unicode-sequence_name 1.14.0 → 1.15.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dc56290d80aa559b72e07cdb113a85785bf38408d3aa8c60cf6ab1096a7c77ab
-  data.tar.gz: e7e6183d46725245663b546c68abe9335ae633247d7814ccea486c1cb55bd033
+  metadata.gz: 4f82b600e2dee51ced0f09804f15738ccbf649f9b514795e1d30d4689c53bda3
+  data.tar.gz: cf50ae70515d8d772eb485f93452a3abdd07218adac8a4c8bfcc8c166fe4803b
 SHA512:
-  metadata.gz: ab8100396577cb4b360f13eef2cdb9f18ddd66436d1c39046d54d45c33aa4cbd9b6f5afc421368dfe816171b6261b0d4eaecd1cef59a0ef594a13974927da1f8
-  data.tar.gz: 9bafbec1dac2df24e2c3b8654c76e4939b415609f8eb30989a3153486fe1d3405f83a6f885df601cc6e7dadea12f209460550faf2f7a4fbda3d2e69d55fb63dd
+  metadata.gz: eb6701614c710ab7abf71bd8a2a2dc6c96a0fffb777d36ba47e2951bfe76b2259eb35f473c1496ffc19544d40cea015728747926e531a33fc881b12a96ee8ac2
+  data.tar.gz: 8941fe7b817418e6792715340bfefd7d803ae89a9704a5bd51b830e3e31777975b5c4b52851da5d127ac4b8d379f0c671452ae5efbbd52b27ef23e069b024247

data/CHANGELOG.md

@@ -1,5 +1,15 @@
 ## CHANGELOG
 
+### 1.15.0
+
+- Include Emoji sequences which are not fully qualified (VS16 is missing) in index
+- You can use the newly introduced method `Unicode::SequenceName.fully_qualified` 
+  if you want to exclude non-fully qualified sequences
+
+### 1.14.1
+
+- Fix bug that some singleton Emoji would be included in index
+
 ### 1.14.0
 
 - Unicode 16.0

data/Gemfile.lock

@@ -1,24 +1,24 @@
 PATH
   remote: .
   specs:
-    unicode-sequence_name (1.14.0)
+    unicode-sequence_name (1.15.0)
 
 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)
 
 PLATFORMS
   ruby

data/README.md

@@ -10,7 +10,7 @@ IVD version: **2022-09-13** (September 2022)
 
 Supported Rubies: **3.3**, **3.2**, **3.1**, **3.0**
 
-Old Rubies which might still work: **2.7**, **2.6**, **2.5**, **2.4**, **2.3**, **2.X**
+Old Rubies which might still work: **2.X**
 
