backrefs 5.9__py314-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- backrefs/__init__.py +2 -0
- backrefs/__meta__.py +197 -0
- backrefs/_bre_parse.py +1529 -0
- backrefs/_bregex_parse.py +1362 -0
- backrefs/_bregex_typing.py +6 -0
- backrefs/bre.py +652 -0
- backrefs/bregex.py +726 -0
- backrefs/py.typed +0 -0
- backrefs/uniprops/__init__.py +592 -0
- backrefs/uniprops/unidata/__init__.py +26 -0
- backrefs/uniprops/unidata/age.py +119 -0
- backrefs/uniprops/unidata/alias.py +783 -0
- backrefs/uniprops/unidata/bidiclass.py +99 -0
- backrefs/uniprops/unidata/bidipairedbrackettype.py +19 -0
- backrefs/uniprops/unidata/binary.py +335 -0
- backrefs/uniprops/unidata/block.py +1363 -0
- backrefs/uniprops/unidata/canonicalcombiningclass.py +1031 -0
- backrefs/uniprops/unidata/decompositiontype.py +79 -0
- backrefs/uniprops/unidata/eastasianwidth.py +31 -0
- backrefs/uniprops/unidata/generalcategory.py +173 -0
- backrefs/uniprops/unidata/graphemeclusterbreak.py +79 -0
- backrefs/uniprops/unidata/hangulsyllabletype.py +31 -0
- backrefs/uniprops/unidata/indicpositionalcategory.py +71 -0
- backrefs/uniprops/unidata/indicsyllabiccategory.py +155 -0
- backrefs/uniprops/unidata/joininggroup.py +427 -0
- backrefs/uniprops/unidata/joiningtype.py +31 -0
- backrefs/uniprops/unidata/linebreak.py +199 -0
- backrefs/uniprops/unidata/numerictype.py +23 -0
- backrefs/uniprops/unidata/numericvalue.py +583 -0
- backrefs/uniprops/unidata/quickcheck.py +59 -0
- backrefs/uniprops/unidata/script.py +695 -0
- backrefs/uniprops/unidata/scriptextensions.py +695 -0
- backrefs/uniprops/unidata/sentencebreak.py +67 -0
- backrefs/uniprops/unidata/verticalorientation.py +23 -0
- backrefs/uniprops/unidata/wordbreak.py +99 -0
- backrefs/util.py +163 -0
- backrefs-5.9.dist-info/METADATA +73 -0
- backrefs-5.9.dist-info/RECORD +40 -0
- backrefs-5.9.dist-info/WHEEL +4 -0
- backrefs-5.9.dist-info/licenses/LICENSE.md +21 -0
|
@@ -0,0 +1,783 @@
|
|
|
1
|
+
"""Unicode Properties from Unicode version 16.0.0 (autogen)."""
|
|
2
|
+
from __future__ import annotations
|
|
3
|
+
|
|
4
|
+
unicode_alias: dict[str, dict[str, str]] = {
|
|
5
|
+
"_": {
|
|
6
|
+
"age": "age",
|
|
7
|
+
"bc": "bidiclass",
|
|
8
|
+
"blk": "block",
|
|
9
|
+
"bpt": "bidipairedbrackettype",
|
|
10
|
+
"ccc": "canonicalcombiningclass",
|
|
11
|
+
"dt": "decompositiontype",
|
|
12
|
+
"ea": "eastasianwidth",
|
|
13
|
+
"gc": "generalcategory",
|
|
14
|
+
"gcb": "graphemeclusterbreak",
|
|
15
|
+
"hst": "hangulsyllabletype",
|
|
16
|
+
"indicconjunctbreak": "incb",
|
|
17
|
+
"inpc": "indicpositionalcategory",
|
|
18
|
+
"insc": "indicsyllabiccategory",
|
|
19
|
+
"jg": "joininggroup",
|
|
20
|
+
"jt": "joiningtype",
|
|
21
|
+
"lb": "linebreak",
|
|
22
|
+
"nfcqc": "nfcquickcheck",
|
|
23
|
+
"nfdqc": "nfdquickcheck",
|
|
24
|
+
"nfkcqc": "nfkcquickcheck",
|
|
25
|
+
"nfkdqc": "nfkdquickcheck",
|
|
26
|
+
"nt": "numerictype",
|
|
27
|
+
"nv": "numericvalue",
|
|
28
|
+
"sb": "sentencebreak",
|
|
29
|
+
"sc": "script",
|
|
30
|
+
"scx": "scriptextensions",
|
|
31
|
+
"vo": "verticalorientation",
|
|
32
|
+
"wb": "wordbreak"
|
|
33
|
+
},
|
|
34
|
+
"age": {
|
|
35
|
+
"unassigned": "na",
|
|
36
|
+
"v100": "10.0",
|
|
37
|
+
"v11": "1.1",
|
|
38
|
+
"v110": "11.0",
|
|
39
|
+
"v120": "12.0",
|
|
40
|
+
"v121": "12.1",
|
|
41
|
+
"v130": "13.0",
|
|
42
|
+
"v140": "14.0",
|
|
43
|
+
"v150": "15.0",
|
|
44
|
+
"v151": "15.1",
|
|
45
|
+
"v160": "16.0",
|
|
46
|
+
"v20": "2.0",
|
|
47
|
+
"v21": "2.1",
|
|
48
|
+
"v30": "3.0",
|
|
49
|
+
"v31": "3.1",
|
|
50
|
+
"v32": "3.2",
|
|
51
|
+
"v40": "4.0",
|
|
52
|
+
"v41": "4.1",
|
|
53
|
+
"v50": "5.0",
|
|
54
|
+
"v51": "5.1",
|
|
55
|
+
"v52": "5.2",
|
|
56
|
+
