1 # PropertyValueAliases-4.1.0.txt
2 # Date: 2005-03-28, 17:21:48 GMT [MD]
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
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.
14 # The names may be translated in appropriate environments, and additional
15 # aliases may be useful.
19 # Each line describes a property value name.
20 # This consists of three or more fields, separated by semicolons.
22 # First Field: The first field describes the property for which that
23 # property value name is used.
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".
28 # Third Field: The third field is a long name.
30 # In the case of ccc, there are 4 fields. The second field is numeric, third
31 # is abbreviated, and fourth is long.
33 # The above are the preferred aliases. Other aliases may be listed in additional fields.
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".
40 # NOTE: Property value names are NOT unique across properties. For example:
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.
46 # In addition, some property names may be the same as some property value names.
49 # sc means the Script property, and
50 # Sc means the General_Category property value Currency_Symbol (Sc)
52 # The combination of property value and property name is, however, unique.
54 # For more information, see UTS #18: Regular Expression Guidelines
55 # ================================================
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
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
99 blk; n/a ; Arabic_Presentation_Forms-A
100 blk; n/a ; Arabic_Presentation_Forms-B
101 blk; n/a ; Arabic_Supplement
104 blk; n/a ; Basic_Latin
106 blk; n/a ; Block_Elements
108 blk; n/a ; Bopomofo_Extended
109 blk; n/a ; Box_Drawing
110 blk; n/a ; Braille_Patterns
113 blk; n/a ; Byzantine_Musical_Symbols
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
131 blk; n/a ; Currency_Symbols
132 blk; n/a ; Cypriot_Syllabary
134 blk; n/a ; Cyrillic_Supplement ; Cyrillic_Supplementary
136 blk; n/a ; Devanagari
138 blk; n/a ; Enclosed_Alphanumerics
139 blk; n/a ; Enclosed_CJK_Letters_and_Months
141 blk; n/a ; Ethiopic_Extended
142 blk; n/a ; Ethiopic_Supplement
143 blk; n/a ; General_Punctuation
144 blk; n/a ; Geometric_Shapes
146 blk; n/a ; Georgian_Supplement
147 blk; n/a ; Glagolitic
149 blk; n/a ; Greek_and_Coptic
150 blk; n/a ; Greek_Extended
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
159 blk; n/a ; High_Private_Use_Surrogates
160 blk; n/a ; High_Surrogates
162 blk; n/a ; Ideographic_Description_Characters
163 blk; n/a ; IPA_Extensions
165 blk; n/a ; Kangxi_Radicals
168 blk; n/a ; Katakana_Phonetic_Extensions
169 blk; n/a ; Kharoshthi
171 blk; n/a ; Khmer_Symbols
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
179 blk; n/a ; Linear_B_Ideograms
180 blk; n/a ; Linear_B_Syllabary
181 blk; n/a ; Low_Surrogates
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
192 blk; n/a ; Musical_Symbols
194 blk; n/a ; New_Tai_Lue
196 blk; n/a ; Number_Forms
198 blk; n/a ; Old_Italic
199 blk; n/a ; Old_Persian
200 blk; n/a ; Optical_Character_Recognition
203 blk; n/a ; Phonetic_Extensions
204 blk; n/a ; Phonetic_Extensions_Supplement
205 blk; n/a ; Private_Use_Area
209 blk; n/a ; Small_Form_Variants
210 blk; n/a ; Spacing_Modifier_Letters
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
225 blk; n/a ; Tai_Xuan_Jing_Symbols
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
246 ccc; 8; KV ; Kana_Voicing
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
253 ccc; 222; BR ; Below_Right
256 ccc; 228; AL ; Above_Left
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)
284 # East_Asian_Width (ea)
293 # General_Category (gc)
295 gc ; C ; Other # Cc | Cf | Cn | Co | Cs
296 gc ; Cc ; Control ; cntrl
299 gc ; Co ; Private_Use
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)
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
364 jg ; n/a ; Dalath_Rish
368 jg ; n/a ; Final_Semkath
372 jg ; n/a ; Hamza_On_Heh_Goal
380 jg ; n/a ; Knotted_Heh
385 jg ; n/a ; No_Joining_Group
392 jg ; n/a ; Reversed_Pe
399 jg ; n/a ; Syriac_Waw
402 jg ; n/a ; Teh_Marbuta
406 jg ; n/a ; Yeh_Barree
407 jg ; n/a ; Yeh_With_Tail
415 jt ; C ; Join_Causing
416 jt ; D ; Dual_Joining
417 jt ; L ; Left_Joining
418 jt ; R ; Right_Joining
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
439 lb ; ID ; Ideographic
440 lb ; IN ; Inseparable ; Inseperable
441 lb ; IS ; Infix_Numeric
449 lb ; OP ; Open_Punctuation
450 lb ; PO ; Postfix_Numeric
451 lb ; PR ; Prefix_Numeric
453 lb ; SA ; Complex_Context
456 lb ; SY ; Break_Symbols
457 lb ; WJ ; Word_Joiner
461 # NFC_Quick_Check (NFC_QC)
467 # NFD_Quick_Check (NFD_QC)
472 # NFKC_Quick_Check (NFKC_QC)
478 # NFKD_Quick_Check (NFKD_QC)
499 sc ; Cans ; Canadian_Aboriginal
501 sc ; Copt ; Coptic ; Qaac
504 sc ; Deva ; Devanagari
508 sc ; Glag ; Glagolitic
518 sc ; Hrkt ; Katakana_Or_Hiragana
519 sc ; Ital ; Old_Italic
521 sc ; Khar ; Kharoshthi
528 sc ; Mlym ; Malayalam
529 sc ; Mong ; Mongolian
534 sc ; Qaai ; Inherited
538 sc ; Sylo ; Syloti_Nagri
542 sc ; Talu ; New_Tai_Lue
551 sc ; Xpeo ; Old_Persian
555 # Sentence_Break (SB)
571 WB ; EX ; ExtendNumLet