unicode-name 1.13.0 → 1.13.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a4698018ace1d5ea494dae78e89b9b034ef75bbb78441c960a3e9afed0a7632b
-  data.tar.gz: 26bec8d0de6272266d958e400b45efc8b979a6e0c5c9792c08824060b239d72d
+  metadata.gz: ca6d8f90ce7c5fa9c9da362be1d90b10260da01d8ac97e2412e0699fa69ca40a
+  data.tar.gz: a3a2a417c76906c32fe429ce51e16c543696687bb0078340aecb293a65595800
 SHA512:
-  metadata.gz: c016a26447bb75579756602a8bf3ea68a29d8fc46074be79c4583d559779f3251bfbdd6838def8913274c2bbf1f69d225acf6ed6dec258513bb2c091535e7d0c
-  data.tar.gz: f67d5e5edf3554ccc69d52709f1551f8ac066325234c428b604f9e050700883a2cb503d812123cd3b88774afca488b63167c331274bf34ab8e15bb00b43e143c
+  metadata.gz: 9ad0910912fcf5e226e00955c72cd3325796acc49137ce2e9c141fdcaa5518585fb38795de6587cd792d22b428110d08592a212220dc09a91f3e92016140a86a
+  data.tar.gz: 5b8de2a4c57c893d6e18ef4ce5b876a032f0cc0f3726504753a0dfbf9b7b4e4bf18d2b6b7aadf1a976231079d285872a6203e352d66fe26154883c31237d9aca

data/.rake_tasks

@@ -0,0 +1,3 @@
+gem
+irb
+spec

data/CHANGELOG.md

@@ -1,5 +1,18 @@
 ## CHANGELOG
 
+### 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:
+
+- Fix medial vowels not generated correctly for Hangul syllables #1
+- Unicode::Name.readable now also applies correction if one exists
+
 ### 1.13.0
 
 - Unicode 16.0
@@ -22,59 +35,58 @@
 
 ### 1.8.0
 
-* Unicode 12.1
+- Unicode 12.1
 
 ### 1.7.1
 
-* Push unicode-types dependency to 1.4.0
+- Push unicode-types dependency to 1.4.0
 
 ### 1.7.0
 
-* Unicode 12
+- Unicode 12
 
 ### 1.6.0
 
-* Unicode 11
-* Do not depend on rubygems (only use zlib stdlib for unzipping)
+- Unicode 11
+- Do not depend on rubygems (only use zlib stdlib for unzipping)
 
 ### 1.5.2
 
-* Explicitly load rubygems/util, fixes regression in 1.5.1
+- Explicitly load rubygems/util, fixes regression in 1.5.1
 
 ### 1.5.1
 
-* Use `Gem::Util` for `gunzip`, removes deprecation warning
+- Use `Gem::Util` for `gunzip`, removes deprecation warning
 
 ### 1.5.0
 
-* Unicode 10
+- Unicode 10
 
 ### 1.4.2
 
-* Fix that Unicode::Name.correct would not fail if codepoint has aliases but no correction
+- Fix that Unicode::Name.correct would not fail if codepoint has aliases but no correction
 
 ### 1.4.1
 
-* Be compatible with Ruby 2.4's surrogate literals
-* Bump unicode-types dependency
+- Be compatible with Ruby 2.4's surrogate literals
+- Bump unicode-types dependency
 
 ### 1.4.0
 
-* Support Hangul Syllables
+- Support Hangul syllables
 
 ### 1.3.0
 
-* Support Unicode 9.0
+- Support Unicode 9.0
 
 ### 1.2.0
 
-* Support CJK Ideographs
+- Support CJK Ideographs
 
 ### 1.1.0
 
-* Support codepoint labels
+- Support codepoint labels
 
 ### 1.0.0
 
-* Initial release
-
+- Initial release

data/Gemfile.lock

@@ -1,25 +1,25 @@
 PATH
   remote: .
   specs:
-    unicode-name (1.13.0)
+    unicode-name (1.13.2)
       unicode-types (~> 1.10)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    io-console (0.6.0)
-    irb (1.8.1)
-      rdoc
-      reline (>= 0.3.8)
-    minitest (5.20.0)
-    psych (5.1.0)
+    io-console (0.7.2)
+    irb (1.14.1)
+      rdoc (>= 4.0.0)
+      reline (>= 0.4.2)
+    minitest (5.25.1)
+    psych (5.1.2)
       stringio
-    rake (13.0.6)
-    rdoc (6.5.0)
+    rake (13.2.1)
+    rdoc (6.7.0)
       psych (>= 4.0.0)
-    reline (0.3.8)
+    reline (0.5.10)
       io-console (~> 0.5)
-    stringio (3.0.8)
+    stringio (3.1.1)
     unicode-types (1.10.0)
 
