1 # PropertyValueAliases-11.0.0.txt
2 # Date: 2018-05-20, 09:03:12 GMT
3 # Copyright (c) 2018 Unicode, Inc.
4 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
5 # For terms of use, see http://www.unicode.org/terms_of_use.html
6 #
7 # Unicode Character Database
8 # For documentation, see http://www.unicode.org/reports/tr44/
9 #
10 # This file contains aliases for property values used in the UCD.
11 # These names can be used for XML formats of UCD data, for regular-expression
12 # property tests, and other programmatic textual descriptions of Unicode data.
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.
20 # This consists of three or more fields, separated by semicolons.
21 #
22 # First Field: The first field describes the property for which that
23 # property value name is used.
24 #
25 # Second Field: The second field is an abbreviated name.
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, hyphens, and '_' are ignored.
37 # For Numeric Property values, numeric equivalence is applied: thus "01.00"
38 # is equivalent to "1".
39 #
40 # NOTE: Property value names are NOT unique across properties. For example:
41 #
42 # AL means Arabic Letter for the Bidi_Class property, and
43 # AL means Above_Left for the Canonical_Combining_Class property, and
44 # AL means Alphabetic for the Line_Break property.
45 #
46 # In addition, some property names may be the same as some property value names.
47 # For example:
48 #
49 # sc means the Script property, and
50 # Sc means the General_Category property value Currency_Symbol (Sc)
51 #
52 # The combination of property value and property name is, however, unique.
53 #
54 # For more information, see UTS #18: Unicode Regular Expressions
55 # ================================================
56
57
58 # ASCII_Hex_Digit (AHex)
59
60 AHex; N ; No ; F ; False
61 AHex; Y ; Yes ; T ; True
62
63 # Age (age)
64
65 age; 1.1 ; V1_1
66 age; 2.0 ; V2_0
67 age; 2.1 ; V2_1
68 age; 3.0 ; V3_0
69 age; 3.1 ; V3_1
70 age; 3.2 ; V3_2
71 age; 4.0 ; V4_0
72 age; 4.1 ; V4_1
73 age; 5.0 ; V5_0
74 age; 5.1 ; V5_1
75 age; 5.2 ; V5_2
76 age; 6.0 ; V6_0
77 age; 6.1 ; V6_1
78 age; 6.2 ; V6_2
79 age; 6.3 ; V6_3
80 age; 7.0 ; V7_0
81 age; 8.0 ; V8_0
82 age; 9.0 ; V9_0
83 age; 10.0 ; V10_0
84 age; 11.0 ; V11_0
85 age; NA ; Unassigned
86
87 # Alphabetic (Alpha)
88
89 Alpha; N ; No ; F ; False
90 Alpha; Y ; Yes ; T ; True
91
92 # Bidi_Class (bc)
93
94 bc ; AL ; Arabic_Letter
95 bc ; AN ; Arabic_Number
96 bc ; B ; Paragraph_Separator
97 bc ; BN ; Boundary_Neutral
98 bc ; CS ; Common_Separator
99 bc ; EN ; European_Number
100 bc ; ES ; European_Separator
101 bc ; ET ; European_Terminator
102 bc ; FSI ; First_Strong_Isolate
103 bc ; L ; Left_To_Right
104 bc ; LRE ; Left_To_Right_Embedding
207 blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation
208 blk; Currency_Symbols ; Currency_Symbols
209 blk; Cypriot_Syllabary ; Cypriot_Syllabary
210 blk; Cyrillic ; Cyrillic
211 blk; Cyrillic_Ext_A ; Cyrillic_Extended_A
212 blk; Cyrillic_Ext_B ; Cyrillic_Extended_B
213 blk; Cyrillic_Ext_C ; Cyrillic_Extended_C
214 blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary
215 blk; Deseret ; Deseret
216 blk; Devanagari ; Devanagari
217 blk; Devanagari_Ext ; Devanagari_Extended
218 blk; Diacriticals ; Combining_Diacritical_Marks
219 blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended
220 blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
221 blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
222 blk; Dingbats ; Dingbats
223 blk; Dogra ; Dogra
224 blk; Domino ; Domino_Tiles
225 blk; Duployan ; Duployan
226 blk; Early_Dynastic_Cuneiform ; Early_Dynastic_Cuneiform