"v60": "6.0",
|
|
57
|
+
"v61": "6.1",
|
|
58
|
+
"v62": "6.2",
|
|
59
|
+
"v63": "6.3",
|
|
60
|
+
"v70": "7.0",
|
|
61
|
+
"v80": "8.0",
|
|
62
|
+
"v90": "9.0"
|
|
63
|
+
},
|
|
64
|
+
"bidiclass": {
|
|
65
|
+
"arabicletter": "al",
|
|
66
|
+
"arabicnumber": "an",
|
|
67
|
+
"boundaryneutral": "bn",
|
|
68
|
+
"commonseparator": "cs",
|
|
69
|
+
"europeannumber": "en",
|
|
70
|
+
"europeanseparator": "es",
|
|
71
|
+
"europeanterminator": "et",
|
|
72
|
+
"firststrongisolate": "fsi",
|
|
73
|
+
"lefttoright": "l",
|
|
74
|
+
"lefttorightembedding": "lre",
|
|
75
|
+
"lefttorightisolate": "lri",
|
|
76
|
+
"lefttorightoverride": "lro",
|
|
77
|
+
"nonspacingmark": "nsm",
|
|
78
|
+
"otherneutral": "on",
|
|
79
|
+
"paragraphseparator": "b",
|
|
80
|
+
"popdirectionalformat": "pdf",
|
|
81
|
+
"popdirectionalisolate": "pdi",
|
|
82
|
+
"righttoleft": "r",
|
|
83
|
+
"righttoleftembedding": "rle",
|
|
84
|
+
"righttoleftisolate": "rli",
|
|
85
|
+
"righttoleftoverride": "rlo",
|
|
86
|
+
"segmentseparator": "s",
|
|
87
|
+
"whitespace": "ws"
|
|
88
|
+
},
|
|
89
|
+
"bidipairedbrackettype": {
|
|
90
|
+
"close": "c",
|
|
91
|
+
"none": "n",
|
|
92
|
+
"open": "o"
|
|
93
|
+
},
|
|
94
|
+
"binary": {
|
|
95
|
+
"ahex": "asciihexdigit",
|
|
96
|
+
"alpha": "alphabetic",
|
|
97
|
+
"bidic": "bidicontrol",
|
|
98
|
+
"bidim": "bidimirrored",
|
|
99
|
+
"blank": "posixblank",
|
|
100
|
+
"cased": "cased",
|
|
101
|
+
"ce": "compositionexclusion",
|
|
102
|
+
"ci": "caseignorable",
|
|
103
|
+
"compex": "fullcompositionexclusion",
|
|
104
|
+
"cwcf": "changeswhencasefolded",
|
|
105
|
+
"cwcm": "changeswhencasemapped",
|
|
106
|
+
"cwkcf": "changeswhennfkccasefolded",
|
|
107
|
+
"cwl": "changeswhenlowercased",
|
|
108
|
+
"cwt": "changeswhentitlecased",
|
|
109
|
+
"cwu": "changeswhenuppercased",
|
|
110
|
+
"dash": "dash",
|
|
111
|
+
"dep": "deprecated",
|
|
112
|
+
"di": "defaultignorablecodepoint",
|
|
113
|
+
"dia": "diacritic",
|
|
114
|
+
"ebase": "emojimodifierbase",
|
|
115
|
+
"ecomp": "emojicomponent",
|
|
116
|
+
"emod": "emojimodifier",
|
|
117
|
+
"emoji": "emoji",
|
|
118
|
+
"epres": "emojipresentation",
|
|
119
|
+
"ext": "extender",
|
|
120
|
+
"extpict": "extendedpictographic",
|
|
121
|
+
"graph": "posixgraph",
|
|
122
|
+
"grbase": "graphemebase",
|
|
123
|
+
"grext": "graphemeextend",
|
|
124
|
+
"grlink": "graphemelink",
|
|
125
|
+
"h": "horizspace",
|
|
126
|
+
"hex": "hexdigit",
|
|
127
|
+
"hyphen": "hyphen",
|
|
128
|
+
"idc": "idcontinue",
|
|
129
|
+
"idcompatmathcontinue": "idcompatmathcontinue",
|
|
130
|
+
"idcompatmathstart": "idcompatmathstart",
|
|
131
|
+
"ideo": "ideographic",
|
|
132
|
+
"ids": "idstart",
|
|
133
|
+
"idsb": "idsbinaryoperator",
|
|
134
|
+
"idst": "idstrinaryoperator",
|
|
135
|
+
"idsu": "idsunaryoperator",
|
|
136
|
+
"joinc": "joincontrol",
|
|
137
|
+
"loe": "logicalorderexception",
|
|
138
|
+
"lower": "lowercase",
|
|
139
|
+
"math": "math",
|
|
140
|
+
"mcm": "modifiercombiningmark",
|
|
141
|
+
"nchar": "noncharactercodepoint",
|
|
142
|
+
"oalpha": "otheralphabetic",
|
|
143
|
+
"odi": "otherdefaultignorablecodepoint",
|
|
144
|
+
"ogrext": "othergraphemeextend",
|
|
145
|
+
"oidc": "otheridcontinue",
|
|
146
|
+
"oids": "otheridstart",
|
|
147
|
+
"olower": "otherlowercase",
|
|
148
|
+
"omath": "othermath",
|
|
149
|
+
"oupper": "otheruppercase",
|
|
150
|
+
"patsyn": "patternsyntax",
|
|
151
|
+
"patws": "patternwhitespace",
|
|
152
|
+
"pcm": "prependedconcatenationmark",
|
|
153
|
+
"posixalpha": "alphabetic",
|
|
154
|
+
"posixlower": "lowercase",
|
|
155
|
+
"posixspace": "whitespace",
|
|
156
|
+
"posixupper": "uppercase",
|
|
157
|
+
"print": "posixprint",
|
|
158
|
+
