1 # PropertyValueAliases-6.2.0.txt
2 # Date: 2012-08-14, 16:05:11 GMT [MD]
3 #
4 # Unicode Character Database
5 # Copyright (c) 1991-2012 Unicode, Inc.
6 # For terms of use, see http://www.unicode.org/terms_of_use.html
7 # For documentation, see http://www.unicode.org/reports/tr44/
8 #
9 # This file contains aliases for property values used in the UCD.
10 # These names can be used for XML formats of UCD data, for regular-expression
11 # property tests, and other programmatic textual descriptions of Unicode data.
12 #
13 # The names may be translated in appropriate environments, and additional
14 # aliases may be useful.
15 #
16 # FORMAT
17 #
18 # Each line describes a property value name.
19 # This consists of three or more fields, separated by semicolons.
20 #
21 # First Field: The first field describes the property for which that
22 # property value name is used.
23 #
24 # Second Field: The second field is an abbreviated name.
25 #
26 # Third Field: The third field is a long name.
27 #
28 # In the case of ccc, there are 4 fields. The second field is numeric, third
29 # is abbreviated, and fourth is long.
30 #
31 # The above are the preferred aliases. Other aliases may be listed in additional fields.
32 #
33 # Loose matching should be applied to all property names and property values, with
34 # the exception of String Property values. With loose matching of property names and
35 # values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property
36 # values, numeric equivalencies are applied: thus "01.00" is equivalent to "1".
37 #
38 # NOTE: Property value names are NOT unique across properties. For example:
39 #
40 # AL means Arabic Letter for the Bidi_Class property, and
41 # AL means Above_Left for the Combining_Class property, and
42 # AL means Alphabetic for the Line_Break property.
43 #
44 # In addition, some property names may be the same as some property value names.
45 # For example:
46 #
47 # sc means the Script property, and
48 # Sc means the General_Category property value Currency_Symbol (Sc)
49 #
50 # The combination of property value and property name is, however, unique.
51 #
52 # For more information, see UTS #18: Unicode Regular Expressions
53 # ================================================
54
55
56 # ASCII_Hex_Digit (AHex)
57
58 AHex; N ; No ; F ; False
59 AHex; Y ; Yes ; T ; True
60
61 # Age (age)
62
63 age; 1.1 ; V1_1
64 age; 2.0 ; V2_0
65 age; 2.1 ; V2_1
66 age; 3.0 ; V3_0
67 age; 3.1 ; V3_1
68 age; 3.2 ; V3_2
69 age; 4.0 ; V4_0
70 age; 4.1 ; V4_1
71 age; 5.0 ; V5_0
72 age; 5.1 ; V5_1
73 age; 5.2 ; V5_2
74 age; 6.0 ; V6_0
75 age; 6.1 ; V6_1
76 age; 6.2 ; V6_2
77 age; NA ; Unassigned
78
79 # Alphabetic (Alpha)
80
81 Alpha; N ; No ; F ; False
82 Alpha; Y ; Yes ; T ; True
83
84 # Bidi_Class (bc)
85
86 bc ; AL ; Arabic_Letter
87 bc ; AN ; Arabic_Number
88 bc ; B ; Paragraph_Separator
89 bc ; BN ; Boundary_Neutral
90 bc ; CS ; Common_Separator
91 bc ; EN ; European_Number
92 bc ; ES ; European_Separator
93 bc ; ET ; European_Terminator
94 bc ; L ; Left_To_Right
95 bc ; LRE ; Left_To_Right_Embedding
96 bc ; LRO ; Left_To_Right_Override
97 bc ; NSM ; Nonspacing_Mark
98 bc ; ON ; Other_Neutral
99 bc ; PDF ; Pop_Directional_Format
100 bc ; R ; Right_To_Left
101 bc ; RLE ; Right_To_Left_Embedding
102 bc ; RLO ; Right_To_Left_Override
103 bc ; S ; Segment_Separator
104 bc ; WS ; White_Space
105
106 # Bidi_Control (Bidi_C)
107
108 Bidi_C; N ; No ; F ; False
109 Bidi_C; Y ; Yes ; T ; True
110
111 # Bidi_Mirrored (Bidi_M)
112
113 Bidi_M; N ; No ; F ; False
114 Bidi_M; Y ; Yes ; T ; True
115
116 # Bidi_Mirroring_Glyph (bmg)
117
118 # @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; <none>
119
120 # Block (blk)
121
122 blk; Aegean_Numbers ; Aegean_Numbers
123 blk; Alchemical ; Alchemical_Symbols
124 blk; Alphabetic_PF ; Alphabetic_Presentation_Forms
125 blk; Ancient_Greek_Music ; Ancient_Greek_Musical_Notation
126 blk; Ancient_Greek_Numbers ; Ancient_Greek_Numbers
127 blk; Ancient_Symbols ; Ancient_Symbols
128 blk; Arabic ; Arabic
129 blk; Arabic_Ext_A ; Arabic_Extended_A
130 blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols
131 blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A
132 blk; Arabic_PF_B ; Arabic_Presentation_Forms_B
133 blk; Arabic_Sup ; Arabic_Supplement
134 blk; Armenian ; Armenian
135 blk; Arrows ; Arrows
136 blk; ASCII ; Basic_Latin
137 blk; Avestan ; Avestan
138 blk; Balinese ; Balinese
139 blk; Bamum ; Bamum
140 blk; Bamum_Sup ; Bamum_Supplement
141 blk; Batak ; Batak
142 blk; Bengali ; Bengali
143 blk; Block_Elements ; Block_Elements
144 blk; Bopomofo ; Bopomofo
145 blk; Bopomofo_Ext ; Bopomofo_Extended
146 blk; Box_Drawing ; Box_Drawing
147 blk; Brahmi ; Brahmi
148 blk; Braille ; Braille_Patterns
149 blk; Buginese ; Buginese
150 blk; Buhid ; Buhid
151 blk; Byzantine_Music ; Byzantine_Musical_Symbols
152 blk; Carian ; Carian
153 blk; Chakma ; Chakma
154 blk; Cham ; Cham
155 blk; Cherokee ; Cherokee
156 blk; CJK ; CJK_Unified_Ideographs
157 blk; CJK_Compat ; CJK_Compatibility
158 blk; CJK_Compat_Forms ; CJK_Compatibility_Forms
159 blk; CJK_Compat_Ideographs ; CJK_Compatibility_Ideographs
160 blk; CJK_Compat_Ideographs_Sup ; CJK_Compatibility_Ideographs_Supplement
161 blk; CJK_Ext_A ; CJK_Unified_Ideographs_Extension_A
162 blk; CJK_Ext_B ; CJK_Unified_Ideographs_Extension_B
163 blk; CJK_Ext_C ; CJK_Unified_Ideographs_Extension_C
164 blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D
165 blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement
166 blk; CJK_Strokes ; CJK_Strokes
167 blk; CJK_Symbols ; CJK_Symbols_And_Punctuation
168 blk; Compat_Jamo ; Hangul_Compatibility_Jamo
169 blk; Control_Pictures ; Control_Pictures
170 blk; Coptic ; Coptic
171 blk; Counting_Rod ; Counting_Rod_Numerals
172 blk; Cuneiform ; Cuneiform
173 blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation
174 blk; Currency_Symbols ; Currency_Symbols
175 blk; Cypriot_Syllabary ; Cypriot_Syllabary
176 blk; Cyrillic ; Cyrillic
177 blk; Cyrillic_Ext_A ; Cyrillic_Extended_A
178 blk; Cyrillic_Ext_B ; Cyrillic_Extended_B
179 blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary
180 blk; Deseret ; Deseret
181 blk; Devanagari ; Devanagari
182 blk; Devanagari_Ext ; Devanagari_Extended
183 blk; Diacriticals ; Combining_Diacritical_Marks
184 blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
185 blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
186 blk; Dingbats ; Dingbats
187 blk; Domino ; Domino_Tiles
188 blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
189 blk; Emoticons ; Emoticons
