regexp_parser 0.5.0 → 1.0.0

data/lib/regexp_parser/syntax/base.rb

@@ -67,8 +67,8 @@ module Regexp::Syntax
         [:backref, :name_ref]
       when :name_call_ab, :name_call_sq
         [:backref, :name_call]
-      when :name_nest_ref_ab, :name_nest_ref_sq
-        [:backref, :name_nest_ref]
+      when :name_recursion_ref_ab, :name_recursion_ref_sq
+        [:backref, :name_recursion_ref]
       when :number_ref_ab, :number_ref_sq
         [:backref, :number_ref]
       when :number_call_ab, :number_call_sq
@@ -77,8 +77,8 @@ module Regexp::Syntax
         [:backref, :number_rel_ref]
       when :number_rel_call_ab, :number_rel_call_sq
         [:backref, :number_rel_call]
-      when :number_nest_ref_ab, :number_nest_ref_sq
-        [:backref, :number_nest_ref]
+      when :number_recursion_ref_ab, :number_recursion_ref_sq
+        [:backref, :number_recursion_ref]
       else
         [type, token]
       end

data/lib/regexp_parser/syntax/tokens.rb

@@ -23,6 +23,7 @@ end
 require 'regexp_parser/syntax/tokens/anchor'
 require 'regexp_parser/syntax/tokens/assertion'
 require 'regexp_parser/syntax/tokens/backref'
+require 'regexp_parser/syntax/tokens/posix_class'
 require 'regexp_parser/syntax/tokens/character_set'
 require 'regexp_parser/syntax/tokens/character_type'
 require 'regexp_parser/syntax/tokens/conditional'

data/lib/regexp_parser/syntax/tokens/backref.rb

@@ -5,9 +5,9 @@ module Regexp::Syntax
       Name      = [:name_ref]
       Number    = [:number, :number_ref, :number_rel_ref]
 
-      NestLevel = [:name_nest_ref, :number_nest_ref]
+      RecursionLevel = [:name_recursion_ref, :number_recursion_ref]
 
-      All = Name + Number + NestLevel
+      All = Name + Number + RecursionLevel
       Type = :backref
     end
 

data/lib/regexp_parser/syntax/tokens/character_set.rb

@@ -4,48 +4,13 @@ module Regexp::Syntax
     module CharacterSet
       OpenClose = [:open, :close]
 
-      Basic     = [:negate, :member, :range]
-      Extended  = Basic + [:escape, :intersection, :backspace,
-                           :member_hex, :range_hex]
+      Basic     = [:negate, :range]
+      Extended  = Basic + [:intersection, :backspace]
 
-      Types     = [:type_digit, :type_nondigit, :type_hex, :type_nonhex,
-                   :type_space, :type_nonspace, :type_word, :type_nonword]
-
-      Clustered = [:type_linebreak, :type_xgrapheme]
-
-      module POSIX
-        Standard  = [
-          :class_alnum, :class_alpha, :class_blank, :class_cntrl,
-          :class_digit, :class_graph, :class_lower, :class_print,
-          :class_punct, :class_space, :class_upper, :class_xdigit,
-        ]
-
-        StandardNegative = [
-          :class_nonalnum, :class_nonalpha, :class_nonblank,
-          :class_noncntrl, :class_nondigit, :class_nongraph,
-          :class_nonlower, :class_nonprint, :class_nonpunct,
-          :class_nonspace, :class_nonupper, :class_nonxdigit,
-        ]
-
-        Extensions         = [:class_ascii, :class_word]
-        ExtensionsNegative = [:class_nonascii, :class_nonword]
-
-        All = Standard + StandardNegative + Extensions + ExtensionsNegative
-      end
-
-      All = Basic + Extended + Types + Clustered + POSIX::All
+      All = Basic + Extended
       Type = :set
-
-      module SubSet
-        OpenClose = [:open, :close]
-
-        All = CharacterSet::All
-        Type = :subset
-      end
     end
 
     Map[CharacterSet::Type] = CharacterSet::All
-    Map[CharacterSet::SubSet::Type] = CharacterSet::All
-
   end
 end

data/lib/regexp_parser/syntax/tokens/escape.rb

@@ -9,7 +9,7 @@ module Regexp::Syntax
       Control = [:control, :meta_sequence]
 
       ASCII = [:bell, :backspace, :escape, :form_feed, :newline, :carriage,
-               :space, :tab, :vertical_tab]
+               :tab, :vertical_tab]
 
       Unicode = [:codepoint, :codepoint_list]
 
