regexp_parser 1.3.0 → 1.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9af74355b57139b93d0207bfbf6fc6fbb43c1eb6aa531bd11710e39168af107a
-  data.tar.gz: 8d63533aa2206b121fd59959a43cad2b64e3b3c6d0f8617953d2c401033c86d5
+  metadata.gz: 0ff2b9541be8d00d5a0f8a355ebb9ab6bc5bc2ac50ffa14df13144bf2d239b42
+  data.tar.gz: b5d4c720eaa3606a7973b110251a5fb1fe87e11714fed5a195908678098a4cbe
 SHA512:
-  metadata.gz: de6afb1888075eaa8d220192882494eb67c54aaba5fa84b991adf753dbb06949b8b0ea6d44054d32c3cba1e8cb6ee04d8f8f2f8643e4663188ddca3b7ec7e07a
-  data.tar.gz: f9e7d91a317bb153b645380a6447faca2656b87fa164afae9dc1cf9bc63463c11a87388258d18a49ed3df7afc3a7b25cd0a2113db412c2e7f504cee9aec8c255
+  metadata.gz: e8759d373fdea7bbd455a5e2ff96ce1a64cb81f35c325fad49a886a99388897486c1904a847a072b14b245e6da0dded81c3ef031e74944b2fe5d8c67a4cffaab
+  data.tar.gz: 6e39afe8a277eced992c0508a99d022dba939401925e6e3e793cab364d0b3b2143cfade3a433b9d0445c49004dad781dc04f7a99c69229c471dff7095823d065

data/CHANGELOG.md

@@ -1,5 +1,11 @@
 ## [Unreleased]
 
+### [1.4.0] - 2019-04-02 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Added
+
+- Added support for 19 new unicode properties introduced in Ruby 2.6.0
+
 ### [1.3.0] - 2018-11-14 - [Janosch Müller](mailto:janosch84@gmail.com)
 
 ### Added

data/README.md

@@ -357,7 +357,7 @@ _Note that not all of these are available in all versions of Ruby_
 |   _**Meta**_                | `\M-c`, `\M-\C-C`, `\M-\cC`, `\C-\M-C`, `\c\M-C`        | ✓ |
 |   _**Octal**_               | `\0`, `\01`, `\012`                                     | ✓ |
 |   _**Unicode**_             | `\uHHHH`, `\u{H+ H+}`                                   | ✓ |
-| **Unicode Properties**                | _<sub>([Unicode 10.0.0](http://www.unicode.org/versions/Unicode10.0.0/))</sub>_ | &#x22f1; |
+| **Unicode Properties**                | _<sub>([Unicode 11.0.0](http://www.unicode.org/versions/Unicode11.0.0/))</sub>_ | &#x22f1; |
 | &emsp;&nbsp;_**Age**_                 | `\p{Age=5.2}`, `\P{age=7.0}`, `\p{^age=8.0}`            | &#x2713; |
 | &emsp;&nbsp;_**Blocks**_              | `\p{InArmenian}`, `\P{InKhmer}`, `\p{^InThai}`          | &#x2713; |
 | &emsp;&nbsp;_**Classes**_             | `\p{Alpha}`, `\P{Space}`, `\p{^Alnum}`                  | &#x2713; |