190 blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
191 blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
192 blk; Enclosed_CJK ; Enclosed_CJK_Letters_And_Months
193 blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement
194 blk; Ethiopic ; Ethiopic
195 blk; Ethiopic_Ext ; Ethiopic_Extended
196 blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
197 blk; Ethiopic_Sup ; Ethiopic_Supplement
198 blk; Geometric_Shapes ; Geometric_Shapes
199 blk; Georgian ; Georgian
200 blk; Georgian_Sup ; Georgian_Supplement
201 blk; Glagolitic ; Glagolitic
202 blk; Gothic ; Gothic
203 blk; Greek ; Greek_And_Coptic
204 blk; Greek_Ext ; Greek_Extended
205 blk; Gujarati ; Gujarati
206 blk; Gurmukhi ; Gurmukhi
207 blk; Half_And_Full_Forms ; Halfwidth_And_Fullwidth_Forms
208 blk; Half_Marks ; Combining_Half_Marks
209 blk; Hangul ; Hangul_Syllables
210 blk; Hanunoo ; Hanunoo
211 blk; Hebrew ; Hebrew
212 blk; High_PU_Surrogates ; High_Private_Use_Surrogates
213 blk; High_Surrogates ; High_Surrogates
214 blk; Hiragana ; Hiragana
215 blk; IDC ; Ideographic_Description_Characters
216 blk; Imperial_Aramaic ; Imperial_Aramaic
217 blk; Indic_Number_Forms ; Common_Indic_Number_Forms
218 blk; Inscriptional_Pahlavi ; Inscriptional_Pahlavi
219 blk; Inscriptional_Parthian ; Inscriptional_Parthian
220 blk; IPA_Ext ; IPA_Extensions
221 blk; Jamo ; Hangul_Jamo
222 blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A
223 blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B
224 blk; Javanese ; Javanese
225 blk; Kaithi ; Kaithi
226 blk; Kana_Sup ; Kana_Supplement
227 blk; Kanbun ; Kanbun
228 blk; Kangxi ; Kangxi_Radicals
229 blk; Kannada ; Kannada
230 blk; Katakana ; Katakana
231 blk; Katakana_Ext ; Katakana_Phonetic_Extensions
232 blk; Kayah_Li ; Kayah_Li
233 blk; Kharoshthi ; Kharoshthi
234 blk; Khmer ; Khmer
235 blk; Khmer_Symbols ; Khmer_Symbols
236 blk; Lao ; Lao
237 blk; Latin_1_Sup ; Latin_1_Supplement ; Latin_1
238 blk; Latin_Ext_A ; Latin_Extended_A
239 blk; Latin_Ext_Additional ; Latin_Extended_Additional
240 blk; Latin_Ext_B ; Latin_Extended_B
241 blk; Latin_Ext_C ; Latin_Extended_C
242 blk; Latin_Ext_D ; Latin_Extended_D
243 blk; Lepcha ; Lepcha
244 blk; Letterlike_Symbols ; Letterlike_Symbols
245 blk; Limbu ; Limbu
246 blk; Linear_B_Ideograms ; Linear_B_Ideograms
247 blk; Linear_B_Syllabary ; Linear_B_Syllabary
248 blk; Lisu ; Lisu
249 blk; Low_Surrogates ; Low_Surrogates
250 blk; Lycian ; Lycian
251 blk; Lydian ; Lydian
252 blk; Mahjong ; Mahjong_Tiles
253 blk; Malayalam ; Malayalam
254 blk; Mandaic ; Mandaic
255 blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols
256 blk; Math_Operators ; Mathematical_Operators
257 blk; Meetei_Mayek ; Meetei_Mayek
258 blk; Meetei_Mayek_Ext ; Meetei_Mayek_Extensions
259 blk; Meroitic_Cursive ; Meroitic_Cursive
260 blk; Meroitic_Hieroglyphs ; Meroitic_Hieroglyphs
261 blk; Miao ; Miao
262 blk; Misc_Arrows ; Miscellaneous_Symbols_And_Arrows
263 blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A
264 blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B
265 blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs
266 blk; Misc_Symbols ; Miscellaneous_Symbols
267 blk; Misc_Technical ; Miscellaneous_Technical
268 blk; Modifier_Letters ; Spacing_Modifier_Letters
269 blk; Modifier_Tone_Letters ; Modifier_Tone_Letters
270 blk; Mongolian ; Mongolian
271 blk; Music ; Musical_Symbols
272 blk; Myanmar ; Myanmar
273 blk; Myanmar_Ext_A ; Myanmar_Extended_A
274 blk; NB ; No_Block
275 blk; New_Tai_Lue ; New_Tai_Lue
276 blk; NKo ; NKo
277 blk; Number_Forms ; Number_Forms
278 blk; OCR ; Optical_Character_Recognition
279 blk; Ogham ; Ogham
280 blk; Ol_Chiki ; Ol_Chiki
281 blk; Old_Italic ; Old_Italic
282 blk; Old_Persian ; Old_Persian
283 blk; Old_South_Arabian ; Old_South_Arabian
284 blk; Old_Turkic ; Old_Turkic
285 blk; Oriya ; Oriya
286 blk; Osmanya ; Osmanya
287 blk; Phags_Pa ; Phags_Pa
288 blk; Phaistos ; Phaistos_Disc
289 blk; Phoenician ; Phoenician
290 blk; Phonetic_Ext ; Phonetic_Extensions
291 blk; Phonetic_Ext_Sup ; Phonetic_Extensions_Supplement
292 blk; Playing_Cards ; Playing_Cards
293 blk; PUA ; Private_Use_Area ; Private_Use
294 blk; Punctuation ; General_Punctuation
295 blk; Rejang ; Rejang
296 blk; Rumi ; Rumi_Numeral_Symbols
297 blk; Runic ; Runic
298 blk; Samaritan ; Samaritan
299 blk; Saurashtra ; Saurashtra
300 blk; Sharada ; Sharada
301 blk; Shavian ; Shavian
302 blk; Sinhala ; Sinhala
303 blk; Small_Forms ; Small_Form_Variants
304 blk; Sora_Sompeng ; Sora_Sompeng
305 blk; Specials ; Specials
306 blk; Sundanese ; Sundanese
307 blk; Sundanese_Sup ; Sundanese_Supplement
308 blk; Sup_Arrows_A ; Supplemental_Arrows_A
309 blk; Sup_Arrows_B ; Supplemental_Arrows_B
310 blk; Sup_Math_Operators ; Supplemental_Mathematical_Operators
311 blk; Sup_PUA_A ; Supplementary_Private_Use_Area_A
312 blk; Sup_PUA_B ; Supplementary_Private_Use_Area_B
313 blk; Sup_Punctuation ; Supplemental_Punctuation
314 blk; Super_And_Sub ; Superscripts_And_Subscripts
315 blk; Syloti_Nagri ; Syloti_Nagri
316 blk; Syriac ; Syriac
317 blk; Tagalog ; Tagalog
318 blk; Tagbanwa ; Tagbanwa
319 blk; Tags ; Tags
320 blk; Tai_Le ; Tai_Le
321 blk; Tai_Tham ; Tai_Tham
322 blk; Tai_Viet ; Tai_Viet
323 blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
324 blk; Takri ; Takri
325 blk; Tamil ; Tamil
326 blk; Telugu ; Telugu
327 blk; Thaana ; Thaana
328 blk; Thai ; Thai
329 blk; Tibetan ; Tibetan
330 blk; Tifinagh ; Tifinagh
331 blk; Transport_And_Map ; Transport_And_Map_Symbols
332 blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
333 blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
334 blk; Ugaritic ; Ugaritic
335 blk; Vai ; Vai
336 blk; Vedic_Ext ; Vedic_Extensions
337 blk; Vertical_Forms ; Vertical_Forms
338 blk; VS ; Variation_Selectors
339 blk; VS_Sup ; Variation_Selectors_Supplement
340 blk; Yi_Radicals ; Yi_Radicals
341 blk; Yi_Syllables ; Yi_Syllables
342 blk; Yijing ; Yijing_Hexagram_Symbols
343
344 # Canonical_Combining_Class (ccc)
345
346 ccc; 0; NR ; Not_Reordered
347 ccc; 1; OV ; Overlay
348 ccc; 7; NK ; Nukta
349 ccc; 8; KV ; Kana_Voicing
350 ccc; 9; VR ; Virama
351 ccc; 10; CCC10 ; CCC10
352 ccc; 11; CCC11 ; CCC11
353 ccc; 12; CCC12 ; CCC12
354 ccc; 13; CCC13 ; CCC13
355 ccc; 14; CCC14 ; CCC14
356 ccc; 15; CCC15 ; CCC15
357 ccc; 16; CCC16 ; CCC16
358 ccc; 17; CCC17 ; CCC17
359 ccc; 18; CCC18 ; CCC18
561 gc ; Nd ; Decimal_Number ; digit
562 gc ; Nl ; Letter_Number
563 gc ; No ; Other_Number
564 gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
565 gc ; Pc ; Connector_Punctuation
566 gc ; Pd ; Dash_Punctuation
