1# PropertyValueAliases-4.0.1.txt
2# Date: 2004-03-02, 19:46:47 GMT [MD]
3#
4# Unicode Character Database
5# Copyright (c) 1991-2004 Unicode, Inc.
6# For terms of use, see http://www.unicode.org/terms_of_use.html
7# For documentation, see UCD.html
8# This file contains aliases for property values used in the UCD.
9# These names can be used for XML formats of UCD data, for regular-expression
10# property tests, and other programmatic textual descriptions of Unicode data.
11# For information on which properties are normative, see UCD.html.
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# If there is no abbreviated name available, the field is marked with "n/a".
26#
27# Third Field: The third field is a long name.
28#
29# In the case of ccc, there are 4 fields. The second field is numeric, third
30# is abbreviated, and fourth is long.
31#
32# The above are the preferred aliases. Other aliases may be listed in additional fields.
33#
34# Loose matching should be applied to all property names and property values, with
35# the exception of String Property values. With loose matching of property names and
36# values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property
37# values, numeric equivalencies are applied: thus "01.00" 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 Alpha_Left for the 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: Regular Expression Guidelines
54# ================================================
55
56
57# Age (age)
58
59age; n/a       ; 1.1
60age; n/a       ; 2.0
61age; n/a       ; 2.1
62age; n/a       ; 3.0
63age; n/a       ; 3.1
64age; n/a       ; 3.2
65age; n/a       ; 4.0
66age; n/a       ; unassigned
67
68# Bidi_Class (bc)
69
70bc ; AL        ; Arabic_Letter
71bc ; AN        ; Arabic_Number
72bc ; B         ; Paragraph_Separator
73bc ; BN        ; Boundary_Neutral
74bc ; CS        ; Common_Separator
75bc ; EN        ; European_Number
76bc ; ES        ; European_Separator
77bc ; ET        ; European_Terminator
78bc ; L         ; Left_To_Right
79bc ; LRE       ; Left_To_Right_Embedding
80bc ; LRO       ; Left_To_Right_Override
81bc ; NSM       ; Nonspacing_Mark
82bc ; ON        ; Other_Neutral
83bc ; PDF       ; Pop_Directional_Format
84bc ; R         ; Right_To_Left
85bc ; RLE       ; Right_To_Left_Embedding
86bc ; RLO       ; Right_To_Left_Override
87bc ; S         ; Segment_Separator
88bc ; WS        ; White_Space
89
90# Block (blk)
91
92blk; n/a       ; Aegean_Numbers
93blk; n/a       ; Alphabetic_Presentation_Forms
94blk; n/a       ; Arabic
95blk; n/a       ; Arabic_Presentation_Forms-A
96blk; n/a       ; Arabic_Presentation_Forms-B
97blk; n/a       ; Armenian
98blk; n/a       ; Arrows
99blk; n/a       ; Basic_Latin
100blk; n/a       ; Bengali
101blk; n/a       ; Block_Elements
102blk; n/a       ; Bopomofo
103blk; n/a       ; Bopomofo_Extended
104blk; n/a       ; Box_Drawing
105blk; n/a       ; Braille_Patterns
106blk; n/a       ; Buhid
107blk; n/a       ; Byzantine_Musical_Symbols
108blk; n/a       ; Cherokee
109blk; n/a       ; CJK_Compatibility
110blk; n/a       ; CJK_Compatibility_Forms
111blk; n/a       ; CJK_Compatibility_Ideographs
112blk; n/a       ; CJK_Compatibility_Ideographs_Supplement
113blk; n/a       ; CJK_Radicals_Supplement
114blk; n/a       ; CJK_Symbols_and_Punctuation
115blk; n/a       ; CJK_Unified_Ideographs
116blk; n/a       ; CJK_Unified_Ideographs_Extension_A
117blk; n/a       ; CJK_Unified_Ideographs_Extension_B
118blk; n/a       ; Combining_Diacritical_Marks
119blk; n/a       ; Combining_Diacritical_Marks_for_Symbols
120blk; n/a       ; Combining_Half_Marks
121blk; n/a       ; Control_Pictures
122blk; n/a       ; Currency_Symbols
123blk; n/a       ; Cypriot_Syllabary
124blk; n/a       ; Cyrillic
125blk; n/a       ; Cyrillic_Supplement              ; Cyrillic_Supplementary
126blk; n/a       ; Deseret
127blk; n/a       ; Devanagari
128blk; n/a       ; Dingbats
129blk; n/a       ; Enclosed_Alphanumerics
130blk; n/a       ; Enclosed_CJK_Letters_and_Months
131blk; n/a       ; Ethiopic
132blk; n/a       ; General_Punctuation
133blk; n/a       ; Geometric_Shapes
134blk; n/a       ; Georgian
135blk; n/a       ; Gothic
136blk; n/a       ; Greek_and_Coptic
137blk; n/a       ; Greek_Extended
138blk; n/a       ; Gujarati
139blk; n/a       ; Gurmukhi
140blk; n/a       ; Halfwidth_and_Fullwidth_Forms
141blk; n/a       ; Hangul_Compatibility_Jamo
142blk; n/a       ; Hangul_Jamo
143blk; n/a       ; Hangul_Syllables
144blk; n/a       ; Hanunoo
145blk; n/a       ; Hebrew
146blk; n/a       ; High_Private_Use_Surrogates
147blk; n/a       ; High_Surrogates
148blk; n/a       ; Hiragana
149blk; n/a       ; Ideographic_Description_Characters
150blk; n/a       ; IPA_Extensions
151blk; n/a       ; Kanbun
152blk; n/a       ; Kangxi_Radicals
153blk; n/a       ; Kannada
154blk; n/a       ; Katakana
155blk; n/a       ; Katakana_Phonetic_Extensions
156blk; n/a       ; Khmer
157blk; n/a       ; Khmer_Symbols
158blk; n/a       ; Lao
159blk; n/a       ; Latin-1_Supplement
160blk; n/a       ; Latin_Extended-A
161blk; n/a       ; Latin_Extended-B
162blk; n/a       ; Latin_Extended_Additional
163blk; n/a       ; Letterlike_Symbols
164blk; n/a       ; Limbu
165blk; n/a       ; Linear_B_Ideograms
166blk; n/a       ; Linear_B_Syllabary
167blk; n/a       ; Low_Surrogates
168blk; n/a       ; Malayalam
169blk; n/a       ; Mathematical_Alphanumeric_Symbols
170blk; n/a       ; Mathematical_Operators
171blk; n/a       ; Miscellaneous_Mathematical_Symbols-A
172blk; n/a       ; Miscellaneous_Mathematical_Symbols-B
173blk; n/a       ; Miscellaneous_Symbols
174blk; n/a       ; Miscellaneous_Symbols_and_Arrows
175blk; n/a       ; Miscellaneous_Technical
176blk; n/a       ; Mongolian
177blk; n/a       ; Musical_Symbols
178blk; n/a       ; Myanmar
179blk; n/a       ; No_Block
180blk; n/a       ; Number_Forms
181blk; n/a       ; Ogham
182blk; n/a       ; Old_Italic
183blk; n/a       ; Optical_Character_Recognition
184blk; n/a       ; Oriya
185blk; n/a       ; Osmanya
186blk; n/a       ; Phonetic_Extensions
187blk; n/a       ; Private_Use_Area
188blk; n/a       ; Runic
