regexp_parser 2.7.0 → 2.12.0
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.
- checksums.yaml +4 -4
- data/Gemfile +7 -5
- data/LICENSE +1 -1
- data/Rakefile +5 -3
- data/lib/regexp_parser/error.rb +2 -0
- data/lib/regexp_parser/expression/base.rb +2 -7
- data/lib/regexp_parser/expression/classes/alternation.rb +3 -1
- data/lib/regexp_parser/expression/classes/anchor.rb +2 -0
- data/lib/regexp_parser/expression/classes/backreference.rb +7 -26
- data/lib/regexp_parser/expression/classes/character_set/intersection.rb +2 -0
- data/lib/regexp_parser/expression/classes/character_set/range.rb +4 -7
- data/lib/regexp_parser/expression/classes/character_set.rb +6 -8
- data/lib/regexp_parser/expression/classes/character_type.rb +2 -0
- data/lib/regexp_parser/expression/classes/conditional.rb +4 -28
- data/lib/regexp_parser/expression/classes/escape_sequence.rb +29 -96
- data/lib/regexp_parser/expression/classes/free_space.rb +5 -1
- data/lib/regexp_parser/expression/classes/group.rb +2 -22
- data/lib/regexp_parser/expression/classes/keep.rb +3 -1
- data/lib/regexp_parser/expression/classes/literal.rb +2 -0
- data/lib/regexp_parser/expression/classes/posix_class.rb +7 -5
- data/lib/regexp_parser/expression/classes/root.rb +2 -0
- data/lib/regexp_parser/expression/classes/unicode_property.rb +13 -11
- data/lib/regexp_parser/expression/methods/construct.rb +4 -4
- data/lib/regexp_parser/expression/methods/escape_sequence_char.rb +7 -0
- data/lib/regexp_parser/expression/methods/escape_sequence_codepoint.rb +76 -0
- data/lib/regexp_parser/expression/methods/human_name.rb +2 -0
- data/lib/regexp_parser/expression/methods/match.rb +2 -0
- data/lib/regexp_parser/expression/methods/match_length.rb +2 -0
- data/lib/regexp_parser/expression/methods/negative.rb +22 -0
- data/lib/regexp_parser/expression/methods/options.rb +2 -0
- data/lib/regexp_parser/expression/methods/parts.rb +25 -0
- data/lib/regexp_parser/expression/methods/printing.rb +28 -0
- data/lib/regexp_parser/expression/methods/referenced_expressions.rb +30 -0
- data/lib/regexp_parser/expression/methods/strfregexp.rb +2 -0
- data/lib/regexp_parser/expression/methods/tests.rb +42 -3
- data/lib/regexp_parser/expression/methods/traverse.rb +35 -20
- data/lib/regexp_parser/expression/quantifier.rb +33 -18
- data/lib/regexp_parser/expression/sequence.rb +7 -9
- data/lib/regexp_parser/expression/sequence_operation.rb +6 -9
- data/lib/regexp_parser/expression/shared.rb +40 -24
- data/lib/regexp_parser/expression/subexpression.rb +22 -18
- data/lib/regexp_parser/expression.rb +39 -31
- data/lib/regexp_parser/lexer.rb +17 -7
- data/lib/regexp_parser/parser.rb +101 -95
- data/lib/regexp_parser/scanner/errors/premature_end_error.rb +10 -0
- data/lib/regexp_parser/scanner/errors/scanner_error.rb +8 -0
- data/lib/regexp_parser/scanner/errors/validation_error.rb +65 -0
