unicode_script_detector 0.0.4 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d80a777771e5076bfb67e1b63ea3a0900f9ca53b16b0e90224608b60c06c78bc
-  data.tar.gz: 266e4ca3ad0728cacbd4a4f37819f271b22205a893f5750c14c862bda8d5cdc2
+  metadata.gz: 58ac1a16218a1a336bb9c2fa6c75c5519a69a6c846c1007ffd236d991f3ef223
+  data.tar.gz: 11c82345a0b3990737b1c1a85c97d6c7552644a10e0c1d9265a4a46e4a0a9ce3
 SHA512:
-  metadata.gz: a0d6741c40ae5adfde691ec742b1bc5440e2b45f265d448cda9b6c40978843404b05419e82ebad258ef40e752bcaffb26c985e625cb52025de7ae37b7aee505a
-  data.tar.gz: 2c81a22c0cb25ec024eb875f4da5a19891bff344acf7daaaa8a4155caf89e0ba77021d5b475b3b3f8e986eaf1b6be8bf8e20747a88afdbd0bfdd083d344c2680
+  metadata.gz: baad85a939325ce58dc96c132e103b81bf1c9cd0f4a3120675bb6db7ec81bad305759b40da55e8d868128baa3d5bbdf3e28d044ae6f735d0ebce5ed4f89bb190
+  data.tar.gz: cfc04d633c2bdbbb0810c505d1cb6d671045b4b0c3651584be63231cb9b722a413c65c59487dbf5953374646af7bdc953ec7e66c4b71c7c1ad069004c8d9dd46

data/README.md

@@ -20,23 +20,45 @@ $ gem install unicode_script_detector
 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>]
+[
+  #<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]
+UnicodeScriptDetector.contains? "Helб🔥", [: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]
+UnicodeScriptDetector.contains_only? "Helб🔥", [:Latin, :Cyrillic]
+```
+
+## Detect all the characters of a string, grouped by the script
+```ruby
+UnicodeScriptDetector.script_groups("Hel6б how are you?").each do |group|
+  puts "#{group.name}: #{group.text} (#{group.length} characters)"
+end
+
+#Output:
+
+Latin: Hel (3 characters)
+Digit: 6 (1 characters)
+Cyrillic: б (1 characters)
+Whitespace:   (1 characters)
+Latin: how (3 characters)
+Whitespace:   (1 characters)
+Latin: are (3 characters)
+Whitespace:   (1 characters)
+Latin: you (3 characters)
+Punctuation: ? (1 characters)
 ```
 
 ## Development
@@ -47,4 +69,4 @@ Run the tests with `bin/test`.
 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).
+This software is released under the [MIT license](LICENSE).

data/lib/unicode_script_detector/character.rb

@@ -15,5 +15,17 @@ module UnicodeScriptDetector
     def hiragana?
       @script === :Hiragana
     end
+
+    def punctuation?
+      @script === :Punctuation
+    end
+
+    def emoji?
+      @script === :Emoji
+    end
+
+    def digit?
