| blob | 3f7aad206e5591df320e96b3f76262b1849b2f11 |
1 # PropertyValueAliases-4.1.0.txt
2 # Date: 2005-03-28, 17:21:48 GMT [MD]
3 #
4 # Unicode Character Database
5 # Copyright (c) 1991-2005 Unicode, Inc.
6 # For terms of use, see http://www.unicode.org/terms_of_use.html
7 # For documentation, see UCD.html
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 # For information on which properties are normative, see UCD.html.
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 an abbreviated name.
26 # If there is no abbreviated name available, the field is marked with "n/a".
27 #
28 # Third Field: The third field is a long name.
29 #
30 # In the case of ccc, there are 4 fields. The second field is numeric, third
31 # is abbreviated, and fourth is long.
32 #
33 # The above are the preferred aliases. Other aliases may be listed in additional fields.
34 #
35 # Loose matching should be applied to all property names and property values, with
36 # the exception of String Property values. With loose matching of property names and
37 # values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property
38 # values, numeric equivalencies are applied: thus "01.00" is equivalent to "1".
39 #
40 # NOTE: Property value names are NOT unique across properties. For example:
41 #
42 # AL means Arabic Letter for the Bidi_Class property, and
43 # AL means Alpha_Left for the Combining_Class property, and
44 # AL means Alphabetic for the Line_Break property.
45 #
46 # In addition, some property names may be the same as some property value names.
47 # For example:
48 #
49 # sc means the Script property, and
50 # Sc means the General_Category property value Currency_Symbol (Sc)
51 #
52 # The combination of property value and property name is, however, unique.
53 #
54 # For more information, see UTS #18: Regular Expression Guidelines
55 # ================================================
58 # Age (age)
60 age; n/a ; 1.1
61 age; n/a ; 2.0
62 age; n/a ; 2.1
63 age; n/a ; 3.0
64 age; n/a ; 3.1
65 age; n/a ; 3.2
66 age; n/a ; 4.0
67 age; n/a ; 4.1
68 age; n/a ; unassigned
70 # Bidi_Class (bc)
72 bc ; AL ; Arabic_Letter
73 bc ; AN ; Arabic_Number
74 bc ; B ; Paragraph_Separator
75 bc ; BN ; Boundary_Neutral
76 bc ; CS ; Common_Separator
77 bc ; EN ; European_Number
78 bc ; ES ; European_Separator
79 bc ; ET ; European_Terminator
80 bc ; L ; Left_To_Right
81 bc ; LRE ; Left_To_Right_Embedding
82 bc ; LRO ; Left_To_Right_Override
83 bc ; NSM ; Nonspacing_Mark
84 bc ; ON ; Other_Neutral
