regexp_property_values 1.2.0 → 1.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6ce99d3efe4e87c82e59b220f8b8b317edb00f971dd82427bbd73ddfbcaa05ae
-  data.tar.gz: e3499f430a59db35346f84b708a4aaceedaa8ecdb5dc25b075666b5ff110be4e
+  metadata.gz: 3e530cc9c245b9a0295f3f4d155ba9cdb32d2d105c8e6beae6f59771eee8e862
+  data.tar.gz: 295197787f2ca187ac8a0ca57eebd1551cf8a243389a107d66fcedb49bc7f792
 SHA512:
-  metadata.gz: 9bc766948aa42da07f0e2c2aabee929139e7fe052d2b28ec117ed923e50b25bd8b7214c58f0aeaf08f52c05d8bdc4d613c6b1d70796344eff064fa793c5bb2ae
-  data.tar.gz: 84256ff9ee3de75f56d2dd6d31ee0f1096ebd28d97fd8f52e085452d550bd53122cf3baaaeac8d7903b6515b659083b478dcb3b81946825472fba73b43605a07
+  metadata.gz: 5879eb2ec3999b46aa8fa66340b0d22704f828328285625670ef8bf2e67e1b10162dd89149ff9950f3842bab0f1978f7975fba0a5bdacb0085e3c9bc070afbf5
+  data.tar.gz: af154b78b8a44ef2ef7fe988d47564c565ab6e4e1a03ca2bc7a0c1951ef556c2ae6f054fa98fdfb775cb34b2a36913cfa6621dc883a44b533290a50dd4861daa

data/CHANGELOG.md

@@ -4,6 +4,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [1.4.0] - 2023-06-10
+
+### Added
+- new properties of Ruby 3.2 / Unicode 15.0
+
+## [1.3.0] - 2022-04-07
+
+### Added
+- new properties of Ruby 3.2 / Unicode 14.0
+
 ## [1.2.0] - 2021-12-31
 
 ### Added

data/Rakefile

@@ -32,3 +32,9 @@ if RUBY_PLATFORM !~ /java/i
   # recompile before running specs
   task(:spec).enhance([:compile])
 end
+
+desc 'Update property lists'
+task :update do
+  require_relative 'lib/regexp_property_values'
+  RegexpPropertyValues.update
+end

data/lib/aliases

@@ -35,6 +35,7 @@ Cn;Unassigned
 Co;Private_Use
 Combining_Mark;Mark
 Copt;Coptic
+Cpmn;Cypro_Minoan
 Cprt;Cypriot
 Cs;Surrogate
 Cyrl;Cyrillic
@@ -132,6 +133,7 @@ Mult;Multani
 Mymr;Myanmar
 N;Number
 NChar;Noncharacter_Code_Point
+Nagm;Nag_Mundari
 Nand;Nandinagari
 Narb;Old_North_Arabian
 Nbat;Nabataean
@@ -154,6 +156,7 @@ Orkh;Old_Turkic
 Orya;Oriya
 Osge;Osage
 Osma;Osmanya
+Ougr;Old_Uyghur
 P;Punctuation
 PCM;Prepended_Concatenation_Mark
 Palm;Palmyrene
@@ -218,10 +221,12 @@ Tglg;Tagalog
 Thaa;Thaana
 Tibt;Tibetan
 Tirh;Tirhuta
+Tnsa;Tangsa
 UIdeo;Unified_Ideograph
 Ugar;Ugaritic
 VS;Variation_Selector
 Vaii;Vai
+Vith;Vithkuqi
 WSpace;White_Space
 Wara;Warang_Citi
 Wcho;Wancho

data/lib/regexp_property_values/updater.rb

@@ -5,7 +5,7 @@ module RegexpPropertyValues
     require 'fileutils'
     require 'set'
 
-    BASE_URL = 'http://www.unicode.org/Public'
+    BASE_URL = 'https://www.unicode.org/Public/UCD/latest/ucd'
 
