1 # PropertyValueAliases-6.2.0.txt
2 # Date: 2012-08-14, 16:05:11 GMT [MD]
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/
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.
13 # The names may be translated in appropriate environments, and additional
14 # aliases may be useful.
18 # Each line describes a property value name.
19 # This consists of three or more fields, separated by semicolons.
21 # First Field: The first field describes the property for which that
22 # property value name is used.
24 # Second Field: The second field is an abbreviated name.
26 # Third Field: The third field is a long name.
28 # In the case of ccc, there are 4 fields. The second field is numeric, third
29 # is abbreviated, and fourth is long.
31 # The above are the preferred aliases. Other aliases may be listed in additional fields.
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".
38 # NOTE: Property value names are NOT unique across properties. For example:
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.
44 # In addition, some property names may be the same as some property value names.
47 # sc means the Script property, and
48 # Sc means the General_Category property value Currency_Symbol (Sc)
50 # The combination of property value and property name is, however, unique.
52 # For more information, see UTS #18: Unicode Regular Expressions
53 # ================================================
56 # ASCII_Hex_Digit (AHex)
58 AHex; N ; No ; F ; False
59 AHex; Y ; Yes ; T ; True
81 Alpha; N ; No ; F ; False
82 Alpha; Y ; Yes ; T ; True
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
106 # Bidi_Control (Bidi_C)
108 Bidi_C; N ; No ; F ; False
109 Bidi_C; Y ; Yes ; T ; True
111 # Bidi_Mirrored (Bidi_M)
113 Bidi_M; N ; No ; F ; False
114 Bidi_M; Y ; Yes ; T ; True
116 # Bidi_Mirroring_Glyph (bmg)
118 # @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; <none>
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
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
136 blk; ASCII ; Basic_Latin
137 blk; Avestan ; Avestan
138 blk; Balinese ; Balinese
140 blk; Bamum_Sup ; Bamum_Supplement
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
148 blk; Braille ; Braille_Patterns
149 blk; Buginese ; Buginese
151 blk; Byzantine_Music ; Byzantine_Musical_Symbols
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
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
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
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
226 blk; Kana_Sup ; Kana_Supplement
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
235 blk; Khmer_Symbols ; Khmer_Symbols
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
244 blk; Letterlike_Symbols ; Letterlike_Symbols
246 blk; Linear_B_Ideograms ; Linear_B_Ideograms
247 blk; Linear_B_Syllabary ; Linear_B_Syllabary