"qmark": "quotationmark",
|
|
159
|
+
"radical": "radical",
|
|
160
|
+
"ri": "regionalindicator",
|
|
161
|
+
"sd": "softdotted",
|
|
162
|
+
"space": "whitespace",
|
|
163
|
+
"sterm": "sentenceterminal",
|
|
164
|
+
"term": "terminalpunctuation",
|
|
165
|
+
"uideo": "unifiedideograph",
|
|
166
|
+
"upper": "uppercase",
|
|
167
|
+
"v": "vertspace",
|
|
168
|
+
"vs": "variationselector",
|
|
169
|
+
"wspace": "whitespace",
|
|
170
|
+
"xidc": "xidcontinue",
|
|
171
|
+
"xids": "xidstart"
|
|
172
|
+
},
|
|
173
|
+
"block": {
|
|
174
|
+
"alchemical": "alchemicalsymbols",
|
|
175
|
+
"alphabeticpf": "alphabeticpresentationforms",
|
|
176
|
+
"ancientgreekmusic": "ancientgreekmusicalnotation",
|
|
177
|
+
"arabicexta": "arabicextendeda",
|
|
178
|
+
"arabicextb": "arabicextendedb",
|
|
179
|
+
"arabicextc": "arabicextendedc",
|
|
180
|
+
"arabicmath": "arabicmathematicalalphabeticsymbols",
|
|
181
|
+
"arabicpfa": "arabicpresentationformsa",
|
|
182
|
+
"arabicpfb": "arabicpresentationformsb",
|
|
183
|
+
"arabicsup": "arabicsupplement",
|
|
184
|
+
"ascii": "basiclatin",
|
|
185
|
+
"bamumsup": "bamumsupplement",
|
|
186
|
+
"bopomofoext": "bopomofoextended",
|
|
187
|
+
"braille": "braillepatterns",
|
|
188
|
+
"byzantinemusic": "byzantinemusicalsymbols",
|
|
189
|
+
"canadiansyllabics": "unifiedcanadianaboriginalsyllabics",
|
|
190
|
+
"cherokeesup": "cherokeesupplement",
|
|
191
|
+
"cjk": "cjkunifiedideographs",
|
|
192
|
+
"cjkcompat": "cjkcompatibility",
|
|
193
|
+
"cjkcompatforms": "cjkcompatibilityforms",
|
|
194
|
+
"cjkcompatideographs": "cjkcompatibilityideographs",
|
|
195
|
+
"cjkcompatideographssup": "cjkcompatibilityideographssupplement",
|
|
196
|
+
"cjkexta": "cjkunifiedideographsextensiona",
|
|
197
|
+
"cjkextb": "cjkunifiedideographsextensionb",
|
|
198
|
+
"cjkextc": "cjkunifiedideographsextensionc",
|
|
199
|
+
"cjkextd": "cjkunifiedideographsextensiond",
|
|
200
|
+
"cjkexte": "cjkunifiedideographsextensione",
|
|
201
|
+
"cjkextf": "cjkunifiedideographsextensionf",
|
|
202
|
+
"cjkextg": "cjkunifiedideographsextensiong",
|
|
203
|
+
"cjkexth": "cjkunifiedideographsextensionh",
|
|
204
|
+
"cjkexti": "cjkunifiedideographsextensioni",
|
|
205
|
+
"cjkradicalssup": "cjkradicalssupplement",
|
|
206
|
+
"cjksymbols": "cjksymbolsandpunctuation",
|
|
207
|
+
"combiningmarksforsymbols": "combiningdiacriticalmarksforsymbols",
|
|
208
|
+
"compatjamo": "hangulcompatibilityjamo",
|
|
209
|
+
"countingrod": "countingrodnumerals",
|
|
210
|
+
"cuneiformnumbers": "cuneiformnumbersandpunctuation",
|
|
211
|
+
"cyrillicexta": "cyrillicextendeda",
|
|
212
|
+
"cyrillicextb": "cyrillicextendedb",
|
|
213
|
+
"cyrillicextc": "cyrillicextendedc",
|
|
214
|
+
"cyrillicextd": "cyrillicextendedd",
|
|
215
|
+
"cyrillicsup": "cyrillicsupplement",
|
|
216
|
+
"cyrillicsupplementary": "cyrillicsupplement",
|
|
217
|
+
"devanagariext": "devanagariextended",
|
|
218
|
+
"devanagariexta": "devanagariextendeda",
|
|
219
|
+
"diacriticals": "combiningdiacriticalmarks",
|
|
220
|
+
"diacriticalsext": "combiningdiacriticalmarksextended",
|
|
221
|
+
"diacriticalsforsymbols": "combiningdiacriticalmarksforsymbols",
|
|
222
|
+
"diacriticalssup": "combiningdiacriticalmarkssupplement",
|
|
223
|
+
"domino": "dominotiles",
|
|
224
|
+
"egyptianhieroglyphsexta": "egyptianhieroglyphsextendeda",
|
|
225
|
+
"enclosedalphanum": "enclosedalphanumerics",
|
|
226
|
+
"enclosedalphanumsup": "enclosedalphanumericsupplement",
|
|
227
|
+
"enclosedcjk": "enclosedcjklettersandmonths",
|
|
228
|
+
"enclosedideographicsup": "enclosedideographicsupplement",
|
|
229
|
+
"ethiopicext": "ethiopicextended",
|
|
230
|
+
"ethiopicexta": "ethiopicextendeda",
|
|
231
|
+
