Commit | Line | Data |
98fbe989 |
1 | # PropertyValueAliases-5.0.0.txt |
2 | # Date: 2006-03-03, 08:23:34 GMT [MD] |
822ebcc8 |
3 | # |
7be0dac3 |
4 | # Unicode Character Database |
98fbe989 |
5 | # Copyright (c) 1991-2006 Unicode, Inc. |
7be0dac3 |
6 | # For terms of use, see http://www.unicode.org/terms_of_use.html |
7 | # For documentation, see UCD.html |
a2bd7410 |
8 | # |
822ebcc8 |
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. |
1911be83 |
12 | # For information on which properties are normative, see UCD.html. |
822ebcc8 |
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. |
7be0dac3 |
20 | # This consists of three or more fields, separated by semicolons. |
822ebcc8 |
21 | # |
22 | # First Field: The first field describes the property for which that |
23 | # property value name is used. |
822ebcc8 |
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 | # |
1911be83 |
30 | # In the case of ccc, there are 4 fields. The second field is numeric, third |
822ebcc8 |
31 | # is abbreviated, and fourth is long. |
32 | # |
7be0dac3 |
33 | # The above are the preferred aliases. Other aliases may be listed in additional fields. |
822ebcc8 |
34 | # |
7be0dac3 |
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". |
822ebcc8 |
39 | # |
7be0dac3 |
40 | # NOTE: Property value names are NOT unique across properties. For example: |
1911be83 |
41 | # |
7be0dac3 |
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. |
822ebcc8 |
45 | # |
1911be83 |
46 | # In addition, some property names may be the same as some property value names. |
47 | # For example: |
48 | # |
7be0dac3 |
49 | # sc means the Script property, and |
50 | # Sc means the General_Category property value Currency_Symbol (Sc) |
822ebcc8 |
51 | # |
52 | # The combination of property value and property name is, however, unique. |
7be0dac3 |
53 | # |
54 | # For more information, see UTS #18: Regular Expression Guidelines |
822ebcc8 |
55 | # ================================================ |
56 | |
57 | |
7be0dac3 |
58 | # Age (age) |
59 | |
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 |
a2bd7410 |
67 | age; n/a ; 4.1 |
98fbe989 |
68 | age; n/a ; 5.0 |
7be0dac3 |
69 | age; n/a ; unassigned |
70 | |
71 | # Bidi_Class (bc) |
72 | |
822ebcc8 |
73 | bc ; AL ; Arabic_Letter |
74 | bc ; AN ; Arabic_Number |
75 | bc ; B ; Paragraph_Separator |
76 | bc ; BN ; Boundary_Neutral |
77 | bc ; CS ; Common_Separator |
78 | bc ; EN ; European_Number |
79 | bc ; ES ; European_Separator |
80 | bc ; ET ; European_Terminator |
81 | bc ; L ; Left_To_Right |
82 | bc ; LRE ; Left_To_Right_Embedding |
83 | bc ; LRO ; Left_To_Right_Override |
84 | bc ; NSM ; Nonspacing_Mark |
85 | bc ; ON ; Other_Neutral |
86 | bc ; PDF ; Pop_Directional_Format |