189blk; n/a       ; Shavian
190blk; n/a       ; Sinhala
191blk; n/a       ; Small_Form_Variants
192blk; n/a       ; Spacing_Modifier_Letters
193blk; n/a       ; Specials
194blk; n/a       ; Superscripts_and_Subscripts
195blk; n/a       ; Supplemental_Arrows-A
196blk; n/a       ; Supplemental_Arrows-B
197blk; n/a       ; Supplemental_Mathematical_Operators
198blk; n/a       ; Supplementary_Private_Use_Area-A
199blk; n/a       ; Supplementary_Private_Use_Area-B
200blk; n/a       ; Syriac
201blk; n/a       ; Tagalog
202blk; n/a       ; Tagbanwa
203blk; n/a       ; Tags
204blk; n/a       ; Tai_Le
205blk; n/a       ; Tai_Xuan_Jing_Symbols
206blk; n/a       ; Tamil
207blk; n/a       ; Telugu
208blk; n/a       ; Thaana
209blk; n/a       ; Thai
210blk; n/a       ; Tibetan
211blk; n/a       ; Ugaritic
212blk; n/a       ; Unified_Canadian_Aboriginal_Syllabics
213blk; n/a       ; Variation_Selectors
214blk; n/a       ; Variation_Selectors_Supplement
215blk; n/a       ; Yi_Radicals
216blk; n/a       ; Yi_Syllables
217blk; n/a       ; Yijing_Hexagram_Symbols
218
219# Canonical_Combining_Class (ccc)
220
221ccc;   0; NR   ; Not_Reordered
222ccc;   1; OV   ; Overlay
223ccc;   7; NK   ; Nukta
224ccc;   8; KV   ; Kana_Voicing
225ccc;   9; VR   ; Virama
226ccc; 200; ATBL ; Attached_Below_Left
227ccc; 202; ATB  ; Attached_Below
228ccc; 216; ATAR ; Attached_Above_Right
229ccc; 218; BL   ; Below_Left
230ccc; 220; B    ; Below
231ccc; 222; BR   ; Below_Right
232ccc; 224; L    ; Left
233ccc; 226; R    ; Right
234ccc; 228; AL   ; Above_Left
235ccc; 230; A    ; Above
236ccc; 232; AR   ; Above_Right
237ccc; 233; DB   ; Double_Below
238ccc; 234; DA   ; Double_Above
239ccc; 240; IS   ; Iota_Subscript
240
241# Decomposition_Type (dt)
242
243dt ; can       ; Canonical
244dt ; com       ; Compat
245dt ; enc       ; Circle
246dt ; fin       ; Final
247dt ; font      ; Font
248dt ; fra       ; Fraction
249dt ; init      ; Initial
250dt ; iso       ; Isolated
251dt ; med       ; Medial
252dt ; nar       ; Narrow
253dt ; nb        ; Nobreak
254dt ; none      ; None
255dt ; sml       ; Small
256dt ; sqr       ; Square
257dt ; sub       ; Sub
258dt ; sup       ; Super
259dt ; vert      ; Vertical
260dt ; wide      ; Wide
261
262# East_Asian_Width (ea)
263
264ea ; A         ; Ambiguous
265ea ; F         ; Fullwidth
266ea ; H         ; Halfwidth
267ea ; N         ; Neutral
268ea ; Na        ; Narrow
269ea ; W         ; Wide
270
271# General_Category (gc)
272
273gc ; C         ; Other                            # Cc | Cf | Cn | Co | Cs
274gc ; Cc        ; Control
275gc ; Cf        ; Format
276gc ; Cn        ; Unassigned
277gc ; Co        ; Private_Use
278gc ; Cs        ; Surrogate
279gc ; L         ; Letter                           # Ll | Lm | Lo | Lt | Lu
280gc ; LC        ; Cased_Letter                     # Ll | Lt | Lu
281gc ; Ll        ; Lowercase_Letter
282gc ; Lm        ; Modifier_Letter
283gc ; Lo        ; Other_Letter
284gc ; Lt        ; Titlecase_Letter
285gc ; Lu        ; Uppercase_Letter
286gc ; M         ; Mark                             # Mc | Me | Mn
