+
# @missing: 0000..10FFFF; Bidi_Paired_Bracket; <none>
|
|
140
|
+
|
|
141
|
+
# Bidi_Paired_Bracket_Type (bpt)
|
|
142
|
+
|
|
143
|
+
bpt; c ; Close
|
|
144
|
+
bpt; n ; None
|
|
145
|
+
bpt; o ; Open
|
|
146
|
+
# @missing: 0000..10FFFF; Bidi_Paired_Bracket_Type; n
|
|
147
|
+
|
|
148
|
+
# Block (blk)
|
|
149
|
+
|
|
150
|
+
blk; Adlam ; Adlam
|
|
151
|
+
blk; Aegean_Numbers ; Aegean_Numbers
|
|
152
|
+
blk; Ahom ; Ahom
|
|
153
|
+
blk; Alchemical ; Alchemical_Symbols
|
|
154
|
+
blk; Alphabetic_PF ; Alphabetic_Presentation_Forms
|
|
155
|
+
blk; Anatolian_Hieroglyphs ; Anatolian_Hieroglyphs
|
|
156
|
+
blk; Ancient_Greek_Music ; Ancient_Greek_Musical_Notation
|
|
157
|
+
blk; Ancient_Greek_Numbers ; Ancient_Greek_Numbers
|
|
158
|
+
blk; Ancient_Symbols ; Ancient_Symbols
|
|
159
|
+
blk; Arabic ; Arabic
|
|
160
|
+
blk; Arabic_Ext_A ; Arabic_Extended_A
|
|
161
|
+
blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols
|
|
162
|
+
blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A
|
|
163
|
+
blk; Arabic_PF_B ; Arabic_Presentation_Forms_B
|
|
164
|
+
blk; Arabic_Sup ; Arabic_Supplement
|
|
165
|
+
blk; Armenian ; Armenian
|
|
166
|
+
blk; Arrows ; Arrows
|
|
167
|
+
blk; ASCII ; Basic_Latin
|
|
168
|
+
blk; Avestan ; Avestan
|
|
169
|
+
blk; Balinese ; Balinese
|
|
170
|
+
blk; Bamum ; Bamum
|
|
171
|
+
blk; Bamum_Sup ; Bamum_Supplement
|
|
172
|
+
blk; Bassa_Vah ; Bassa_Vah
|
|
173
|
+
blk; Batak ; Batak
|
|
174
|
+
blk; Bengali ; Bengali
|
|
175
|
+
blk; Bhaiksuki ; Bhaiksuki
|
|
176
|
+
blk; Block_Elements ; Block_Elements
|
|
177
|
+
blk; Bopomofo ; Bopomofo
|
|
178
|
+
blk; Bopomofo_Ext ; Bopomofo_Extended
|
|
179
|
+
blk; Box_Drawing ; Box_Drawing
|
|
180
|
+
blk; Brahmi ; Brahmi
|
|
181
|
+
blk; Braille ; Braille_Patterns
|
|
182
|
+
blk; Buginese ; Buginese
|
|
183
|
+
blk; Buhid ; Buhid
|
|
184
|
+
blk; Byzantine_Music ; Byzantine_Musical_Symbols
|
|
185
|
+
blk; Carian ; Carian
|
|
186
|
+
blk; Caucasian_Albanian ; Caucasian_Albanian
|
|
187
|
+
blk; Chakma ; Chakma
|
|
188
|
+
blk; Cham ; Cham
|
|
189
|
+
blk; Cherokee ; Cherokee
|
|
190
|
+
blk; Cherokee_Sup ; Cherokee_Supplement
|
|
191
|
+
blk; Chess_Symbols ; Chess_Symbols
|
|
192
|
+
blk; CJK ; CJK_Unified_Ideographs
|
|
193
|
+
blk; CJK_Compat ; CJK_Compatibility
|
|
194
|
+
blk; CJK_Compat_Forms ; CJK_Compatibility_Forms
|
|
195
|
+
blk; CJK_Compat_Ideographs ; CJK_Compatibility_Ideographs
|
|
196
|
+
blk; CJK_Compat_Ideographs_Sup ; CJK_Compatibility_Ideographs_Supplement
|
|
197
|
+
blk; CJK_Ext_A ; CJK_Unified_Ideographs_Extension_A
|
|
198
|
+
blk; CJK_Ext_B ; CJK_Unified_Ideographs_Extension_B
|
|
199
|
+
blk; CJK_Ext_C ; CJK_Unified_Ideographs_Extension_C
|
|
200
|
+
blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D
|
|
201
|
+
blk; CJK_Ext_E ; CJK_Unified_Ideographs_Extension_E
|
|
202
|
+
blk; CJK_Ext_F ; CJK_Unified_Ideographs_Extension_F
|
|
203
|
+
blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement
|
|
204
|
+
blk; CJK_Strokes ; CJK_Strokes
|
|
205
|
+
blk; CJK_Symbols ; CJK_Symbols_And_Punctuation
|
|
206
|
+
blk; Compat_Jamo ; Hangul_Compatibility_Jamo
|
|
207
|
+
blk; Control_Pictures ; Control_Pictures
|
|
208
|
+
blk; Coptic ; Coptic
|
|
209
|
+
blk; Coptic_Epact_Numbers ; Coptic_Epact_Numbers
|
|
210
|
+
blk; Counting_Rod ; Counting_Rod_Numerals
|
|
211
|
+
blk; Cuneiform ; Cuneiform
|
|
212
|
+
blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation
|
|
213
|
+
blk; Currency_Symbols ; Currency_Symbols
|
|
214
|
+
blk; Cypriot_Syllabary ; Cypriot_Syllabary
|
|
215
|
+
blk; Cyrillic ; Cyrillic
|
|
216
|
+
blk; Cyrillic_Ext_A ; Cyrillic_Extended_A
|
|
217
|
+
blk; Cyrillic_Ext_B ; Cyrillic_Extended_B
|
|
218
|
+
blk; Cyrillic_Ext_C ; Cyrillic_Extended_C
|
|
219
|
+
blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary
|
|
220
|
+
blk; Deseret ; Deseret
|
|
221
|
+
blk; Devanagari ; Devanagari
|
|
222
|
+
blk; Devanagari_Ext ; Devanagari_Extended
|
|
223
|
+
blk; Diacriticals ; Combining_Diacritical_Marks
|
|
224
|
+
blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended
|
|
225
|
+
blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
|
|
226
|
+
blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
|
|
227
|
+
blk; Dingbats ; Dingbats
|
|
228
|
+
blk; Dogra ; Dogra
|
|
229
|
+
blk; Domino ; Domino_Tiles
|
|
230
|
+
blk; Duployan ; Duployan
|
|
231
|
+
blk; Early_Dynastic_Cuneiform ; Early_Dynastic_Cuneiform
|
|
232
|
+
blk; Egyptian_Hieroglyph_Format_Controls; Egyptian_Hieroglyph_Format_Controls
|
|
233
|
+
blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
|
|
234
|
+
blk; Elbasan ; Elbasan
|
|
235
|
+
blk; Elymaic ; Elymaic
|
|
236
|
+
blk; Emoticons ; Emoticons
|
|
237
|
+
blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
|
|
238
|
+
blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
|
|
239
|
+
blk; Enclosed_CJK ; Enclosed_CJK_Letters_And_Months
|
|
240
|
+
blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement
|
|
241
|
+
blk; Ethiopic ; Ethiopic
|
|
242
|
+
blk; Ethiopic_Ext ; Ethiopic_Extended
|
|
243
|
+
blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
|
|
244
|
+
blk; Ethiopic_Sup ; Ethiopic_Supplement
|
|
245
|
+
blk; Geometric_Shapes ; Geometric_Shapes
|
|
246
|
+
blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended
|
|
247
|
+
blk; Georgian ; Georgian
|
|
248
|
+
blk; Georgian_Ext ; Georgian_Extended
|
|
249
|
+
blk; Georgian_Sup ; Georgian_Supplement
|
|
250
|
+
blk; Glagolitic ; Glagolitic
|
|
251
|
+
blk; Glagolitic_Sup ; Glagolitic_Supplement
|
|
252
|
+
blk; Gothic ; Gothic
|
|
253
|
+
blk; Grantha ; Grantha
|
|
254
|
+
blk; Greek ; Greek_And_Coptic
|
|
255
|
+
blk; Greek_Ext ; Greek_Extended
|
|
256
|
+
blk; Gujarati ; Gujarati
|
|
257
|
+
blk; Gunjala_Gondi ; Gunjala_Gondi
|
|
258
|
+
blk; Gurmukhi ; Gurmukhi
|
|
259
|
+
blk; Half_And_Full_Forms ; Halfwidth_And_Fullwidth_Forms
|
|
260
|
+
blk; Half_Marks ; Combining_Half_Marks
|
|
261
|
+
blk; Hangul ; Hangul_Syllables
|
|
262
|
+
blk; Hanifi_Rohingya ; Hanifi_Rohingya
|
|
263
|
+
blk; Hanunoo ; Hanunoo
|
|
264
|
+
blk; Hatran ; Hatran
|
|
265
|
+
blk; Hebrew ; Hebrew
|
|
266
|
+
blk; High_PU_Surrogates ; High_Private_Use_Surrogates
|
|
267
|
+
blk; High_Surrogates ; High_Surrogates
|
|
268
|
+
blk; Hiragana ; Hiragana
|
|
269
|
+