87 | bc ; R ; Right_To_Left |
88 | bc ; RLE ; Right_To_Left_Embedding |
89 | bc ; RLO ; Right_To_Left_Override |
90 | bc ; S ; Segment_Separator |
91 | bc ; WS ; White_Space |
92 | |
7be0dac3 |
93 | # Block (blk) |
94 | |
1911be83 |
95 | blk; n/a ; Aegean_Numbers |
96 | blk; n/a ; Alphabetic_Presentation_Forms |
a2bd7410 |
97 | blk; n/a ; Ancient_Greek_Musical_Notation |
98 | blk; n/a ; Ancient_Greek_Numbers |
1911be83 |
99 | blk; n/a ; Arabic |
100 | blk; n/a ; Arabic_Presentation_Forms-A |
101 | blk; n/a ; Arabic_Presentation_Forms-B |
a2bd7410 |
102 | blk; n/a ; Arabic_Supplement |
1911be83 |
103 | blk; n/a ; Armenian |
104 | blk; n/a ; Arrows |
98fbe989 |
105 | blk; n/a ; Balinese |
1911be83 |
106 | blk; n/a ; Basic_Latin |
107 | blk; n/a ; Bengali |
108 | blk; n/a ; Block_Elements |
109 | blk; n/a ; Bopomofo |
110 | blk; n/a ; Bopomofo_Extended |
111 | blk; n/a ; Box_Drawing |
112 | blk; n/a ; Braille_Patterns |
a2bd7410 |
113 | blk; n/a ; Buginese |
1911be83 |
114 | blk; n/a ; Buhid |
115 | blk; n/a ; Byzantine_Musical_Symbols |
116 | blk; n/a ; Cherokee |
117 | blk; n/a ; CJK_Compatibility |
118 | blk; n/a ; CJK_Compatibility_Forms |
119 | blk; n/a ; CJK_Compatibility_Ideographs |
120 | blk; n/a ; CJK_Compatibility_Ideographs_Supplement |
121 | blk; n/a ; CJK_Radicals_Supplement |
a2bd7410 |
122 | blk; n/a ; CJK_Strokes |
1911be83 |
123 | blk; n/a ; CJK_Symbols_and_Punctuation |
124 | blk; n/a ; CJK_Unified_Ideographs |
125 | blk; n/a ; CJK_Unified_Ideographs_Extension_A |
126 | blk; n/a ; CJK_Unified_Ideographs_Extension_B |
127 | blk; n/a ; Combining_Diacritical_Marks |
128 | blk; n/a ; Combining_Diacritical_Marks_for_Symbols |
a2bd7410 |
129 | blk; n/a ; Combining_Diacritical_Marks_Supplement |
1911be83 |
130 | blk; n/a ; Combining_Half_Marks |
131 | blk; n/a ; Control_Pictures |
a2bd7410 |
132 | blk; n/a ; Coptic |
98fbe989 |
133 | blk; n/a ; Counting_Rod_Numerals |
134 | blk; n/a ; Cuneiform |
135 | blk; n/a ; Cuneiform_Numbers_and_Punctuation |
1911be83 |
136 | blk; n/a ; Currency_Symbols |
137 | blk; n/a ; Cypriot_Syllabary |
138 | blk; n/a ; Cyrillic |
7be0dac3 |
139 | blk; n/a ; Cyrillic_Supplement ; Cyrillic_Supplementary |
1911be83 |
140 | blk; n/a ; Deseret |
141 | blk; n/a ; Devanagari |
142 | blk; n/a ; Dingbats |
143 | blk; n/a ; Enclosed_Alphanumerics |
144 | blk; n/a ; Enclosed_CJK_Letters_and_Months |
145 | blk; n/a ; Ethiopic |
a2bd7410 |
146 | blk; n/a ; Ethiopic_Extended |
147 | blk; n/a ; Ethiopic_Supplement |
1911be83 |
148 | blk; n/a ; General_Punctuation |
149 | blk; n/a ; Geometric_Shapes |
150 | blk; n/a ; Georgian |
a2bd7410 |
151 | blk; n/a ; Georgian_Supplement |
152 | blk; n/a ; Glagolitic |
1911be83 |
153 | blk; n/a ; Gothic |
154 | blk; n/a ; Greek_and_Coptic |