567 gc ; Pe ; Close_Punctuation
568 gc ; Pf ; Final_Punctuation
569 gc ; Pi ; Initial_Punctuation
570 gc ; Po ; Other_Punctuation
571 gc ; Ps ; Open_Punctuation
572 gc ; S ; Symbol # Sc | Sk | Sm | So
573 gc ; Sc ; Currency_Symbol
574 gc ; Sk ; Modifier_Symbol
575 gc ; Sm ; Math_Symbol
576 gc ; So ; Other_Symbol
577 gc ; Z ; Separator # Zl | Zp | Zs
578 gc ; Zl ; Line_Separator
579 gc ; Zp ; Paragraph_Separator
580 gc ; Zs ; Space_Separator
581
582 # Grapheme_Base (Gr_Base)
583
584 Gr_Base; N ; No ; F ; False
585 Gr_Base; Y ; Yes ; T ; True
586
587 # Grapheme_Cluster_Break (GCB)
588
589 GCB; CN ; Control
590 GCB; CR ; CR
591 GCB; EX ; Extend
592 GCB; L ; L
593 GCB; LF ; LF
594 GCB; LV ; LV
595 GCB; LVT ; LVT
596 GCB; PP ; Prepend
597 GCB; RI ; Regional_Indicator
598 GCB; SM ; SpacingMark
599 GCB; T ; T
600 GCB; V ; V
645 IDC; Y ; Yes ; T ; True
646
647 # ID_Start (IDS)
648
649 IDS; N ; No ; F ; False
650 IDS; Y ; Yes ; T ; True
651
652 # ISO_Comment (isc)
653
654 # @missing: 0000..10FFFF; ISO_Comment; <none>
655
656 # Ideographic (Ideo)
657
658 Ideo; N ; No ; F ; False
659 Ideo; Y ; Yes ; T ; True
660
661 # Indic_Matra_Category (InMC)
662
663 InMC; Bottom ; Bottom
664 InMC; Bottom_And_Right ; Bottom_And_Right
665 InMC; Invisible ; Invisible
666 InMC; Left ; Left
667 InMC; Left_And_Right ; Left_And_Right
668 InMC; NA ; NA
669 InMC; Overstruck ; Overstruck
670 InMC; Right ; Right
671 InMC; Top ; Top
672 InMC; Top_And_Bottom ; Top_And_Bottom
673 InMC; Top_And_Bottom_And_Right ; Top_And_Bottom_And_Right
674 InMC; Top_And_Left ; Top_And_Left
675 InMC; Top_And_Left_And_Right ; Top_And_Left_And_Right
676 InMC; Top_And_Right ; Top_And_Right
677 InMC; Visual_Order_Left ; Visual_Order_Left
678
679 # Indic_Syllabic_Category (InSC)
680
681 InSC; Avagraha ; Avagraha
682 InSC; Bindu ; Bindu
683 InSC; Consonant ; Consonant
684 InSC; Consonant_Dead ; Consonant_Dead
685 InSC; Consonant_Final ; Consonant_Final
686 InSC; Consonant_Head_Letter ; Consonant_Head_Letter
687 InSC; Consonant_Medial ; Consonant_Medial
688 InSC; Consonant_Placeholder ; Consonant_Placeholder
689 InSC; Consonant_Repha ; Consonant_Repha
690 InSC; Consonant_Subjoined ; Consonant_Subjoined
691 InSC; Modifying_Letter ; Modifying_Letter
692 InSC; Nukta ; Nukta
693 InSC; Other ; Other
694 InSC; Register_Shifter ; Register_Shifter
695 InSC; Tone_Letter ; Tone_Letter
696 InSC; Tone_Mark ; Tone_Mark
697 InSC; Virama ; Virama
698 InSC; Visarga ; Visarga
699 InSC; Vowel ; Vowel
700 InSC; Vowel_Dependent ; Vowel_Dependent
701 InSC; Vowel_Independent ; Vowel_Independent
702
703 # Jamo_Short_Name (JSN)
704
705 # @missing: 0000..10FFFF; Jamo_Short_Name; <none>
706 JSN; A ; A
707 JSN; AE ; AE
708 JSN; B ; B
709 JSN; BB ; BB
710 JSN; BS ; BS
711 JSN; C ; C
712 JSN; D ; D
713 JSN; DD ; DD
714 JSN; E ; E
715 JSN; EO ; EO
716 JSN; EU ; EU
717 JSN; G ; G
718 JSN; GG ; GG
719 JSN; GS ; GS
720 JSN; H ; H
721 JSN; I ; I
722 JSN; J ; J
723 JSN; JJ ; JJ
724 JSN; K ; K
725 JSN; L ; L
738 JSN; O ; O
739 JSN; OE ; OE
740 JSN; P ; P
741 JSN; R ; R
742 JSN; S ; S
743 JSN; SS ; SS
744 JSN; T ; T
745 JSN; U ; U
746 JSN; WA ; WA
747 JSN; WAE ; WAE
748 JSN; WE ; WE
749 JSN; WEO ; WEO
750 JSN; WI ; WI
751 JSN; YA ; YA
752 JSN; YAE ; YAE
753 JSN; YE ; YE
754 JSN; YEO ; YEO
755 JSN; YI ; YI
756 JSN; YO ; YO
757 JSN; YU ; YU
758
759 # Join_Control (Join_C)
760
761 Join_C; N ; No ; F ; False
762 Join_C; Y ; Yes ; T ; True
763
764 # Joining_Group (jg)
765
766 jg ; Ain ; Ain
767 jg ; Alaph ; Alaph
768 jg ; Alef ; Alef
769 jg ; Beh ; Beh
770 jg ; Beth ; Beth
771 jg ; Burushaski_Yeh_Barree ; Burushaski_Yeh_Barree
772 jg ; Dal ; Dal
773 jg ; Dalath_Rish ; Dalath_Rish
774 jg ; E ; E
775 jg ; Farsi_Yeh ; Farsi_Yeh
776 jg ; Fe ; Fe
777 jg ; Feh ; Feh
778 jg ; Final_Semkath ; Final_Semkath
779 jg ; Gaf ; Gaf
780 jg ; Gamal ; Gamal
781 jg ; Hah ; Hah
782 jg ; He ; He
783 jg ; Heh ; Heh
784 jg ; Heh_Goal ; Heh_Goal
785 jg ; Heth ; Heth
786 jg ; Kaf ; Kaf
787 jg ; Kaph ; Kaph
788 jg ; Khaph ; Khaph
789 jg ; Knotted_Heh ; Knotted_Heh
790 jg ; Lam ; Lam
791 jg ; Lamadh ; Lamadh
792 jg ; Meem ; Meem
793 jg ; Mim ; Mim
794 jg ; No_Joining_Group ; No_Joining_Group
795 jg ; Noon ; Noon
796 jg ; Nun ; Nun
797 jg ; Nya ; Nya
798 jg ; Pe ; Pe
799 jg ; Qaf ; Qaf
800 jg ; Qaph ; Qaph
801 jg ; Reh ; Reh
802 jg ; Reversed_Pe ; Reversed_Pe
803 jg ; Rohingya_Yeh ; Rohingya_Yeh
804 jg ; Sad ; Sad
805 jg ; Sadhe ; Sadhe
806 jg ; Seen ; Seen
807 jg ; Semkath ; Semkath
808 jg ; Shin ; Shin
809 jg ; Swash_Kaf ; Swash_Kaf
810 jg ; Syriac_Waw ; Syriac_Waw
811 jg ; Tah ; Tah
812 jg ; Taw ; Taw
813 jg ; Teh_Marbuta ; Teh_Marbuta
814 jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
815 jg ; Teth ; Teth
816 jg ; Waw ; Waw
817 jg ; Yeh ; Yeh
818 jg ; Yeh_Barree ; Yeh_Barree
819 jg ; Yeh_With_Tail ; Yeh_With_Tail
820 jg ; Yudh ; Yudh
821 jg ; Yudh_He ; Yudh_He
822 jg ; Zain ; Zain
823 jg ; Zhain ; Zhain
824
825 # Joining_Type (jt)
826
827 jt ; C ; Join_Causing
828 jt ; D ; Dual_Joining
867 lb ; QU ; Quotation
868 lb ; RI ; Regional_Indicator
869 lb ; SA ; Complex_Context
870 lb ; SG ; Surrogate
871 lb ; SP ; Space
872 lb ; SY ; Break_Symbols
873 lb ; WJ ; Word_Joiner
874 lb ; XX ; Unknown
875 lb ; ZW ; ZWSpace
876
877 # Logical_Order_Exception (LOE)
878
879 LOE; N ; No ; F ; False
880 LOE; Y ; Yes ; T ; True
881
882 # Lowercase (Lower)
883
884 Lower; N ; No ; F ; False
885 Lower; Y ; Yes ; T ; True
886
887 # Math (Math)
888
889 Math; N ; No ; F ; False
890 Math; Y ; Yes ; T ; True
891
892 # NFC_Quick_Check (NFC_QC)
893
894 NFC_QC; M ; Maybe
895 NFC_QC; N ; No
896 NFC_QC; Y ; Yes
897
898 # NFD_Quick_Check (NFD_QC)
899
900 NFD_QC; N ; No
901 NFD_QC; Y ; Yes
902
903 # NFKC_Casefold (NFKC_CF)
904
905 # @missing: 0000..10FFFF; NFKC_Casefold; <code point>
906
989 Pat_WS; N ; No ; F ; False
990 Pat_WS; Y ; Yes ; T ; True
991
992 # Quotation_Mark (QMark)
993
994 QMark; N ; No ; F ; False
995 QMark; Y ; Yes ; T ; True
996
997 # Radical (Radical)
998
999 Radical; N ; No ; F ; False
1000 Radical; Y ; Yes ; T ; True
1001
1002 # STerm (STerm)
1003
1004 STerm; N ; No ; F ; False
1005 STerm; Y ; Yes ; T ; True
1006
1007 # Script (sc)
1008
1009 sc ; Arab ; Arabic
1010 sc ; Armi ; Imperial_Aramaic
1011 sc ; Armn ; Armenian
1012 sc ; Avst ; Avestan
1013 sc ; Bali ; Balinese
1014 sc ; Bamu ; Bamum
1015 sc ; Batk ; Batak
1016 sc ; Beng ; Bengali
1017 sc ; Bopo ; Bopomofo
1018 sc ; Brah ; Brahmi
1019 sc ; Brai ; Braille
1020 sc ; Bugi ; Buginese
1021 sc ; Buhd ; Buhid
1022 sc ; Cakm ; Chakma
1023 sc ; Cans ; Canadian_Aboriginal
1024 sc ; Cari ; Carian
1025 sc ; Cham ; Cham