85 bc ; PDF ; Pop_Directional_Format
86 bc ; R ; Right_To_Left
87 bc ; RLE ; Right_To_Left_Embedding
88 bc ; RLO ; Right_To_Left_Override
89 bc ; S ; Segment_Separator
90 bc ; WS ; White_Space
92 # Block (blk)
94 blk; n/a ; Aegean_Numbers
95 blk; n/a ; Alphabetic_Presentation_Forms
96 blk; n/a ; Ancient_Greek_Musical_Notation
97 blk; n/a ; Ancient_Greek_Numbers
98 blk; n/a ; Arabic
99 blk; n/a ; Arabic_Presentation_Forms-A
100 blk; n/a ; Arabic_Presentation_Forms-B
101 blk; n/a ; Arabic_Supplement
102 blk; n/a ; Armenian
103 blk; n/a ; Arrows
104 blk; n/a ; Basic_Latin
105 blk; n/a ; Bengali
106 blk; n/a ; Block_Elements
107 blk; n/a ; Bopomofo
108 blk; n/a ; Bopomofo_Extended
109 blk; n/a ; Box_Drawing
110 blk; n/a ; Braille_Patterns
111 blk; n/a ; Buginese
112 blk; n/a ; Buhid
113 blk; n/a ; Byzantine_Musical_Symbols
114 blk; n/a ; Cherokee
115 blk; n/a ; CJK_Compatibility
116 blk; n/a ; CJK_Compatibility_Forms
117 blk; n/a ; CJK_Compatibility_Ideographs
118 blk; n/a ; CJK_Compatibility_Ideographs_Supplement
119 blk; n/a ; CJK_Radicals_Supplement
120 blk; n/a ; CJK_Strokes
121 blk; n/a ; CJK_Symbols_and_Punctuation
122 blk; n/a ; CJK_Unified_Ideographs
123 blk; n/a ; CJK_Unified_Ideographs_Extension_A
124 blk; n/a ; CJK_Unified_Ideographs_Extension_B
125 blk; n/a ; Combining_Diacritical_Marks
126 blk; n/a ; Combining_Diacritical_Marks_for_Symbols
127 blk; n/a ; Combining_Diacritical_Marks_Supplement
128 blk; n/a ; Combining_Half_Marks
129 blk; n/a ; Control_Pictures
130 blk; n/a ; Coptic
131 blk; n/a ; Currency_Symbols
132 blk; n/a ; Cypriot_Syllabary
133 blk; n/a ; Cyrillic
134 blk; n/a ; Cyrillic_Supplement ; Cyrillic_Supplementary
135 blk; n/a ; Deseret
136 blk; n/a ; Devanagari
137 blk; n/a ; Dingbats
138 blk; n/a ; Enclosed_Alphanumerics
139 blk; n/a ; Enclosed_CJK_Letters_and_Months
140 blk; n/a ; Ethiopic
141 blk; n/a ; Ethiopic_Extended
142 blk; n/a ; Ethiopic_Supplement
143 blk; n/a ; General_Punctuation
144 blk; n/a ; Geometric_Shapes
145 blk; n/a ; Georgian
146 blk; n/a ; Georgian_Supplement
147 blk; n/a ; Glagolitic
148 blk; n/a ; Gothic
149 blk; n/a ; Greek_and_Coptic
150 blk; n/a ; Greek_Extended
151 blk; n/a ; Gujarati
152 blk; n/a ; Gurmukhi
153 blk; n/a ; Halfwidth_and_Fullwidth_Forms
154 blk; n/a ; Hangul_Compatibility_Jamo
155 blk; n/a ; Hangul_Jamo
156 blk; n/a ; Hangul_Syllables
157 blk; n/a ; Hanunoo
158 blk; n/a ; Hebrew
159 blk; n/a ; High_Private_Use_Surrogates
160 blk; n/a ; High_Surrogates
161 blk; n/a ; Hiragana
162 blk; n/a ; Ideographic_Description_Characters