"ethiopicextb": "ethiopicextendedb",
|
|
232
|
+
"ethiopicsup": "ethiopicsupplement",
|
|
233
|
+
"geometricshapesext": "geometricshapesextended",
|
|
234
|
+
"georgianext": "georgianextended",
|
|
235
|
+
"georgiansup": "georgiansupplement",
|
|
236
|
+
"glagoliticsup": "glagoliticsupplement",
|
|
237
|
+
"greek": "greekandcoptic",
|
|
238
|
+
"greekext": "greekextended",
|
|
239
|
+
"halfandfullforms": "halfwidthandfullwidthforms",
|
|
240
|
+
"halfmarks": "combininghalfmarks",
|
|
241
|
+
"hangul": "hangulsyllables",
|
|
242
|
+
"highpusurrogates": "highprivateusesurrogates",
|
|
243
|
+
"idc": "ideographicdescriptioncharacters",
|
|
244
|
+
"ideographicsymbols": "ideographicsymbolsandpunctuation",
|
|
245
|
+
"indicnumberforms": "commonindicnumberforms",
|
|
246
|
+
"ipaext": "ipaextensions",
|
|
247
|
+
"jamo": "hanguljamo",
|
|
248
|
+
"jamoexta": "hanguljamoextendeda",
|
|
249
|
+
"jamoextb": "hanguljamoextendedb",
|
|
250
|
+
"kanaexta": "kanaextendeda",
|
|
251
|
+
"kanaextb": "kanaextendedb",
|
|
252
|
+
"kanasup": "kanasupplement",
|
|
253
|
+
"kangxi": "kangxiradicals",
|
|
254
|
+
"katakanaext": "katakanaphoneticextensions",
|
|
255
|
+
"latin1": "latin1supplement",
|
|
256
|
+
"latin1sup": "latin1supplement",
|
|
257
|
+
"latinexta": "latinextendeda",
|
|
258
|
+
"latinextadditional": "latinextendedadditional",
|
|
259
|
+
"latinextb": "latinextendedb",
|
|
260
|
+
"latinextc": "latinextendedc",
|
|
261
|
+
"latinextd": "latinextendedd",
|
|
262
|
+
"latinexte": "latinextendede",
|
|
263
|
+
"latinextf": "latinextendedf",
|
|
264
|
+
"latinextg": "latinextendedg",
|
|
265
|
+
"lisusup": "lisusupplement",
|
|
266
|
+
"mahjong": "mahjongtiles",
|
|
267
|
+
"mathalphanum": "mathematicalalphanumericsymbols",
|
|
268
|
+
"mathoperators": "mathematicaloperators",
|
|
269
|
+
"meeteimayekext": "meeteimayekextensions",
|
|
270
|
+
"miscarrows": "miscellaneoussymbolsandarrows",
|
|
271
|
+
"miscmathsymbolsa": "miscellaneousmathematicalsymbolsa",
|
|
272
|
+
"miscmathsymbolsb": "miscellaneousmathematicalsymbolsb",
|
|
273
|
+
"miscpictographs": "miscellaneoussymbolsandpictographs",
|
|
274
|
+
"miscsymbols": "miscellaneoussymbols",
|
|
275
|
+
"misctechnical": "miscellaneoustechnical",
|
|
276
|
+
"modifierletters": "spacingmodifierletters",
|
|
277
|
+
"mongoliansup": "mongoliansupplement",
|
|
278
|
+
"music": "musicalsymbols",
|
|
279
|
+
"myanmarexta": "myanmarextendeda",
|
|
280
|
+
"myanmarextb": "myanmarextendedb",
|
|
281
|
+
"myanmarextc": "myanmarextendedc",
|
|
282
|
+
"nb": "noblock",
|
|
283
|
+
"ocr": "opticalcharacterrecognition",
|
|
284
|
+
"phaistos": "phaistosdisc",
|
|
285
|
+
"phoneticext": "phoneticextensions",
|
|
286
|
+
"phoneticextsup": "phoneticextensionssupplement",
|
|
287
|
+
"privateuse": "privateusearea",
|
|
288
|
+
"pua": "privateusearea",
|
|
289
|
+
"punctuation": "generalpunctuation",
|
|
290
|
+
"rumi": "ruminumeralsymbols",
|
|
291
|
+
"smallforms": "smallformvariants",
|
|
292
|
+
"smallkanaext": "smallkanaextension",
|
|
293
|
+
"sundanesesup": "sundanesesupplement",
|
|
294
|
+
"suparrowsa": "supplementalarrowsa",
|
|
295
|
+
"suparrowsb": "supplementalarrowsb",
|
|
296
|
+
"suparrowsc": "supplementalarrowsc",
|
|
297
|
+
"superandsub": "superscriptsandsubscripts",
|
|
298
|
+
"supmathoperators": "supplementalmathematicaloperators",
|
|
299
|
+
"suppuaa": "supplementaryprivateuseareaa",
|
|
300
|
+
"suppuab": "supplementaryprivateuseareab",
|
|
301
|
+
"suppunctuation": "supplementalpunctuation",
|
|
302
|
+
"supsymbolsandpictographs": "supplementalsymbolsandpictographs",
|
|
303
|
+
"symbolsandpictographsexta": "symbolsandpictographsextendeda",
|
|
304
|
+
"symbolsforlegacycomputingsup": "symbolsforlegacycomputingsupplement",
