unicode-name 1.13.1 → 1.13.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ad37a86c74a53f8ed0fd5b7d99958e63f06537392c1156810405d8cf83e98082
-  data.tar.gz: ec21c556d90d33b7dbef6ac61cfca62805505f4a3afba068a5efc8f3d967b686
+  metadata.gz: 7d5b492a10c5d32a1452b2c01a98dce50e1dbeedbe75b5fc3d73aae7cac013d8
+  data.tar.gz: d1b1cd8ced4f9685c31833b15e7d441469ec3117911f46a13b07cbd7ea33426b
 SHA512:
-  metadata.gz: 5a86c60936a59105991a4e769ecfa2ea6cff752ab85a4ad87ca800d2455d13cf2b276cfa20a4d281bc4b91eb4f9c7155293b4da8a454d544a992045b66b9006e
-  data.tar.gz: 8e2ad3afb63a2dda11dee3b2a5b3e7ea24e275e3744fbfe14615b8cca698ae14b2d9784cf6180e4d4136eb058fe1ae4b1a1fddd1ff34fc220ac059a0639586fb
+  metadata.gz: 20e926fc2271e4421359f767a0b601c52e37c012c8bb804c1318df4bf8d50686bfd8206d6c0bf26454921e14aae237c255c734e15aaede0ef875a398a91757e7
+  data.tar.gz: c2c46f3bd4dd9b83f32343c7d18e15a16a1af440a51db7c0512f3acdd0382a6b5cb7653653b3ed9695ebd277172b7d8c15bedda517ce9d8028b4db0bf475f4bb

data/CHANGELOG.md

@@ -1,5 +1,15 @@
 ## CHANGELOG
 
+### 1.13.3
+
+- Fix regression introduced in 1.13.2 that some CJK ideographs were missing
+
+### 1.13.2
+
+- Optimize index size by removing ranges that have codepoints embedded
+- Optimize index size by substituting common words
+- Fix missing Tangut ideographs
+
 ### 1.13.1
 
 Bugfix release:

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    unicode-name (1.13.1)
+    unicode-name (1.13.3)
       unicode-types (~> 1.10)
 
 GEM

data/README.md

@@ -42,7 +42,11 @@ Unicode::Name.readable("\0") # => "NULL"
 Unicode::Name.readable("\u{FFFFD}") # => "<private-use-FFFFD>"
 ```
 
-See [unicode-sequence_names](https://github.com/janlelis/unicode-sequence_name) for character names of more complex codepoint sequences.
+See [unicode-sequence_names](https://github.com/janlelis/unicode-sequence_name) for character names of more complex codepoint sequences. This is how you could use both libraries together to get the most relevant name of a character:
+
+```ruby
+name = Unicode::SequenceName.of(char) || Unicode::Name.readable(char)
+```
 
 See [unicode-x](https://github.com/janlelis/unicode-x) for more Unicode related micro libraries.
 

data/lib/unicode/name/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   module Name
-    VERSION = "1.13.1"
+    VERSION = "1.13.3"
     UNICODE_VERSION = "16.0.0"
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/").freeze
     INDEX_FILENAME = (DATA_DIRECTORY + "/name.marshal.gz").freeze

data/lib/unicode/name.rb

@@ -11,11 +11,18 @@ module Unicode
     def self.unicode_name(char) 
       codepoint = char.unpack("U")[0]
       require_relative "name/index" unless defined? ::Unicode::Name::INDEX
+
       if res = INDEX[:NAMES][codepoint]
-        res
-      elsif INDEX[:CJK].any?{ |cjk_range| codepoint >= cjk_range[0] && codepoint <= cjk_range[1] }
-        "CJK UNIFIED IDEOGRAPH-%.4X" % codepoint
-      elsif codepoint >= HANGUL_START && codepoint <= HANGUL_END
+        return insert_words(res)
+      end
+
+      INDEX[:CP_RANGES].each{|prefix, range|
+        if range.any?{ |range| codepoint >= range[0] && codepoint <= range[1] }
+          return "%s%.4X" %[prefix, codepoint]
+        end
+      }
+
+      if codepoint >= HANGUL_START && codepoint <= HANGUL_END
         "HANGUL SYLLABLE %s" % hangul_decomposition(codepoint)
       else
         nil
@@ -72,8 +79,6 @@ module Unicode
       label(char)
     end
 
-    private
-
     # See https://en.wikipedia.org/wiki/Korean_language_and_computers#Hangul_Syllables_Area
     def self.hangul_decomposition(codepoint)
       base = codepoint - HANGUL_START
@@ -82,6 +87,22 @@ module Unicode
       initial = base / HANGUL_MEDIAL_MAX
       "#{INDEX[:JAMO][:INITIAL][initial]}#{INDEX[:JAMO][:MEDIAL][medial]}#{INDEX[:JAMO][:FINAL][final]}"
     end
+
+    def self.insert_words(raw_name)
+      raw_name.chars.map{ |char|
+        codepoint = char.ord
+        if codepoint < INDEX[:REPLACE_BASE]
+          char
+        else
+          "#{INDEX[:COMMON_WORDS][codepoint - INDEX[:REPLACE_BASE]]} "
+        end
+      }.join.chomp
+    end
+
+    class << self
+      private :hangul_decomposition
+      private :insert_words
+    end
   end
 end
 

data/spec/unicode_name_spec.rb

@@ -9,11 +9,12 @@ describe Unicode::Name do
       assert_equal "REPLACEMENT CHARACTER", Unicode::Name.of("�")
     end
 
-    it "works for CJK Ideographs" do
+    it "works for CJK unified ideographs" do
       assert_equal "CJK UNIFIED IDEOGRAPH-4E01", Unicode::Name.of("丁")
+      assert_equal "SQUARED CJK UNIFIED IDEOGRAPH-6709", Unicode::Name.of("🈶")
     end
 
-    it "works for Hangul Syllables" do
+    it "works for Hangul syllables" do
       assert_equal "HANGUL SYLLABLE HAN", Unicode::Name.of("한")
       assert_equal "HANGUL SYLLABLE GAG", Unicode::Name.of("각")
       assert_equal "HANGUL SYLLABLE GAE", Unicode::Name.of("개")
@@ -21,6 +22,14 @@ describe Unicode::Name do
       assert_equal "HANGUL SYLLABLE DWALB", Unicode::Name.of("돫")
     end
 
+    it "works with some ranges that have the codepoint embedded" do
+      assert_equal "EGYPTIAN HIEROGLYPH-143F5", Unicode::Name.of("𔏵")
+      assert_equal "KHITAN SMALL SCRIPT CHARACTER-18C12", Unicode::Name.of("𘰒")
+      assert_equal "TANGUT IDEOGRAPH-18D00", Unicode::Name.of("𘴀")
+      assert_equal "NUSHU CHARACTER-1B171", Unicode::Name.of("𛅱")
+      assert_equal "CJK COMPATIBILITY IDEOGRAPH-2F9B1", Unicode::Name.of("𧃒")
+    end
+
     it "will return nil for characters without name" do
       assert_nil Unicode::Name.of("\u{10c50}")
       assert_nil Unicode::Name.of("\0")

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-name
 version: !ruby/object:Gem::Version
-  version: 1.13.1
+  version: 1.13.3
 platform: ruby
 authors:
 - Jan Lelis
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-10-03 00:00:00.000000000 Z
+date: 2024-10-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unicode-types
@@ -68,7 +68,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.20
+rubygems_version: 3.5.21
 signing_key:
 specification_version: 4
 summary: Returns name/aliases/label of a Unicode codepoint