unicode-scripts 1.3.0 → 1.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4553aef6ef38f7ab727daa55ee8a3baf29848f5599f6e116f3e192bb12fecd72
-  data.tar.gz: 431a7deb7daab9a0651d9223cedeb0d2f4d32bd5e8e2417ca095e32251ddc0d3
+  metadata.gz: c907fd10ee383e77217efda8304b1e6182aa59b2dd5f38eb4f6399fed987e1cc
+  data.tar.gz: e51d4c2a61b4c59c6ac5c0ad8cb36ae455e81d4132e6ebc8b1dbf6b1a8735591
 SHA512:
-  metadata.gz: bc8d031a9f5528608dff602cb383907c3ba26c7f54ac6e9e183b3d7dd112d8697d8e8d937531015d5a8030bbefdc4027ccbcaf0a253f73784db5795a8de3b45d
-  data.tar.gz: df002e70c93bdb45c9c0bf8467d497a16ffa0e840539762191eea9959daebefc36e438d53555421bb936ccc587ca4bc0bce8ea683f6c48fbb7b65686ff3fcd73
+  metadata.gz: d01c9f77598090ad2026476eee867cdf4564fdc4cb666e67a6adb99b8ff1fb1ad9345ba3133eff6a53a23ee4ed52a1c1a1503799bf42abe52748f1f10e8c6a60
+  data.tar.gz: 7663f839ebaf0375276356e8815f117180559fbfc959b8c28afadc35999da82a7ca56d67b55a8ef2c0e5263ac6de354e1edee60879e7ec3f8017e40ee6be7d3d

data/CHANGELOG.md

@@ -1,5 +1,21 @@
 ## CHANGELOG
 
+### 1.7.0
+
+- Unicode 14.0
+
+### 1.6.0
+
+* Unicode 13
+
+### 1.5.0
+
+* Unicode 12.1
+
+### 1.4.0
+
+* Unicode 12
+
 ### 1.3.0
 
 * Unicode 11

data/Gemfile

@@ -4,3 +4,4 @@ gemspec
 
 gem 'minitest'
 gem 'rake'
+gem 'irb' unless RUBY_ENGINE == "jruby"

data/Gemfile.lock

@@ -1,11 +1,12 @@
 PATH
   remote: .
   specs:
-    unicode-scripts (1.3.0)
+    unicode-scripts (1.5.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    irb (1.0.0)
     minitest (5.9.0)
     rake (12.0.0)
 
@@ -13,9 +14,10 @@ PLATFORMS
   ruby
 
 DEPENDENCIES
+  irb
   minitest
   rake
   unicode-scripts!
 
 BUNDLED WITH
-   1.16.1
+   1.17.2

data/MIT-LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2016-2018 Jan Lelis, mail@janlelis.de
+Copyright (c) 2016-2021 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

@@ -1,12 +1,12 @@
-# Unicode::Scripts [![[version]](https://badge.fury.io/rb/unicode-scripts.svg)](http://badge.fury.io/rb/unicode-scripts)  [![[travis]](https://travis-ci.org/janlelis/unicode-scripts.png)](https://travis-ci.org/janlelis/unicode-scripts)
+# Unicode::Scripts [![[version]](https://badge.fury.io/rb/unicode-scripts.svg)](https://badge.fury.io/rb/unicode-scripts)  [![[ci]](https://github.com/janlelis/unicode-scripts/workflows/Test/badge.svg)](https://github.com/janlelis/unicode-scripts/actions?query=workflow%3ATest)
 
 Retrieve the [Unicode script(s)](https://en.wikipedia.org/wiki/Script_%28Unicode%29) 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".
 
-Unicode version: **11.0.0**
+Unicode version: **14.0.0** (September 2021)
 
-Supported Rubies: **2.5**, **2.4**, **2.3**
+Supported Rubies: **3.0**, **2.7**
 
-Old Rubies that might still work: **2.2**, **2.1**, **2.0**
+Old Rubies that might still work: **2.6**, **2.5**, **2.4**, **2.3**, **2.2**, **2.1**, **2.0**
 
 ## Gemfile
 
@@ -29,21 +29,22 @@ Unicode::Scripts.script("ᴦ") # => "Greek"
 
