regexp_parser 1.7.1 → 2.2.1

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 (139) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +157 -1
  3. data/Gemfile +6 -1
  4. data/LICENSE +1 -1
  5. data/README.md +38 -32
  6. data/Rakefile +18 -27
  7. data/lib/regexp_parser/error.rb +4 -0
  8. data/lib/regexp_parser/expression/base.rb +123 -0
  9. data/lib/regexp_parser/expression/classes/anchor.rb +0 -2
  10. data/lib/regexp_parser/expression/classes/{backref.rb → backreference.rb} +5 -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 -1
  13. data/lib/regexp_parser/expression/classes/{set.rb → character_set.rb} +0 -0
  14. data/lib/regexp_parser/expression/classes/conditional.rb +11 -1
  15. data/lib/regexp_parser/expression/classes/{escape.rb → escape_sequence.rb} +13 -7
  16. data/lib/regexp_parser/expression/classes/free_space.rb +2 -4
  17. data/lib/regexp_parser/expression/classes/group.rb +28 -3
  18. data/lib/regexp_parser/expression/classes/literal.rb +1 -5
  19. data/lib/regexp_parser/expression/classes/property.rb +1 -3
  20. data/lib/regexp_parser/expression/classes/root.rb +4 -17
  21. data/lib/regexp_parser/expression/classes/type.rb +0 -2
  22. data/lib/regexp_parser/expression/methods/match_length.rb +2 -2
  23. data/lib/regexp_parser/expression/methods/strfregexp.rb +1 -1
  24. data/lib/regexp_parser/expression/methods/traverse.rb +2 -2
  25. data/lib/regexp_parser/expression/quantifier.rb +11 -2
  26. data/lib/regexp_parser/expression/sequence.rb +3 -20
  27. data/lib/regexp_parser/expression/subexpression.rb +1 -2
  28. data/lib/regexp_parser/expression.rb +7 -139
  29. data/lib/regexp_parser/lexer.rb +13 -11
  30. data/lib/regexp_parser/parser.rb +325 -344
  31. data/lib/regexp_parser/scanner/char_type.rl +11 -11
  32. data/lib/regexp_parser/scanner/properties/long.csv +604 -0
  33. data/lib/regexp_parser/scanner/properties/short.csv +242 -0
  34. data/lib/regexp_parser/scanner/property.rl +2 -2
  35. data/lib/regexp_parser/scanner/scanner.rl +235 -255
  36. data/lib/regexp_parser/scanner.rb +1324 -1387
  37. data/lib/regexp_parser/syntax/any.rb +4 -6
  38. data/lib/regexp_parser/syntax/base.rb +13 -15
  39. data/lib/regexp_parser/syntax/token/anchor.rb +15 -0
  40. data/lib/regexp_parser/syntax/{tokens → token}/assertion.rb +2 -2
  41. data/lib/regexp_parser/syntax/token/backreference.rb +30 -0
  42. data/lib/regexp_parser/syntax/{tokens → token}/character_set.rb +2 -2
  43. data/lib/regexp_parser/syntax/{tokens → token}/character_type.rb +3 -3
  44. data/lib/regexp_parser/syntax/{tokens → token}/conditional.rb +3 -3
  45. data/lib/regexp_parser/syntax/token/escape.rb +31 -0
  46. data/lib/regexp_parser/syntax/{tokens → token}/group.rb +7 -7
  47. data/lib/regexp_parser/syntax/{tokens → token}/keep.rb +1 -1
  48. data/lib/regexp_parser/syntax/{tokens → token}/meta.rb +2 -2
  49. data/lib/regexp_parser/syntax/{tokens → token}/posix_class.rb +3 -3
  50. data/lib/regexp_parser/syntax/token/quantifier.rb +35 -0
  51. data/lib/regexp_parser/syntax/token/unicode_property.rb +696 -0
  52. data/lib/regexp_parser/syntax/token.rb +45 -0
  53. data/lib/regexp_parser/syntax/version_lookup.rb +4 -4
  54. data/lib/regexp_parser/syntax/versions/1.8.6.rb +2 -2
  55. data/lib/regexp_parser/syntax/versions/1.9.1.rb +1 -1
  56. data/lib/regexp_parser/syntax/versions/3.1.0.rb +10 -0
  57. data/lib/regexp_parser/syntax.rb +8 -6
  58. data/lib/regexp_parser/token.rb +9 -20
  59. data/lib/regexp_parser/version.rb +1 -1
  60. data/lib/regexp_parser.rb +0 -2
  61. data/regexp_parser.gemspec +20 -22
  62. metadata +34 -165
  63. data/lib/regexp_parser/scanner/properties/long.yml +0 -594
  64. data/lib/regexp_parser/scanner/properties/short.yml +0 -237