1026 sc ; Cher ; Cherokee
1027 sc ; Copt ; Coptic ; Qaac
1028 sc ; Cprt ; Cypriot
1029 sc ; Cyrl ; Cyrillic
1030 sc ; Deva ; Devanagari
1031 sc ; Dsrt ; Deseret
1032 sc ; Egyp ; Egyptian_Hieroglyphs
1033 sc ; Ethi ; Ethiopic
1034 sc ; Geor ; Georgian
1035 sc ; Glag ; Glagolitic
1036 sc ; Goth ; Gothic
1037 sc ; Grek ; Greek
1038 sc ; Gujr ; Gujarati
1039 sc ; Guru ; Gurmukhi
1040 sc ; Hang ; Hangul
1041 sc ; Hani ; Han
1042 sc ; Hano ; Hanunoo
1043 sc ; Hebr ; Hebrew
1044 sc ; Hira ; Hiragana
1045 sc ; Hrkt ; Katakana_Or_Hiragana
1046 sc ; Ital ; Old_Italic
1047 sc ; Java ; Javanese
1048 sc ; Kali ; Kayah_Li
1049 sc ; Kana ; Katakana
1050 sc ; Khar ; Kharoshthi
1051 sc ; Khmr ; Khmer
1052 sc ; Knda ; Kannada
1053 sc ; Kthi ; Kaithi
1054 sc ; Lana ; Tai_Tham
1055 sc ; Laoo ; Lao
1056 sc ; Latn ; Latin
1057 sc ; Lepc ; Lepcha
1058 sc ; Limb ; Limbu
1059 sc ; Linb ; Linear_B
1060 sc ; Lisu ; Lisu
1061 sc ; Lyci ; Lycian
1062 sc ; Lydi ; Lydian
1063 sc ; Mand ; Mandaic
1064 sc ; Merc ; Meroitic_Cursive
1065 sc ; Mero ; Meroitic_Hieroglyphs
1066 sc ; Mlym ; Malayalam
1067 sc ; Mong ; Mongolian
1068 sc ; Mtei ; Meetei_Mayek
1069 sc ; Mymr ; Myanmar
1070 sc ; Nkoo ; Nko
1071 sc ; Ogam ; Ogham
1072 sc ; Olck ; Ol_Chiki
1073 sc ; Orkh ; Old_Turkic
1074 sc ; Orya ; Oriya
1075 sc ; Osma ; Osmanya
1076 sc ; Phag ; Phags_Pa
1077 sc ; Phli ; Inscriptional_Pahlavi
1078 sc ; Phnx ; Phoenician
1079 sc ; Plrd ; Miao
1080 sc ; Prti ; Inscriptional_Parthian
1081 sc ; Rjng ; Rejang
1082 sc ; Runr ; Runic
1083 sc ; Samr ; Samaritan
1084 sc ; Sarb ; Old_South_Arabian
1085 sc ; Saur ; Saurashtra
1086 sc ; Shaw ; Shavian
1087 sc ; Shrd ; Sharada
1088 sc ; Sinh ; Sinhala
1089 sc ; Sora ; Sora_Sompeng
1090 sc ; Sund ; Sundanese
1091 sc ; Sylo ; Syloti_Nagri
1092 sc ; Syrc ; Syriac
1093 sc ; Tagb ; Tagbanwa
1094 sc ; Takr ; Takri
1095 sc ; Tale ; Tai_Le
1096 sc ; Talu ; New_Tai_Lue
1097 sc ; Taml ; Tamil
1098 sc ; Tavt ; Tai_Viet
1099 sc ; Telu ; Telugu
1100 sc ; Tfng ; Tifinagh
1101 sc ; Tglg ; Tagalog
1102 sc ; Thaa ; Thaana
1103 sc ; Thai ; Thai
1104 sc ; Tibt ; Tibetan
1105 sc ; Ugar ; Ugaritic
1106 sc ; Vaii ; Vai
1107 sc ; Xpeo ; Old_Persian
1108 sc ; Xsux ; Cuneiform
1109 sc ; Yiii ; Yi
1110 sc ; Zinh ; Inherited ; Qaai
1111 sc ; Zyyy ; Common
1112 sc ; Zzzz ; Unknown
1113
1114 # Script_Extensions (scx)
1115
1116 # @missing: 0000..10FFFF; Script_Extensions; <script>
1117
1118 # Sentence_Break (SB)
1119
1120 SB ; AT ; ATerm
1121 SB ; CL ; Close
1122 SB ; CR ; CR
1123 SB ; EX ; Extend
1124 SB ; FO ; Format
1125 SB ; LE ; OLetter
1126 SB ; LF ; LF
1142 # @missing: 0000..10FFFF; Simple_Lowercase_Mapping; <code point>
1143
1144 # Simple_Titlecase_Mapping (stc)
1145
1146 # @missing: 0000..10FFFF; Simple_Titlecase_Mapping; <code point>
1147
1148 # Simple_Uppercase_Mapping (suc)
1149
1150 # @missing: 0000..10FFFF; Simple_Uppercase_Mapping; <code point>
1151
1152 # Soft_Dotted (SD)
1153
1154 SD ; N ; No ; F ; False
1155 SD ; Y ; Yes ; T ; True
1156
1157 # Terminal_Punctuation (Term)
1158
1159 Term; N ; No ; F ; False
1160 Term; Y ; Yes ; T ; True
1161
1162 # Unicode_1_Name (na1)
1163
1164 # @missing: 0000..10FFFF; Unicode_1_Name; <none>
1165
1166 # Unified_Ideograph (UIdeo)
1167
1168 UIdeo; N ; No ; F ; False
1169 UIdeo; Y ; Yes ; T ; True
1170
1171 # Uppercase (Upper)
1172
1173 Upper; N ; No ; F ; False
1174 Upper; Y ; Yes ; T ; True
1175
1176 # Variation_Selector (VS)
1177
1178 VS ; N ; No ; F ; False
1179 VS ; Y ; Yes ; T ; True
1180
1181 # White_Space (WSpace)
1182
1183 WSpace; N ; No ; F ; False
1184 WSpace; Y ; Yes ; T ; True
1185
1186 # Word_Break (WB)
1187
1188 WB ; CR ; CR
1189 WB ; EX ; ExtendNumLet
1190 WB ; Extend ; Extend
1191 WB ; FO ; Format
1192 WB ; KA ; Katakana
1193 WB ; LE ; ALetter
1194 WB ; LF ; LF
1195 WB ; MB ; MidNumLet
1196 WB ; ML ; MidLetter
1197 WB ; MN ; MidNum
1198 WB ; NL ; Newline
1199 WB ; NU ; Numeric
1200 WB ; RI ; Regional_Indicator
1201 WB ; XX ; Other
1202
1203 # XID_Continue (XIDC)
1204
1205 XIDC; N ; No ; F ; False
1206 XIDC; Y ; Yes ; T ; True
1207
1208 # XID_Start (XIDS)
1209
1210 XIDS; N ; No ; F ; False
1211 XIDS; Y ; Yes ; T ; True
1212
1213 # cjkAccountingNumeric (cjkAccountingNumeric)
1214
1215 # @missing: 0000..10FFFF; cjkAccountingNumeric; NaN
1216
1217 # cjkCompatibilityVariant (cjkCompatibilityVariant)
1218
1219 # @missing: 0000..10FFFF; cjkCompatibilityVariant; <code point>
1220
|
1 # PropertyValueAliases-7.0.0.txt
2 # Date: 2014-05-14, 23:55:16 GMT [MD]
3 #
4 # Unicode Character Database
5 # Copyright (c) 1991-2014 Unicode, Inc.
6 # For terms of use, see http://www.unicode.org/terms_of_use.html
7 # For documentation, see http://www.unicode.org/reports/tr44/
8 #
9 # This file contains aliases for property values used in the UCD.
10 # These names can be used for XML formats of UCD data, for regular-expression
11 # property tests, and other programmatic textual descriptions of Unicode data.
12 #
13 # The names may be translated in appropriate environments, and additional
14 # aliases may be useful.
15 #
16 # FORMAT
17 #
18 # Each line describes a property value name.
19 # This consists of three or more fields, separated by semicolons.
20 #
21 # First Field: The first field describes the property for which that
22 # property value name is used.
23 #
24 # Second Field: The second field is an abbreviated name.
25 #
26 # Third Field: The third field is a long name.
27 #
28 # In the case of ccc, there are 4 fields. The second field is numeric, third
29 # is abbreviated, and fourth is long.
30 #
31 # The above are the preferred aliases. Other aliases may be listed in additional fields.
32 #
33 # Loose matching should be applied to all property names and property values, with
34 # the exception of String Property values. With loose matching of property names and
35 # values, the case distinctions, whitespace, hyphens, and '_' are ignored.
36 # For Numeric Property values, numeric equivalence is applied: thus "01.00"
37 # is equivalent to "1".
38 #
39 # NOTE: Property value names are NOT unique across properties. For example:
40 #
41 # AL means Arabic Letter for the Bidi_Class property, and
42 # AL means Above_Left for the Canonical_Combining_Class property, and
43 # AL means Alphabetic for the Line_Break property.
44 #
45 # In addition, some property names may be the same as some property value names.
46 # For example:
47 #
48 # sc means the Script property, and
49 # Sc means the General_Category property value Currency_Symbol (Sc)
50 #
51 # The combination of property value and property name is, however, unique.