155 | blk; n/a ; Greek_Extended |
156 | blk; n/a ; Gujarati |
157 | blk; n/a ; Gurmukhi |
158 | blk; n/a ; Halfwidth_and_Fullwidth_Forms |
159 | blk; n/a ; Hangul_Compatibility_Jamo |
160 | blk; n/a ; Hangul_Jamo |
161 | blk; n/a ; Hangul_Syllables |
162 | blk; n/a ; Hanunoo |
163 | blk; n/a ; Hebrew |
164 | blk; n/a ; High_Private_Use_Surrogates |
165 | blk; n/a ; High_Surrogates |
166 | blk; n/a ; Hiragana |
167 | blk; n/a ; Ideographic_Description_Characters |
168 | blk; n/a ; IPA_Extensions |
169 | blk; n/a ; Kanbun |
170 | blk; n/a ; Kangxi_Radicals |
171 | blk; n/a ; Kannada |
172 | blk; n/a ; Katakana |
173 | blk; n/a ; Katakana_Phonetic_Extensions |
a2bd7410 |
174 | blk; n/a ; Kharoshthi |
1911be83 |
175 | blk; n/a ; Khmer |
176 | blk; n/a ; Khmer_Symbols |
177 | blk; n/a ; Lao |
7be0dac3 |
178 | blk; n/a ; Latin-1_Supplement |
1911be83 |
179 | blk; n/a ; Latin_Extended-A |
180 | blk; n/a ; Latin_Extended-B |
98fbe989 |
181 | blk; n/a ; Latin_Extended-C |
182 | blk; n/a ; Latin_Extended-D |
7be0dac3 |
183 | blk; n/a ; Latin_Extended_Additional |
1911be83 |
184 | blk; n/a ; Letterlike_Symbols |
185 | blk; n/a ; Limbu |
186 | blk; n/a ; Linear_B_Ideograms |
187 | blk; n/a ; Linear_B_Syllabary |
188 | blk; n/a ; Low_Surrogates |
189 | blk; n/a ; Malayalam |
190 | blk; n/a ; Mathematical_Alphanumeric_Symbols |
191 | blk; n/a ; Mathematical_Operators |
192 | blk; n/a ; Miscellaneous_Mathematical_Symbols-A |
193 | blk; n/a ; Miscellaneous_Mathematical_Symbols-B |
194 | blk; n/a ; Miscellaneous_Symbols |
195 | blk; n/a ; Miscellaneous_Symbols_and_Arrows |
196 | blk; n/a ; Miscellaneous_Technical |
a2bd7410 |
197 | blk; n/a ; Modifier_Tone_Letters |
1911be83 |
198 | blk; n/a ; Mongolian |
199 | blk; n/a ; Musical_Symbols |
200 | blk; n/a ; Myanmar |
a2bd7410 |
201 | blk; n/a ; New_Tai_Lue |
98fbe989 |
202 | blk; n/a ; NKo |
1911be83 |
203 | blk; n/a ; No_Block |
204 | blk; n/a ; Number_Forms |
205 | blk; n/a ; Ogham |
206 | blk; n/a ; Old_Italic |
a2bd7410 |
207 | blk; n/a ; Old_Persian |
1911be83 |
208 | blk; n/a ; Optical_Character_Recognition |
209 | blk; n/a ; Oriya |
210 | blk; n/a ; Osmanya |
98fbe989 |
211 | blk; n/a ; Phags-pa |
212 | blk; n/a ; Phoenician |
1911be83 |
213 | blk; n/a ; Phonetic_Extensions |
a2bd7410 |
214 | blk; n/a ; Phonetic_Extensions_Supplement |
1911be83 |
215 | blk; n/a ; Private_Use_Area |
216 | blk; n/a ; Runic |
217 | blk; n/a ; Shavian |
218 | blk; n/a ; Sinhala |
219 | blk; n/a ; Small_Form_Variants |
220 | blk; n/a ; Spacing_Modifier_Letters |
221 | blk; n/a ; Specials |
222 | blk; n/a ; Superscripts_and_Subscripts |
223 | blk; n/a ; Supplemental_Arrows-A |
224 | blk; n/a ; Supplemental_Arrows-B |
225 | blk; n/a ; Supplemental_Mathematical_Operators |
a2bd7410 |