227 blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
228 blk; Elbasan ; Elbasan
229 blk; Emoticons ; Emoticons
230 blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
231 blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
232 blk; Enclosed_CJK ; Enclosed_CJK_Letters_And_Months
233 blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement
234 blk; Ethiopic ; Ethiopic
235 blk; Ethiopic_Ext ; Ethiopic_Extended
236 blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
237 blk; Ethiopic_Sup ; Ethiopic_Supplement
238 blk; Geometric_Shapes ; Geometric_Shapes
239 blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended
240 blk; Georgian ; Georgian
241 blk; Georgian_Ext ; Georgian_Extended
242 blk; Georgian_Sup ; Georgian_Supplement
243 blk; Glagolitic ; Glagolitic
244 blk; Glagolitic_Sup ; Glagolitic_Supplement
245 blk; Gothic ; Gothic
246 blk; Grantha ; Grantha
247 blk; Greek ; Greek_And_Coptic
248 blk; Greek_Ext ; Greek_Extended
322 blk; Meroitic_Hieroglyphs ; Meroitic_Hieroglyphs
323 blk; Miao ; Miao
324 blk; Misc_Arrows ; Miscellaneous_Symbols_And_Arrows
325 blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A
326 blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B
327 blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs
328 blk; Misc_Symbols ; Miscellaneous_Symbols
329 blk; Misc_Technical ; Miscellaneous_Technical
330 blk; Modi ; Modi
331 blk; Modifier_Letters ; Spacing_Modifier_Letters
332 blk; Modifier_Tone_Letters ; Modifier_Tone_Letters
333 blk; Mongolian ; Mongolian
334 blk; Mongolian_Sup ; Mongolian_Supplement
335 blk; Mro ; Mro
336 blk; Multani ; Multani
337 blk; Music ; Musical_Symbols
338 blk; Myanmar ; Myanmar
339 blk; Myanmar_Ext_A ; Myanmar_Extended_A
340 blk; Myanmar_Ext_B ; Myanmar_Extended_B
341 blk; Nabataean ; Nabataean
342 blk; NB ; No_Block
343 blk; New_Tai_Lue ; New_Tai_Lue
344 blk; Newa ; Newa
345 blk; NKo ; NKo
346 blk; Number_Forms ; Number_Forms
347 blk; Nushu ; Nushu
348 blk; OCR ; Optical_Character_Recognition
349 blk; Ogham ; Ogham
350 blk; Ol_Chiki ; Ol_Chiki
351 blk; Old_Hungarian ; Old_Hungarian
352 blk; Old_Italic ; Old_Italic
353 blk; Old_North_Arabian ; Old_North_Arabian
354 blk; Old_Permic ; Old_Permic
355 blk; Old_Persian ; Old_Persian
356 blk; Old_Sogdian ; Old_Sogdian
357 blk; Old_South_Arabian ; Old_South_Arabian
358 blk; Old_Turkic ; Old_Turkic
359 blk; Oriya ; Oriya
360 blk; Ornamental_Dingbats ; Ornamental_Dingbats
361 blk; Osage ; Osage
362 blk; Osmanya ; Osmanya
363 blk; Pahawh_Hmong ; Pahawh_Hmong
364 blk; Palmyrene ; Palmyrene
365 blk; Pau_Cin_Hau ; Pau_Cin_Hau
366 blk; Phags_Pa ; Phags_Pa
367 blk; Phaistos ; Phaistos_Disc
368 blk; Phoenician ; Phoenician
369 blk; Phonetic_Ext ; Phonetic_Extensions
370 blk; Phonetic_Ext_Sup ; Phonetic_Extensions_Supplement
371 blk; Playing_Cards ; Playing_Cards
372 blk; Psalter_Pahlavi ; Psalter_Pahlavi
373 blk; PUA ; Private_Use_Area ; Private_Use
374 blk; Punctuation ; General_Punctuation
375 blk; Rejang ; Rejang
376 blk; Rumi ; Rumi_Numeral_Symbols
377 blk; Runic ; Runic
378 blk; Samaritan ; Samaritan
379 blk; Saurashtra ; Saurashtra
380 blk; Sharada ; Sharada
381 blk; Shavian ; Shavian
382 blk; Shorthand_Format_Controls ; Shorthand_Format_Controls
383 blk; Siddham ; Siddham
384 blk; Sinhala ; Sinhala
385 blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers
386 blk; Small_Forms ; Small_Form_Variants
387 blk; Sogdian ; Sogdian
388 blk; Sora_Sompeng ; Sora_Sompeng
389 blk; Soyombo ; Soyombo
390 blk; Specials ; Specials
391 blk; Sundanese ; Sundanese
392 blk; Sundanese_Sup ; Sundanese_Supplement
393 blk; Sup_Arrows_A ; Supplemental_Arrows_A