+      @script === :Digit
+    end
   end
-end
+end

data/lib/unicode_script_detector/detector.rb

@@ -1,45 +1,65 @@
 module UnicodeScriptDetector
   class Detector
-    attr_reader :characters, :scripts
+    attr_reader :scripts
 
     def initialize(string)
       @string = string
-      @characters = []
-      @scripts = []
+      @char_scripts = []
+      @script_names = []
 
       detect_scripts
     end
 
     def scripts
-      @scripts.uniq
+      @char_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
+    def contains?(scripts)
+      return @char_scripts.include?(scripts) if scripts.is_a?(Symbol)
+      scripts.all? { |script| @char_scripts.include?(script) }
     end
 
-    def contains?(scripts)
-      return @scripts.include?(scripts) if scripts.is_a?(Symbol)
+    def contains_only?(scripts)
+      return @char_scripts.uniq == [scripts] if scripts.is_a?(Symbol)
+      @char_scripts.uniq.sort == scripts.uniq.sort
+    end
 
-      scripts.all? { |script| @scripts.include?(script) }
+    def script_groups
+      @string.chars
+        .zip(@char_scripts, @script_names)
+        .chunk { |_, script, _| script }
+        .map do |script, char_data| 
+          chars = char_data.map(&:first)
+          name = char_data.first[2]
+          ScriptGroup.new(script, chars, name)
+        end
     end
 
-    def contains_only?(scripts)
-      return @scripts.uniq == [scripts] if scripts.is_a?(Symbol)
+    def grouped_scripts_hash
+      script_groups.map { |group| [group.script, group.text] }.to_h
+    end
 
-      @scripts.uniq.sort == scripts.uniq.sort
+    def characters
+      @characters ||= @string.chars.zip(@char_scripts, @script_names).map do |char, script, name|
+        Character.new(char, script, name)
+      end
     end
+
+    private 
+      def detect_scripts
+        @string.chars.each do |char|
+          script_info = find_script_for_char(char)
+          @char_scripts << script_info[:script]
+          @script_names << script_info[:name]
+        end
+      end
+
+      def find_script_for_char(char)
+        Scripts::LIST.each do |script_data|
+          return script_data if char.match?(script_data[:regex])
+        end
+        { script: :Other, name: "Other" }
+      end
+
   end
-end
+end

data/lib/unicode_script_detector/script_group.rb

@@ -0,0 +1,20 @@
+module UnicodeScriptDetector
+  class ScriptGroup
+    attr_reader :script, :text, :name
+
+    def initialize(script, chars, name)
+      @script = script
+      @chars = chars
+      @text = chars.join
+      @name = name
+    end
+
+    def length
+      @chars.length
+    end
+
+    def characters
+      @characters ||= @chars.map { |char| Character.new(char, @script, @name) }
+    end
+  end
+end

data/lib/unicode_script_detector/scripts.rb

@@ -837,7 +837,12 @@ module UnicodeScriptDetector
       { 
         script: :Emoji, 
         name: "Emoji", 
-        regex: /\p{Emoji}/, 
+        regex: /\p{Emoji_Presentation}/, 
+      },
+      {
+        script: :Punctuation,
+        name: "Punctuation",
+        regex: /[[:punct:]]/
       },
       { 
         script: :Common, 

data/lib/unicode_script_detector/version.rb

@@ -1,3 +1,3 @@
 module UnicodeScriptDetector
-  VERSION = "0.0.4"
+  VERSION = "0.0.6"
 end

data/lib/unicode_script_detector.rb

@@ -9,6 +9,10 @@ module UnicodeScriptDetector
       UnicodeScriptDetector::Detector.new(string).characters
     end
 
+    def script_groups(string)
+      UnicodeScriptDetector::Detector.new(string).script_groups
+    end
+
     def contains?(string, scripts)
       UnicodeScriptDetector::Detector.new(string).contains?(scripts)
     end
@@ -17,4 +21,4 @@ module UnicodeScriptDetector
       UnicodeScriptDetector::Detector.new(string).contains_only?(scripts)
     end
   end
-end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode_script_detector
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.6
 platform: ruby
 authors:
 - David Arendsen
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-12-04 00:00:00.000000000 Z
+date: 2026-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: zeitwerk
@@ -55,6 +55,7 @@ files:
 - lib/unicode_script_detector.rb
 - lib/unicode_script_detector/character.rb
 - lib/unicode_script_detector/detector.rb
+- lib/unicode_script_detector/script_group.rb
 - lib/unicode_script_detector/scripts.rb
 - lib/unicode_script_detector/version.rb
 homepage: https://github.com/davidarendsen/unicode_script_detector
@@ -79,7 +80,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.23
+rubygems_version: 3.5.11
 signing_key:
 specification_version: 4
 summary: Unicode Script Detector