RubyGems - regexp_parser - Versions diffs - 1.7.0 → 2.8.3 - Mend

regexp_parser 1.7.0 → 2.8.3

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 (165) hide show

checksums.yaml +4 -4
data/Gemfile +8 -2
data/LICENSE +1 -1
data/Rakefile +6 -70
data/lib/regexp_parser/error.rb +4 -0
data/lib/regexp_parser/expression/base.rb +76 -0
data/lib/regexp_parser/expression/classes/alternation.rb +1 -1
data/lib/regexp_parser/expression/classes/anchor.rb +0 -2
data/lib/regexp_parser/expression/classes/{backref.rb → backreference.rb} +22 -2
data/lib/regexp_parser/expression/classes/{set → character_set}/range.rb +4 -8
data/lib/regexp_parser/expression/classes/{set.rb → character_set.rb} +3 -4
data/lib/regexp_parser/expression/classes/{type.rb → character_type.rb} +0 -2
data/lib/regexp_parser/expression/classes/conditional.rb +11 -5
data/lib/regexp_parser/expression/classes/{escape.rb → escape_sequence.rb} +15 -7
data/lib/regexp_parser/expression/classes/free_space.rb +5 -5
data/lib/regexp_parser/expression/classes/group.rb +28 -15
data/lib/regexp_parser/expression/classes/keep.rb +2 -0
data/lib/regexp_parser/expression/classes/literal.rb +1 -5
data/lib/regexp_parser/expression/classes/posix_class.rb +5 -1
data/lib/regexp_parser/expression/classes/root.rb +4 -19
data/lib/regexp_parser/expression/classes/{property.rb → unicode_property.rb} +5 -3
data/lib/regexp_parser/expression/methods/construct.rb +41 -0
data/lib/regexp_parser/expression/methods/human_name.rb +43 -0
data/lib/regexp_parser/expression/methods/match_length.rb +11 -7
data/lib/regexp_parser/expression/methods/parts.rb +23 -0
data/lib/regexp_parser/expression/methods/printing.rb +26 -0
data/lib/regexp_parser/expression/methods/strfregexp.rb +1 -1
data/lib/regexp_parser/expression/methods/tests.rb +47 -1
data/lib/regexp_parser/expression/methods/traverse.rb +34 -18
data/lib/regexp_parser/expression/quantifier.rb +57 -17
data/lib/regexp_parser/expression/sequence.rb +11 -47
data/lib/regexp_parser/expression/sequence_operation.rb +4 -9
data/lib/regexp_parser/expression/shared.rb +111 -0
data/lib/regexp_parser/expression/subexpression.rb +27 -19
data/lib/regexp_parser/expression.rb +14 -141
data/lib/regexp_parser/lexer.rb +83 -41
data/lib/regexp_parser/parser.rb +371 -429
data/lib/regexp_parser/scanner/char_type.rl +11 -11
data/lib/regexp_parser/scanner/errors/premature_end_error.rb +8 -0
data/lib/regexp_parser/scanner/errors/scanner_error.rb +6 -0
data/lib/regexp_parser/scanner/errors/validation_error.rb +63 -0
data/lib/regexp_parser/scanner/properties/long.csv +633 -0
data/lib/regexp_parser/scanner/properties/short.csv +248 -0
data/lib/regexp_parser/scanner/property.rl +4 -4
data/lib/regexp_parser/scanner/scanner.rl +303 -368
data/lib/regexp_parser/scanner.rb +1423 -1674
data/lib/regexp_parser/syntax/any.rb +2 -7
data/lib/regexp_parser/syntax/base.rb +92 -67
data/lib/regexp_parser/syntax/token/anchor.rb +15 -0
data/lib/regexp_parser/syntax/{tokens → token}/assertion.rb +2 -2
data/lib/regexp_parser/syntax/token/backreference.rb +33 -0
data/lib/regexp_parser/syntax/token/character_set.rb +16 -0
data/lib/regexp_parser/syntax/{tokens → token}/character_type.rb +3 -3
data/lib/regexp_parser/syntax/{tokens → token}/conditional.rb +3 -3
data/lib/regexp_parser/syntax/token/escape.rb +33 -0
data/lib/regexp_parser/syntax/{tokens → token}/group.rb +7 -7
data/lib/regexp_parser/syntax/{tokens → token}/keep.rb +1 -1
data/lib/regexp_parser/syntax/token/meta.rb +20 -0