 # Script_Extension property
 Unicode::Scripts.script_extensions("॥")
-# => ["Bengali", "Devanagari", "Dogra", "Grantha", "Gujarati",
-"Gunjala_Gondi", "Gurmukhi", "Kannada", "Khudawadi", "Limbu",
-"Mahajani", "Malayalam", "Oriya", "Sinhala", "Syloti_Nagri",
-"Takri", "Tamil", "Telugu", "Tirhuta"]
+# => ["Bengali", "Devanagari", "Dogra", "Grantha", "Gujarati","Gunjala_Gondi", "Gurmukhi", "Kannada",
+"Khudawadi", "Limbu", "Mahajani", "Malayalam", "Masaram_Gondi", "Nandinagari", "Oriya", "Sinhala",
+"Syloti_Nagri", "Takri", "Tamil", "Telugu", "Tirhuta"]
 ```
 
 ## Hints
 ### Regex Matching
 
-If you have a string and want to match a substring/character from a specific Unicode script, you actually won't need this gem. Instead, you can use the [Regexp Unicode Property Syntax `\p{}`](http://ruby-doc.org/core-2.3.0/Regexp.html#class-Regexp-label-Character+Properties):
+If you have a string and want to match a substring/character from a specific Unicode script, you actually won't need this gem. Instead, you can use the [Regexp Unicode Property Syntax `\p{}`](https://ruby-doc.org/core/Regexp.html#class-Regexp-label-Character+Properties):
 
 ```ruby
 "Coptic letter: ⲁ".scan(/\p{Coptic}/) # => ["ⲁ"]
 ```
 
+See [Idiosyncratic Ruby: Proper Unicoding](https://idiosyncratic-ruby.com/41-proper-unicoding.html) for more info.
+
 ### Script Names
 
 You can extract all script names from the gem like this:
@@ -77,17 +78,21 @@ Caucasian_Albanian
 Chakma
 Cham
 Cherokee
+Chorasmian
 Common
 Coptic
 Cuneiform
 Cypriot
+Cypro_Minoan
 Cyrillic
 Deseret
 Devanagari
+Dives_Akuru
 Dogra
 Duployan
 Egyptian_Hieroglyphs
 Elbasan
+Elymaic
 Ethiopic
 Georgian
 Glagolitic
@@ -115,6 +120,7 @@ Katakana
 Katakana_Or_Hiragana
 Kayah_Li
 Kharoshthi
+Khitan_Small_Script
 Khmer
 Khojki
 Khudawadi
@@ -146,10 +152,12 @@ Mro
 Multani
 Myanmar
 Nabataean
+Nandinagari
 New_Tai_Lue
 Newa
 Nko
 Nushu
+Nyiakeng_Puachue_Hmong
 Ogham
 Ol_Chiki
 Old_Hungarian
@@ -160,6 +168,7 @@ Old_Persian
 Old_Sogdian
 Old_South_Arabian
 Old_Turkic
+Old_Uyghur
 Oriya
 Osage
 Osmanya
@@ -191,6 +200,7 @@ Tai_Tham
 Tai_Viet
 Takri
 Tamil
+Tangsa
 Tangut
 Telugu
 Thaana
@@ -198,10 +208,14 @@ Thai
 Tibetan
 Tifinagh
 Tirhuta
+Toto
 Ugaritic
 Unknown
 Vai
+Vithkuqi
+Wancho
 Warang_Citi
+Yezidi
 Yi
 Zanabazar_Square
 ```
@@ -239,15 +253,19 @@ Cans
 Cari
 Cham
 Cher
+Chrs
 Copt
+Cpmn
 Cprt
 Cyrl
 Deva
+Diak
 Dogr
 Dsrt
 Dupl
 Egyp
 Elba
+Elym
 Ethi
 Geor
 Glag
@@ -266,6 +284,7 @@ Hebr
 Hira
 Hluw
 Hmng
+Hmnp
 Hrkt
 Hung
 Ital
@@ -275,6 +294,7 @@ Kana
 Khar
 Khmr
 Khoj
+Kits
 Knda
 Kthi
 Lana
@@ -303,6 +323,7 @@ Mroo
 Mtei
 Mult
 Mymr
+Nand
 Narb
 Nbat
 Newa
@@ -314,6 +335,7 @@ Orkh
 Orya
 Osge
 Osma
+Ougr
 Palm
 Pauc
 Perm
@@ -358,11 +380,16 @@ Thaa
 Thai
 Tibt
 Tirh
+Tnsa
+Toto
 Ugar
 Vaii
+Vith
 Wara
+Wcho
 Xpeo
 Xsux
+Yezi
 Yiii
 Zanb
 Zinh
@@ -374,5 +401,5 @@ See [unicode-x](https://github.com/janlelis/unicode-x) for more Unicode related
 