|
|
305
|
+
"syriacsup": "syriacsupplement",
|
|
306
|
+
"taixuanjing": "taixuanjingsymbols",
|
|
307
|
+
"tamilsup": "tamilsupplement",
|
|
308
|
+
"tangutsup": "tangutsupplement",
|
|
309
|
+
"transportandmap": "transportandmapsymbols",
|
|
310
|
+
"ucas": "unifiedcanadianaboriginalsyllabics",
|
|
311
|
+
"ucasext": "unifiedcanadianaboriginalsyllabicsextended",
|
|
312
|
+
"ucasexta": "unifiedcanadianaboriginalsyllabicsextendeda",
|
|
313
|
+
"vedicext": "vedicextensions",
|
|
314
|
+
"vs": "variationselectors",
|
|
315
|
+
"vssup": "variationselectorssupplement",
|
|
316
|
+
"yijing": "yijinghexagramsymbols",
|
|
317
|
+
"znamennymusic": "znamennymusicalnotation"
|
|
318
|
+
},
|
|
319
|
+
"canonicalcombiningclass": {
|
|
320
|
+
"a": "230",
|
|
321
|
+
"above": "230",
|
|
322
|
+
"aboveleft": "228",
|
|
323
|
+
"aboveright": "232",
|
|
324
|
+
"al": "228",
|
|
325
|
+
"ar": "232",
|
|
326
|
+
"ata": "214",
|
|
327
|
+
"atar": "216",
|
|
328
|
+
"atb": "202",
|
|
329
|
+
"atbl": "200",
|
|
330
|
+
"attachedabove": "214",
|
|
331
|
+
"attachedaboveright": "216",
|
|
332
|
+
"attachedbelow": "202",
|
|
333
|
+
"attachedbelowleft": "200",
|
|
334
|
+
"b": "220",
|
|
335
|
+
"below": "220",
|
|
336
|
+
"belowleft": "218",
|
|
337
|
+
"belowright": "222",
|
|
338
|
+
"bl": "218",
|
|
339
|
+
"br": "222",
|
|
340
|
+
"ccc10": "10",
|
|
341
|
+
"ccc103": "103",
|
|
342
|
+
"ccc107": "107",
|
|
343
|
+
"ccc11": "11",
|
|
344
|
+
"ccc118": "118",
|
|
345
|
+
"ccc12": "12",
|
|
346
|
+
"ccc122": "122",
|
|
347
|
+
"ccc129": "129",
|
|
348
|
+
"ccc13": "13",
|
|
349
|
+
"ccc130": "130",
|
|
350
|
+
"ccc132": "132",
|
|
351
|
+
"ccc133": "133",
|
|
352
|
+
"ccc14": "14",
|
|
353
|
+
"ccc15": "15",
|
|
354
|
+
"ccc16": "16",
|
|
355
|
+
"ccc17": "17",
|
|
356
|
+
"ccc18": "18",
|
|
357
|
+
"ccc19": "19",
|
|
358
|
+
"ccc20": "20",
|
|
359
|
+
"ccc21": "21",
|
|
360
|
+
"ccc22": "22",
|
|
361
|
+
"ccc23": "23",
|
|
362
|
+
"ccc24": "24",
|
|
363
|
+
"ccc25": "25",
|
|
364
|
+
"ccc26": "26",
|
|
365
|
+
"ccc27": "27",
|
|
366
|
+
"ccc28": "28",
|
|
367
|
+
"ccc29": "29",
|
|
368
|
+
"ccc30": "30",
|
|
369
|
+
"ccc31": "31",
|
|
370
|
+
"ccc32": "32",
|
|
371
|
+
"ccc33": "33",
|
|
372
|
+
"ccc34": "34",
|
|
373
|
+
"ccc35": "35",
|
|
374
|
+
"ccc36": "36",
|
|
375
|
+
"ccc84": "84",
|
|
376
|
+
"ccc91": "91",
|
|
377
|
+
"da": "234",
|
|
378
|
+
"db": "233",
|
|
379
|
+
"doubleabove": "234",
|
|
380
|
+
"doublebelow": "233",
|
|
381
|
+
"hanr": "6",
|
|
382
|
+
"hanreading": "6",
|
|
383
|
+
"iotasubscript": "240",
|
|
384
|
+
"is": "240",
|
|
385
|
+
"kanavoicing": "8",
|
|
386
|
+
"kv": "8",
|
|
387
|
+
"l": "224",
|
|
388
|
+
"left": "224",
|
|
389
|
+
"nk": "7",
|
|
390
|
+
"notreordered": "0",
|
|
391
|
+
"nr": "0",
|
|
392
|
+
"nukta": "7",
|
|
393
|
+
"ov": "1",
|
|
394
|
+
"overlay": "1",
|
|
395
|
+
"r": "226",
|
|
396
|
+
"right": "226",
|
|
397
|
+
"virama": "9",
|
|
398
|
+
"vr": "9"
|
|
399
|
+
},
|
|
400
|
+
"decompositiontype": {
|
|
401
|
+
"can": "canonical",
|
|
402
|
+
"com": "compat",
|
|
403
|
+
"enc": "circle",
|
|
404
|
+
"fin": "final",
|
|
405
|
+
"fra": "fraction",
|
|
406
|
+
"init": "initial",
|
|
407
|
+
"iso": "isolated",
|
|
408
|
+
"med": "medial",
|
|
409
|
+
"nar": "narrow",
|
|
410
|
+
"nb": "nobreak",
|
|
411
|
+
"sml": "small",
|
|
412
|
+
"sqr": "square",
|
|
413
|
+
"sup": "super",
|
|
414
|
+
"vert": "vertical"
|
|
415
|
+
},
|
|
416
|
+
"eastasianwidth": {
|
|
417
|
+
"ambiguous": "a",
|
|
418
|
+
"fullwidth": "f",
|
|
419
|
+
"halfwidth": "h",
|
|
420
|
+
"narrow": "na",
|
|
421
|
+
"neutral": "n",
|
|
422
|
+
"wide": "w"
|
|
423
|
+
},
|
|
424
|
+
"generalcategory": {
|
|
425
|
+