287gc ; Mc        ; Spacing_Mark
288gc ; Me        ; Enclosing_Mark
289gc ; Mn        ; Nonspacing_Mark
290gc ; N         ; Number                           # Nd | Nl | No
291gc ; Nd        ; Decimal_Number
292gc ; Nl        ; Letter_Number
293gc ; No        ; Other_Number
294gc ; P         ; Punctuation                      # Pc | Pd | Pe | Pf | Pi | Po | Ps
295gc ; Pc        ; Connector_Punctuation
296gc ; Pd        ; Dash_Punctuation
297gc ; Pe        ; Close_Punctuation
298gc ; Pf        ; Final_Punctuation
299gc ; Pi        ; Initial_Punctuation
300gc ; Po        ; Other_Punctuation
301gc ; Ps        ; Open_Punctuation
302gc ; S         ; Symbol                           # Sc | Sk | Sm | So
303gc ; Sc        ; Currency_Symbol
304gc ; Sk        ; Modifier_Symbol
305gc ; Sm        ; Math_Symbol
306gc ; So        ; Other_Symbol
307gc ; Z         ; Separator                        # Zl | Zp | Zs
308gc ; Zl        ; Line_Separator
309gc ; Zp        ; Paragraph_Separator
310gc ; Zs        ; Space_Separator
311
312# Hangul_Syllable_Type (hst)
313
314hst; L         ; Leading_Jamo
315hst; LV        ; LV_Syllable
316hst; LVT       ; LVT_Syllable
317hst; NA        ; Not_Applicable
318hst; T         ; Trailing_Jamo
319hst; V         ; Vowel_Jamo
320
321# Joining_Group (jg)
322
323jg ; n/a       ; Ain
324jg ; n/a       ; Alaph
325jg ; n/a       ; Alef
326jg ; n/a       ; Beh
327jg ; n/a       ; Beth
328jg ; n/a       ; Dal
329jg ; n/a       ; Dalath_Rish
330jg ; n/a       ; E
331jg ; n/a       ; Fe
332jg ; n/a       ; Feh
333jg ; n/a       ; Final_Semkath
334jg ; n/a       ; Gaf
335jg ; n/a       ; Gamal
336jg ; n/a       ; Hah
337jg ; n/a       ; Hamza_On_Heh_Goal
338jg ; n/a       ; He
339jg ; n/a       ; Heh
340jg ; n/a       ; Heh_Goal
341jg ; n/a       ; Heth
342jg ; n/a       ; Kaf
343jg ; n/a       ; Kaph
344jg ; n/a       ; Khaph
345jg ; n/a       ; Knotted_Heh
346jg ; n/a       ; Lam
347jg ; n/a       ; Lamadh
348jg ; n/a       ; Meem
349jg ; n/a       ; Mim
350jg ; n/a       ; No_Joining_Group
351jg ; n/a       ; Noon
352jg ; n/a       ; Nun
353jg ; n/a       ; Pe
354jg ; n/a       ; Qaf
355jg ; n/a       ; Qaph
356jg ; n/a       ; Reh
357jg ; n/a       ; Reversed_Pe
358jg ; n/a       ; Sad
359jg ; n/a       ; Sadhe
360jg ; n/a       ; Seen
361jg ; n/a       ; Semkath
362jg ; n/a       ; Shin
363jg ; n/a       ; Swash_Kaf
364jg ; n/a       ; Syriac_Waw
365jg ; n/a       ; Tah
366jg ; n/a       ; Taw
367jg ; n/a       ; Teh_Marbuta
368jg ; n/a       ; Teth
369jg ; n/a       ; Waw
370jg ; n/a       ; Yeh
371jg ; n/a       ; Yeh_Barree
372jg ; n/a       ; Yeh_With_Tail
373jg ; n/a       ; Yudh
374jg ; n/a       ; Yudh_He
375jg ; n/a       ; Zain
376jg ; n/a       ; Zhain
377
378# Joining_Type (jt)
379
380jt ; C         ; Join_Causing
381jt ; D         ; Dual_Joining
382jt ; L         ; Left_Joining
383jt ; R         ; Right_Joining
384jt ; T         ; Transparent
385jt ; U         ; Non_Joining
386
387# Line_Break (lb)
388
389lb ; AI        ; Ambiguous
390lb ; AL        ; Alphabetic
