regexp_parser 1.5.1 → 1.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 43db9cc4386341a5cf035787960682043390ae0d4c19c7e2a165a6e3a1f58a3e
-  data.tar.gz: c501318f87c285e73ae5374cc7accc9b1822d9c08ac4a6db7e95aa7a031d69bd
+  metadata.gz: 0e084510a97816730f68028cba8be7b9ee576e886347952d8400cd26293f3361
+  data.tar.gz: f98f2bbb3558c6a50d3415c830ba6dae1f09b2aca944f411b88c1cd65d527f60
 SHA512:
-  metadata.gz: 85e8424ad11e4cb8d50d8900be3bd5fc79755a49561d5ae64e4d0913dccd0473254d2ad78e77a2695013b81dcc70c78c7209049b291d7cab5784c9cc4e6c8043
-  data.tar.gz: de283a627fc5caed42da0c01cab7f9680136c2438536d443c2c3a62d7f8fb1fda86d2a5f7daf2f3d5d3f111d5e23abf3beff55586d7560f76f23b03aa926bbd9
+  metadata.gz: 972c429ea4b47e2d2fefbc087cb23362f3e385cbbdbbead8013537d9bfe12b07237dcb1dcfaab6e1793037347d310702fa7fc035ab874dc24722b041493cc3f2
+  data.tar.gz: 6ace6c2390101f9d95bcc9325ba70c4d4d9d90d5796ab015ffcef1f58b907eb3a2649ee07f3f77e6f2682a2f4803e6f94e634855e39a97480a1fb17f00b97c23

data/CHANGELOG.md

@@ -1,5 +1,11 @@
 ## [Unreleased]
 
+### [1.6.0] - 2019-06-16 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Added
+
+- Added support for 16 new unicode properties introduced in Ruby 2.6.2 and 2.6.3
+
 ### [1.5.1] - 2019-05-23 - [Janosch Müller](mailto:janosch84@gmail.com)
 
 ### Fixed

data/Gemfile

@@ -3,7 +3,7 @@ source 'https://rubygems.org'
 gemspec
 
 group :development, :test do
-  gem 'rake'
-  gem 'regexp_property_values'
-  gem 'rspec'
+  gem 'rake', '~> 12.2'
+  gem 'regexp_property_values', '~> 1.0'
+  gem 'rspec', '~> 3.8'
 end

data/Rakefile

@@ -74,14 +74,13 @@ namespace :props do
       puts "Wrote #{hash.count} aliases to `#{path}`"
     end
 
-    _, long_names = RegexpPropertyValues.short_and_long_names
-    long_names_to_tokens = long_names.map do |name|
-      [name.downcase.gsub(/[^0-9a-z=.]/, ''), name.downcase]
+    long_names_to_tokens = RegexpPropertyValues.all.map do |val|
+      [val.identifier, val.full_name.downcase]
     end
     write_hash_to_file.call(long_names_to_tokens, "#{dir}/long.yml")
 
     short_names_to_tokens = RegexpPropertyValues.alias_hash.map do |k, v|
-      [k.downcase.gsub(/[^0-9a-z=.]/, ''), v.downcase]
+      [k.identifier, v.full_name.downcase]
     end
     write_hash_to_file.call(short_names_to_tokens, "#{dir}/short.yml")
   end

