unicode-scripts 1.12.0 → 1.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 408f42160ba401c0d6434f304703bea2f037ace4ba151887111003970564ea08
-  data.tar.gz: 1392a2b3b7b4a717343334f5ac60c0cfec4b32773fddfd46c2287cdda2232279
+  metadata.gz: b0b88898119662f0432faae60c47e9271c09cbf0b0be6a4eef47d5b7c4d92fff
+  data.tar.gz: 46d74594eed212777caffe3fa29bdaaf1f04ddfb5eaaf6f18e6b761a794cb2d1
 SHA512:
-  metadata.gz: 9dad0578c6bee57413301c74c08ec09e86b517d3c206e6671d038dfae3c2b85e624b58ee46a32cf1abf01f8f834be136e7234254e2f147f56bca15901163fe69
-  data.tar.gz: b8f1e8895cff59f52e50d191465bc4608376ff7178b2e96c5e3f720c45abd81636f7c7cac386a3492ad36c8b72e4cd69cff193d02050e123dba7222ce0480507
+  metadata.gz: 777938842e782d0fe2d4ae853e2d8311c65d2bfd2ab62bfed02bc0d43921ad01f1dfe349c56d02e83e7c496bc71c8278c462d0474baf233bffa54ecbd99aedaa
+  data.tar.gz: 4da9b319921f9146dd33080642ca34099af995da26b08546de360ef213cd90f16a2e2d045269d0478c641bf5f87f1dd34c629b6fea283923caa93d60bf43d99b

data/.rake_tasks

@@ -0,0 +1,3 @@
+gem
+irb
+spec

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 ## CHANGELOG
 
+### 1.13.0
+
+- Unicode 18.0
+- Adapt augmented script set (and therefor mixed/single script detection) to Unicode 18 (-> add Hntl)
+
 ### 1.12.0
 
 - Unicode 17.0

data/Gemfile

@@ -3,5 +3,6 @@ source 'https://rubygems.org'
 gemspec
 
 gem 'minitest'
+gem 'minitest-mock'
 gem 'rake'
-gem 'irb' unless RUBY_ENGINE == "jruby"
+gem 'irb'

data/Gemfile.lock

@@ -1,24 +1,41 @@
 PATH
   remote: .
   specs:
-    unicode-scripts (1.12.0)
+    unicode-scripts (1.13.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    io-console (0.6.0)
-    irb (1.8.1)
-      rdoc
-      reline (>= 0.3.8)
-    minitest (5.20.0)
-    psych (5.1.0)
-      stringio
-    rake (13.0.6)
-    rdoc (6.5.0)
-      psych (>= 4.0.0)
-    reline (0.3.8)
+    drb (2.2.3)
+    erb (6.0.7)
+    io-console (0.9.4)
+    irb (1.18.0)
+      pp (>= 0.6.0)
+      prism (>= 1.3.0)
+      rdoc (>= 4.0.0)
+      reline (>= 0.4.2)
+    logger (1.7.0)
+    minitest (6.0.6)
+      drb (~> 2.0)
+      prism (~> 1.5)
+    minitest-mock (5.27.0)
+    pp (0.6.4)
+      prettyprint
+    prettyprint (0.2.0)
+    prism (1.9.0)
+    rake (13.4.2)
+    rbs (4.2.0)
+      logger
+      prism (>= 1.6.0)
+      tsort
+    rdoc (8.0.0)
+      erb
+      prism (>= 1.6.0)
+      rbs (>= 4.0.0)
+      tsort
+    reline (0.7.0)
       io-console (~> 0.5)
-    stringio (3.0.8)
+    tsort (0.2.0)
 
 PLATFORMS
   ruby
@@ -26,6 +43,7 @@ PLATFORMS
 DEPENDENCIES
   irb
   minitest
+  minitest-mock
   rake
   unicode-scripts!
 

data/MIT-LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2016-2025 Jan Lelis, https://janlelis.com
+Copyright (c) 2016-2026 Jan Lelis, https://janlelis.com
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

data/README.md

@@ -4,9 +4,7 @@ Retrieve all [Unicode script(s)](https://en.wikipedia.org/wiki/Script_%28Unicode
 
 Based on the *Script_Extension*, this library can also return the [augmented script set](https://www.unicode.org/reports/tr39/#def-augmented-script-set) to figure out if a string is **mixed-script** or **single-script**. Mixed scripts can be an indicator of suspicious user inputs.
 