- data/lib/regexp_parser/scanner/properties/long.csv +61 -0
- data/lib/regexp_parser/scanner/properties/short.csv +15 -0
- data/lib/regexp_parser/scanner/property.rl +1 -1
- data/lib/regexp_parser/scanner/scanner.rl +90 -140
- data/lib/regexp_parser/scanner.rb +1336 -1450
- data/lib/regexp_parser/syntax/any.rb +2 -0
- data/lib/regexp_parser/syntax/base.rb +2 -0
- data/lib/regexp_parser/syntax/token/anchor.rb +5 -3
- data/lib/regexp_parser/syntax/token/assertion.rb +4 -2
- data/lib/regexp_parser/syntax/token/backreference.rb +11 -6
- data/lib/regexp_parser/syntax/token/character_set.rb +6 -1
- data/lib/regexp_parser/syntax/token/character_type.rb +6 -4
- data/lib/regexp_parser/syntax/token/conditional.rb +5 -3
- data/lib/regexp_parser/syntax/token/escape.rb +12 -8
- data/lib/regexp_parser/syntax/token/group.rb +8 -6
- data/lib/regexp_parser/syntax/token/keep.rb +3 -1
- data/lib/regexp_parser/syntax/token/meta.rb +11 -2
- data/lib/regexp_parser/syntax/token/posix_class.rb +4 -2
- data/lib/regexp_parser/syntax/token/quantifier.rb +8 -6
- data/lib/regexp_parser/syntax/token/unicode_property.rb +164 -70
- data/lib/regexp_parser/syntax/token/virtual.rb +13 -0
- data/lib/regexp_parser/syntax/token.rb +18 -16
- data/lib/regexp_parser/syntax/version_lookup.rb +4 -2
- data/lib/regexp_parser/syntax/versions/1.8.6.rb +2 -0
- data/lib/regexp_parser/syntax/versions/1.9.1.rb +2 -0
- data/lib/regexp_parser/syntax/versions/1.9.3.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.0.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.2.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.3.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.4.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.4.1.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.5.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.6.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.6.2.rb +2 -0
- data/lib/regexp_parser/syntax/versions/2.6.3.rb +2 -0
- data/lib/regexp_parser/syntax/versions/3.1.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/3.2.0.rb +2 -0
- data/lib/regexp_parser/syntax/versions/3.5.0.rb +4 -0
- data/lib/regexp_parser/syntax/versions/4.0.0.rb +4 -0
- data/lib/regexp_parser/syntax/versions.rb +3 -1
- data/lib/regexp_parser/syntax.rb +3 -1
- data/lib/regexp_parser/token.rb +2 -0
- data/lib/regexp_parser/version.rb +3 -1
- data/lib/regexp_parser.rb +8 -6
- data/regexp_parser.gemspec +7 -5
- metadata +19 -11
- data/CHANGELOG.md +0 -632
- data/README.md +0 -503
|
@@ -7,6 +7,10 @@ age=12.0,age=12.0
|
|
|
7
7
|
age=12.1,age=12.1
|
|
8
8
|
age=13.0,age=13.0
|
|
9
9
|
age=14.0,age=14.0
|
|
10
|
+
age=15.0,age=15.0
|
|
11
|
+
age=15.1,age=15.1
|
|
12
|
+
age=16.0,age=16.0
|
|
13
|
+
age=17.0,age=17.0
|
|
10
14
|
age=2.0,age=2.0
|
|
11
15
|
age=2.1,age=2.1
|
|
12
16
|
age=3.0,age=3.0
|
|
@@ -41,6 +45,7 @@ bamum,bamum
|
|
|
41
45
|
bassavah,bassa_vah
|
|
42
46
|
batak,batak
|
|
43