     UCD_FILES = %w[
       Blocks.txt
@@ -38,26 +38,11 @@ module RegexpPropertyValues
     end
 
     def download_ucd_files(ucd_path: nil, emoji_path: nil)
-      unicode_version = RbConfig::CONFIG.fetch('UNICODE_VERSION')
-      emoji_version   = RbConfig::CONFIG.fetch('UNICODE_EMOJI_VERSION')
-
-      ucd_path   ||= ENV['RPV_UCD_PATH']
-      emoji_path ||= ENV['RPV_EMOJI_PATH']
-
-      if ucd_path.nil? && emoji_path.nil?
-        puts <<-EOS.gsub(/\n */, ' ')
-          This try will load ucd and emoji data for the CURRENT RUBY (
-          (#{RUBY_VERSION} - ucd #{unicode_version}, emoji #{emoji_version}).
-          Run this on the latest Ruby version you want to support.
-          Unicode directory structure changes sometimes, so you might need to
-          pass the right path(s) as keyword args or ENV vars. Continue? [y/n]'
-        EOS
-
-        return puts 'download skipped.' unless $stdin.gets =~ /^y/i
-      end
+      puts 'This will try to load the latest UCD data. Continue? [y/n]'
+      return puts 'download skipped.' unless $stdin.gets =~ /^y/i
 
-      ucd_path   ||= "#{BASE_URL}/#{unicode_version}/ucd"
-      emoji_path ||= "#{BASE_URL}/emoji/#{emoji_version}"
+      ucd_path   ||= ENV['RPV_UCD_PATH']   || BASE_URL
+      emoji_path ||= ENV['RPV_EMOJI_PATH'] || "#{BASE_URL}/emoji/"
 
       Dir.chdir(TMP_DIR) do
         UCD_FILES.each   { |f| `wget #{ucd_path}/#{f}` }
@@ -76,7 +61,9 @@ module RegexpPropertyValues
       ]
 
       # special properties
-      @values += %w[Any Assigned In_No_Block Unknown]
+      @values += %w[
+        Any Assigned Extended_Pictographic In_No_Block Unknown
+      ]
 
       # legacy properties
       @values += %w[Newline]

data/lib/regexp_property_values/version.rb

@@ -1,3 +1,3 @@
 module RegexpPropertyValues
-  VERSION = '1.2.0'
+  VERSION = '1.4.0'
 end

