unicode_script_detector 0.0.5 → 0.0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4795cdb246ac34ccb0ee5183ff0e704d25e4e67410acee321f36f4446dd28356
-  data.tar.gz: 0c7b9c4c835718f2fc7509225204e38c0a7148949c5745f1448b299c27e0e88d
+  metadata.gz: a0febe236b556e42077b401d8e117b3996c6065dcbb33c974a572a8af64d14a4
+  data.tar.gz: f8ef874b90e0ca8e387bc16d5fc947745fcbe34bbd8ea53c328f98d8c3d8eddd
 SHA512:
-  metadata.gz: 5da7422c57295f4ac3dee3ac9ccfaa99b5586418de956a88876035541da023e9fa4afe609a4aa79d4c3a1a5f9b1ffe64370984657844c06fc6a575578beb5ee2
-  data.tar.gz: aa9fecf48386b6eb5a0074cbbec8819af80153c6111e042debd9e9c312145bc11a936b3003a406370a28e8a27a48b2bd0409c0cf043b26fe465f4c58ee9669e2
+  metadata.gz: c5b931f1a8f527900f9c37ba0af67ca4e1fbfc0a0fde2f382fc1c2853a2c8813654f1d334f692e39882421eb3a4825f8e056d91d92d58fb4c2c1c22266c347b3
+  data.tar.gz: 69ac1e2314cefd944af0958cba15764afdf05e6e6eb314b68bc75172c7d1085be00725d40df5fe7f1af23abccc0243fa5d134c0b590da62d83913dce6570f0c1

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

@@ -1,21 +1,6 @@
 module UnicodeScriptDetector
   class Scripts
     LIST = [
-      {
-        script: :Whitespace,
-        name: "Whitespace",
-        regex: /\s/
-      },
-      {
-        script: :Digit,
-        name: "Digit",
-        regex: /\d/
-      },
-      {
-        script: :Punctuation,
-        name: "Punctuation",
-        regex: /[[:punct:]]/
-      },
       { 
         script: :Adlam, 
         name: "Adlam", 
@@ -28,7 +13,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Anatolian_Hieroglyphs, 
-        name: "Anatolian_Hieroglyphs", 
+        name: "Anatolian Hieroglyphs", 
         regex: /\p{Anatolian_Hieroglyphs}/, 
       },
       { 
@@ -58,7 +43,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Bassa_Vah, 
-        name: "Bassa_Vah", 
+        name: "Bassa Vah", 
         regex: /\p{Bassa_Vah}/, 
       },
       { 
@@ -103,7 +88,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Canadian_Aboriginal, 
-        name: "Canadian_Aboriginal", 
+        name: "Canadian Aboriginal", 
         regex: /\p{Canadian_Aboriginal}/, 
       },
       { 
@@ -113,7 +98,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Caucasian_Albanian, 
-        name: "Caucasian_Albanian", 
+        name: "Caucasian Albanian", 
         regex: /\p{Caucasian_Albanian}/, 
       },
       { 
@@ -153,7 +138,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Cypro_Minoan, 
-        name: "Cypro_Minoan", 
+        name: "Cypro Minoan", 
         regex: /\p{Cypro_Minoan}/, 
       },
       { 
@@ -173,7 +158,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Dives_Akuru, 
-        name: "Dives_Akuru", 
+        name: "Dives Akuru", 
         regex: /\p{Dives_Akuru}/, 
       },
       { 
@@ -188,8 +173,8 @@ module UnicodeScriptDetector
       },
       { 
         script: :Egyptian_Hieroglyphs, 
-        name: "Egyptian_Hieroglyphs", 
-        regex: /\p{Egyptian_Hieroglyphs}/, 
+        name: "Egyptian Hieroglyphs", 
+        regex: /\p{Egyptian_Hieroglyphs}|[\u{13460}-\u{1355F}]/, 
       },
       { 
         script: :Elbasan, 
@@ -206,7 +191,11 @@ module UnicodeScriptDetector
         name: "Ethiopic", 
         regex: /\p{Ethiopic}/, 
       },
-    
+      { 
+        script: :Garay, 
+        name: "Garay", 
+        regex: /[\u{10D40}-\u{10D8F}]/,
+      },
       { 
         script: :Georgian, 
         name: "Georgian", 
@@ -239,7 +228,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Gunjala_Gondi, 
-        name: "Gunjala_Gondi", 
+        name: "Gunjala Gondi", 
         regex: /\p{Gunjala_Gondi}/, 
       },
       { 
@@ -247,11 +236,15 @@ module UnicodeScriptDetector