@@ -18,8 +18,7 @@ module Regexp::Syntax
                :bol, :eol,
                :group_open, :group_close,
                :interval_open, :interval_close,
-               :set_open, :set_close,
-               :baclslash]
+               :set_open, :set_close]
 
       Hex   = [:hex]
 

data/lib/regexp_parser/syntax/tokens/group.rb

@@ -3,18 +3,19 @@ module Regexp::Syntax
 
     module Group
       Basic     = [:capture, :close]
-      Extended  = Basic + [:options]
+      Extended  = Basic + [:options, :options_switch]
 
       Named     = [:named]
       Atomic    = [:atomic]
       Passive   = [:passive]
       Comment   = [:comment]
 
-      All = Group::Extended + Group::Named + Group::Atomic +
-            Group::Passive + Group::Comment
+      V1_8_6 = Group::Extended + Group::Named + Group::Atomic +
+               Group::Passive + Group::Comment
 
-      Absence = [:absence]
+      V2_4_1 = [:absence]
 
+      All = V1_8_6 + V2_4_1
       Type = :group
     end
 

data/lib/regexp_parser/syntax/tokens/{character_class.rb → posix_class.rb}

@@ -1,16 +1,16 @@
 module Regexp::Syntax
   module Token
-    module CharacterClass
+    module PosixClass
       Standard  = [:alnum, :alpha, :blank, :cntrl, :digit, :graph,
                    :lower, :print, :punct, :space, :upper, :xdigit]
 
       Extensions = [:ascii, :word]
 
       All = Standard + Extensions
-      Type = :class
-      NonType = :nonclass
+      Type = :posixclass
+      NonType = :nonposixclass
     end
-    Map[CharacterClass::Type]    = CharacterClass::All
-    Map[CharacterClass::NonType] = CharacterClass::All
+    Map[PosixClass::Type]    = PosixClass::All
+    Map[PosixClass::NonType] = PosixClass::All
   end
 end

data/lib/regexp_parser/syntax/tokens/unicode_property.rb

@@ -10,24 +10,24 @@ module Regexp::Syntax
       POSIX  = [:any, :assigned, :newline]
 
       module Category
-        Letter        = [:letter_any, :letter_uppercase, :letter_lowercase,
-                         :letter_titlecase, :letter_modifier, :letter_other]
+        Letter        = [:letter, :uppercase_letter, :lowercase_letter,
+                         :titlecase_letter, :modifier_letter, :other_letter]
 
-        Mark          = [:mark_any, :mark_nonspacing, :mark_spacing,
-                         :mark_enclosing]
+        Mark          = [:mark, :nonspacing_mark, :spacing_mark,
+                         :enclosing_mark]
 
-        Number        = [:number_any, :number_decimal, :number_letter,
-                         :number_other]
+        Number        = [:number, :decimal_number, :letter_number,
+                         :other_number]
 
-        Punctuation   = [:punct_any, :punct_connector, :punct_dash,
-                         :punct_open, :punct_close, :punct_initial,
-                         :punct_final, :punct_other]
+        Punctuation   = [:punctuation, :connector_punctuation, :dash_punctuation,
+                         :open_punctuation, :close_punctuation, :initial_punctuation,
+                         :final_punctuation, :other_punctuation]
 
-        Symbol        = [:symbol_any, :symbol_math, :symbol_currency,
-                         :symbol_modifier, :symbol_other]
+        Symbol        = [:symbol, :math_symbol, :currency_symbol,
+                         :modifier_symbol, :other_symbol]
 
-        Separator     = [:separator_any, :separator_space, :separator_line,
-                         :separator_para]
+        Separator     = [:separator, :space_separator, :line_separator,
+                         :paragraph_separator]
 
         Codepoint     = [:other, :control, :format,
                          :surrogate, :private_use, :unassigned]
@@ -37,25 +37,25 @@ module Regexp::Syntax
       end
 
       # As of ruby version 1.9.3
-      Age_V1_9_3 = [:age_1_1, :age_2_0, :age_2_1, :age_3_0, :age_3_1,
-                    :age_3_2, :age_4_0, :age_4_1, :age_5_0, :age_5_1,
-                    :age_5_2, :age_6_0]
+      Age_V1_9_3 = [:'age=1.1', :'age=2.0', :'age=2.1', :'age=3.0', :'age=3.1',
+                    :'age=3.2', :'age=4.0', :'age=4.1', :'age=5.0', :'age=5.1',
+                    :'age=5.2', :'age=6.0']
 
-      Age_V2_0_0 = [:age_6_1]
+      Age_V2_0_0 = [:'age=6.1']
 