blk; IDC ; Ideographic_Description_Characters
|
|
270
|
+
blk; Ideographic_Symbols ; Ideographic_Symbols_And_Punctuation
|
|
271
|
+
blk; Imperial_Aramaic ; Imperial_Aramaic
|
|
272
|
+
blk; Indic_Number_Forms ; Common_Indic_Number_Forms
|
|
273
|
+
blk; Indic_Siyaq_Numbers ; Indic_Siyaq_Numbers
|
|
274
|
+
blk; Inscriptional_Pahlavi ; Inscriptional_Pahlavi
|
|
275
|
+
blk; Inscriptional_Parthian ; Inscriptional_Parthian
|
|
276
|
+
blk; IPA_Ext ; IPA_Extensions
|
|
277
|
+
blk; Jamo ; Hangul_Jamo
|
|
278
|
+
blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A
|
|
279
|
+
blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B
|
|
280
|
+
blk; Javanese ; Javanese
|
|
281
|
+
blk; Kaithi ; Kaithi
|
|
282
|
+
blk; Kana_Ext_A ; Kana_Extended_A
|
|
283
|
+
blk; Kana_Sup ; Kana_Supplement
|
|
284
|
+
blk; Kanbun ; Kanbun
|
|
285
|
+
blk; Kangxi ; Kangxi_Radicals
|
|
286
|
+
blk; Kannada ; Kannada
|
|
287
|
+
blk; Katakana ; Katakana
|
|
288
|
+
blk; Katakana_Ext ; Katakana_Phonetic_Extensions
|
|
289
|
+
blk; Kayah_Li ; Kayah_Li
|
|
290
|
+
blk; Kharoshthi ; Kharoshthi
|
|
291
|
+
blk; Khmer ; Khmer
|
|
292
|
+
blk; Khmer_Symbols ; Khmer_Symbols
|
|
293
|
+
blk; Khojki ; Khojki
|
|
294
|
+
blk; Khudawadi ; Khudawadi
|
|
295
|
+
blk; Lao ; Lao
|
|
296
|
+
blk; Latin_1_Sup ; Latin_1_Supplement ; Latin_1
|
|
297
|
+
blk; Latin_Ext_A ; Latin_Extended_A
|
|
298
|
+
blk; Latin_Ext_Additional ; Latin_Extended_Additional
|
|
299
|
+
blk; Latin_Ext_B ; Latin_Extended_B
|
|
300
|
+
blk; Latin_Ext_C ; Latin_Extended_C
|
|
301
|
+
blk; Latin_Ext_D ; Latin_Extended_D
|
|
302
|
+
blk; Latin_Ext_E ; Latin_Extended_E
|
|
303
|
+
blk; Lepcha ; Lepcha
|
|
304
|
+
blk; Letterlike_Symbols ; Letterlike_Symbols
|
|
305
|
+
blk; Limbu ; Limbu
|
|
306
|
+
blk; Linear_A ; Linear_A
|
|
307
|
+
blk; Linear_B_Ideograms ; Linear_B_Ideograms
|
|
308
|
+
blk; Linear_B_Syllabary ; Linear_B_Syllabary
|
|
309
|
+
blk; Lisu ; Lisu
|
|
310
|
+
blk; Low_Surrogates ; Low_Surrogates
|
|
311
|
+
blk; Lycian ; Lycian
|
|
312
|
+
blk; Lydian ; Lydian
|
|
313
|
+
blk; Mahajani ; Mahajani
|
|
314
|
+
blk; Mahjong ; Mahjong_Tiles
|
|
315
|
+
blk; Makasar ; Makasar
|
|
316
|
+
blk; Malayalam ; Malayalam
|
|
317
|
+
blk; Mandaic ; Mandaic
|
|
318
|
+
blk; Manichaean ; Manichaean
|
|
319
|
+
blk; Marchen ; Marchen
|
|
320
|
+
blk; Masaram_Gondi ; Masaram_Gondi
|
|
321
|
+
blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols
|
|
322
|
+
blk; Math_Operators ; Mathematical_Operators
|
|
323
|
+
blk; Mayan_Numerals ; Mayan_Numerals
|
|
324
|
+
blk; Medefaidrin ; Medefaidrin
|
|
325
|
+
blk; Meetei_Mayek ; Meetei_Mayek
|
|
326
|
+
blk; Meetei_Mayek_Ext ; Meetei_Mayek_Extensions
|
|
327
|
+
blk; Mende_Kikakui ; Mende_Kikakui
|
|
328
|
+
blk; Meroitic_Cursive ; Meroitic_Cursive
|
|
329
|
+
blk; Meroitic_Hieroglyphs ; Meroitic_Hieroglyphs
|
|
330
|
+
blk; Miao ; Miao
|
|
331
|
+
blk; Misc_Arrows ; Miscellaneous_Symbols_And_Arrows
|
|
332
|
+
blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A
|
|
333
|
+
blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B
|
|
334
|
+
blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs
|
|
335
|
+
blk; Misc_Symbols ; Miscellaneous_Symbols
|
|
336
|
+
blk; Misc_Technical ; Miscellaneous_Technical
|
|
337
|
+
blk; Modi ; Modi
|
|
338
|
+
blk; Modifier_Letters ; Spacing_Modifier_Letters
|
|
339
|
+
blk; Modifier_Tone_Letters ; Modifier_Tone_Letters
|
|
340
|
+
blk; Mongolian ; Mongolian
|
|
341
|
+
blk; Mongolian_Sup ; Mongolian_Supplement
|
|
342
|
+
blk; Mro ; Mro
|
|
343
|
+
blk; Multani ; Multani
|
|
344
|
+
blk; Music ; Musical_Symbols
|
|
345
|
+
blk; Myanmar ; Myanmar
|
|
346
|
+
blk; Myanmar_Ext_A ; Myanmar_Extended_A
|
|
347
|
+
blk; Myanmar_Ext_B ; Myanmar_Extended_B
|
|
348
|
+
blk; Nabataean ; Nabataean
|
|
349
|
+
blk; Nandinagari ; Nandinagari
|
|
350
|
+
blk; NB ; No_Block
|
|
351
|
+
blk; New_Tai_Lue ; New_Tai_Lue
|
|
352
|
+
blk; Newa ; Newa
|
|
353
|
+
blk; NKo ; NKo
|
|
354
|
+
blk; Number_Forms ; Number_Forms
|
|
355
|
+
blk; Nushu ; Nushu
|
|
356
|
+
blk; Nyiakeng_Puachue_Hmong ; Nyiakeng_Puachue_Hmong
|
|
357
|
+
blk; OCR ; Optical_Character_Recognition
|
|
358
|
+
blk; Ogham ; Ogham
|
|
359
|
+
blk; Ol_Chiki ; Ol_Chiki
|
|
360
|
+
blk; Old_Hungarian ; Old_Hungarian
|
|
361
|
+
blk; Old_Italic ; Old_Italic
|
|
362
|
+
blk; Old_North_Arabian ; Old_North_Arabian
|
|
363
|
+
blk; Old_Permic ; Old_Permic
|
|
364
|
+
blk; Old_Persian ; Old_Persian
|
|
365
|
+
blk; Old_Sogdian ; Old_Sogdian
|
|
366
|
+
blk; Old_South_Arabian ; Old_South_Arabian
|
|
367
|
+
blk; Old_Turkic ; Old_Turkic
|
|
368
|
+
blk; Oriya ; Oriya
|
|
369
|
+
blk; Ornamental_Dingbats ; Ornamental_Dingbats
|
|
370
|
+
blk; Osage ; Osage
|
|
371
|
+
blk; Osmanya ; Osmanya
|
|
372
|
+
blk; Ottoman_Siyaq_Numbers ; Ottoman_Siyaq_Numbers
|
|
373
|
+
blk; Pahawh_Hmong ; Pahawh_Hmong
|
|
374
|
+
blk; Palmyrene ; Palmyrene
|
|
375
|
+
blk; Pau_Cin_Hau ; Pau_Cin_Hau
|
|
376
|
+
blk; Phags_Pa ; Phags_Pa
|
|
377
|
+
blk; Phaistos ; Phaistos_Disc
|
|
378
|
+
blk; Phoenician ; Phoenician
|
|
379
|
+
blk; Phonetic_Ext ; Phonetic_Extensions
|
|
380
|
+
blk; Phonetic_Ext_Sup ; Phonetic_Extensions_Supplement
|
|
381
|
+
blk; Playing_Cards ; Playing_Cards
|
|
382
|
+
blk; Psalter_Pahlavi ; Psalter_Pahlavi
|
|
383
|
+
blk; PUA ; Private_Use_Area ; Private_Use
|
|
384
|
+
blk; Punctuation ; General_Punctuation
|
|
385
|
+
blk; Rejang ; Rejang
|
|
386
|
+
blk; Rumi ; Rumi_Numeral_Symbols
|
|
387
|
+
blk; Runic ; Runic
|
|
388
|
+
blk; Samaritan ; Samaritan
|
|
389
|
+
blk; Saurashtra ; Saurashtra
|
|
390
|
+
blk; Sharada ; Sharada
|
|
391
|
+
blk; Shavian ; Shavian
|
|
392
|
+
blk; Shorthand_Format_Controls ; Shorthand_Format_Controls
|
|
393
|
+
blk; Siddham ; Siddham
|
|
394
|
+
blk; Sinhala ; Sinhala
|
|
395
|
+
blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers
|
|
396
|
+
blk; Small_Forms ; Small_Form_Variants
|
|
397
|
+
blk; Small_Kana_Ext ; Small_Kana_Extension
|
|
398
|
+
blk; Sogdian ; Sogdian
|
|
399
|
+
blk; Sora_Sompeng ; Sora_Sompeng
|
|
400
|
+
blk; Soyombo ; Soyombo
|
|
401
|
+
blk; Specials ; Specials
|
|
402
|
+
blk; Sundanese ; Sundanese
|
|
403
|
+
blk; Sundanese_Sup ; Sundanese_Supplement
|
|
404
|
+
blk; Sup_Arrows_A ; Supplemental_Arrows_A
|
|
405
|
+
blk; Sup_Arrows_B ; Supplemental_Arrows_B
|
|
406
|
+