249 blk; Low_Surrogates ; Low_Surrogates
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
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
275 blk; New_Tai_Lue ; New_Tai_Lue
277 blk; Number_Forms ; Number_Forms
278 blk; OCR ; Optical_Character_Recognition
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
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
296 blk; Rumi ; Rumi_Numeral_Symbols
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
317 blk; Tagalog ; Tagalog
318 blk; Tagbanwa ; Tagbanwa
321 blk; Tai_Tham ; Tai_Tham
322 blk; Tai_Viet ; Tai_Viet
323 blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
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
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
344 # Canonical_Combining_Class (ccc)
346 ccc; 0; NR ; Not_Reordered
349 ccc; 8; KV ; Kana_Voicing
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
360 ccc; 19; CCC19 ; CCC19
361 ccc; 20; CCC20 ; CCC20
362 ccc; 21; CCC21 ; CCC21
363 ccc; 22; CCC22 ; CCC22
364 ccc; 23; CCC23 ; CCC23
365 ccc; 24; CCC24 ; CCC24
366 ccc; 25; CCC25 ; CCC25
367 ccc; 26; CCC26 ; CCC26
368 ccc; 27; CCC27 ; CCC27
369 ccc; 28; CCC28 ; CCC28
370 ccc; 29; CCC29 ; CCC29
371 ccc; 30; CCC30 ; CCC30
372 ccc; 31; CCC31 ; CCC31
373 ccc; 32; CCC32 ; CCC32
374 ccc; 33; CCC33 ; CCC33
375 ccc; 34; CCC34 ; CCC34
376 ccc; 35; CCC35 ; CCC35
377 ccc; 36; CCC36 ; CCC36
378 ccc; 84; CCC84 ; CCC84
379 ccc; 91; CCC91 ; CCC91
380 ccc; 103; CCC103 ; CCC103
381 ccc; 107; CCC107 ; CCC107
382 ccc; 118; CCC118 ; CCC118
383 ccc; 122; CCC122 ; CCC122
384 ccc; 129; CCC129 ; CCC129
385 ccc; 130; CCC130 ; CCC130
386 ccc; 132; CCC132 ; CCC132
387 ccc; 133; CCC133 ; CCC133 # RESERVED
388 ccc; 200; ATBL ; Attached_Below_Left
389 ccc; 202; ATB ; Attached_Below
390 ccc; 214; ATA ; Attached_Above
391 ccc; 216; ATAR ; Attached_Above_Right
392 ccc; 218; BL ; Below_Left
394 ccc; 222; BR ; Below_Right
397 ccc; 228; AL ; Above_Left
399 ccc; 232; AR ; Above_Right
400 ccc; 233; DB ; Double_Below
401 ccc; 234; DA ; Double_Above
402 ccc; 240; IS ; Iota_Subscript
406 # @missing: 0000..10FFFF; Case_Folding; <code point>
408 # Case_Ignorable (CI)
410 CI ; N ; No ; F ; False
411 CI ; Y ; Yes ; T ; True
415 Cased; N ; No ; F ; False
416 Cased; Y ; Yes ; T ; True
418 # Changes_When_Casefolded (CWCF)
420 CWCF; N ; No ; F ; False
421 CWCF; Y ; Yes ; T ; True
423 # Changes_When_Casemapped (CWCM)
425 CWCM; N ; No ; F ; False
426 CWCM; Y ; Yes ; T ; True
428 # Changes_When_Lowercased (CWL)
430 CWL; N ; No ; F ; False
431 CWL; Y ; Yes ; T ; True
433 # Changes_When_NFKC_Casefolded (CWKCF)
435 CWKCF; N ; No ; F ; False
436 CWKCF; Y ; Yes ; T ; True
438 # Changes_When_Titlecased (CWT)
440 CWT; N ; No ; F ; False
441 CWT; Y ; Yes ; T ; True
443 # Changes_When_Uppercased (CWU)
445 CWU; N ; No ; F ; False