-Unicode version: **17.0.0** (September 2025)
-
-Supported Rubies: **3.x** (might work: **2.x**)
+Unicode version: **18.0.0** (September 2026)
 
 ## Gemfile
 
@@ -128,5 +126,5 @@ See [Idiosyncratic Ruby: Proper Unicoding](https://idiosyncratic-ruby.com/41-pro
 
 ## MIT License
 
-- Copyright (C) 2016-2025 Jan Lelis <https://janlelis.com>. Released under the MIT license.
+- Copyright (C) 2016-2026 Jan Lelis <https://janlelis.com>. Released under the MIT license.
 - Unicode data: https://www.unicode.org/copyright.html#Exhibit1

data/lib/unicode/scripts/constants.rb

@@ -2,11 +2,11 @@
 
 module Unicode
   module Scripts
-    VERSION = "1.12.0"
-    UNICODE_VERSION = "17.0.0"
+    VERSION = "1.13.0"
+    UNICODE_VERSION = "18.0.0"
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/").freeze
     INDEX_FILENAME = (DATA_DIRECTORY + "/scripts.marshal.gz").freeze
 
-    AUGMENTED_SCRIPT_CODES = ["Hanb", "Jpan", "Kore"]
+    AUGMENTED_SCRIPT_CODES = ["Hanb", "Hntl",  "Jpan", "Kore"].freeze
   end
 end

data/lib/unicode/scripts.rb

@@ -62,7 +62,7 @@ module Unicode
       }
 
       if augmented.include? "Hani"
-        augmented |= ["Hanb", "Jpan", "Kore"]
+        augmented |= Unicode::Scripts::AUGMENTED_SCRIPT_CODES
       end
       if augmented.include?("Hira") || augmented.include?("Kana")
         augmented |= ["Jpan"]
@@ -73,6 +73,9 @@ module Unicode
       if augmented.include? "Bopo"
         augmented |= ["Hanb"]
       end
+      if augmented.include? "Latn"
+        augmented |= ["Hntl"]
+      end
       if augmented.include?("Zyyy") || augmented.include?("Zinh")
         augmented |= names(format: :short, augmented: :include )
       end

data/spec/unicode_scripts_spec.rb

@@ -1,4 +1,5 @@
 require_relative "../lib/unicode/scripts"
+require "minitest/mock"
 require "minitest/autorun"
 
 describe Unicode::Scripts do
@@ -138,7 +139,15 @@ describe Unicode::Scripts do
     it "will return all extended scripts that characters in the string belong to + augmented" do
       assert_equal ["Hira", "Jpan", "Kana"], Unicode::Scripts.augmented_scripts("ねガ")
     end
-    
+
+    it "add all Unicode::Scripts::AUGMENTED_SCRIPT_CODES for Han characters" do
+      assert_equal ["Hanb", "Hani", "Hntl", "Jpan", "Kore"], Unicode::Scripts.augmented_scripts("⺀")
+    end
+
+    it "add Hntl for Latin characters" do
+      assert_equal ["Hntl", "Latn"], Unicode::Scripts.augmented_scripts("A")
+    end
+   
     it "will replace Common with all scripts" do
       assert_equal \
         Unicode::Scripts.names(format: :short, augmented: :include),
@@ -183,11 +192,15 @@ describe Unicode::Scripts do
     end
 
     it "will return a list of all augmented script codes" do
-      assert_equal Unicode::Scripts.names(format: :short, augmented: :only), ["Hanb", "Jpan", "Kore"]
+      assert_equal Unicode::Scripts.names(format: :short, augmented: :only), ["Hanb", "Hntl", "Jpan", "Kore"]
     end
   end
 
   describe '[unicode versions]' do
+    it "works for scripts introduced in Unicode 18" do
+      assert_equal "Jurchen", Unicode::Scripts.script("\u{18E20}")
+    end
+
     it "works for scripts introduced in Unicode 17" do
       assert_equal "Tai_Yo", Unicode::Scripts.script("𞛀")
     end

metadata

@@ -1,16 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: unicode-scripts
 version: !ruby/object:Gem::Version
-  version: 1.12.0
+  version: 1.13.0
 platform: ruby
 authors:
 - Jan Lelis
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-09-09 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies: []
-description: "[Unicode 17.0.0] Retrieve the Unicode script(s) a string belongs to.
+description: "[Unicode 18.0.0] Retrieve the Unicode script(s) a string belongs to.
   Can also return the Script_Extension property which is defined as characters which
   are 'commonly used with more than one script, but with a limited number of scripts'. "
 email:
@@ -20,6 +19,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".rake_tasks"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - Gemfile
@@ -39,7 +39,6 @@ licenses:
 - MIT
 metadata:
   rubygems_mfa_required: 'true'
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -54,8 +53,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.21
-signing_key:
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Which script(s) does a Unicode string belong to?
 test_files: