unicode_script_detector 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4795cdb246ac34ccb0ee5183ff0e704d25e4e67410acee321f36f4446dd28356
-  data.tar.gz: 0c7b9c4c835718f2fc7509225204e38c0a7148949c5745f1448b299c27e0e88d
+  metadata.gz: 58ac1a16218a1a336bb9c2fa6c75c5519a69a6c846c1007ffd236d991f3ef223
+  data.tar.gz: 11c82345a0b3990737b1c1a85c97d6c7552644a10e0c1d9265a4a46e4a0a9ce3
 SHA512:
-  metadata.gz: 5da7422c57295f4ac3dee3ac9ccfaa99b5586418de956a88876035541da023e9fa4afe609a4aa79d4c3a1a5f9b1ffe64370984657844c06fc6a575578beb5ee2
-  data.tar.gz: aa9fecf48386b6eb5a0074cbbec8819af80153c6111e042debd9e9c312145bc11a936b3003a406370a28e8a27a48b2bd0409c0cf043b26fe465f4c58ee9669e2
+  metadata.gz: baad85a939325ce58dc96c132e103b81bf1c9cd0f4a3120675bb6db7ec81bad305759b40da55e8d868128baa3d5bbdf3e28d044ae6f735d0ebce5ed4f89bb190
+  data.tar.gz: cfc04d633c2bdbbb0810c505d1cb6d671045b4b0c3651584be63231cb9b722a413c65c59487dbf5953374646af7bdc953ec7e66c4b71c7c1ad069004c8d9dd46

data/lib/unicode_script_detector/detector.rb

@@ -1,55 +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
-    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
+      @char_scripts.uniq
     end
 
     def contains?(scripts)
-      return @scripts.include?(scripts) if scripts.is_a?(Symbol)
-
-      scripts.all? { |script| @scripts.include?(script) }
+      return @char_scripts.include?(scripts) if scripts.is_a?(Symbol)
+      scripts.all? { |script| @char_scripts.include?(script) }
     end
 
     def contains_only?(scripts)
-      return @scripts.uniq == [scripts] if scripts.is_a?(Symbol)
-
-      @scripts.uniq.sort == scripts.uniq.sort
+      return @char_scripts.uniq == [scripts] if scripts.is_a?(Symbol)
+      @char_scripts.uniq.sort == scripts.uniq.sort
     end
 
     def script_groups
-      @characters
-        .chunk { |char| char.script }
-        .map { |script, chars| ScriptGroup.new(script, chars) }
+      @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 grouped_scripts_hash
       script_groups.map { |group| [group.script, group.text] }.to_h
     end
+
+    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

data/lib/unicode_script_detector/script_group.rb

@@ -1,19 +1,20 @@
 module UnicodeScriptDetector
   class ScriptGroup
-    attr_reader :script, :characters, :text
+    attr_reader :script, :text, :name
 
-    def initialize(script, characters)
+    def initialize(script, chars, name)
       @script = script
-      @characters = characters
-      @text = characters.map(&:char).join
+      @chars = chars
+      @text = chars.join
+      @name = name
     end
 
     def length
-      @characters.length
+      @chars.length
     end
 
-    def name
-      @characters.first&.name
+    def characters
+      @characters ||= @chars.map { |char| Character.new(char, @script, @name) }
     end
   end
 end

data/lib/unicode_script_detector/scripts.rb

@@ -11,11 +11,6 @@ module UnicodeScriptDetector
         name: "Digit",
         regex: /\d/
       },
-      {
-        script: :Punctuation,
-        name: "Punctuation",
-        regex: /[[:punct:]]/
-      },
       { 
         script: :Adlam, 
         name: "Adlam", 
@@ -842,7 +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 = "0.0.5"
+  VERSION = "0.0.6"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode_script_detector
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - David Arendsen
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-12-31 00:00:00.000000000 Z
+date: 2026-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: zeitwerk