52 #
53 # For more information, see UTS #18: Unicode Regular Expressions
54 # ================================================
55
56
57 # ASCII_Hex_Digit (AHex)
58
59 AHex; N ; No ; F ; False
60 AHex; Y ; Yes ; T ; True
61
62 # Age (age)
63
64 age; 1.1 ; V1_1
65 age; 2.0 ; V2_0
66 age; 2.1 ; V2_1
67 age; 3.0 ; V3_0
68 age; 3.1 ; V3_1
69 age; 3.2 ; V3_2
70 age; 4.0 ; V4_0
71 age; 4.1 ; V4_1
72 age; 5.0 ; V5_0
73 age; 5.1 ; V5_1
74 age; 5.2 ; V5_2
75 age; 6.0 ; V6_0
76 age; 6.1 ; V6_1
77 age; 6.2 ; V6_2
78 age; 6.3 ; V6_3
79 age; 7.0 ; V7_0
80 age; NA ; Unassigned
81
82 # Alphabetic (Alpha)
83
84 Alpha; N ; No ; F ; False
85 Alpha; Y ; Yes ; T ; True
86
87 # Bidi_Class (bc)
88
89 bc ; AL ; Arabic_Letter
90 bc ; AN ; Arabic_Number
91 bc ; B ; Paragraph_Separator
92 bc ; BN ; Boundary_Neutral
93 bc ; CS ; Common_Separator
94 bc ; EN ; European_Number
95 bc ; ES ; European_Separator
96 bc ; ET ; European_Terminator
97 bc ; FSI ; First_Strong_Isolate
98 bc ; L ; Left_To_Right
99 bc ; LRE ; Left_To_Right_Embedding
100 bc ; LRI ; Left_To_Right_Isolate
101 bc ; LRO ; Left_To_Right_Override
102 bc ; NSM ; Nonspacing_Mark
103 bc ; ON ; Other_Neutral
104 bc ; PDF ; Pop_Directional_Format
105 bc ; PDI ; Pop_Directional_Isolate
106 bc ; R ; Right_To_Left
107 bc ; RLE ; Right_To_Left_Embedding
108 bc ; RLI ; Right_To_Left_Isolate
109 bc ; RLO ; Right_To_Left_Override
110 bc ; S ; Segment_Separator
111 bc ; WS ; White_Space
112
113 # Bidi_Control (Bidi_C)
114
115 Bidi_C; N ; No ; F ; False
116 Bidi_C; Y ; Yes ; T ; True
117
118 # Bidi_Mirrored (Bidi_M)
119
120 Bidi_M; N ; No ; F ; False
121 Bidi_M; Y ; Yes ; T ; True
122
123 # Bidi_Mirroring_Glyph (bmg)
124
125 # @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; <none>
126
127 # Bidi_Paired_Bracket (bpb)
128
129 # @missing: 0000..10FFFF; Bidi_Paired_Bracket; <none>
130
131 # Bidi_Paired_Bracket_Type (bpt)
132
133 bpt; c ; Close
134 bpt; n ; None
135 bpt; o ; Open
136 # @missing: 0000..10FFFF; Bidi_Paired_Bracket_Type; n
137
138 # Block (blk)
139
140 blk; Aegean_Numbers ; Aegean_Numbers
141 blk; Alchemical ; Alchemical_Symbols
142 blk; Alphabetic_PF ; Alphabetic_Presentation_Forms
143 blk; Ancient_Greek_Music ; Ancient_Greek_Musical_Notation
144 blk; Ancient_Greek_Numbers ; Ancient_Greek_Numbers
145 blk; Ancient_Symbols ; Ancient_Symbols
146 blk; Arabic ; Arabic
147 blk; Arabic_Ext_A ; Arabic_Extended_A
148 blk; Arabic_Math ; Arabic_Mathematical_Alphabetic_Symbols
149 blk; Arabic_PF_A ; Arabic_Presentation_Forms_A ; Arabic_Presentation_Forms-A
150 blk; Arabic_PF_B ; Arabic_Presentation_Forms_B
151 blk; Arabic_Sup ; Arabic_Supplement
152 blk; Armenian ; Armenian
153 blk; Arrows ; Arrows
154 blk; ASCII ; Basic_Latin
155 blk; Avestan ; Avestan
156 blk; Balinese ; Balinese
157 blk; Bamum ; Bamum
158 blk; Bamum_Sup ; Bamum_Supplement
159 blk; Bassa_Vah ; Bassa_Vah
160 blk; Batak ; Batak
161 blk; Bengali ; Bengali
162 blk; Block_Elements ; Block_Elements
163 blk; Bopomofo ; Bopomofo
164 blk; Bopomofo_Ext ; Bopomofo_Extended
165 blk; Box_Drawing ; Box_Drawing
166 blk; Brahmi ; Brahmi
167 blk; Braille ; Braille_Patterns
168 blk; Buginese ; Buginese
169 blk; Buhid ; Buhid
170 blk; Byzantine_Music ; Byzantine_Musical_Symbols
171 blk; Carian ; Carian
172 blk; Caucasian_Albanian ; Caucasian_Albanian
173 blk; Chakma ; Chakma
174 blk; Cham ; Cham
175 blk; Cherokee ; Cherokee
176 blk; CJK ; CJK_Unified_Ideographs
177 blk; CJK_Compat ; CJK_Compatibility
178 blk; CJK_Compat_Forms ; CJK_Compatibility_Forms
179 blk; CJK_Compat_Ideographs ; CJK_Compatibility_Ideographs
180 blk; CJK_Compat_Ideographs_Sup ; CJK_Compatibility_Ideographs_Supplement
181 blk; CJK_Ext_A ; CJK_Unified_Ideographs_Extension_A
182 blk; CJK_Ext_B ; CJK_Unified_Ideographs_Extension_B
183 blk; CJK_Ext_C ; CJK_Unified_Ideographs_Extension_C
184 blk; CJK_Ext_D ; CJK_Unified_Ideographs_Extension_D
185 blk; CJK_Radicals_Sup ; CJK_Radicals_Supplement
186 blk; CJK_Strokes ; CJK_Strokes
187 blk; CJK_Symbols ; CJK_Symbols_And_Punctuation
188 blk; Compat_Jamo ; Hangul_Compatibility_Jamo
189 blk; Control_Pictures ; Control_Pictures
190 blk; Coptic ; Coptic
191 blk; Coptic_Epact_Numbers ; Coptic_Epact_Numbers
192 blk; Counting_Rod ; Counting_Rod_Numerals
193 blk; Cuneiform ; Cuneiform
194 blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation
195 blk; Currency_Symbols ; Currency_Symbols
196 blk; Cypriot_Syllabary ; Cypriot_Syllabary
197 blk; Cyrillic ; Cyrillic
198 blk; Cyrillic_Ext_A ; Cyrillic_Extended_A
199 blk; Cyrillic_Ext_B ; Cyrillic_Extended_B
200 blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary
201 blk; Deseret ; Deseret
202 blk; Devanagari ; Devanagari
203 blk; Devanagari_Ext ; Devanagari_Extended
204 blk; Diacriticals ; Combining_Diacritical_Marks
205 blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended
206 blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
207 blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
208 blk; Dingbats ; Dingbats
209 blk; Domino ; Domino_Tiles
210 blk; Duployan ; Duployan
211 blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
212 blk; Elbasan ; Elbasan
213 blk; Emoticons ; Emoticons
214 blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
215 blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
216 blk; Enclosed_CJK ; Enclosed_CJK_Letters_And_Months
217 blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement
218 blk; Ethiopic ; Ethiopic
219 blk; Ethiopic_Ext ; Ethiopic_Extended
220 blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
221 blk; Ethiopic_Sup ; Ethiopic_Supplement
222 blk; Geometric_Shapes ; Geometric_Shapes
223 blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended
224 blk; Georgian ; Georgian
225 blk; Georgian_Sup ; Georgian_Supplement
226 blk; Glagolitic ; Glagolitic
227 blk; Gothic ; Gothic
228 blk; Grantha ; Grantha
229 blk; Greek ; Greek_And_Coptic
230 blk; Greek_Ext ; Greek_Extended
231 blk; Gujarati ; Gujarati
232 blk; Gurmukhi ; Gurmukhi
233 blk; Half_And_Full_Forms ; Halfwidth_And_Fullwidth_Forms
234 blk; Half_Marks ; Combining_Half_Marks
235 blk; Hangul ; Hangul_Syllables
236 blk; Hanunoo ; Hanunoo
237 blk; Hebrew ; Hebrew
238 blk; High_PU_Surrogates ; High_Private_Use_Surrogates
239 blk; High_Surrogates ; High_Surrogates
240 blk; Hiragana ; Hiragana
241 blk; IDC ; Ideographic_Description_Characters
242 blk; Imperial_Aramaic ; Imperial_Aramaic
243 blk; Indic_Number_Forms ; Common_Indic_Number_Forms
244 blk; Inscriptional_Pahlavi ; Inscriptional_Pahlavi
245 blk; Inscriptional_Parthian ; Inscriptional_Parthian
246 blk; IPA_Ext ; IPA_Extensions
247 blk; Jamo ; Hangul_Jamo