163 blk; n/a ; IPA_Extensions
164 blk; n/a ; Kanbun
165 blk; n/a ; Kangxi_Radicals
166 blk; n/a ; Kannada
167 blk; n/a ; Katakana
168 blk; n/a ; Katakana_Phonetic_Extensions
169 blk; n/a ; Kharoshthi
170 blk; n/a ; Khmer
171 blk; n/a ; Khmer_Symbols
172 blk; n/a ; Lao
173 blk; n/a ; Latin-1_Supplement
174 blk; n/a ; Latin_Extended-A
175 blk; n/a ; Latin_Extended-B
176 blk; n/a ; Latin_Extended_Additional
177 blk; n/a ; Letterlike_Symbols
178 blk; n/a ; Limbu
179 blk; n/a ; Linear_B_Ideograms
180 blk; n/a ; Linear_B_Syllabary
181 blk; n/a ; Low_Surrogates
182 blk; n/a ; Malayalam
183 blk; n/a ; Mathematical_Alphanumeric_Symbols
184 blk; n/a ; Mathematical_Operators
185 blk; n/a ; Miscellaneous_Mathematical_Symbols-A
186 blk; n/a ; Miscellaneous_Mathematical_Symbols-B
187 blk; n/a ; Miscellaneous_Symbols
188 blk; n/a ; Miscellaneous_Symbols_and_Arrows
189 blk; n/a ; Miscellaneous_Technical
190 blk; n/a ; Modifier_Tone_Letters
191 blk; n/a ; Mongolian
192 blk; n/a ; Musical_Symbols
193 blk; n/a ; Myanmar
194 blk; n/a ; New_Tai_Lue
195 blk; n/a ; No_Block
196 blk; n/a ; Number_Forms
197 blk; n/a ; Ogham
198 blk; n/a ; Old_Italic
199 blk; n/a ; Old_Persian
200 blk; n/a ; Optical_Character_Recognition
201 blk; n/a ; Oriya
202 blk; n/a ; Osmanya
203 blk; n/a ; Phonetic_Extensions
204 blk; n/a ; Phonetic_Extensions_Supplement
205 blk; n/a ; Private_Use_Area
206 blk; n/a ; Runic
207 blk; n/a ; Shavian
208 blk; n/a ; Sinhala
209 blk; n/a ; Small_Form_Variants
210 blk; n/a ; Spacing_Modifier_Letters
211 blk; n/a ; Specials
212 blk; n/a ; Superscripts_and_Subscripts
213 blk; n/a ; Supplemental_Arrows-A
214 blk; n/a ; Supplemental_Arrows-B
215 blk; n/a ; Supplemental_Mathematical_Operators
216 blk; n/a ; Supplemental_Punctuation
217 blk; n/a ; Supplementary_Private_Use_Area-A
218 blk; n/a ; Supplementary_Private_Use_Area-B
219 blk; n/a ; Syloti_Nagri
220 blk; n/a ; Syriac
221 blk; n/a ; Tagalog
222 blk; n/a ; Tagbanwa
223 blk; n/a ; Tags
224 blk; n/a ; Tai_Le
225 blk; n/a ; Tai_Xuan_Jing_Symbols
226 blk; n/a ; Tamil
227 blk; n/a ; Telugu
228 blk; n/a ; Thaana
229 blk; n/a ; Thai
230 blk; n/a ; Tibetan
231 blk; n/a ; Tifinagh
232 blk; n/a ; Ugaritic
233 blk; n/a ; Unified_Canadian_Aboriginal_Syllabics
234 blk; n/a ; Variation_Selectors
235 blk; n/a ; Variation_Selectors_Supplement
236 blk; n/a ; Vertical_Forms
237 blk; n/a ; Yi_Radicals
238 blk; n/a ; Yi_Syllables
239 blk; n/a ; Yijing_Hexagram_Symbols
241 # Canonical_Combining_Class (ccc)
243 ccc; 0; NR ; Not_Reordered