446 CWU; Y ; Yes ; T ; True
448 # Composition_Exclusion (CE)
450 CE ; N ; No ; F ; False
451 CE ; Y ; Yes ; T ; True
455 Dash; N ; No ; F ; False
456 Dash; Y ; Yes ; T ; True
458 # Decomposition_Mapping (dm)
460 # @missing: 0000..10FFFF; Decomposition_Mapping; <code point>
462 # Decomposition_Type (dt)
464 dt ; Can ; Canonical ; can
465 dt ; Com ; Compat ; com
466 dt ; Enc ; Circle ; enc
467 dt ; Fin ; Final ; fin
468 dt ; Font ; Font ; font
469 dt ; Fra ; Fraction ; fra
470 dt ; Init ; Initial ; init
471 dt ; Iso ; Isolated ; iso
472 dt ; Med ; Medial ; med
473 dt ; Nar ; Narrow ; nar
474 dt ; Nb ; Nobreak ; nb
475 dt ; None ; None ; none
476 dt ; Sml ; Small ; sml
477 dt ; Sqr ; Square ; sqr
479 dt ; Sup ; Super ; sup
480 dt ; Vert ; Vertical ; vert
481 dt ; Wide ; Wide ; wide
483 # Default_Ignorable_Code_Point (DI)
485 DI ; N ; No ; F ; False
486 DI ; Y ; Yes ; T ; True
490 Dep; N ; No ; F ; False
491 Dep; Y ; Yes ; T ; True
495 Dia; N ; No ; F ; False
496 Dia; Y ; Yes ; T ; True
498 # East_Asian_Width (ea)
507 # Expands_On_NFC (XO_NFC)
509 XO_NFC; N ; No ; F ; False
510 XO_NFC; Y ; Yes ; T ; True
512 # Expands_On_NFD (XO_NFD)
514 XO_NFD; N ; No ; F ; False
515 XO_NFD; Y ; Yes ; T ; True
517 # Expands_On_NFKC (XO_NFKC)
519 XO_NFKC; N ; No ; F ; False
520 XO_NFKC; Y ; Yes ; T ; True
522 # Expands_On_NFKD (XO_NFKD)
524 XO_NFKD; N ; No ; F ; False
525 XO_NFKD; Y ; Yes ; T ; True
529 Ext; N ; No ; F ; False
530 Ext; Y ; Yes ; T ; True
532 # FC_NFKC_Closure (FC_NFKC)
534 # @missing: 0000..10FFFF; FC_NFKC_Closure; <code point>
536 # Full_Composition_Exclusion (Comp_Ex)
538 Comp_Ex; N ; No ; F ; False
539 Comp_Ex; Y ; Yes ; T ; True
541 # General_Category (gc)
543 gc ; C ; Other # Cc | Cf | Cn | Co | Cs
544 gc ; Cc ; Control ; cntrl
547 gc ; Co ; Private_Use
549 gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu
550 gc ; LC ; Cased_Letter # Ll | Lt | Lu
551 gc ; Ll ; Lowercase_Letter
552 gc ; Lm ; Modifier_Letter
553 gc ; Lo ; Other_Letter
554 gc ; Lt ; Titlecase_Letter
555 gc ; Lu ; Uppercase_Letter
556 gc ; M ; Mark ; Combining_Mark # Mc | Me | Mn
557 gc ; Mc ; Spacing_Mark
558 gc ; Me ; Enclosing_Mark
559 gc ; Mn ; Nonspacing_Mark
560 gc ; N ; Number # Nd | Nl | No
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
582 # Grapheme_Base (Gr_Base)
584 Gr_Base; N ; No ; F ; False
585 Gr_Base; Y ; Yes ; T ; True
587 # Grapheme_Cluster_Break (GCB)
597 GCB; RI ; Regional_Indicator
598 GCB; SM ; SpacingMark
603 # Grapheme_Extend (Gr_Ext)
605 Gr_Ext; N ; No ; F ; False
606 Gr_Ext; Y ; Yes ; T ; True
608 # Grapheme_Link (Gr_Link)
610 Gr_Link; N ; No ; F ; False
611 Gr_Link; Y ; Yes ; T ; True
613 # Hangul_Syllable_Type (hst)
615 hst; L ; Leading_Jamo
616 hst; LV ; LV_Syllable
617 hst; LVT ; LVT_Syllable
618 hst; NA ; Not_Applicable
619 hst; T ; Trailing_Jamo
624 Hex; N ; No ; F ; False