         name: "Gurmukhi", 
         regex: /\p{Gurmukhi}/, 
       },
-    
+      { 
+        script: :Gurung_Khema, 
+        name: "Gurung Khema", 
+        regex: /[\u{16100}-\u{1613F}]/,
+      },
       { 
         script: :Han, 
         name: "Han", 
-        regex: /\p{Han}/, 
+        regex: /\p{Han}|[\u{323B0}-\u{3347F}]/, 
       },
       { 
         script: :Hangul, 
@@ -260,7 +253,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Hanifi_Rohingya, 
-        name: "Hanifi_Rohingya", 
+        name: "Hanifi Rohingya", 
         regex: /\p{Hanifi_Rohingya}/, 
       },
       { 
@@ -285,7 +278,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Imperial_Aramaic, 
-        name: "Imperial_Aramaic", 
+        name: "Imperial Aramaic", 
         regex: /\p{Imperial_Aramaic}/, 
       },
       { 
@@ -295,12 +288,12 @@ module UnicodeScriptDetector
       },
       { 
         script: :Inscriptional_Pahlavi, 
-        name: "Inscriptional_Pahlavi", 
+        name: "Inscriptional Pahlavi", 
         regex: /\p{Inscriptional_Pahlavi}/, 
       },
       { 
         script: :Inscriptional_Parthian, 
-        name: "Inscriptional_Parthian", 
+        name: "Inscriptional Parthian", 
         regex: /\p{Inscriptional_Parthian}/, 
       },
       { 
@@ -323,7 +316,6 @@ module UnicodeScriptDetector
         name: "Katakana", 
         regex: /\p{Katakana}/, 
       },
-    
       { 
         script: :Kawi, 
         name: "Kawi", 
@@ -331,7 +323,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Kayah_Li, 
-        name: "Kayah_Li", 
+        name: "Kayah Li", 
         regex: /\p{Kayah_Li}/, 
       },
       { 
@@ -341,7 +333,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Khitan_Small_Script, 
-        name: "Khitan_Small_Script", 
+        name: "Khitan Small Script", 
         regex: /\p{Khitan_Small_Script}/, 
       },
       { 
@@ -359,7 +351,11 @@ module UnicodeScriptDetector
         name: "Khudawadi", 
         regex: /\p{Khudawadi}/, 
       },
-    
+      { 
+        script: :Kirat_Rai, 
+        name: "Kirat Rai", 
+        regex: /[\u{16D40}-\u{16D7F}]/,
+      },
       { 
         script: :Lao, 
         name: "Lao", 
@@ -382,12 +378,12 @@ module UnicodeScriptDetector
       },
       { 
         script: :Linear_A, 
-        name: "Linear_A", 
+        name: "Linear A", 
         regex: /\p{Linear_A}/, 
       },
       { 
         script: :Linear_B, 
-        name: "Linear_B", 
+        name: "Linear B", 
         regex: /\p{Linear_B}/, 
       },
       { 
@@ -437,7 +433,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Masaram_Gondi, 
-        name: "Masaram_Gondi", 
+        name: "Masaram Gondi", 
         regex: /\p{Masaram_Gondi}/, 
       },
       { 
@@ -447,22 +443,22 @@ module UnicodeScriptDetector
       },
       { 
         script: :Meetei_Mayek, 
-        name: "Meetei_Mayek", 
+        name: "Meetei Mayek", 
         regex: /\p{Meetei_Mayek}/, 
       },
       { 
         script: :Mende_Kikakui, 
-        name: "Mende_Kikakui", 
+        name: "Mende Kikakui", 
         regex: /\p{Mende_Kikakui}/, 
       },
       { 
         script: :Meroitic_Cursive, 
-        name: "Meroitic_Cursive", 
+        name: "Meroitic Cursive", 
         regex: /\p{Meroitic_Cursive}/, 
       },
       { 
         script: :Meroitic_Hieroglyphs, 
-        name: "Meroitic_Hieroglyphs", 
+        name: "Meroitic Hieroglyphs", 
         regex: /\p{Meroitic_Hieroglyphs}/, 
       },
       { 
@@ -493,7 +489,7 @@ module UnicodeScriptDetector
       { 
         script: :Myanmar, 
         name: "Myanmar", 
-        regex: /\p{Myanmar}/, 
+        regex: /\p{Myanmar}|[\u{116D0}-\u{116FF}]/, 