data/lib/regexp_parser/scanner/properties/long.yml

@@ -5,6 +5,7 @@
 adlam: adlam
 age=1.1: age=1.1
 age=10.0: age=10.0
+age=11.0: age=11.0
 age=2.0: age=2.0
 age=2.1: age=2.1
 age=3.0: age=3.0
@@ -81,6 +82,7 @@ deseret: deseret
 devanagari: devanagari
 diacritic: diacritic
 digit: digit
+dogra: dogra
 duployan: duployan
 egyptianhieroglyphs: egyptian_hieroglyphs
 elbasan: elbasan
@@ -104,9 +106,11 @@ 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
@@ -160,6 +164,7 @@ inchakma: in_chakma
 incham: in_cham
 incherokee: in_cherokee
 incherokeesupplement: in_cherokee_supplement
+inchesssymbols: in_chess_symbols
 incjkcompatibility: in_cjk_compatibility
 incjkcompatibilityforms: in_cjk_compatibility_forms
 incjkcompatibilityideographs: in_cjk_compatibility_ideographs
@@ -197,6 +202,7 @@ indeseret: in_deseret
 indevanagari: in_devanagari
 indevanagariextended: in_devanagari_extended
 indingbats: in_dingbats
+indogra: in_dogra
 indominotiles: in_domino_tiles
 induployan: in_duployan
 inearlydynasticcuneiform: in_early_dynastic_cuneiform
@@ -215,6 +221,7 @@ 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
@@ -223,6 +230,7 @@ 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
@@ -230,6 +238,7 @@ 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
@@ -240,6 +249,7 @@ 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
@@ -279,6 +289,7 @@ 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
@@ -286,6 +297,8 @@ 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
@@ -322,6 +335,7 @@ 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
 inopticalcharacterrecognition: in_optical_character_recognition
@@ -354,6 +368,7 @@ insiddham: in_siddham
 insinhala: in_sinhala
 insinhalaarchaicnumbers: in_sinhala_archaic_numbers
 insmallformvariants: in_small_form_variants
+insogdian: in_sogdian
 insorasompeng: in_sora_sompeng
 insoyombo: in_soyombo
 inspacingmodifierletters: in_spacing_modifier_letters
@@ -431,6 +446,7 @@ lowercaseletter: lowercase_letter
 lycian: lycian
 lydian: lydian
 mahajani: mahajani
+makasar: makasar
 malayalam: malayalam
 mandaic: mandaic
 manichaean: manichaean
@@ -439,6 +455,7 @@ mark: mark
 masaramgondi: masaram_gondi
 math: math
 mathsymbol: math_symbol
+medefaidrin: medefaidrin
 meeteimayek: meetei_mayek
 mendekikakui: mende_kikakui
 meroiticcursive: meroitic_cursive
@@ -467,6 +484,7 @@ olditalic: old_italic
 oldnortharabian: old_north_arabian
 oldpermic: old_permic
 oldpersian: old_persian
+oldsogdian: old_sogdian
 oldsoutharabian: old_south_arabian
 oldturkic: old_turkic
 openpunctuation: open_punctuation
@@ -515,6 +533,7 @@ siddham: siddham
 signwriting: signwriting
 sinhala: sinhala
 softdotted: soft_dotted
+sogdian: sogdian
 sorasompeng: sora_sompeng
 soyombo: soyombo
 space: space

data/lib/regexp_parser/scanner/properties/short.yml

@@ -44,6 +44,7 @@ dep: deprecated
 deva: devanagari
 di: default_ignorable_code_point
 dia: diacritic
+dogr: dogra
 dsrt: deseret
 dupl: duployan
 egyp: egyptian_hieroglyphs
@@ -52,6 +53,7 @@ ethi: ethiopic
 ext: extender
 geor: georgian
 glag: glagolitic
+gong: gunjala_gondi
 gonm: masaram_gondi
 goth: gothic
 gran: grantha
@@ -105,11 +107,13 @@ lyci: lycian
 lydi: lydian
 m: mark
 mahj: mahajani
+maka: makasar
 mand: mandaic
 mani: manichaean
 marc: marchen
 mc: spacing_mark
 me: enclosing_mark
+medf: medefaidrin
 mend: mende_kikakui
 merc: meroitic_cursive
 mero: meroitic_hieroglyphs
@@ -168,6 +172,7 @@ qaai: inherited
 qmark: quotation_mark
 ri: regional_indicator
 rjng: rejang
+rohg: hanifi_rohingya
 runr: runic
 s: symbol
 samr: samaritan
@@ -184,6 +189,8 @@ sinh: sinhala
 sk: modifier_symbol
 sm: math_symbol
 so: other_symbol
+sogd: sogdian
+sogo: old_sogdian
 sora: sora_sompeng
 soyo: soyombo
 sterm: sentence_terminal

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

@@ -1,6 +1,8 @@
 module Regexp::Syntax
   module Token
     module UnicodeProperty
+      all = proc { |name| constants.grep(/#{name}/).flat_map(&method(:const_get)) }
+
       CharType_V1_9_0 = [:alnum, :alpha, :ascii, :blank, :cntrl, :digit, :graph,
                          :lower, :print, :punct, :space, :upper, :word, :xdigit]
 
@@ -49,7 +51,9 @@ module Regexp::Syntax
 
       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
+      Age_V2_6_0 = [:'age=11.0']
+
+      Age = all[:Age_V]
 
       Derived_V1_9_0 = [
         :ascii_hex_digit,
@@ -118,7 +122,7 @@ module Regexp::Syntax
         :regional_indicator
       ]
 
-      Derived = Derived_V1_9_0 + Derived_V2_0_0 + Derived_V2_4_0 + Derived_V2_5_0
+      Derived = all[:Derived_V]
 
       Script_V1_9_0 = [
         :arabic,
@@ -283,8 +287,17 @@ module Regexp::Syntax
         :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
+      Script_V2_6_0 = [
+        :dogra,
+        :gunjala_gondi,
+        :hanifi_rohingya,
+        :makasar,
+        :medefaidrin,
+        :old_sogdian,
+        :sogdian,
+      ]
+
+      Script = all[:Script_V]
 
