Commit | Line | Data |
---|---|---|
86530b38 AT |
1 | # PropertyValueAliases-3.2.0.txt |
2 | # Date: 2002-03-19,23:31:21 GMT [MD] | |
3 | # | |
4 | # This file contains aliases for property values used in the UCD. | |
5 | # These names can be used for XML formats of UCD data, for regular-expression | |
6 | # property tests, and other programmatic textual descriptions of Unicode data. | |
7 | # The names are not normative, except where they correspond to normative property | |
8 | # values in the UCD. For information on which properties are normative, see | |
9 | # UnicodeCharacterDatabase.html. | |
10 | # | |
11 | # The names may be translated in appropriate environments, and additional | |
12 | # aliases may be useful. | |
13 | # | |
14 | # FORMAT | |
15 | # | |
16 | # Each line describes a property value name. | |
17 | # This consists of three fields, separated by semicolons. | |
18 | # | |
19 | # First Field: The first field describes the property for which that | |
20 | # property value name is used. | |
21 | # There is one special pseudo-property: "qc" stands for any quick-check property | |
22 | # | |
23 | # Second Field: The second field is an abbreviated name. | |
24 | # If there is no abbreviated name available, the field is marked with "n/a". | |
25 | # | |
26 | # Third Field: The third field is a long name. | |
27 | # | |
28 | # In the case of ccc, their are 4 fields. The second field is numeric, third | |
29 | # is abbreviated, and fourth is long. | |
30 | # | |
31 | # With loose matching of property names, the case distinctions, whitespace, | |
32 | # and '_' are ignored. | |
33 | # | |
34 | # NOTE: The Block property values are in Blocks.txt, and not repeated here. | |
35 | # For more information on the use of blocks, see UTR #24: Regular Expression Guidelines | |
36 | # | |
37 | # NOTE: Currently there is at most one abbreviated name and one long name for | |
38 | # property value. However, in the future additional aliases | |
39 | # may be added. In such a case, the first line for the property value | |
40 | # would have the preferred alias for output. | |
41 | # | |
42 | # NOTE: The property value names are NOT unique across properties, especially | |
43 | # with loose matches. For example, | |
44 | # AL means Arabic Letter for the Bidi_Class property, and | |
45 | # AL means Alpha_Left for the Combining_Class property, and | |
46 | # AL means Alphabetic for the Line_Break property. | |
47 | # | |
48 | # In addition, some property names may be the same as some property value names: | |
49 | # cc means Combining_Class property, and | |
50 | # cc means the General_Category property value Control (cc) | |
51 | # | |
52 | # The combination of property value and property name is, however, unique. | |
53 | # For more information, see UTR #24: Regular Expression Guidelines | |
54 | # ================================================ | |
55 | ||
56 | ||
57 | bc ; AL ; Arabic_Letter | |
58 | bc ; AN ; Arabic_Number | |
59 | bc ; B ; Paragraph_Separator | |
60 | bc ; BN ; Boundary_Neutral | |
61 | bc ; CS ; Common_Separator | |
62 | bc ; EN ; European_Number | |
63 | bc ; ES ; European_Separator | |
64 | bc ; ET ; European_Terminator | |
65 | bc ; L ; Left_To_Right | |
66 | bc ; LRE ; Left_To_Right_Embedding | |
67 | bc ; LRO ; Left_To_Right_Override | |
68 | bc ; NSM ; Nonspacing_Mark | |
69 | bc ; ON ; Other_Neutral | |
70 | bc ; PDF ; Pop_Directional_Format | |
71 | bc ; R ; Right_To_Left | |
72 | bc ; RLE ; Right_To_Left_Embedding | |