       # These were merged (from Onigmo) in the branch for 2.2.0
-      Age_V2_2_0 = [:age_6_2, :age_6_3, :age_7_0]
+      Age_V2_2_0 = [:'age=6.2', :'age=6.3', :'age=7.0']
 
-      Age_V2_3_0 = [:age_8_0]
+      Age_V2_3_0 = [:'age=8.0']
 
-      Age_V2_4_0 = [:age_9_0]
+      Age_V2_4_0 = [:'age=9.0']
 
-      Age_V2_5_0 = [:age_10_0]
+      Age_V2_5_0 = [:'age=10.0']
 
       Age = Age_V1_9_3 + Age_V2_0_0 + Age_V2_2_0 + Age_V2_3_0 + Age_V2_4_0 + Age_V2_5_0
 
       Derived_V1_9_0 = [
-        :ascii_hex,
+        :ascii_hex_digit,
         :alphabetic,
         :cased,
         :changes_when_casefolded,
@@ -67,7 +67,7 @@ module Regexp::Syntax
         :bidi_control,
         :dash,
         :deprecated,
-        :default_ignorable_cp,
+        :default_ignorable_code_point,
         :diacritic,
         :extender,
         :grapheme_base,
@@ -78,297 +78,550 @@ module Regexp::Syntax
         :id_continue,
         :ideographic,
         :id_start,
-        :ids_binary_op,
-        :ids_trinary_op,
+        :ids_binary_operator,
+        :ids_trinary_operator,
         :join_control,
         :logical_order_exception,
         :lowercase,
         :math,
-        :non_character_cp,
+        :noncharacter_code_point,
         :other_alphabetic,
-        :other_default_ignorable_cp,
-        :other_grapheme_extended,
+        :other_default_ignorable_code_point,
+        :other_grapheme_extend,
         :other_id_continue,
         :other_id_start,
         :other_lowercase,
         :other_math,
         :other_uppercase,
         :pattern_syntax,
-        :pattern_whitespace,
+        :pattern_white_space,
         :quotation_mark,
         :radical,
-        :soft_dotted,
         :sentence_terminal,
+        :soft_dotted,
         :terminal_punctuation,
         :unified_ideograph,
         :uppercase,
         :variation_selector,
-        :whitespace,
+        :white_space,
         :xid_start,
         :xid_continue,
       ]
 
+      Derived_V2_0_0 = [
+        :cased_letter,
+        :combining_mark,
+      ]
+
+      Derived_V2_4_0 = [
+        :prepended_concatenation_mark,
+      ]
+
       Derived_V2_5_0 = [
         :regional_indicator
       ]
 
-      Derived = Derived_V1_9_0 + Derived_V2_5_0
+      Derived = Derived_V1_9_0 + Derived_V2_0_0 + Derived_V2_4_0 + Derived_V2_5_0
 