data/lib/values

@@ -7,6 +7,8 @@ Age=11.0
 Age=12.0
 Age=12.1
 Age=13.0
+Age=14.0
+Age=15.0
 Age=2.0
 Age=2.1
 Age=3.0
@@ -71,6 +73,7 @@ Coptic
 Cuneiform
 Currency_Symbol
 Cypriot
+Cypro_Minoan
 Cyrillic
 Dash
 Dash_Punctuation
@@ -94,6 +97,7 @@ Emoji_Modifier_Base
 Emoji_Presentation
 Enclosing_Mark
 Ethiopic
+Extended_Pictographic
 Extender
 Final_Punctuation
 Format
@@ -135,6 +139,8 @@ In_Ancient_Greek_Numbers
 In_Ancient_Symbols
 In_Arabic
 In_Arabic_Extended_A
+In_Arabic_Extended_B
+In_Arabic_Extended_C
 In_Arabic_Mathematical_Alphabetic_Symbols
 In_Arabic_Presentation_Forms_A
 In_Arabic_Presentation_Forms_B
@@ -174,6 +180,7 @@ In_CJK_Unified_Ideographs_Extension_D
 In_CJK_Unified_Ideographs_Extension_E
 In_CJK_Unified_Ideographs_Extension_F
 In_CJK_Unified_Ideographs_Extension_G
+In_CJK_Unified_Ideographs_Extension_H
 In_Carian
 In_Caucasian_Albanian
 In_Chakma
@@ -196,14 +203,17 @@ In_Cuneiform
 In_Cuneiform_Numbers_and_Punctuation
 In_Currency_Symbols
 In_Cypriot_Syllabary
+In_Cypro_Minoan
 In_Cyrillic
 In_Cyrillic_Extended_A
 In_Cyrillic_Extended_B
 In_Cyrillic_Extended_C
+In_Cyrillic_Extended_D
 In_Cyrillic_Supplement
 In_Deseret
 In_Devanagari
 In_Devanagari_Extended
+In_Devanagari_Extended_A
 In_Dingbats
 In_Dives_Akuru
 In_Dogra
@@ -222,6 +232,7 @@ In_Enclosed_Ideographic_Supplement
 In_Ethiopic
 In_Ethiopic_Extended
 In_Ethiopic_Extended_A
+In_Ethiopic_Extended_B
 In_Ethiopic_Supplement
 In_General_Punctuation
 In_Geometric_Shapes
@@ -260,13 +271,16 @@ In_Inscriptional_Pahlavi
 In_Inscriptional_Parthian
 In_Javanese
 In_Kaithi
+In_Kaktovik_Numerals
 In_Kana_Extended_A
+In_Kana_Extended_B
 In_Kana_Supplement
 In_Kanbun
 In_Kangxi_Radicals
 In_Kannada
 In_Katakana
 In_Katakana_Phonetic_Extensions
+In_Kawi
 In_Kayah_Li
 In_Kharoshthi
 In_Khitan_Small_Script
@@ -282,6 +296,8 @@ In_Latin_Extended_B
 In_Latin_Extended_C
 In_Latin_Extended_D
 In_Latin_Extended_E
+In_Latin_Extended_F
+In_Latin_Extended_G
 In_Lepcha
 In_Letterlike_Symbols
 In_Limbu
@@ -329,6 +345,7 @@ In_Myanmar_Extended_A
 In_Myanmar_Extended_B
 In_NKo
 In_Nabataean
+In_Nag_Mundari
 In_Nandinagari
 In_New_Tai_Lue
 In_Newa
@@ -346,6 +363,7 @@ In_Old_Persian
 In_Old_Sogdian
 In_Old_South_Arabian
 In_Old_Turkic
+In_Old_Uyghur
 In_Optical_Character_Recognition
 In_Oriya
 In_Ornamental_Dingbats
@@ -408,6 +426,7 @@ In_Tai_Xuan_Jing_Symbols
 In_Takri
 In_Tamil
 In_Tamil_Supplement
+In_Tangsa
 In_Tangut
 In_Tangut_Components
 In_Tangut_Supplement
@@ -417,15 +436,18 @@ In_Thai
 In_Tibetan
 In_Tifinagh
 In_Tirhuta
+In_Toto
 In_Transport_and_Map_Symbols
 In_Ugaritic
 In_Unified_Canadian_Aboriginal_Syllabics
 In_Unified_Canadian_Aboriginal_Syllabics_Extended
+In_Unified_Canadian_Aboriginal_Syllabics_Extended_A
 In_Vai
 In_Variation_Selectors
 In_Variation_Selectors_Supplement
 In_Vedic_Extensions
 In_Vertical_Forms
+In_Vithkuqi
 In_Wancho
 In_Warang_Citi
 In_Yezidi
@@ -433,6 +455,7 @@ In_Yi_Radicals
 In_Yi_Syllables
 In_Yijing_Hexagram_Symbols
 In_Zanabazar_Square
+In_Znamenny_Musical_Notation
 Inherited
 Initial_Punctuation
 Inscriptional_Pahlavi
@@ -442,6 +465,7 @@ Join_Control
 Kaithi
 Kannada
 Katakana
+Kawi
 Kayah_Li
 Kharoshthi
 Khitan_Small_Script
@@ -488,6 +512,7 @@ Mro
 Multani
 Myanmar
 Nabataean
+Nag_Mundari
 Nandinagari
 New_Tai_Lue
 Newa
@@ -508,6 +533,7 @@ Old_Persian
 Old_Sogdian
 Old_South_Arabian
 Old_Turkic
+Old_Uyghur
 Open_Punctuation
 Oriya
 Osage
@@ -572,6 +598,7 @@ Tai_Tham
 Tai_Viet
 Takri
 Tamil
+Tangsa
 Tangut
 Telugu
 Terminal_Punctuation
@@ -581,6 +608,7 @@ Tibetan
 Tifinagh
 Tirhuta
 Titlecase_Letter
+Toto
 Ugaritic
 Unassigned
 Unified_Ideograph
@@ -590,6 +618,7 @@ Uppercase
 Uppercase_Letter
 Vai
 Variation_Selector
+Vithkuqi
 Wancho
 Warang_Citi
 White_Space

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp_property_values
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.4.0
 platform: ruby
 authors:
 - Janosch Müller
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-12-31 00:00:00.000000000 Z
+date: 2023-06-10 00:00:00.000000000 Z
 dependencies: []
 description: This small library lets you see which property values are supported by
   the regular expression engine of the Ruby version you are running, and what they
@@ -61,7 +61,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.0.dev
+rubygems_version: 3.4.10
 signing_key:
 specification_version: 4
 summary: Inspect property values supported by Ruby's regex engine