  65. data/lib/regexp_parser/syntax/tokens/anchor.rb +0 -15
  66. data/lib/regexp_parser/syntax/tokens/backref.rb +0 -24
  67. data/lib/regexp_parser/syntax/tokens/escape.rb +0 -30
  68. data/lib/regexp_parser/syntax/tokens/quantifier.rb +0 -35
  69. data/lib/regexp_parser/syntax/tokens/unicode_property.rb +0 -675
  70. data/lib/regexp_parser/syntax/tokens.rb +0 -45
  71. data/spec/expression/base_spec.rb +0 -94
  72. data/spec/expression/clone_spec.rb +0 -120
  73. data/spec/expression/conditional_spec.rb +0 -89
  74. data/spec/expression/free_space_spec.rb +0 -27
  75. data/spec/expression/methods/match_length_spec.rb +0 -161
  76. data/spec/expression/methods/match_spec.rb +0 -25
  77. data/spec/expression/methods/strfregexp_spec.rb +0 -224
  78. data/spec/expression/methods/tests_spec.rb +0 -99
  79. data/spec/expression/methods/traverse_spec.rb +0 -161
  80. data/spec/expression/options_spec.rb +0 -128
  81. data/spec/expression/root_spec.rb +0 -9
  82. data/spec/expression/sequence_spec.rb +0 -9
  83. data/spec/expression/subexpression_spec.rb +0 -50
  84. data/spec/expression/to_h_spec.rb +0 -26
  85. data/spec/expression/to_s_spec.rb +0 -100
  86. data/spec/lexer/all_spec.rb +0 -22
  87. data/spec/lexer/conditionals_spec.rb +0 -53
  88. data/spec/lexer/delimiters_spec.rb +0 -68
  89. data/spec/lexer/escapes_spec.rb +0 -14
  90. data/spec/lexer/keep_spec.rb +0 -10
  91. data/spec/lexer/literals_spec.rb +0 -89
  92. data/spec/lexer/nesting_spec.rb +0 -99
  93. data/spec/lexer/refcalls_spec.rb +0 -55
  94. data/spec/parser/all_spec.rb +0 -43
  95. data/spec/parser/alternation_spec.rb +0 -88
  96. data/spec/parser/anchors_spec.rb +0 -17
  97. data/spec/parser/conditionals_spec.rb +0 -179
  98. data/spec/parser/errors_spec.rb +0 -30
  99. data/spec/parser/escapes_spec.rb +0 -121
  100. data/spec/parser/free_space_spec.rb +0 -130
  101. data/spec/parser/groups_spec.rb +0 -108
  102. data/spec/parser/keep_spec.rb +0 -6
  103. data/spec/parser/posix_classes_spec.rb +0 -8
  104. data/spec/parser/properties_spec.rb +0 -115
  105. data/spec/parser/quantifiers_spec.rb +0 -52
  106. data/spec/parser/refcalls_spec.rb +0 -112
  107. data/spec/parser/set/intersections_spec.rb +0 -127
  108. data/spec/parser/set/ranges_spec.rb +0 -111
  109. data/spec/parser/sets_spec.rb +0 -178
  110. data/spec/parser/types_spec.rb +0 -18
  111. data/spec/scanner/all_spec.rb +0 -18
  112. data/spec/scanner/anchors_spec.rb +0 -21
  113. data/spec/scanner/conditionals_spec.rb +0 -128
  114. data/spec/scanner/delimiters_spec.rb +0 -52
  115. data/spec/scanner/errors_spec.rb +0 -67
  116. data/spec/scanner/escapes_spec.rb +0 -53
  117. data/spec/scanner/free_space_spec.rb +0 -133
  118. data/spec/scanner/groups_spec.rb +0 -52
  119. data/spec/scanner/keep_spec.rb +0 -10
  120. data/spec/scanner/literals_spec.rb +0 -49
  121. data/spec/scanner/meta_spec.rb +0 -18
  122. data/spec/scanner/properties_spec.rb +0 -64
  123. data/spec/scanner/quantifiers_spec.rb +0 -20
  124. data/spec/scanner/refcalls_spec.rb +0 -36
  125. data/spec/scanner/sets_spec.rb +0 -102
  126. data/spec/scanner/types_spec.rb +0 -14
  127. data/spec/spec_helper.rb +0 -15
  128. data/spec/support/runner.rb +0 -42
  129. data/spec/support/shared_examples.rb +0 -77
  130. data/spec/support/warning_extractor.rb +0 -60
  131. data/spec/syntax/syntax_spec.rb +0 -48
  132. data/spec/syntax/syntax_token_map_spec.rb +0 -23
  133. data/spec/syntax/versions/1.8.6_spec.rb +0 -17
  134. data/spec/syntax/versions/1.9.1_spec.rb +0 -10
  135. data/spec/syntax/versions/1.9.3_spec.rb +0 -9
  136. data/spec/syntax/versions/2.0.0_spec.rb +0 -13
  137. data/spec/syntax/versions/2.2.0_spec.rb +0 -9
  138. data/spec/syntax/versions/aliases_spec.rb +0 -37
  139. data/spec/token/token_spec.rb +0 -85