       Script_V1_9_0 = [
-        :script_arabic,
-        :script_imperial_aramaic,
-        :script_armenian,
-        :script_avestan,
-        :script_balinese,
-        :script_bamum,
-        :script_bengali,
-        :script_bopomofo,
-        :script_braille,
-        :script_buginese,
-        :script_buhid,
-        :script_canadian_aboriginal,
-        :script_carian,
-        :script_cham,
-        :script_cherokee,
-        :script_coptic,
-        :script_cypriot,
-        :script_cyrillic,
-        :script_devanagari,
-        :script_deseret,
-        :script_egyptian_hieroglyphs,
-        :script_ethiopic,
-        :script_georgian,
-        :script_glagolitic,
-        :script_gothic,
-        :script_greek,
-        :script_gujarati,
-        :script_gurmukhi,
-        :script_hangul,
-        :script_han,
-        :script_hanunoo,
-        :script_hebrew,
-        :script_hiragana,
-        :script_katakana_or_hiragana,
-        :script_old_italic,
-        :script_javanese,
-        :script_kayah_li,
-        :script_katakana,
-        :script_kharoshthi,
-        :script_khmer,
-        :script_kannada,
-        :script_kaithi,
-        :script_tai_tham,
-        :script_lao,
-        :script_latin,
-        :script_lepcha,
-        :script_limbu,
-        :script_linear_b,
-        :script_lisu,
-        :script_lycian,
-        :script_lydian,
-        :script_malayalam,
-        :script_mongolian,
-        :script_meetei_mayek,
-        :script_myanmar,
-        :script_nko,
-        :script_ogham,
-        :script_ol_chiki,
-        :script_old_turkic,
-        :script_oriya,
-        :script_osmanya,
-        :script_phags_pa,
-        :script_inscriptional_pahlavi,
-        :script_phoenician,
-        :script_inscriptional_parthian,
-        :script_rejang,
-        :script_runic,
-        :script_samaritan,
-        :script_old_south_arabian,
-        :script_saurashtra,
-        :script_shavian,
-        :script_sinhala,
-        :script_sundanese,
-        :script_syloti_nagri,
-        :script_syriac,
-        :script_tagbanwa,
-        :script_tai_le,
-        :script_new_tai_lue,
-        :script_tamil,
-        :script_tai_viet,
-        :script_telugu,
-        :script_tifinagh,
-        :script_tagalog,
-        :script_thaana,
-        :script_thai,
-        :script_tibetan,
-        :script_ugaritic,
-        :script_vai,
-        :script_old_persian,
-        :script_cuneiform,
-        :script_yi,
-        :script_inherited,
-        :script_common,
-        :script_unknown
+        :arabic,
+        :imperial_aramaic,
+        :armenian,
+        :avestan,
+        :balinese,
+        :bamum,
+        :bengali,
+        :bopomofo,
+        :braille,
+        :buginese,
+        :buhid,
+        :canadian_aboriginal,
+        :carian,
+        :cham,
+        :cherokee,
+        :coptic,
+        :cypriot,
+        :cyrillic,
+        :devanagari,
+        :deseret,
+        :egyptian_hieroglyphs,
+        :ethiopic,
+        :georgian,
+        :glagolitic,
+        :gothic,
+        :greek,
+        :gujarati,
+        :gurmukhi,
+        :hangul,
+        :han,
+        :hanunoo,
+        :hebrew,
+        :hiragana,
+        :old_italic,
+        :javanese,
+        :kayah_li,
+        :katakana,
+        :kharoshthi,
+        :khmer,
+        :kannada,
+        :kaithi,
+        :tai_tham,
+        :lao,
+        :latin,
+        :lepcha,
+        :limbu,
+        :linear_b,
+        :lisu,
+        :lycian,
+        :lydian,
+        :malayalam,
+        :mongolian,
+        :meetei_mayek,
+        :myanmar,
+        :nko,
+        :ogham,
+        :ol_chiki,
+        :old_turkic,
+        :oriya,
+        :osmanya,
+        :phags_pa,
+        :inscriptional_pahlavi,
+        :phoenician,
+        :inscriptional_parthian,
+        :rejang,
+        :runic,
+        :samaritan,
+        :old_south_arabian,
+        :saurashtra,
+        :shavian,
+        :sinhala,
+        :sundanese,
+        :syloti_nagri,
+        :syriac,
+        :tagbanwa,
+        :tai_le,
+        :new_tai_lue,
+        :tamil,
+        :tai_viet,
+        :telugu,
+        :tifinagh,
+        :tagalog,
+        :thaana,
+        :thai,
+        :tibetan,
+        :ugaritic,
+        :vai,
+        :old_persian,
+        :cuneiform,
+        :yi,
+        :inherited,
+        :common,
+        :unknown
+      ]
+
+      Script_V1_9_3 = [
+        :brahmi,
+        :batak,
+        :mandaic
       ]
 
-      Script_V1_9_3 = [:script_brahmi, :script_batak, :script_mandaic]
+      Script_V2_0_0 = [
+        :chakma,
+        :meroitic_cursive,
+        :meroitic_hieroglyphs,
+        :miao,
+        :sharada,
+        :sora_sompeng,
+        :takri,
+      ]
 
       Script_V2_2_0 = [
-        :script_caucasian_albanian,
-        :script_bassa_vah,
-        :script_duployan,
-        :script_elbasan,
-        :script_grantha,
-        :script_pahawh_hmong,
-        :script_khojki,
-        :script_linear_a,
-        :script_mahajani,
-        :script_manichaean,
-        :script_mende_kikakui,
-        :script_modi,
-        :script_mro,
-        :script_old_north_arabian,
-        :script_nabataean,
-        :script_palmyrene,
-        :script_pau_cin_hau,
-        :script_old_permic,
-        :script_psalter_pahlavi,
-        :script_siddham,
-        :script_khudawadi,
-        :script_tirhuta,
-        :script_warang_citi
+        :caucasian_albanian,
+        :bassa_vah,
+        :duployan,
+        :elbasan,
+        :grantha,
+        :pahawh_hmong,
+        :khojki,
+        :linear_a,
+        :mahajani,
+        :manichaean,
+        :mende_kikakui,
+        :modi,
+        :mro,
+        :old_north_arabian,
+        :nabataean,
+        :palmyrene,
+        :pau_cin_hau,
+        :old_permic,
+        :psalter_pahlavi,
+        :siddham,
+        :khudawadi,
+        :tirhuta,
+        :warang_citi
+      ]
+
+      Script_V2_3_0 = [
+        :ahom,
+        :anatolian_hieroglyphs,
+        :hatran,
+        :multani,
+        :old_hungarian,
+        :signwriting,
       ]
 