394 blk; Sup_Arrows_B ; Supplemental_Arrows_B
395 blk; Sup_Arrows_C ; Supplemental_Arrows_C
396 blk; Sup_Math_Operators ; Supplemental_Mathematical_Operators
397 blk; Sup_PUA_A ; Supplementary_Private_Use_Area_A
398 blk; Sup_PUA_B ; Supplementary_Private_Use_Area_B
399 blk; Sup_Punctuation ; Supplemental_Punctuation
400 blk; Sup_Symbols_And_Pictographs ; Supplemental_Symbols_And_Pictographs
401 blk; Super_And_Sub ; Superscripts_And_Subscripts
402 blk; Sutton_SignWriting ; Sutton_SignWriting
403 blk; Syloti_Nagri ; Syloti_Nagri
404 blk; Syriac ; Syriac
405 blk; Syriac_Sup ; Syriac_Supplement
406 blk; Tagalog ; Tagalog
407 blk; Tagbanwa ; Tagbanwa
408 blk; Tags ; Tags
409 blk; Tai_Le ; Tai_Le
410 blk; Tai_Tham ; Tai_Tham
411 blk; Tai_Viet ; Tai_Viet
412 blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
413 blk; Takri ; Takri
414 blk; Tamil ; Tamil
415 blk; Tangut ; Tangut
416 blk; Tangut_Components ; Tangut_Components
417 blk; Telugu ; Telugu
418 blk; Thaana ; Thaana
419 blk; Thai ; Thai
420 blk; Tibetan ; Tibetan
421 blk; Tifinagh ; Tifinagh
422 blk; Tirhuta ; Tirhuta
423 blk; Transport_And_Map ; Transport_And_Map_Symbols
424 blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
425 blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
426 blk; Ugaritic ; Ugaritic
427 blk; Vai ; Vai
428 blk; Vedic_Ext ; Vedic_Extensions
429 blk; Vertical_Forms ; Vertical_Forms
430 blk; VS ; Variation_Selectors
431 blk; VS_Sup ; Variation_Selectors_Supplement
432 blk; Warang_Citi ; Warang_Citi
433 blk; Yi_Radicals ; Yi_Radicals
434 blk; Yi_Syllables ; Yi_Syllables
435 blk; Yijing ; Yijing_Hexagram_Symbols
436 blk; Zanabazar_Square ; Zanabazar_Square
437
438 # Canonical_Combining_Class (ccc)
439
440 ccc; 0; NR ; Not_Reordered
441 ccc; 1; OV ; Overlay
442 ccc; 7; NK ; Nukta
443 ccc; 8; KV ; Kana_Voicing
444 ccc; 9; VR ; Virama
445 ccc; 10; CCC10 ; CCC10
446 ccc; 11; CCC11 ; CCC11
447 ccc; 12; CCC12 ; CCC12
448 ccc; 13; CCC13 ; CCC13
449 ccc; 14; CCC14 ; CCC14
450 ccc; 15; CCC15 ; CCC15
451 ccc; 16; CCC16 ; CCC16
1196 sc ; Bhks ; Bhaiksuki
1197 sc ; Bopo ; Bopomofo
1198 sc ; Brah ; Brahmi
1199 sc ; Brai ; Braille
1200 sc ; Bugi ; Buginese
1201 sc ; Buhd ; Buhid
1202 sc ; Cakm ; Chakma
1203 sc ; Cans ; Canadian_Aboriginal
1204 sc ; Cari ; Carian
1205 sc ; Cham ; Cham
1206 sc ; Cher ; Cherokee
1207 sc ; Copt ; Coptic ; Qaac
1208 sc ; Cprt ; Cypriot
1209 sc ; Cyrl ; Cyrillic
1210 sc ; Deva ; Devanagari
1211 sc ; Dogr ; Dogra
1212 sc ; Dsrt ; Deseret
1213 sc ; Dupl ; Duployan
1214 sc ; Egyp ; Egyptian_Hieroglyphs
1215 sc ; Elba ; Elbasan
1216 sc ; Ethi ; Ethiopic
1217 sc ; Geor ; Georgian
1218 sc ; Glag ; Glagolitic
1219 sc ; Gong ; Gunjala_Gondi
1220 sc ; Gonm ; Masaram_Gondi
1221 sc ; Goth ; Gothic
1222 sc ; Gran ; Grantha
1223 sc ; Grek ; Greek
1224 sc ; Gujr ; Gujarati
1225 sc ; Guru ; Gurmukhi
1226 sc ; Hang ; Hangul
1227 sc ; Hani ; Han
1228 sc ; Hano ; Hanunoo
1229 sc ; Hatr ; Hatran
1230 sc ; Hebr ; Hebrew
1231 sc ; Hira ; Hiragana
1232 sc ; Hluw ; Anatolian_Hieroglyphs
1233 sc ; Hmng ; Pahawh_Hmong
1234 sc ; Hrkt ; Katakana_Or_Hiragana
1235 sc ; Hung ; Old_Hungarian
1236 sc ; Ital ; Old_Italic
1237 sc ; Java ; Javanese
1238 sc ; Kali ; Kayah_Li
1239 sc ; Kana ; Katakana
1240 sc ; Khar ; Kharoshthi
1241 sc ; Khmr ; Khmer
1242 sc ; Khoj ; Khojki
1243 sc ; Knda ; Kannada
1244 sc ; Kthi ; Kaithi
1245 sc ; Lana ; Tai_Tham
1246 sc ; Laoo ; Lao
1247 sc ; Latn ; Latin
1248 sc ; Lepc ; Lepcha
1249 sc ; Limb ; Limbu
1250 sc ; Lina ; Linear_A
1251 sc ; Linb ; Linear_B
1252 sc ; Lisu ; Lisu
1253 sc ; Lyci ; Lycian
1254 sc ; Lydi ; Lydian
1255 sc ; Mahj ; Mahajani