248 blk; Jamo_Ext_A ; Hangul_Jamo_Extended_A
249 blk; Jamo_Ext_B ; Hangul_Jamo_Extended_B
250 blk; Javanese ; Javanese
251 blk; Kaithi ; Kaithi
252 blk; Kana_Sup ; Kana_Supplement
253 blk; Kanbun ; Kanbun
254 blk; Kangxi ; Kangxi_Radicals
255 blk; Kannada ; Kannada
256 blk; Katakana ; Katakana
257 blk; Katakana_Ext ; Katakana_Phonetic_Extensions
258 blk; Kayah_Li ; Kayah_Li
259 blk; Kharoshthi ; Kharoshthi
260 blk; Khmer ; Khmer
261 blk; Khmer_Symbols ; Khmer_Symbols
262 blk; Khojki ; Khojki
263 blk; Khudawadi ; Khudawadi
264 blk; Lao ; Lao
265 blk; Latin_1_Sup ; Latin_1_Supplement ; Latin_1
266 blk; Latin_Ext_A ; Latin_Extended_A
267 blk; Latin_Ext_Additional ; Latin_Extended_Additional
268 blk; Latin_Ext_B ; Latin_Extended_B
269 blk; Latin_Ext_C ; Latin_Extended_C
270 blk; Latin_Ext_D ; Latin_Extended_D
271 blk; Latin_Ext_E ; Latin_Extended_E
272 blk; Lepcha ; Lepcha
273 blk; Letterlike_Symbols ; Letterlike_Symbols
274 blk; Limbu ; Limbu
275 blk; Linear_A ; Linear_A
276 blk; Linear_B_Ideograms ; Linear_B_Ideograms
277 blk; Linear_B_Syllabary ; Linear_B_Syllabary
278 blk; Lisu ; Lisu
279 blk; Low_Surrogates ; Low_Surrogates
280 blk; Lycian ; Lycian
281 blk; Lydian ; Lydian
282 blk; Mahajani ; Mahajani
283 blk; Mahjong ; Mahjong_Tiles
284 blk; Malayalam ; Malayalam
285 blk; Mandaic ; Mandaic
286 blk; Manichaean ; Manichaean
287 blk; Math_Alphanum ; Mathematical_Alphanumeric_Symbols
288 blk; Math_Operators ; Mathematical_Operators
289 blk; Meetei_Mayek ; Meetei_Mayek
290 blk; Meetei_Mayek_Ext ; Meetei_Mayek_Extensions
291 blk; Mende_Kikakui ; Mende_Kikakui
292 blk; Meroitic_Cursive ; Meroitic_Cursive
293 blk; Meroitic_Hieroglyphs ; Meroitic_Hieroglyphs
294 blk; Miao ; Miao
295 blk; Misc_Arrows ; Miscellaneous_Symbols_And_Arrows
296 blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A
297 blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B
298 blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs
299 blk; Misc_Symbols ; Miscellaneous_Symbols
300 blk; Misc_Technical ; Miscellaneous_Technical
301 blk; Modi ; Modi
302 blk; Modifier_Letters ; Spacing_Modifier_Letters
303 blk; Modifier_Tone_Letters ; Modifier_Tone_Letters
304 blk; Mongolian ; Mongolian
305 blk; Mro ; Mro
306 blk; Music ; Musical_Symbols
307 blk; Myanmar ; Myanmar
308 blk; Myanmar_Ext_A ; Myanmar_Extended_A
309 blk; Myanmar_Ext_B ; Myanmar_Extended_B
310 blk; Nabataean ; Nabataean
311 blk; NB ; No_Block
312 blk; New_Tai_Lue ; New_Tai_Lue
313 blk; NKo ; NKo
314 blk; Number_Forms ; Number_Forms
315 blk; OCR ; Optical_Character_Recognition
316 blk; Ogham ; Ogham
317 blk; Ol_Chiki ; Ol_Chiki
318 blk; Old_Italic ; Old_Italic
319 blk; Old_North_Arabian ; Old_North_Arabian
320 blk; Old_Permic ; Old_Permic
321 blk; Old_Persian ; Old_Persian
322 blk; Old_South_Arabian ; Old_South_Arabian
323 blk; Old_Turkic ; Old_Turkic
324 blk; Oriya ; Oriya
325 blk; Ornamental_Dingbats ; Ornamental_Dingbats
326 blk; Osmanya ; Osmanya
327 blk; Pahawh_Hmong ; Pahawh_Hmong
328 blk; Palmyrene ; Palmyrene
329 blk; Pau_Cin_Hau ; Pau_Cin_Hau
330 blk; Phags_Pa ; Phags_Pa
331 blk; Phaistos ; Phaistos_Disc
332 blk; Phoenician ; Phoenician
333 blk; Phonetic_Ext ; Phonetic_Extensions
334 blk; Phonetic_Ext_Sup ; Phonetic_Extensions_Supplement
335 blk; Playing_Cards ; Playing_Cards
336 blk; Psalter_Pahlavi ; Psalter_Pahlavi
337 blk; PUA ; Private_Use_Area ; Private_Use
338 blk; Punctuation ; General_Punctuation
339 blk; Rejang ; Rejang
340 blk; Rumi ; Rumi_Numeral_Symbols
341 blk; Runic ; Runic
342 blk; Samaritan ; Samaritan
343 blk; Saurashtra ; Saurashtra
344 blk; Sharada ; Sharada
345 blk; Shavian ; Shavian
346 blk; Shorthand_Format_Controls ; Shorthand_Format_Controls
347 blk; Siddham ; Siddham
348 blk; Sinhala ; Sinhala
349 blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers
350 blk; Small_Forms ; Small_Form_Variants
351 blk; Sora_Sompeng ; Sora_Sompeng
352 blk; Specials ; Specials
353 blk; Sundanese ; Sundanese
354 blk; Sundanese_Sup ; Sundanese_Supplement
355 blk; Sup_Arrows_A ; Supplemental_Arrows_A
356 blk; Sup_Arrows_B ; Supplemental_Arrows_B
357 blk; Sup_Arrows_C ; Supplemental_Arrows_C
358 blk; Sup_Math_Operators ; Supplemental_Mathematical_Operators
359 blk; Sup_PUA_A ; Supplementary_Private_Use_Area_A
360 blk; Sup_PUA_B ; Supplementary_Private_Use_Area_B
361 blk; Sup_Punctuation ; Supplemental_Punctuation
362 blk; Super_And_Sub ; Superscripts_And_Subscripts
363 blk; Syloti_Nagri ; Syloti_Nagri
364 blk; Syriac ; Syriac
365 blk; Tagalog ; Tagalog
366 blk; Tagbanwa ; Tagbanwa
367 blk; Tags ; Tags
368 blk; Tai_Le ; Tai_Le
369 blk; Tai_Tham ; Tai_Tham
370 blk; Tai_Viet ; Tai_Viet
371 blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
372 blk; Takri ; Takri
373 blk; Tamil ; Tamil
374 blk; Telugu ; Telugu
375 blk; Thaana ; Thaana
376 blk; Thai ; Thai
377 blk; Tibetan ; Tibetan
378 blk; Tifinagh ; Tifinagh
379 blk; Tirhuta ; Tirhuta
380 blk; Transport_And_Map ; Transport_And_Map_Symbols
381 blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
382 blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
383 blk; Ugaritic ; Ugaritic
384 blk; Vai ; Vai
385 blk; Vedic_Ext ; Vedic_Extensions
386 blk; Vertical_Forms ; Vertical_Forms
387 blk; VS ; Variation_Selectors
388 blk; VS_Sup ; Variation_Selectors_Supplement
389 blk; Warang_Citi ; Warang_Citi
390 blk; Yi_Radicals ; Yi_Radicals
391 blk; Yi_Syllables ; Yi_Syllables
392 blk; Yijing ; Yijing_Hexagram_Symbols
393
394 # Canonical_Combining_Class (ccc)
395
396 ccc; 0; NR ; Not_Reordered
397 ccc; 1; OV ; Overlay
398 ccc; 7; NK ; Nukta
399 ccc; 8; KV ; Kana_Voicing
400 ccc; 9; VR ; Virama
401 ccc; 10; CCC10 ; CCC10
402 ccc; 11; CCC11 ; CCC11
403 ccc; 12; CCC12 ; CCC12
404 ccc; 13; CCC13 ; CCC13
405 ccc; 14; CCC14 ; CCC14
406 ccc; 15; CCC15 ; CCC15
407 ccc; 16; CCC16 ; CCC16
408 ccc; 17; CCC17 ; CCC17
409 ccc; 18; CCC18 ; CCC18
611 gc ; Nd ; Decimal_Number ; digit
612 gc ; Nl ; Letter_Number
613 gc ; No ; Other_Number
614 gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
615 gc ; Pc ; Connector_Punctuation
616 gc ; Pd ; Dash_Punctuation
617 gc ; Pe ; Close_Punctuation
618 gc ; Pf ; Final_Punctuation
619 gc ; Pi ; Initial_Punctuation
620 gc ; Po ; Other_Punctuation
621 gc ; Ps ; Open_Punctuation
622 gc ; S ; Symbol # Sc | Sk | Sm | So
623 gc ; Sc ; Currency_Symbol
624 gc ; Sk ; Modifier_Symbol
625 gc ; Sm ; Math_Symbol
626 gc ; So ; Other_Symbol
627 gc ; Z ; Separator # Zl | Zp | Zs
628 gc ; Zl ; Line_Separator
629 gc ; Zp ; Paragraph_Separator
630 gc ; Zs ; Space_Separator
631 # @missing: 0000..10FFFF; General_Category; Unassigned
632