blk; Sup_Arrows_C ; Supplemental_Arrows_C
|
|
407
|
+
blk; Sup_Math_Operators ; Supplemental_Mathematical_Operators
|
|
408
|
+
blk; Sup_PUA_A ; Supplementary_Private_Use_Area_A
|
|
409
|
+
blk; Sup_PUA_B ; Supplementary_Private_Use_Area_B
|
|
410
|
+
blk; Sup_Punctuation ; Supplemental_Punctuation
|
|
411
|
+
blk; Sup_Symbols_And_Pictographs ; Supplemental_Symbols_And_Pictographs
|
|
412
|
+
blk; Super_And_Sub ; Superscripts_And_Subscripts
|
|
413
|
+
blk; Sutton_SignWriting ; Sutton_SignWriting
|
|
414
|
+
blk; Syloti_Nagri ; Syloti_Nagri
|
|
415
|
+
blk; Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A
|
|
416
|
+
blk; Syriac ; Syriac
|
|
417
|
+
blk; Syriac_Sup ; Syriac_Supplement
|
|
418
|
+
blk; Tagalog ; Tagalog
|
|
419
|
+
blk; Tagbanwa ; Tagbanwa
|
|
420
|
+
blk; Tags ; Tags
|
|
421
|
+
blk; Tai_Le ; Tai_Le
|
|
422
|
+
blk; Tai_Tham ; Tai_Tham
|
|
423
|
+
blk; Tai_Viet ; Tai_Viet
|
|
424
|
+
blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
|
|
425
|
+
blk; Takri ; Takri
|
|
426
|
+
blk; Tamil ; Tamil
|
|
427
|
+
blk; Tamil_Sup ; Tamil_Supplement
|
|
428
|
+
blk; Tangut ; Tangut
|
|
429
|
+
blk; Tangut_Components ; Tangut_Components
|
|
430
|
+
blk; Telugu ; Telugu
|
|
431
|
+
blk; Thaana ; Thaana
|
|
432
|
+
blk; Thai ; Thai
|
|
433
|
+
blk; Tibetan ; Tibetan
|
|
434
|
+
blk; Tifinagh ; Tifinagh
|
|
435
|
+
blk; Tirhuta ; Tirhuta
|
|
436
|
+
blk; Transport_And_Map ; Transport_And_Map_Symbols
|
|
437
|
+
blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
|
|
438
|
+
blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
|
|
439
|
+
blk; Ugaritic ; Ugaritic
|
|
440
|
+
blk; Vai ; Vai
|
|
441
|
+
blk; Vedic_Ext ; Vedic_Extensions
|
|
442
|
+
blk; Vertical_Forms ; Vertical_Forms
|
|
443
|
+
blk; VS ; Variation_Selectors
|
|
444
|
+
blk; VS_Sup ; Variation_Selectors_Supplement
|
|
445
|
+
blk; Wancho ; Wancho
|
|
446
|
+
blk; Warang_Citi ; Warang_Citi
|
|
447
|
+
blk; Yi_Radicals ; Yi_Radicals
|
|
448
|
+
blk; Yi_Syllables ; Yi_Syllables
|
|
449
|
+
blk; Yijing ; Yijing_Hexagram_Symbols
|
|
450
|
+
blk; Zanabazar_Square ; Zanabazar_Square
|
|
451
|
+
|
|
452
|
+
# Canonical_Combining_Class (ccc)
|
|
453
|
+
|
|
454
|
+
ccc; 0; NR ; Not_Reordered
|
|
455
|
+
ccc; 1; OV ; Overlay
|
|
456
|
+
ccc; 7; NK ; Nukta
|
|
457
|
+
ccc; 8; KV ; Kana_Voicing
|
|
458
|
+
ccc; 9; VR ; Virama
|
|
459
|
+
ccc; 10; CCC10 ; CCC10
|
|
460
|
+
ccc; 11; CCC11 ; CCC11
|
|
461
|
+
ccc; 12; CCC12 ; CCC12
|
|
462
|
+
ccc; 13; CCC13 ; CCC13
|
|
463
|
+
ccc; 14; CCC14 ; CCC14
|
|
464
|
+
ccc; 15; CCC15 ; CCC15
|
|
465
|
+
ccc; 16; CCC16 ; CCC16
|
|
466
|
+
ccc; 17; CCC17 ; CCC17
|
|
467
|
+
ccc; 18; CCC18 ; CCC18
|
|
468
|
+
ccc; 19; CCC19 ; CCC19
|
|
469
|
+
ccc; 20; CCC20 ; CCC20
|
|
470
|
+
ccc; 21; CCC21 ; CCC21
|
|
471
|
+
ccc; 22; CCC22 ; CCC22
|
|
472
|
+
ccc; 23; CCC23 ; CCC23
|
|
473
|
+
ccc; 24; CCC24 ; CCC24
|
|
474
|
+
ccc; 25; CCC25 ; CCC25
|
|
475
|
+
ccc; 26; CCC26 ; CCC26
|
|
476
|
+
ccc; 27; CCC27 ; CCC27
|
|
477
|
+
ccc; 28; CCC28 ; CCC28
|
|
478
|
+
ccc; 29; CCC29 ; CCC29
|
|
479
|
+
ccc; 30; CCC30 ; CCC30
|
|
480
|
+
ccc; 31; CCC31 ; CCC31
|
|
481
|
+
ccc; 32; CCC32 ; CCC32
|
|
482
|
+
ccc; 33; CCC33 ; CCC33
|
|
483
|
+
ccc; 34; CCC34 ; CCC34
|
|
484
|
+
ccc; 35; CCC35 ; CCC35
|
|
485
|
+
ccc; 36; CCC36 ; CCC36
|
|
486
|
+
ccc; 84; CCC84 ; CCC84
|
|
487
|
+
ccc; 91; CCC91 ; CCC91
|
|
488
|
+
ccc; 103; CCC103 ; CCC103
|
|
489
|
+
ccc; 107; CCC107 ; CCC107
|
|
490
|
+
ccc; 118; CCC118 ; CCC118
|
|
491
|
+
ccc; 122; CCC122 ; CCC122
|
|
492
|
+
ccc; 129; CCC129 ; CCC129
|
|
493
|
+
ccc; 130; CCC130 ; CCC130
|
|
494
|
+
ccc; 132; CCC132 ; CCC132
|
|
495
|
+
ccc; 133; CCC133 ; CCC133 # RESERVED
|
|
496
|
+
ccc; 200; ATBL ; Attached_Below_Left
|
|
497
|
+
ccc; 202; ATB ; Attached_Below
|
|
498
|
+
ccc; 214; ATA ; Attached_Above
|
|
499
|
+
ccc; 216; ATAR ; Attached_Above_Right
|
|
500
|
+
ccc; 218; BL ; Below_Left
|
|
501
|
+
ccc; 220; B ; Below
|
|
502
|
+
ccc; 222; BR ; Below_Right
|
|
503
|
+
ccc; 224; L ; Left
|
|
504
|
+
ccc; 226; R ; Right
|
|
505
|
+
ccc; 228; AL ; Above_Left
|
|
506
|
+
ccc; 230; A ; Above
|
|
507
|
+
ccc; 232; AR ; Above_Right
|
|
508
|
+
ccc; 233; DB ; Double_Below
|
|
509
|
+
ccc; 234; DA ; Double_Above
|
|
510
|
+
ccc; 240; IS ; Iota_Subscript
|
|
511
|
+
|
|
512
|
+
# Case_Folding (cf)
|
|
513
|
+
|
|
514
|
+
# @missing: 0000..10FFFF; Case_Folding; <code point>
|
|
515
|
+
|
|
516
|
+
# Case_Ignorable (CI)
|
|
517
|
+
|
|
518
|
+
CI ; N ; No ; F ; False
|
|
519
|
+
CI ; Y ; Yes ; T ; True
|
|
520
|
+
|
|
521
|
+
# Cased (Cased)
|
|
522
|
+
|
|
523
|
+
Cased; N ; No ; F ; False
|
|
524
|
+
Cased; Y ; Yes ; T ; True
|
|
525
|
+
|
|
526
|
+
# Changes_When_Casefolded (CWCF)
|
|
527
|
+
|
|
528
|
+
CWCF; N ; No ; F ; False
|
|
529
|
+
CWCF; Y ; Yes ; T ; True
|
|
530
|
+
|
|
531
|
+
# Changes_When_Casemapped (CWCM)
|
|
532
|
+
|
|
533
|
+
CWCM; N ; No ; F ; False
|
|
534
|
+
CWCM; Y ; Yes ; T ; True
|
|
535
|
+
|
|
536
|
+
# Changes_When_Lowercased (CWL)
|
|
537
|
+
|
|
538
|
+
CWL; N ; No ; F ; False
|
|
539
|
+
CWL; Y ; Yes ; T ; True
|
|
540
|
+
|
|
541
|
+
# Changes_When_NFKC_Casefolded (CWKCF)
|
|
542
|
+
|
|
543
|
+
CWKCF; N ; No ; F ; False
|
|
544
|
+
CWKCF; Y ; Yes ; T ; True
|
|
545
|
+
|
|
546
|
+
# Changes_When_Titlecased (CWT)
|
|
547
|
+
|
|
548
|
+
CWT; N ; No ; F ; False
|
|
549
|
+
CWT; Y ; Yes ; T ; True
|
|
550
|
+
|
|
551
|
+
# Changes_When_Uppercased (CWU)
|
|
552
|
+
|
|
553
|
+
CWU; N ; No ; F ; False
|
|
554
|
+
CWU; Y ; Yes ; T ; True
|
|
555
|
+
|
|
556
|
+
# Composition_Exclusion (CE)
|
|
557
|
+
|
|
558
|
+
CE ; N ; No ; F ; False
|
|
559
|
+
CE ; Y ; Yes ; T ; True
|
|
560
|
+
|
|
561
|
+
# Dash (Dash)
|
|
562
|
+
|
|
563
|
+
Dash; N ; No ; F ; False
|
|
564
|
+
Dash; Y ; Yes ; T ; True
|
|
565
|
+
|
|
566
|
+
# Decomposition_Mapping (dm)
|
|
567
|
+
|
|
568
|
+
# @missing: 0000..10FFFF; Decomposition_Mapping; <code point>
|
|
569
|
+
|
|
570
|
+
# Decomposition_Type (dt)
|
|
571
|
+
|
|
572
|
+
dt ; Can ; Canonical ; can
|
|
573
|
+
dt ; Com ; Compat ; com
|
|
574
|
+
dt ; Enc ; Circle ; enc
|
|
575
|
+
dt ; Fin ; Final ; fin
|
|
576
|
+
dt ; Font ; Font ; font
|
|
577
|
+
dt ; Fra ; Fraction ; fra
|
|
578
|
+
dt ; Init ; Initial ; init
|
|
579
|
+
dt ; Iso ; Isolated ; iso
|
|
580
|
+
dt ; Med ; Medial ; med
|
|
581
|
+
dt ; Nar ; Narrow ; nar
|
|
