regexp_parser 2.1.1 → 2.5.0

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.
Files changed (154) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +94 -6
  3. data/Gemfile +2 -1
  4. data/LICENSE +1 -1
  5. data/README.md +40 -30
  6. data/Rakefile +6 -70
  7. data/lib/regexp_parser/error.rb +1 -1
  8. data/lib/regexp_parser/expression/base.rb +75 -0
  9. data/lib/regexp_parser/expression/classes/anchor.rb +0 -2
  10. data/lib/regexp_parser/expression/classes/{backref.rb → backreference.rb} +1 -0
  11. data/lib/regexp_parser/expression/classes/{set → character_set}/intersection.rb +0 -0
  12. data/lib/regexp_parser/expression/classes/{set → character_set}/range.rb +2 -2
  13. data/lib/regexp_parser/expression/classes/{set.rb → character_set.rb} +2 -2
  14. data/lib/regexp_parser/expression/classes/{type.rb → character_type.rb} +0 -2
  15. data/lib/regexp_parser/expression/classes/conditional.rb +2 -2
  16. data/lib/regexp_parser/expression/classes/{escape.rb → escape_sequence.rb} +13 -7
  17. data/lib/regexp_parser/expression/classes/free_space.rb +1 -3
  18. data/lib/regexp_parser/expression/classes/group.rb +6 -6
  19. data/lib/regexp_parser/expression/classes/keep.rb +2 -0
  20. data/lib/regexp_parser/expression/classes/literal.rb +1 -5
  21. data/lib/regexp_parser/expression/classes/root.rb +3 -6
  22. data/lib/regexp_parser/expression/classes/{property.rb → unicode_property.rb} +1 -2
  23. data/lib/regexp_parser/expression/methods/construct.rb +43 -0
  24. data/lib/regexp_parser/expression/methods/match_length.rb +1 -1
  25. data/lib/regexp_parser/expression/methods/strfregexp.rb +1 -1
  26. data/lib/regexp_parser/expression/methods/tests.rb +10 -1
  27. data/lib/regexp_parser/expression/quantifier.rb +41 -23
  28. data/lib/regexp_parser/expression/sequence.rb +9 -24
  29. data/lib/regexp_parser/expression/sequence_operation.rb +2 -2
  30. data/lib/regexp_parser/expression/shared.rb +85 -0
  31. data/lib/regexp_parser/expression/subexpression.rb +11 -8
  32. data/lib/regexp_parser/expression.rb +10 -132
  33. data/lib/regexp_parser/lexer.rb +8 -6
  34. data/lib/regexp_parser/parser.rb +21 -72
  35. data/lib/regexp_parser/scanner/properties/long.csv +622 -0
  36. data/lib/regexp_parser/scanner/properties/short.csv +246 -0
  37. data/lib/regexp_parser/scanner/property.rl +1 -1
  38. data/lib/regexp_parser/scanner/scanner.rl +48 -35
  39. data/lib/regexp_parser/scanner.rb +735 -801
  40. data/lib/regexp_parser/syntax/any.rb +2 -7
  41. data/lib/regexp_parser/syntax/base.rb +91 -66
  42. data/lib/regexp_parser/syntax/token/anchor.rb +15 -0
  43. data/lib/regexp_parser/syntax/{tokens → token}/assertion.rb +2 -2
  44. data/lib/regexp_parser/syntax/token/backreference.rb +30 -0
  45. data/lib/regexp_parser/syntax/{tokens → token}/character_set.rb +2 -2
  46. data/lib/regexp_parser/syntax/{tokens → token}/character_type.rb +3 -3
  47. data/lib/regexp_parser/syntax/{tokens → token}/conditional.rb +3 -3
  48. data/lib/regexp_parser/syntax/token/escape.rb +31 -0
  49. data/lib/regexp_parser/syntax/{tokens → token}/group.rb +7 -7
  50. data/lib/regexp_parser/syntax/{tokens → token}/keep.rb +1 -1
  51. data/lib/regexp_parser/syntax/{tokens → token}/meta.rb +2 -2
  52. data/lib/regexp_parser/syntax/{tokens → token}/posix_class.rb +3 -3
  53. data/lib/regexp_parser/syntax/token/quantifier.rb +35 -0
  54. data/lib/regexp_parser/syntax/token/unicode_property.rb +717 -0
  55. data/lib/regexp_parser/syntax/token.rb +45 -0
  56. data/lib/regexp_parser/syntax/version_lookup.rb +20 -29
  57. data/lib/regexp_parser/syntax/versions/1.8.6.rb +13 -20
  58. data/lib/regexp_parser/syntax/versions/1.9.1.rb +10 -17
  59. data/lib/regexp_parser/syntax/versions/1.9.3.rb +3 -10
  60. data/lib/regexp_parser/syntax/versions/2.0.0.rb +8 -15
  61. data/lib/regexp_parser/syntax/versions/2.2.0.rb +3 -9