data/lib/regexp_parser/syntax/{tokens → token}/posix_class.rb +3 -3
data/lib/regexp_parser/syntax/token/quantifier.rb +35 -0
data/lib/regexp_parser/syntax/token/unicode_property.rb +733 -0
data/lib/regexp_parser/syntax/token/virtual.rb +11 -0
data/lib/regexp_parser/syntax/token.rb +45 -0
data/lib/regexp_parser/syntax/version_lookup.rb +19 -36
data/lib/regexp_parser/syntax/versions/1.8.6.rb +13 -20
data/lib/regexp_parser/syntax/versions/1.9.1.rb +10 -17
data/lib/regexp_parser/syntax/versions/1.9.3.rb +3 -10
data/lib/regexp_parser/syntax/versions/2.0.0.rb +8 -15
data/lib/regexp_parser/syntax/versions/2.2.0.rb +3 -9
data/lib/regexp_parser/syntax/versions/2.3.0.rb +3 -9
data/lib/regexp_parser/syntax/versions/2.4.0.rb +3 -9
data/lib/regexp_parser/syntax/versions/2.4.1.rb +2 -8
data/lib/regexp_parser/syntax/versions/2.5.0.rb +3 -9
data/lib/regexp_parser/syntax/versions/2.6.0.rb +3 -9
data/lib/regexp_parser/syntax/versions/2.6.2.rb +3 -9
data/lib/regexp_parser/syntax/versions/2.6.3.rb +3 -9
data/lib/regexp_parser/syntax/versions/3.1.0.rb +4 -0
data/lib/regexp_parser/syntax/versions/3.2.0.rb +4 -0
data/lib/regexp_parser/syntax/versions.rb +3 -1
data/lib/regexp_parser/syntax.rb +8 -6
data/lib/regexp_parser/token.rb +9 -20
data/lib/regexp_parser/version.rb +1 -1
data/lib/regexp_parser.rb +0 -2
data/regexp_parser.gemspec +19 -23
metadata +52 -171
data/CHANGELOG.md +0 -349
data/README.md +0 -470
data/lib/regexp_parser/scanner/properties/long.yml +0 -594
data/lib/regexp_parser/scanner/properties/short.yml +0 -237
data/lib/regexp_parser/syntax/tokens/anchor.rb +0 -15
data/lib/regexp_parser/syntax/tokens/backref.rb +0 -24
data/lib/regexp_parser/syntax/tokens/character_set.rb +0 -13
data/lib/regexp_parser/syntax/tokens/escape.rb +0 -30
data/lib/regexp_parser/syntax/tokens/meta.rb +0 -13
data/lib/regexp_parser/syntax/tokens/quantifier.rb +0 -35
data/lib/regexp_parser/syntax/tokens/unicode_property.rb +0 -675
data/lib/regexp_parser/syntax/tokens.rb +0 -45
data/spec/expression/base_spec.rb +0 -94
data/spec/expression/clone_spec.rb +0 -120
data/spec/expression/conditional_spec.rb +0 -89
data/spec/expression/free_space_spec.rb +0 -27
data/spec/expression/methods/match_length_spec.rb +0 -161
data/spec/expression/methods/match_spec.rb +0 -25
data/spec/expression/methods/strfregexp_spec.rb +0 -224
data/spec/expression/methods/tests_spec.rb +0 -99
data/spec/expression/methods/traverse_spec.rb +0 -161
data/spec/expression/options_spec.rb +0 -128
data/spec/expression/root_spec.rb +0 -9
data/spec/expression/sequence_spec.rb +0 -9
data/spec/expression/subexpression_spec.rb +0 -50
data/spec/expression/to_h_spec.rb +0 -26
data/spec/expression/to_s_spec.rb +0 -100
data/spec/lexer/all_spec.rb +0 -22
data/spec/lexer/conditionals_spec.rb +0 -53
data/spec/lexer/escapes_spec.rb +0 -14
data/spec/lexer/keep_spec.rb +0 -10
data/spec/lexer/literals_spec.rb +0 -89
data/spec/lexer/nesting_spec.rb +0 -99
data/spec/lexer/refcalls_spec.rb +0 -55
data/spec/parser/all_spec.rb +0 -43
data/spec/parser/alternation_spec.rb +0 -88
data/spec/parser/anchors_spec.rb +0 -17
data/spec/parser/conditionals_spec.rb +0 -179
data/spec/parser/errors_spec.rb +0 -30
data/spec/parser/escapes_spec.rb +0 -121
data/spec/parser/free_space_spec.rb +0 -130
data/spec/parser/groups_spec.rb +0 -108
data/spec/parser/keep_spec.rb +0 -6
data/spec/parser/posix_classes_spec.rb +0 -8
data/spec/parser/properties_spec.rb +0 -115
data/spec/parser/quantifiers_spec.rb +0 -51
data/spec/parser/refcalls_spec.rb +0 -112