@@ -10,17 +10,17 @@
10
10
  # --------------------------------------------------------------------------
11
11
  char_type := |*
12
12
  char_type_char {
13
- case text = text(data, ts, te, 1).first
14
- when '\d'; emit(:type, :digit, text, ts - 1, te)
15
- when '\D'; emit(:type, :nondigit, text, ts - 1, te)
16
- when '\h'; emit(:type, :hex, text, ts - 1, te)
17
- when '\H'; emit(:type, :nonhex, text, ts - 1, te)
18
- when '\s'; emit(:type, :space, text, ts - 1, te)
19
- when '\S'; emit(:type, :nonspace, text, ts - 1, te)
20
- when '\w'; emit(:type, :word, text, ts - 1, te)
21
- when '\W'; emit(:type, :nonword, text, ts - 1, te)
22
- when '\R'; emit(:type, :linebreak, text, ts - 1, te)
23
- when '\X'; emit(:type, :xgrapheme, text, ts - 1, te)
13
+ case text = copy(data, ts-1, te)
14
+ when '\d'; emit(:type, :digit, text)
15
+ when '\D'; emit(:type, :nondigit, text)
16
+ when '\h'; emit(:type, :hex, text)
17
+ when '\H'; emit(:type, :nonhex, text)
18
+ when '\s'; emit(:type, :space, text)
19
+ when '\S'; emit(:type, :nonspace, text)
20
+ when '\w'; emit(:type, :word, text)
21
+ when '\W'; emit(:type, :nonword, text)
22
+ when '\R'; emit(:type, :linebreak, text)
23
+ when '\X'; emit(:type, :xgrapheme, text)
24
24
  end
25
25
  fret;
26
26
  };
@@ -0,0 +1,604 @@
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=2.0,age=2.0
10
+ age=2.1,age=2.1
11
+ age=3.0,age=3.0
12
+ age=3.1,age=3.1
13
+ age=3.2,age=3.2
14
+ age=4.0,age=4.0
15
+ age=4.1,age=4.1
16
+ age=5.0,age=5.0
17
+ age=5.1,age=5.1
18
+ age=5.2,age=5.2
19
+ age=6.0,age=6.0
20
+ age=6.1,age=6.1
21
+ age=6.2,age=6.2
22
+ age=6.3,age=6.3
23
+ age=7.0,age=7.0
24
+ age=8.0,age=8.0
25
+ age=9.0,age=9.0
26
+ ahom,ahom
27
+ alnum,alnum
28
+ alpha,alpha
29
+ alphabetic,alphabetic
30
+ anatolianhieroglyphs,anatolian_hieroglyphs
31
+ any,any
32
+ arabic,arabic
33
+ armenian,armenian
34
+ ascii,ascii
35
+ asciihexdigit,ascii_hex_digit
36
+ assigned,assigned
37
+ avestan,avestan
38
+ balinese,balinese
39
+ bamum,bamum
40
+ bassavah,bassa_vah
41
+ batak,batak
42
+ bengali,bengali
43
+ bhaiksuki,bhaiksuki
44
+ bidicontrol,bidi_control
45
+ blank,blank
46
+ bopomofo,bopomofo
47
+ brahmi,brahmi
48
+ braille,braille
49
+ buginese,buginese
50
+ buhid,buhid
51
+ canadianaboriginal,canadian_aboriginal
52
+ carian,carian
53
+ cased,cased
54
+ casedletter,cased_letter
55
+ caseignorable,case_ignorable
56
+ caucasianalbanian,caucasian_albanian
57
+ chakma,chakma
58
+ cham,cham
59
+ changeswhencasefolded,changes_when_casefolded
60
+ changeswhencasemapped,changes_when_casemapped
61
+ changeswhenlowercased,changes_when_lowercased
62
+ changeswhentitlecased,changes_when_titlecased
63
+ changeswhenuppercased,changes_when_uppercased
64
+ cherokee,cherokee
65
+ chorasmian,chorasmian
66
+ closepunctuation,close_punctuation
67
+ cntrl,cntrl
68
+ common,common
69
+ connectorpunctuation,connector_punctuation
70
+ control,control
71
+ coptic,coptic
72
+ cuneiform,cuneiform
73
+ currencysymbol,currency_symbol
74
+ cypriot,cypriot
75
+ cyrillic,cyrillic
76
+ dash,dash
77
+ dashpunctuation,dash_punctuation
78
+ decimalnumber,decimal_number
79
+ defaultignorablecodepoint,default_ignorable_code_point
80
+ deprecated,deprecated
81
+ deseret,deseret
82
+ devanagari,devanagari
83
+ diacritic,diacritic
84
+ digit,digit
85
+ divesakuru,dives_akuru
86
+ dogra,dogra
87
+ duployan,duployan
88
+ egyptianhieroglyphs,egyptian_hieroglyphs
89
+ elbasan,elbasan
90
+ elymaic,elymaic
91
+ emoji,emoji
92
+ emojicomponent,emoji_component
93
+ emojimodifier,emoji_modifier
94
+ emojimodifierbase,emoji_modifier_base
95
+ emojipresentation,emoji_presentation
96
+ enclosingmark,enclosing_mark
97
+ ethiopic,ethiopic
98
+ extender,extender
99
+ finalpunctuation,final_punctuation