582
|
+
dt ; Nb ; Nobreak ; nb
|
|
583
|
+
dt ; None ; None ; none
|
|
584
|
+
dt ; Sml ; Small ; sml
|
|
585
|
+
dt ; Sqr ; Square ; sqr
|
|
586
|
+
dt ; Sub ; Sub ; sub
|
|
587
|
+
dt ; Sup ; Super ; sup
|
|
588
|
+
dt ; Vert ; Vertical ; vert
|
|
589
|
+
dt ; Wide ; Wide ; wide
|
|
590
|
+
|
|
591
|
+
# Default_Ignorable_Code_Point (DI)
|
|
592
|
+
|
|
593
|
+
DI ; N ; No ; F ; False
|
|
594
|
+
DI ; Y ; Yes ; T ; True
|
|
595
|
+
|
|
596
|
+
# Deprecated (Dep)
|
|
597
|
+
|
|
598
|
+
Dep; N ; No ; F ; False
|
|
599
|
+
Dep; Y ; Yes ; T ; True
|
|
600
|
+
|
|
601
|
+
# Diacritic (Dia)
|
|
602
|
+
|
|
603
|
+
Dia; N ; No ; F ; False
|
|
604
|
+
Dia; Y ; Yes ; T ; True
|
|
605
|
+
|
|
606
|
+
# East_Asian_Width (ea)
|
|
607
|
+
|
|
608
|
+
ea ; A ; Ambiguous
|
|
609
|
+
ea ; F ; Fullwidth
|
|
610
|
+
ea ; H ; Halfwidth
|
|
611
|
+
ea ; N ; Neutral
|
|
612
|
+
ea ; Na ; Narrow
|
|
613
|
+
ea ; W ; Wide
|
|
614
|
+
|
|
615
|
+
# Equivalent_Unified_Ideograph (EqUIdeo)
|
|
616
|
+
|
|
617
|
+
# @missing: 0000..10FFFF; Equivalent_Unified_Ideograph; <none>
|
|
618
|
+
|
|
619
|
+
# Expands_On_NFC (XO_NFC)
|
|
620
|
+
|
|
621
|
+
XO_NFC; N ; No ; F ; False
|
|
622
|
+
XO_NFC; Y ; Yes ; T ; True
|
|
623
|
+
|
|
624
|
+
# Expands_On_NFD (XO_NFD)
|
|
625
|
+
|
|
626
|
+
XO_NFD; N ; No ; F ; False
|
|
627
|
+
XO_NFD; Y ; Yes ; T ; True
|
|
628
|
+
|
|
629
|
+
# Expands_On_NFKC (XO_NFKC)
|
|
630
|
+
|
|
631
|
+
XO_NFKC; N ; No ; F ; False
|
|
632
|
+
XO_NFKC; Y ; Yes ; T ; True
|
|
633
|
+
|
|
634
|
+
# Expands_On_NFKD (XO_NFKD)
|
|
635
|
+
|
|
636
|
+
XO_NFKD; N ; No ; F ; False
|
|
637
|
+
XO_NFKD; Y ; Yes ; T ; True
|
|
638
|
+
|
|
639
|
+
# Extender (Ext)
|
|
640
|
+
|
|
641
|
+
Ext; N ; No ; F ; False
|
|
642
|
+
Ext; Y ; Yes ; T ; True
|
|
643
|
+
|
|
644
|
+
# FC_NFKC_Closure (FC_NFKC)
|
|
645
|
+
|
|
646
|
+
# @missing: 0000..10FFFF; FC_NFKC_Closure; <code point>
|
|
647
|
+
|
|
648
|
+
# Full_Composition_Exclusion (Comp_Ex)
|
|
649
|
+
|
|
650
|
+
Comp_Ex; N ; No ; F ; False
|
|
651
|
+
Comp_Ex; Y ; Yes ; T ; True
|
|
652
|
+
|
|
653
|
+
# General_Category (gc)
|
|
654
|
+
|
|
655
|
+
gc ; C ; Other # Cc | Cf | Cn | Co | Cs
|
|
656
|
+
gc ; Cc ; Control ; cntrl
|
|
657
|
+
gc ; Cf ; Format
|
|
658
|
+
gc ; Cn ; Unassigned
|
|
659
|
+
gc ; Co ; Private_Use
|
|
660
|
+
gc ; Cs ; Surrogate
|
|
661
|
+
gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu
|
|
662
|
+
gc ; LC ; Cased_Letter # Ll | Lt | Lu
|
|
663
|
+
gc ; Ll ; Lowercase_Letter
|
|
664
|
+
gc ; Lm ; Modifier_Letter
|
|
665
|
+
gc ; Lo ; Other_Letter
|
|
666
|
+
gc ; Lt ; Titlecase_Letter
|
|
667
|
+
gc ; Lu ; Uppercase_Letter
|
|
668
|
+
gc ; M ; Mark ; Combining_Mark # Mc | Me | Mn
|
|
669
|
+
gc ; Mc ; Spacing_Mark
|
|
670
|
+
gc ; Me ; Enclosing_Mark
|
|
671
|
+
gc ; Mn ; Nonspacing_Mark
|
|
672
|
+
gc ; N ; Number # Nd | Nl | No
|
|
673
|
+
gc ; Nd ; Decimal_Number ; digit
|
|
674
|
+
gc ; Nl ; Letter_Number
|
|
675
|
+
gc ; No ; Other_Number
|
|
676
|
+
gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
|
|
677
|
+
gc ; Pc ; Connector_Punctuation
|
|
678
|
+
gc ; Pd ; Dash_Punctuation
|
|
679
|
+
gc ; Pe ; Close_Punctuation
|
|
680
|
+
gc ; Pf ; Final_Punctuation
|
|
681
|
+
gc ; Pi ; Initial_Punctuation
|
|
682
|
+
gc ; Po ; Other_Punctuation
|
|
683
|
+
gc ; Ps ; Open_Punctuation
|
|
684
|
+
gc ; S ; Symbol # Sc | Sk | Sm | So
|
|
685
|
+
gc ; Sc ; Currency_Symbol
|
|
686
|
+
gc ; Sk ; Modifier_Symbol
|
|
687
|
+
gc ; Sm ; Math_Symbol
|
|
688
|
+
gc ; So ; Other_Symbol
|
|
689
|
+
gc ; Z ; Separator # Zl | Zp | Zs
|
|
690
|
+
gc ; Zl ; Line_Separator
|
|
691
|
+
gc ; Zp ; Paragraph_Separator
|
|
692
|
+
gc ; Zs ; Space_Separator
|
|
693
|
+
# @missing: 0000..10FFFF; General_Category; Unassigned
|
|
694
|
+
|
|
695
|
+
# Grapheme_Base (Gr_Base)
|
|
696
|
+
|
|
697
|
+
Gr_Base; N ; No ; F ; False
|
|
698
|
+
Gr_Base; Y ; Yes ; T ; True
|
|
699
|
+
|
|
700
|
+
# Grapheme_Cluster_Break (GCB)
|
|
701
|
+
|
|
702
|
+
GCB; CN ; Control
|
|
703
|
+
GCB; CR ; CR
|
|
704
|
+
GCB; EB ; E_Base
|
|
705
|
+
GCB; EBG ; E_Base_GAZ
|
|
706
|
+
GCB; EM ; E_Modifier
|
|
707
|
+
GCB; EX ; Extend
|
|
708
|
+
GCB; GAZ ; Glue_After_Zwj
|
|
709
|
+
GCB; L ; L
|
|
710
|
+
GCB; LF ; LF
|
|
711
|
+
GCB; LV ; LV
|
|
712
|
+
GCB; LVT ; LVT
|
|
713
|
+
GCB; PP ; Prepend
|
|
714
|
+
GCB; RI ; Regional_Indicator
|
|
715
|
+
GCB; SM ; SpacingMark
|
|
716
|
+
GCB; T ; T
|
|
717
|
+
GCB; V ; V
|
|
718
|
+
GCB; XX ; Other
|
|
719
|
+
GCB; ZWJ ; ZWJ
|
|
720
|
+
|
|
721
|
+
# Grapheme_Extend (Gr_Ext)
|
|
722
|
+
|
|
723
|
+
Gr_Ext; N ; No ; F ; False
|
|
724
|
+
Gr_Ext; Y ; Yes ; T ; True
|
|
725
|
+
|
|
726
|
+
# Grapheme_Link (Gr_Link)
|
|
727
|
+
|
|
728
|
+
Gr_Link; N ; No ; F ; False
|
|
729
|
+
Gr_Link; Y ; Yes ; T ; True
|
|
730
|
+
|
|
731
|
+
# Hangul_Syllable_Type (hst)
|
|
732
|
+
|
|
733
|
+
hst; L ; Leading_Jamo
|
|
734
|
+
hst; LV ; LV_Syllable
|
|
735
|
+
hst; LVT ; LVT_Syllable
|
|
736
|
+
hst; NA ; Not_Applicable
|
|
737
|
+
hst; T ; Trailing_Jamo
|
|
738
|
+
hst; V ; Vowel_Jamo
|
|
739
|
+
|
|
740
|
+
# Hex_Digit (Hex)
|
|
741
|
+
|
|
742
|
+
Hex; N ; No ; F ; False
|
|
743
|
+
Hex; Y ; Yes ; T ; True
|
|
744
|
+
|
|
745
|
+
# Hyphen (Hyphen)
|
|
746
|
+
|
|
747
|
+
Hyphen; N ; No ; F ; False
|
|
748
|
+
Hyphen; Y ; Yes ; T ; True
|
|
749
|
+
|
|
750
|
+
# IDS_Binary_Operator (IDSB)
|
|
751
|
+
|
|
752
|
+
IDSB; N ; No ; F ; False
|
|
753
|
+
IDSB; Y ; Yes ; T ; True
|
|
754
|
+
|
|
755
|
+
# IDS_Trinary_Operator (IDST)
|
|
756
|
+
|
|
757
|
+
IDST; N ; No ; F ; False
|
|
758
|
+
IDST; Y ; Yes ; T ; True
|
|
759
|
+
|
|
760
|
+
# ID_Continue (IDC)
|
|
761
|
+
|
|
762
|
+
IDC; N ; No ; F ; False
|
|
763
|
+
IDC; Y ; Yes ; T ; True
|
|
764
|
+
|
|
765
|
+
# ID_Start (IDS)
|
|
766
|
+
|
|
767
|
+
IDS; N ; No ; F ; False
|
|
768
|
+
IDS; Y ; Yes ; T ; True
|
|
769
|
+
|
|
770
|
+
# ISO_Comment (isc)
|
|
771
|
+
|
|
772
|
+
# @missing: 0000..10FFFF; ISO_Comment; <none>
|
|
773
|
+
|
|
774
|
+
# Ideographic (Ideo)
|
|
775
|
+
|
|
776
|
+
Ideo; N ; No ; F ; False
|
|
777
|
+
Ideo; Y ; Yes ; T ; True
|
|
778
|
+
|
|
779
|
+
# Indic_Positional_Category (InPC)
|
|
780
|
+
|
|
781
|
+
InPC; Bottom ; Bottom
|
|
782
|
+
InPC; Bottom_And_Left ; Bottom_And_Left
|
|
783
|
+
InPC; Bottom_And_Right ; Bottom_And_Right
|
|
784
|
+
InPC; Left ; Left
|
|
785
|