73 | bc ; RLO ; Right_To_Left_Override | |
74 | bc ; S ; Segment_Separator | |
75 | bc ; WS ; White_Space | |
76 | ||
77 | ccc; 0; NR ; Not_Reordered | |
78 | ccc; 1; OV ; Overlay | |
79 | ccc; 202; ATBL ; Attached_Below_Left | |
80 | ccc; 216; ATAR ; Attached_Above_Right | |
81 | ccc; 218; BL ; Below_Left | |
82 | ccc; 220; B ; Below | |
83 | ccc; 222; BR ; Below_Right | |
84 | ccc; 224; L ; Left | |
85 | ccc; 226; R ; Right | |
86 | ccc; 228; AL ; Above_Left | |
87 | ccc; 230; A ; Above | |
88 | ccc; 232; AR ; Above_Right | |
89 | ccc; 233; DB ; Double_Below | |
90 | ccc; 234; DA ; Double_Above | |
91 | ccc; 240; IS ; Iota_Subscript | |
92 | ccc; 7; NK ; Nukta | |
93 | ccc; 8; KV ; Kana_Voicing | |
94 | ccc; 9; VR ; Virama | |
95 | ||
96 | dt ; can ; canonical | |
97 | dt ; com ; compat | |
98 | dt ; enc ; circle | |
99 | dt ; fin ; final | |
100 | dt ; font ; font | |
101 | dt ; fra ; fraction | |
102 | dt ; init ; initial | |
103 | dt ; iso ; isolated | |
104 | dt ; med ; medial | |
105 | dt ; n/a ; none | |
106 | dt ; nar ; narrow | |
107 | dt ; nb ; noBreak | |
108 | dt ; sml ; small | |
109 | dt ; sqr ; square | |
110 | dt ; sub ; sub | |
111 | dt ; sup ; super | |
112 | dt ; vert ; vertical | |
113 | dt ; wide ; wide | |
114 | ||
115 | ea ; A ; Ambiguous | |
116 | ea ; F ; Fullwidth | |
117 | ea ; H ; Halfwidth | |
118 | ea ; N ; Neutral | |
119 | ea ; Na ; Narrow | |
120 | ea ; W ; Wide | |
121 | ||
122 | gc ; C ; Other # Cc | Cf | Cn | Co | Cs | |
123 | gc ; Cc ; Control | |
124 | gc ; Cf ; Format | |
125 | gc ; Cn ; Unassigned | |
126 | gc ; Co ; Private_Use | |
127 | gc ; Cs ; Surrogate | |
128 | gc ; L ; Letter # Ll | Lm | Lo | Lt | Lu | |
129 | gc ; LC ; Cased_Letter # Ll | Lt | Lu | |
130 | gc ; Ll ; Lowercase_Letter | |
131 | gc ; Lm ; Modifier_Letter | |
132 | gc ; Lo ; Other_Letter | |
133 | gc ; Lt ; Titlecase_Letter | |
134 | gc ; Lu ; Uppercase_Letter | |
135 | gc ; M ; Mark # Mc | Me | Mn | |
136 | gc ; Mc ; Spacing_Mark | |
137 | gc ; Me ; Enclosing_Mark | |
138 | gc ; Mn ; Nonspacing_Mark | |
139 | gc ; N ; Number # Nd | Nl | No | |
140 | gc ; Nd ; Decimal_Number | |
141 | gc ; Nl ; Letter_Number | |
142 | gc ; No ; Other_Number | |
143 | gc ; P ; Punctuation # Pc | Pd | Pe | Pf | Pi | Po | Ps | |
144 | gc ; Pc ; Connector_Punctuation | |
145 | gc ; Pd ; Dash_Punctuation | |
146 | gc ; Pe ; Close_Punctuation | |
147 | gc ; Pf ; Final_Punctuation | |
148 | gc ; Pi ; Initial_Punctuation | |
149 | gc ; Po ; Other_Punctuation | |
150 | gc ; Ps ; Open_Punctuation | |
151 | gc ; S ; Symbol # Sc | Sk | Sm | So | |
152 | gc ; Sc ; Currency_Symbol | |
153 | gc ; Sk ; Modifier_Symbol | |
154 | gc ; Sm ; Math_Symbol | |
155 | gc ; So ; Other_Symbol | |
156 | gc ; Z ; Separator # Zl | Zp | Zs | |
157 | gc ; Zl ; Line_Separator | |
158 | gc ; Zp ; Paragraph_Separator | |
159 | gc ; Zs ; Space_Separator | |
160 | ||
161 | jg ; n/a ; AIN | |
162 | jg ; n/a ; ALAPH | |
163 | jg ; n/a ; ALEF | |
164 | jg ; n/a ; BEH | |
165 | jg ; n/a ; BETH | |
166 | jg ; n/a ; DAL | |
167 | jg ; n/a ; DALATH_RISH | |
168 | jg ; n/a ; E | |
169 | jg ; n/a ; FEH | |
170 | jg ; n/a ; FINAL_SEMKATH | |
171 | jg ; n/a ; GAF | |
172 | jg ; n/a ; GAMAL | |
173 | jg ; n/a ; HAH | |
174 | jg ; n/a ; HAMZA_ON_HEH_GOAL | |
175 | jg ; n/a ; HE | |
176 | jg ; n/a ; HEH | |
177 | jg ; n/a ; HEH_GOAL | |
178 | jg ; n/a ; HETH | |
179 | jg ; n/a ; KAF | |
180 | jg ; n/a ; KAPH | |
181 | jg ; n/a ; KNOTTED_HEH | |
182 | jg ; n/a ; LAM | |