       },
       { 
         script: :Nabataean, 
@@ -502,7 +498,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Nag_Mundari, 
-        name: "Nag_Mundari", 
+        name: "Nag Mundari", 
         regex: /\p{Nag_Mundari}/, 
       },
       { 
@@ -512,7 +508,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :New_Tai_Lue, 
-        name: "New_Tai_Lue", 
+        name: "New Tai Lue", 
         regex: /\p{New_Tai_Lue}/, 
       },
       { 
@@ -532,7 +528,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Nyiakeng_Puachue_Hmong, 
-        name: "Nyiakeng_Puachue_Hmong", 
+        name: "Nyiakeng Puachue Hmong", 
         regex: /\p{Nyiakeng_Puachue_Hmong}/, 
       },
       { 
@@ -542,53 +538,57 @@ module UnicodeScriptDetector
       },
       { 
         script: :Ol_Chiki, 
-        name: "Ol_Chiki", 
+        name: "Ol Chiki", 
         regex: /\p{Ol_Chiki}/, 
       },
-    
+      { 
+        script: :Ol_Onal, 
+        name: "Ol Onal", 
+        regex: /[\u{1E5D0}-\u{1E5FF}]/,
+      },
       { 
         script: :Old_Hungarian, 
-        name: "Old_Hungarian", 
+        name: "Old Hungarian", 
         regex: /\p{Old_Hungarian}/, 
       },
       { 
         script: :Old_Italic, 
-        name: "Old_Italic", 
+        name: "Old Italic", 
         regex: /\p{Old_Italic}/, 
       },
       { 
         script: :Old_North_Arabian, 
-        name: "Old_North_Arabian", 
+        name: "Old North Arabian", 
         regex: /\p{Old_North_Arabian}/, 
       },
       { 
         script: :Old_Permic, 
-        name: "Old_Permic", 
+        name: "Old Permic", 
         regex: /\p{Old_Permic}/, 
       },
       { 
         script: :Old_Persian, 
-        name: "Old_Persian", 
+        name: "Old Persian", 
         regex: /\p{Old_Persian}/, 
       },
       { 
         script: :Old_Sogdian, 
-        name: "Old_Sogdian", 
+        name: "Old Sogdian", 
         regex: /\p{Old_Sogdian}/, 
       },
       { 
         script: :Old_South_Arabian, 
-        name: "Old_South_Arabian", 
+        name: "Old South Arabian", 
         regex: /\p{Old_South_Arabian}/, 
       },
       { 
         script: :Old_Turkic, 
-        name: "Old_Turkic", 
+        name: "Old Turkic", 
         regex: /\p{Old_Turkic}/, 
       },
       { 
         script: :Old_Uyghur, 
-        name: "Old_Uyghur", 
+        name: "Old Uyghur", 
         regex: /\p{Old_Uyghur}/, 
       },
       { 
@@ -608,7 +608,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Pahawh_Hmong, 
-        name: "Pahawh_Hmong", 
+        name: "Pahawh Hmong", 
         regex: /\p{Pahawh_Hmong}/, 
       },
       { 
@@ -618,12 +618,12 @@ module UnicodeScriptDetector
       },
       { 
         script: :Pau_Cin_Hau, 
-        name: "Pau_Cin_Hau", 
+        name: "Pau Cin Hau", 
         regex: /\p{Pau_Cin_Hau}/, 
       },
       { 
         script: :Phags_Pa, 
-        name: "Phags_Pa", 
+        name: "Phags Pa", 
         regex: /\p{Phags_Pa}/, 
       },
       { 
@@ -633,7 +633,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Psalter_Pahlavi, 
-        name: "Psalter_Pahlavi", 
+        name: "Psalter Pahlavi", 
         regex: /\p{Psalter_Pahlavi}/, 
       },
       { 
@@ -659,7 +659,7 @@ module UnicodeScriptDetector
       { 
         script: :Sharada, 
         name: "Sharada", 
-        regex: /\p{Sharada}/, 
+        regex: /\p{Sharada}|[\u{11B60}-\u{11B7F}]/, 
       },
       { 
         script: :Shavian, 
@@ -671,6 +671,11 @@ module UnicodeScriptDetector
         name: "Siddham", 
         regex: /\p{Siddham}/, 
       },
+      {
+        script: :Sidetic,
+        name: "Sidetic",
+        regex: /[\u{10940}-\u{1095F}]/