+
InPC; Left_And_Right ; Left_And_Right
|
|
786
|
+
InPC; NA ; NA
|
|
787
|
+
InPC; Overstruck ; Overstruck
|
|
788
|
+
InPC; Right ; Right
|
|
789
|
+
InPC; Top ; Top
|
|
790
|
+
InPC; Top_And_Bottom ; Top_And_Bottom
|
|
791
|
+
InPC; Top_And_Bottom_And_Right ; Top_And_Bottom_And_Right
|
|
792
|
+
InPC; Top_And_Left ; Top_And_Left
|
|
793
|
+
InPC; Top_And_Left_And_Right ; Top_And_Left_And_Right
|
|
794
|
+
InPC; Top_And_Right ; Top_And_Right
|
|
795
|
+
InPC; Visual_Order_Left ; Visual_Order_Left
|
|
796
|
+
|
|
797
|
+
# Indic_Syllabic_Category (InSC)
|
|
798
|
+
|
|
799
|
+
InSC; Avagraha ; Avagraha
|
|
800
|
+
InSC; Bindu ; Bindu
|
|
801
|
+
InSC; Brahmi_Joining_Number ; Brahmi_Joining_Number
|
|
802
|
+
InSC; Cantillation_Mark ; Cantillation_Mark
|
|
803
|
+
InSC; Consonant ; Consonant
|
|
804
|
+
InSC; Consonant_Dead ; Consonant_Dead
|
|
805
|
+
InSC; Consonant_Final ; Consonant_Final
|
|
806
|
+
InSC; Consonant_Head_Letter ; Consonant_Head_Letter
|
|
807
|
+
InSC; Consonant_Initial_Postfixed ; Consonant_Initial_Postfixed
|
|
808
|
+
InSC; Consonant_Killer ; Consonant_Killer
|
|
809
|
+
InSC; Consonant_Medial ; Consonant_Medial
|
|
810
|
+
InSC; Consonant_Placeholder ; Consonant_Placeholder
|
|
811
|
+
InSC; Consonant_Preceding_Repha ; Consonant_Preceding_Repha
|
|
812
|
+
InSC; Consonant_Prefixed ; Consonant_Prefixed
|
|
813
|
+
InSC; Consonant_Subjoined ; Consonant_Subjoined
|
|
814
|
+
InSC; Consonant_Succeeding_Repha ; Consonant_Succeeding_Repha
|
|
815
|
+
InSC; Consonant_With_Stacker ; Consonant_With_Stacker
|
|
816
|
+
InSC; Gemination_Mark ; Gemination_Mark
|
|
817
|
+
InSC; Invisible_Stacker ; Invisible_Stacker
|
|
818
|
+
InSC; Joiner ; Joiner
|
|
819
|
+
InSC; Modifying_Letter ; Modifying_Letter
|
|
820
|
+
InSC; Non_Joiner ; Non_Joiner
|
|
821
|
+
InSC; Nukta ; Nukta
|
|
822
|
+
InSC; Number ; Number
|
|
823
|
+
InSC; Number_Joiner ; Number_Joiner
|
|
824
|
+
InSC; Other ; Other
|
|
825
|
+
InSC; Pure_Killer ; Pure_Killer
|
|
826
|
+
InSC; Register_Shifter ; Register_Shifter
|
|
827
|
+
InSC; Syllable_Modifier ; Syllable_Modifier
|
|
828
|
+
InSC; Tone_Letter ; Tone_Letter
|
|
829
|
+
InSC; Tone_Mark ; Tone_Mark
|
|
830
|
+
InSC; Virama ; Virama
|
|
831
|
+
InSC; Visarga ; Visarga
|
|
832
|
+
InSC; Vowel ; Vowel
|
|
833
|
+
InSC; Vowel_Dependent ; Vowel_Dependent
|
|
834
|
+
InSC; Vowel_Independent ; Vowel_Independent
|
|
835
|
+
|
|
836
|
+
# Jamo_Short_Name (JSN)
|
|
837
|
+
|
|
838
|
+
JSN; A ; A
|
|
839
|
+
JSN; AE ; AE
|
|
840
|
+
JSN; B ; B
|
|
841
|
+
JSN; BB ; BB
|
|
842
|
+
JSN; BS ; BS
|
|
843
|
+
JSN; C ; C
|
|
844
|
+
JSN; D ; D
|
|
845
|
+
JSN; DD ; DD
|
|
846
|
+
JSN; E ; E
|
|
847
|
+
JSN; EO ; EO
|
|
848
|
+
JSN; EU ; EU
|
|
849
|
+
JSN; G ; G
|
|
850
|
+
JSN; GG ; GG
|
|
851
|
+
JSN; GS ; GS
|
|
852
|
+
JSN; H ; H
|
|
853
|
+
JSN; I ; I
|
|
854
|
+
JSN; J ; J
|
|
855
|
+
JSN; JJ ; JJ
|
|
856
|
+
JSN; K ; K
|
|
857
|
+
JSN; L ; L
|
|
858
|
+
JSN; LB ; LB
|
|
859
|
+
JSN; LG ; LG
|
|
860
|
+
JSN; LH ; LH
|
|
861
|
+
JSN; LM ; LM
|
|
862
|
+
JSN; LP ; LP
|
|
863
|
+
JSN; LS ; LS
|
|
864
|
+
JSN; LT ; LT
|
|
865
|
+
JSN; M ; M
|
|
866
|
+
JSN; N ; N
|
|
867
|
+
JSN; NG ; NG
|
|
868
|
+
JSN; NH ; NH
|
|
869
|
+
JSN; NJ ; NJ
|
|
870
|
+
JSN; O ; O
|
|
871
|
+
JSN; OE ; OE
|
|
872
|
+
JSN; P ; P
|
|
873
|
+
JSN; R ; R
|
|
874
|
+
JSN; S ; S
|
|
875
|
+
JSN; SS ; SS
|
|
876
|
+
JSN; T ; T
|
|
877
|
+
JSN; U ; U
|
|
878
|
+
JSN; WA ; WA
|
|
879
|
+
JSN; WAE ; WAE
|
|
880
|
+
JSN; WE ; WE
|
|
881
|
+
JSN; WEO ; WEO
|
|
882
|
+
JSN; WI ; WI
|
|
883
|
+
JSN; YA ; YA
|
|
884
|
+
JSN; YAE ; YAE
|
|
885
|
+
JSN; YE ; YE
|
|
886
|
+
JSN; YEO ; YEO
|
|
887
|
+
JSN; YI ; YI
|
|
888
|
+
JSN; YO ; YO
|
|
889
|
+
JSN; YU ; YU
|
|
890
|
+
# @missing: 0000..10FFFF; Jamo_Short_Name; <none>
|
|
891
|
+
|
|
892
|
+
# Join_Control (Join_C)
|
|
893
|
+
|
|
894
|
+
Join_C; N ; No ; F ; False
|
|
895
|
+
Join_C; Y ; Yes ; T ; True
|
|
896
|
+
|
|
897
|
+
# Joining_Group (jg)
|
|
898
|
+
|
|
899
|
+
jg ; African_Feh ; African_Feh
|
|
900
|
+
jg ; African_Noon ; African_Noon
|
|
901
|
+
jg ; African_Qaf ; African_Qaf
|
|
902
|
+
jg ; Ain ; Ain
|
|
903
|
+
jg ; Alaph ; Alaph
|
|
904
|
+
jg ; Alef ; Alef
|
|
905
|
+
jg ; Beh ; Beh
|
|
906
|
+
jg ; Beth ; Beth
|
|
907
|
+
jg ; Burushaski_Yeh_Barree ; Burushaski_Yeh_Barree
|
|
908
|
+
jg ; Dal ; Dal
|
|
909
|
+
jg ; Dalath_Rish ; Dalath_Rish
|
|
910
|
+
jg ; E ; E
|
|
911
|
+
jg ; Farsi_Yeh ; Farsi_Yeh
|
|
912
|
+
jg ; Fe ; Fe
|
|
913
|
+
jg ; Feh ; Feh
|
|
914
|
+
jg ; Final_Semkath ; Final_Semkath
|
|
915
|
+
jg ; Gaf ; Gaf
|
|
916
|
+
jg ; Gamal ; Gamal
|
|
917
|
+
jg ; Hah ; Hah
|
|
918
|
+
jg ; Hanifi_Rohingya_Kinna_Ya ; Hanifi_Rohingya_Kinna_Ya
|
|
919
|
+
jg ; Hanifi_Rohingya_Pa ; Hanifi_Rohingya_Pa
|
|
920
|
+
jg ; He ; He
|
|
921
|
+
jg ; Heh ; Heh
|
|
922
|
+
jg ; Heh_Goal ; Heh_Goal
|
|
923
|
+
jg ; Heth ; Heth
|
|
924
|
+
jg ; Kaf ; Kaf
|
|
925
|
+
jg ; Kaph ; Kaph
|
|
926
|
+
jg ; Khaph ; Khaph
|
|
927
|
+
jg ; Knotted_Heh ; Knotted_Heh
|
|
928
|
+
jg ; Lam ; Lam
|
|
929
|
+
jg ; Lamadh ; Lamadh
|
|
930
|
+
jg ; Malayalam_Bha ; Malayalam_Bha
|
|
931
|
+
jg ; Malayalam_Ja ; Malayalam_Ja
|
|
932
|
+
jg ; Malayalam_Lla ; Malayalam_Lla
|
|
933
|
+
jg ; Malayalam_Llla ; Malayalam_Llla
|
|
934
|
+
jg ; Malayalam_Nga ; Malayalam_Nga
|
|
935
|
+
jg ; Malayalam_Nna ; Malayalam_Nna
|
|
936
|
+
jg ; Malayalam_Nnna ; Malayalam_Nnna
|
|
937
|
+
jg ; Malayalam_Nya ; Malayalam_Nya
|
|
938
|
+
jg ; Malayalam_Ra ; Malayalam_Ra
|
|
939
|
+
jg ; Malayalam_Ssa ; Malayalam_Ssa
|
|
940
|
+
jg ; Malayalam_Tta ; Malayalam_Tta
|
|
941
|
+
jg ; Manichaean_Aleph ; Manichaean_Aleph
|
|
942
|
+
jg ; Manichaean_Ayin ; Manichaean_Ayin
|
|
943
|
+
jg ; Manichaean_Beth ; Manichaean_Beth
|
|
944
|
+
jg ; Manichaean_Daleth ; Manichaean_Daleth
|
|
945
|
+
jg ; Manichaean_Dhamedh ; Manichaean_Dhamedh
|
|
946
|
+
jg ; Manichaean_Five ; Manichaean_Five
|
|
947
|
+
jg ; Manichaean_Gimel ; Manichaean_Gimel
|
|
948
|
+
jg ; Manichaean_Heth ; Manichaean_Heth
|
|
949
|
+
jg ; Manichaean_Hundred ; Manichaean_Hundred
|
|
950
|
+
jg ; Manichaean_Kaph ; Manichaean_Kaph
|
|
951
|
+
jg ; Manichaean_Lamedh ; Manichaean_Lamedh
|
|
952
|
+
jg ; Manichaean_Mem ; Manichaean_Mem
|
|
953
|
+
jg ; Manichaean_Nun ; Manichaean_Nun
|
|
954
|
+
jg ; Manichaean_One ; Manichaean_One
|
|
955
|