1256 sc ; Maka ; Makasar
1257 sc ; Mand ; Mandaic
1258 sc ; Mani ; Manichaean
1259 sc ; Marc ; Marchen
1260 sc ; Medf ; Medefaidrin
1261 sc ; Mend ; Mende_Kikakui
1262 sc ; Merc ; Meroitic_Cursive
1263 sc ; Mero ; Meroitic_Hieroglyphs
1264 sc ; Mlym ; Malayalam
1265 sc ; Modi ; Modi
1266 sc ; Mong ; Mongolian
1267 sc ; Mroo ; Mro
1268 sc ; Mtei ; Meetei_Mayek
1269 sc ; Mult ; Multani
1270 sc ; Mymr ; Myanmar
1271 sc ; Narb ; Old_North_Arabian
1272 sc ; Nbat ; Nabataean
1273 sc ; Newa ; Newa
1274 sc ; Nkoo ; Nko
1275 sc ; Nshu ; Nushu
1276 sc ; Ogam ; Ogham
1277 sc ; Olck ; Ol_Chiki
1278 sc ; Orkh ; Old_Turkic
1279 sc ; Orya ; Oriya
1280 sc ; Osge ; Osage
1281 sc ; Osma ; Osmanya
1282 sc ; Palm ; Palmyrene
1283 sc ; Pauc ; Pau_Cin_Hau
1284 sc ; Perm ; Old_Permic
1285 sc ; Phag ; Phags_Pa
1286 sc ; Phli ; Inscriptional_Pahlavi
1287 sc ; Phlp ; Psalter_Pahlavi
1288 sc ; Phnx ; Phoenician
1289 sc ; Plrd ; Miao
1290 sc ; Prti ; Inscriptional_Parthian
1307 sc ; Sund ; Sundanese
1308 sc ; Sylo ; Syloti_Nagri
1309 sc ; Syrc ; Syriac
1310 sc ; Tagb ; Tagbanwa
1311 sc ; Takr ; Takri
1312 sc ; Tale ; Tai_Le
1313 sc ; Talu ; New_Tai_Lue
1314 sc ; Taml ; Tamil
1315 sc ; Tang ; Tangut
1316 sc ; Tavt ; Tai_Viet
1317 sc ; Telu ; Telugu
1318 sc ; Tfng ; Tifinagh
1319 sc ; Tglg ; Tagalog
1320 sc ; Thaa ; Thaana
1321 sc ; Thai ; Thai
1322 sc ; Tibt ; Tibetan
1323 sc ; Tirh ; Tirhuta
1324 sc ; Ugar ; Ugaritic
1325 sc ; Vaii ; Vai
1326 sc ; Wara ; Warang_Citi
1327 sc ; Xpeo ; Old_Persian
1328 sc ; Xsux ; Cuneiform
1329 sc ; Yiii ; Yi
1330 sc ; Zanb ; Zanabazar_Square
1331 sc ; Zinh ; Inherited ; Qaai
1332 sc ; Zyyy ; Common
1333 sc ; Zzzz ; Unknown
1334
1335 # Script_Extensions (scx)
1336
1337 # @missing: 0000..10FFFF; Script_Extensions; <script>
1338
1339 # Sentence_Break (SB)
1340
1341 SB ; AT ; ATerm
1342 SB ; CL ; Close
1343 SB ; CR ; CR
1344 SB ; EX ; Extend
1345 SB ; FO ; Format
1346 SB ; LE ; OLetter
|
1 # PropertyValueAliases-12.1.0.txt
2 # Date: 2019-03-10, 10:53:18 GMT
3 # Copyright (c) 2019 Unicode, Inc.
4 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
5 # For terms of use, see http://www.unicode.org/terms_of_use.html
6 #
7 # Unicode Character Database
8 # For documentation, see http://www.unicode.org/reports/tr44/
9 #
10 # This file contains aliases for property values used in the UCD.
11 # These names can be used for XML formats of UCD data, for regular-expression
12 # property tests, and other programmatic textual descriptions of Unicode data.
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.
20 # This consists of three or more fields, separated by semicolons.
21 #
22 # First Field: The first field describes the property for which that
23 # property value name is used.
24 #
25 # Second Field: The second field is the short name for the property value.
26 # It is typically an abbreviation, but in a number of cases it is simply
27 # a duplicate of the "long name" in the third field.
28 #
29 # Third Field: The third field is the long name for the property value,
30 # typically the formal name used in documentation about the property value.
31 #
32 # In the case of Canonical_Combining_Class (ccc), there are 4 fields:
33 # The second field is numeric, the third is the short name, and the fourth is the long name.
34 #
35 # The above are the preferred aliases. Other aliases may be listed in additional fields.
36 #
37 # Loose matching should be applied to all property names and property values, with
38 # the exception of String Property values. With loose matching of property names and
39 # values, the case distinctions, whitespace, hyphens, and '_' are ignored.