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

@@ -6,6 +6,8 @@ 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=2.0: age=2.0
 age=2.1: age=2.1
 age=3.0: age=3.0
@@ -64,7 +66,6 @@ changeswhenuppercased: changes_when_uppercased
 cherokee: cherokee
 closepunctuation: close_punctuation
 cntrl: cntrl
-combiningmark: combining_mark
 common: common
 connectorpunctuation: connector_punctuation
 control: control
@@ -86,6 +87,7 @@ dogra: dogra
 duployan: duployan
 egyptianhieroglyphs: egyptian_hieroglyphs
 elbasan: elbasan
+elymaic: elymaic
 emoji: emoji
 emojicomponent: emoji_component
 emojimodifier: emoji_modifier
@@ -206,8 +208,10 @@ 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
@@ -322,12 +326,14 @@ inmyanmar: in_myanmar
 inmyanmarextendeda: in_myanmar_extended_a
 inmyanmarextendedb: in_myanmar_extended_b
 innabataean: in_nabataean
+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
@@ -343,6 +349,7 @@ 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
@@ -368,6 +375,7 @@ 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
@@ -386,6 +394,7 @@ 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
 insyriac: in_syriac
 insyriacsupplement: in_syriac_supplement
 intagalog: in_tagalog
@@ -397,6 +406,7 @@ intaiviet: in_tai_viet
 intaixuanjingsymbols: in_tai_xuan_jing_symbols
 intakri: in_takri
 intamil: in_tamil
+intamilsupplement: in_tamil_supplement
 intangut: in_tangut
 intangutcomponents: in_tangut_components
 intelugu: in_telugu
@@ -414,6 +424,7 @@ invariationselectors: in_variation_selectors
 invariationselectorssupplement: in_variation_selectors_supplement
 invedicextensions: in_vedic_extensions
 inverticalforms: in_vertical_forms
+inwancho: in_wancho
 inwarangciti: in_warang_citi
 inyijinghexagramsymbols: in_yijing_hexagram_symbols
 inyiradicals: in_yi_radicals
@@ -469,6 +480,7 @@ mro: mro
 multani: multani
 myanmar: myanmar
 nabataean: nabataean
+nandinagari: nandinagari
 newa: newa
 newline: newline
 newtailue: new_tai_lue
@@ -477,6 +489,7 @@ noncharactercodepoint: noncharacter_code_point
 nonspacingmark: nonspacing_mark
 number: number
 nushu: nushu
+nyiakengpuachuehmong: nyiakeng_puachue_hmong
 ogham: ogham
 olchiki: ol_chiki
 oldhungarian: old_hungarian
@@ -569,6 +582,7 @@ uppercase: uppercase
 uppercaseletter: uppercase_letter
 vai: vai
 variationselector: variation_selector
+wancho: wancho
 warangciti: warang_citi
 whitespace: white_space
 word: word

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

@@ -31,6 +31,7 @@ cher: cherokee
 ci: case_ignorable
 cn: unassigned
 co: private_use
+combiningmark: mark
 copt: coptic
 cprt: cypriot
 cs: surrogate
@@ -49,6 +50,7 @@ dsrt: deseret
 dupl: duployan
 egyp: egyptian_hieroglyphs
 elba: elbasan
+elym: elymaic
 ethi: ethiopic
 ext: extender
 geor: georgian
@@ -72,6 +74,7 @@ hex: hex_digit
 hira: hiragana
 hluw: anatolian_hieroglyphs
 hmng: pahawh_hmong
+hmnp: nyiakeng_puachue_hmong
 hung: old_hungarian
 idc: id_continue
 ideo: ideographic
@@ -125,6 +128,7 @@ mtei: meetei_mayek
 mult: multani
 mymr: myanmar
 n: number
+nand: nandinagari
 narb: old_north_arabian
 nbat: nabataean
 nchar: noncharacter_code_point
@@ -216,6 +220,7 @@ uideo: unified_ideograph
 vaii: vai
 vs: variation_selector
 wara: warang_citi
+wcho: wancho
 wspace: white_space
 xidc: xid_continue
 xids: xid_start

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

@@ -53,6 +53,10 @@ module Regexp::Syntax
 
       Age_V2_6_0 = [:'age=11.0']
 
+      Age_V2_6_2 = [:'age=12.0']
+
+      Age_V2_6_3 = [:'age=12.1']
+
       Age = all[:Age_V]
 
       Derived_V1_9_0 = [
@@ -297,6 +301,18 @@ module Regexp::Syntax
         :sogdian,
       ]
 