  62. data/lib/regexp_parser/syntax/versions/2.3.0.rb +3 -9
  63. data/lib/regexp_parser/syntax/versions/2.4.0.rb +3 -9
  64. data/lib/regexp_parser/syntax/versions/2.4.1.rb +2 -8
  65. data/lib/regexp_parser/syntax/versions/2.5.0.rb +3 -9
  66. data/lib/regexp_parser/syntax/versions/2.6.0.rb +3 -9
  67. data/lib/regexp_parser/syntax/versions/2.6.2.rb +3 -9
  68. data/lib/regexp_parser/syntax/versions/2.6.3.rb +3 -9
  69. data/lib/regexp_parser/syntax/versions/3.1.0.rb +4 -0
  70. data/lib/regexp_parser/syntax/versions/3.2.0.rb +4 -0
  71. data/lib/regexp_parser/syntax/versions.rb +1 -1
  72. data/lib/regexp_parser/syntax.rb +1 -1
  73. data/lib/regexp_parser/token.rb +9 -20
  74. data/lib/regexp_parser/version.rb +1 -1
  75. data/lib/regexp_parser.rb +0 -2
  76. data/regexp_parser.gemspec +20 -22
  77. metadata +37 -166
  78. data/lib/regexp_parser/scanner/properties/long.yml +0 -594
  79. data/lib/regexp_parser/scanner/properties/short.yml +0 -237
  80. data/lib/regexp_parser/syntax/tokens/anchor.rb +0 -15
  81. data/lib/regexp_parser/syntax/tokens/backref.rb +0 -24
  82. data/lib/regexp_parser/syntax/tokens/escape.rb +0 -30
  83. data/lib/regexp_parser/syntax/tokens/quantifier.rb +0 -35
  84. data/lib/regexp_parser/syntax/tokens/unicode_property.rb +0 -675
  85. data/lib/regexp_parser/syntax/tokens.rb +0 -45
  86. data/spec/expression/base_spec.rb +0 -104
  87. data/spec/expression/clone_spec.rb +0 -152
  88. data/spec/expression/conditional_spec.rb +0 -89
  89. data/spec/expression/free_space_spec.rb +0 -27
  90. data/spec/expression/methods/match_length_spec.rb +0 -161
  91. data/spec/expression/methods/match_spec.rb +0 -25
  92. data/spec/expression/methods/strfregexp_spec.rb +0 -224
  93. data/spec/expression/methods/tests_spec.rb +0 -99
  94. data/spec/expression/methods/traverse_spec.rb +0 -161
  95. data/spec/expression/options_spec.rb +0 -128
  96. data/spec/expression/subexpression_spec.rb +0 -50
  97. data/spec/expression/to_h_spec.rb +0 -26
  98. data/spec/expression/to_s_spec.rb +0 -108
  99. data/spec/lexer/all_spec.rb +0 -22
  100. data/spec/lexer/conditionals_spec.rb +0 -53
  101. data/spec/lexer/delimiters_spec.rb +0 -68
  102. data/spec/lexer/escapes_spec.rb +0 -14
  103. data/spec/lexer/keep_spec.rb +0 -10
  104. data/spec/lexer/literals_spec.rb +0 -64
  105. data/spec/lexer/nesting_spec.rb +0 -99
  106. data/spec/lexer/refcalls_spec.rb +0 -60
  107. data/spec/parser/all_spec.rb +0 -43
  108. data/spec/parser/alternation_spec.rb +0 -88
  109. data/spec/parser/anchors_spec.rb +0 -17
  110. data/spec/parser/conditionals_spec.rb +0 -179
  111. data/spec/parser/errors_spec.rb +0 -30
  112. data/spec/parser/escapes_spec.rb +0 -121
  113. data/spec/parser/free_space_spec.rb +0 -130
  114. data/spec/parser/groups_spec.rb +0 -108
  115. data/spec/parser/keep_spec.rb +0 -6
  116. data/spec/parser/options_spec.rb +0 -28
  117. data/spec/parser/posix_classes_spec.rb +0 -8
  118. data/spec/parser/properties_spec.rb +0 -115
  119. data/spec/parser/quantifiers_spec.rb +0 -68
  120. data/spec/parser/refcalls_spec.rb +0 -117
  121. data/spec/parser/set/intersections_spec.rb +0 -127
  122. data/spec/parser/set/ranges_spec.rb +0 -111
  123. data/spec/parser/sets_spec.rb +0 -178
  124. data/spec/parser/types_spec.rb +0 -18
  125. data/spec/scanner/all_spec.rb +0 -18
  126. data/spec/scanner/anchors_spec.rb +0 -21
  127. data/spec/scanner/conditionals_spec.rb +0 -128
  128. data/spec/scanner/delimiters_spec.rb +0 -52
  129. data/spec/scanner/errors_spec.rb +0 -67
  130. data/spec/scanner/escapes_spec.rb +0 -64
  131. data/spec/scanner/free_space_spec.rb +0 -165
  132. data/spec/scanner/groups_spec.rb +0 -61
  133. data/spec/scanner/keep_spec.rb +0 -10
  134. data/spec/scanner/literals_spec.rb +0 -39
  135. data/spec/scanner/meta_spec.rb +0 -18