"casedletter": "lc",
|
|
426
|
+
"closepunctuation": "pe",
|
|
427
|
+
"cntrl": "cc",
|
|
428
|
+
"combiningmark": "m",
|
|
429
|
+
"connectorpunctuation": "pc",
|
|
430
|
+
"control": "cc",
|
|
431
|
+
"currencysymbol": "sc",
|
|
432
|
+
"dashpunctuation": "pd",
|
|
433
|
+
"decimalnumber": "nd",
|
|
434
|
+
"digit": "nd",
|
|
435
|
+
"enclosingmark": "me",
|
|
436
|
+
"finalpunctuation": "pf",
|
|
437
|
+
"format": "cf",
|
|
438
|
+
"initialpunctuation": "pi",
|
|
439
|
+
"letter": "l",
|
|
440
|
+
"letternumber": "nl",
|
|
441
|
+
"lineseparator": "zl",
|
|
442
|
+
"lowercaseletter": "ll",
|
|
443
|
+
"mark": "m",
|
|
444
|
+
"mathsymbol": "sm",
|
|
445
|
+
"modifierletter": "lm",
|
|
446
|
+
"modifiersymbol": "sk",
|
|
447
|
+
"nonspacingmark": "mn",
|
|
448
|
+
"number": "n",
|
|
449
|
+
"openpunctuation": "ps",
|
|
450
|
+
"other": "c",
|
|
451
|
+
"otherletter": "lo",
|
|
452
|
+
"othernumber": "no",
|
|
453
|
+
"otherpunctuation": "po",
|
|
454
|
+
"othersymbol": "so",
|
|
455
|
+
"paragraphseparator": "zp",
|
|
456
|
+
"privateuse": "co",
|
|
457
|
+
"punct": "p",
|
|
458
|
+
"punctuation": "p",
|
|
459
|
+
"separator": "z",
|
|
460
|
+
"spaceseparator": "zs",
|
|
461
|
+
"spacingmark": "mc",
|
|
462
|
+
"surrogate": "cs",
|
|
463
|
+
"symbol": "s",
|
|
464
|
+
"titlecaseletter": "lt",
|
|
465
|
+
"unassigned": "cn",
|
|
466
|
+
"uppercaseletter": "lu"
|
|
467
|
+
},
|
|
468
|
+
"graphemeclusterbreak": {
|
|
469
|
+
"cn": "control",
|
|
470
|
+
"eb": "ebase",
|
|
471
|
+
"ebg": "ebasegaz",
|
|
472
|
+
"em": "emodifier",
|
|
473
|
+
"ex": "extend",
|
|
474
|
+
"gaz": "glueafterzwj",
|
|
475
|
+
"pp": "prepend",
|
|
476
|
+
"ri": "regionalindicator",
|
|
477
|
+
"sm": "spacingmark",
|
|
478
|
+
"xx": "other"
|
|
479
|
+
},
|
|
480
|
+
"hangulsyllabletype": {
|
|
481
|
+
"leadingjamo": "l",
|
|
482
|
+
"lvsyllable": "lv",
|
|
483
|
+
"lvtsyllable": "lvt",
|
|
484
|
+
"notapplicable": "na",
|
|
485
|
+
"trailingjamo": "t",
|
|
486
|
+
"voweljamo": "v"
|
|
487
|
+
},
|
|
488
|
+
"indicpositionalcategory": {
|
|
489
|
+
},
|
|
490
|
+
"indicsyllabiccategory": {
|
|
491
|
+
},
|
|
492
|
+
"joininggroup": {
|
|
493
|
+
"hamzaonhehgoal": "tehmarbutagoal"
|
|
494
|
+
},
|
|
495
|
+
"joiningtype": {
|
|
496
|
+
"dualjoining": "d",
|
|
497
|
+
"joincausing": "c",
|
|
498
|
+
"leftjoining": "l",
|
|
499
|
+
"nonjoining": "u",
|
|
500
|
+
"rightjoining": "r",
|
|
501
|
+
"transparent": "t"
|
|
502
|
+
},
|
|
503
|
+
"linebreak": {
|
|
504
|
+
"aksara": "ak",
|
|
505
|
+
"aksaraprebase": "ap",
|
|
506
|
+
"aksarastart": "as",
|
|
507
|
+
"alphabetic": "al",
|
|
508
|
+
"ambiguous": "ai",
|
|
509
|
+
"breakafter": "ba",
|
|
510
|
+
"breakbefore": "bb",
|
|
511
|
+
"breakboth": "b2",
|
|
512
|
+
"breaksymbols": "sy",
|
|
513
|
+
"carriagereturn": "cr",
|
|
514
|
+
"closeparenthesis": "cp",
|
|
515
|
+
"closepunctuation": "cl",
|
|
516
|
+
"combiningmark": "cm",
|
|
517
|
+
"complexcontext": "sa",
|
|
518
|
+
"conditionaljapanesestarter": "cj",
|
|
519
|
+
"contingentbreak": "cb",
|
|
520
|
+
"ebase": "eb",
|
|
521
|
+
"emodifier": "em",
|
|
522
|
+
"exclamation": "ex",
|
|
523
|
+
"glue": "gl",
|
|
524
|
+
"hebrewletter": "hl",
|
|
525
|
+
"hyphen": "hy",
|
|
526
|
+
"ideographic": "id",
|
|
527
|
+
"infixnumeric": "is",
|
|
528
|
+
"inseparable": "in",
|
|
529
|
+
"inseperable": "in",
|
|
530
|
+
"linefeed": "lf",
|
|
531
|
+
"mandatorybreak": "bk",
|
|
532
|
+
"nextline": "nl",
|
|
533
|
+
"nonstarter": "ns",
|
|
534
|
+
"numeric": "nu",
|
|
535
|
+
"openpunctuation": "op",
|
|
536
|
+
"postfixnumeric": "po",
|
|
537
|
+
"prefixnumeric": "pr",
|
|
538
|
+
"quotation": "qu",
|
|
539
|
+
"regionalindicator": "ri",
|
|
540
|
+
"space": "sp",
|
|
541
|
+