data/spec/parser/set/intersections_spec.rb +0 -127
data/spec/parser/set/ranges_spec.rb +0 -111
data/spec/parser/sets_spec.rb +0 -178
data/spec/parser/types_spec.rb +0 -18
data/spec/scanner/all_spec.rb +0 -18
data/spec/scanner/anchors_spec.rb +0 -21
data/spec/scanner/conditionals_spec.rb +0 -128
data/spec/scanner/errors_spec.rb +0 -68
data/spec/scanner/escapes_spec.rb +0 -53
data/spec/scanner/free_space_spec.rb +0 -133
data/spec/scanner/groups_spec.rb +0 -52
data/spec/scanner/keep_spec.rb +0 -10
data/spec/scanner/literals_spec.rb +0 -49
data/spec/scanner/meta_spec.rb +0 -18
data/spec/scanner/properties_spec.rb +0 -64
data/spec/scanner/quantifiers_spec.rb +0 -20
data/spec/scanner/refcalls_spec.rb +0 -36
data/spec/scanner/sets_spec.rb +0 -102
data/spec/scanner/types_spec.rb +0 -14
data/spec/spec_helper.rb +0 -15
data/spec/support/runner.rb +0 -42
data/spec/support/shared_examples.rb +0 -77
data/spec/support/warning_extractor.rb +0 -60
data/spec/syntax/syntax_spec.rb +0 -48
data/spec/syntax/syntax_token_map_spec.rb +0 -23
data/spec/syntax/versions/1.8.6_spec.rb +0 -17
data/spec/syntax/versions/1.9.1_spec.rb +0 -10
data/spec/syntax/versions/1.9.3_spec.rb +0 -9
data/spec/syntax/versions/2.0.0_spec.rb +0 -13
data/spec/syntax/versions/2.2.0_spec.rb +0 -9
data/spec/syntax/versions/aliases_spec.rb +0 -37
data/spec/token/token_spec.rb +0 -85
/data/lib/regexp_parser/expression/classes/{set → character_set}/intersection.rb +0 -0

data/lib/regexp_parser/scanner/properties/long.csv ADDED Viewed

@@ -0,0 +1,633 @@
+# THIS FILE IS AUTO-GENERATED BY `rake props:update` - DO NOT EDIT
+adlam,adlam
+age=1.1,age=1.1
+age=10.0,age=10.0
+age=11.0,age=11.0
+age=12.0,age=12.0
+age=12.1,age=12.1
+age=13.0,age=13.0
+age=14.0,age=14.0
+age=15.0,age=15.0
+age=2.0,age=2.0
+age=2.1,age=2.1
+age=3.0,age=3.0
+age=3.1,age=3.1
+age=3.2,age=3.2
+age=4.0,age=4.0
+age=4.1,age=4.1
+age=5.0,age=5.0
+age=5.1,age=5.1
+age=5.2,age=5.2
+age=6.0,age=6.0
+age=6.1,age=6.1
+age=6.2,age=6.2
+age=6.3,age=6.3
+age=7.0,age=7.0
+age=8.0,age=8.0
+age=9.0,age=9.0
+ahom,ahom
+alnum,alnum
+alpha,alpha
+alphabetic,alphabetic
+anatolianhieroglyphs,anatolian_hieroglyphs
+any,any
+arabic,arabic
+armenian,armenian
+ascii,ascii
+asciihexdigit,ascii_hex_digit
+assigned,assigned
+avestan,avestan
+balinese,balinese
+bamum,bamum
+bassavah,bassa_vah
+batak,batak
+bengali,bengali
+bhaiksuki,bhaiksuki
+bidicontrol,bidi_control
+blank,blank
+bopomofo,bopomofo
+brahmi,brahmi
+braille,braille
+buginese,buginese
+buhid,buhid
+canadianaboriginal,canadian_aboriginal
+carian,carian
+cased,cased
+casedletter,cased_letter
+caseignorable,case_ignorable
+caucasianalbanian,caucasian_albanian
+chakma,chakma
+cham,cham
+changeswhencasefolded,changes_when_casefolded
+changeswhencasemapped,changes_when_casemapped
+changeswhenlowercased,changes_when_lowercased
+changeswhentitlecased,changes_when_titlecased
+changeswhenuppercased,changes_when_uppercased
+cherokee,cherokee
+chorasmian,chorasmian
+closepunctuation,close_punctuation
+cntrl,cntrl
+common,common
+connectorpunctuation,connector_punctuation
+control,control
+coptic,coptic
+cuneiform,cuneiform
+currencysymbol,currency_symbol
+cypriot,cypriot
+cyprominoan,cypro_minoan
+cyrillic,cyrillic
+dash,dash
+dashpunctuation,dash_punctuation
+decimalnumber,decimal_number
+defaultignorablecodepoint,default_ignorable_code_point
+deprecated,deprecated
+deseret,deseret
+devanagari,devanagari
+diacritic,diacritic
+digit,digit
+divesakuru,dives_akuru
+dogra,dogra
+duployan,duployan