-      Script = Script_V1_9_0 + Script_V1_9_3 + Script_V2_2_0
-
-      UnicodeBlock = [
-        :block_inalphabetic_presentation_forms,
-        :block_inarabic_presentation_forms_a,
-        :block_inarabic_presentation_forms_b,
-        :block_inarabic,
-        :block_inarmenian,
-        :block_inarrows,
-        :block_inbasic_latin,
-        :block_inbengali,
-        :block_inblock_elements,
-        :block_inbopomofo_extended,
-        :block_inbopomofo,
-        :block_inbox_drawing,
-        :block_inbraille_patterns,
-        :block_inbuhid,
-        :block_incjk_compatibility_forms,
-        :block_incjk_compatibility_ideographs,
-        :block_incjk_compatibility,
-        :block_incjk_radicals_supplement,
-        :block_incjk_symbols_and_punctuation,
-        :block_incjk_unified_ideographs_extension_a,
-        :block_incjk_unified_ideographs,
-        :block_incherokee,
-        :block_incombining_diacritical_marks_for_symbols,
-        :block_incombining_diacritical_marks,
-        :block_incombining_half_marks,
-        :block_incontrol_pictures,
-        :block_incurrency_symbols,
-        :block_incyrillic_supplement,
-        :block_incyrillic,
-        :block_indevanagari,
-        :block_indingbats,
-        :block_inenclosed_alphanumerics,
-        :block_inenclosed_cjk_letters_and_months,
-        :block_inethiopic,
-        :block_ingeneral_punctuation,
-        :block_ingeometric_shapes,
-        :block_ingeorgian,
-        :block_ingreek_extended,
-        :block_ingreek_and_coptic,
-        :block_ingujarati,
-        :block_ingurmukhi,
-        :block_inhalfwidth_and_fullwidth_forms,
-        :block_inhangul_compatibility_jamo,
-        :block_inhangul_jamo,
-        :block_inhangul_syllables,
-        :block_inhanunoo,
-        :block_inhebrew,
-        :block_inhigh_private_use_surrogates,
-        :block_inhigh_surrogates,
-        :block_inhiragana,
-        :block_inipa_extensions,
-        :block_inideographic_description_characters,
-        :block_inkanbun,
-        :block_inkangxi_radicals,
-        :block_inkannada,
-        :block_inkatakana_phonetic_extensions,
-        :block_inkatakana,
-        :block_inkhmer_symbols,
-        :block_inkhmer,
-        :block_inlao,
-        :block_inlatin_1_supplement,
-        :block_inlatin_extended_a,
-        :block_inlatin_extended_b,
-        :block_inlatin_extended_additional,
-        :block_inletterlike_symbols,
-        :block_inlimbu,
-        :block_inlow_surrogates,
-        :block_inmalayalam,
-        :block_inmathematical_operators,
-        :block_inmiscellaneous_mathematical_symbols_a,
-        :block_inmiscellaneous_mathematical_symbols_b,
-        :block_inmiscellaneous_symbols_and_arrows,
-        :block_inmiscellaneous_symbols,
-        :block_inmiscellaneous_technical,
-        :block_inmongolian,
-        :block_inmyanmar,
-        :block_innumber_forms,
-        :block_inogham,
-        :block_inoptical_character_recognition,
-        :block_inoriya,
-        :block_inphonetic_extensions,
-        :block_inprivate_use_area,
-        :block_inrunic,
-        :block_insinhala,
-        :block_insmall_form_variants,
-        :block_inspacing_modifier_letters,
-        :block_inspecials,
-        :block_insuperscripts_and_subscripts,
-        :block_insupplemental_arrows_a,
-        :block_insupplemental_arrows_b,
-        :block_insupplemental_mathematical_operators,
-        :block_insyriac,
-        :block_intagalog,
-        :block_intagbanwa,
-        :block_intai_le,
-        :block_intamil,
-        :block_intelugu,
-        :block_inthaana,
-        :block_inthai,
-        :block_intibetan,
-        :block_inunified_canadian_aboriginal_syllabics,
-        :block_invariation_selectors,
-        :block_inyi_radicals,
-        :block_inyi_syllables,
-        :block_inyijing_hexagram_symbols,
+      Script_V2_4_0 = [
+        :adlam,
+        :bhaiksuki,
+        :marchen,
+        :newa,
+        :osage,
+        :tangut,
       ]
 