       UnicodeBlock_V1_9_0 = [
         :in_alphabetic_presentation_forms,
@@ -585,8 +598,21 @@ module Regexp::Syntax
         :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
+      UnicodeBlock_V2_6_0 = [
+        :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 = all[:UnicodeBlock_V]
 
       Emoji_V2_5_0 = [
         :emoji,
@@ -596,23 +622,18 @@ module Regexp::Syntax
         :emoji_presentation,
       ]
 
-      Emoji = Emoji_V2_5_0
-
-      V1_9_0 = Category::All + POSIX + CharType_V1_9_0 + 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 + Derived_V2_0_0 + Script_V2_0_0 + UnicodeBlock_V2_0_0
-
-      V2_2_0 = Age_V2_2_0 + Script_V2_2_0 + UnicodeBlock_V2_2_0
-
-      V2_3_0 = Age_V2_3_0 + Script_V2_3_0 + UnicodeBlock_V2_3_0
-
-      V2_4_0 = Age_V2_4_0 + Derived_V2_4_0 + Script_V2_4_0 + UnicodeBlock_V2_4_0
+      Emoji = all[:Emoji_V]
 
-      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
+      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]
 
-      All = V1_9_0 + V1_9_3 + V2_0_0 + V2_2_0 + V2_3_0 + V2_4_0 + V2_5_0
+      All = all[/^V\d+_\d+_\d+$/]
 
       Type = :property
       NonType = :nonproperty

data/lib/regexp_parser/syntax/versions/2.6.0.rb

@@ -0,0 +1,10 @@
+module Regexp::Syntax
+  class V2_6_0 < Regexp::Syntax::V2_5
+    def initialize
+      super
+
+      implements :property,    UnicodeProperty::V2_6_0
+      implements :nonproperty, UnicodeProperty::V2_6_0
+    end
+  end
+end

data/lib/regexp_parser/version.rb

@@ -1,5 +1,5 @@
 class Regexp
   class Parser
-    VERSION = '1.3.0'
+    VERSION = '1.4.0'
   end
 end

data/regexp_parser.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |gem|
 
   gem.summary       = "Scanner, lexer, parser for ruby's regular expressions"
   gem.description   = 'A library for tokenizing, lexing, and parsing Ruby regular expressions.'
-  gem.homepage      = 'http://github.com/ammar/regexp_parser'
+  gem.homepage      = 'https://github.com/ammar/regexp_parser'
 
   if gem.respond_to?(:metadata)
     gem.metadata    = { 'issue_tracker' => 'https://github.com/ammar/regexp_parser/issues' }

data/test/parser/test_properties.rb

@@ -17,6 +17,7 @@ class ParserProperties < Test::Unit::TestCase
     'xidc',
     'XID_Continue',
     'Emoji',
+    'InChessSymbols',
   ]
 
   modes.each do |mode|
@@ -24,7 +25,7 @@ class ParserProperties < Test::Unit::TestCase
 
     example_props.each do |property|
       define_method "test_parse_#{token_type}_#{property}" do
-        t = RP.parse "ab\\#{mode}{#{property}}", 'ruby/2.5'
+        t = RP.parse "ab\\#{mode}{#{property}}", '*'
 
         assert t.expressions.last.is_a?(UnicodeProperty::Base),
                "Expected property, but got #{t.expressions.last.class.name}"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp_parser
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.4.0
 platform: ruby
 authors:
 - Ammar Ali
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-11-14 00:00:00.000000000 Z
+date: 2019-04-02 00:00:00.000000000 Z
 dependencies: []
 description: A library for tokenizing, lexing, and parsing Ruby regular expressions.
 email:
@@ -83,6 +83,7 @@ files:
 - lib/regexp_parser/syntax/versions/2.4.0.rb
 - lib/regexp_parser/syntax/versions/2.4.1.rb
 - lib/regexp_parser/syntax/versions/2.5.0.rb
+- lib/regexp_parser/syntax/versions/2.6.0.rb
 - lib/regexp_parser/token.rb
 - lib/regexp_parser/version.rb
 - regexp_parser.gemspec
@@ -155,7 +156,7 @@ files:
 - test/test_all.rb
 - test/token/test_all.rb
 - test/token/test_token.rb
-homepage: http://github.com/ammar/regexp_parser
+homepage: https://github.com/ammar/regexp_parser
 licenses:
 - MIT
 metadata:
@@ -177,8 +178,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: Scanner, lexer, parser for ruby's regular expressions