+
jg ; Manichaean_Pe ; Manichaean_Pe
|
|
956
|
+
jg ; Manichaean_Qoph ; Manichaean_Qoph
|
|
957
|
+
jg ; Manichaean_Resh ; Manichaean_Resh
|
|
958
|
+
jg ; Manichaean_Sadhe ; Manichaean_Sadhe
|
|
959
|
+
jg ; Manichaean_Samekh ; Manichaean_Samekh
|
|
960
|
+
jg ; Manichaean_Taw ; Manichaean_Taw
|
|
961
|
+
jg ; Manichaean_Ten ; Manichaean_Ten
|
|
962
|
+
jg ; Manichaean_Teth ; Manichaean_Teth
|
|
963
|
+
jg ; Manichaean_Thamedh ; Manichaean_Thamedh
|
|
964
|
+
jg ; Manichaean_Twenty ; Manichaean_Twenty
|
|
965
|
+
jg ; Manichaean_Waw ; Manichaean_Waw
|
|
966
|
+
jg ; Manichaean_Yodh ; Manichaean_Yodh
|
|
967
|
+
jg ; Manichaean_Zayin ; Manichaean_Zayin
|
|
968
|
+
jg ; Meem ; Meem
|
|
969
|
+
jg ; Mim ; Mim
|
|
970
|
+
jg ; No_Joining_Group ; No_Joining_Group
|
|
971
|
+
jg ; Noon ; Noon
|
|
972
|
+
jg ; Nun ; Nun
|
|
973
|
+
jg ; Nya ; Nya
|
|
974
|
+
jg ; Pe ; Pe
|
|
975
|
+
jg ; Qaf ; Qaf
|
|
976
|
+
jg ; Qaph ; Qaph
|
|
977
|
+
jg ; Reh ; Reh
|
|
978
|
+
jg ; Reversed_Pe ; Reversed_Pe
|
|
979
|
+
jg ; Rohingya_Yeh ; Rohingya_Yeh
|
|
980
|
+
jg ; Sad ; Sad
|
|
981
|
+
jg ; Sadhe ; Sadhe
|
|
982
|
+
jg ; Seen ; Seen
|
|
983
|
+
jg ; Semkath ; Semkath
|
|
984
|
+
jg ; Shin ; Shin
|
|
985
|
+
jg ; Straight_Waw ; Straight_Waw
|
|
986
|
+
jg ; Swash_Kaf ; Swash_Kaf
|
|
987
|
+
jg ; Syriac_Waw ; Syriac_Waw
|
|
988
|
+
jg ; Tah ; Tah
|
|
989
|
+
jg ; Taw ; Taw
|
|
990
|
+
jg ; Teh_Marbuta ; Teh_Marbuta
|
|
991
|
+
jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
|
|
992
|
+
jg ; Teth ; Teth
|
|
993
|
+
jg ; Waw ; Waw
|
|
994
|
+
jg ; Yeh ; Yeh
|
|
995
|
+
jg ; Yeh_Barree ; Yeh_Barree
|
|
996
|
+
jg ; Yeh_With_Tail ; Yeh_With_Tail
|
|
997
|
+
jg ; Yudh ; Yudh
|
|
998
|
+
jg ; Yudh_He ; Yudh_He
|
|
999
|
+
jg ; Zain ; Zain
|
|
1000
|
+
jg ; Zhain ; Zhain
|
|
1001
|
+
|
|
1002
|
+
# Joining_Type (jt)
|
|
1003
|
+
|
|
1004
|
+
jt ; C ; Join_Causing
|
|
1005
|
+
jt ; D ; Dual_Joining
|
|
1006
|
+
jt ; L ; Left_Joining
|
|
1007
|
+
jt ; R ; Right_Joining
|
|
1008
|
+
jt ; T ; Transparent
|
|
1009
|
+
jt ; U ; Non_Joining
|
|
1010
|
+
|
|
1011
|
+
# Line_Break (lb)
|
|
1012
|
+
|
|
1013
|
+
lb ; AI ; Ambiguous
|
|
1014
|
+
lb ; AL ; Alphabetic
|
|
1015
|
+
lb ; B2 ; Break_Both
|
|
1016
|
+
lb ; BA ; Break_After
|
|
1017
|
+
lb ; BB ; Break_Before
|
|
1018
|
+
lb ; BK ; Mandatory_Break
|
|
1019
|
+
lb ; CB ; Contingent_Break
|
|
1020
|
+
lb ; CJ ; Conditional_Japanese_Starter
|
|
1021
|
+
lb ; CL ; Close_Punctuation
|
|
1022
|
+
lb ; CM ; Combining_Mark
|
|
1023
|
+
lb ; CP ; Close_Parenthesis
|
|
1024
|
+
lb ; CR ; Carriage_Return
|
|
1025
|
+
lb ; EB ; E_Base
|
|
1026
|
+
lb ; EM ; E_Modifier
|
|
1027
|
+
lb ; EX ; Exclamation
|
|
1028
|
+
lb ; GL ; Glue
|
|
1029
|
+
lb ; H2 ; H2
|
|
1030
|
+
lb ; H3 ; H3
|
|
1031
|
+
lb ; HL ; Hebrew_Letter
|
|
1032
|
+
lb ; HY ; Hyphen
|
|
1033
|
+
lb ; ID ; Ideographic
|
|
1034
|
+
lb ; IN ; Inseparable ; Inseperable
|
|
1035
|
+
lb ; IS ; Infix_Numeric
|
|
1036
|
+
lb ; JL ; JL
|
|
1037
|
+
lb ; JT ; JT
|
|
1038
|
+
lb ; JV ; JV
|
|
1039
|
+
lb ; LF ; Line_Feed
|
|
1040
|
+
lb ; NL ; Next_Line
|
|
1041
|
+
lb ; NS ; Nonstarter
|
|
1042
|
+
lb ; NU ; Numeric
|
|
1043
|
+
lb ; OP ; Open_Punctuation
|
|
1044
|
+
lb ; PO ; Postfix_Numeric
|
|
1045
|
+
lb ; PR ; Prefix_Numeric
|
|
1046
|
+
lb ; QU ; Quotation
|
|
1047
|
+
lb ; RI ; Regional_Indicator
|
|
1048
|
+
lb ; SA ; Complex_Context
|
|
1049
|
+
lb ; SG ; Surrogate
|
|
1050
|
+
lb ; SP ; Space
|
|
1051
|
+
lb ; SY ; Break_Symbols
|
|
1052
|
+
lb ; WJ ; Word_Joiner
|
|
1053
|
+
lb ; XX ; Unknown
|
|
1054
|
+
lb ; ZW ; ZWSpace
|
|
1055
|
+
lb ; ZWJ ; ZWJ
|
|
1056
|
+
|
|
1057
|
+
# Logical_Order_Exception (LOE)
|
|
1058
|
+
|
|
1059
|
+
LOE; N ; No ; F ; False
|
|
1060
|
+
LOE; Y ; Yes ; T ; True
|
|
1061
|
+
|
|
1062
|
+
# Lowercase (Lower)
|
|
1063
|
+
|
|
1064
|
+
Lower; N ; No ; F ; False
|
|
1065
|
+
Lower; Y ; Yes ; T ; True
|
|
1066
|
+
|
|
1067
|
+
# Lowercase_Mapping (lc)
|
|
1068
|
+
|
|
1069
|
+
# @missing: 0000..10FFFF; Lowercase_Mapping; <code point>
|
|
1070
|
+
|
|
1071
|
+
# Math (Math)
|
|
1072
|
+
|
|
1073
|
+
Math; N ; No ; F ; False
|
|
1074
|
+
Math; Y ; Yes ; T ; True
|
|
1075
|
+
|
|
1076
|
+
# NFC_Quick_Check (NFC_QC)
|
|
1077
|
+
|
|
1078
|
+
NFC_QC; M ; Maybe
|
|
1079
|
+
NFC_QC; N ; No
|
|
1080
|
+
NFC_QC; Y ; Yes
|
|
1081
|
+
|
|
1082
|
+
# NFD_Quick_Check (NFD_QC)
|
|
1083
|
+
|
|
1084
|
+
NFD_QC; N ; No
|
|
1085
|
+
NFD_QC; Y ; Yes
|
|
1086
|
+
|
|
1087
|
+
# NFKC_Casefold (NFKC_CF)
|
|
1088
|
+
|
|
1089
|
+
# @missing: 0000..10FFFF; NFKC_Casefold; <code point>
|
|
1090
|
+
|
|
1091
|
+
# NFKC_Quick_Check (NFKC_QC)
|
|
1092
|
+
|
|
1093
|
+
NFKC_QC; M ; Maybe
|
|
1094
|
+
NFKC_QC; N ; No
|
|
1095
|
+
NFKC_QC; Y ; Yes
|
|
1096
|
+
|
|
1097
|
+
# NFKD_Quick_Check (NFKD_QC)
|
|
1098
|
+
|
|
1099
|
+
NFKD_QC; N ; No
|
|
1100
|
+
NFKD_QC; Y ; Yes
|
|
1101
|
+
|
|
1102
|
+
# Name (na)
|
|
1103
|
+
|
|
1104
|
+
# @missing: 0000..10FFFF; Name; <none>
|
|
1105
|
+
|
|
1106
|
+
# Name_Alias (Name_Alias)
|
|
1107
|
+
|
|
1108
|
+
# @missing: 0000..10FFFF; Name_Alias; <none>
|
|
1109
|
+
|
|
1110
|
+
# Noncharacter_Code_Point (NChar)
|
|
1111
|
+
|
|
1112
|
+
NChar; N ; No ; F ; False
|
|
1113
|
+
NChar; Y ; Yes ; T ; True
|
|
1114
|
+
|
|
1115
|
+
# Numeric_Type (nt)
|
|
1116
|
+
|
|
1117
|
+
nt ; De ; Decimal
|
|
1118
|
+
nt ; Di ; Digit
|
|
1119
|
+
nt ; None ; None
|
|
1120
|
+
nt ; Nu ; Numeric
|
|
1121
|
+
|
|
1122
|
+
# Numeric_Value (nv)
|
|
1123
|
+
|
|
1124
|
+
# @missing: 0000..10FFFF; Numeric_Value; NaN
|
|
1125
|
+
|
|
1126
|
+
# Other_Alphabetic (OAlpha)
|
|
1127
|
+
|
|
1128
|
+
OAlpha; N ; No ; F ; False
|
|
1129
|
+
OAlpha; Y ; Yes ; T ; True
|
|
1130
|
+
|
|
1131
|
+
# Other_Default_Ignorable_Code_Point (ODI)
|
|
1132
|
+
|
|
1133
|
+
ODI; N ; No ; F ; False
|
|
1134
|
+
ODI; Y ; Yes ; T ; True
|
|
1135
|
+
|
|
1136
|
+
# Other_Grapheme_Extend (OGr_Ext)
|
|
1137
|
+
|
|
1138
|
+
OGr_Ext; N ; No ; F ; False
|
|
1139
|
+
OGr_Ext; Y ; Yes ; T ; True
|
|
1140
|
+
|
|
1141
|
+
# Other_ID_Continue (OIDC)
|
|
1142
|
+
|
|
1143
|
+
OIDC; N ; No ; F ; False
|
|
1144
|
+
OIDC; Y ; Yes ; T ; True
|
|
1145
|
+
|
|
1146
|
+
# Other_ID_Start (OIDS)
|
|
1147
|
+
|
|
1148
|
+
OIDS; N ; No ; F ; False
|
|
1149
|
+
OIDS; Y ; Yes ; T ; True
|
|
1150
|
+
|
|
1151
|
+
# Other_Lowercase (OLower)
|