  136. data/spec/scanner/options_spec.rb +0 -36
  137. data/spec/scanner/properties_spec.rb +0 -64
  138. data/spec/scanner/quantifiers_spec.rb +0 -25
  139. data/spec/scanner/refcalls_spec.rb +0 -55
  140. data/spec/scanner/sets_spec.rb +0 -151
  141. data/spec/scanner/types_spec.rb +0 -14
  142. data/spec/spec_helper.rb +0 -16
  143. data/spec/support/runner.rb +0 -42
  144. data/spec/support/shared_examples.rb +0 -77
  145. data/spec/support/warning_extractor.rb +0 -60
  146. data/spec/syntax/syntax_spec.rb +0 -48
  147. data/spec/syntax/syntax_token_map_spec.rb +0 -23
  148. data/spec/syntax/versions/1.8.6_spec.rb +0 -17
  149. data/spec/syntax/versions/1.9.1_spec.rb +0 -10
  150. data/spec/syntax/versions/1.9.3_spec.rb +0 -9
  151. data/spec/syntax/versions/2.0.0_spec.rb +0 -13
  152. data/spec/syntax/versions/2.2.0_spec.rb +0 -9
  153. data/spec/syntax/versions/aliases_spec.rb +0 -37
  154. data/spec/token/token_spec.rb +0 -85
@@ -0,0 +1,622 @@
1
+ # THIS FILE IS AUTO-GENERATED BY `rake props:update` - DO NOT EDIT
2
+ adlam,adlam
3
+ age=1.1,age=1.1
4
+ age=10.0,age=10.0
5
+ age=11.0,age=11.0
6
+ age=12.0,age=12.0
7
+ age=12.1,age=12.1
8
+ age=13.0,age=13.0
9
+ age=14.0,age=14.0
10
+ age=2.0,age=2.0
11
+ age=2.1,age=2.1
12
+ age=3.0,age=3.0
13
+ age=3.1,age=3.1
14
+ age=3.2,age=3.2
15
+ age=4.0,age=4.0
16
+ age=4.1,age=4.1
17
+ age=5.0,age=5.0
18
+ age=5.1,age=5.1
19
+ age=5.2,age=5.2
20
+ age=6.0,age=6.0
21
+ age=6.1,age=6.1
22
+ age=6.2,age=6.2
23
+ age=6.3,age=6.3
24
+ age=7.0,age=7.0
25
+ age=8.0,age=8.0
26
+ age=9.0,age=9.0
27
+ ahom,ahom
28
+ alnum,alnum
29
+ alpha,alpha
30
+ alphabetic,alphabetic
31
+ anatolianhieroglyphs,anatolian_hieroglyphs
32
+ any,any
33
+ arabic,arabic
34
+ armenian,armenian
35
+ ascii,ascii
36
+ asciihexdigit,ascii_hex_digit
37
+ assigned,assigned
38
+ avestan,avestan
39
+ balinese,balinese
40
+ bamum,bamum
41
+ bassavah,bassa_vah
42
+ batak,batak
43
+ bengali,bengali
44
+ bhaiksuki,bhaiksuki
45
+ bidicontrol,bidi_control
46
+ blank,blank
47
+ bopomofo,bopomofo
48
+ brahmi,brahmi
49
+ braille,braille
50
+ buginese,buginese
51
+ buhid,buhid
52
+ canadianaboriginal,canadian_aboriginal
53
+ carian,carian
54
+ cased,cased
55
+ casedletter,cased_letter
56
+ caseignorable,case_ignorable
57
+ caucasianalbanian,caucasian_albanian
58
+ chakma,chakma
59
+ cham,cham
60
+ changeswhencasefolded,changes_when_casefolded
61
+ changeswhencasemapped,changes_when_casemapped
62
+ changeswhenlowercased,changes_when_lowercased
63
+ changeswhentitlecased,changes_when_titlecased
64
+ changeswhenuppercased,changes_when_uppercased
65
+ cherokee,cherokee
66
+ chorasmian,chorasmian
67
+ closepunctuation,close_punctuation
68
+ cntrl,cntrl
69
+ common,common
70
+ connectorpunctuation,connector_punctuation
71
+ control,control
72
+ coptic,coptic
73
+ cuneiform,cuneiform
74
+ currencysymbol,currency_symbol
75
+ cypriot,cypriot
76
+ cyprominoan,cypro_minoan
77
+ cyrillic,cyrillic
78
+ dash,dash
79
+ dashpunctuation,dash_punctuation
80
+ decimalnumber,decimal_number
81
+ defaultignorablecodepoint,default_ignorable_code_point
82
+ deprecated,deprecated
83
+ deseret,deseret
84
+ devanagari,devanagari
85
+ diacritic,diacritic
86
+ digit,digit
87
+ divesakuru,dives_akuru
88
+ dogra,dogra
89
+ duployan,duployan
90
+ egyptianhieroglyphs,egyptian_hieroglyphs
91
+ elbasan,elbasan
92
+ elymaic,elymaic
93
+ emoji,emoji
94
+ emojicomponent,emoji_component
95
+ emojimodifier,emoji_modifier
96
+ emojimodifierbase,emoji_modifier_base
97
+ emojipresentation,emoji_presentation
98
+ enclosingmark,enclosing_mark
99
+ ethiopic,ethiopic
100
+ extender,extender
101
+ finalpunctuation,final_punctuation
102
+ format,format
103
+ georgian,georgian
104
+ glagolitic,glagolitic
105
+ gothic,gothic
106
+ grantha,grantha
107
+ graph,graph
108
+ graphemebase,grapheme_base
109
+ graphemeextend,grapheme_extend