100
+ format,format
101
+ georgian,georgian
102
+ glagolitic,glagolitic
103
+ gothic,gothic
104
+ grantha,grantha
105
+ graph,graph
106
+ graphemebase,grapheme_base
107
+ graphemeextend,grapheme_extend
108
+ graphemelink,grapheme_link
109
+ greek,greek
110
+ gujarati,gujarati
111
+ gunjalagondi,gunjala_gondi
112
+ gurmukhi,gurmukhi
113
+ han,han
114
+ hangul,hangul
115
+ hanifirohingya,hanifi_rohingya
116
+ hanunoo,hanunoo
117
+ hatran,hatran
118
+ hebrew,hebrew
119
+ hexdigit,hex_digit
120
+ hiragana,hiragana
121
+ hyphen,hyphen
122
+ idcontinue,id_continue
123
+ ideographic,ideographic
124
+ idsbinaryoperator,ids_binary_operator
125
+ idstart,id_start
126
+ idstrinaryoperator,ids_trinary_operator
127
+ imperialaramaic,imperial_aramaic
128
+ inadlam,in_adlam
129
+ inaegeannumbers,in_aegean_numbers
130
+ inahom,in_ahom
131
+ inalchemicalsymbols,in_alchemical_symbols
132
+ inalphabeticpresentationforms,in_alphabetic_presentation_forms
133
+ inanatolianhieroglyphs,in_anatolian_hieroglyphs
134
+ inancientgreekmusicalnotation,in_ancient_greek_musical_notation
135
+ inancientgreeknumbers,in_ancient_greek_numbers
136
+ inancientsymbols,in_ancient_symbols
137
+ inarabic,in_arabic
138
+ inarabicextendeda,in_arabic_extended_a
139
+ inarabicmathematicalalphabeticsymbols,in_arabic_mathematical_alphabetic_symbols
140
+ inarabicpresentationformsa,in_arabic_presentation_forms_a
141
+ inarabicpresentationformsb,in_arabic_presentation_forms_b
142
+ inarabicsupplement,in_arabic_supplement
143
+ inarmenian,in_armenian
144
+ inarrows,in_arrows
145
+ inavestan,in_avestan
146
+ inbalinese,in_balinese
147
+ inbamum,in_bamum
148
+ inbamumsupplement,in_bamum_supplement
149
+ inbasiclatin,in_basic_latin
150
+ inbassavah,in_bassa_vah
151
+ inbatak,in_batak
152
+ inbengali,in_bengali
153
+ inbhaiksuki,in_bhaiksuki
154
+ inblockelements,in_block_elements
155
+ inbopomofo,in_bopomofo
156
+ inbopomofoextended,in_bopomofo_extended
157
+ inboxdrawing,in_box_drawing
158
+ inbrahmi,in_brahmi
159
+ inbraillepatterns,in_braille_patterns
160
+ inbuginese,in_buginese
161
+ inbuhid,in_buhid
162
+ inbyzantinemusicalsymbols,in_byzantine_musical_symbols
163
+ incarian,in_carian
164
+ incaucasianalbanian,in_caucasian_albanian
165
+ inchakma,in_chakma
166
+ incham,in_cham
167
+ incherokee,in_cherokee
168
+ incherokeesupplement,in_cherokee_supplement
169
+ inchesssymbols,in_chess_symbols
170
+ inchorasmian,in_chorasmian
171
+ incjkcompatibility,in_cjk_compatibility
172
+ incjkcompatibilityforms,in_cjk_compatibility_forms
173
+ incjkcompatibilityideographs,in_cjk_compatibility_ideographs
174
+ incjkcompatibilityideographssupplement,in_cjk_compatibility_ideographs_supplement
175
+ incjkradicalssupplement,in_cjk_radicals_supplement
176
+ incjkstrokes,in_cjk_strokes
177
+ incjksymbolsandpunctuation,in_cjk_symbols_and_punctuation
178
+ incjkunifiedideographs,in_cjk_unified_ideographs
179
+ incjkunifiedideographsextensiona,in_cjk_unified_ideographs_extension_a
180
+ incjkunifiedideographsextensionb,in_cjk_unified_ideographs_extension_b
181
+ incjkunifiedideographsextensionc,in_cjk_unified_ideographs_extension_c
182
+ incjkunifiedideographsextensiond,in_cjk_unified_ideographs_extension_d
183
+ incjkunifiedideographsextensione,in_cjk_unified_ideographs_extension_e
184
+ incjkunifiedideographsextensionf,in_cjk_unified_ideographs_extension_f
185
+ incjkunifiedideographsextensiong,in_cjk_unified_ideographs_extension_g
186
+ incombiningdiacriticalmarks,in_combining_diacritical_marks
187
+ incombiningdiacriticalmarksextended,in_combining_diacritical_marks_extended
188
+ incombiningdiacriticalmarksforsymbols,in_combining_diacritical_marks_for_symbols
189
+ incombiningdiacriticalmarkssupplement,in_combining_diacritical_marks_supplement