-      Emoji = [
-        :emoji_any,
+      Script_V2_5_0 = [
+        :masaram_gondi,
+        :nushu,
+        :soyombo,
+        :zanabazar_square,
+      ]
+
+      Script = Script_V1_9_0 + Script_V1_9_3 + Script_V2_0_0 +
+               Script_V2_2_0 + Script_V2_3_0 + Script_V2_4_0 + Script_V2_5_0
+
+      UnicodeBlock_V1_9_0 = [
+        :in_alphabetic_presentation_forms,
+        :in_arabic_presentation_forms_a,
+        :in_arabic_presentation_forms_b,
+        :in_arabic,
+        :in_armenian,
+        :in_arrows,
+        :in_basic_latin,
+        :in_bengali,
+        :in_block_elements,
+        :in_bopomofo_extended,
+        :in_bopomofo,
+        :in_box_drawing,
+        :in_braille_patterns,
+        :in_buhid,
+        :in_cjk_compatibility_forms,
+        :in_cjk_compatibility_ideographs,
+        :in_cjk_compatibility,
+        :in_cjk_radicals_supplement,
+        :in_cjk_symbols_and_punctuation,
+        :in_cjk_unified_ideographs_extension_a,
+        :in_cjk_unified_ideographs,
+        :in_cherokee,
+        :in_combining_diacritical_marks_for_symbols,
+        :in_combining_diacritical_marks,
+        :in_combining_half_marks,
+        :in_control_pictures,
+        :in_currency_symbols,
+        :in_cyrillic_supplement,
+        :in_cyrillic,
+        :in_devanagari,
+        :in_dingbats,
+        :in_enclosed_alphanumerics,
+        :in_enclosed_cjk_letters_and_months,
+        :in_ethiopic,
+        :in_general_punctuation,
+        :in_geometric_shapes,
+        :in_georgian,
+        :in_greek_extended,
+        :in_greek_and_coptic,
+        :in_gujarati,
+        :in_gurmukhi,
+        :in_halfwidth_and_fullwidth_forms,
+        :in_hangul_compatibility_jamo,
+        :in_hangul_jamo,
+        :in_hangul_syllables,
+        :in_hanunoo,
+        :in_hebrew,
+        :in_high_private_use_surrogates,
+        :in_high_surrogates,
+        :in_hiragana,
+        :in_ipa_extensions,
+        :in_ideographic_description_characters,
+        :in_kanbun,
+        :in_kangxi_radicals,
+        :in_kannada,
+        :in_katakana_phonetic_extensions,
+        :in_katakana,
+        :in_khmer_symbols,
+        :in_khmer,
+        :in_lao,
+        :in_latin_1_supplement,
+        :in_latin_extended_a,
+        :in_latin_extended_b,
+        :in_latin_extended_additional,
+        :in_letterlike_symbols,
+        :in_limbu,
+        :in_low_surrogates,
+        :in_malayalam,
+        :in_mathematical_operators,
+        :in_miscellaneous_mathematical_symbols_a,
+        :in_miscellaneous_mathematical_symbols_b,
+        :in_miscellaneous_symbols_and_arrows,
+        :in_miscellaneous_symbols,
+        :in_miscellaneous_technical,
+        :in_mongolian,
+        :in_myanmar,
+        :in_number_forms,
+        :in_ogham,
+        :in_optical_character_recognition,
+        :in_oriya,
+        :in_phonetic_extensions,
+        :in_private_use_area,
+        :in_runic,
+        :in_sinhala,
+        :in_small_form_variants,
+        :in_spacing_modifier_letters,
+        :in_specials,
+        :in_superscripts_and_subscripts,
+        :in_supplemental_arrows_a,
+        :in_supplemental_arrows_b,
+        :in_supplemental_mathematical_operators,
+        :in_syriac,
+        :in_tagalog,
+        :in_tagbanwa,
+        :in_tai_le,
+        :in_tamil,
+        :in_telugu,
+        :in_thaana,
+        :in_thai,
+        :in_tibetan,
+        :in_unified_canadian_aboriginal_syllabics,
+        :in_variation_selectors,
+        :in_yi_radicals,
+        :in_yi_syllables,
+        :in_yijing_hexagram_symbols,
+      ]
+
+      UnicodeBlock_V2_0_0 = [
+        :in_aegean_numbers,
+        :in_alchemical_symbols,
+        :in_ancient_greek_musical_notation,
+        :in_ancient_greek_numbers,
+        :in_ancient_symbols,
+        :in_arabic_extended_a,
+        :in_arabic_mathematical_alphabetic_symbols,
+        :in_arabic_presentation_forms_a,
+        :in_arabic_presentation_forms_b,
+        :in_arabic_supplement,
+        :in_avestan,
+        :in_balinese,
+        :in_bamum,
+        :in_bamum_supplement,
+        :in_batak,
+        :in_brahmi,
+        :in_buginese,
+        :in_byzantine_musical_symbols,
+        :in_cjk_compatibility_ideographs_supplement,
+        :in_cjk_strokes,
+        :in_cjk_unified_ideographs_extension_b,
+        :in_cjk_unified_ideographs_extension_c,
+        :in_cjk_unified_ideographs_extension_d,
+        :in_carian,
+        :in_chakma,
+        :in_cham,
+        :in_combining_diacritical_marks_supplement,
+        :in_common_indic_number_forms,
+        :in_coptic,
+        :in_counting_rod_numerals,
+        :in_cuneiform,
+        :in_cuneiform_numbers_and_punctuation,
+        :in_cypriot_syllabary,
+        :in_cyrillic_extended_a,
+        :in_cyrillic_extended_b,
+        :in_deseret,
+        :in_devanagari_extended,
+        :in_domino_tiles,
+        :in_egyptian_hieroglyphs,
