unicode_script_detector 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 642b20bc8d5ac4e9235bae7468d7b78eba92ff63522473ae4a17ee78bba1b82c
+  data.tar.gz: dc8c392cf8301c17f16718ff07f6ce3b3ba6e940126b3b1e23917340b61c7819
+SHA512:
+  metadata.gz: '0478c770eec54d36171fc251a6b061b6babddd222db0abc62b858c388213bf74711f44ebc6e2a3351509fcdc8c44addde5fcd29cd683dabea53c38d081499acb'
+  data.tar.gz: 45fac137742fc05c44514745018483c930fccd37839c96cc537bed1009b59a49287d1df0b2b8379ef59e5155bbb79b4cf2accc972c911dd3c75cc09937271072

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 David Arendsen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,50 @@
+# Unicode Script Detector
+
+Detect all Unicode scripts in a text.
+
+## Installation
+
+Add this line to your application's Gemfile:
+```ruby
+gem "unicode_script_detector"
+```
+
+Or install it globally:
+
+```bash
+$ gem install unicode_script_detector
+```
+
+## Detect all the characters of a string
+```ruby
+UnicodeScriptDetector.detect_characters "Hel6б"
+
+#Output:
+[#<UnicodeScriptDetector::Character:0x00007768fefdead8 @char="H", @name="Latin", @script=:Latin>,
+ #<UnicodeScriptDetector::Character:0x00007768fefdea10 @char="e", @name="Latin", @script=:Latin>,
+ #<UnicodeScriptDetector::Character:0x00007768fefde970 @char="l", @name="Latin", @script=:Latin>,
+ #<UnicodeScriptDetector::Character:0x00007768fefde8d0 @char="6", @name="Digit", @script=:Digit>,
+ #<UnicodeScriptDetector::Character:0x00007768fefde830 @char="б", @name="Cyrillic", @script=:Cyrillic>]
+```
+
+## Detect if a script contains certain scripts
+```ruby
+# This will return true because it contains Latin and Cyrillic
+UnicodeScriptDetector.contains? "Hellб🔥", [:Latin, :Cyrillic]
+```
+
+## Detect if a script contains only certain scripts
+```ruby
+# This will return false because it contains an Emoji as well
+UnicodeScriptDetector.contains_only? "Hellб🔥", [:Latin, :Cyrillic]
+```
+
+## Development
+Start the console with `bin/console`.
+Run the tests with `bin/test`.
+
+## Contributing
+You're welcome to contribute to this project. See https://github.com/davidarendsen/unicode_script_detector.
+
+## License
+This software is released under the [MIT license](LICENSE).

data/lib/unicode_script_detector/character.rb

@@ -0,0 +1,19 @@
+module UnicodeScriptDetector
+  class Character
+    attr_reader :char, :script, :name
+
+    def initialize(char, script, name)
+      @char = char
+      @script = script
+      @name = name
+    end
+
+    def latin?
+      @script === :Latin
+    end
+
+    def hiragana?
+      @script === :Hiragana
+    end
+  end
+end

data/lib/unicode_script_detector/detector.rb

@@ -0,0 +1,45 @@
+module UnicodeScriptDetector
+  class Detector
+    attr_reader :characters, :scripts
+
+    def initialize(string)
+      @string = string
+      @characters = []
+      @scripts = []
+
+      detect_scripts
+    end
+
+    def scripts
+      @scripts.uniq
+    end
+
+    def detect_scripts
+      @string.chars.each_with_index do |char, index|
+        detected = false
+        Scripts::LIST.each_with_index do |script_data, index|
+          if char.match?(script_data[:regex])
+            @characters << Character.new(char, script_data[:script], script_data[:name])
+            @scripts << script_data[:script]
+            detected = true
+            break
+          end
+        end
+        @characters << Character.new(char, :Other, "Other") unless detected
+        @scripts << :Other unless detected
+      end
+    end
+
+    def contains?(scripts)
+      return @scripts.include?(scripts) if scripts.is_a?(Symbol)
+
+      scripts.all? { |script| @scripts.include?(script) }
+    end
+
+    def contains_only?(scripts)
+      return @scripts.uniq == [scripts] if scripts.is_a?(Symbol)
+
+      @scripts.uniq.sort == scripts.uniq.sort
+    end
+  end
+end