625 Hex; Y ; Yes ; T ; True
629 Hyphen; N ; No ; F ; False
630 Hyphen; Y ; Yes ; T ; True
632 # IDS_Binary_Operator (IDSB)
634 IDSB; N ; No ; F ; False
635 IDSB; Y ; Yes ; T ; True
637 # IDS_Trinary_Operator (IDST)
639 IDST; N ; No ; F ; False
640 IDST; Y ; Yes ; T ; True
644 IDC; N ; No ; F ; False
645 IDC; Y ; Yes ; T ; True
649 IDS; N ; No ; F ; False
650 IDS; Y ; Yes ; T ; True
654 # @missing: 0000..10FFFF; ISO_Comment; <none>
658 Ideo; N ; No ; F ; False
659 Ideo; Y ; Yes ; T ; True
661 # Indic_Matra_Category (InMC)
663 InMC; Bottom ; Bottom
664 InMC; Bottom_And_Right ; Bottom_And_Right
665 InMC; Invisible ; Invisible
667 InMC; Left_And_Right ; Left_And_Right
669 InMC; Overstruck ; Overstruck
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
679 # Indic_Syllabic_Category (InSC)
681 InSC; Avagraha ; Avagraha
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
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
700 InSC; Vowel_Dependent ; Vowel_Dependent
701 InSC; Vowel_Independent ; Vowel_Independent
703 # Jamo_Short_Name (JSN)
705 # @missing: 0000..10FFFF; Jamo_Short_Name; <none>
759 # Join_Control (Join_C)
761 Join_C; N ; No ; F ; False
762 Join_C; Y ; Yes ; T ; True
771 jg ; Burushaski_Yeh_Barree ; Burushaski_Yeh_Barree
773 jg ; Dalath_Rish ; Dalath_Rish
775 jg ; Farsi_Yeh ; Farsi_Yeh
778 jg ; Final_Semkath ; Final_Semkath
784 jg ; Heh_Goal ; Heh_Goal
789 jg ; Knotted_Heh ; Knotted_Heh
794 jg ; No_Joining_Group ; No_Joining_Group
802 jg ; Reversed_Pe ; Reversed_Pe
803 jg ; Rohingya_Yeh ; Rohingya_Yeh
807 jg ; Semkath ; Semkath
809 jg ; Swash_Kaf ; Swash_Kaf
810 jg ; Syriac_Waw ; Syriac_Waw
813 jg ; Teh_Marbuta ; Teh_Marbuta
814 jg ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal
818 jg ; Yeh_Barree ; Yeh_Barree
819 jg ; Yeh_With_Tail ; Yeh_With_Tail
821 jg ; Yudh_He ; Yudh_He
827 jt ; C ; Join_Causing
828 jt ; D ; Dual_Joining
829 jt ; L ; Left_Joining
830 jt ; R ; Right_Joining
839 lb ; BA ; Break_After
840 lb ; BB ; Break_Before
841 lb ; BK ; Mandatory_Break
842 lb ; CB ; Contingent_Break
843 lb ; CJ ; Conditional_Japanese_Starter
844 lb ; CL ; Close_Punctuation
845 lb ; CM ; Combining_Mark
846 lb ; CP ; Close_Parenthesis
847 lb ; CR ; Carriage_Return
848 lb ; EX ; Exclamation
852 lb ; HL ; Hebrew_Letter
854 lb ; ID ; Ideographic
855 lb ; IN ; Inseparable ; Inseperable
856 lb ; IS ; Infix_Numeric
864 lb ; OP ; Open_Punctuation
865 lb ; PO ; Postfix_Numeric
866 lb ; PR ; Prefix_Numeric
868 lb ; RI ; Regional_Indicator
869 lb ; SA ; Complex_Context
872 lb ; SY ; Break_Symbols
873 lb ; WJ ; Word_Joiner
877 # Logical_Order_Exception (LOE)
879 LOE; N ; No ; F ; False
880 LOE; Y ; Yes ; T ; True
884 Lower; N ; No ; F ; False
885 Lower; Y ; Yes ; T ; True
889 Math; N ; No ; F ; False
890 Math; Y ; Yes ; T ; True
892 # NFC_Quick_Check (NFC_QC)