190
+ incombininghalfmarks,in_combining_half_marks
191
+ incommonindicnumberforms,in_common_indic_number_forms
192
+ incontrolpictures,in_control_pictures
193
+ incoptic,in_coptic
194
+ incopticepactnumbers,in_coptic_epact_numbers
195
+ incountingrodnumerals,in_counting_rod_numerals
196
+ incuneiform,in_cuneiform
197
+ incuneiformnumbersandpunctuation,in_cuneiform_numbers_and_punctuation
198
+ incurrencysymbols,in_currency_symbols
199
+ incypriotsyllabary,in_cypriot_syllabary
200
+ incyrillic,in_cyrillic
201
+ incyrillicextendeda,in_cyrillic_extended_a
202
+ incyrillicextendedb,in_cyrillic_extended_b
203
+ incyrillicextendedc,in_cyrillic_extended_c
204
+ incyrillicsupplement,in_cyrillic_supplement
205
+ indeseret,in_deseret
206
+ indevanagari,in_devanagari
207
+ indevanagariextended,in_devanagari_extended
208
+ indingbats,in_dingbats
209
+ indivesakuru,in_dives_akuru
210
+ indogra,in_dogra
211
+ indominotiles,in_domino_tiles
212
+ induployan,in_duployan
213
+ inearlydynasticcuneiform,in_early_dynastic_cuneiform
214
+ inegyptianhieroglyphformatcontrols,in_egyptian_hieroglyph_format_controls
215
+ inegyptianhieroglyphs,in_egyptian_hieroglyphs
216
+ inelbasan,in_elbasan
217
+ inelymaic,in_elymaic
218
+ inemoticons,in_emoticons
219
+ inenclosedalphanumerics,in_enclosed_alphanumerics
220
+ inenclosedalphanumericsupplement,in_enclosed_alphanumeric_supplement
221
+ inenclosedcjklettersandmonths,in_enclosed_cjk_letters_and_months
222
+ inenclosedideographicsupplement,in_enclosed_ideographic_supplement
223
+ inethiopic,in_ethiopic
224
+ inethiopicextended,in_ethiopic_extended
225
+ inethiopicextendeda,in_ethiopic_extended_a
226
+ inethiopicsupplement,in_ethiopic_supplement
227
+ ingeneralpunctuation,in_general_punctuation
228
+ ingeometricshapes,in_geometric_shapes
229
+ ingeometricshapesextended,in_geometric_shapes_extended
230
+ ingeorgian,in_georgian
231
+ ingeorgianextended,in_georgian_extended
232
+ ingeorgiansupplement,in_georgian_supplement
233
+ inglagolitic,in_glagolitic
234
+ inglagoliticsupplement,in_glagolitic_supplement
235
+ ingothic,in_gothic
236
+ ingrantha,in_grantha
237
+ ingreekandcoptic,in_greek_and_coptic
238
+ ingreekextended,in_greek_extended
239
+ ingujarati,in_gujarati
240
+ ingunjalagondi,in_gunjala_gondi
241
+ ingurmukhi,in_gurmukhi
242
+ inhalfwidthandfullwidthforms,in_halfwidth_and_fullwidth_forms
243
+ inhangulcompatibilityjamo,in_hangul_compatibility_jamo
244
+ inhanguljamo,in_hangul_jamo
245
+ inhanguljamoextendeda,in_hangul_jamo_extended_a
246
+ inhanguljamoextendedb,in_hangul_jamo_extended_b
247
+ inhangulsyllables,in_hangul_syllables
248
+ inhanifirohingya,in_hanifi_rohingya
249
+ inhanunoo,in_hanunoo
250
+ inhatran,in_hatran
251
+ inhebrew,in_hebrew
252
+ inherited,inherited
253
+ inhighprivateusesurrogates,in_high_private_use_surrogates
254
+ inhighsurrogates,in_high_surrogates
255
+ inhiragana,in_hiragana
256
+ inideographicdescriptioncharacters,in_ideographic_description_characters
257
+ inideographicsymbolsandpunctuation,in_ideographic_symbols_and_punctuation
258
+ inimperialaramaic,in_imperial_aramaic
259
+ inindicsiyaqnumbers,in_indic_siyaq_numbers
260
+ ininscriptionalpahlavi,in_inscriptional_pahlavi
261
+ ininscriptionalparthian,in_inscriptional_parthian
262
+ inipaextensions,in_ipa_extensions
263
+ initialpunctuation,initial_punctuation
264
+ injavanese,in_javanese
265
+ inkaithi,in_kaithi
266
+ inkanaextendeda,in_kana_extended_a
267
+ inkanasupplement,in_kana_supplement
268
+ inkanbun,in_kanbun
269
+ inkangxiradicals,in_kangxi_radicals
270
+ inkannada,in_kannada
271
+ inkatakana,in_katakana
272
+ inkatakanaphoneticextensions,in_katakana_phonetic_extensions
273
+ inkayahli,in_kayah_li
274
+ inkharoshthi,in_kharoshthi
275
+ inkhitansmallscript,in_khitan_small_script