+egyptianhieroglyphs,egyptian_hieroglyphs
+elbasan,elbasan
+elymaic,elymaic
+emoji,emoji
+emojicomponent,emoji_component
+emojimodifier,emoji_modifier
+emojimodifierbase,emoji_modifier_base
+emojipresentation,emoji_presentation
+enclosingmark,enclosing_mark
+ethiopic,ethiopic
+extendedpictographic,extended_pictographic
+extender,extender
+finalpunctuation,final_punctuation
+format,format
+georgian,georgian
+glagolitic,glagolitic
+gothic,gothic
+grantha,grantha
+graph,graph
+graphemebase,grapheme_base
+graphemeextend,grapheme_extend
+graphemelink,grapheme_link
+greek,greek
+gujarati,gujarati
+gunjalagondi,gunjala_gondi
+gurmukhi,gurmukhi
+han,han
+hangul,hangul
+hanifirohingya,hanifi_rohingya
+hanunoo,hanunoo
+hatran,hatran
+hebrew,hebrew
+hexdigit,hex_digit
+hiragana,hiragana
+hyphen,hyphen
+idcontinue,id_continue
+ideographic,ideographic
+idsbinaryoperator,ids_binary_operator
+idstart,id_start
+idstrinaryoperator,ids_trinary_operator
+imperialaramaic,imperial_aramaic
+inadlam,in_adlam
+inaegeannumbers,in_aegean_numbers
+inahom,in_ahom
+inalchemicalsymbols,in_alchemical_symbols
+inalphabeticpresentationforms,in_alphabetic_presentation_forms
+inanatolianhieroglyphs,in_anatolian_hieroglyphs
+inancientgreekmusicalnotation,in_ancient_greek_musical_notation
+inancientgreeknumbers,in_ancient_greek_numbers
+inancientsymbols,in_ancient_symbols
+inarabic,in_arabic
+inarabicextendeda,in_arabic_extended_a
+inarabicextendedb,in_arabic_extended_b
+inarabicextendedc,in_arabic_extended_c
+inarabicmathematicalalphabeticsymbols,in_arabic_mathematical_alphabetic_symbols
+inarabicpresentationformsa,in_arabic_presentation_forms_a
+inarabicpresentationformsb,in_arabic_presentation_forms_b
+inarabicsupplement,in_arabic_supplement
+inarmenian,in_armenian
+inarrows,in_arrows
+inavestan,in_avestan
+inbalinese,in_balinese
+inbamum,in_bamum
+inbamumsupplement,in_bamum_supplement
+inbasiclatin,in_basic_latin
+inbassavah,in_bassa_vah
+inbatak,in_batak
+inbengali,in_bengali
+inbhaiksuki,in_bhaiksuki
+inblockelements,in_block_elements
+inbopomofo,in_bopomofo
+inbopomofoextended,in_bopomofo_extended
+inboxdrawing,in_box_drawing
+inbrahmi,in_brahmi
+inbraillepatterns,in_braille_patterns
+inbuginese,in_buginese
+inbuhid,in_buhid
+inbyzantinemusicalsymbols,in_byzantine_musical_symbols
+incarian,in_carian
+incaucasianalbanian,in_caucasian_albanian
+inchakma,in_chakma
+incham,in_cham
+incherokee,in_cherokee
+incherokeesupplement,in_cherokee_supplement
+inchesssymbols,in_chess_symbols
+inchorasmian,in_chorasmian
+incjkcompatibility,in_cjk_compatibility
+incjkcompatibilityforms,in_cjk_compatibility_forms
+incjkcompatibilityideographs,in_cjk_compatibility_ideographs
+incjkcompatibilityideographssupplement,in_cjk_compatibility_ideographs_supplement
+incjkradicalssupplement,in_cjk_radicals_supplement
+incjkstrokes,in_cjk_strokes
+incjksymbolsandpunctuation,in_cjk_symbols_and_punctuation
+incjkunifiedideographs,in_cjk_unified_ideographs
+incjkunifiedideographsextensiona,in_cjk_unified_ideographs_extension_a
+incjkunifiedideographsextensionb,in_cjk_unified_ideographs_extension_b
+incjkunifiedideographsextensionc,in_cjk_unified_ideographs_extension_c
+incjkunifiedideographsextensiond,in_cjk_unified_ideographs_extension_d
+incjkunifiedideographsextensione,in_cjk_unified_ideographs_extension_e
+incjkunifiedideographsextensionf,in_cjk_unified_ideographs_extension_f
+incjkunifiedideographsextensiong,in_cjk_unified_ideographs_extension_g
+incjkunifiedideographsextensionh,in_cjk_unified_ideographs_extension_h