110
+ graphemelink,grapheme_link
111
+ greek,greek
112
+ gujarati,gujarati
113
+ gunjalagondi,gunjala_gondi
114
+ gurmukhi,gurmukhi
115
+ han,han
116
+ hangul,hangul
117
+ hanifirohingya,hanifi_rohingya
118
+ hanunoo,hanunoo
119
+ hatran,hatran
120
+ hebrew,hebrew
121
+ hexdigit,hex_digit
122
+ hiragana,hiragana
123
+ hyphen,hyphen
124
+ idcontinue,id_continue
125
+ ideographic,ideographic
126
+ idsbinaryoperator,ids_binary_operator
127
+ idstart,id_start
128
+ idstrinaryoperator,ids_trinary_operator
129
+ imperialaramaic,imperial_aramaic
130
+ inadlam,in_adlam
131
+ inaegeannumbers,in_aegean_numbers
132
+ inahom,in_ahom
133
+ inalchemicalsymbols,in_alchemical_symbols
134
+ inalphabeticpresentationforms,in_alphabetic_presentation_forms
135
+ inanatolianhieroglyphs,in_anatolian_hieroglyphs
136
+ inancientgreekmusicalnotation,in_ancient_greek_musical_notation
137
+ inancientgreeknumbers,in_ancient_greek_numbers
138
+ inancientsymbols,in_ancient_symbols
139
+ inarabic,in_arabic
140
+ inarabicextendeda,in_arabic_extended_a
141
+ inarabicextendedb,in_arabic_extended_b
142
+ inarabicmathematicalalphabeticsymbols,in_arabic_mathematical_alphabetic_symbols
143
+ inarabicpresentationformsa,in_arabic_presentation_forms_a
144
+ inarabicpresentationformsb,in_arabic_presentation_forms_b
145
+ inarabicsupplement,in_arabic_supplement
146
+ inarmenian,in_armenian
147
+ inarrows,in_arrows
148
+ inavestan,in_avestan
149
+ inbalinese,in_balinese
150
+ inbamum,in_bamum
151
+ inbamumsupplement,in_bamum_supplement
152
+ inbasiclatin,in_basic_latin
153
+ inbassavah,in_bassa_vah
154
+ inbatak,in_batak
155
+ inbengali,in_bengali
156
+ inbhaiksuki,in_bhaiksuki
157
+ inblockelements,in_block_elements
158
+ inbopomofo,in_bopomofo
159
+ inbopomofoextended,in_bopomofo_extended
160
+ inboxdrawing,in_box_drawing
161
+ inbrahmi,in_brahmi
162
+ inbraillepatterns,in_braille_patterns
163
+ inbuginese,in_buginese
164
+ inbuhid,in_buhid
165
+ inbyzantinemusicalsymbols,in_byzantine_musical_symbols
166
+ incarian,in_carian
167
+ incaucasianalbanian,in_caucasian_albanian
168
+ inchakma,in_chakma
169
+ incham,in_cham
170
+ incherokee,in_cherokee
171
+ incherokeesupplement,in_cherokee_supplement
172
+ inchesssymbols,in_chess_symbols
173
+ inchorasmian,in_chorasmian
174
+ incjkcompatibility,in_cjk_compatibility
175
+ incjkcompatibilityforms,in_cjk_compatibility_forms
176
+ incjkcompatibilityideographs,in_cjk_compatibility_ideographs
177
+ incjkcompatibilityideographssupplement,in_cjk_compatibility_ideographs_supplement
178
+ incjkradicalssupplement,in_cjk_radicals_supplement
179
+ incjkstrokes,in_cjk_strokes
180
+ incjksymbolsandpunctuation,in_cjk_symbols_and_punctuation
181
+ incjkunifiedideographs,in_cjk_unified_ideographs
182
+ incjkunifiedideographsextensiona,in_cjk_unified_ideographs_extension_a
183
+ incjkunifiedideographsextensionb,in_cjk_unified_ideographs_extension_b
184
+ incjkunifiedideographsextensionc,in_cjk_unified_ideographs_extension_c
185
+ incjkunifiedideographsextensiond,in_cjk_unified_ideographs_extension_d
186
+ incjkunifiedideographsextensione,in_cjk_unified_ideographs_extension_e
187
+ incjkunifiedideographsextensionf,in_cjk_unified_ideographs_extension_f
188
+ incjkunifiedideographsextensiong,in_cjk_unified_ideographs_extension_g
189
+ incombiningdiacriticalmarks,in_combining_diacritical_marks
190
+ incombiningdiacriticalmarksextended,in_combining_diacritical_marks_extended
191
+ incombiningdiacriticalmarksforsymbols,in_combining_diacritical_marks_for_symbols
192
+ incombiningdiacriticalmarkssupplement,in_combining_diacritical_marks_supplement
193
+ incombininghalfmarks,in_combining_half_marks
194
+ incommonindicnumberforms,in_common_indic_number_forms
195
+ incontrolpictures,in_control_pictures
196
+ incoptic,in_coptic
197
+ incopticepactnumbers,in_coptic_epact_numbers
