RubyGems - regexp_parser - Versions diffs - 1.7.0 → 2.9.0 - Mend

regexp_parser 1.7.0 → 2.9.0

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 (166) hide show

checksums.yaml +4 -4
data/Gemfile +9 -3
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} +4 -8
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 -5
data/lib/regexp_parser/expression/classes/root.rb +4 -19
data/lib/regexp_parser/expression/classes/{property.rb → unicode_property.rb} +11 -12
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/negative.rb +20 -0
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 +15 -141
data/lib/regexp_parser/lexer.rb +83 -41
data/lib/regexp_parser/parser.rb +372 -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 +651 -0
data/lib/regexp_parser/scanner/properties/short.csv +249 -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 +751 -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 +53 -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/syntax/token/unicode_property.rb ADDED Viewed

@@ -0,0 +1,751 @@
+module Regexp::Syntax
+  module Token
+    module UnicodeProperty
+      all = proc { |name| constants.grep(/#{name}/).flat_map(&method(:const_get)) }
+      CharType_V1_9_0 = %i[alnum alpha ascii blank cntrl digit graph
+                           lower print punct space upper word xdigit]
+      CharType_V2_5_0 = %i[xposixpunct]
+      POSIX = %i[any assigned newline]
+      module Category
+        Letter        = %i[letter uppercase_letter lowercase_letter
+                           titlecase_letter modifier_letter other_letter]
+        Mark          = %i[mark nonspacing_mark spacing_mark
+                           enclosing_mark]
+        Number        = %i[number decimal_number letter_number
+                           other_number]
+        Punctuation   = %i[punctuation connector_punctuation dash_punctuation
+                           open_punctuation close_punctuation initial_punctuation
+                           final_punctuation other_punctuation]
+        Symbol        = %i[symbol math_symbol currency_symbol
+                           modifier_symbol other_symbol]
+        Separator     = %i[separator space_separator line_separator
+                           paragraph_separator]
+        Codepoint     = %i[other control format
+                           surrogate private_use unassigned]
+        All = Letter + Mark + Number + Punctuation +
+              Symbol + Separator + Codepoint
+      end
+      Age_V1_9_3 = %i[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 = %i[age=6.1]
+      Age_V2_2_0 = %i[age=6.2 age=6.3 age=7.0]
+      Age_V2_3_0 = %i[age=8.0]
+      Age_V2_4_0 = %i[age=9.0]
+      Age_V2_5_0 = %i[age=10.0]
+      Age_V2_6_0 = %i[age=11.0]
+      Age_V2_6_2 = %i[age=12.0]
+      Age_V2_6_3 = %i[age=12.1]
+      Age_V3_1_0 = %i[age=13.0]
+      Age_V3_2_0 = %i[age=14.0 age=15.0]
+      Age = all[:Age_V]
+      Derived_V1_9_0 = %i[
+        ascii_hex_digit
+        alphabetic
+        cased
+        changes_when_casefolded
+        changes_when_casemapped
+        changes_when_lowercased
+        changes_when_titlecased
+        changes_when_uppercased
+        case_ignorable
+        bidi_control
+        dash
+        deprecated
+        default_ignorable_code_point
+        diacritic
+        extender
+        grapheme_base
+        grapheme_extend
+        grapheme_link
+        hex_digit
+        hyphen
+        id_continue
+        ideographic
+        id_start
+        ids_binary_operator
+        ids_trinary_operator
+        join_control
+        logical_order_exception
+        lowercase
+        math
+        noncharacter_code_point
+        other_alphabetic
+        other_default_ignorable_code_point
+        other_grapheme_extend
+        other_id_continue
+        other_id_start
+        other_lowercase
+        other_math
+        other_uppercase
+        pattern_syntax
+        pattern_white_space
+        quotation_mark
+        radical
+        sentence_terminal
+        soft_dotted
+        terminal_punctuation
+        unified_ideograph
+        uppercase
+        variation_selector
+        white_space
+        xid_start
+        xid_continue
+      ]
+      Derived_V2_0_0 = %i[
+        cased_letter
+        combining_mark
+      ]
+      Derived_V2_4_0 = %i[
+        prepended_concatenation_mark
+      ]
+      Derived_V2_5_0 = %i[
+        regional_indicator
+      ]
+      Derived = all[:Derived_V]
+      Script_V1_9_0 = %i[
+        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 = %i[
+        brahmi
+        batak
+        mandaic
+      ]
+      Script_V2_0_0 = %i[
+        chakma
+        meroitic_cursive
+        meroitic_hieroglyphs
+        miao
+        sharada
+        sora_sompeng
+        takri
+      ]
+      Script_V2_2_0 = %i[
+        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 = %i[
+        ahom
+        anatolian_hieroglyphs