47
|
bengali,bengali
|
|
48
|
+
beriaerfe,beria_erfe
|
|
44
49
|
bhaiksuki,bhaiksuki
|
|
45
50
|
bidicontrol,bidi_control
|
|
46
51
|
blank,blank
|
|
@@ -97,21 +102,37 @@ emojimodifierbase,emoji_modifier_base
|
|
|
97
102
|
emojipresentation,emoji_presentation
|
|
98
103
|
enclosingmark,enclosing_mark
|
|
99
104
|
ethiopic,ethiopic
|
|
105
|
+
extendedpictographic,extended_pictographic
|
|
100
106
|
extender,extender
|
|
101
107
|
finalpunctuation,final_punctuation
|
|
102
108
|
format,format
|
|
109
|
+
garay,garay
|
|
103
110
|
georgian,georgian
|
|
104
111
|
glagolitic,glagolitic
|
|
105
112
|
gothic,gothic
|
|
106
113
|
grantha,grantha
|
|
107
114
|
graph,graph
|
|
108
115
|
graphemebase,grapheme_base
|
|
116
|
+
graphemeclusterbreak=control,grapheme_cluster_break=control
|
|
117
|
+
graphemeclusterbreak=cr,grapheme_cluster_break=cr
|
|
118
|
+
graphemeclusterbreak=extend,grapheme_cluster_break=extend
|
|
119
|
+
graphemeclusterbreak=l,grapheme_cluster_break=l
|
|
120
|
+
graphemeclusterbreak=lf,grapheme_cluster_break=lf
|
|
121
|
+
graphemeclusterbreak=lv,grapheme_cluster_break=lv
|
|
122
|
+
graphemeclusterbreak=lvt,grapheme_cluster_break=lvt
|
|
123
|
+
graphemeclusterbreak=prepend,grapheme_cluster_break=prepend
|
|
124
|
+
graphemeclusterbreak=regionalindicator,grapheme_cluster_break=regional_indicator
|
|
125
|
+
graphemeclusterbreak=spacingmark,grapheme_cluster_break=spacingmark
|
|
126
|
+
graphemeclusterbreak=t,grapheme_cluster_break=t
|
|
127
|
+
graphemeclusterbreak=v,grapheme_cluster_break=v
|
|
128
|
+
graphemeclusterbreak=zwj,grapheme_cluster_break=zwj
|
|
109
129
|
graphemeextend,grapheme_extend
|
|
110
130
|
graphemelink,grapheme_link
|
|
111
131
|
greek,greek
|
|
112
132
|
gujarati,gujarati
|
|
113
133
|
gunjalagondi,gunjala_gondi
|
|
114
134
|
gurmukhi,gurmukhi
|
|
135
|
+
gurungkhema,gurung_khema
|
|
115
136
|
han,han
|
|
116
137
|
hangul,hangul
|
|
117
138
|
hanifirohingya,hanifi_rohingya
|
|
@@ -121,11 +142,14 @@ hebrew,hebrew
|
|
|
121
142
|
hexdigit,hex_digit
|
|
122
143
|
hiragana,hiragana
|
|
123
144
|
hyphen,hyphen
|
|
145
|
+
idcompatmathcontinue,id_compat_math_continue
|
|
146
|
+
idcompatmathstart,id_compat_math_start
|
|
124
147
|
idcontinue,id_continue
|
|
125
148
|
ideographic,ideographic
|
|
126
149
|
idsbinaryoperator,ids_binary_operator
|
|
127
150
|
idstart,id_start
|
|
128
151
|
idstrinaryoperator,ids_trinary_operator
|
|
152
|
+
idsunaryoperator,ids_unary_operator
|
|
129
153
|
imperialaramaic,imperial_aramaic
|
|
130
154
|
inadlam,in_adlam
|
|
131
155
|
inaegeannumbers,in_aegean_numbers
|
|
@@ -139,6 +163,7 @@ inancientsymbols,in_ancient_symbols
|
|
|
139
163
|
inarabic,in_arabic
|
|
140
164
|
inarabicextendeda,in_arabic_extended_a
|
|
141
165
|
inarabicextendedb,in_arabic_extended_b
|
|
166
|
+
inarabicextendedc,in_arabic_extended_c
|
|
142
167
|
inarabicmathematicalalphabeticsymbols,in_arabic_mathematical_alphabetic_symbols