198
+ incountingrodnumerals,in_counting_rod_numerals
199
+ incuneiform,in_cuneiform
200
+ incuneiformnumbersandpunctuation,in_cuneiform_numbers_and_punctuation
201
+ incurrencysymbols,in_currency_symbols
202
+ incypriotsyllabary,in_cypriot_syllabary
203
+ incyprominoan,in_cypro_minoan
204
+ incyrillic,in_cyrillic
205
+ incyrillicextendeda,in_cyrillic_extended_a
206
+ incyrillicextendedb,in_cyrillic_extended_b
207
+ incyrillicextendedc,in_cyrillic_extended_c
208
+ incyrillicsupplement,in_cyrillic_supplement
209
+ indeseret,in_deseret
210
+ indevanagari,in_devanagari
211
+ indevanagariextended,in_devanagari_extended
212
+ indingbats,in_dingbats
213
+ indivesakuru,in_dives_akuru
214
+ indogra,in_dogra
215
+ indominotiles,in_domino_tiles
216
+ induployan,in_duployan
217
+ inearlydynasticcuneiform,in_early_dynastic_cuneiform
218
+ inegyptianhieroglyphformatcontrols,in_egyptian_hieroglyph_format_controls
219
+ inegyptianhieroglyphs,in_egyptian_hieroglyphs
220
+ inelbasan,in_elbasan
221
+ inelymaic,in_elymaic
222
+ inemoticons,in_emoticons
223
+ inenclosedalphanumerics,in_enclosed_alphanumerics
224
+ inenclosedalphanumericsupplement,in_enclosed_alphanumeric_supplement
225
+ inenclosedcjklettersandmonths,in_enclosed_cjk_letters_and_months
226
+ inenclosedideographicsupplement,in_enclosed_ideographic_supplement
227
+ inethiopic,in_ethiopic
228
+ inethiopicextended,in_ethiopic_extended
229
+ inethiopicextendeda,in_ethiopic_extended_a
230
+ inethiopicextendedb,in_ethiopic_extended_b
231
+ inethiopicsupplement,in_ethiopic_supplement
232
+ ingeneralpunctuation,in_general_punctuation
233
+ ingeometricshapes,in_geometric_shapes
234
+ ingeometricshapesextended,in_geometric_shapes_extended
235
+ ingeorgian,in_georgian
236
+ ingeorgianextended,in_georgian_extended
237
+ ingeorgiansupplement,in_georgian_supplement
238
+ inglagolitic,in_glagolitic
239
+ inglagoliticsupplement,in_glagolitic_supplement
240
+ ingothic,in_gothic
241
+ ingrantha,in_grantha
242
+ ingreekandcoptic,in_greek_and_coptic
243
+ ingreekextended,in_greek_extended
244
+ ingujarati,in_gujarati
245
+ ingunjalagondi,in_gunjala_gondi
246
+ ingurmukhi,in_gurmukhi
247
+ inhalfwidthandfullwidthforms,in_halfwidth_and_fullwidth_forms
248
+ inhangulcompatibilityjamo,in_hangul_compatibility_jamo
249
+ inhanguljamo,in_hangul_jamo
250
+ inhanguljamoextendeda,in_hangul_jamo_extended_a
251
+ inhanguljamoextendedb,in_hangul_jamo_extended_b
252
+ inhangulsyllables,in_hangul_syllables
253
+ inhanifirohingya,in_hanifi_rohingya
254
+ inhanunoo,in_hanunoo
255
+ inhatran,in_hatran
256
+ inhebrew,in_hebrew
257
+ inherited,inherited
258
+ inhighprivateusesurrogates,in_high_private_use_surrogates
259
+ inhighsurrogates,in_high_surrogates
260
+ inhiragana,in_hiragana
261
+ inideographicdescriptioncharacters,in_ideographic_description_characters
262
+ inideographicsymbolsandpunctuation,in_ideographic_symbols_and_punctuation
263
+ inimperialaramaic,in_imperial_aramaic
264
+ inindicsiyaqnumbers,in_indic_siyaq_numbers
265
+ ininscriptionalpahlavi,in_inscriptional_pahlavi
266
+ ininscriptionalparthian,in_inscriptional_parthian
267
+ inipaextensions,in_ipa_extensions
268
+ initialpunctuation,initial_punctuation
269
+ injavanese,in_javanese
270
+ inkaithi,in_kaithi
271
+ inkanaextendeda,in_kana_extended_a
272
+ inkanaextendedb,in_kana_extended_b
273
+ inkanasupplement,in_kana_supplement
274
+ inkanbun,in_kanbun
275
+ inkangxiradicals,in_kangxi_radicals
276
+ inkannada,in_kannada
277
+ inkatakana,in_katakana
278
+ inkatakanaphoneticextensions,in_katakana_phonetic_extensions
279
+ inkayahli,in_kayah_li
280
+ inkharoshthi,in_kharoshthi
281
+ inkhitansmallscript,in_khitan_small_script
282
+ inkhmer,in_khmer
283
+ inkhmersymbols,in_khmer_symbols
284
+ inkhojki,in_khojki
285
+ inkhudawadi,in_khudawadi
286
+ inlao,in_lao
287
+ inlatin1supplement,in_latin_1_supplement