391lb ; B2        ; Break_Both
392lb ; BA        ; Break_After
393lb ; BB        ; Break_Before
394lb ; BK        ; Mandatory_Break
395lb ; CB        ; Contingent_Break
396lb ; CL        ; Close_Punctuation
397lb ; CM        ; Combining_Mark
398lb ; CR        ; Carriage_Return
399lb ; EX        ; Exclamation
400lb ; GL        ; Glue
401lb ; HY        ; Hyphen
402lb ; ID        ; Ideographic
403lb ; IN        ; Inseparable                      ; Inseperable
404lb ; IS        ; Infix_Numeric
405lb ; LF        ; Line_Feed
406lb ; NL        ; Next_Line
407lb ; NS        ; Nonstarter
408lb ; NU        ; Numeric
409lb ; OP        ; Open_Punctuation
410lb ; PO        ; Postfix_Numeric
411lb ; PR        ; Prefix_Numeric
412lb ; QU        ; Quotation
413lb ; SA        ; Complex_Context
414lb ; SG        ; Surrogate
415lb ; SP        ; Space
416lb ; SY        ; Break_Symbols
417lb ; WJ        ; Word_Joiner
418lb ; XX        ; Unknown
419lb ; ZW        ; ZWSpace
420
421# NFC_Quick_Check (NFC_QC)
422
423NFC_QC; M      ; Maybe
424NFC_QC; N      ; No
425NFC_QC; Y      ; Yes
426
427# NFD_Quick_Check (NFD_QC)
428
429NFD_QC; N      ; No
430NFD_QC; Y      ; Yes
431
432# NFKC_Quick_Check (NFKC_QC)
433
434NFKC_QC; M     ; Maybe
435NFKC_QC; N     ; No
436NFKC_QC; Y     ; Yes
437
438# NFKD_Quick_Check (NFKD_QC)
439
440NFKD_QC; N     ; No
441NFKD_QC; Y     ; Yes
442
443# Numeric_Type (nt)
444
445nt ; De        ; Decimal
446nt ; Di        ; Digit
447nt ; None      ; None
448nt ; Nu        ; Numeric
449
450# Script (sc)
451
452sc ; Arab      ; Arabic
453sc ; Armn      ; Armenian
454sc ; Beng      ; Bengali
455sc ; Bopo      ; Bopomofo
456sc ; Brai      ; Braille
457sc ; Buhd      ; Buhid
458sc ; Cans      ; Canadian_Aboriginal
459sc ; Cher      ; Cherokee
460sc ; Cprt      ; Cypriot
461sc ; Cyrl      ; Cyrillic
462sc ; Deva      ; Devanagari
463sc ; Dsrt      ; Deseret
464sc ; Ethi      ; Ethiopic
465sc ; Geor      ; Georgian
466sc ; Goth      ; Gothic
467sc ; Grek      ; Greek
468sc ; Gujr      ; Gujarati
469sc ; Guru      ; Gurmukhi
470sc ; Hang      ; Hangul
471sc ; Hani      ; Han
472sc ; Hano      ; Hanunoo
473sc ; Hebr      ; Hebrew
474sc ; Hira      ; Hiragana
475sc ; Hrkt      ; Katakana_Or_Hiragana
476sc ; Ital      ; Old_Italic
477sc ; Kana      ; Katakana
478sc ; Khmr      ; Khmer
479sc ; Knda      ; Kannada
480sc ; Laoo      ; Lao
481sc ; Latn      ; Latin
482sc ; Limb      ; Limbu
483sc ; Linb      ; Linear_B
484sc ; Mlym      ; Malayalam
485sc ; Mong      ; Mongolian
486sc ; Mymr      ; Myanmar
487sc ; Ogam      ; Ogham
488sc ; Orya      ; Oriya
489sc ; Osma      ; Osmanya
490sc ; Qaai      ; Inherited
491sc ; Runr      ; Runic
492sc ; Shaw      ; Shavian
493sc ; Sinh      ; Sinhala
494sc ; Syrc      ; Syriac
495sc ; Tagb      ; Tagbanwa
496sc ; Tale      ; Tai_Le
497sc ; Taml      ; Tamil
498sc ; Telu      ; Telugu
499sc ; Tglg      ; Tagalog
500sc ; Thaa      ; Thaana
501sc ; Thai      ; Thai
502sc ; Tibt      ; Tibetan
503sc ; Ugar      ; Ugaritic
504sc ; Yiii      ; Yi
505sc ; Zyyy      ; Common
506