|
|
143
168
|
inarabicpresentationformsa,in_arabic_presentation_forms_a
|
|
144
169
|
inarabicpresentationformsb,in_arabic_presentation_forms_b
|
|
@@ -153,6 +178,7 @@ inbasiclatin,in_basic_latin
|
|
|
153
178
|
inbassavah,in_bassa_vah
|
|
154
179
|
inbatak,in_batak
|
|
155
180
|
inbengali,in_bengali
|
|
181
|
+
inberiaerfe,in_beria_erfe
|
|
156
182
|
inbhaiksuki,in_bhaiksuki
|
|
157
183
|
inblockelements,in_block_elements
|
|
158
184
|
inbopomofo,in_bopomofo
|
|
@@ -186,6 +212,9 @@ incjkunifiedideographsextensiond,in_cjk_unified_ideographs_extension_d
|
|
|
186
212
|
incjkunifiedideographsextensione,in_cjk_unified_ideographs_extension_e
|
|
187
213
|
incjkunifiedideographsextensionf,in_cjk_unified_ideographs_extension_f
|
|
188
214
|
incjkunifiedideographsextensiong,in_cjk_unified_ideographs_extension_g
|
|
215
|
+
incjkunifiedideographsextensionh,in_cjk_unified_ideographs_extension_h
|
|
216
|
+
incjkunifiedideographsextensioni,in_cjk_unified_ideographs_extension_i
|
|
217
|
+
incjkunifiedideographsextensionj,in_cjk_unified_ideographs_extension_j
|
|
189
218
|
incombiningdiacriticalmarks,in_combining_diacritical_marks
|
|
190
219
|
incombiningdiacriticalmarksextended,in_combining_diacritical_marks_extended
|
|
191
220
|
incombiningdiacriticalmarksforsymbols,in_combining_diacritical_marks_for_symbols
|
|
@@ -205,10 +234,12 @@ incyrillic,in_cyrillic
|
|
|
205
234
|
incyrillicextendeda,in_cyrillic_extended_a
|
|
206
235
|
incyrillicextendedb,in_cyrillic_extended_b
|
|
207
236
|
incyrillicextendedc,in_cyrillic_extended_c
|
|
237
|
+
incyrillicextendedd,in_cyrillic_extended_d
|
|
208
238
|
incyrillicsupplement,in_cyrillic_supplement
|
|
209
239
|
indeseret,in_deseret
|
|
210
240
|
indevanagari,in_devanagari
|
|
211
241
|
indevanagariextended,in_devanagari_extended
|
|
242
|
+
indevanagariextendeda,in_devanagari_extended_a
|
|
212
243
|
indingbats,in_dingbats
|
|
213
244
|
indivesakuru,in_dives_akuru
|
|
214
245
|
indogra,in_dogra
|
|
@@ -217,6 +248,7 @@ induployan,in_duployan
|
|
|
217
248
|
inearlydynasticcuneiform,in_early_dynastic_cuneiform
|
|
218
249
|
inegyptianhieroglyphformatcontrols,in_egyptian_hieroglyph_format_controls
|
|
219
250
|
inegyptianhieroglyphs,in_egyptian_hieroglyphs
|
|
251
|
+
inegyptianhieroglyphsextendeda,in_egyptian_hieroglyphs_extended_a
|
|
220
252
|
inelbasan,in_elbasan
|
|
221
253
|
inelymaic,in_elymaic
|
|
222
254
|
inemoticons,in_emoticons
|
|
@@ -229,6 +261,7 @@ inethiopicextended,in_ethiopic_extended
|
|
|
229
261
|
inethiopicextendeda,in_ethiopic_extended_a
|
|
230
262
|
inethiopicextendedb,in_ethiopic_extended_b
|
|
231
263
|
inethiopicsupplement,in_ethiopic_supplement
|
|
264
|
+
ingaray,in_garay
|
|
232
265
|
ingeneralpunctuation,in_general_punctuation
|
|
233
266
|
ingeometricshapes,in_geometric_shapes
|
|
234
267
|
ingeometricshapesextended,in_geometric_shapes_extended