data/lib/unicode_script_detector/scripts.rb

@@ -0,0 +1,516 @@
+module UnicodeScriptDetector
+  class Scripts
+    LIST = [
+      {
+        script: :Digit,
+        name: "Digit",
+        regex: /\d/,
+      },
+      {
+        script: :Whitespace,
+        name: "Whitespace",
+        regex: /\s/,
+      },
+      { 
+        script: :Arabic, 
+        name: "Arabic", 
+        regex: /\p{Arabic}/, 
+      },
+      { 
+        script: :Armenian, 
+        name: "Armenian", 
+        regex: /\p{Armenian}/, 
+      },
+      { 
+        script: :Balinese, 
+        name: "Balinese", 
+        regex: /\p{Balinese}/, 
+      },
+      { 
+        script: :Bamum, 
+        name: "Bamum", 
+        regex: /\p{Bamum}/, 
+      },
+      { 
+        script: :Batak, 
+        name: "Batak", 
+        regex: /\p{Batak}/, 
+      },
+      { 
+        script: :Bengali, 
+        name: "Bengali", 
+        regex: /\p{Bengali}/, 
+      },
+      { 
+        script: :Bopomofo, 
+        name: "Bopomofo", 
+        regex: /\p{Bopomofo}/, 
+      },
+      { 
+        script: :Brahmi, 
+        name: "Brahmi", 
+        regex: /\p{Brahmi}/, 
+      },
+      { 
+        script: :Braille, 
+        name: "Braille", 
+        regex: /\p{Braille}/, 
+      },
+      { 
+        script: :Buginese, 
+        name: "Buginese", 
+        regex: /\p{Buginese}/, 
+      },
+      { 
+        script: :Buhid, 
+        name: "Buhid", 
+        regex: /\p{Buhid}/, 
+      },
+      { 
+        script: :Canadian_Aboriginal, 
+        name: "Canadian_Aboriginal", 
+        regex: /\p{Canadian_Aboriginal}/, 
+      },
+      { 
+        script: :Carian, 
+        name: "Carian", 
+        regex: /\p{Carian}/, 
+      },
+      { 
+        script: :Chakma, 
+        name: "Chakma", 
+        regex: /\p{Chakma}/, 
+      },
+      { 
+        script: :Cham, 
+        name: "Cham", 
+        regex: /\p{Cham}/, 
+      },
+      { 
+        script: :Cherokee, 
+        name: "Cherokee", 
+        regex: /\p{Cherokee}/, 
+      },
+      { 
+        script: :Coptic, 
+        name: "Coptic", 
+        regex: /\p{Coptic}/, 
+      },
+      { 
+        script: :Cuneiform, 
+        name: "Cuneiform", 
+        regex: /\p{Cuneiform}/, 
+      },
+      { 
+        script: :Cypriot, 
+        name: "Cypriot", 
+        regex: /\p{Cypriot}/, 
+      },
+      { 
+        script: :Cyrillic, 
+        name: "Cyrillic", 
+        regex: /\p{Cyrillic}/, 
+      },
+      { 
+        script: :Deseret, 
+        name: "Deseret", 
+        regex: /\p{Deseret}/, 
+      },
+      { 
+        script: :Devanagari, 
+        name: "Devanagari", 
+        regex: /\p{Devanagari}/, 
+      },
+      { 
+        script: :Egyptian_Hieroglyphs, 
+        name: "Egyptian_Hieroglyphs", 
+        regex: /\p{Egyptian_Hieroglyphs}/, 
+      },
+      { 
+        script: :Ethiopic, 
+        name: "Ethiopic", 
+        regex: /\p{Ethiopic}/, 
+      },
+      { 
+        script: :Georgian, 
+        name: "Georgian", 
+        regex: /\p{Georgian}/, 
+      },
+      { 
+        script: :Glagolitic, 
+        name: "Glagolitic", 
+        regex: /\p{Glagolitic}/, 
+      },
+      { 
+        script: :Gothic, 
+        name: "Gothic", 
+        regex: /\p{Gothic}/, 
+      },
+      { 
+        script: :Greek, 
+        name: "Greek", 
+        regex: /\p{Greek}/, 
+      },
+      { 
+        script: :Gujarati, 
+        name: "Gujarati", 
+        regex: /\p{Gujarati}/, 
+      },
+      { 
+        script: :Gurmukhi, 
+        name: "Gurmukhi", 
+        regex: /\p{Gurmukhi}/, 
+      },
+      { 
+        script: :Han, 
+        name: "Han", 
+        regex: /\p{Han}/, 
+      },
+      { 
+        script: :Hangul, 
+        name: "Hangul", 