+      },
       { 
         script: :SignWriting, 
         name: "SignWriting", 
@@ -688,7 +693,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Sora_Sompeng, 
-        name: "Sora_Sompeng", 
+        name: "Sora Sompeng", 
         regex: /\p{Sora_Sompeng}/, 
       },
       { 
@@ -701,10 +706,14 @@ module UnicodeScriptDetector
         name: "Sundanese", 
         regex: /\p{Sundanese}/, 
       },
-    
+      { 
+        script: :Sunuwar, 
+        name: "Sunuwar", 
+        regex: /[\u{11BC0}-\u{11BFF}]/,
+      },
       { 
         script: :Syloti_Nagri, 
-        name: "Syloti_Nagri", 
+        name: "Syloti Nagri", 
         regex: /\p{Syloti_Nagri}/, 
       },
       { 
@@ -724,19 +733,24 @@ module UnicodeScriptDetector
       },
       { 
         script: :Tai_Le, 
-        name: "Tai_Le", 
+        name: "Tai Le", 
         regex: /\p{Tai_Le}/, 
       },
       { 
         script: :Tai_Tham, 
-        name: "Tai_Tham", 
+        name: "Tai Tham", 
         regex: /\p{Tai_Tham}/, 
       },
       { 
         script: :Tai_Viet, 
-        name: "Tai_Viet", 
+        name: "Tai Viet", 
         regex: /\p{Tai_Viet}/, 
       },
+      { 
+        script: :Tai_Yo, 
+        name: "Tai Yo", 
+        regex: /[\u{1E6C0}-\u{1E6FF}]/,
+      },
       { 
         script: :Takri, 
         name: "Takri", 
@@ -755,7 +769,7 @@ module UnicodeScriptDetector
       { 
         script: :Tangut, 
         name: "Tangut", 
-        regex: /\p{Tangut}/, 
+        regex: /\p{Tangut}|[\u{18D80}-\u{18DFF}]/, 
       },
       { 
         script: :Telugu, 
@@ -787,13 +801,26 @@ module UnicodeScriptDetector
         name: "Tirhuta", 
         regex: /\p{Tirhuta}/, 
       },
-    
+      { 
+        script: :Todhri, 
+        name: "Todhri", 
+        regex: /[\u{105C0}-\u{105FF}]/,
+      },
+      { 
+        script: :Tolong_Siki, 
+        name: "Tolong Siki", 
+        regex: /[\u{11DB0}-\u{11DEF}]/,
+      },
       { 
         script: :Toto, 
         name: "Toto", 
         regex: /\p{Toto}/, 
       },
-    
+      { 
+        script: :Tulu_Tigalari, 
+        name: "Tulu Tigalari", 
+        regex: /[\u{11380}-\u{113FF}]/,
+      },
       { 
         script: :Ugaritic, 
         name: "Ugaritic", 
@@ -821,7 +848,7 @@ module UnicodeScriptDetector
       },
       { 
         script: :Warang_Citi, 
-        name: "Warang_Citi", 
+        name: "Warang Citi", 
         regex: /\p{Warang_Citi}/, 
       },
       { 
@@ -836,18 +863,35 @@ module UnicodeScriptDetector
       },
       { 
         script: :Zanabazar_Square, 
-        name: "Zanabazar_Square", 
+        name: "Zanabazar Square", 
         regex: /\p{Zanabazar_Square}/, 
       },
+
+      #Special characters
+      {
+        script: :Whitespace,
+        name: "Whitespace",
+        regex: /\s/
+      },
+      {
+        script: :Digit,
+        name: "Digit",
+        regex: /\d/
+      },
       { 
         script: :Emoji, 
         name: "Emoji", 
-        regex: /\p{Emoji}/, 
+        regex: /\p{Emoji_Presentation}/, 
+      },
+      {
+        script: :Punctuation,
+        name: "Punctuation",
+        regex: /[[:punct:]]/
       },
       { 
         script: :Common, 
         name: "Common", 
-        regex: /\p{Common}/, 
+        regex: /\p{Common}|[\u{1CEC0}-\u{1CEFF}]|[\u{1CC00}-\u{1CEBF}]/, 
       },
     ]
   end

data/lib/unicode_script_detector/version.rb

@@ -1,3 +1,3 @@
 module UnicodeScriptDetector
-  VERSION = "0.0.5"
+  VERSION = "0.0.7"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode_script_detector
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.7
 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