"surrogate": "sg",
|
|
542
|
+
"unknown": "xx",
|
|
543
|
+
"virama": "vi",
|
|
544
|
+
"viramafinal": "vf",
|
|
545
|
+
"wordjoiner": "wj",
|
|
546
|
+
"zwspace": "zw"
|
|
547
|
+
},
|
|
548
|
+
"nfcquickcheck": {
|
|
549
|
+
"maybe": "m",
|
|
550
|
+
"no": "n",
|
|
551
|
+
"yes": "y"
|
|
552
|
+
},
|
|
553
|
+
"nfdquickcheck": {
|
|
554
|
+
"no": "n",
|
|
555
|
+
"yes": "y"
|
|
556
|
+
},
|
|
557
|
+
"nfkcquickcheck": {
|
|
558
|
+
"maybe": "m",
|
|
559
|
+
"no": "n",
|
|
560
|
+
"yes": "y"
|
|
561
|
+
},
|
|
562
|
+
"nfkdquickcheck": {
|
|
563
|
+
"no": "n",
|
|
564
|
+
"yes": "y"
|
|
565
|
+
},
|
|
566
|
+
"numerictype": {
|
|
567
|
+
"de": "decimal",
|
|
568
|
+
"di": "digit",
|
|
569
|
+
"nu": "numeric"
|
|
570
|
+
},
|
|
571
|
+
"numericvalue": {
|
|
572
|
+
},
|
|
573
|
+
"script": {
|
|
574
|
+
"adlm": "adlam",
|
|
575
|
+
"aghb": "caucasianalbanian",
|
|
576
|
+
"arab": "arabic",
|
|
577
|
+
"armi": "imperialaramaic",
|
|
578
|
+
"armn": "armenian",
|
|
579
|
+
"avst": "avestan",
|
|
580
|
+
"bali": "balinese",
|
|
581
|
+
"bamu": "bamum",
|
|
582
|
+
"bass": "bassavah",
|
|
583
|
+
"batk": "batak",
|
|
584
|
+
"beng": "bengali",
|
|
585
|
+
"bhks": "bhaiksuki",
|
|
586
|
+
"bopo": "bopomofo",
|
|
587
|
+
"brah": "brahmi",
|
|
588
|
+
"brai": "braille",
|
|
589
|
+
"bugi": "buginese",
|
|
590
|
+
"buhd": "buhid",
|
|
591
|
+
"cakm": "chakma",
|
|
592
|
+
"cans": "canadianaboriginal",
|
|
593
|
+
"cari": "carian",
|
|
594
|
+
"cher": "cherokee",
|
|
595
|
+
"chrs": "chorasmian",
|
|
596
|
+
"copt": "coptic",
|
|
597
|
+
"cpmn": "cyprominoan",
|
|
598
|
+
"cprt": "cypriot",
|
|
599
|
+
"cyrl": "cyrillic",
|
|
600
|
+
"deva": "devanagari",
|
|
601
|
+
"diak": "divesakuru",
|
|
602
|
+
"dogr": "dogra",
|
|
603
|
+
"dsrt": "deseret",
|
|
604
|
+
"dupl": "duployan",
|
|
605
|
+
"egyp": "egyptianhieroglyphs",
|
|
606
|
+
"elba": "elbasan",
|
|
607
|
+
"elym": "elymaic",
|
|
608
|
+
"ethi": "ethiopic",
|
|
609
|
+
"gara": "garay",
|
|
610
|
+
"geor": "georgian",
|
|
611
|
+
"glag": "glagolitic",
|
|
612
|
+
"gong": "gunjalagondi",
|
|
613
|
+
"gonm": "masaramgondi",
|
|
614
|
+
"goth": "gothic",
|
|
615
|
+
"gran": "grantha",
|
|
616
|
+
"grek": "greek",
|
|
617
|
+
"gujr": "gujarati",
|
|
618
|
+
"gukh": "gurungkhema",
|
|
619
|
+
"guru": "gurmukhi",
|
|
620
|
+
"hang": "hangul",
|
|
621
|
+
"hani": "han",
|
|
622
|
+
"hano": "hanunoo",
|
|
623
|
+
"hatr": "hatran",
|
|
624
|
+
"hebr": "hebrew",
|
|
625
|
+
"hira": "hiragana",
|
|
626
|
+
"hluw": "anatolianhieroglyphs",
|
|
627
|
+
"hmng": "pahawhhmong",
|
|
628
|
+
"hmnp": "nyiakengpuachuehmong",
|
|
629
|
+
"hrkt": "katakanaorhiragana",
|
|
630
|
+
"hung": "oldhungarian",
|
|
631
|
+
"ital": "olditalic",
|
|
632
|
+
"java": "javanese",
|
|
633
|
+
"kali": "kayahli",
|
|
634
|
+
"kana": "katakana",
|
|
635
|
+
"khar": "kharoshthi",
|
|
636
|
+
"khmr": "khmer",
|
|
637
|
+
"khoj": "khojki",
|
|
638
|
+
"kits": "khitansmallscript",
|
|
639
|
+
"knda": "kannada",
|
|
640
|
+
"krai": "kiratrai",
|
|
641
|
+
"kthi": "kaithi",
|
|
642
|
+
"lana": "taitham",
|
|
643
|
+
"laoo": "lao",
|
|
644
|
+
"latn": "latin",
|
|
645
|
+
"lepc": "lepcha",
|
|
646
|
+
"limb": "limbu",
|
|
647
|
+
"lina": "lineara",
|
|
648
|
+
"linb": "linearb",
|
|
649
|
+
"lyci": "lycian",
|
|
650
|
+
"lydi": "lydian",
|
|
651
|
+
"mahj": "mahajani",
|
|
652
|
+
"maka": "makasar",
|
|
653
|
+
"mand": "mandaic",
|
|
654
|
+
"mani": "manichaean",
|
|
655
|
+
"marc": "marchen",
|
|
656
|
+
"medf": "medefaidrin",
|
|
657
|
+
"mend": "mendekikakui",
|
|
658
|
+
"merc": "meroiticcursive",
|
|
659
|
+
"mero": "meroitichieroglyphs",
|
|
660
|
+
"mlym": "malayalam",
|
|
661
|
+
"mong": "mongolian",
|
|
662
|
+
"mroo": "mro",
|
|
663
|
+