+        regex: /\p{Hangul}/, 
+      },
+      { 
+        script: :Hanunoo, 
+        name: "Hanunoo", 
+        regex: /\p{Hanunoo}/, 
+      },
+      { 
+        script: :Hebrew, 
+        name: "Hebrew", 
+        regex: /\p{Hebrew}/, 
+      },
+      { 
+        script: :Hiragana, 
+        name: "Hiragana", 
+        regex: /\p{Hiragana}/, 
+      },
+      { 
+        script: :Imperial_Aramaic, 
+        name: "Imperial_Aramaic", 
+        regex: /\p{Imperial_Aramaic}/, 
+      },
+      { 
+        script: :Inherited, 
+        name: "Inherited", 
+        regex: /\p{Inherited}/, 
+      },
+      { 
+        script: :Inscriptional_Pahlavi, 
+        name: "Inscriptional_Pahlavi", 
+        regex: /\p{Inscriptional_Pahlavi}/, 
+      },
+      { 
+        script: :Inscriptional_Parthian, 
+        name: "Inscriptional_Parthian", 
+        regex: /\p{Inscriptional_Parthian}/, 
+      },
+      { 
+        script: :Javanese, 
+        name: "Javanese", 
+        regex: /\p{Javanese}/, 
+      },
+      { 
+        script: :Kaithi, 
+        name: "Kaithi", 
+        regex: /\p{Kaithi}/, 
+      },
+      { 
+        script: :Kannada, 
+        name: "Kannada", 
+        regex: /\p{Kannada}/, 
+      },
+      { 
+        script: :Katakana, 
+        name: "Katakana", 
+        regex: /\p{Katakana}/, 
+      },
+      { 
+        script: :Kayah_Li, 
+        name: "Kayah_Li", 
+        regex: /\p{Kayah_Li}/, 
+      },
+      { 
+        script: :Kharoshthi, 
+        name: "Kharoshthi", 
+        regex: /\p{Kharoshthi}/, 
+      },
+      { 
+        script: :Khmer, 
+        name: "Khmer", 
+        regex: /\p{Khmer}/, 
+      },
+      { 
+        script: :Lao, 
+        name: "Lao", 
+        regex: /\p{Lao}/, 
+      },
+      { 
+        script: :Latin, 
+        name: "Latin", 
+        regex: /\p{Latin}/, 
+      },
+      { 
+        script: :Lepcha, 
+        name: "Lepcha", 
+        regex: /\p{Lepcha}/, 
+      },
+      { 
+        script: :Limbu, 
+        name: "Limbu", 
+        regex: /\p{Limbu}/, 
+      },
+      { 
+        script: :Linear_B, 
+        name: "Linear_B", 
+        regex: /\p{Linear_B}/, 
+      },
+      { 
+        script: :Lycian, 
+        name: "Lycian", 
+        regex: /\p{Lycian}/, 
+      },
+      { 
+        script: :Lydian, 
+        name: "Lydian", 
+        regex: /\p{Lydian}/, 
+      },
+      { 
+        script: :Malayalam, 
+        name: "Malayalam", 
+        regex: /\p{Malayalam}/, 
+      },
+      { 
+        script: :Mandaic, 
+        name: "Mandaic", 
+        regex: /\p{Mandaic}/, 
+      },
+      { 
+        script: :Meetei_Mayek, 
+        name: "Meetei_Mayek", 
+        regex: /\p{Meetei_Mayek}/, 
+      },
+      { 
+        script: :Meroitic_Cursive, 
+        name: "Meroitic_Cursive", 
+        regex: /\p{Meroitic_Cursive}/, 
+      },
+      { 
+        script: :Meroitic_Hieroglyphs, 
+        name: "Meroitic_Hieroglyphs", 
+        regex: /\p{Meroitic_Hieroglyphs}/, 
+      },
+      { 
+        script: :Miao, 
+        name: "Miao", 
+        regex: /\p{Miao}/, 
+      },
+      { 
+        script: :Mongolian, 
+        name: "Mongolian", 
+        regex: /\p{Mongolian}/, 
+      },
+      { 
+        script: :Myanmar, 
+        name: "Myanmar", 
+        regex: /\p{Myanmar}/, 
+      },
+      { 
+        script: :New_Tai_Lue, 
+        name: "New_Tai_Lue", 
+        regex: /\p{New_Tai_Lue}/, 
+      },
+      { 
+        script: :Nko, 
+        name: "Nko", 
+        regex: /\p{Nko}/, 
+      },
+      { 
+        script: :Ogham, 
+        name: "Ogham", 
+        regex: /\p{Ogham}/, 
+      },
+      { 
+        script: :Ol_Chiki, 
+        name: "Ol_Chiki", 
+        regex: /\p{Ol_Chiki}/, 
+      },
+      { 
+        script: :Old_Italic, 