226 | blk; n/a ; Supplemental_Punctuation |
1911be83 |
227 | blk; n/a ; Supplementary_Private_Use_Area-A |
228 | blk; n/a ; Supplementary_Private_Use_Area-B |
a2bd7410 |
229 | blk; n/a ; Syloti_Nagri |
1911be83 |
230 | blk; n/a ; Syriac |
231 | blk; n/a ; Tagalog |
232 | blk; n/a ; Tagbanwa |
233 | blk; n/a ; Tags |
234 | blk; n/a ; Tai_Le |
235 | blk; n/a ; Tai_Xuan_Jing_Symbols |
236 | blk; n/a ; Tamil |
237 | blk; n/a ; Telugu |
238 | blk; n/a ; Thaana |
239 | blk; n/a ; Thai |
240 | blk; n/a ; Tibetan |
a2bd7410 |
241 | blk; n/a ; Tifinagh |
1911be83 |
242 | blk; n/a ; Ugaritic |
243 | blk; n/a ; Unified_Canadian_Aboriginal_Syllabics |
244 | blk; n/a ; Variation_Selectors |
245 | blk; n/a ; Variation_Selectors_Supplement |
a2bd7410 |
246 | blk; n/a ; Vertical_Forms |
1911be83 |
247 | blk; n/a ; Yi_Radicals |
248 | blk; n/a ; Yi_Syllables |
249 | blk; n/a ; Yijing_Hexagram_Symbols |
250 | |
7be0dac3 |
251 | # Canonical_Combining_Class (ccc) |
252 | |
822ebcc8 |
253 | ccc; 0; NR ; Not_Reordered |
254 | ccc; 1; OV ; Overlay |
7be0dac3 |
255 | ccc; 7; NK ; Nukta |
256 | ccc; 8; KV ; Kana_Voicing |
257 | ccc; 9; VR ; Virama |
258 | ccc; 200; ATBL ; Attached_Below_Left |
1911be83 |
259 | ccc; 202; ATB ; Attached_Below |
822ebcc8 |
260 | ccc; 216; ATAR ; Attached_Above_Right |
261 | ccc; 218; BL ; Below_Left |
262 | ccc; 220; B ; Below |
263 | ccc; 222; BR ; Below_Right |
264 | ccc; 224; L ; Left |
265 | ccc; 226; R ; Right |
266 | ccc; 228; AL ; Above_Left |
267 | ccc; 230; A ; Above |
268 | ccc; 232; AR ; Above_Right |
269 | ccc; 233; DB ; Double_Below |
270 | ccc; 234; DA ; Double_Above |
271 | ccc; 240; IS ; Iota_Subscript |
822ebcc8 |
272 | |
7be0dac3 |
273 | # Decomposition_Type (dt) |
274 | |
275 | dt ; can ; Canonical |
276 | dt ; com ; Compat |
277 | dt ; enc ; Circle |
278 | dt ; fin ; Final |
279 | dt ; font ; Font |
280 | dt ; fra ; Fraction |
281 | dt ; init ; Initial |
282 | dt ; iso ; Isolated |
283 | dt ; med ; Medial |
284 | dt ; nar ; Narrow |
285 | dt ; nb ; Nobreak |
286 | dt ; none ; None |
287 | dt ; sml ; Small |
288 | dt ; sqr ; Square |
289 | dt ; sub ; Sub |
290 | dt ; sup ; Super |
291 | dt ; vert ; Vertical |
292 | dt ; wide ; Wide |
293 | |
294 | # East_Asian_Width (ea) |
822ebcc8 |
295 | |
296 | ea ; A ; Ambiguous |
297 | ea ; F ; Fullwidth |
298 | ea ; H ; Halfwidth |
299 | ea ; N ; Neutral |
300 | ea ; Na ; Narrow |
301 | ea ; W ; Wide |
302 | |
7be0dac3 |
303 | # General_Category (gc) |
304 | |
822ebcc8 |
305 | gc ; C ; Other # Cc | Cf | Cn | Co | Cs |
a2bd7410 |
306 | gc ; Cc ; Control ; cntrl |
822ebcc8 |
307 | gc ; Cf ; Format |
308 | gc ; Cn ; Unassigned |
309 | gc ; Co ; Private_Use |
310 | gc ; Cs ; Surrogate |
311 | gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu |
312 | gc ; LC ; Cased_Letter # Ll | Lt | Lu |
313 | gc ; Ll ; Lowercase_Letter |
314 | gc ; Lm ; Modifier_Letter |
315 | gc ; Lo ; Other_Letter |
316 | gc ; Lt ; Titlecase_Letter |
317 | gc ; Lu ; Uppercase_Letter |
318 | gc ; M ; Mark # Mc | Me | Mn |
319 | gc ; Mc ; Spacing_Mark |
320 | gc ; Me ; Enclosing_Mark |
321 | gc ; Mn ; Nonspacing_Mark |
322 | gc ; N ; Number # Nd | Nl | No |
a2bd7410 |
323 | gc ; Nd ; Decimal_Number ; digit |
822ebcc8 |
324 | gc ; Nl ; Letter_Number |
325 | gc ; No ; Other_Number |
a2bd7410 |
326 | gc ; P ; Punctuation ; punct # Pc | Pd | Pe | Pf | Pi | Po | Ps |
822ebcc8 |
327 | gc ; Pc ; Connector_Punctuation |
328 | gc ; Pd ; Dash_Punctuation |
329 | gc ; Pe ; Close_Punctuation |
330 | gc ; Pf ; Final_Punctuation |
331 | gc ; Pi ; Initial_Punctuation |
332 | gc ; Po ; Other_Punctuation |
333 | gc ; Ps ; Open_Punctuation |
334 | gc ; S ; Symbol # Sc | Sk | Sm | So |
335 | gc ; Sc ; Currency_Symbol |
336 | gc ; Sk ; Modifier_Symbol |
337 | gc ; Sm ; Math_Symbol |
338 | gc ; So ; Other_Symbol |
339 | gc ; Z ; Separator # Zl | Zp | Zs |
340 | gc ; Zl ; Line_Separator |
341 | gc ; Zp ; Paragraph_Separator |
342 | gc ; Zs ; Space_Separator |
343 | |
a2bd7410 |
344 | # Grapheme_Cluster_Break (GCB) |
345 | |
346 | GCB; CN ; Control |
347 | GCB; CR ; CR |
348 | GCB; EX ; Extend |
349 | GCB; L ; L |
350 | GCB; LF ; LF |
351 | GCB; LV ; LV |
352 | GCB; LVT ; LVT |
353 | GCB; T ; T |
354 | GCB; V ; V |
355 | GCB; XX ; Other |
356 | |
7be0dac3 |
357 | # Hangul_Syllable_Type (hst) |
358 | |
1911be83 |
359 | hst; L ; Leading_Jamo |
360 | hst; LV ; LV_Syllable |
361 | hst; LVT ; LVT_Syllable |
362 | hst; NA ; Not_Applicable |
363 | hst; T ; Trailing_Jamo |
364 | hst; V ; Vowel_Jamo |
365 | |
7be0dac3 |
366 | # Joining_Group (jg) |
367 | |
368 | jg ; n/a ; Ain |
369 | jg ; n/a ; Alaph |
370 | jg ; n/a ; Alef |
371 | jg ; n/a ; Beh |
372 | jg ; n/a ; Beth |
373 | jg ; n/a ; Dal |
374 | jg ; n/a ; Dalath_Rish |
822ebcc8 |
375 | jg ; n/a ; E |
7be0dac3 |
376 | jg ; n/a ; Fe |
377 | jg ; n/a ; Feh |
378 | jg ; n/a ; Final_Semkath |
379 | jg ; n/a ; Gaf |
380 | jg ; n/a ; Gamal |
381 | jg ; n/a ; Hah |
382 | jg ; n/a ; Hamza_On_Heh_Goal |
383 | jg ; n/a ; He |
384 | jg ; n/a ; Heh |
385 | jg ; n/a ; Heh_Goal |
386 | jg ; n/a ; Heth |
387 | jg ; n/a ; Kaf |
388 | jg ; n/a ; Kaph |
389 | jg ; n/a ; Khaph |
390 | jg ; n/a ; Knotted_Heh |
391 | jg ; n/a ; Lam |
392 | jg ; n/a ; Lamadh |
393 | jg ; n/a ; Meem |
394 | jg ; n/a ; Mim |
395 | jg ; n/a ; No_Joining_Group |
396 | jg ; n/a ; Noon |
397 | jg ; n/a ; Nun |
398 | jg ; n/a ; Pe |
399 | jg ; n/a ; Qaf |
400 | jg ; n/a ; Qaph |
401 | jg ; n/a ; Reh |
402 | jg ; n/a ; Reversed_Pe |
403 | jg ; n/a ; Sad |
404 | jg ; n/a ; Sadhe |
405 | jg ; n/a ; Seen |