"mtei": "meeteimayek",
|
|
664
|
+
"mult": "multani",
|
|
665
|
+
"mymr": "myanmar",
|
|
666
|
+
"nagm": "nagmundari",
|
|
667
|
+
"nand": "nandinagari",
|
|
668
|
+
"narb": "oldnortharabian",
|
|
669
|
+
"nbat": "nabataean",
|
|
670
|
+
"nkoo": "nko",
|
|
671
|
+
"nshu": "nushu",
|
|
672
|
+
"ogam": "ogham",
|
|
673
|
+
"olck": "olchiki",
|
|
674
|
+
"onao": "olonal",
|
|
675
|
+
"orkh": "oldturkic",
|
|
676
|
+
"orya": "oriya",
|
|
677
|
+
"osge": "osage",
|
|
678
|
+
"osma": "osmanya",
|
|
679
|
+
"ougr": "olduyghur",
|
|
680
|
+
"palm": "palmyrene",
|
|
681
|
+
"pauc": "paucinhau",
|
|
682
|
+
"perm": "oldpermic",
|
|
683
|
+
"phag": "phagspa",
|
|
684
|
+
"phli": "inscriptionalpahlavi",
|
|
685
|
+
"phlp": "psalterpahlavi",
|
|
686
|
+
"phnx": "phoenician",
|
|
687
|
+
"plrd": "miao",
|
|
688
|
+
"prti": "inscriptionalparthian",
|
|
689
|
+
"qaac": "coptic",
|
|
690
|
+
"qaai": "inherited",
|
|
691
|
+
"rjng": "rejang",
|
|
692
|
+
"rohg": "hanifirohingya",
|
|
693
|
+
"runr": "runic",
|
|
694
|
+
"samr": "samaritan",
|
|
695
|
+
"sarb": "oldsoutharabian",
|
|
696
|
+
"saur": "saurashtra",
|
|
697
|
+
"sgnw": "signwriting",
|
|
698
|
+
"shaw": "shavian",
|
|
699
|
+
"shrd": "sharada",
|
|
700
|
+
"sidd": "siddham",
|
|
701
|
+
"sind": "khudawadi",
|
|
702
|
+
"sinh": "sinhala",
|
|
703
|
+
"sogd": "sogdian",
|
|
704
|
+
"sogo": "oldsogdian",
|
|
705
|
+
"sora": "sorasompeng",
|
|
706
|
+
"soyo": "soyombo",
|
|
707
|
+
"sund": "sundanese",
|
|
708
|
+
"sunu": "sunuwar",
|
|
709
|
+
"sylo": "sylotinagri",
|
|
710
|
+
"syrc": "syriac",
|
|
711
|
+
"tagb": "tagbanwa",
|
|
712
|
+
"takr": "takri",
|
|
713
|
+
"tale": "taile",
|
|
714
|
+
"talu": "newtailue",
|
|
715
|
+
"taml": "tamil",
|
|
716
|
+
"tang": "tangut",
|
|
717
|
+
"tavt": "taiviet",
|
|
718
|
+
"telu": "telugu",
|
|
719
|
+
"tfng": "tifinagh",
|
|
720
|
+
"tglg": "tagalog",
|
|
721
|
+
"thaa": "thaana",
|
|
722
|
+
"tibt": "tibetan",
|
|
723
|
+
"tirh": "tirhuta",
|
|
724
|
+
"tnsa": "tangsa",
|
|
725
|
+
"todr": "todhri",
|
|
726
|
+
"tutg": "tulutigalari",
|
|
727
|
+
"ugar": "ugaritic",
|
|
728
|
+
"vaii": "vai",
|
|
729
|
+
"vith": "vithkuqi",
|
|
730
|
+
"wara": "warangciti",
|
|
731
|
+
"wcho": "wancho",
|
|
732
|
+
"xpeo": "oldpersian",
|
|
733
|
+
"xsux": "cuneiform",
|
|
734
|
+
"yezi": "yezidi",
|
|
735
|
+
"yiii": "yi",
|
|
736
|
+
"zanb": "zanabazarsquare",
|
|
737
|
+
"zinh": "inherited",
|
|
738
|
+
"zyyy": "common",
|
|
739
|
+
"zzzz": "unknown"
|
|
740
|
+
},
|
|
741
|
+
"scriptextensions": {
|
|
742
|
+
},
|
|
743
|
+
"sentencebreak": {
|
|
744
|
+
"at": "aterm",
|
|
745
|
+
"cl": "close",
|
|
746
|
+
"ex": "extend",
|
|
747
|
+
"fo": "format",
|
|
748
|
+
"le": "oletter",
|
|
749
|
+
"lo": "lower",
|
|
750
|
+
"nu": "numeric",
|
|
751
|
+
"sc": "scontinue",
|
|
752
|
+
"se": "sep",
|
|
753
|
+
"st": "sterm",
|
|
754
|
+
"up": "upper",
|
|
755
|
+
"xx": "other"
|
|
756
|
+
},
|
|
757
|
+
"verticalorientation": {
|
|
758
|
+
"rotated": "r",
|
|
759
|
+
"transformedrotated": "tr",
|
|
760
|
+
"transformedupright": "tu",
|
|
761
|
+
"upright": "u"
|
|
762
|
+
},
|
|
763
|
+
"wordbreak": {
|
|
764
|
+
"dq": "doublequote",
|
|
765
|
+
"eb": "ebase",
|
|
766
|
+
"ebg": "ebasegaz",
|
|
767
|
+
"em": "emodifier",
|
|
768
|
+
"ex": "extendnumlet",
|
|
769
|
+
"fo": "format",
|
|
770
|
+
"gaz": "glueafterzwj",
|
|
771
|
+
"hl": "hebrewletter",
|
|
772
|
+
"ka": "katakana",
|
|
773
|
+
"le": "aletter",
|
|
774
|
+
"mb": "midnumlet",
|
|
775
|
+
"ml": "midletter",
|
|
776
|
+
"mn": "midnum",
|
|
777
|
+
"nl": "newline",
|
|
778
|
+
"nu": "numeric",
|
|
779
|
+
"ri": "regionalindicator",
|
|
780
|
+
"sq": "singlequote",
|
|
781
|
+
"xx": "other"
|
|
782
|
+
}
|
|
783
|
+
}
|