+        name: "Old_Italic", 
+        regex: /\p{Old_Italic}/, 
+      },
+      { 
+        script: :Old_Persian, 
+        name: "Old_Persian", 
+        regex: /\p{Old_Persian}/, 
+      },
+      { 
+        script: :Old_South_Arabian, 
+        name: "Old_South_Arabian", 
+        regex: /\p{Old_South_Arabian}/, 
+      },
+      { 
+        script: :Old_Turkic, 
+        name: "Old_Turkic", 
+        regex: /\p{Old_Turkic}/, 
+      },
+      { 
+        script: :Oriya, 
+        name: "Oriya", 
+        regex: /\p{Oriya}/, 
+      },
+      { 
+        script: :Osmanya, 
+        name: "Osmanya", 
+        regex: /\p{Osmanya}/, 
+      },
+      { 
+        script: :Phags_Pa, 
+        name: "Phags_Pa", 
+        regex: /\p{Phags_Pa}/, 
+      },
+      { 
+        script: :Phoenician, 
+        name: "Phoenician", 
+        regex: /\p{Phoenician}/, 
+      },
+      { 
+        script: :Rejang, 
+        name: "Rejang", 
+        regex: /\p{Rejang}/, 
+      },
+      { 
+        script: :Runic, 
+        name: "Runic", 
+        regex: /\p{Runic}/, 
+      },
+      { 
+        script: :Saurashtra, 
+        name: "Saurashtra", 
+        regex: /\p{Saurashtra}/, 
+      },
+      { 
+        script: :Sharada, 
+        name: "Sharada", 
+        regex: /\p{Sharada}/, 
+      },
+      { 
+        script: :Shavian, 
+        name: "Shavian", 
+        regex: /\p{Shavian}/, 
+      },
+      { 
+        script: :Sinhala, 
+        name: "Sinhala", 
+        regex: /\p{Sinhala}/, 
+      },
+      { 
+        script: :Sora_Sompeng, 
+        name: "Sora_Sompeng", 
+        regex: /\p{Sora_Sompeng}/, 
+      },
+      { 
+        script: :Sundanese, 
+        name: "Sundanese", 
+        regex: /\p{Sundanese}/, 
+      },
+      { 
+        script: :Syloti_Nagri, 
+        name: "Syloti_Nagri", 
+        regex: /\p{Syloti_Nagri}/, 
+      },
+      { 
+        script: :Syriac, 
+        name: "Syriac", 
+        regex: /\p{Syriac}/, 
+      },
+      { 
+        script: :Tagalog, 
+        name: "Tagalog", 
+        regex: /\p{Tagalog}/, 
+      },
+      { 
+        script: :Tagbanwa, 
+        name: "Tagbanwa", 
+        regex: /\p{Tagbanwa}/, 
+      },
+      { 
+        script: :Tai_Le, 
+        name: "Tai_Le", 
+        regex: /\p{Tai_Le}/, 
+      },
+      { 
+        script: :Tai_Tham, 
+        name: "Tai_Tham", 
+        regex: /\p{Tai_Tham}/, 
+      },
+      { 
+        script: :Tai_Viet, 
+        name: "Tai_Viet", 
+        regex: /\p{Tai_Viet}/, 
+      },
+      { 
+        script: :Takri, 
+        name: "Takri", 
+        regex: /\p{Takri}/, 
+      },
+      { 
+        script: :Tamil, 
+        name: "Tamil", 
+        regex: /\p{Tamil}/, 
+      },
+      { 
+        script: :Telugu, 
+        name: "Telugu", 
+        regex: /\p{Telugu}/, 
+      },
+      { 
+        script: :Thaana, 
+        name: "Thaana", 
+        regex: /\p{Thaana}/, 
+      },
+      { 
+        script: :Thai, 
+        name: "Thai", 
+        regex: /\p{Thai}/, 
+      },
+      { 
+        script: :Tibetan, 
+        name: "Tibetan", 
+        regex: /\p{Tibetan}/, 
+      },
+      { 
+        script: :Tifinagh, 
+        name: "Tifinagh", 
+        regex: /\p{Tifinagh}/, 
+      },
+      { 
+        script: :Ugaritic, 
+        name: "Ugaritic", 
+        regex: /\p{Ugaritic}/, 
+      },
+      { 
+        script: :Vai, 
+        name: "Vai", 
+        regex: /\p{Vai}/, 
+      },
+      { 
+        script: :Yi, 
+        name: "Yi", 
+        regex: /\p{Yi}/, 
+      },
+      {
+        script: :Emoji,
+        name: "Emoji",
+        regex: /\p{Emoji}/,
+      },
+      { 
+        script: :Common, 
+        name: "Common", 
+        regex: /\p{Common}/, 
+      },
+    ]
+  end
+end