244 ccc; 1; OV ; Overlay
245 ccc; 7; NK ; Nukta
246 ccc; 8; KV ; Kana_Voicing
247 ccc; 9; VR ; Virama
248 ccc; 200; ATBL ; Attached_Below_Left
249 ccc; 202; ATB ; Attached_Below
250 ccc; 216; ATAR ; Attached_Above_Right
251 ccc; 218; BL ; Below_Left
252 ccc; 220; B ; Below
253 ccc; 222; BR ; Below_Right
254 ccc; 224; L ; Left
255 ccc; 226; R ; Right
256 ccc; 228; AL ; Above_Left
257 ccc; 230; A ; Above
258 ccc; 232; AR ; Above_Right
259 ccc; 233; DB ; Double_Below
260 ccc; 234; DA ; Double_Above
261 ccc; 240; IS ; Iota_Subscript
263 # Decomposition_Type (dt)
265 dt ; can ; Canonical
266 dt ; com ; Compat
267 dt ; enc ; Circle
268 dt ; fin ; Final
269 dt ; font ; Font
270 dt ; fra ; Fraction
271 dt ; init ; Initial
272 dt ; iso ; Isolated
273 dt ; med ; Medial
274 dt ; nar ; Narrow
275 dt ; nb ; Nobreak
276 dt ; none ; None
277 dt ; sml ; Small
278 dt ; sqr ; Square
279 dt ; sub ; Sub
280 dt ; sup ; Super
281 dt ; vert ; Vertical
282 dt ; wide ; Wide
284 # East_Asian_Width (ea)
286 ea ; A ; Ambiguous
287 ea ; F ; Fullwidth
288 ea ; H ; Halfwidth
289 ea ; N ; Neutral
290 ea ; Na ; Narrow
291 ea ; W ; Wide
293 # General_Category (gc)
295 gc ; C ; Other # Cc | Cf | Cn | Co | Cs
296 gc ; Cc ; Control ; cntrl
297 gc ; Cf ; Format
298 gc ; Cn ; Unassigned
299 gc ; Co ; Private_Use
300 gc ; Cs ; Surrogate
301 gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu
302 gc ; LC ; Cased_Letter # Ll | Lt | Lu
303 gc ; Ll ; Lowercase_Letter
304 gc ; Lm ; Modifier_Letter
305 gc ; Lo ; Other_Letter
306 gc ; Lt ; Titlecase_Letter
307 gc ; Lu ; Uppercase_Letter
308 gc ; M ; Mark # Mc | Me | Mn
309 gc ; Mc ; Spacing_Mark
310 gc ; Me ; Enclosing_Mark
311 gc ; Mn ; Nonspacing_Mark
312 gc ; N ; Number # Nd | Nl | No
313 gc ; Nd ; Decimal_Number ; digit
314 gc ; Nl ; Letter_Number
315 gc ; No ; Other_Number
316 gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps
317 gc ; Pc ; Connector_Punctuation
318 gc ; Pd ; Dash_Punctuation
319 gc ; Pe ; Close_Punctuation
320 gc ; Pf ; Final_Punctuation
321 gc ; Pi ; Initial_Punctuation
322 gc ; Po ; Other_Punctuation
323 gc ; Ps ; Open_Punctuation
324 gc ; S ; Symbol # Sc | Sk | Sm | So
325 gc ; Sc ; Currency_Symbol
326 gc ; Sk ; Modifier_Symbol
327 gc ; Sm ; Math_Symbol
328 gc ; So ; Other_Symbol
329 gc ; Z ; Separator # Zl | Zp | Zs
330 gc ; Zl ; Line_Separator
331 gc ; Zp ; Paragraph_Separator
332 gc ; Zs ; Space_Separator
334 # Grapheme_Cluster_Break (GCB)
336 GCB; CN ; Control
337 GCB; CR ; CR
338 GCB; EX ; Extend
339 GCB; L ; L