406 | jg ; n/a ; Semkath |
407 | jg ; n/a ; Shin |
408 | jg ; n/a ; Swash_Kaf |
409 | jg ; n/a ; Syriac_Waw |
410 | jg ; n/a ; Tah |
411 | jg ; n/a ; Taw |
412 | jg ; n/a ; Teh_Marbuta |
413 | jg ; n/a ; Teth |
414 | jg ; n/a ; Waw |
415 | jg ; n/a ; Yeh |
416 | jg ; n/a ; Yeh_Barree |
417 | jg ; n/a ; Yeh_With_Tail |
418 | jg ; n/a ; Yudh |
419 | jg ; n/a ; Yudh_He |
420 | jg ; n/a ; Zain |
421 | jg ; n/a ; Zhain |
422 | |
423 | # Joining_Type (jt) |
822ebcc8 |
424 | |
425 | jt ; C ; Join_Causing |
426 | jt ; D ; Dual_Joining |
427 | jt ; L ; Left_Joining |
428 | jt ; R ; Right_Joining |
429 | jt ; T ; Transparent |
430 | jt ; U ; Non_Joining |
431 | |
7be0dac3 |
432 | # Line_Break (lb) |
433 | |
822ebcc8 |
434 | lb ; AI ; Ambiguous |
435 | lb ; AL ; Alphabetic |
436 | lb ; B2 ; Break_Both |
437 | lb ; BA ; Break_After |
438 | lb ; BB ; Break_Before |
439 | lb ; BK ; Mandatory_Break |
440 | lb ; CB ; Contingent_Break |
441 | lb ; CL ; Close_Punctuation |
442 | lb ; CM ; Combining_Mark |
443 | lb ; CR ; Carriage_Return |
444 | lb ; EX ; Exclamation |
445 | lb ; GL ; Glue |
a2bd7410 |
446 | lb ; H2 ; H2 |
447 | lb ; H3 ; H3 |
822ebcc8 |
448 | lb ; HY ; Hyphen |
449 | lb ; ID ; Ideographic |
7be0dac3 |
450 | lb ; IN ; Inseparable ; Inseperable |
822ebcc8 |
451 | lb ; IS ; Infix_Numeric |
a2bd7410 |
452 | lb ; JL ; JL |
453 | lb ; JT ; JT |
454 | lb ; JV ; JV |
822ebcc8 |
455 | lb ; LF ; Line_Feed |
1911be83 |
456 | lb ; NL ; Next_Line |
822ebcc8 |
457 | lb ; NS ; Nonstarter |
458 | lb ; NU ; Numeric |
459 | lb ; OP ; Open_Punctuation |
460 | lb ; PO ; Postfix_Numeric |
461 | lb ; PR ; Prefix_Numeric |
462 | lb ; QU ; Quotation |
463 | lb ; SA ; Complex_Context |
464 | lb ; SG ; Surrogate |
465 | lb ; SP ; Space |
466 | lb ; SY ; Break_Symbols |
1911be83 |
467 | lb ; WJ ; Word_Joiner |
822ebcc8 |
468 | lb ; XX ; Unknown |
469 | lb ; ZW ; ZWSpace |
470 | |
7be0dac3 |
471 | # NFC_Quick_Check (NFC_QC) |
472 | |
473 | NFC_QC; M ; Maybe |
474 | NFC_QC; N ; No |
475 | NFC_QC; Y ; Yes |
476 | |
477 | # NFD_Quick_Check (NFD_QC) |
478 | |
479 | NFD_QC; N ; No |
480 | NFD_QC; Y ; Yes |
481 | |
482 | # NFKC_Quick_Check (NFKC_QC) |
483 | |
484 | NFKC_QC; M ; Maybe |
485 | NFKC_QC; N ; No |
486 | NFKC_QC; Y ; Yes |
487 | |
488 | # NFKD_Quick_Check (NFKD_QC) |
489 | |
490 | NFKD_QC; N ; No |
491 | NFKD_QC; Y ; Yes |
492 | |
493 | # Numeric_Type (nt) |
494 | |
495 | nt ; De ; Decimal |
496 | nt ; Di ; Digit |
497 | nt ; None ; None |
498 | nt ; Nu ; Numeric |
822ebcc8 |
499 | |
7be0dac3 |
500 | # Script (sc) |
822ebcc8 |
501 | |
502 | sc ; Arab ; Arabic |
503 | sc ; Armn ; Armenian |
98fbe989 |
504 | sc ; Bali ; Balinese |
822ebcc8 |
505 | sc ; Beng ; Bengali |
506 | sc ; Bopo ; Bopomofo |
1911be83 |