|
|
@@ -244,6 +277,7 @@ ingreekextended,in_greek_extended
|
|
|
244
277
|
ingujarati,in_gujarati
|
|
245
278
|
ingunjalagondi,in_gunjala_gondi
|
|
246
279
|
ingurmukhi,in_gurmukhi
|
|
280
|
+
ingurungkhema,in_gurung_khema
|
|
247
281
|
inhalfwidthandfullwidthforms,in_halfwidth_and_fullwidth_forms
|
|
248
282
|
inhangulcompatibilityjamo,in_hangul_compatibility_jamo
|
|
249
283
|
inhanguljamo,in_hangul_jamo
|
|
@@ -268,6 +302,7 @@ inipaextensions,in_ipa_extensions
|
|
|
268
302
|
initialpunctuation,initial_punctuation
|
|
269
303
|
injavanese,in_javanese
|
|
270
304
|
inkaithi,in_kaithi
|
|
305
|
+
inkaktoviknumerals,in_kaktovik_numerals
|
|
271
306
|
inkanaextendeda,in_kana_extended_a
|
|
272
307
|
inkanaextendedb,in_kana_extended_b
|
|
273
308
|
inkanasupplement,in_kana_supplement
|
|
@@ -276,6 +311,7 @@ inkangxiradicals,in_kangxi_radicals
|
|
|
276
311
|
inkannada,in_kannada
|
|
277
312
|
inkatakana,in_katakana
|
|
278
313
|
inkatakanaphoneticextensions,in_katakana_phonetic_extensions
|
|
314
|
+
inkawi,in_kawi
|
|
279
315
|
inkayahli,in_kayah_li
|
|
280
316
|
inkharoshthi,in_kharoshthi
|
|
281
317
|
inkhitansmallscript,in_khitan_small_script
|
|
@@ -283,6 +319,7 @@ inkhmer,in_khmer
|
|
|
283
319
|
inkhmersymbols,in_khmer_symbols
|
|
284
320
|
inkhojki,in_khojki
|
|
285
321
|
inkhudawadi,in_khudawadi
|
|
322
|
+
inkiratrai,in_kirat_rai
|
|
286
323
|
inlao,in_lao
|
|
287
324
|
inlatin1supplement,in_latin_1_supplement
|
|
288
325
|
inlatinextendeda,in_latin_extended_a
|
|
@@ -327,6 +364,7 @@ inmiscellaneousmathematicalsymbolsb,in_miscellaneous_mathematical_symbols_b
|
|
|
327
364
|
inmiscellaneoussymbols,in_miscellaneous_symbols
|
|
328
365
|
inmiscellaneoussymbolsandarrows,in_miscellaneous_symbols_and_arrows
|
|
329
366
|
inmiscellaneoussymbolsandpictographs,in_miscellaneous_symbols_and_pictographs
|
|
367
|
+
inmiscellaneoussymbolssupplement,in_miscellaneous_symbols_supplement
|
|
330
368
|
inmiscellaneoustechnical,in_miscellaneous_technical
|
|
331
369
|
inmodi,in_modi
|
|
332
370
|
inmodifiertoneletters,in_modifier_tone_letters
|
|
@@ -338,7 +376,9 @@ inmusicalsymbols,in_musical_symbols
|
|
|
338
376
|
inmyanmar,in_myanmar
|
|
339
377
|
inmyanmarextendeda,in_myanmar_extended_a
|
|
340
378
|
inmyanmarextendedb,in_myanmar_extended_b
|
|
379
|
+
inmyanmarextendedc,in_myanmar_extended_c
|
|
341
380
|
innabataean,in_nabataean
|
|
381
|
+
innagmundari,in_nag_mundari
|
|
342
382
|
innandinagari,in_nandinagari
|
|
343
383
|
innewa,in_newa
|
|
344
384
|
innewtailue,in_new_tai_lue
|
|
@@ -358,6 +398,7 @@ inoldsogdian,in_old_sogdian
|
|
|
358
398
|
inoldsoutharabian,in_old_south_arabian
|
|
359
399
|
inoldturkic,in_old_turkic
|
|
360
400
|
inolduyghur,in_old_uyghur
|
|
401
|
+
inolonal,in_ol_onal
|
|
361
402
|
inopticalcharacterrecognition,in_optical_character_recognition
|
|
362
403
|
inoriya,in_oriya
|
|
363
404
|