data/lib/unicode_script_detector/version.rb

@@ -0,0 +1,3 @@
+module UnicodeScriptDetector
+  VERSION = "0.0.1"
+end

data/lib/unicode_script_detector.rb

@@ -0,0 +1,20 @@
+require "zeitwerk"
+
+loader = Zeitwerk::Loader.for_gem
+loader.setup
+
+module UnicodeScriptDetector
+  class << self
+    def detect_characters(string)
+      UnicodeScriptDetector::Detector.new(string).characters
+    end
+
+    def contains?(string, scripts)
+      UnicodeScriptDetector::Detector.new(string).contains?(scripts)
+    end
+
+    def contains_only?(string, scripts)
+      UnicodeScriptDetector::Detector.new(string).contains_only?(scripts)
+    end
+  end
+end

metadata

@@ -0,0 +1,83 @@
+--- !ruby/object:Gem::Specification
+name: unicode_script_detector
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- David Arendsen
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2024-12-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: zeitwerk
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.5'
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '7.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 7.2.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '7.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 7.2.2
+description: Detect the unicode script per character
+email: davidarendsen@hey.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE
+- README.md
+- lib/unicode_script_detector.rb
+- lib/unicode_script_detector/character.rb
+- lib/unicode_script_detector/detector.rb
+- lib/unicode_script_detector/scripts.rb
+- lib/unicode_script_detector/version.rb
+homepage: https://rubygems.org/gems/unicode_script_detector
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.1.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.11
+signing_key:
+specification_version: 4
+summary: Unicode Script Detector
+test_files: []