 PLATFORMS

data/README.md

@@ -1,4 +1,4 @@
-# Unicode::Name [![[version]](https://badge.fury.io/rb/unicode-name.svg)](https://badge.fury.io/rb/unicode-name)  [![[ci]](https://github.com/janlelis/unicode-name/workflows/Test/badge.svg)](https://github.com/janlelis/unicode-name/actions?query=workflow%3ATest)
+# Unicode::Name [![[version]](https://badge.fury.io/rb/unicode-name.svg)](https://badge.fury.io/rb/unicode-name) [![[ci]](https://github.com/janlelis/unicode-name/workflows/Test/badge.svg)](https://github.com/janlelis/unicode-name/actions?query=workflow%3ATest)
 
 Return Unicode codepoint names, aliases, and labels.
 
@@ -6,7 +6,7 @@ Unicode version: **16.0.0** (September 2024)
 
 Supported Rubies: **3.3**, **3.2**, **3.1**, **3.0**
 
-Old Rubies that might still work: **2.7**, **2.6**, **2.5**, **2.4**, **2.3**, **2.X**
+Old Rubies that might still work: **2.X**
 
 ## Usage
 
@@ -42,10 +42,16 @@ 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.
 
+See [unicode-name.js](https://github.com/janlelis/unicode-name.js) for a JavaScript implementation of this gem.
+
 ## MIT License
 
 - Copyright (C) 2016-2024 Jan Lelis <https://janlelis.com>. Released under the MIT license.

data/lib/unicode/name/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   module Name
-    VERSION = "1.13.0"
+    VERSION = "1.13.2"
     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
@@ -63,7 +70,7 @@ module Unicode
     end
 
     def self.readable(char)
-      unicode_name(char) ||
+      correct(char) ||
       ( as = aliases(char) ) &&
       ( as[:control]      && as[:control][0]      ||
         as[:figment]      && as[:figment][0]      ||
@@ -78,10 +85,21 @@ module Unicode
     def self.hangul_decomposition(codepoint)
       base = codepoint - HANGUL_START
       final = base % HANGUL_FINAL_MAX
-      medial = (base - final) % HANGUL_MEDIAL_MAX
+      medial = (base % HANGUL_MEDIAL_MAX) / HANGUL_FINAL_MAX
       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
   end
 end
 

data/spec/unicode_name_spec.rb

@@ -9,13 +9,24 @@ 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")
     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")
+      assert_equal "HANGUL SYLLABLE GAENG", Unicode::Name.of("갱")
+      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
@@ -89,6 +100,7 @@ describe Unicode::Name do
   describe ".readable" do
     it "will return best readable representation of a codepoint" do
       assert_equal "LATIN CAPITAL LETTER A", Unicode::Name.readable("A")
+      assert_equal "LATIN CAPITAL LETTER GHA", Unicode::Name.readable("Ƣ")
       assert_equal "NULL", Unicode::Name.readable("\0")
       assert_equal "<noncharacter-FFFFF>", Unicode::Name.readable("\u{FFFFF}")
       assert_equal "<reserved-10C50>", Unicode::Name.readable("\u{10C50}")

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-name
 version: !ruby/object:Gem::Version
-  version: 1.13.0
+  version: 1.13.2
 platform: ruby
 authors:
 - Jan Lelis
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-09-13 00:00:00.000000000 Z
+date: 2024-10-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unicode-types
@@ -33,6 +33,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".rake_tasks"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - Gemfile
@@ -67,7 +68,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.9
+rubygems_version: 3.5.21
 signing_key:
 specification_version: 4
 summary: Returns name/aliases/label of a Unicode codepoint