inornamentaldingbats,in_ornamental_dingbats
|
|
@@ -383,9 +424,11 @@ insaurashtra,in_saurashtra
|
|
|
383
424
|
inscriptionalpahlavi,inscriptional_pahlavi
|
|
384
425
|
inscriptionalparthian,inscriptional_parthian
|
|
385
426
|
insharada,in_sharada
|
|
427
|
+
insharadasupplement,in_sharada_supplement
|
|
386
428
|
inshavian,in_shavian
|
|
387
429
|
inshorthandformatcontrols,in_shorthand_format_controls
|
|
388
430
|
insiddham,in_siddham
|
|
431
|
+
insidetic,in_sidetic
|
|
389
432
|
insinhala,in_sinhala
|
|
390
433
|
insinhalaarchaicnumbers,in_sinhala_archaic_numbers
|
|
391
434
|
insmallformvariants,in_small_form_variants
|
|
@@ -397,6 +440,7 @@ inspacingmodifierletters,in_spacing_modifier_letters
|
|
|
397
440
|
inspecials,in_specials
|
|
398
441
|
insundanese,in_sundanese
|
|
399
442
|
insundanesesupplement,in_sundanese_supplement
|
|
443
|
+
insunuwar,in_sunuwar
|
|
400
444
|
insuperscriptsandsubscripts,in_superscripts_and_subscripts
|
|
401
445
|
insupplementalarrowsa,in_supplemental_arrows_a
|
|
402
446
|
insupplementalarrowsb,in_supplemental_arrows_b
|
|
@@ -410,6 +454,7 @@ insuttonsignwriting,in_sutton_signwriting
|
|
|
410
454
|
insylotinagri,in_syloti_nagri
|
|
411
455
|
insymbolsandpictographsextendeda,in_symbols_and_pictographs_extended_a
|
|
412
456
|
insymbolsforlegacycomputing,in_symbols_for_legacy_computing
|
|
457
|
+
insymbolsforlegacycomputingsupplement,in_symbols_for_legacy_computing_supplement
|
|
413
458
|
insyriac,in_syriac
|
|
414
459
|
insyriacsupplement,in_syriac_supplement
|
|
415
460
|
intagalog,in_tagalog
|
|
@@ -419,12 +464,14 @@ intaile,in_tai_le
|
|
|
419
464
|
intaitham,in_tai_tham
|
|
420
465
|
intaiviet,in_tai_viet
|
|
421
466
|
intaixuanjingsymbols,in_tai_xuan_jing_symbols
|
|
467
|
+
intaiyo,in_tai_yo
|
|
422
468
|
intakri,in_takri
|
|
423
469
|
intamil,in_tamil
|
|
424
470
|
intamilsupplement,in_tamil_supplement
|
|
425
471
|
intangsa,in_tangsa
|
|
426
472
|
intangut,in_tangut
|
|
427
473
|
intangutcomponents,in_tangut_components
|
|
474
|
+
intangutcomponentssupplement,in_tangut_components_supplement
|
|
428
475
|
intangutsupplement,in_tangut_supplement
|
|
429
476
|
intelugu,in_telugu
|
|
430
477
|
inthaana,in_thaana
|
|
@@ -432,8 +479,11 @@ inthai,in_thai
|
|
|
432
479
|
intibetan,in_tibetan
|
|
433
480
|
intifinagh,in_tifinagh
|
|
434
481
|
intirhuta,in_tirhuta
|
|
482
|
+
intodhri,in_todhri
|
|
483
|
+
intolongsiki,in_tolong_siki
|
|
435
484
|
intoto,in_toto
|
|
436
485
|
intransportandmapsymbols,in_transport_and_map_symbols
|
|
486
|
+
intulutigalari,in_tulu_tigalari
|
|
437
487
|
inugaritic,in_ugaritic
|
|
438
488
|
inunifiedcanadianaboriginalsyllabics,in_unified_canadian_aboriginal_syllabics
|
|
439
489
|
inunifiedcanadianaboriginalsyllabicsextended,in_unified_canadian_aboriginal_syllabics_extended
|
|
@@ -457,12 +507,14 @@ joincontrol,join_control
|
|
|
457
507
|
kaithi,kaithi
|
|
458
508
|
kannada,kannada