898 # NFD_Quick_Check (NFD_QC)
903 # NFKC_Casefold (NFKC_CF)
905 # @missing: 0000..10FFFF; NFKC_Casefold; <code point>
907 # NFKC_Quick_Check (NFKC_QC)
913 # NFKD_Quick_Check (NFKD_QC)
920 # @missing: 0000..10FFFF; Name; <none>
922 # Name_Alias (Name_Alias)
924 # @missing: 0000..10FFFF; Name_Alias; <none>
926 # Noncharacter_Code_Point (NChar)
928 NChar; N ; No ; F ; False
929 NChar; Y ; Yes ; T ; True
940 # @missing: 0000..10FFFF; Numeric_Value; NaN
942 # Other_Alphabetic (OAlpha)
944 OAlpha; N ; No ; F ; False
945 OAlpha; Y ; Yes ; T ; True
947 # Other_Default_Ignorable_Code_Point (ODI)
949 ODI; N ; No ; F ; False
950 ODI; Y ; Yes ; T ; True
952 # Other_Grapheme_Extend (OGr_Ext)
954 OGr_Ext; N ; No ; F ; False
955 OGr_Ext; Y ; Yes ; T ; True
957 # Other_ID_Continue (OIDC)
959 OIDC; N ; No ; F ; False
960 OIDC; Y ; Yes ; T ; True
962 # Other_ID_Start (OIDS)
964 OIDS; N ; No ; F ; False
965 OIDS; Y ; Yes ; T ; True
967 # Other_Lowercase (OLower)
969 OLower; N ; No ; F ; False
970 OLower; Y ; Yes ; T ; True
974 OMath; N ; No ; F ; False
975 OMath; Y ; Yes ; T ; True
977 # Other_Uppercase (OUpper)
979 OUpper; N ; No ; F ; False
980 OUpper; Y ; Yes ; T ; True
982 # Pattern_Syntax (Pat_Syn)
984 Pat_Syn; N ; No ; F ; False
985 Pat_Syn; Y ; Yes ; T ; True
987 # Pattern_White_Space (Pat_WS)
989 Pat_WS; N ; No ; F ; False
990 Pat_WS; Y ; Yes ; T ; True
992 # Quotation_Mark (QMark)
994 QMark; N ; No ; F ; False
995 QMark; Y ; Yes ; T ; True
999 Radical; N ; No ; F ; False
1000 Radical; Y ; Yes ; T ; True
1004 STerm; N ; No ; F ; False
1005 STerm; Y ; Yes ; T ; True
1010 sc ; Armi ; Imperial_Aramaic
1011 sc ; Armn ; Armenian
1013 sc ; Bali ; Balinese
1017 sc ; Bopo ; Bopomofo
1020 sc ; Bugi ; Buginese
1023 sc ; Cans ; Canadian_Aboriginal
1026 sc ; Cher ; Cherokee
1027 sc ; Copt ; Coptic ; Qaac
1029 sc ; Cyrl ; Cyrillic
1030 sc ; Deva ; Devanagari
1032 sc ; Egyp ; Egyptian_Hieroglyphs
1033 sc ; Ethi ; Ethiopic
1034 sc ; Geor ; Georgian
1035 sc ; Glag ; Glagolitic
1038 sc ; Gujr ; Gujarati
1039 sc ; Guru ; Gurmukhi
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
1054 sc ; Lana ; Tai_Tham
1059 sc ; Linb ; Linear_B
1064 sc ; Merc ; Meroitic_Cursive
1065 sc ; Mero ; Meroitic_Hieroglyphs
1066 sc ; Mlym ; Malayalam
1067 sc ; Mong ; Mongolian
1068 sc ; Mtei ; Meetei_Mayek
1072 sc ; Olck ; Ol_Chiki
1073 sc ; Orkh ; Old_Turkic
1076 sc ; Phag ; Phags_Pa
1077 sc ; Phli ; Inscriptional_Pahlavi
1078 sc ; Phnx ; Phoenician
1080 sc ; Prti ; Inscriptional_Parthian
1083 sc ; Samr ; Samaritan
1084 sc ; Sarb ; Old_South_Arabian
1085 sc ; Saur ; Saurashtra
1089 sc ; Sora ; Sora_Sompeng
1090 sc ; Sund ; Sundanese
1091 sc ; Sylo ; Syloti_Nagri
1093 sc ; Tagb ; Tagbanwa
1096 sc ; Talu ; New_Tai_Lue
1098 sc ; Tavt ; Tai_Viet
1100 sc ; Tfng ; Tifinagh
1105 sc ; Ugar ; Ugaritic
1107 sc ; Xpeo ; Old_Persian