+        :in_emoticons,
+        :in_enclosed_alphanumeric_supplement,
+        :in_enclosed_ideographic_supplement,
+        :in_ethiopic_extended,
+        :in_ethiopic_extended_a,
+        :in_ethiopic_supplement,
+        :in_georgian_supplement,
+        :in_glagolitic,
+        :in_gothic,
+        :in_hangul_jamo_extended_a,
+        :in_hangul_jamo_extended_b,
+        :in_imperial_aramaic,
+        :in_inscriptional_pahlavi,
+        :in_inscriptional_parthian,
+        :in_javanese,
+        :in_kaithi,
+        :in_kana_supplement,
+        :in_kayah_li,
+        :in_kharoshthi,
+        :in_latin_1_supplement,
+        :in_latin_extended_a,
+        :in_latin_extended_b,
+        :in_latin_extended_c,
+        :in_latin_extended_d,
+        :in_lepcha,
+        :in_linear_b_ideograms,
+        :in_linear_b_syllabary,
+        :in_lisu,
+        :in_lycian,
+        :in_lydian,
+        :in_mahjong_tiles,
+        :in_mandaic,
+        :in_mathematical_alphanumeric_symbols,
+        :in_meetei_mayek,
+        :in_meetei_mayek_extensions,
+        :in_meroitic_cursive,
+        :in_meroitic_hieroglyphs,
+        :in_miao,
+        :in_miscellaneous_mathematical_symbols_a,
+        :in_miscellaneous_mathematical_symbols_b,
+        :in_miscellaneous_symbols_and_pictographs,
+        :in_modifier_tone_letters,
+        :in_musical_symbols,
+        :in_myanmar_extended_a,
+        :in_nko,
+        :in_new_tai_lue,
+        :in_no_block,
+        :in_ol_chiki,
+        :in_old_italic,
+        :in_old_persian,
+        :in_old_south_arabian,
+        :in_old_turkic,
+        :in_osmanya,
+        :in_phags_pa,
+        :in_phaistos_disc,
+        :in_phoenician,
+        :in_phonetic_extensions_supplement,
+        :in_playing_cards,
+        :in_rejang,
+        :in_rumi_numeral_symbols,
+        :in_samaritan,
+        :in_saurashtra,
+        :in_sharada,
+        :in_shavian,
+        :in_sora_sompeng,
+        :in_sundanese,
+        :in_sundanese_supplement,
+        :in_supplemental_arrows_a,
+        :in_supplemental_arrows_b,
+        :in_supplemental_punctuation,
+        :in_supplementary_private_use_area_a,
+        :in_supplementary_private_use_area_b,
+        :in_syloti_nagri,
+        :in_tags,
+        :in_tai_tham,
+        :in_tai_viet,
+        :in_tai_xuan_jing_symbols,
+        :in_takri,
+        :in_tifinagh,
+        :in_transport_and_map_symbols,
+        :in_ugaritic,
+        :in_unified_canadian_aboriginal_syllabics_extended,
+        :in_vai,
+        :in_variation_selectors_supplement,
+        :in_vedic_extensions,
+        :in_vertical_forms,
+      ]
+
+      UnicodeBlock_V2_2_0 = [
+        :in_bassa_vah,
+        :in_caucasian_albanian,
+        :in_combining_diacritical_marks_extended,
+        :in_coptic_epact_numbers,
+        :in_duployan,
+        :in_elbasan,
+        :in_geometric_shapes_extended,
+        :in_grantha,
+        :in_khojki,
+        :in_khudawadi,
+        :in_latin_extended_e,
+        :in_linear_a,
+        :in_mahajani,
+        :in_manichaean,
+        :in_mende_kikakui,
+        :in_modi,
+        :in_mro,
+        :in_myanmar_extended_b,
+        :in_nabataean,
+        :in_old_north_arabian,
+        :in_old_permic,
+        :in_ornamental_dingbats,
+        :in_pahawh_hmong,
+        :in_palmyrene,
+        :in_pau_cin_hau,
+        :in_psalter_pahlavi,
+        :in_shorthand_format_controls,
+        :in_siddham,
+        :in_sinhala_archaic_numbers,
+        :in_supplemental_arrows_c,
+        :in_tirhuta,
+        :in_warang_citi,
+      ]
+
+      UnicodeBlock_V2_3_0 = [
+        :in_ahom,
+        :in_anatolian_hieroglyphs,
+        :in_cjk_unified_ideographs_extension_e,
+        :in_cherokee_supplement,
+        :in_early_dynastic_cuneiform,
+        :in_hatran,
+        :in_multani,
+        :in_old_hungarian,
+        :in_supplemental_symbols_and_pictographs,
+        :in_sutton_signwriting,
+      ]
+
+      UnicodeBlock_V2_4_0 = [
+        :in_adlam,
+        :in_bhaiksuki,
+        :in_cyrillic_extended_c,
+        :in_glagolitic_supplement,
+        :in_ideographic_symbols_and_punctuation,
+        :in_marchen,
+        :in_mongolian_supplement,
+        :in_newa,
+        :in_osage,
+        :in_tangut,
+        :in_tangut_components,
+      ]
+
+      UnicodeBlock_V2_5_0 = [
+        :in_cjk_unified_ideographs_extension_f,
+        :in_kana_extended_a,
+        :in_masaram_gondi,
+        :in_nushu,
+        :in_soyombo,
+        :in_syriac_supplement,
+        :in_zanabazar_square,
+      ]
+
+      UnicodeBlock = UnicodeBlock_V1_9_0 + UnicodeBlock_V2_0_0 + UnicodeBlock_V2_2_0 +
+                     UnicodeBlock_V2_3_0 + UnicodeBlock_V2_4_0 + UnicodeBlock_V2_5_0
+
+      Emoji_V2_5_0 = [
+        :emoji,
         :emoji_component,
         :emoji_modifier,
         :emoji_modifier_base,
         :emoji_presentation,
       ]
 
