icuSources/data/unidata/PropertyValueAliases.txt

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