+      Script_V2_6_2 = [
+        :egyptian_hieroglyph_format_controls,
+        :elymaic,
+        :nandinagari,
+        :nyiakeng_puachue_hmong,
+        :ottoman_siyaq_numbers,
+        :small_kana_extension,
+        :symbols_and_pictographs_extended_a,
+        :tamil_supplement,
+        :wancho,
+      ]
+
       Script = all[:Script_V]
 
       UnicodeBlock_V1_9_0 = [
@@ -612,6 +628,18 @@ module Regexp::Syntax
         :in_sogdian,
       ]
 
+      UnicodeBlock_V2_6_2 = [
+        :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 = all[:UnicodeBlock_V]
 
       Emoji_V2_5_0 = [
@@ -632,6 +660,8 @@ module Regexp::Syntax
       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]
 
       All = all[/^V\d+_\d+_\d+$/]
 

data/lib/regexp_parser/syntax/versions/2.6.2.rb

@@ -0,0 +1,10 @@
+module Regexp::Syntax
+  class V2_6_2 < Regexp::Syntax::V2_6_0
+    def initialize
+      super
+
+      implements :property,    UnicodeProperty::V2_6_2
+      implements :nonproperty, UnicodeProperty::V2_6_2
+    end
+  end
+end

data/lib/regexp_parser/syntax/versions/2.6.3.rb

@@ -0,0 +1,10 @@
+module Regexp::Syntax
+  class V2_6_3 < Regexp::Syntax::V2_6_2
+    def initialize
+      super
+
+      implements :property,    UnicodeProperty::V2_6_3
+      implements :nonproperty, UnicodeProperty::V2_6_3
+    end
+  end
+end

data/lib/regexp_parser/version.rb

@@ -1,5 +1,5 @@
 class Regexp
   class Parser
-    VERSION = '1.5.1'
+    VERSION = '1.6.0'
   end
 end

data/spec/parser/properties_spec.rb

@@ -65,7 +65,7 @@ RSpec.describe('Property parsing') do
   end
 
   specify('parse property shortcut') do
-    expect(RP.parse('\p{mark}')[0].shortcut).to eq 'm'
+    expect(RP.parse('\p{lowercase_letter}')[0].shortcut).to eq 'll'
     expect(RP.parse('\p{sc}')[0].shortcut).to eq 'sc'
     expect(RP.parse('\p{in_bengali}')[0].shortcut).to be_nil
   end

data/spec/syntax/versions/aliases_spec.rb

@@ -25,7 +25,9 @@ RSpec.describe(Regexp::Syntax) do
   include_examples 'syntax alias', 'ruby/2.5.0',  Regexp::Syntax::V2_4_1
   include_examples 'syntax alias', 'ruby/2.5',    Regexp::Syntax::V2_5_0
   include_examples 'syntax alias', 'ruby/2.6.0',  Regexp::Syntax::V2_5_0
-  include_examples 'syntax alias', 'ruby/2.6',    Regexp::Syntax::V2_5_0
+  include_examples 'syntax alias', 'ruby/2.6.2',  Regexp::Syntax::V2_6_2
+  include_examples 'syntax alias', 'ruby/2.6.3',  Regexp::Syntax::V2_6_3
+  include_examples 'syntax alias', 'ruby/2.6',    Regexp::Syntax::V2_6_3
 
   specify('future alias warning') do
     expect { Regexp::Syntax.new('ruby/5.0') }

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp_parser
 version: !ruby/object:Gem::Version
-  version: 1.5.1
+  version: 1.6.0
 platform: ruby
 authors:
 - Ammar Ali
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-05-23 00:00:00.000000000 Z
+date: 2019-07-16 00:00:00.000000000 Z
 dependencies: []
 description: A library for tokenizing, lexing, and parsing Ruby regular expressions.
 email:
@@ -87,6 +87,8 @@ files:
 - 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/syntax/versions/2.6.2.rb
+- lib/regexp_parser/syntax/versions/2.6.3.rb
 - lib/regexp_parser/token.rb
 - lib/regexp_parser/version.rb
 - regexp_parser.gemspec