|
|
459
509
|
katakana,katakana
|
|
510
|
+
kawi,kawi
|
|
460
511
|
kayahli,kayah_li
|
|
461
512
|
kharoshthi,kharoshthi
|
|
462
513
|
khitansmallscript,khitan_small_script
|
|
463
514
|
khmer,khmer
|
|
464
515
|
khojki,khojki
|
|
465
516
|
khudawadi,khudawadi
|
|
517
|
+
kiratrai,kirat_rai
|
|
466
518
|
lao,lao
|
|
467
519
|
latin,latin
|
|
468
520
|
lepcha,lepcha
|
|
@@ -496,6 +548,7 @@ meroiticcursive,meroitic_cursive
|
|
|
496
548
|
meroitichieroglyphs,meroitic_hieroglyphs
|
|
497
549
|
miao,miao
|
|
498
550
|
modi,modi
|
|
551
|
+
modifiercombiningmark,modifier_combining_mark
|
|
499
552
|
modifierletter,modifier_letter
|
|
500
553
|
modifiersymbol,modifier_symbol
|
|
501
554
|
mongolian,mongolian
|
|
@@ -503,6 +556,7 @@ mro,mro
|
|
|
503
556
|
multani,multani
|
|
504
557
|
myanmar,myanmar
|
|
505
558
|
nabataean,nabataean
|
|
559
|
+
nagmundari,nag_mundari
|
|
506
560
|
nandinagari,nandinagari
|
|
507
561
|
newa,newa
|
|
508
562
|
newline,newline
|
|
@@ -524,6 +578,7 @@ oldsogdian,old_sogdian
|
|
|
524
578
|
oldsoutharabian,old_south_arabian
|
|
525
579
|
oldturkic,old_turkic
|
|
526
580
|
olduyghur,old_uyghur
|
|
581
|
+
olonal,ol_onal
|
|
527
582
|
openpunctuation,open_punctuation
|
|
528
583
|
oriya,oriya
|
|
529
584
|
osage,osage
|
|
@@ -567,6 +622,7 @@ separator,separator
|
|
|
567
622
|
sharada,sharada
|
|
568
623
|
shavian,shavian
|
|
569
624
|
siddham,siddham
|
|
625
|
+
sidetic,sidetic
|
|
570
626
|
signwriting,signwriting
|
|
571
627
|
sinhala,sinhala
|
|
572
628
|
softdotted,soft_dotted
|
|
@@ -577,6 +633,7 @@ space,space
|
|
|
577
633
|
spaceseparator,space_separator
|
|
578
634
|
spacingmark,spacing_mark
|
|
579
635
|
sundanese,sundanese
|
|
636
|
+
sunuwar,sunuwar
|
|
580
637
|
surrogate,surrogate
|
|
581
638
|
sylotinagri,syloti_nagri
|
|
582
639
|
symbol,symbol
|
|
@@ -586,6 +643,7 @@ tagbanwa,tagbanwa
|
|
|
586
643
|
taile,tai_le
|
|
587
644
|
taitham,tai_tham
|
|
588
645
|
taiviet,tai_viet
|
|
646
|
+
taiyo,tai_yo
|
|
589
647
|
takri,takri
|
|
590
648
|
tamil,tamil
|
|
591
649
|
tangsa,tangsa
|
|
@@ -598,7 +656,10 @@ tibetan,tibetan
|
|
|
598
656
|
tifinagh,tifinagh
|
|
599
657
|
tirhuta,tirhuta
|
|
600
658
|
titlecaseletter,titlecase_letter
|
|
659
|
+
todhri,todhri
|
|
660
|
+
tolongsiki,tolong_siki
|
|
601
661
|
toto,toto
|
|
662
|
+
tulutigalari,tulu_tigalari
|
|
602
663
|
ugaritic,ugaritic
|
|
603
664
|
unassigned,unassigned
|
|
604
665
|
unifiedideograph,unified_ideograph
|
|
@@ -11,6 +11,7 @@ bamu,bamum
|
|
|
11
11
|
bass,bassa_vah
|
|
12
12
|
batk,batak
|
|
13
13
|
beng,bengali
|
|
14
|
+
berf,beria_erfe
|
|
14
15
|
bhks,bhaiksuki
|
|
15
16
|
bidic,bidi_control
|
|
16
17
|
bopo,bopomofo
|
|
@@ -57,6 +58,8 @@ emod,emoji_modifier
|
|
|
57
58
|
epres,emoji_presentation
|
|
58
59
|
ethi,ethiopic
|
|
59
60
|
ext,extender
|
|
61
|
+
extpict,extended_pictographic
|
|
62
|
+
gara,garay
|
|
60
63
|
geor,georgian
|
|
61
64
|
glag,glagolitic
|
|
62
65
|
gong,gunjala_gondi
|
|
@@ -68,6 +71,7 @@ grek,greek
|
|
|
68
71
|
grext,grapheme_extend
|
|
69
72
|
grlink,grapheme_link
|
|
70
73
|
gujr,gujarati
|
|
74
|
+
gukh,gurung_khema
|
|
71
75
|
guru,gurmukhi
|
|
72
76
|
hang,hangul
|
|
73
77
|
hani,han
|
|
@@ -85,6 +89,7 @@ ideo,ideographic
|
|
|
85
89
|
ids,id_start
|
|
86
90
|
idsb,ids_binary_operator
|
|
87
91
|
idst,ids_trinary_operator
|
|
92
|
+
idsu,ids_unary_operator
|
|
88
93
|
ital,old_italic
|
|
89
94
|
java,javanese
|
|
90
95
|
joinc,join_control
|
|
@@ -95,6 +100,7 @@ khmr,khmer
|
|
|
95
100
|
khoj,khojki
|
|
96
101
|
kits,khitan_small_script
|
|
97
102
|
knda,kannada
|
|
103
|
+
krai,kirat_rai
|
|
98
104
|
kthi,kaithi
|
|
99
105
|
l,letter
|
|
100
106
|
lana,tai_tham
|
|
@@ -120,6 +126,7 @@ mand,mandaic
|
|
|
120
126
|
mani,manichaean
|
|
121
127
|
marc,marchen
|
|
122
128
|
mc,spacing_mark
|
|
129
|
+
mcm,modifier_combining_mark
|
|
123
130
|
me,enclosing_mark
|
|
124
131
|
medf,medefaidrin
|
|
125
132
|
mend,mende_kikakui
|
|
@@ -133,6 +140,7 @@ mtei,meetei_mayek
|
|
|
133
140
|
mult,multani
|
|
134
141
|
mymr,myanmar
|
|
135
142
|
n,number
|
|
143
|
+
nagm,nag_mundari
|
|
136
144
|
nand,nandinagari
|
|
137
145
|
narb,old_north_arabian
|
|
138
146
|
nbat,nabataean
|
|
@@ -151,6 +159,7 @@ oids,other_id_start
|
|
|
151
159
|
olck,ol_chiki
|
|
152
160
|
olower,other_lowercase
|
|
153
161
|
omath,other_math
|
|
162
|
+
onao,ol_onal
|
|
154
163
|
orkh,old_turkic
|
|
155
164
|
orya,oriya
|
|
156
165
|
osge,osage
|
|
@@ -194,6 +203,7 @@ sgnw,signwriting
|
|
|
194
203
|
shaw,shavian
|
|
195
204
|
shrd,sharada
|
|
196
205
|
sidd,siddham
|
|
206
|
+
sidt,sidetic
|
|
197
207
|
sind,khudawadi
|
|
198
208
|
sinh,sinhala
|
|
199
209
|
sk,modifier_symbol
|
|
@@ -205,6 +215,7 @@ sora,sora_sompeng
|
|
|
205
215
|
soyo,soyombo
|
|
206
216
|
sterm,sentence_terminal
|
|
207
217
|
sund,sundanese
|
|
218
|
+
sunu,sunuwar
|
|
208
219
|
sylo,syloti_nagri
|
|
209
220
|
syrc,syriac
|
|
210
221
|
tagb,tagbanwa
|
|
@@ -214,6 +225,7 @@ talu,new_tai_lue
|
|
|
214
225
|
taml,tamil
|
|
215
226
|
tang,tangut
|
|
216
227
|
tavt,tai_viet
|
|
228
|
+
tayo,tai_yo
|
|
217
229
|
telu,telugu
|
|
218
230
|
term,terminal_punctuation
|
|
219
231
|
tfng,tifinagh
|
|
@@ -222,6 +234,9 @@ thaa,thaana
|
|
|
222
234
|
tibt,tibetan
|
|
223
235
|
tirh,tirhuta
|
|
224
236
|
tnsa,tangsa
|
|
237
|
+
todr,todhri
|
|
238
|
+
tols,tolong_siki
|
|
239
|
+
tutg,tulu_tigalari
|
|
225
240
|
ugar,ugaritic
|
|
226
241
|
uideo,unified_ideograph
|
|
227
242
|
vaii,vai
|
|
@@ -20,7 +20,7 @@
|
|
|
20
20
|
name = text[3..-2].gsub(/[\^\s_\-]/, '').downcase
|
|
21
21
|
|
|
22
22
|
token = self.class.short_prop_map[name] || self.class.long_prop_map[name]
|
|
23
|
-
|
|
23
|
+
raise ValidationError.for(:property, name) unless token
|
|
24
24
|
|
|
25
25
|
self.emit(type, token.to_sym, text)
|
|
26
26
|
|