+incombiningdiacriticalmarks,in_combining_diacritical_marks
+incombiningdiacriticalmarksextended,in_combining_diacritical_marks_extended
+incombiningdiacriticalmarksforsymbols,in_combining_diacritical_marks_for_symbols
+incombiningdiacriticalmarkssupplement,in_combining_diacritical_marks_supplement
+incombininghalfmarks,in_combining_half_marks
+incommonindicnumberforms,in_common_indic_number_forms
+incontrolpictures,in_control_pictures
+incoptic,in_coptic
+incopticepactnumbers,in_coptic_epact_numbers
+incountingrodnumerals,in_counting_rod_numerals
+incuneiform,in_cuneiform
+incuneiformnumbersandpunctuation,in_cuneiform_numbers_and_punctuation
+incurrencysymbols,in_currency_symbols
+incypriotsyllabary,in_cypriot_syllabary
+incyprominoan,in_cypro_minoan
+incyrillic,in_cyrillic
+incyrillicextendeda,in_cyrillic_extended_a
+incyrillicextendedb,in_cyrillic_extended_b
+incyrillicextendedc,in_cyrillic_extended_c
+incyrillicextendedd,in_cyrillic_extended_d
+incyrillicsupplement,in_cyrillic_supplement
+indeseret,in_deseret
+indevanagari,in_devanagari
+indevanagariextended,in_devanagari_extended
+indevanagariextendeda,in_devanagari_extended_a
+indingbats,in_dingbats
+indivesakuru,in_dives_akuru
+indogra,in_dogra
+indominotiles,in_domino_tiles
+induployan,in_duployan
+inearlydynasticcuneiform,in_early_dynastic_cuneiform
+inegyptianhieroglyphformatcontrols,in_egyptian_hieroglyph_format_controls
+inegyptianhieroglyphs,in_egyptian_hieroglyphs
+inelbasan,in_elbasan
+inelymaic,in_elymaic
+inemoticons,in_emoticons
+inenclosedalphanumerics,in_enclosed_alphanumerics
+inenclosedalphanumericsupplement,in_enclosed_alphanumeric_supplement
+inenclosedcjklettersandmonths,in_enclosed_cjk_letters_and_months
+inenclosedideographicsupplement,in_enclosed_ideographic_supplement
+inethiopic,in_ethiopic
+inethiopicextended,in_ethiopic_extended
+inethiopicextendeda,in_ethiopic_extended_a
+inethiopicextendedb,in_ethiopic_extended_b
+inethiopicsupplement,in_ethiopic_supplement
+ingeneralpunctuation,in_general_punctuation
+ingeometricshapes,in_geometric_shapes
+ingeometricshapesextended,in_geometric_shapes_extended
+ingeorgian,in_georgian
+ingeorgianextended,in_georgian_extended
+ingeorgiansupplement,in_georgian_supplement
+inglagolitic,in_glagolitic
+inglagoliticsupplement,in_glagolitic_supplement
+ingothic,in_gothic
+ingrantha,in_grantha
+ingreekandcoptic,in_greek_and_coptic
+ingreekextended,in_greek_extended
+ingujarati,in_gujarati
+ingunjalagondi,in_gunjala_gondi
+ingurmukhi,in_gurmukhi
+inhalfwidthandfullwidthforms,in_halfwidth_and_fullwidth_forms
+inhangulcompatibilityjamo,in_hangul_compatibility_jamo
+inhanguljamo,in_hangul_jamo
+inhanguljamoextendeda,in_hangul_jamo_extended_a
+inhanguljamoextendedb,in_hangul_jamo_extended_b
+inhangulsyllables,in_hangul_syllables
+inhanifirohingya,in_hanifi_rohingya
+inhanunoo,in_hanunoo
+inhatran,in_hatran
+inhebrew,in_hebrew
+inherited,inherited
+inhighprivateusesurrogates,in_high_private_use_surrogates
+inhighsurrogates,in_high_surrogates
+inhiragana,in_hiragana
+inideographicdescriptioncharacters,in_ideographic_description_characters
+inideographicsymbolsandpunctuation,in_ideographic_symbols_and_punctuation
+inimperialaramaic,in_imperial_aramaic
+inindicsiyaqnumbers,in_indic_siyaq_numbers
+ininscriptionalpahlavi,in_inscriptional_pahlavi
+ininscriptionalparthian,in_inscriptional_parthian
+inipaextensions,in_ipa_extensions
+initialpunctuation,initial_punctuation
+injavanese,in_javanese
+inkaithi,in_kaithi