288
+ inlatinextendeda,in_latin_extended_a
289
+ inlatinextendedadditional,in_latin_extended_additional
290
+ inlatinextendedb,in_latin_extended_b
291
+ inlatinextendedc,in_latin_extended_c
292
+ inlatinextendedd,in_latin_extended_d
293
+ inlatinextendede,in_latin_extended_e
294
+ inlatinextendedf,in_latin_extended_f
295
+ inlatinextendedg,in_latin_extended_g
296
+ inlepcha,in_lepcha
297
+ inletterlikesymbols,in_letterlike_symbols
298
+ inlimbu,in_limbu
299
+ inlineara,in_linear_a
300
+ inlinearbideograms,in_linear_b_ideograms
301
+ inlinearbsyllabary,in_linear_b_syllabary
302
+ inlisu,in_lisu
303
+ inlisusupplement,in_lisu_supplement
304
+ inlowsurrogates,in_low_surrogates
305
+ inlycian,in_lycian
306
+ inlydian,in_lydian
307
+ inmahajani,in_mahajani
308
+ inmahjongtiles,in_mahjong_tiles
309
+ inmakasar,in_makasar
310
+ inmalayalam,in_malayalam
311
+ inmandaic,in_mandaic
312
+ inmanichaean,in_manichaean
313
+ inmarchen,in_marchen
314
+ inmasaramgondi,in_masaram_gondi
315
+ inmathematicalalphanumericsymbols,in_mathematical_alphanumeric_symbols
316
+ inmathematicaloperators,in_mathematical_operators
317
+ inmayannumerals,in_mayan_numerals
318
+ inmedefaidrin,in_medefaidrin
319
+ inmeeteimayek,in_meetei_mayek
320
+ inmeeteimayekextensions,in_meetei_mayek_extensions
321
+ inmendekikakui,in_mende_kikakui
322
+ inmeroiticcursive,in_meroitic_cursive
323
+ inmeroitichieroglyphs,in_meroitic_hieroglyphs
324
+ inmiao,in_miao
325
+ inmiscellaneousmathematicalsymbolsa,in_miscellaneous_mathematical_symbols_a
326
+ inmiscellaneousmathematicalsymbolsb,in_miscellaneous_mathematical_symbols_b
327
+ inmiscellaneoussymbols,in_miscellaneous_symbols
328
+ inmiscellaneoussymbolsandarrows,in_miscellaneous_symbols_and_arrows
329
+ inmiscellaneoussymbolsandpictographs,in_miscellaneous_symbols_and_pictographs
330
+ inmiscellaneoustechnical,in_miscellaneous_technical
331
+ inmodi,in_modi
332
+ inmodifiertoneletters,in_modifier_tone_letters
333
+ inmongolian,in_mongolian
334
+ inmongoliansupplement,in_mongolian_supplement
335
+ inmro,in_mro
336
+ inmultani,in_multani
337
+ inmusicalsymbols,in_musical_symbols
338
+ inmyanmar,in_myanmar
339
+ inmyanmarextendeda,in_myanmar_extended_a
340
+ inmyanmarextendedb,in_myanmar_extended_b
341
+ innabataean,in_nabataean
342
+ innandinagari,in_nandinagari
343
+ innewa,in_newa
344
+ innewtailue,in_new_tai_lue
345
+ innko,in_nko
346
+ innoblock,in_no_block
347
+ innumberforms,in_number_forms
348
+ innushu,in_nushu
349
+ innyiakengpuachuehmong,in_nyiakeng_puachue_hmong
350
+ inogham,in_ogham
351
+ inolchiki,in_ol_chiki
352
+ inoldhungarian,in_old_hungarian
353
+ inolditalic,in_old_italic
354
+ inoldnortharabian,in_old_north_arabian
355
+ inoldpermic,in_old_permic
356
+ inoldpersian,in_old_persian
357
+ inoldsogdian,in_old_sogdian
358
+ inoldsoutharabian,in_old_south_arabian
359
+ inoldturkic,in_old_turkic
360
+ inolduyghur,in_old_uyghur
361
+ inopticalcharacterrecognition,in_optical_character_recognition
362
+ inoriya,in_oriya
363
+ inornamentaldingbats,in_ornamental_dingbats
364
+ inosage,in_osage
365
+ inosmanya,in_osmanya
366
+ inottomansiyaqnumbers,in_ottoman_siyaq_numbers
367
+ inpahawhhmong,in_pahawh_hmong
368
+ inpalmyrene,in_palmyrene
369
+ inpaucinhau,in_pau_cin_hau
370
+ inphagspa,in_phags_pa
371
+ inphaistosdisc,in_phaistos_disc
372
+ inphoenician,in_phoenician
373
+ inphoneticextensions,in_phonetic_extensions
374
+ inphoneticextensionssupplement,in_phonetic_extensions_supplement
375
+ inplayingcards,in_playing_cards
376
+ inprivateusearea,in_private_use_area
377
+ inpsalterpahlavi,in_psalter_pahlavi
378
+ inrejang,in_rejang
379
+ inruminumeralsymbols,in_rumi_numeral_symbols
380
+ inrunic,in_runic
381
+ insamaritan,in_samaritan
382
+ insaurashtra,in_saurashtra
383
+ inscriptionalpahlavi,inscriptional_pahlavi
384
+ inscriptionalparthian,inscriptional_parthian