1108 sc ; Xsux ; Cuneiform
1110 sc ; Zinh ; Inherited ; Qaai
1114 # Script_Extensions (scx)
1116 # @missing: 0000..10FFFF; Script_Extensions; <script>
1118 # Sentence_Break (SB)
1136 # Simple_Case_Folding (scf)
1138 # @missing: 0000..10FFFF; Simple_Case_Folding; <code point>
1140 # Simple_Lowercase_Mapping (slc)
1142 # @missing: 0000..10FFFF; Simple_Lowercase_Mapping; <code point>
1144 # Simple_Titlecase_Mapping (stc)
1146 # @missing: 0000..10FFFF; Simple_Titlecase_Mapping; <code point>
1148 # Simple_Uppercase_Mapping (suc)
1150 # @missing: 0000..10FFFF; Simple_Uppercase_Mapping; <code point>
1154 SD ; N ; No ; F ; False
1155 SD ; Y ; Yes ; T ; True
1157 # Terminal_Punctuation (Term)
1159 Term; N ; No ; F ; False
1160 Term; Y ; Yes ; T ; True
1162 # Unicode_1_Name (na1)
1164 # @missing: 0000..10FFFF; Unicode_1_Name; <none>
1166 # Unified_Ideograph (UIdeo)
1168 UIdeo; N ; No ; F ; False
1169 UIdeo; Y ; Yes ; T ; True
1173 Upper; N ; No ; F ; False
1174 Upper; Y ; Yes ; T ; True
1176 # Variation_Selector (VS)
1178 VS ; N ; No ; F ; False
1179 VS ; Y ; Yes ; T ; True
1181 # White_Space (WSpace)
1183 WSpace; N ; No ; F ; False
1184 WSpace; Y ; Yes ; T ; True
1189 WB ; EX ; ExtendNumLet
1190 WB ; Extend ; Extend
1200 WB ; RI ; Regional_Indicator
1203 # XID_Continue (XIDC)
1205 XIDC; N ; No ; F ; False
1206 XIDC; Y ; Yes ; T ; True
1210 XIDS; N ; No ; F ; False
1211 XIDS; Y ; Yes ; T ; True
1213 # cjkAccountingNumeric (cjkAccountingNumeric)
1215 # @missing: 0000..10FFFF; cjkAccountingNumeric; NaN
1217 # cjkCompatibilityVariant (cjkCompatibilityVariant)
1219 # @missing: 0000..10FFFF; cjkCompatibilityVariant; <code point>
1221 # cjkIICore (cjkIICore)
1223 # @missing: 0000..10FFFF; cjkIICore; <none>
1225 # cjkIRG_GSource (cjkIRG_GSource)
1227 # @missing: 0000..10FFFF; cjkIRG_GSource; <none>
1229 # cjkIRG_HSource (cjkIRG_HSource)
1231 # @missing: 0000..10FFFF; cjkIRG_HSource; <none>
1233 # cjkIRG_JSource (cjkIRG_JSource)
1235 # @missing: 0000..10FFFF; cjkIRG_JSource; <none>
1237 # cjkIRG_KPSource (cjkIRG_KPSource)
1239 # @missing: 0000..10FFFF; cjkIRG_KPSource; <none>
1241 # cjkIRG_KSource (cjkIRG_KSource)
1243 # @missing: 0000..10FFFF; cjkIRG_KSource; <none>
1245 # cjkIRG_MSource (cjkIRG_MSource)
1247 # @missing: 0000..10FFFF; cjkIRG_MSource; <none>
1249 # cjkIRG_TSource (cjkIRG_TSource)
1251 # @missing: 0000..10FFFF; cjkIRG_TSource; <none>
1253 # cjkIRG_USource (cjkIRG_USource)
1255 # @missing: 0000..10FFFF; cjkIRG_USource; <none>
1257 # cjkIRG_VSource (cjkIRG_VSource)
1259 # @missing: 0000..10FFFF; cjkIRG_VSource; <none>
1261 # cjkOtherNumeric (cjkOtherNumeric)
1263 # @missing: 0000..10FFFF; cjkOtherNumeric; NaN
1265 # cjkPrimaryNumeric (cjkPrimaryNumeric)
1267 # @missing: 0000..10FFFF; cjkPrimaryNumeric; NaN
1269 # cjkRSUnicode (cjkRSUnicode)
1271 # @missing: 0000..10FFFF; cjkRSUnicode; <none>