40 # For Numeric Property values, numeric equivalence is applied: thus "01.00"
41 # is equivalent to "1".
42 #
43 # NOTE: Property value names are NOT unique across properties. For example:
44 #
45 # AL means Arabic Letter for the Bidi_Class property, and
46 # AL means Above_Left for the Canonical_Combining_Class property, and
47 # AL means Alphabetic for the Line_Break property.
48 #
49 # In addition, some property names may be the same as some property value names.
50 # For example:
51 #
52 # sc means the Script property, and
53 # Sc means the General_Category property value Currency_Symbol (Sc)
54 #
55 # The combination of property value and property name is, however, unique.
56 #
57 # For more information, see UAX #44, Unicode Character Database, and
58 # UTS #18, Unicode Regular Expressions.
59 # ================================================
60
61
62 # ASCII_Hex_Digit (AHex)
63
64 AHex; N ; No ; F ; False
65 AHex; Y ; Yes ; T ; True
66
67 # Age (age)
68
69 age; 1.1 ; V1_1
70 age; 2.0 ; V2_0
71 age; 2.1 ; V2_1
72 age; 3.0 ; V3_0
73 age; 3.1 ; V3_1
74 age; 3.2 ; V3_2
75 age; 4.0 ; V4_0
76 age; 4.1 ; V4_1
77 age; 5.0 ; V5_0
78 age; 5.1 ; V5_1
79 age; 5.2 ; V5_2
80 age; 6.0 ; V6_0
81 age; 6.1 ; V6_1
82 age; 6.2 ; V6_2
83 age; 6.3 ; V6_3
84 age; 7.0 ; V7_0
85 age; 8.0 ; V8_0
86 age; 9.0 ; V9_0
87 age; 10.0 ; V10_0
88 age; 11.0 ; V11_0
89 age; 12.0 ; V12_0
90 age; 12.1 ; V12_1
91 age; NA ; Unassigned
92
93 # Alphabetic (Alpha)
94
95 Alpha; N ; No ; F ; False
96 Alpha; Y ; Yes ; T ; True
97
98 # Bidi_Class (bc)
99
100 bc ; AL ; Arabic_Letter
101 bc ; AN ; Arabic_Number
102 bc ; B ; Paragraph_Separator
103 bc ; BN ; Boundary_Neutral
104 bc ; CS ; Common_Separator
105 bc ; EN ; European_Number
106 bc ; ES ; European_Separator
107 bc ; ET ; European_Terminator
108 bc ; FSI ; First_Strong_Isolate
109 bc ; L ; Left_To_Right
110 bc ; LRE ; Left_To_Right_Embedding
213 blk; Cuneiform_Numbers ; Cuneiform_Numbers_And_Punctuation
214 blk; Currency_Symbols ; Currency_Symbols
215 blk; Cypriot_Syllabary ; Cypriot_Syllabary
216 blk; Cyrillic ; Cyrillic
217 blk; Cyrillic_Ext_A ; Cyrillic_Extended_A
218 blk; Cyrillic_Ext_B ; Cyrillic_Extended_B
219 blk; Cyrillic_Ext_C ; Cyrillic_Extended_C
220 blk; Cyrillic_Sup ; Cyrillic_Supplement ; Cyrillic_Supplementary
221 blk; Deseret ; Deseret
222 blk; Devanagari ; Devanagari
223 blk; Devanagari_Ext ; Devanagari_Extended
224 blk; Diacriticals ; Combining_Diacritical_Marks
225 blk; Diacriticals_Ext ; Combining_Diacritical_Marks_Extended
226 blk; Diacriticals_For_Symbols ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
227 blk; Diacriticals_Sup ; Combining_Diacritical_Marks_Supplement
228 blk; Dingbats ; Dingbats
229 blk; Dogra ; Dogra
230 blk; Domino ; Domino_Tiles
231 blk; Duployan ; Duployan
232 blk; Early_Dynastic_Cuneiform ; Early_Dynastic_Cuneiform
233 blk; Egyptian_Hieroglyph_Format_Controls; Egyptian_Hieroglyph_Format_Controls
234 blk; Egyptian_Hieroglyphs ; Egyptian_Hieroglyphs
235 blk; Elbasan ; Elbasan
236 blk; Elymaic ; Elymaic
237 blk; Emoticons ; Emoticons
238 blk; Enclosed_Alphanum ; Enclosed_Alphanumerics