+inkaktoviknumerals,in_kaktovik_numerals
+inkanaextendeda,in_kana_extended_a
+inkanaextendedb,in_kana_extended_b
+inkanasupplement,in_kana_supplement
+inkanbun,in_kanbun
+inkangxiradicals,in_kangxi_radicals
+inkannada,in_kannada
+inkatakana,in_katakana
+inkatakanaphoneticextensions,in_katakana_phonetic_extensions
+inkawi,in_kawi
+inkayahli,in_kayah_li
+inkharoshthi,in_kharoshthi
+inkhitansmallscript,in_khitan_small_script
+inkhmer,in_khmer
+inkhmersymbols,in_khmer_symbols
+inkhojki,in_khojki
+inkhudawadi,in_khudawadi
+inlao,in_lao
+inlatin1supplement,in_latin_1_supplement
+inlatinextendeda,in_latin_extended_a
+inlatinextendedadditional,in_latin_extended_additional
+inlatinextendedb,in_latin_extended_b
+inlatinextendedc,in_latin_extended_c
+inlatinextendedd,in_latin_extended_d
+inlatinextendede,in_latin_extended_e
+inlatinextendedf,in_latin_extended_f
+inlatinextendedg,in_latin_extended_g
+inlepcha,in_lepcha
+inletterlikesymbols,in_letterlike_symbols
+inlimbu,in_limbu
+inlineara,in_linear_a
+inlinearbideograms,in_linear_b_ideograms
+inlinearbsyllabary,in_linear_b_syllabary
+inlisu,in_lisu
+inlisusupplement,in_lisu_supplement
+inlowsurrogates,in_low_surrogates
+inlycian,in_lycian
+inlydian,in_lydian
+inmahajani,in_mahajani
+inmahjongtiles,in_mahjong_tiles
+inmakasar,in_makasar
+inmalayalam,in_malayalam
+inmandaic,in_mandaic
+inmanichaean,in_manichaean
+inmarchen,in_marchen
+inmasaramgondi,in_masaram_gondi
+inmathematicalalphanumericsymbols,in_mathematical_alphanumeric_symbols
+inmathematicaloperators,in_mathematical_operators
+inmayannumerals,in_mayan_numerals
+inmedefaidrin,in_medefaidrin
+inmeeteimayek,in_meetei_mayek
+inmeeteimayekextensions,in_meetei_mayek_extensions
+inmendekikakui,in_mende_kikakui
+inmeroiticcursive,in_meroitic_cursive
+inmeroitichieroglyphs,in_meroitic_hieroglyphs
+inmiao,in_miao
+inmiscellaneousmathematicalsymbolsa,in_miscellaneous_mathematical_symbols_a
+inmiscellaneousmathematicalsymbolsb,in_miscellaneous_mathematical_symbols_b
+inmiscellaneoussymbols,in_miscellaneous_symbols
+inmiscellaneoussymbolsandarrows,in_miscellaneous_symbols_and_arrows
+inmiscellaneoussymbolsandpictographs,in_miscellaneous_symbols_and_pictographs
+inmiscellaneoustechnical,in_miscellaneous_technical
+inmodi,in_modi
+inmodifiertoneletters,in_modifier_tone_letters
+inmongolian,in_mongolian
+inmongoliansupplement,in_mongolian_supplement
+inmro,in_mro
+inmultani,in_multani
+inmusicalsymbols,in_musical_symbols
+inmyanmar,in_myanmar
+inmyanmarextendeda,in_myanmar_extended_a
+inmyanmarextendedb,in_myanmar_extended_b
+innabataean,in_nabataean
+innagmundari,in_nag_mundari
+innandinagari,in_nandinagari
+innewa,in_newa
+innewtailue,in_new_tai_lue
+innko,in_nko
+innoblock,in_no_block
+innumberforms,in_number_forms
+innushu,in_nushu
+innyiakengpuachuehmong,in_nyiakeng_puachue_hmong
+inogham,in_ogham
+inolchiki,in_ol_chiki
+inoldhungarian,in_old_hungarian
+inolditalic,in_old_italic
+inoldnortharabian,in_old_north_arabian
+inoldpermic,in_old_permic
+inoldpersian,in_old_persian
+inoldsogdian,in_old_sogdian
+inoldsoutharabian,in_old_south_arabian
+inoldturkic,in_old_turkic
+inolduyghur,in_old_uyghur
+inopticalcharacterrecognition,in_optical_character_recognition
+inoriya,in_oriya
+inornamentaldingbats,in_ornamental_dingbats
+inosage,in_osage
+inosmanya,in_osmanya
+inottomansiyaqnumbers,in_ottoman_siyaq_numbers
+inpahawhhmong,in_pahawh_hmong
+inpalmyrene,in_palmyrene
+inpaucinhau,in_pau_cin_hau
+inphagspa,in_phags_pa
+inphaistosdisc,in_phaistos_disc