183 | jg ; n/a ; LAMADH | |
184 | jg ; n/a ; MEEM | |
185 | jg ; n/a ; MIM | |
186 | jg ; n/a ; NO_JOINING_GROUP | |
187 | jg ; n/a ; NOON | |
188 | jg ; n/a ; NUN | |
189 | jg ; n/a ; PE | |
190 | jg ; n/a ; QAF | |
191 | jg ; n/a ; QAPH | |
192 | jg ; n/a ; REH | |
193 | jg ; n/a ; REVERSED_PE | |
194 | jg ; n/a ; SAD | |
195 | jg ; n/a ; SADHE | |
196 | jg ; n/a ; SEEN | |
197 | jg ; n/a ; SEMKATH | |
198 | jg ; n/a ; SHIN | |
199 | jg ; n/a ; SWASH_KAF | |
200 | jg ; n/a ; SYRIAC_WAW | |
201 | jg ; n/a ; TAH | |
202 | jg ; n/a ; TAW | |
203 | jg ; n/a ; TEH_MARBUTA | |
204 | jg ; n/a ; TETH | |
205 | jg ; n/a ; WAW | |
206 | jg ; n/a ; YEH | |
207 | jg ; n/a ; YEH_BARREE | |
208 | jg ; n/a ; YEH_WITH_TAIL | |
209 | jg ; n/a ; YUDH | |
210 | jg ; n/a ; YUDH_HE | |
211 | jg ; n/a ; ZAIN | |
212 | ||
213 | jt ; C ; Join_Causing | |
214 | jt ; D ; Dual_Joining | |
215 | jt ; L ; Left_Joining | |
216 | jt ; R ; Right_Joining | |
217 | jt ; T ; Transparent | |
218 | jt ; U ; Non_Joining | |
219 | ||
220 | lb ; AI ; Ambiguous | |
221 | lb ; AL ; Alphabetic | |
222 | lb ; B2 ; Break_Both | |
223 | lb ; BA ; Break_After | |
224 | lb ; BB ; Break_Before | |
225 | lb ; BK ; Mandatory_Break | |
226 | lb ; CB ; Contingent_Break | |
227 | lb ; CL ; Close_Punctuation | |
228 | lb ; CM ; Combining_Mark | |
229 | lb ; CR ; Carriage_Return | |
230 | lb ; EX ; Exclamation | |
231 | lb ; GL ; Glue | |
232 | lb ; HY ; Hyphen | |
233 | lb ; ID ; Ideographic | |
234 | lb ; IN ; Inseperable | |
235 | lb ; IS ; Infix_Numeric | |
236 | lb ; LF ; Line_Feed | |
237 | lb ; NS ; Nonstarter | |
238 | lb ; NU ; Numeric | |
239 | lb ; OP ; Open_Punctuation | |
240 | lb ; PO ; Postfix_Numeric | |
241 | lb ; PR ; Prefix_Numeric | |
242 | lb ; QU ; Quotation | |
243 | lb ; SA ; Complex_Context | |
244 | lb ; SG ; Surrogate | |
245 | lb ; SP ; Space | |
246 | lb ; SY ; Break_Symbols | |
247 | lb ; XX ; Unknown | |
248 | lb ; ZW ; ZWSpace | |
249 | ||
250 | nt ; de ; Decimal | |
251 | nt ; di ; Digit | |
252 | nt ; n/a ; None | |
253 | nt ; nu ; Numeric | |
254 | ||
255 | qc ; M ; Maybe | |
256 | qc ; N ; No | |
257 | qc ; Y ; Yes | |
258 | ||
259 | sc ; Arab ; Arabic | |
260 | sc ; Armn ; Armenian | |
261 | sc ; Beng ; Bengali | |
262 | sc ; Bopo ; Bopomofo | |
263 | sc ; Buhd ; Buhid | |
264 | sc ; Cans ; Canadian_Aboriginal | |
265 | sc ; Cher ; Cherokee | |
266 | sc ; Cyrl ; Cyrillic | |
267 | sc ; Deva ; Devanagari | |
268 | sc ; Dsrt ; Deseret | |
269 | sc ; Ethi ; Ethiopic | |
270 | sc ; Geor ; Georgian | |
271 | sc ; Goth ; Gothic | |
272 | sc ; Grek ; Greek | |
273 | sc ; Gujr ; Gujarati | |
274 | sc ; Guru ; Gurmukhi | |
275 | sc ; Hang ; Hangul | |
276 | sc ; Hani ; Han | |
277 | sc ; Hano ; Hanunoo | |
278 | sc ; Hebr ; Hebrew | |
279 | sc ; Hira ; Hiragana | |
280 | sc ; Ital ; Old_Italic | |
281 | sc ; Kana ; Katakana | |
282 | sc ; Khmr ; Khmer | |
283 | sc ; Knda ; Kannada | |
284 | sc ; Laoo ; Lao | |
285 | sc ; Latn ; Latin | |
286 | sc ; Mlym ; Malayalam | |
287 | sc ; Mong ; Mongolian | |
288 | sc ; Mymr ; Myanmar | |
289 | sc ; Ogam ; Ogham | |
290 | sc ; Orya ; Oriya | |
291 | sc ; Qaai ; Inherited | |
292 | sc ; Runr ; Runic | |
293 | sc ; Sinh ; Sinhala | |
294 | sc ; Syrc ; Syriac | |
295 | sc ; Tagb ; Tagbanwa | |
296 | sc ; Taml ; Tamil | |
297 | sc ; Telu ; Telugu | |
298 | sc ; Tglg ; Tagalog | |
299 | sc ; Thaa ; Thaana | |
300 | sc ; Thai ; Thai | |
301 | sc ; Tibt ; Tibetan | |
302 | sc ; Yiii ; Yi | |
303 | sc ; Zyyy ; Common |