340 GCB; LF ; LF
341 GCB; LV ; LV
342 GCB; LVT ; LVT
343 GCB; T ; T
344 GCB; V ; V
345 GCB; XX ; Other
347 # Hangul_Syllable_Type (hst)
349 hst; L ; Leading_Jamo
350 hst; LV ; LV_Syllable
351 hst; LVT ; LVT_Syllable
352 hst; NA ; Not_Applicable
353 hst; T ; Trailing_Jamo
354 hst; V ; Vowel_Jamo
356 # Joining_Group (jg)
358 jg ; n/a ; Ain
359 jg ; n/a ; Alaph
360 jg ; n/a ; Alef
361 jg ; n/a ; Beh
362 jg ; n/a ; Beth
363 jg ; n/a ; Dal
364 jg ; n/a ; Dalath_Rish
365 jg ; n/a ; E
366 jg ; n/a ; Fe
367 jg ; n/a ; Feh
368 jg ; n/a ; Final_Semkath
369 jg ; n/a ; Gaf
370 jg ; n/a ; Gamal
371 jg ; n/a ; Hah
372 jg ; n/a ; Hamza_On_Heh_Goal
373 jg ; n/a ; He
374 jg ; n/a ; Heh
375 jg ; n/a ; Heh_Goal
376 jg ; n/a ; Heth
377 jg ; n/a ; Kaf
378 jg ; n/a ; Kaph
379 jg ; n/a ; Khaph
380 jg ; n/a ; Knotted_Heh
381 jg ; n/a ; Lam
382 jg ; n/a ; Lamadh
383 jg ; n/a ; Meem
384 jg ; n/a ; Mim
385 jg ; n/a ; No_Joining_Group
386 jg ; n/a ; Noon
387 jg ; n/a ; Nun
388 jg ; n/a ; Pe
389 jg ; n/a ; Qaf
390 jg ; n/a ; Qaph
391 jg ; n/a ; Reh
392 jg ; n/a ; Reversed_Pe
393 jg ; n/a ; Sad
394 jg ; n/a ; Sadhe
395 jg ; n/a ; Seen
396 jg ; n/a ; Semkath
397 jg ; n/a ; Shin
398 jg ; n/a ; Swash_Kaf
399 jg ; n/a ; Syriac_Waw
400 jg ; n/a ; Tah
401 jg ; n/a ; Taw
402 jg ; n/a ; Teh_Marbuta
403 jg ; n/a ; Teth
404 jg ; n/a ; Waw
405 jg ; n/a ; Yeh
406 jg ; n/a ; Yeh_Barree
407 jg ; n/a ; Yeh_With_Tail
408 jg ; n/a ; Yudh
409 jg ; n/a ; Yudh_He
410 jg ; n/a ; Zain
411 jg ; n/a ; Zhain
413 # Joining_Type (jt)
415 jt ; C ; Join_Causing
416 jt ; D ; Dual_Joining
417 jt ; L ; Left_Joining
418 jt ; R ; Right_Joining
419 jt ; T ; Transparent
420 jt ; U ; Non_Joining
422 # Line_Break (lb)
424 lb ; AI ; Ambiguous
425 lb ; AL ; Alphabetic
426 lb ; B2 ; Break_Both
427 lb ; BA ; Break_After
428 lb ; BB ; Break_Before
429 lb ; BK ; Mandatory_Break
430 lb ; CB ; Contingent_Break
431 lb ; CL ; Close_Punctuation
432 lb ; CM ; Combining_Mark
433 lb ; CR ; Carriage_Return
434 lb ; EX ; Exclamation
435 lb ; GL ; Glue
436 lb ; H2 ; H2
437 lb ; H3 ; H3
438 lb ; HY ; Hyphen
439 lb ; ID ; Ideographic
440 lb ; IN ; Inseparable ; Inseperable
441 lb ; IS ; Infix_Numeric
442 lb ; JL ; JL
443 lb ; JT ; JT
444 lb ; JV ; JV
445 lb ; LF ; Line_Feed
446 lb ; NL ; Next_Line
447 lb ; NS ; Nonstarter
448 lb ; NU ; Numeric
449 lb ; OP ; Open_Punctuation
450 lb ; PO ; Postfix_Numeric
451 lb ; PR ; Prefix_Numeric
452 lb ; QU ; Quotation
453 lb ; SA ; Complex_Context
454 lb ; SG ; Surrogate
455 lb ; SP ; Space
456 lb ; SY ; Break_Symbols