239 blk; Enclosed_Alphanum_Sup ; Enclosed_Alphanumeric_Supplement
240 blk; Enclosed_CJK ; Enclosed_CJK_Letters_And_Months
241 blk; Enclosed_Ideographic_Sup ; Enclosed_Ideographic_Supplement
242 blk; Ethiopic ; Ethiopic
243 blk; Ethiopic_Ext ; Ethiopic_Extended
244 blk; Ethiopic_Ext_A ; Ethiopic_Extended_A
245 blk; Ethiopic_Sup ; Ethiopic_Supplement
246 blk; Geometric_Shapes ; Geometric_Shapes
247 blk; Geometric_Shapes_Ext ; Geometric_Shapes_Extended
248 blk; Georgian ; Georgian
249 blk; Georgian_Ext ; Georgian_Extended
250 blk; Georgian_Sup ; Georgian_Supplement
251 blk; Glagolitic ; Glagolitic
252 blk; Glagolitic_Sup ; Glagolitic_Supplement
253 blk; Gothic ; Gothic
254 blk; Grantha ; Grantha
255 blk; Greek ; Greek_And_Coptic
256 blk; Greek_Ext ; Greek_Extended
330 blk; Meroitic_Hieroglyphs ; Meroitic_Hieroglyphs
331 blk; Miao ; Miao
332 blk; Misc_Arrows ; Miscellaneous_Symbols_And_Arrows
333 blk; Misc_Math_Symbols_A ; Miscellaneous_Mathematical_Symbols_A
334 blk; Misc_Math_Symbols_B ; Miscellaneous_Mathematical_Symbols_B
335 blk; Misc_Pictographs ; Miscellaneous_Symbols_And_Pictographs
336 blk; Misc_Symbols ; Miscellaneous_Symbols
337 blk; Misc_Technical ; Miscellaneous_Technical
338 blk; Modi ; Modi
339 blk; Modifier_Letters ; Spacing_Modifier_Letters
340 blk; Modifier_Tone_Letters ; Modifier_Tone_Letters
341 blk; Mongolian ; Mongolian
342 blk; Mongolian_Sup ; Mongolian_Supplement
343 blk; Mro ; Mro
344 blk; Multani ; Multani
345 blk; Music ; Musical_Symbols
346 blk; Myanmar ; Myanmar
347 blk; Myanmar_Ext_A ; Myanmar_Extended_A
348 blk; Myanmar_Ext_B ; Myanmar_Extended_B
349 blk; Nabataean ; Nabataean
350 blk; Nandinagari ; Nandinagari
351 blk; NB ; No_Block
352 blk; New_Tai_Lue ; New_Tai_Lue
353 blk; Newa ; Newa
354 blk; NKo ; NKo
355 blk; Number_Forms ; Number_Forms
356 blk; Nushu ; Nushu
357 blk; Nyiakeng_Puachue_Hmong ; Nyiakeng_Puachue_Hmong
358 blk; OCR ; Optical_Character_Recognition
359 blk; Ogham ; Ogham
360 blk; Ol_Chiki ; Ol_Chiki
361 blk; Old_Hungarian ; Old_Hungarian
362 blk; Old_Italic ; Old_Italic
363 blk; Old_North_Arabian ; Old_North_Arabian
364 blk; Old_Permic ; Old_Permic
365 blk; Old_Persian ; Old_Persian
366 blk; Old_Sogdian ; Old_Sogdian
367 blk; Old_South_Arabian ; Old_South_Arabian
368 blk; Old_Turkic ; Old_Turkic
369 blk; Oriya ; Oriya
370 blk; Ornamental_Dingbats ; Ornamental_Dingbats
371 blk; Osage ; Osage
372 blk; Osmanya ; Osmanya
373 blk; Ottoman_Siyaq_Numbers ; Ottoman_Siyaq_Numbers
374 blk; Pahawh_Hmong ; Pahawh_Hmong
375 blk; Palmyrene ; Palmyrene
376 blk; Pau_Cin_Hau ; Pau_Cin_Hau
377 blk; Phags_Pa ; Phags_Pa
378 blk; Phaistos ; Phaistos_Disc
379 blk; Phoenician ; Phoenician
380 blk; Phonetic_Ext ; Phonetic_Extensions
381 blk; Phonetic_Ext_Sup ; Phonetic_Extensions_Supplement
382 blk; Playing_Cards ; Playing_Cards
383 blk; Psalter_Pahlavi ; Psalter_Pahlavi
384 blk; PUA ; Private_Use_Area ; Private_Use
385 blk; Punctuation ; General_Punctuation
386 blk; Rejang ; Rejang
387 blk; Rumi ; Rumi_Numeral_Symbols
388 blk; Runic ; Runic
389 blk; Samaritan ; Samaritan
390 blk; Saurashtra ; Saurashtra
391 blk; Sharada ; Sharada
392 blk; Shavian ; Shavian
393 blk; Shorthand_Format_Controls ; Shorthand_Format_Controls
