unicode-sequence_name 1.14.1 → 1.15.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4503c1bf10b43d732a5ee88c9a9059837f2190910f10a0c33fdfda6dd516b68f
-  data.tar.gz: 6d821ef47679dc9be1aef97a9a489051127b54f160e2fd7609a9cded3ee5decf
+  metadata.gz: 9027ebad3f5176ac6e6e554460da72a6fc2edcefa99e73027df557693f197d3a
+  data.tar.gz: 34ea77e121ff2ed7c88e94da43bfe78ad313b52fba516255459de01ba7027d5e
 SHA512:
-  metadata.gz: e5e8ff63ca2e1e97a604fdf4bc4f8067afb8eba9d7e163a6ddd0eb6e13b6b565a19cc67b2f43b70566d3e5903dc429a6b8fbfb2379a938d201bd1482dccb41c9
-  data.tar.gz: b8728edb403073493e7d135016981ffdd2d046f1369a696fb23e0e4ec36075035aee38a19f4e03545b8d9174490e7e45235283ab4491af5fe654e8c035c4fb67
+  metadata.gz: 537a1b631841da656b8bd8a1445791383271f6f7a2fff62c9d413e0db1780d8af1d67f98c7793ec797999985ed6d2b694741c0e101ec14899a37f5e010864fe9
+  data.tar.gz: f4f0943434c71e329bfa4b7c9551804ab46dc1547a629bde186c95c0aeb2087661232bc74d067dac50a03ce6d12411d1753b582c664dd76d3b547fc89d1f12d5

data/CHANGELOG.md

@@ -1,5 +1,15 @@
 ## CHANGELOG
 
+### 1.15.1
+
+- Optimize index size by substituting common words
+
+### 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

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    unicode-sequence_name (1.14.1)
+    unicode-sequence_name (1.15.1)
 
 GEM
   remote: https://rubygems.org/

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
 
@@ -32,10 +32,10 @@ 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. This is how you could use both libraries together to get the most relevant name of a character:
+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::Name.sequence_name(char) || Unicode::Name.readable(char)
+name = Unicode::SequenceName.of(char) || Unicode::Name.readable(char)
 ```
 
 ## Also See

data/lib/unicode/sequence_name/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   module SequenceName
-    VERSION = "1.14.1"
+    VERSION = "1.15.1"
     UNICODE_VERSION = "16.0.0"
     EMOJI_VERSION = "16.0"
     IVD_VERSION = "2022-09-13"

data/lib/unicode/sequence_name.rb

@@ -5,14 +5,24 @@ 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[:SEQUENCES][codepoints]
-        res
+      if res = INDEX[:SEQUENCES][codepoints] || INDEX[:SEQUENCES_NOT_QUALIFIED][codepoints]
+        insert_words(res)
       else
         nil
       end
     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]
+        insert_words(res)
+      else
+        nil
+      end
+    end
+
     def self.get_codepoint_values(string)
       if string.valid_encoding?
         return string.codepoints
@@ -26,8 +36,20 @@ module Unicode
       raise(ArgumentError, "Unicode::SequenceName.of must be given a valid string")
     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 :get_codepoint_values
+      private :insert_words
     end
   end
 end

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")
@@ -19,6 +19,13 @@ 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")
@@ -28,5 +35,14 @@ describe Unicode::SequenceName 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: 1.14.1
+  version: 1.15.1
 platform: ruby
 authors:
 - Jan Lelis
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-10-04 00:00:00.000000000 Z
+date: 2024-10-09 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: 3.5.20
+rubygems_version: 3.5.21
 signing_key:
 specification_version: 4
 summary: Returns the name of a Unicode codepoint sequence, if one exists