457 lb ; WJ ; Word_Joiner
458 lb ; XX ; Unknown
459 lb ; ZW ; ZWSpace
461 # NFC_Quick_Check (NFC_QC)
463 NFC_QC; M ; Maybe
464 NFC_QC; N ; No
465 NFC_QC; Y ; Yes
467 # NFD_Quick_Check (NFD_QC)
469 NFD_QC; N ; No
470 NFD_QC; Y ; Yes
472 # NFKC_Quick_Check (NFKC_QC)
474 NFKC_QC; M ; Maybe
475 NFKC_QC; N ; No
476 NFKC_QC; Y ; Yes
478 # NFKD_Quick_Check (NFKD_QC)
480 NFKD_QC; N ; No
481 NFKD_QC; Y ; Yes
483 # Numeric_Type (nt)
485 nt ; De ; Decimal
486 nt ; Di ; Digit
487 nt ; None ; None
488 nt ; Nu ; Numeric
490 # Script (sc)
492 sc ; Arab ; Arabic
493 sc ; Armn ; Armenian
494 sc ; Beng ; Bengali
495 sc ; Bopo ; Bopomofo
496 sc ; Brai ; Braille
497 sc ; Bugi ; Buginese
498 sc ; Buhd ; Buhid
499 sc ; Cans ; Canadian_Aboriginal
500 sc ; Cher ; Cherokee
501 sc ; Copt ; Coptic ; Qaac
502 sc ; Cprt ; Cypriot
503 sc ; Cyrl ; Cyrillic
504 sc ; Deva ; Devanagari
505 sc ; Dsrt ; Deseret
506 sc ; Ethi ; Ethiopic
507 sc ; Geor ; Georgian
508 sc ; Glag ; Glagolitic
509 sc ; Goth ; Gothic
510 sc ; Grek ; Greek
511 sc ; Gujr ; Gujarati
512 sc ; Guru ; Gurmukhi
513 sc ; Hang ; Hangul
514 sc ; Hani ; Han
515 sc ; Hano ; Hanunoo
516 sc ; Hebr ; Hebrew
517 sc ; Hira ; Hiragana
518 sc ; Hrkt ; Katakana_Or_Hiragana
519 sc ; Ital ; Old_Italic
520 sc ; Kana ; Katakana
521 sc ; Khar ; Kharoshthi
522 sc ; Khmr ; Khmer
523 sc ; Knda ; Kannada
524 sc ; Laoo ; Lao
525 sc ; Latn ; Latin
526 sc ; Limb ; Limbu
527 sc ; Linb ; Linear_B
528 sc ; Mlym ; Malayalam
529 sc ; Mong ; Mongolian
530 sc ; Mymr ; Myanmar
531 sc ; Ogam ; Ogham
532 sc ; Orya ; Oriya
533 sc ; Osma ; Osmanya
534 sc ; Qaai ; Inherited
535 sc ; Runr ; Runic
536 sc ; Shaw ; Shavian
537 sc ; Sinh ; Sinhala
538 sc ; Sylo ; Syloti_Nagri
539 sc ; Syrc ; Syriac
540 sc ; Tagb ; Tagbanwa
541 sc ; Tale ; Tai_Le
542 sc ; Talu ; New_Tai_Lue
543 sc ; Taml ; Tamil
544 sc ; Telu ; Telugu
545 sc ; Tfng ; Tifinagh
546 sc ; Tglg ; Tagalog
547 sc ; Thaa ; Thaana
548 sc ; Thai ; Thai
549 sc ; Tibt ; Tibetan
550 sc ; Ugar ; Ugaritic
551 sc ; Xpeo ; Old_Persian
552 sc ; Yiii ; Yi
553 sc ; Zyyy ; Common
555 # Sentence_Break (SB)
557 SB ; AT ; ATerm
558 SB ; CL ; Close
559 SB ; FO ; Format
560 SB ; LE ; OLetter
561 SB ; LO ; Lower
562 SB ; NU ; Numeric
563 SB ; SE ; Sep
564 SB ; SP ; Sp
565 SB ; ST ; STerm
566 SB ; UP ; Upper
567 SB ; XX ; Other
569 # Word_Break (WB)
571 WB ; EX ; ExtendNumLet
572 WB ; FO ; Format
573 WB ; KA ; Katakana
574 WB ; LE ; ALetter
575 WB ; ML ; MidLetter
576 WB ; MN ; MidNum
577 WB ; NU ; Numeric
578 WB ; XX ; Other