394 blk; Siddham ; Siddham
395 blk; Sinhala ; Sinhala
396 blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers
397 blk; Small_Forms ; Small_Form_Variants
398 blk; Small_Kana_Ext ; Small_Kana_Extension
399 blk; Sogdian ; Sogdian
400 blk; Sora_Sompeng ; Sora_Sompeng
401 blk; Soyombo ; Soyombo
402 blk; Specials ; Specials
403 blk; Sundanese ; Sundanese
404 blk; Sundanese_Sup ; Sundanese_Supplement
405 blk; Sup_Arrows_A ; Supplemental_Arrows_A
406 blk; Sup_Arrows_B ; Supplemental_Arrows_B
407 blk; Sup_Arrows_C ; Supplemental_Arrows_C
408 blk; Sup_Math_Operators ; Supplemental_Mathematical_Operators
409 blk; Sup_PUA_A ; Supplementary_Private_Use_Area_A
410 blk; Sup_PUA_B ; Supplementary_Private_Use_Area_B
411 blk; Sup_Punctuation ; Supplemental_Punctuation
412 blk; Sup_Symbols_And_Pictographs ; Supplemental_Symbols_And_Pictographs
413 blk; Super_And_Sub ; Superscripts_And_Subscripts
414 blk; Sutton_SignWriting ; Sutton_SignWriting
415 blk; Syloti_Nagri ; Syloti_Nagri
416 blk; Symbols_And_Pictographs_Ext_A ; Symbols_And_Pictographs_Extended_A
417 blk; Syriac ; Syriac
418 blk; Syriac_Sup ; Syriac_Supplement
419 blk; Tagalog ; Tagalog
420 blk; Tagbanwa ; Tagbanwa
421 blk; Tags ; Tags
422 blk; Tai_Le ; Tai_Le
423 blk; Tai_Tham ; Tai_Tham
424 blk; Tai_Viet ; Tai_Viet
425 blk; Tai_Xuan_Jing ; Tai_Xuan_Jing_Symbols
426 blk; Takri ; Takri
427 blk; Tamil ; Tamil
428 blk; Tamil_Sup ; Tamil_Supplement
429 blk; Tangut ; Tangut
430 blk; Tangut_Components ; Tangut_Components
431 blk; Telugu ; Telugu
432 blk; Thaana ; Thaana
433 blk; Thai ; Thai
434 blk; Tibetan ; Tibetan
435 blk; Tifinagh ; Tifinagh
436 blk; Tirhuta ; Tirhuta
437 blk; Transport_And_Map ; Transport_And_Map_Symbols
438 blk; UCAS ; Unified_Canadian_Aboriginal_Syllabics; Canadian_Syllabics
439 blk; UCAS_Ext ; Unified_Canadian_Aboriginal_Syllabics_Extended
440 blk; Ugaritic ; Ugaritic
441 blk; Vai ; Vai
442 blk; Vedic_Ext ; Vedic_Extensions
443 blk; Vertical_Forms ; Vertical_Forms
444 blk; VS ; Variation_Selectors
445 blk; VS_Sup ; Variation_Selectors_Supplement
446 blk; Wancho ; Wancho
447 blk; Warang_Citi ; Warang_Citi
448 blk; Yi_Radicals ; Yi_Radicals
449 blk; Yi_Syllables ; Yi_Syllables
450 blk; Yijing ; Yijing_Hexagram_Symbols
451 blk; Zanabazar_Square ; Zanabazar_Square
452
453 # Canonical_Combining_Class (ccc)
454
455 ccc; 0; NR ; Not_Reordered
456 ccc; 1; OV ; Overlay
457 ccc; 7; NK ; Nukta
458 ccc; 8; KV ; Kana_Voicing
459 ccc; 9; VR ; Virama
460 ccc; 10; CCC10 ; CCC10
461 ccc; 11; CCC11 ; CCC11
462 ccc; 12; CCC12 ; CCC12
463 ccc; 13; CCC13 ; CCC13
464 ccc; 14; CCC14 ; CCC14
465 ccc; 15; CCC15 ; CCC15
466 ccc; 16; CCC16 ; CCC16
1211 sc ; Bhks ; Bhaiksuki
1212 sc ; Bopo ; Bopomofo
1213 sc ; Brah ; Brahmi
1214 sc ; Brai ; Braille
1215 sc ; Bugi ; Buginese
1216 sc ; Buhd ; Buhid
1217 sc ; Cakm ; Chakma
1218 sc ; Cans ; Canadian_Aboriginal
1219 sc ; Cari ; Carian
1220 sc ; Cham ; Cham
1221 sc ; Cher ; Cherokee
1222 sc ; Copt ; Coptic ; Qaac
1223 sc ; Cprt ; Cypriot
1224 sc ; Cyrl ; Cyrillic
1225 sc ; Deva ; Devanagari
1226 sc ; Dogr ; Dogra
1227 sc ; Dsrt ; Deseret
1228 sc ; Dupl ; Duployan