276
+ inkhmer,in_khmer
277
+ inkhmersymbols,in_khmer_symbols
278
+ inkhojki,in_khojki
279
+ inkhudawadi,in_khudawadi
280
+ inlao,in_lao
281
+ inlatin1supplement,in_latin_1_supplement
282
+ inlatinextendeda,in_latin_extended_a
283
+ inlatinextendedadditional,in_latin_extended_additional
284
+ inlatinextendedb,in_latin_extended_b
285
+ inlatinextendedc,in_latin_extended_c
286
+ inlatinextendedd,in_latin_extended_d
287
+ inlatinextendede,in_latin_extended_e
288
+ inlepcha,in_lepcha
289
+ inletterlikesymbols,in_letterlike_symbols
290
+ inlimbu,in_limbu
291
+ inlineara,in_linear_a
292
+ inlinearbideograms,in_linear_b_ideograms
293
+ inlinearbsyllabary,in_linear_b_syllabary
294
+ inlisu,in_lisu
295
+ inlisusupplement,in_lisu_supplement
296
+ inlowsurrogates,in_low_surrogates
297
+ inlycian,in_lycian
298
+ inlydian,in_lydian
299
+ inmahajani,in_mahajani
300
+ inmahjongtiles,in_mahjong_tiles
301
+ inmakasar,in_makasar
302
+ inmalayalam,in_malayalam
303
+ inmandaic,in_mandaic
304
+ inmanichaean,in_manichaean
305
+ inmarchen,in_marchen
306
+ inmasaramgondi,in_masaram_gondi
307
+ inmathematicalalphanumericsymbols,in_mathematical_alphanumeric_symbols
308
+ inmathematicaloperators,in_mathematical_operators
309
+ inmayannumerals,in_mayan_numerals
310
+ inmedefaidrin,in_medefaidrin
311
+ inmeeteimayek,in_meetei_mayek
312
+ inmeeteimayekextensions,in_meetei_mayek_extensions
313
+ inmendekikakui,in_mende_kikakui
314
+ inmeroiticcursive,in_meroitic_cursive
315
+ inmeroitichieroglyphs,in_meroitic_hieroglyphs
316
+ inmiao,in_miao
317
+ inmiscellaneousmathematicalsymbolsa,in_miscellaneous_mathematical_symbols_a
318
+ inmiscellaneousmathematicalsymbolsb,in_miscellaneous_mathematical_symbols_b
319
+ inmiscellaneoussymbols,in_miscellaneous_symbols
320
+ inmiscellaneoussymbolsandarrows,in_miscellaneous_symbols_and_arrows
321
+ inmiscellaneoussymbolsandpictographs,in_miscellaneous_symbols_and_pictographs
322
+ inmiscellaneoustechnical,in_miscellaneous_technical
323
+ inmodi,in_modi
324
+ inmodifiertoneletters,in_modifier_tone_letters
325
+ inmongolian,in_mongolian
326
+ inmongoliansupplement,in_mongolian_supplement
327
+ inmro,in_mro
328
+ inmultani,in_multani
329
+ inmusicalsymbols,in_musical_symbols
330
+ inmyanmar,in_myanmar
331
+ inmyanmarextendeda,in_myanmar_extended_a
332
+ inmyanmarextendedb,in_myanmar_extended_b
333
+ innabataean,in_nabataean
334
+ innandinagari,in_nandinagari
335
+ innewa,in_newa
336
+ innewtailue,in_new_tai_lue
337
+ innko,in_nko
338
+ innoblock,in_no_block
339
+ innumberforms,in_number_forms
340
+ innushu,in_nushu
341
+ innyiakengpuachuehmong,in_nyiakeng_puachue_hmong
342
+ inogham,in_ogham
343
+ inolchiki,in_ol_chiki
344
+ inoldhungarian,in_old_hungarian
345
+ inolditalic,in_old_italic
346
+ inoldnortharabian,in_old_north_arabian
347
+ inoldpermic,in_old_permic
348
+ inoldpersian,in_old_persian
349
+ inoldsogdian,in_old_sogdian
350
+ inoldsoutharabian,in_old_south_arabian
351
+ inoldturkic,in_old_turkic
352
+ inopticalcharacterrecognition,in_optical_character_recognition
353
+ inoriya,in_oriya
354
+ inornamentaldingbats,in_ornamental_dingbats
355
+ inosage,in_osage
356
+ inosmanya,in_osmanya
357
+ inottomansiyaqnumbers,in_ottoman_siyaq_numbers
358
+ inpahawhhmong,in_pahawh_hmong
359
+ inpalmyrene,in_palmyrene
360
+ inpaucinhau,in_pau_cin_hau
361
+ inphagspa,in_phags_pa
362
+ inphaistosdisc,in_phaistos_disc
363
+ inphoenician,in_phoenician
364
+ inphoneticextensions,in_phonetic_extensions
365
+ inphoneticextensionssupplement,in_phonetic_extensions_supplement
366
+ inplayingcards,in_playing_cards
367
+ inprivateusearea,in_private_use_area
368
+ inpsalterpahlavi,in_psalter_pahlavi
369
+ inrejang,in_rejang
370
+ inruminumeralsymbols,in_rumi_numeral_symbols
371