|
1152
|
+
|
|
1153
|
+
OLower; N ; No ; F ; False
|
|
1154
|
+
OLower; Y ; Yes ; T ; True
|
|
1155
|
+
|
|
1156
|
+
# Other_Math (OMath)
|
|
1157
|
+
|
|
1158
|
+
OMath; N ; No ; F ; False
|
|
1159
|
+
OMath; Y ; Yes ; T ; True
|
|
1160
|
+
|
|
1161
|
+
# Other_Uppercase (OUpper)
|
|
1162
|
+
|
|
1163
|
+
OUpper; N ; No ; F ; False
|
|
1164
|
+
OUpper; Y ; Yes ; T ; True
|
|
1165
|
+
|
|
1166
|
+
# Pattern_Syntax (Pat_Syn)
|
|
1167
|
+
|
|
1168
|
+
Pat_Syn; N ; No ; F ; False
|
|
1169
|
+
Pat_Syn; Y ; Yes ; T ; True
|
|
1170
|
+
|
|
1171
|
+
# Pattern_White_Space (Pat_WS)
|
|
1172
|
+
|
|
1173
|
+
Pat_WS; N ; No ; F ; False
|
|
1174
|
+
Pat_WS; Y ; Yes ; T ; True
|
|
1175
|
+
|
|
1176
|
+
# Prepended_Concatenation_Mark (PCM)
|
|
1177
|
+
|
|
1178
|
+
PCM; N ; No ; F ; False
|
|
1179
|
+
PCM; Y ; Yes ; T ; True
|
|
1180
|
+
|
|
1181
|
+
# Quotation_Mark (QMark)
|
|
1182
|
+
|
|
1183
|
+
QMark; N ; No ; F ; False
|
|
1184
|
+
QMark; Y ; Yes ; T ; True
|
|
1185
|
+
|
|
1186
|
+
# Radical (Radical)
|
|
1187
|
+
|
|
1188
|
+
Radical; N ; No ; F ; False
|
|
1189
|
+
Radical; Y ; Yes ; T ; True
|
|
1190
|
+
|
|
1191
|
+
# Regional_Indicator (RI)
|
|
1192
|
+
|
|
1193
|
+
RI ; N ; No ; F ; False
|
|
1194
|
+
RI ; Y ; Yes ; T ; True
|
|
1195
|
+
|
|
1196
|
+
# Script (sc)
|
|
1197
|
+
|
|
1198
|
+
sc ; Adlm ; Adlam
|
|
1199
|
+
sc ; Aghb ; Caucasian_Albanian
|
|
1200
|
+
sc ; Ahom ; Ahom
|
|
1201
|
+
sc ; Arab ; Arabic
|
|
1202
|
+
sc ; Armi ; Imperial_Aramaic
|
|
1203
|
+
sc ; Armn ; Armenian
|
|
1204
|
+
sc ; Avst ; Avestan
|
|
1205
|
+
sc ; Bali ; Balinese
|
|
1206
|
+
sc ; Bamu ; Bamum
|
|
1207
|
+
sc ; Bass ; Bassa_Vah
|
|
1208
|
+
sc ; Batk ; Batak
|
|
1209
|
+
sc ; Beng ; Bengali
|
|
1210
|
+
sc ; Bhks ; Bhaiksuki
|
|
1211
|
+
sc ; Bopo ; Bopomofo
|
|
1212
|
+
sc ; Brah ; Brahmi
|
|
1213
|
+
sc ; Brai ; Braille
|
|
1214
|
+
sc ; Bugi ; Buginese
|
|
1215
|
+
sc ; Buhd ; Buhid
|
|
1216
|
+
sc ; Cakm ; Chakma
|
|
1217
|
+
sc ; Cans ; Canadian_Aboriginal
|
|
1218
|
+
sc ; Cari ; Carian
|
|
1219
|
+
sc ; Cham ; Cham
|
|
1220
|
+
sc ; Cher ; Cherokee
|
|
1221
|
+
sc ; Copt ; Coptic ; Qaac
|
|
1222
|
+
sc ; Cprt ; Cypriot
|
|
1223
|
+
sc ; Cyrl ; Cyrillic
|
|
1224
|
+
sc ; Deva ; Devanagari
|
|
1225
|
+
sc ; Dogr ; Dogra
|
|
1226
|
+
sc ; Dsrt ; Deseret
|
|
1227
|
+
sc ; Dupl ; Duployan
|
|
1228
|
+
sc ; Egyp ; Egyptian_Hieroglyphs
|
|
1229
|
+
sc ; Elba ; Elbasan
|
|
1230
|
+
sc ; Elym ; Elymaic
|
|
1231
|
+
sc ; Ethi ; Ethiopic
|
|
1232
|
+
sc ; Geor ; Georgian
|
|
1233
|
+
sc ; Glag ; Glagolitic
|
|
1234
|
+
sc ; Gong ; Gunjala_Gondi
|
|
1235
|
+
sc ; Gonm ; Masaram_Gondi
|
|
1236
|
+
sc ; Goth ; Gothic
|
|
1237
|
+
sc ; Gran ; Grantha
|
|
1238
|
+
sc ; Grek ; Greek
|
|
1239
|
+
sc ; Gujr ; Gujarati
|
|
1240
|
+
sc ; Guru ; Gurmukhi
|
|
1241
|
+
sc ; Hang ; Hangul
|
|
1242
|
+
sc ; Hani ; Han
|
|
1243
|
+
sc ; Hano ; Hanunoo
|
|
1244
|
+
sc ; Hatr ; Hatran
|
|
1245
|
+
sc ; Hebr ; Hebrew
|
|
1246
|
+
sc ; Hira ; Hiragana
|
|
1247
|
+
sc ; Hluw ; Anatolian_Hieroglyphs
|
|
1248
|
+
sc ; Hmng ; Pahawh_Hmong
|
|
1249
|
+
sc ; Hmnp ; Nyiakeng_Puachue_Hmong
|
|
1250
|
+
sc ; Hrkt ; Katakana_Or_Hiragana
|
|
1251
|
+
sc ; Hung ; Old_Hungarian
|
|
1252
|
+
sc ; Ital ; Old_Italic
|
|
1253
|
+
sc ; Java ; Javanese
|
|
1254
|
+
sc ; Kali ; Kayah_Li
|
|
1255
|
+
sc ; Kana ; Katakana
|
|
1256
|
+
sc ; Khar ; Kharoshthi
|
|
1257
|
+
sc ; Khmr ; Khmer
|
|
1258
|
+
sc ; Khoj ; Khojki
|
|
1259
|
+
sc ; Knda ; Kannada
|
|
1260
|
+
sc ; Kthi ; Kaithi
|
|
1261
|
+
sc ; Lana ; Tai_Tham
|
|
1262
|
+
sc ; Laoo ; Lao
|
|
1263
|
+
sc ; Latn ; Latin
|
|
1264
|
+
sc ; Lepc ; Lepcha
|
|
1265
|
+
sc ; Limb ; Limbu
|
|
1266
|
+
sc ; Lina ; Linear_A
|
|
1267
|
+
sc ; Linb ; Linear_B
|
|
1268
|
+
sc ; Lisu ; Lisu
|
|
1269
|
+
sc ; Lyci ; Lycian
|
|
1270
|
+
sc ; Lydi ; Lydian
|
|
1271
|
+
sc ; Mahj ; Mahajani
|
|
1272
|
+
sc ; Maka ; Makasar
|
|
1273
|
+
sc ; Mand ; Mandaic
|
|
1274
|
+
sc ; Mani ; Manichaean
|
|
1275
|
+
sc ; Marc ; Marchen
|
|
1276
|
+
sc ; Medf ; Medefaidrin
|
|
1277
|
+
sc ; Mend ; Mende_Kikakui
|
|
1278
|
+
sc ; Merc ; Meroitic_Cursive
|
|
1279
|
+
sc ; Mero ; Meroitic_Hieroglyphs
|
|
1280
|
+
sc ; Mlym ; Malayalam
|
|
1281
|
+
sc ; Modi ; Modi
|
|
1282
|
+
sc ; Mong ; Mongolian
|
|
1283
|
+
sc ; Mroo ; Mro
|
|
1284
|
+
sc ; Mtei ; Meetei_Mayek
|
|
1285
|
+
sc ; Mult ; Multani
|
|
1286
|
+
sc ; Mymr ; Myanmar
|
|
1287
|
+
sc ; Nand ; Nandinagari
|
|
1288
|
+
sc ; Narb ; Old_North_Arabian
|
|
1289
|
+
sc ; Nbat ; Nabataean
|
|
1290
|
+
sc ; Newa ; Newa
|
|
1291
|
+
sc ; Nkoo ; Nko
|
|
1292
|
+
sc ; Nshu ; Nushu
|
|
1293
|
+
sc ; Ogam ; Ogham
|
|
1294
|
+
sc ; Olck ; Ol_Chiki
|
|
1295
|
+
sc ; Orkh ; Old_Turkic
|
|
1296
|
+
sc ; Orya ; Oriya
|
|
1297
|
+
sc ; Osge ; Osage
|
|
1298
|
+
sc ; Osma ; Osmanya
|
|
1299
|
+
sc ; Palm ; Palmyrene
|
|
1300
|
+
sc ; Pauc ; Pau_Cin_Hau
|
|
1301
|
+
sc ; Perm ; Old_Permic
|
|
1302
|
+
sc ; Phag ; Phags_Pa
|
|
1303
|
+
sc ; Phli ; Inscriptional_Pahlavi
|
|
1304
|
+
sc ; Phlp ; Psalter_Pahlavi
|
|
1305
|
+
sc ; Phnx ; Phoenician
|
|
1306
|
+
sc ; Plrd ; Miao
|
|
1307
|
+
sc ; Prti ; Inscriptional_Parthian
|
|
1308
|
+
sc ; Rjng ; Rejang
|
|
1309
|
+
sc ; Rohg ; Hanifi_Rohingya
|
|
1310
|
+
sc ; Runr ; Runic
|
|
1311
|
+
sc ; Samr ; Samaritan
|
|
1312
|
+
sc ; Sarb ; Old_South_Arabian
|
|
1313
|
+
sc ; Saur ; Saurashtra
|
|
1314
|
+
sc ; Sgnw ; SignWriting
|
|
1315
|
+
sc ; Shaw ; Shavian
|
|
1316
|
+
sc ; Shrd ; Sharada
|
|
1317
|
+
sc ; Sidd ; Siddham
|
|
1318
|
+
sc ; Sind ; Khudawadi
|
|
1319
|
+
sc ; Sinh ; Sinhala
|
|
1320
|
+
sc ; Sogd ; Sogdian
|
|
1321
|
+
sc ; Sogo ; Old_Sogdian
|
|
1322
|
+
sc ; Sora ; Sora_Sompeng
|
|
1323
|
+
sc ; Soyo ; Soyombo
|
|
1324
|
+
sc ; Sund ; Sundanese
|
|
1325
|
+
sc ; Sylo ; Syloti_Nagri
|
|
1326
|
+
sc ; Syrc ; Syriac
|
|
1327
|
+
sc ; Tagb ; Tagbanwa
|
|
1328
|
+
sc ; Takr ; Takri
|
|
1329
|
+
sc ; Tale ; Tai_Le
|
|
1330
|
+
sc ; Talu ; New_Tai_Lue
|
|
1331
|
+
sc ; Taml ; Tamil
|
|
1332
|
+
sc ; Tang ; Tangut
|
|
1333
|
+
sc ; Tavt ; Tai_Viet
|
|
1334
|
+
sc ; Telu ; Telugu
|
|
1335
|
+
sc ; Tfng ; Tifinagh
|
|
1336
|
+
sc ; Tglg ; Tagalog
|
|
1337
|
+
sc ; Thaa ; Thaana
|
|
1338
|
+
sc ; Thai ; Thai
|
|
1339
|
+
sc ; Tibt ; Tibetan
|
|
1340
|
+
sc ; Tirh ; Tirhuta
|
|
1341
|
+
sc ; Ugar ; Ugaritic
|
|
1342
|
+
sc ; Vaii ; Vai