1229 sc ; Egyp ; Egyptian_Hieroglyphs
1230 sc ; Elba ; Elbasan
1231 sc ; Elym ; Elymaic
1232 sc ; Ethi ; Ethiopic
1233 sc ; Geor ; Georgian
1234 sc ; Glag ; Glagolitic
1235 sc ; Gong ; Gunjala_Gondi
1236 sc ; Gonm ; Masaram_Gondi
1237 sc ; Goth ; Gothic
1238 sc ; Gran ; Grantha
1239 sc ; Grek ; Greek
1240 sc ; Gujr ; Gujarati
1241 sc ; Guru ; Gurmukhi
1242 sc ; Hang ; Hangul
1243 sc ; Hani ; Han
1244 sc ; Hano ; Hanunoo
1245 sc ; Hatr ; Hatran
1246 sc ; Hebr ; Hebrew
1247 sc ; Hira ; Hiragana
1248 sc ; Hluw ; Anatolian_Hieroglyphs
1249 sc ; Hmng ; Pahawh_Hmong
1250 sc ; Hmnp ; Nyiakeng_Puachue_Hmong
1251 sc ; Hrkt ; Katakana_Or_Hiragana
1252 sc ; Hung ; Old_Hungarian
1253 sc ; Ital ; Old_Italic
1254 sc ; Java ; Javanese
1255 sc ; Kali ; Kayah_Li
1256 sc ; Kana ; Katakana
1257 sc ; Khar ; Kharoshthi
1258 sc ; Khmr ; Khmer
1259 sc ; Khoj ; Khojki
1260 sc ; Knda ; Kannada
1261 sc ; Kthi ; Kaithi
1262 sc ; Lana ; Tai_Tham
1263 sc ; Laoo ; Lao
1264 sc ; Latn ; Latin
1265 sc ; Lepc ; Lepcha
1266 sc ; Limb ; Limbu
1267 sc ; Lina ; Linear_A
1268 sc ; Linb ; Linear_B
1269 sc ; Lisu ; Lisu
1270 sc ; Lyci ; Lycian
1271 sc ; Lydi ; Lydian
1272 sc ; Mahj ; Mahajani
1273 sc ; Maka ; Makasar
1274 sc ; Mand ; Mandaic
1275 sc ; Mani ; Manichaean
1276 sc ; Marc ; Marchen
1277 sc ; Medf ; Medefaidrin
1278 sc ; Mend ; Mende_Kikakui
1279 sc ; Merc ; Meroitic_Cursive
1280 sc ; Mero ; Meroitic_Hieroglyphs
1281 sc ; Mlym ; Malayalam
1282 sc ; Modi ; Modi
1283 sc ; Mong ; Mongolian
1284 sc ; Mroo ; Mro
1285 sc ; Mtei ; Meetei_Mayek
1286 sc ; Mult ; Multani
1287 sc ; Mymr ; Myanmar
1288 sc ; Nand ; Nandinagari
1289 sc ; Narb ; Old_North_Arabian
1290 sc ; Nbat ; Nabataean
1291 sc ; Newa ; Newa
1292 sc ; Nkoo ; Nko
1293 sc ; Nshu ; Nushu
1294 sc ; Ogam ; Ogham
1295 sc ; Olck ; Ol_Chiki
1296 sc ; Orkh ; Old_Turkic
1297 sc ; Orya ; Oriya
1298 sc ; Osge ; Osage
1299 sc ; Osma ; Osmanya
1300 sc ; Palm ; Palmyrene
1301 sc ; Pauc ; Pau_Cin_Hau
1302 sc ; Perm ; Old_Permic
1303 sc ; Phag ; Phags_Pa
1304 sc ; Phli ; Inscriptional_Pahlavi
1305 sc ; Phlp ; Psalter_Pahlavi
1306 sc ; Phnx ; Phoenician
1307 sc ; Plrd ; Miao
1308 sc ; Prti ; Inscriptional_Parthian
1325 sc ; Sund ; Sundanese
1326 sc ; Sylo ; Syloti_Nagri
1327 sc ; Syrc ; Syriac
1328 sc ; Tagb ; Tagbanwa
1329 sc ; Takr ; Takri
1330 sc ; Tale ; Tai_Le
1331 sc ; Talu ; New_Tai_Lue
1332 sc ; Taml ; Tamil
1333 sc ; Tang ; Tangut
1334 sc ; Tavt ; Tai_Viet
1335 sc ; Telu ; Telugu
1336 sc ; Tfng ; Tifinagh
1337 sc ; Tglg ; Tagalog
1338 sc ; Thaa ; Thaana
1339 sc ; Thai ; Thai
1340 sc ; Tibt ; Tibetan
1341 sc ; Tirh ; Tirhuta
1342 sc ; Ugar ; Ugaritic
1343 sc ; Vaii ; Vai
1344 sc ; Wara ; Warang_Citi
1345 sc ; Wcho ; Wancho
1346 sc ; Xpeo ; Old_Persian
1347 sc ; Xsux ; Cuneiform
1348 sc ; Yiii ; Yi
1349 sc ; Zanb ; Zanabazar_Square
1350 sc ; Zinh ; Inherited ; Qaai
1351 sc ; Zyyy ; Common
1352 sc ; Zzzz ; Unknown
1353
1354 # Script_Extensions (scx)
1355
1356 # @missing: 0000..10FFFF; Script_Extensions; <script>
1357
1358 # Sentence_Break (SB)
1359
1360 SB ; AT ; ATerm
1361 SB ; CL ; Close
1362 SB ; CR ; CR
1363 SB ; EX ; Extend
1364 SB ; FO ; Format
1365 SB ; LE ; OLetter
|