633 # Grapheme_Base (Gr_Base)
634
635 Gr_Base; N ; No ; F ; False
636 Gr_Base; Y ; Yes ; T ; True
637
638 # Grapheme_Cluster_Break (GCB)
639
640 GCB; CN ; Control
641 GCB; CR ; CR
642 GCB; EX ; Extend
643 GCB; L ; L
644 GCB; LF ; LF
645 GCB; LV ; LV
646 GCB; LVT ; LVT
647 GCB; PP ; Prepend
648 GCB; RI ; Regional_Indicator
649 GCB; SM ; SpacingMark
650 GCB; T ; T
651 GCB; V ; V
696 IDC; Y ; Yes ; T ; True
697
698 # ID_Start (IDS)
699
700 IDS; N ; No ; F ; False
701 IDS; Y ; Yes ; T ; True
702
703 # ISO_Comment (isc)
704
705 # @missing: 0000..10FFFF; ISO_Comment; <none>
706
707 # Ideographic (Ideo)
708
709 Ideo; N ; No ; F ; False
710 Ideo; Y ; Yes ; T ; True
711
712 # Indic_Matra_Category (InMC)
713
714 InMC; Bottom ; Bottom
715 InMC; Bottom_And_Right ; Bottom_And_Right
716 InMC; Left ; Left
717 InMC; Left_And_Right ; Left_And_Right
718 InMC; NA ; NA
719 InMC; Overstruck ; Overstruck
720 InMC; Right ; Right
721 InMC; Top ; Top
722 InMC; Top_And_Bottom ; Top_And_Bottom
723 InMC; Top_And_Bottom_And_Right ; Top_And_Bottom_And_Right
724 InMC; Top_And_Left ; Top_And_Left
725 InMC; Top_And_Left_And_Right ; Top_And_Left_And_Right
726 InMC; Top_And_Right ; Top_And_Right
727 InMC; Visual_Order_Left ; Visual_Order_Left
728
729 # Indic_Syllabic_Category (InSC)
730
731 InSC; Avagraha ; Avagraha
732 InSC; Bindu ; Bindu
733 InSC; Brahmi_Joining_Number ; Brahmi_Joining_Number
734 InSC; Cantillation_Mark ; Cantillation_Mark
735 InSC; Consonant ; Consonant
736 InSC; Consonant_Dead ; Consonant_Dead
737 InSC; Consonant_Final ; Consonant_Final
738 InSC; Consonant_Head_Letter ; Consonant_Head_Letter
739 InSC; Consonant_Medial ; Consonant_Medial
740 InSC; Consonant_Placeholder ; Consonant_Placeholder
741 InSC; Consonant_Preceding_Repha ; Consonant_Preceding_Repha
742 InSC; Consonant_Subjoined ; Consonant_Subjoined
743 InSC; Consonant_Succeeding_Repha ; Consonant_Succeeding_Repha
744 InSC; Gemination_Mark ; Gemination_Mark
745 InSC; Invisible_Stacker ; Invisible_Stacker
746 InSC; Joiner ; Joiner
747 InSC; Modifying_Letter ; Modifying_Letter
748 InSC; Non_Joiner ; Non_Joiner
749 InSC; Nukta ; Nukta
750 InSC; Number ; Number
751 InSC; Number_Joiner ; Number_Joiner
752 InSC; Other ; Other
753 InSC; Pure_Killer ; Pure_Killer
754 InSC; Register_Shifter ; Register_Shifter
755 InSC; Tone_Letter ; Tone_Letter
756 InSC; Tone_Mark ; Tone_Mark
757 InSC; Virama ; Virama
758 InSC; Visarga ; Visarga
759 InSC; Vowel ; Vowel
760 InSC; Vowel_Dependent ; Vowel_Dependent
761 InSC; Vowel_Independent ; Vowel_Independent
762
763 # Jamo_Short_Name (JSN)
764
765 JSN; A ; A
766 JSN; AE ; AE
767 JSN; B ; B
768 JSN; BB ; BB
769 JSN; BS ; BS
770 JSN; C ; C
771 JSN; D ; D
772 JSN; DD ; DD
773 JSN; E ; E
774 JSN; EO ; EO
775 JSN; EU ; EU
776 JSN; G ; G
777 JSN; GG ; GG
778 JSN; GS ; GS
779 JSN; H ; H
780 JSN; I ; I
781 JSN; J ; J
782 JSN; JJ ; JJ
783 JSN; K ; K
784 JSN; L ; L
797 JSN; O ; O
798 JSN; OE ; OE
799 JSN; P ; P
800 JSN; R ; R
801 JSN; S ; S
802 JSN; SS ; SS
803 JSN; T ; T
804 JSN; U ; U
805 JSN; WA ; WA
806 JSN; WAE ; WAE
807 JSN; WE ; WE
808 JSN; WEO ; WEO
809 JSN; WI ; WI
810 JSN; YA ; YA
811 JSN; YAE ; YAE
812 JSN; YE ; YE
813 JSN; YEO ; YEO
814 JSN; YI ; YI
815 JSN; YO ; YO
816 JSN; YU ; YU
817 # @missing: 0000..10FFFF; Jamo_Short_Name; <none>
818
819 # Join_Control (Join_C)
820
821 Join_C; N ; No ; F ; False
822 Join_C; Y ; Yes ; T ; True
823
824 # Joining_Group (jg)
825
826 jg ; Ain ; Ain
827 jg ; Alaph ; Alaph
828 jg ; Alef ; Alef
829 jg ; Beh ; Beh
830 jg ; Beth ; Beth
831 jg ; Burushaski_Yeh_Barree ; Burushaski_Yeh_Barree
832 jg ; Dal ; Dal
833 jg ; Dalath_Rish ; Dalath_Rish
834 jg ; E ; E
835 jg ; Farsi_Yeh ; Farsi_Yeh
836 jg ; Fe ; Fe
837 jg ; Feh ; Feh
838 jg ; Final_Semkath ; Final_Semkath
839 jg ; Gaf ; Gaf
840 jg ; Gamal ; Gamal
841 jg ; Hah ; Hah
842 jg ; He ; He
843 jg ; Heh ; Heh
844 jg ; Heh_Goal ; Heh_Goal
845 jg ; Heth ; Heth
846 jg ; Kaf ; Kaf
847 jg ; Kaph ; Kaph
848 jg ; Khaph ; Khaph
849 jg ; Knotted_Heh ; Knotted_Heh
850 jg ; Lam ; Lam
851 jg ; Lamadh ; Lamadh
852 jg ; Manichaean_Aleph ; Manichaean_Aleph
853 jg ; Manichaean_Ayin ; Manichaean_Ayin
854 jg ; Manichaean_Beth ; Manichaean_Beth
855 jg ; Manichaean_Daleth ; Manichaean_Daleth
856 jg ; Manichaean_Dhamedh ; Manichaean_Dhamedh
857 jg ; Manichaean_Five ; Manichaean_Five
858 jg ; Manichaean_Gimel ; Manichaean_Gimel
859 jg ; Manichaean_Heth ; Manichaean_Heth
860 jg ; Manichaean_Hundred ; Manichaean_Hundred
861 jg ; Manichaean_Kaph ; Manichaean_Kaph
862 jg ; Manichaean_Lamedh ; Manichaean_Lamedh
863 jg ; Manichaean_Mem ; Manichaean_Mem
864 jg ; Manichaean_Nun ; Manichaean_Nun
865 jg ; Manichaean_One ; Manichaean_One
866 jg ; Manichaean_Pe ; Manichaean_Pe
867 jg ; Manichaean_Qoph ; Manichaean_Qoph
868 jg ; Manichaean_Resh ; Manichaean_Resh
869 jg ; Manichaean_Sadhe ; Manichaean_Sadhe
870 jg ; Manichaean_Samekh ; Manichaean_Samekh
871 jg ; Manichaean_Taw ; Manichaean_Taw
872 jg ; Manichaean_Ten ; Manichaean_Ten
873 jg ; Manichaean_Teth ; Manichaean_Teth
874 jg ; Manichaean_Thamedh ; Manichaean_Thamedh
875 jg ; Manichaean_Twenty ; Manichaean_Twenty
876 jg ; Manichaean_Waw ; Manichaean_Waw
877 jg ; Manichaean_Yodh ; Manichaean_Yodh
878 jg ; Manichaean_Zayin ; Manichaean_Zayin
879 jg ; Meem ; Meem
880 jg ; Mim ; Mim
881 jg ; No_Joining_Group ; No_Joining_Group
882 jg ; Noon ; Noon
883 jg ; Nun ; Nun
884 jg ; Nya ; Nya
885 jg ; Pe ; Pe
886 jg ; Qaf ; Qaf
887 jg ; Qaph ; Qaph
888 jg ; Reh ; Reh
889 jg ; Reversed_Pe ; Reversed_Pe
890 jg ; Rohingya_Yeh ; Rohingya_Yeh
891 jg ; Sad ; Sad
892 jg ; Sadhe ; Sadhe
893 jg ; Seen ; Seen
894 jg ; Semkath ; Semkath
895 jg ; Shin ; Shin
896 jg ; Straight_Waw ; Straight_Waw
897 jg ; Swash_Kaf ; Swash_Kaf
898 jg ; Syriac_Waw ; Syriac_Waw
899 jg ; Tah ; Tah
900 jg ; Taw ; Taw
901 jg ; Teh_Marbuta ; Teh_Marbuta
902 jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
903 jg ; Teth ; Teth
904 jg ; Waw ; Waw
905 jg ; Yeh ; Yeh
906 jg ; Yeh_Barree ; Yeh_Barree
907 jg ; Yeh_With_Tail ; Yeh_With_Tail
908 jg ; Yudh ; Yudh
909 jg ; Yudh_He ; Yudh_He
910 jg ; Zain ; Zain
911 jg ; Zhain ; Zhain
912
913 # Joining_Type (jt)
914
915 jt ; C ; Join_Causing
916 jt ; D ; Dual_Joining
955 lb ; QU ; Quotation
956 lb ; RI ; Regional_Indicator
957 lb ; SA ; Complex_Context
958 lb ; SG ; Surrogate
959 lb ; SP ; Space
960 lb ; SY ; Break_Symbols
961 lb ; WJ ; Word_Joiner
962 lb ; XX ; Unknown
963 lb ; ZW ; ZWSpace
964
965 # Logical_Order_Exception (LOE)
966
967 LOE; N ; No ; F ; False
968 LOE; Y ; Yes ; T ; True
969
970 # Lowercase (Lower)
971
972 Lower; N ; No ; F ; False
973 Lower; Y ; Yes ; T ; True
974