+inphoenician,in_phoenician
+inphoneticextensions,in_phonetic_extensions
+inphoneticextensionssupplement,in_phonetic_extensions_supplement
+inplayingcards,in_playing_cards
+inprivateusearea,in_private_use_area
+inpsalterpahlavi,in_psalter_pahlavi
+inrejang,in_rejang
+inruminumeralsymbols,in_rumi_numeral_symbols
+inrunic,in_runic
+insamaritan,in_samaritan
+insaurashtra,in_saurashtra
+inscriptionalpahlavi,inscriptional_pahlavi
+inscriptionalparthian,inscriptional_parthian
+insharada,in_sharada
+inshavian,in_shavian
+inshorthandformatcontrols,in_shorthand_format_controls
+insiddham,in_siddham
+insinhala,in_sinhala
+insinhalaarchaicnumbers,in_sinhala_archaic_numbers
+insmallformvariants,in_small_form_variants
+insmallkanaextension,in_small_kana_extension
+insogdian,in_sogdian
+insorasompeng,in_sora_sompeng
+insoyombo,in_soyombo
+inspacingmodifierletters,in_spacing_modifier_letters
+inspecials,in_specials
+insundanese,in_sundanese
+insundanesesupplement,in_sundanese_supplement
+insuperscriptsandsubscripts,in_superscripts_and_subscripts
+insupplementalarrowsa,in_supplemental_arrows_a
+insupplementalarrowsb,in_supplemental_arrows_b
+insupplementalarrowsc,in_supplemental_arrows_c
+insupplementalmathematicaloperators,in_supplemental_mathematical_operators
+insupplementalpunctuation,in_supplemental_punctuation
+insupplementalsymbolsandpictographs,in_supplemental_symbols_and_pictographs
+insupplementaryprivateuseareaa,in_supplementary_private_use_area_a
+insupplementaryprivateuseareab,in_supplementary_private_use_area_b
+insuttonsignwriting,in_sutton_signwriting
+insylotinagri,in_syloti_nagri
+insymbolsandpictographsextendeda,in_symbols_and_pictographs_extended_a
+insymbolsforlegacycomputing,in_symbols_for_legacy_computing
+insyriac,in_syriac
+insyriacsupplement,in_syriac_supplement
+intagalog,in_tagalog
+intagbanwa,in_tagbanwa
+intags,in_tags
+intaile,in_tai_le
+intaitham,in_tai_tham
+intaiviet,in_tai_viet
+intaixuanjingsymbols,in_tai_xuan_jing_symbols
+intakri,in_takri
+intamil,in_tamil
+intamilsupplement,in_tamil_supplement
+intangsa,in_tangsa
+intangut,in_tangut
+intangutcomponents,in_tangut_components
+intangutsupplement,in_tangut_supplement
+intelugu,in_telugu
+inthaana,in_thaana
+inthai,in_thai
+intibetan,in_tibetan
+intifinagh,in_tifinagh
+intirhuta,in_tirhuta
+intoto,in_toto
+intransportandmapsymbols,in_transport_and_map_symbols
+inugaritic,in_ugaritic
+inunifiedcanadianaboriginalsyllabics,in_unified_canadian_aboriginal_syllabics
+inunifiedcanadianaboriginalsyllabicsextended,in_unified_canadian_aboriginal_syllabics_extended
+inunifiedcanadianaboriginalsyllabicsextendeda,in_unified_canadian_aboriginal_syllabics_extended_a
+invai,in_vai
+invariationselectors,in_variation_selectors
+invariationselectorssupplement,in_variation_selectors_supplement
+invedicextensions,in_vedic_extensions
+inverticalforms,in_vertical_forms
+invithkuqi,in_vithkuqi
+inwancho,in_wancho
+inwarangciti,in_warang_citi
+inyezidi,in_yezidi
+inyijinghexagramsymbols,in_yijing_hexagram_symbols
+inyiradicals,in_yi_radicals
+inyisyllables,in_yi_syllables
+inzanabazarsquare,in_zanabazar_square
+inznamennymusicalnotation,in_znamenny_musical_notation
+javanese,javanese
+joincontrol,join_control
+kaithi,kaithi
+kannada,kannada
+katakana,katakana
+kawi,kawi
+kayahli,kayah_li
+kharoshthi,kharoshthi
+khitansmallscript,khitan_small_script
+khmer,khmer
+khojki,khojki
+khudawadi,khudawadi
+lao,lao
+latin,latin
+lepcha,lepcha
+letter,letter
+letternumber,letter_number