+        hatran
+        multani
+        old_hungarian
+        signwriting
+      ]
+      Script_V2_4_0 = %i[
+        adlam
+        bhaiksuki
+        marchen
+        newa
+        osage
+        tangut
+      ]
+      Script_V2_5_0 = %i[
+        masaram_gondi
+        nushu
+        soyombo
+        zanabazar_square
+      ]
+      Script_V2_6_0 = %i[
+        dogra
+        gunjala_gondi
+        hanifi_rohingya
+        makasar
+        medefaidrin
+        old_sogdian
+        sogdian
+      ]
+      Script_V2_6_2 = %i[
+        elymaic
+        nandinagari
+        nyiakeng_puachue_hmong
+        wancho
+      ]
+      Script_V3_1_0 = %i[
+        chorasmian
+        dives_akuru
+        khitan_small_script
+        yezidi
+      ]
+      Script_V3_2_0 = %i[
+        cypro_minoan
+        kawi
+        nag_mundari
+        old_uyghur
+        tangsa
+        toto
+        vithkuqi
+      ]
+      Script = all[:Script_V]
+      UnicodeBlock_V1_9_0 = %i[
+        in_alphabetic_presentation_forms
+        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_extended_additional
+        in_letterlike_symbols
+        in_limbu
+        in_low_surrogates
+        in_malayalam
+        in_mathematical_operators
+        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_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 = %i[
+        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 = %i[
+        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 = %i[
+        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 = %i[
+        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 = %i[
+        in_cjk_unified_ideographs_extension_f
+        in_kana_extended_a
+        in_masaram_gondi
+        in_nushu
+        in_soyombo
+        in_syriac_supplement
+        in_zanabazar_square
+      ]
+      UnicodeBlock_V2_6_0 = %i[
+        in_chess_symbols
+        in_dogra
+        in_georgian_extended
+        in_gunjala_gondi
+        in_hanifi_rohingya
+        in_indic_siyaq_numbers
+        in_makasar
+        in_mayan_numerals
+        in_medefaidrin
+        in_old_sogdian
+        in_sogdian
+      ]
+      UnicodeBlock_V2_6_2 = %i[
+        in_egyptian_hieroglyph_format_controls
+        in_elymaic
+        in_nandinagari
+        in_nyiakeng_puachue_hmong
+        in_ottoman_siyaq_numbers
+        in_small_kana_extension
+        in_symbols_and_pictographs_extended_a
+        in_tamil_supplement
+        in_wancho
+      ]
+      UnicodeBlock_V3_1_0 = %i[
+        in_chorasmian
+        in_cjk_unified_ideographs_extension_g
+        in_dives_akuru
+        in_khitan_small_script
+        in_lisu_supplement
+        in_symbols_for_legacy_computing
+        in_tangut_supplement
+        in_yezidi
+      ]
+      UnicodeBlock_V3_2_0 = %i[
+        in_arabic_extended_b
+        in_arabic_extended_c
+        in_cjk_unified_ideographs_extension_h
+        in_cypro_minoan
+        in_cyrillic_extended_d
+        in_devanagari_extended_a
+        in_ethiopic_extended_b
+        in_kaktovik_numerals
+        in_kana_extended_b
+        in_kawi
+        in_latin_extended_f
+        in_latin_extended_g
+        in_nag_mundari
+        in_old_uyghur
+        in_tangsa
+        in_toto
+        in_unified_canadian_aboriginal_syllabics_extended_a
+        in_vithkuqi
+        in_znamenny_musical_notation
+      ]
+      UnicodeBlock = all[:UnicodeBlock_V]
+      Emoji_V2_5_0 = %i[
+        emoji
+        emoji_component
+        emoji_modifier
+        emoji_modifier_base
+        emoji_presentation
+      ]
+      Emoji_V2_6_0 = %i[
+        extended_pictographic
+      ]
+      Enumerated_V2_4_0 = %i[
+        grapheme_cluster_break=control
+        grapheme_cluster_break=cr
+        grapheme_cluster_break=extend
+        grapheme_cluster_break=l
+        grapheme_cluster_break=lf
+        grapheme_cluster_break=lv
+        grapheme_cluster_break=lvt
+        grapheme_cluster_break=prepend
+        grapheme_cluster_break=regional_indicator
+        grapheme_cluster_break=spacingmark
+        grapheme_cluster_break=t
+        grapheme_cluster_break=v
+        grapheme_cluster_break=zwj
+      ]
+      Enumerated = all[:Enumerated_V]
+      Emoji = all[:Emoji_V]
+      V1_9_0 = Category::All + POSIX + all[:V1_9_0]
+      V1_9_3 = all[:V1_9_3]
+      V2_0_0 = all[:V2_0_0]
+      V2_2_0 = all[:V2_2_0]
+      V2_3_0 = all[:V2_3_0]
+      V2_4_0 = all[:V2_4_0]
+      V2_5_0 = all[:V2_5_0]
+      V2_6_0 = all[:V2_6_0]
+      V2_6_2 = all[:V2_6_2]
+      V2_6_3 = all[:V2_6_3]
+      V3_1_0 = all[:V3_1_0]
+      V3_2_0 = all[:V3_2_0]
+      All = all[/^V\d+_\d+_\d+$/]
+      Type = :property
+      NonType = :nonproperty
+    end
+    Map[UnicodeProperty::Type] = UnicodeProperty::All
+    Map[UnicodeProperty::NonType] = UnicodeProperty::All
+    # alias for symmetry between token symbol and Token module name
+    Property = UnicodeProperty
+  end
+end