+ inrunic,in_runic
372
+ insamaritan,in_samaritan
373
+ insaurashtra,in_saurashtra
374
+ inscriptionalpahlavi,inscriptional_pahlavi
375
+ inscriptionalparthian,inscriptional_parthian
376
+ insharada,in_sharada
377
+ inshavian,in_shavian
378
+ inshorthandformatcontrols,in_shorthand_format_controls
379
+ insiddham,in_siddham
380
+ insinhala,in_sinhala
381
+ insinhalaarchaicnumbers,in_sinhala_archaic_numbers
382
+ insmallformvariants,in_small_form_variants
383
+ insmallkanaextension,in_small_kana_extension
384
+ insogdian,in_sogdian
385
+ insorasompeng,in_sora_sompeng
386
+ insoyombo,in_soyombo
387
+ inspacingmodifierletters,in_spacing_modifier_letters
388
+ inspecials,in_specials
389
+ insundanese,in_sundanese
390
+ insundanesesupplement,in_sundanese_supplement
391
+ insuperscriptsandsubscripts,in_superscripts_and_subscripts
392
+ insupplementalarrowsa,in_supplemental_arrows_a
393
+ insupplementalarrowsb,in_supplemental_arrows_b
394
+ insupplementalarrowsc,in_supplemental_arrows_c
395
+ insupplementalmathematicaloperators,in_supplemental_mathematical_operators
396
+ insupplementalpunctuation,in_supplemental_punctuation
397
+ insupplementalsymbolsandpictographs,in_supplemental_symbols_and_pictographs
398
+ insupplementaryprivateuseareaa,in_supplementary_private_use_area_a
399
+ insupplementaryprivateuseareab,in_supplementary_private_use_area_b
400
+ insuttonsignwriting,in_sutton_signwriting
401
+ insylotinagri,in_syloti_nagri
402
+ insymbolsandpictographsextendeda,in_symbols_and_pictographs_extended_a
403
+ insymbolsforlegacycomputing,in_symbols_for_legacy_computing
404
+ insyriac,in_syriac
405
+ insyriacsupplement,in_syriac_supplement
406
+ intagalog,in_tagalog
407
+ intagbanwa,in_tagbanwa
408
+ intags,in_tags
409
+ intaile,in_tai_le
410
+ intaitham,in_tai_tham
411
+ intaiviet,in_tai_viet
412
+ intaixuanjingsymbols,in_tai_xuan_jing_symbols
413
+ intakri,in_takri
414
+ intamil,in_tamil
415
+ intamilsupplement,in_tamil_supplement
416
+ intangut,in_tangut
417
+ intangutcomponents,in_tangut_components
418
+ intangutsupplement,in_tangut_supplement
419
+ intelugu,in_telugu
420
+ inthaana,in_thaana
421
+ inthai,in_thai
422
+ intibetan,in_tibetan
423
+ intifinagh,in_tifinagh
424
+ intirhuta,in_tirhuta
425
+ intransportandmapsymbols,in_transport_and_map_symbols
426
+ inugaritic,in_ugaritic
427
+ inunifiedcanadianaboriginalsyllabics,in_unified_canadian_aboriginal_syllabics
428
+ inunifiedcanadianaboriginalsyllabicsextended,in_unified_canadian_aboriginal_syllabics_extended
429
+ invai,in_vai
430
+ invariationselectors,in_variation_selectors
431
+ invariationselectorssupplement,in_variation_selectors_supplement
432
+ invedicextensions,in_vedic_extensions
433
+ inverticalforms,in_vertical_forms
434
+ inwancho,in_wancho
435
+ inwarangciti,in_warang_citi
436
+ inyezidi,in_yezidi
437
+ inyijinghexagramsymbols,in_yijing_hexagram_symbols
438
+ inyiradicals,in_yi_radicals
439
+ inyisyllables,in_yi_syllables
440
+ inzanabazarsquare,in_zanabazar_square
441
+ javanese,javanese
442
+ joincontrol,join_control
443
+ kaithi,kaithi
444
+ kannada,kannada
445
+ katakana,katakana
446
+ kayahli,kayah_li
447
+ kharoshthi,kharoshthi
448
+ khitansmallscript,khitan_small_script
449
+ khmer,khmer
450
+ khojki,khojki
451
+ khudawadi,khudawadi
452
+ lao,lao
453
+ latin,latin
454
+ lepcha,lepcha
455
+ letter,letter
456
+ letternumber,letter_number
457
+ limbu,limbu
458
+ lineara,linear_a
459
+ linearb,linear_b
460
+ lineseparator,line_separator
461
+ lisu,lisu
462
+ logicalorderexception,logical_order_exception
463
+ lower,lower
464
+ lowercase,lowercase
465
+ lowercaseletter,lowercase_letter
466
+ lycian,lycian
467
+ lydian,lydian
468
+ mahajani,mahajani
469
+ makasar,makasar
470
+ malayalam,malayalam
471
+ mandaic,mandaic