|
|
1343
|
+
sc ; Wara ; Warang_Citi
|
|
1344
|
+
sc ; Wcho ; Wancho
|
|
1345
|
+
sc ; Xpeo ; Old_Persian
|
|
1346
|
+
sc ; Xsux ; Cuneiform
|
|
1347
|
+
sc ; Yiii ; Yi
|
|
1348
|
+
sc ; Zanb ; Zanabazar_Square
|
|
1349
|
+
sc ; Zinh ; Inherited ; Qaai
|
|
1350
|
+
sc ; Zyyy ; Common
|
|
1351
|
+
sc ; Zzzz ; Unknown
|
|
1352
|
+
|
|
1353
|
+
# Script_Extensions (scx)
|
|
1354
|
+
|
|
1355
|
+
# @missing: 0000..10FFFF; Script_Extensions; <script>
|
|
1356
|
+
|
|
1357
|
+
# Sentence_Break (SB)
|
|
1358
|
+
|
|
1359
|
+
SB ; AT ; ATerm
|
|
1360
|
+
SB ; CL ; Close
|
|
1361
|
+
SB ; CR ; CR
|
|
1362
|
+
SB ; EX ; Extend
|
|
1363
|
+
SB ; FO ; Format
|
|
1364
|
+
SB ; LE ; OLetter
|
|
1365
|
+
SB ; LF ; LF
|
|
1366
|
+
SB ; LO ; Lower
|
|
1367
|
+
SB ; NU ; Numeric
|
|
1368
|
+
SB ; SC ; SContinue
|
|
1369
|
+
SB ; SE ; Sep
|
|
1370
|
+
SB ; SP ; Sp
|
|
1371
|
+
SB ; ST ; STerm
|
|
1372
|
+
SB ; UP ; Upper
|
|
1373
|
+
SB ; XX ; Other
|
|
1374
|
+
|
|
1375
|
+
# Sentence_Terminal (STerm)
|
|
1376
|
+
|
|
1377
|
+
STerm; N ; No ; F ; False
|
|
1378
|
+
STerm; Y ; Yes ; T ; True
|
|
1379
|
+
|
|
1380
|
+
# Simple_Case_Folding (scf)
|
|
1381
|
+
|
|
1382
|
+
# @missing: 0000..10FFFF; Simple_Case_Folding; <code point>
|
|
1383
|
+
|
|
1384
|
+
# Simple_Lowercase_Mapping (slc)
|
|
1385
|
+
|
|
1386
|
+
# @missing: 0000..10FFFF; Simple_Lowercase_Mapping; <code point>
|
|
1387
|
+
|
|
1388
|
+
# Simple_Titlecase_Mapping (stc)
|
|
1389
|
+
|
|
1390
|
+
# @missing: 0000..10FFFF; Simple_Titlecase_Mapping; <code point>
|
|
1391
|
+
|
|
1392
|
+
# Simple_Uppercase_Mapping (suc)
|
|
1393
|
+
|
|
1394
|
+
# @missing: 0000..10FFFF; Simple_Uppercase_Mapping; <code point>
|
|
1395
|
+
|
|
1396
|
+
# Soft_Dotted (SD)
|
|
1397
|
+
|
|
1398
|
+
SD ; N ; No ; F ; False
|
|
1399
|
+
SD ; Y ; Yes ; T ; True
|
|
1400
|
+
|
|
1401
|
+
# Terminal_Punctuation (Term)
|
|
1402
|
+
|
|
1403
|
+
Term; N ; No ; F ; False
|
|
1404
|
+
Term; Y ; Yes ; T ; True
|
|
1405
|
+
|
|
1406
|
+
# Titlecase_Mapping (tc)
|
|
1407
|
+
|
|
1408
|
+
# @missing: 0000..10FFFF; Titlecase_Mapping; <code point>
|
|
1409
|
+
|
|
1410
|
+
# Unicode_1_Name (na1)
|
|
1411
|
+
|
|
1412
|
+
# @missing: 0000..10FFFF; Unicode_1_Name; <none>
|
|
1413
|
+
|
|
1414
|
+
# Unified_Ideograph (UIdeo)
|
|
1415
|
+
|
|
1416
|
+
UIdeo; N ; No ; F ; False
|
|
1417
|
+
UIdeo; Y ; Yes ; T ; True
|
|
1418
|
+
|
|
1419
|
+
# Uppercase (Upper)
|
|
1420
|
+
|
|
1421
|
+
Upper; N ; No ; F ; False
|
|
1422
|
+
Upper; Y ; Yes ; T ; True
|
|
1423
|
+
|
|
1424
|
+
# Uppercase_Mapping (uc)
|
|
1425
|
+
|
|
1426
|
+
# @missing: 0000..10FFFF; Uppercase_Mapping; <code point>
|
|
1427
|
+
|
|
1428
|
+
# Variation_Selector (VS)
|
|
1429
|
+
|
|
1430
|
+
VS ; N ; No ; F ; False
|
|
1431
|
+
VS ; Y ; Yes ; T ; True
|
|
1432
|
+
|
|
1433
|
+
# Vertical_Orientation (vo)
|
|
1434
|
+
|
|
1435
|
+
vo ; R ; Rotated
|
|
1436
|
+
vo ; Tr ; Transformed_Rotated
|
|
1437
|
+
vo ; Tu ; Transformed_Upright
|
|
1438
|
+
vo ; U ; Upright
|
|
1439
|
+
|
|
1440
|
+
# White_Space (WSpace)
|
|
1441
|
+
|
|
1442
|
+
WSpace; N ; No ; F ; False
|
|
1443
|
+
WSpace; Y ; Yes ; T ; True
|
|
1444
|
+
|
|
1445
|
+
# Word_Break (WB)
|
|
1446
|
+
|
|
1447
|
+
WB ; CR ; CR
|
|
1448
|
+
WB ; DQ ; Double_Quote
|
|
1449
|
+
WB ; EB ; E_Base
|
|
1450
|
+
WB ; EBG ; E_Base_GAZ
|
|
1451
|
+
WB ; EM ; E_Modifier
|
|
1452
|
+
WB ; EX ; ExtendNumLet
|
|
1453
|
+
WB ; Extend ; Extend
|
|
1454
|
+
WB ; FO ; Format
|
|
1455
|
+
WB ; GAZ ; Glue_After_Zwj
|
|
1456
|
+
WB ; HL ; Hebrew_Letter
|
|
1457
|
+
WB ; KA ; Katakana
|
|
1458
|
+
WB ; LE ; ALetter
|
|
1459
|
+
WB ; LF ; LF
|
|
1460
|
+
WB ; MB ; MidNumLet
|
|
1461
|
+
WB ; ML ; MidLetter
|
|
1462
|
+
WB ; MN ; MidNum
|
|
1463
|
+
WB ; NL ; Newline
|
|
1464
|
+
WB ; NU ; Numeric
|
|
1465
|
+
WB ; RI ; Regional_Indicator
|
|
1466
|
+
WB ; SQ ; Single_Quote
|
|
1467
|
+
WB ; WSegSpace ; WSegSpace
|
|
1468
|
+
WB ; XX ; Other
|
|
1469
|
+
WB ; ZWJ ; ZWJ
|
|
1470
|
+
|
|
1471
|
+
# XID_Continue (XIDC)
|
|
1472
|
+
|
|
1473
|
+
XIDC; N ; No ; F ; False
|
|
1474
|
+
XIDC; Y ; Yes ; T ; True
|
|
1475
|
+
|
|
1476
|
+
# XID_Start (XIDS)
|
|
1477
|
+
|
|
1478
|
+
XIDS; N ; No ; F ; False
|
|
1479
|
+
XIDS; Y ; Yes ; T ; True
|
|
1480
|
+
|
|
1481
|
+
# cjkAccountingNumeric (cjkAccountingNumeric)
|
|
1482
|
+
|
|
1483
|
+
# @missing: 0000..10FFFF; cjkAccountingNumeric; NaN
|
|
1484
|
+
|
|
1485
|
+
# cjkCompatibilityVariant (cjkCompatibilityVariant)
|
|
1486
|
+
|
|
1487
|
+
# @missing: 0000..10FFFF; cjkCompatibilityVariant; <code point>
|
|
1488
|
+
|
|
1489
|
+
# cjkIICore (cjkIICore)
|
|
1490
|
+
|
|
1491
|
+
# @missing: 0000..10FFFF; cjkIICore; <none>
|
|
1492
|
+
|
|
1493
|
+
# cjkIRG_GSource (cjkIRG_GSource)
|
|
1494
|
+
|
|
1495
|
+
# @missing: 0000..10FFFF; cjkIRG_GSource; <none>
|
|
1496
|
+
|
|
1497
|
+
# cjkIRG_HSource (cjkIRG_HSource)
|
|
1498
|
+
|
|
1499
|
+
# @missing: 0000..10FFFF; cjkIRG_HSource; <none>
|
|
1500
|
+
|
|
1501
|
+
# cjkIRG_JSource (cjkIRG_JSource)
|
|
1502
|
+
|
|
1503
|
+
# @missing: 0000..10FFFF; cjkIRG_JSource; <none>
|
|
1504
|
+
|
|
1505
|
+
# cjkIRG_KPSource (cjkIRG_KPSource)
|
|
1506
|
+
|
|
1507
|
+
# @missing: 0000..10FFFF; cjkIRG_KPSource; <none>
|
|
1508
|
+
|
|
1509
|
+
# cjkIRG_KSource (cjkIRG_KSource)
|
|
1510
|
+
|
|
1511
|
+
# @missing: 0000..10FFFF; cjkIRG_KSource; <none>
|
|
1512
|
+
|
|
1513
|
+
# cjkIRG_MSource (cjkIRG_MSource)
|
|
1514
|
+
|
|
1515
|
+
# @missing: 0000..10FFFF; cjkIRG_MSource; <none>
|
|
1516
|
+
|
|
1517
|
+
# cjkIRG_TSource (cjkIRG_TSource)
|
|
1518
|
+
|
|
1519
|
+
# @missing: 0000..10FFFF; cjkIRG_TSource; <none>
|
|
1520
|
+
|
|
1521
|
+
# cjkIRG_USource (cjkIRG_USource)
|
|
1522
|
+
|
|
1523
|
+
# @missing: 0000..10FFFF; cjkIRG_USource; <none>
|
|
1524
|
+
|
|
1525
|
+
# cjkIRG_VSource (cjkIRG_VSource)
|
|
1526
|
+
|
|
1527
|
+
# @missing: 0000..10FFFF; cjkIRG_VSource; <none>
|
|
1528
|
+
|
|
1529
|
+
# cjkOtherNumeric (cjkOtherNumeric)
|
|
1530
|
+
|
|
1531
|
+
# @missing: 0000..10FFFF; cjkOtherNumeric; NaN
|
|
1532
|
+
|
|
1533
|
+
# cjkPrimaryNumeric (cjkPrimaryNumeric)
|
|
1534
|
+
|
|
1535
|
+
# @missing: 0000..10FFFF; cjkPrimaryNumeric; NaN
|
|
1536
|
+
|
|
1537
|
+
# cjkRSUnicode (cjkRSUnicode)
|
|
1538
|
+
|
|
1539
|
+
# @missing: 0000..10FFFF; cjkRSUnicode; <none>
|
|
1540
|
+
|
|
1541
|
+
# EOF
|