+limbu,limbu
+lineara,linear_a
+linearb,linear_b
+lineseparator,line_separator
+lisu,lisu
+logicalorderexception,logical_order_exception
+lower,lower
+lowercase,lowercase
+lowercaseletter,lowercase_letter
+lycian,lycian
+lydian,lydian
+mahajani,mahajani
+makasar,makasar
+malayalam,malayalam
+mandaic,mandaic
+manichaean,manichaean
+marchen,marchen
+mark,mark
+masaramgondi,masaram_gondi
+math,math
+mathsymbol,math_symbol
+medefaidrin,medefaidrin
+meeteimayek,meetei_mayek
+mendekikakui,mende_kikakui
+meroiticcursive,meroitic_cursive
+meroitichieroglyphs,meroitic_hieroglyphs
+miao,miao
+modi,modi
+modifierletter,modifier_letter
+modifiersymbol,modifier_symbol
+mongolian,mongolian
+mro,mro
+multani,multani
+myanmar,myanmar
+nabataean,nabataean
+nagmundari,nag_mundari
+nandinagari,nandinagari
+newa,newa
+newline,newline
+newtailue,new_tai_lue
+nko,nko
+noncharactercodepoint,noncharacter_code_point
+nonspacingmark,nonspacing_mark
+number,number
+nushu,nushu
+nyiakengpuachuehmong,nyiakeng_puachue_hmong
+ogham,ogham
+olchiki,ol_chiki
+oldhungarian,old_hungarian
+olditalic,old_italic
+oldnortharabian,old_north_arabian
+oldpermic,old_permic
+oldpersian,old_persian
+oldsogdian,old_sogdian
+oldsoutharabian,old_south_arabian
+oldturkic,old_turkic
+olduyghur,old_uyghur
+openpunctuation,open_punctuation
+oriya,oriya
+osage,osage
+osmanya,osmanya
+other,other
+otheralphabetic,other_alphabetic
+otherdefaultignorablecodepoint,other_default_ignorable_code_point
+othergraphemeextend,other_grapheme_extend
+otheridcontinue,other_id_continue
+otheridstart,other_id_start
+otherletter,other_letter
+otherlowercase,other_lowercase
+othermath,other_math
+othernumber,other_number
+otherpunctuation,other_punctuation
+othersymbol,other_symbol
+otheruppercase,other_uppercase
+pahawhhmong,pahawh_hmong
+palmyrene,palmyrene
+paragraphseparator,paragraph_separator
+patternsyntax,pattern_syntax
+patternwhitespace,pattern_white_space
+paucinhau,pau_cin_hau
+phagspa,phags_pa
+phoenician,phoenician
+prependedconcatenationmark,prepended_concatenation_mark
+print,print
+privateuse,private_use
+psalterpahlavi,psalter_pahlavi
+punct,punct
+punctuation,punctuation
+quotationmark,quotation_mark
+radical,radical
+regionalindicator,regional_indicator
+rejang,rejang
+runic,runic
+samaritan,samaritan
+saurashtra,saurashtra
+sentenceterminal,sentence_terminal
+separator,separator
+sharada,sharada
+shavian,shavian
+siddham,siddham
+signwriting,signwriting
+sinhala,sinhala
+softdotted,soft_dotted
+sogdian,sogdian
+sorasompeng,sora_sompeng
+soyombo,soyombo
+space,space
+spaceseparator,space_separator
+spacingmark,spacing_mark
+sundanese,sundanese
+surrogate,surrogate
+sylotinagri,syloti_nagri
+symbol,symbol
+syriac,syriac
+tagalog,tagalog
+tagbanwa,tagbanwa
+taile,tai_le
+taitham,tai_tham
+taiviet,tai_viet
+takri,takri
+tamil,tamil
+tangsa,tangsa
+tangut,tangut
+telugu,telugu
+terminalpunctuation,terminal_punctuation
+thaana,thaana
+thai,thai
+tibetan,tibetan
+tifinagh,tifinagh
+tirhuta,tirhuta
+titlecaseletter,titlecase_letter
+toto,toto
+ugaritic,ugaritic
+unassigned,unassigned
+unifiedideograph,unified_ideograph
+unknown,unknown
+upper,upper
+uppercase,uppercase
+uppercaseletter,uppercase_letter
+vai,vai
+variationselector,variation_selector
+vithkuqi,vithkuqi
+wancho,wancho
+warangciti,warang_citi
+whitespace,white_space
+word,word
+xdigit,xdigit
+xidcontinue,xid_continue
+xidstart,xid_start
+xposixpunct,xposixpunct
+yezidi,yezidi
+yi,yi
+zanabazarsquare,zanabazar_square