-      V1_9_0 = CharType_V1_9_0 + POSIX + Category::All + Derived_V1_9_0 + Script_V1_9_0 + UnicodeBlock
+      Emoji = Emoji_V2_5_0
+
+      V1_9_0 = CharType_V1_9_0 + POSIX + Category::All + Derived_V1_9_0 + Script_V1_9_0 + UnicodeBlock_V1_9_0
       V1_9_3 = Age_V1_9_3 + Script_V1_9_3
 
-      V2_0_0 = Age_V2_0_0
+      V2_0_0 = Age_V2_0_0 + Derived_V2_0_0 + Script_V2_0_0 + UnicodeBlock_V2_0_0
 
-      V2_2_0 = Age_V2_2_0 + Script_V2_2_0
+      V2_2_0 = Age_V2_2_0 + Script_V2_2_0 + UnicodeBlock_V2_2_0
 
-      V2_3_0 = Age_V2_3_0
+      V2_3_0 = Age_V2_3_0 + Script_V2_3_0 + UnicodeBlock_V2_3_0
 
-      V2_4_0 = Age_V2_4_0
+      V2_4_0 = Age_V2_4_0 + Derived_V2_4_0 + Script_V2_4_0 + UnicodeBlock_V2_4_0
 
-      V2_5_0 = Age_V2_5_0 + CharType_V2_5_0 + Derived_V2_5_0 + Emoji
+      V2_5_0 = Age_V2_5_0 + CharType_V2_5_0 + Derived_V2_5_0 + Emoji_V2_5_0 + Script_V2_5_0 + UnicodeBlock_V2_5_0
 
       All  = V1_9_0 + V1_9_3 + V2_0_0 + V2_2_0 + V2_3_0 + V2_4_0 + V2_5_0