975 # Lowercase_Mapping (lc)
976
977 # @missing: 0000..10FFFF; Lowercase_Mapping; <code point>
978
979 # Math (Math)
980
981 Math; N ; No ; F ; False
982 Math; Y ; Yes ; T ; True
983
984 # NFC_Quick_Check (NFC_QC)
985
986 NFC_QC; M ; Maybe
987 NFC_QC; N ; No
988 NFC_QC; Y ; Yes
989
990 # NFD_Quick_Check (NFD_QC)
991
992 NFD_QC; N ; No
993 NFD_QC; Y ; Yes
994
995 # NFKC_Casefold (NFKC_CF)
996
997 # @missing: 0000..10FFFF; NFKC_Casefold; <code point>
998
1081 Pat_WS; N ; No ; F ; False
1082 Pat_WS; Y ; Yes ; T ; True
1083
1084 # Quotation_Mark (QMark)
1085
1086 QMark; N ; No ; F ; False
1087 QMark; Y ; Yes ; T ; True
1088
1089 # Radical (Radical)
1090
1091 Radical; N ; No ; F ; False
1092 Radical; Y ; Yes ; T ; True
1093
1094 # STerm (STerm)
1095
1096 STerm; N ; No ; F ; False
1097 STerm; Y ; Yes ; T ; True
1098
1099 # Script (sc)
1100
1101 sc ; Aghb ; Caucasian_Albanian
1102 sc ; Arab ; Arabic
1103 sc ; Armi ; Imperial_Aramaic
1104 sc ; Armn ; Armenian
1105 sc ; Avst ; Avestan
1106 sc ; Bali ; Balinese
1107 sc ; Bamu ; Bamum
1108 sc ; Bass ; Bassa_Vah
1109 sc ; Batk ; Batak
1110 sc ; Beng ; Bengali
1111 sc ; Bopo ; Bopomofo
1112 sc ; Brah ; Brahmi
1113 sc ; Brai ; Braille
1114 sc ; Bugi ; Buginese
1115 sc ; Buhd ; Buhid
1116 sc ; Cakm ; Chakma
1117 sc ; Cans ; Canadian_Aboriginal
1118 sc ; Cari ; Carian
1119 sc ; Cham ; Cham
1120 sc ; Cher ; Cherokee
1121 sc ; Copt ; Coptic ; Qaac
1122 sc ; Cprt ; Cypriot
1123 sc ; Cyrl ; Cyrillic
1124 sc ; Deva ; Devanagari
1125 sc ; Dsrt ; Deseret
1126 sc ; Dupl ; Duployan
1127 sc ; Egyp ; Egyptian_Hieroglyphs
1128 sc ; Elba ; Elbasan
1129 sc ; Ethi ; Ethiopic
1130 sc ; Geor ; Georgian
1131 sc ; Glag ; Glagolitic
1132 sc ; Goth ; Gothic
1133 sc ; Gran ; Grantha
1134 sc ; Grek ; Greek
1135 sc ; Gujr ; Gujarati
1136 sc ; Guru ; Gurmukhi
1137 sc ; Hang ; Hangul
1138 sc ; Hani ; Han
1139 sc ; Hano ; Hanunoo
1140 sc ; Hebr ; Hebrew
1141 sc ; Hira ; Hiragana
1142 sc ; Hmng ; Pahawh_Hmong
1143 sc ; Hrkt ; Katakana_Or_Hiragana
1144 sc ; Ital ; Old_Italic
1145 sc ; Java ; Javanese
1146 sc ; Kali ; Kayah_Li
1147 sc ; Kana ; Katakana
1148 sc ; Khar ; Kharoshthi
1149 sc ; Khmr ; Khmer
1150 sc ; Khoj ; Khojki
1151 sc ; Knda ; Kannada
1152 sc ; Kthi ; Kaithi
1153 sc ; Lana ; Tai_Tham
1154 sc ; Laoo ; Lao
1155 sc ; Latn ; Latin
1156 sc ; Lepc ; Lepcha
1157 sc ; Limb ; Limbu
1158 sc ; Lina ; Linear_A
1159 sc ; Linb ; Linear_B
1160 sc ; Lisu ; Lisu
1161 sc ; Lyci ; Lycian
1162 sc ; Lydi ; Lydian
1163 sc ; Mahj ; Mahajani
1164 sc ; Mand ; Mandaic
1165 sc ; Mani ; Manichaean
1166 sc ; Mend ; Mende_Kikakui
1167 sc ; Merc ; Meroitic_Cursive
1168 sc ; Mero ; Meroitic_Hieroglyphs
1169 sc ; Mlym ; Malayalam
1170 sc ; Modi ; Modi
1171 sc ; Mong ; Mongolian
1172 sc ; Mroo ; Mro
1173 sc ; Mtei ; Meetei_Mayek
1174 sc ; Mymr ; Myanmar
1175 sc ; Narb ; Old_North_Arabian
1176 sc ; Nbat ; Nabataean
1177 sc ; Nkoo ; Nko
1178 sc ; Ogam ; Ogham
1179 sc ; Olck ; Ol_Chiki
1180 sc ; Orkh ; Old_Turkic
1181 sc ; Orya ; Oriya
1182 sc ; Osma ; Osmanya
1183 sc ; Palm ; Palmyrene
1184 sc ; Pauc ; Pau_Cin_Hau
1185 sc ; Perm ; Old_Permic
1186 sc ; Phag ; Phags_Pa
1187 sc ; Phli ; Inscriptional_Pahlavi
1188 sc ; Phlp ; Psalter_Pahlavi
1189 sc ; Phnx ; Phoenician
1190 sc ; Plrd ; Miao
1191 sc ; Prti ; Inscriptional_Parthian
1192 sc ; Rjng ; Rejang
1193 sc ; Runr ; Runic
1194 sc ; Samr ; Samaritan
1195 sc ; Sarb ; Old_South_Arabian
1196 sc ; Saur ; Saurashtra
1197 sc ; Shaw ; Shavian
1198 sc ; Shrd ; Sharada
1199 sc ; Sidd ; Siddham
1200 sc ; Sind ; Khudawadi
1201 sc ; Sinh ; Sinhala
1202 sc ; Sora ; Sora_Sompeng
1203 sc ; Sund ; Sundanese
1204 sc ; Sylo ; Syloti_Nagri
1205 sc ; Syrc ; Syriac
1206 sc ; Tagb ; Tagbanwa
1207 sc ; Takr ; Takri
1208 sc ; Tale ; Tai_Le
1209 sc ; Talu ; New_Tai_Lue
1210 sc ; Taml ; Tamil
1211 sc ; Tavt ; Tai_Viet
1212 sc ; Telu ; Telugu
1213 sc ; Tfng ; Tifinagh
1214 sc ; Tglg ; Tagalog
1215 sc ; Thaa ; Thaana
1216 sc ; Thai ; Thai
1217 sc ; Tibt ; Tibetan
1218 sc ; Tirh ; Tirhuta
1219 sc ; Ugar ; Ugaritic
1220 sc ; Vaii ; Vai
1221 sc ; Wara ; Warang_Citi
1222 sc ; Xpeo ; Old_Persian
1223 sc ; Xsux ; Cuneiform
1224 sc ; Yiii ; Yi
1225 sc ; Zinh ; Inherited ; Qaai
1226 sc ; Zyyy ; Common
1227 sc ; Zzzz ; Unknown
1228
1229 # Script_Extensions (scx)
1230
1231 # @missing: 0000..10FFFF; Script_Extensions; <script>
1232
1233 # Sentence_Break (SB)
1234
1235 SB ; AT ; ATerm
1236 SB ; CL ; Close
1237 SB ; CR ; CR
1238 SB ; EX ; Extend
1239 SB ; FO ; Format
1240 SB ; LE ; OLetter
1241 SB ; LF ; LF
1257 # @missing: 0000..10FFFF; Simple_Lowercase_Mapping; <code point>
1258
1259 # Simple_Titlecase_Mapping (stc)
1260
1261 # @missing: 0000..10FFFF; Simple_Titlecase_Mapping; <code point>
1262
1263 # Simple_Uppercase_Mapping (suc)
1264
1265 # @missing: 0000..10FFFF; Simple_Uppercase_Mapping; <code point>
1266
1267 # Soft_Dotted (SD)
1268
1269 SD ; N ; No ; F ; False
1270 SD ; Y ; Yes ; T ; True
1271
1272 # Terminal_Punctuation (Term)
1273
1274 Term; N ; No ; F ; False
1275 Term; Y ; Yes ; T ; True
1276
1277 # Titlecase_Mapping (tc)
1278
1279 # @missing: 0000..10FFFF; Titlecase_Mapping; <code point>
1280
1281 # Unicode_1_Name (na1)
1282
1283 # @missing: 0000..10FFFF; Unicode_1_Name; <none>
1284
1285 # Unified_Ideograph (UIdeo)
1286
1287 UIdeo; N ; No ; F ; False
1288 UIdeo; Y ; Yes ; T ; True
1289
1290 # Uppercase (Upper)
1291
1292 Upper; N ; No ; F ; False
1293 Upper; Y ; Yes ; T ; True
1294
1295 # Uppercase_Mapping (uc)
1296
1297 # @missing: 0000..10FFFF; Uppercase_Mapping; <code point>
1298
1299 # Variation_Selector (VS)
1300
1301 VS ; N ; No ; F ; False
1302 VS ; Y ; Yes ; T ; True
1303
1304 # White_Space (WSpace)
1305
1306 WSpace; N ; No ; F ; False
1307 WSpace; Y ; Yes ; T ; True
1308
1309 # Word_Break (WB)
1310
1311 WB ; CR ; CR
1312 WB ; DQ ; Double_Quote
1313 WB ; EX ; ExtendNumLet
1314 WB ; Extend ; Extend
1315 WB ; FO ; Format
1316 WB ; HL ; Hebrew_Letter
1317 WB ; KA ; Katakana
1318 WB ; LE ; ALetter
1319 WB ; LF ; LF
1320 WB ; MB ; MidNumLet
1321 WB ; ML ; MidLetter
1322 WB ; MN ; MidNum
1323 WB ; NL ; Newline
1324 WB ; NU ; Numeric
1325 WB ; RI ; Regional_Indicator
1326 WB ; SQ ; Single_Quote
1327 WB ; XX ; Other
1328
1329 # XID_Continue (XIDC)
1330
1331 XIDC; N ; No ; F ; False
1332 XIDC; Y ; Yes ; T ; True
1333
1334 # XID_Start (XIDS)
1335
1336 XIDS; N ; No ; F ; False
1337 XIDS; Y ; Yes ; T ; True
1338
1339 # cjkAccountingNumeric (cjkAccountingNumeric)
1340
1341 # @missing: 0000..10FFFF; cjkAccountingNumeric; NaN
1342
1343 # cjkCompatibilityVariant (cjkCompatibilityVariant)
1344
1345 # @missing: 0000..10FFFF; cjkCompatibilityVariant; <code point>
1346
|