 ## MIT License
 
-- Copyright (C) 2016-2018 Jan Lelis <http://janlelis.com>. Released under the MIT license.
-- Unicode data: http://www.unicode.org/copyright.html#Exhibit1
+- Copyright (C) 2016-2021 Jan Lelis <https://janlelis.com>. Released under the MIT license.
+- Unicode data: https://www.unicode.org/copyright.html#Exhibit1

data/Rakefile

@@ -32,6 +32,10 @@ end
 
 desc "#{gemspec.name} | Spec"
 task :spec do
-  sh "for file in spec/*.rb; do ruby $file; done"
+  if RbConfig::CONFIG['host_os'] =~ /mswin|mingw/
+    sh "for %f in (spec/\*.rb) do ruby spec/%f"
+  else
+    sh "for file in spec/*.rb; do ruby $file; done"
+  end
 end
 task default: :spec

data/lib/unicode/scripts/constants.rb

@@ -1,9 +1,10 @@
+# frozen_string_literal: true
+
 module Unicode
   module Scripts
-    VERSION = "1.3.0".freeze
-    UNICODE_VERSION = "11.0.0".freeze
-    DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + '/../../../data/').freeze
-    INDEX_FILENAME = (DATA_DIRECTORY + '/scripts.marshal.gz').freeze
+    VERSION = "1.7.0"
+    UNICODE_VERSION = "14.0.0"
+    DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/").freeze
+    INDEX_FILENAME = (DATA_DIRECTORY + "/scripts.marshal.gz").freeze
   end
 end
-

data/spec/unicode_scripts_spec.rb

@@ -18,8 +18,13 @@ describe Unicode::Scripts do
 
     it "will call .script for every character" do
       mocked_method = MiniTest::Mock.new
-      mocked_method.expect :call, "first script",  ["С", {}]
-      mocked_method.expect :call, "second script", ["A", {}]
+      if RUBY_VERSION >= "2.7"
+        mocked_method.expect :call, "first script",  ["С"]
+        mocked_method.expect :call, "second script", ["A"]
+      else
+        mocked_method.expect :call, "first script",  ["С", {}]
+        mocked_method.expect :call, "second script", ["A", {}]
+      end
       Unicode::Scripts.stub :script, mocked_method do
         Unicode::Scripts.of("СA")
       end
@@ -51,14 +56,18 @@ describe Unicode::Scripts do
       assert_equal [
         "Bengali",
         "Devanagari",
+        "Dogra",
         "Grantha",
         "Gujarati",
+        "Gunjala_Gondi",
         "Gurmukhi",
         "Kannada",
         "Khudawadi",
         "Limbu",
         "Mahajani",
         "Malayalam",
+        "Masaram_Gondi",
+        "Nandinagari",
         "Oriya",
         "Sinhala",
         "Syloti_Nagri",
@@ -73,6 +82,9 @@ describe Unicode::Scripts do
       assert_equal [
         "Beng",
         "Deva",
+        "Dogr",
+        "Gong",
+        "Gonm",
         "Gran",
         "Gujr",
         "Guru",
@@ -80,6 +92,7 @@ describe Unicode::Scripts do
         "Limb",
         "Mahj",
         "Mlym",
+        "Nand",
         "Orya",
         "Sind",
         "Sinh",

data/unicode-scripts.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |gem|
   gem.summary       = "Which script(s) does a Unicode string belong to?"
   gem.description   = "[Unicode #{Unicode::Scripts::UNICODE_VERSION}] 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'. "
   gem.authors       = ["Jan Lelis"]
-  gem.email         = ["mail@janlelis.de"]
+  gem.email         = ["hi@ruby.consulting"]
   gem.homepage      = "https://github.com/janlelis/unicode-scripts"
   gem.license       = "MIT"
 
@@ -17,5 +17,5 @@ Gem::Specification.new do |gem|
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
   gem.require_paths = ["lib"]
 
-  gem.required_ruby_version = "~> 2.0"
+  gem.required_ruby_version = ">= 2.0"
 end

metadata

@@ -1,26 +1,25 @@
 --- !ruby/object:Gem::Specification
 name: unicode-scripts
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.7.0
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-06-05 00:00:00.000000000 Z
+date: 2021-09-15 00:00:00.000000000 Z
 dependencies: []
-description: "[Unicode 11.0.0] Retrieve the Unicode script(s) a string belongs to.
+description: "[Unicode 14.0.0] 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:
-- mail@janlelis.de
+- hi@ruby.consulting
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
-- ".travis.yml"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - Gemfile
@@ -45,7 +44,7 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - "~>"
+  - - ">="
     - !ruby/object:Gem::Version
       version: '2.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
@@ -54,8 +53,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.2.3
 signing_key: 
 specification_version: 4
 summary: Which script(s) does a Unicode string belong to?

data/.travis.yml

@@ -1,22 +0,0 @@
-sudo: false
-language: ruby
-
-script: bundle exec ruby spec/unicode_scripts_spec.rb
-
-rvm:
-- ruby-head
-- 2.5.1
-- 2.4.4
-- 2.3.7
-- 2.2
-- 2.1
-- 2.0
-- jruby-head
-- jruby-9.1.16.0
-
-matrix:
-  allow_failures:
-    - rvm: 2.2
-    - rvm: 2.1
-    - rvm: 2.0
-    - rvm: jruby-head