385
+ insharada,in_sharada
386
+ inshavian,in_shavian
387
+ inshorthandformatcontrols,in_shorthand_format_controls
388
+ insiddham,in_siddham
389
+ insinhala,in_sinhala
390
+ insinhalaarchaicnumbers,in_sinhala_archaic_numbers
391
+ insmallformvariants,in_small_form_variants
392
+ insmallkanaextension,in_small_kana_extension
393
+ insogdian,in_sogdian
394
+ insorasompeng,in_sora_sompeng
395
+ insoyombo,in_soyombo
396
+ inspacingmodifierletters,in_spacing_modifier_letters
397
+ inspecials,in_specials
398
+ insundanese,in_sundanese
399
+ insundanesesupplement,in_sundanese_supplement
400
+ insuperscriptsandsubscripts,in_superscripts_and_subscripts
401
+ insupplementalarrowsa,in_supplemental_arrows_a
402
+ insupplementalarrowsb,in_supplemental_arrows_b
403
+ insupplementalarrowsc,in_supplemental_arrows_c
404
+ insupplementalmathematicaloperators,in_supplemental_mathematical_operators
405
+ insupplementalpunctuation,in_supplemental_punctuation
406
+ insupplementalsymbolsandpictographs,in_supplemental_symbols_and_pictographs
407
+ insupplementaryprivateuseareaa,in_supplementary_private_use_area_a
408
+ insupplementaryprivateuseareab,in_supplementary_private_use_area_b
409
+ insuttonsignwriting,in_sutton_signwriting
410
+ insylotinagri,in_syloti_nagri
411
+ insymbolsandpictographsextendeda,in_symbols_and_pictographs_extended_a
412
+ insymbolsforlegacycomputing,in_symbols_for_legacy_computing
413
+ insyriac,in_syriac
414
+ insyriacsupplement,in_syriac_supplement
415
+ intagalog,in_tagalog
416
+ intagbanwa,in_tagbanwa
417
+ intags,in_tags
418
+ intaile,in_tai_le
419
+ intaitham,in_tai_tham
420
+ intaiviet,in_tai_viet
421
+ intaixuanjingsymbols,in_tai_xuan_jing_symbols
422
+ intakri,in_takri
423
+ intamil,in_tamil
424
+ intamilsupplement,in_tamil_supplement
425
+ intangsa,in_tangsa
426
+ intangut,in_tangut
427
+ intangutcomponents,in_tangut_components
428
+ intangutsupplement,in_tangut_supplement
429
+ intelugu,in_telugu
430
+ inthaana,in_thaana
431
+ inthai,in_thai
432
+ intibetan,in_tibetan
433
+ intifinagh,in_tifinagh
434
+ intirhuta,in_tirhuta
435
+ intoto,in_toto
436
+ intransportandmapsymbols,in_transport_and_map_symbols
437
+ inugaritic,in_ugaritic
438
+ inunifiedcanadianaboriginalsyllabics,in_unified_canadian_aboriginal_syllabics
439
+ inunifiedcanadianaboriginalsyllabicsextended,in_unified_canadian_aboriginal_syllabics_extended
440
+ inunifiedcanadianaboriginalsyllabicsextendeda,in_unified_canadian_aboriginal_syllabics_extended_a
441
+ invai,in_vai
442
+ invariationselectors,in_variation_selectors
443
+ invariationselectorssupplement,in_variation_selectors_supplement
444
+ invedicextensions,in_vedic_extensions
445
+ inverticalforms,in_vertical_forms
446
+ invithkuqi,in_vithkuqi
447
+ inwancho,in_wancho
448
+ inwarangciti,in_warang_citi
449
+ inyezidi,in_yezidi
450
+ inyijinghexagramsymbols,in_yijing_hexagram_symbols
451
+ inyiradicals,in_yi_radicals
452
+ inyisyllables,in_yi_syllables
453
+ inzanabazarsquare,in_zanabazar_square
454
+ inznamennymusicalnotation,in_znamenny_musical_notation
455
+ javanese,javanese
456
+ joincontrol,join_control
457
+ kaithi,kaithi
458
+ kannada,kannada
459
+ katakana,katakana
460
+ kayahli,kayah_li
461
+ kharoshthi,kharoshthi
462
+ khitansmallscript,khitan_small_script
463
+ khmer,khmer
464
+ khojki,khojki
465
+ khudawadi,khudawadi
466
+ lao,lao
467
+ latin,latin
468
+ lepcha,lepcha
469
+ letter,letter
470
+ letternumber,letter_number
471
+ limbu,limbu
472
+ lineara,linear_a
473
+ linearb,linear_b
474
+ lineseparator,line_separator
475
+ lisu,lisu
476
+ logicalorderexception,logical_order_exception
477
+ lower,lower
478
+ lowercase,lowercase
479
+ lowercaseletter,lowercase_letter
480
+ lycian,lycian
481
+ lydian,lydian
482
+ mahajani,mahajani
483
+ makasar,makasar
484
+ malayalam,malayalam
485
+ mandaic,mandaic
486
+ manichaean,manichaean
487
+ marchen,marchen
488
+ mark,mark
489
+ masaramgondi,masaram_gondi
490
+ math,math
491
+ mathsymbol,math_symbol
492
+ medefaidrin,medefaidrin
493
+ meeteimayek,meetei_mayek
494
+ mendekikakui,mende_kikakui
495
+ meroiticcursive,meroitic_cursive
496
+ meroitichieroglyphs,meroitic_hieroglyphs
497
+ miao,miao
498
+ modi,modi
499
+ modifierletter,modifier_letter
500
+ modifiersymbol,modifier_symbol
501
+ mongolian,mongolian
502
+ mro,mro
503
+ multani,multani
504
+ myanmar,myanmar
505
+ nabataean,nabataean
506
+ nandinagari,nandinagari
507
+ newa,newa
508
+ newline,newline
509
+ newtailue,new_tai_lue
510
+ nko,nko
511
+ noncharactercodepoint,noncharacter_code_point
512
+ nonspacingmark,nonspacing_mark
513
+ number,number
514
+ nushu,nushu
515
+ nyiakengpuachuehmong,nyiakeng_puachue_hmong
516
+ ogham,ogham
517
+ olchiki,ol_chiki
518
+ oldhungarian,old_hungarian
519
+ olditalic,old_italic
520
+ oldnortharabian,old_north_arabian
521
+ oldpermic,old_permic
522
+ oldpersian,old_persian
523
+ oldsogdian,old_sogdian
524
+ oldsoutharabian,old_south_arabian
525
+ oldturkic,old_turkic
526
+ olduyghur,old_uyghur
527
+ openpunctuation,open_punctuation
528
+ oriya,oriya
529
+ osage,osage
530
+ osmanya,osmanya
531
+ other,other
532
+ otheralphabetic,other_alphabetic
533
+ otherdefaultignorablecodepoint,other_default_ignorable_code_point
534
+ othergraphemeextend,other_grapheme_extend
535
+ otheridcontinue,other_id_continue
536
+ otheridstart,other_id_start
537
+ otherletter,other_letter
538
+ otherlowercase,other_lowercase
539
+ othermath,other_math
540
+ othernumber,other_number
541
+ otherpunctuation,other_punctuation
542
+ othersymbol,other_symbol
543
+ otheruppercase,other_uppercase
544
+ pahawhhmong,pahawh_hmong
545
+ palmyrene,palmyrene
546
+ paragraphseparator,paragraph_separator
547
+ patternsyntax,pattern_syntax
548
+ patternwhitespace,pattern_white_space
549
+ paucinhau,pau_cin_hau
550
+ phagspa,phags_pa
551
+ phoenician,phoenician
552
+ prependedconcatenationmark,prepended_concatenation_mark
553
+ print,print
554
+ privateuse,private_use
555
+ psalterpahlavi,psalter_pahlavi
556
+ punct,punct
557
+ punctuation,punctuation
558
+ quotationmark,quotation_mark
559
+ radical,radical
560
+ regionalindicator,regional_indicator
561
+ rejang,rejang
562
+ runic,runic
563
+ samaritan,samaritan
564
+ saurashtra,saurashtra
565
+ sentenceterminal,sentence_terminal
566
+ separator,separator
567
+ sharada,sharada
568
+ shavian,shavian
569
+ siddham,siddham
570
+ signwriting,signwriting
571
+ sinhala,sinhala
572
+ softdotted,soft_dotted
573
+ sogdian,sogdian
574
+ sorasompeng,sora_sompeng
575
+ soyombo,soyombo
576
+ space,space
577
+ spaceseparator,space_separator
578
+ spacingmark,spacing_mark
579
+ sundanese,sundanese
580
+ surrogate,surrogate
581
+ sylotinagri,syloti_nagri
582
+ symbol,symbol
583
+ syriac,syriac
584
+ tagalog,tagalog
585
+ tagbanwa,tagbanwa
586
+ taile,tai_le
587
+ taitham,tai_tham
588
+ taiviet,tai_viet
589
+ takri,takri
590
+ tamil,tamil
591
+ tangsa,tangsa
592
+ tangut,tangut
593
+ telugu,telugu
594
+ terminalpunctuation,terminal_punctuation
595
+ thaana,thaana
596
+ thai,thai
597
+ tibetan,tibetan
598
+ tifinagh,tifinagh
599
+ tirhuta,tirhuta
600
+ titlecaseletter,titlecase_letter
601
+ toto,toto
602
+ ugaritic,ugaritic
603
+ unassigned,unassigned
604
+ unifiedideograph,unified_ideograph
605
+ unknown,unknown
606
+ upper,upper
607
+ uppercase,uppercase
608
+ uppercaseletter,uppercase_letter
609
+ vai,vai
610
+ variationselector,variation_selector
611
+ vithkuqi,vithkuqi
612
+ wancho,wancho
613
+ warangciti,warang_citi
614
+ whitespace,white_space
615
+ word,word
616
+ xdigit,xdigit
617
+ xidcontinue,xid_continue
618
+ xidstart,xid_start
619
+ xposixpunct,xposixpunct
620
+ yezidi,yezidi
621
+ yi,yi
622
+ zanabazarsquare,zanabazar_square