507 | sc ; Brai ; Braille |
a2bd7410 |
508 | sc ; Bugi ; Buginese |
822ebcc8 |
509 | sc ; Buhd ; Buhid |
510 | sc ; Cans ; Canadian_Aboriginal |
511 | sc ; Cher ; Cherokee |
a2bd7410 |
512 | sc ; Copt ; Coptic ; Qaac |
1911be83 |
513 | sc ; Cprt ; Cypriot |
822ebcc8 |
514 | sc ; Cyrl ; Cyrillic |
515 | sc ; Deva ; Devanagari |
516 | sc ; Dsrt ; Deseret |
517 | sc ; Ethi ; Ethiopic |
518 | sc ; Geor ; Georgian |
a2bd7410 |
519 | sc ; Glag ; Glagolitic |
822ebcc8 |
520 | sc ; Goth ; Gothic |
521 | sc ; Grek ; Greek |
522 | sc ; Gujr ; Gujarati |
523 | sc ; Guru ; Gurmukhi |
524 | sc ; Hang ; Hangul |
525 | sc ; Hani ; Han |
526 | sc ; Hano ; Hanunoo |
527 | sc ; Hebr ; Hebrew |
528 | sc ; Hira ; Hiragana |
7be0dac3 |
529 | sc ; Hrkt ; Katakana_Or_Hiragana |
822ebcc8 |
530 | sc ; Ital ; Old_Italic |
531 | sc ; Kana ; Katakana |
a2bd7410 |
532 | sc ; Khar ; Kharoshthi |
822ebcc8 |
533 | sc ; Khmr ; Khmer |
534 | sc ; Knda ; Kannada |
535 | sc ; Laoo ; Lao |
536 | sc ; Latn ; Latin |
1911be83 |
537 | sc ; Limb ; Limbu |
538 | sc ; Linb ; Linear_B |
822ebcc8 |
539 | sc ; Mlym ; Malayalam |
540 | sc ; Mong ; Mongolian |
541 | sc ; Mymr ; Myanmar |
98fbe989 |
542 | sc ; Nkoo ; Nko |
822ebcc8 |
543 | sc ; Ogam ; Ogham |
544 | sc ; Orya ; Oriya |
1911be83 |
545 | sc ; Osma ; Osmanya |
98fbe989 |
546 | sc ; Phag ; Phags_Pa |
547 | sc ; Phnx ; Phoenician |
822ebcc8 |
548 | sc ; Qaai ; Inherited |
549 | sc ; Runr ; Runic |
1911be83 |
550 | sc ; Shaw ; Shavian |
822ebcc8 |
551 | sc ; Sinh ; Sinhala |
a2bd7410 |
552 | sc ; Sylo ; Syloti_Nagri |
822ebcc8 |
553 | sc ; Syrc ; Syriac |
554 | sc ; Tagb ; Tagbanwa |
1911be83 |
555 | sc ; Tale ; Tai_Le |
a2bd7410 |
556 | sc ; Talu ; New_Tai_Lue |
822ebcc8 |
557 | sc ; Taml ; Tamil |
558 | sc ; Telu ; Telugu |
a2bd7410 |
559 | sc ; Tfng ; Tifinagh |
822ebcc8 |
560 | sc ; Tglg ; Tagalog |
561 | sc ; Thaa ; Thaana |
562 | sc ; Thai ; Thai |
563 | sc ; Tibt ; Tibetan |
1911be83 |
564 | sc ; Ugar ; Ugaritic |
a2bd7410 |
565 | sc ; Xpeo ; Old_Persian |
98fbe989 |
566 | sc ; Xsux ; Cuneiform |
822ebcc8 |
567 | sc ; Yiii ; Yi |
568 | sc ; Zyyy ; Common |
98fbe989 |
569 | sc ; Zzzz ; Unknown |
a2bd7410 |
570 | |
571 | # Sentence_Break (SB) |
572 | |
573 | SB ; AT ; ATerm |
574 | SB ; CL ; Close |
575 | SB ; FO ; Format |
576 | SB ; LE ; OLetter |
577 | SB ; LO ; Lower |
578 | SB ; NU ; Numeric |
579 | SB ; SE ; Sep |
580 | SB ; SP ; Sp |
581 | SB ; ST ; STerm |
582 | SB ; UP ; Upper |
583 | SB ; XX ; Other |
584 | |
585 | # Word_Break (WB) |
586 | |
587 | WB ; EX ; ExtendNumLet |
588 | WB ; FO ; Format |
589 | WB ; KA ; Katakana |
590 | WB ; LE ; ALetter |
591 | WB ; ML ; MidLetter |
592 | WB ; MN ; MidNum |
593 | WB ; NU ; Numeric |
594 | WB ; XX ; Other |
98fbe989 |
595 | |
596 | # EOF |