 ## Usage
 
@@ -32,12 +32,17 @@ Unicode::SequenceName.of "🙂‍↔️" # => "HEAD SHAKING HORIZONTALLY"
 Unicode::SequenceName.of "‘︁" # => "LEFT SINGLE QUOTATION MARK (right-justified fullwidth form)"
 ```
 
-Names for singular codepoints are not included, you can use [unicode-name](https://github.com/janlelis/unicode-name) for that purpose.
+Names for singular codepoints are not included, but you can use [unicode-name](https://github.com/janlelis/unicode-name) for that purpose. 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)
+```
 
 ## Also See
 
 - [uniscribe](https://github.com/janlelis/uniscribe) - cli utility that makes use of unicode_sequence-name
 - [unicode-x](https://github.com/janlelis/unicode-x) - more Unicode related micro libraries
+- [unicode-name.js](https://github.com/janlelis/unicode-name.js) - JavaScript implementation of name and sequence_name
 
 ## MIT License
 

data/lib/unicode/sequence_name/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   module SequenceName
-    VERSION = "1.14.0"
+    VERSION = "1.15.0"
     UNICODE_VERSION = "16.0.0"
     EMOJI_VERSION = "16.0"
     IVD_VERSION = "2022-09-13"

data/lib/unicode/sequence_name.rb

@@ -5,7 +5,7 @@ module Unicode
     def self.sequence_name(string)
       codepoints = get_codepoint_values(string)
       require_relative "sequence_name/index" unless defined? ::Unicode::SequenceName::INDEX
-      if res = INDEX[codepoints]
+      if res = INDEX[:SEQUENCES][codepoints] || INDEX[:SEQUENCES_NOT_QUALIFIED][codepoints]
         res
       else
         nil
@@ -13,6 +13,16 @@ module Unicode
     end
     class << self; alias of sequence_name; end
 
+    def self.fully_qualified(string)
+      codepoints = get_codepoint_values(string)
+      require_relative "sequence_name/index" unless defined? ::Unicode::SequenceName::INDEX
+      if res = INDEX[:SEQUENCES][codepoints]
+        res
+      else
+        nil
+      end
+    end
+
     def self.get_codepoint_values(string)
       if string.valid_encoding?
         return string.codepoints

data/spec/unicode_sequence_name_spec.rb

@@ -3,7 +3,7 @@ require "minitest/autorun"
 
 describe Unicode::SequenceName do
   describe ".sequence_name (alias .of)" do
-    it "will return name for that sequence name" do
+    it "will return name for that sequence" do
       assert_equal "DOUBLE EXCLAMATION MARK (text style)", Unicode::SequenceName.of("‼︎")
       assert_equal "CJK COMPATIBILITY IDEOGRAPH-2F81F", Unicode::SequenceName.of("㓟︀")
       assert_equal "MYANMAR LETTER NGA (dotted form)", Unicode::SequenceName.of("င︀")
@@ -19,10 +19,30 @@ describe Unicode::SequenceName do
       assert_equal "LEFT SINGLE QUOTATION MARK (right-justified fullwidth form)", Unicode::SequenceName.of("‘︁") # Unicode 16.0
     end
 
+    it "will return name for that sequence (not fully qualified: VS16 missing)" do
+      assert_equal "COUPLE WITH HEART: WOMAN, WOMAN, DARK SKIN TONE, MEDIUM SKIN TONE", Unicode::SequenceName.of("👩🏿‍❤‍👩🏽")
+      assert_equal "MAN JUDGE", Unicode::SequenceName.of("👨‍⚖")
+      assert_equal "WOMAN BOUNCING BALL", Unicode::SequenceName.of("⛹‍♀️") # First VS16 missing
+      assert_equal "WOMAN BOUNCING BALL", Unicode::SequenceName.of("⛹️‍♀") # Second VS16 missing
+    end
+
     it "will return nil for characters without name" do
       assert_nil Unicode::SequenceName.of("\u{10c50}")
       assert_nil Unicode::SequenceName.of("bla")
     end
+
+    it "will return nil for single codepoints" do
+      assert_nil Unicode::SequenceName.of("⏳")
+    end
+  end
+
+  describe ".fully_qualified" do
+    it "will *not* return name for that sequence (not fully qualified: VS16 missing)" do
+      assert_nil Unicode::SequenceName.fully_qualified("👩🏿‍❤‍👩🏽")
+      assert_nil Unicode::SequenceName.fully_qualified("👨‍⚖")
+      assert_nil Unicode::SequenceName.fully_qualified("⛹‍♀️") # First VS16 missing
+      assert_nil Unicode::SequenceName.fully_qualified("⛹️‍♀") # Second VS16 missing
+    end
   end
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-sequence_name
 version: !ruby/object:Gem::Version
-  version: 1.14.0
+  version: 1.15.0
 platform: ruby
 authors:
 - Jan Lelis
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-09-13 00:00:00.000000000 Z
+date: 2024-10-06 00:00:00.000000000 Z
 dependencies: []
 description: "[Unicode 16.0.0][Emoji 16.0] Returns the name of a Unicode code point
   sequence, if one exists"
@@ -53,7 +53,7 @@ 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 the name of a Unicode codepoint sequence, if one exists