472
+ manichaean,manichaean
473
+ marchen,marchen
474
+ mark,mark
475
+ masaramgondi,masaram_gondi
476
+ math,math
477
+ mathsymbol,math_symbol
478
+ medefaidrin,medefaidrin
479
+ meeteimayek,meetei_mayek
480
+ mendekikakui,mende_kikakui
481
+ meroiticcursive,meroitic_cursive
482
+ meroitichieroglyphs,meroitic_hieroglyphs
483
+ miao,miao
484
+ modi,modi
485
+ modifierletter,modifier_letter
486
+ modifiersymbol,modifier_symbol
487
+ mongolian,mongolian
488
+ mro,mro
489
+ multani,multani
490
+ myanmar,myanmar
491
+ nabataean,nabataean
492
+ nandinagari,nandinagari
493
+ newa,newa
494
+ newline,newline
495
+ newtailue,new_tai_lue
496
+ nko,nko
497
+ noncharactercodepoint,noncharacter_code_point
498
+ nonspacingmark,nonspacing_mark
499
+ number,number
500
+ nushu,nushu
501
+ nyiakengpuachuehmong,nyiakeng_puachue_hmong
502
+ ogham,ogham
503
+ olchiki,ol_chiki
504
+ oldhungarian,old_hungarian
505
+ olditalic,old_italic
506
+ oldnortharabian,old_north_arabian
507
+ oldpermic,old_permic
508
+ oldpersian,old_persian
509
+ oldsogdian,old_sogdian
510
+ oldsoutharabian,old_south_arabian
511
+ oldturkic,old_turkic
512
+ openpunctuation,open_punctuation
513
+ oriya,oriya
514
+ osage,osage
515
+ osmanya,osmanya
516
+ other,other
517
+ otheralphabetic,other_alphabetic
518
+ otherdefaultignorablecodepoint,other_default_ignorable_code_point
519
+ othergraphemeextend,other_grapheme_extend
520
+ otheridcontinue,other_id_continue
521
+ otheridstart,other_id_start
522
+ otherletter,other_letter
523
+ otherlowercase,other_lowercase
524
+ othermath,other_math
525
+ othernumber,other_number
526
+ otherpunctuation,other_punctuation
527
+ othersymbol,other_symbol
528
+ otheruppercase,other_uppercase
529
+ pahawhhmong,pahawh_hmong
530
+ palmyrene,palmyrene
531
+ paragraphseparator,paragraph_separator
532
+ patternsyntax,pattern_syntax
533
+ patternwhitespace,pattern_white_space
534
+ paucinhau,pau_cin_hau
535
+ phagspa,phags_pa
536
+ phoenician,phoenician
537
+ prependedconcatenationmark,prepended_concatenation_mark
538
+ print,print
539
+ privateuse,private_use
540
+ psalterpahlavi,psalter_pahlavi
541
+ punct,punct
542
+ punctuation,punctuation
543
+ quotationmark,quotation_mark
544
+ radical,radical
545
+ regionalindicator,regional_indicator
546
+ rejang,rejang
547
+ runic,runic
548
+ samaritan,samaritan
549
+ saurashtra,saurashtra
550
+ sentenceterminal,sentence_terminal
551
+ separator,separator
552
+ sharada,sharada
553
+ shavian,shavian
554
+ siddham,siddham
555
+ signwriting,signwriting
556
+ sinhala,sinhala
557
+ softdotted,soft_dotted
558
+ sogdian,sogdian
559
+ sorasompeng,sora_sompeng
560
+ soyombo,soyombo
561
+ space,space
562
+ spaceseparator,space_separator
563
+ spacingmark,spacing_mark
564
+ sundanese,sundanese
565
+ surrogate,surrogate
566
+ sylotinagri,syloti_nagri
567
+ symbol,symbol
568
+ syriac,syriac
569
+ tagalog,tagalog
570
+ tagbanwa,tagbanwa
571
+ taile,tai_le
572
+ taitham,tai_tham
573
+ taiviet,tai_viet
574
+ takri,takri
575
+ tamil,tamil
576
+ tangut,tangut
577
+ telugu,telugu
578
+ terminalpunctuation,terminal_punctuation
579
+ thaana,thaana
580
+ thai,thai
581
+ tibetan,tibetan
582
+ tifinagh,tifinagh
583
+ tirhuta,tirhuta
584
+ titlecaseletter,titlecase_letter
585
+ ugaritic,ugaritic
586
+ unassigned,unassigned
587
+ unifiedideograph,unified_ideograph
588
+ unknown,unknown
589
+ upper,upper
590
+ uppercase,uppercase
591
+ uppercaseletter,uppercase_letter
592
+ vai,vai
593
+ variationselector,variation_selector
594
+ wancho,wancho
595
+ warangciti,warang_citi
596
+ whitespace,white_space
597
+ word,word
598
+ xdigit,xdigit
599
+ xidcontinue,xid_continue
600
+ xidstart,xid_start
601
+ xposixpunct,xposixpunct
602
+ yezidi,yezidi
603
+ yi,yi
604
+ zanabazarsquare,zanabazar_square