unicode-name 1.1.0 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f3a8de48e9b0cde71e28b66a905775a415258861
-  data.tar.gz: ce9bb0b4e85c1b456ae79a62287ce0e48e4ba238
+  metadata.gz: e822a1e4a2633c877133bdfae948fe8a55d17de5
+  data.tar.gz: 68275ded458adc208f387824efab0b44b3bb0ac6
 SHA512:
-  metadata.gz: 97265bf800a36c2207ae3e2bb74d24473ed91f399e726ae5e1136eacbbdf16be87007fd5fc277f3d0024e339f8c80adfc4c22160fc862c5bcb4a6bfb96b2e68e
-  data.tar.gz: 2a140e46907de2e489279970763b49d5b9ec87059b621af60338835ca69fec7097a02550ccd8d25c778e0ac8678cab38af04f36f681e4c293e1a35212d2e56b7
+  metadata.gz: 5f1bb82a0b9b9a45c2e62016ee2942b9b7dea94e9094622a9b58c64bd740afa75cbb9b5230bd4af3fda6512011ffc01b9e9713652334b915be39890d2431a44d
+  data.tar.gz: c82bf02c6c09ad07caad0857c1a5ce40b833c23e2a1146c82614cb4042298547efd37e3b889a5b9e29c61599161768eaefce26819dc18774fb23c867c8f83de9

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 ## CHANGELOG
 
+### 1.2.0
+
+* Support CJK Ideographs
+
 ### 1.1.0
 
 * Support codepoint labels

data/README.md

@@ -14,6 +14,7 @@ require "unicode/name"
 # Name
 Unicode::Name.of "A" # => "LATIN CAPITAL LETTER A"
 Unicode::Name.of "🚡" # => "AERIAL TRAMWAY"
+Unicode::Name.of "丁" # => "CJK UNIFIED IDEOGRAPH-4E01"
 
 # Aliases, by type
 Unicode::Name.aliases "\t" # => {:control=>["CHARACTER TABULATION", "HORIZONTAL TABULATION"],
@@ -37,6 +38,10 @@ Unicode::Name.readable("\u{FFFFD}") # => "<private-use-FFFFD>"
 
 See [unicode-x](https://github.com/janlelis/unicode-x) for more Unicode related micro libraries.
 
+## Todo
+
+* Hangul syllable names
+
 ## MIT License
 
 - Copyright (C) 2016 Jan Lelis <http://janlelis.com>. Released under the MIT license.

data/lib/unicode/name/constants.rb

@@ -1,6 +1,6 @@
 module Unicode
   module Name
-    VERSION = "1.1.0".freeze
+    VERSION = "1.2.0".freeze
     UNICODE_VERSION = "8.0.0".freeze
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + '/../../../data/').freeze
     INDEX_FILENAME = (DATA_DIRECTORY + '/name.marshal.gz').freeze

data/lib/unicode/name.rb

@@ -6,7 +6,15 @@ module Unicode
     def self.unicode_name(char) 
       codepoint = char.unpack("U")[0]
       require_relative "name/index" unless defined? ::Unicode::Name::INDEX
-      INDEX[:NAMES][codepoint]
+      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 >= INDEX[:HANGUL][0][0] && codepoint <= INDEX[:HANGUL][0][1]
+        "HANGUL SYLLABLE-%.4X" % codepoint
+      else
+        nil
+      end
     end
     class << self; alias of unicode_name; end
 
@@ -16,7 +24,7 @@ module Unicode
       if correction = INDEX[:ALIASES][codepoint] && INDEX[:ALIASES][codepoint][:correction][-1]
         correction
       else
-        INDEX[:NAMES][codepoint]
+        unicode_name(char)
       end
     end
 

data/spec/unicode_name_spec.rb

@@ -9,6 +9,14 @@ describe Unicode::Name do
       assert_equal "REPLACEMENT CHARACTER", Unicode::Name.of("�")
     end
 
+    it "works for CJK Ideographs" do
+      assert_equal "CJK UNIFIED IDEOGRAPH-4E01", Unicode::Name.of("丁")
+    end
+
+    # it "works for Hangul Syllables" do
+    #   assert_equal "HANGUL SYLLABLE GAG", Unicode::Name.of("각")
+    # end
+
     it "will return nil for characters without name" do
       assert_equal nil, Unicode::Name.of("\u{10c50}")
       assert_equal nil, Unicode::Name.of("\0")

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unicode-name
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Jan Lelis
@@ -46,10 +46,12 @@ files:
 - README.md
 - Rakefile
 - data/name.marshal.gz
+- lib/unicode/.name.rb.swp
 - lib/unicode/name.rb
 - lib/unicode/name/constants.rb
 - lib/unicode/name/index.rb
 - lib/unicode/name/string_ext.rb
+- spec/.unicode_name_spec.rb.swp
 - spec/unicode_name_spec.rb
 - unicode-name.gemspec
 homepage: https://github.com/janlelis/unicode-name
@@ -77,5 +79,6 @@ signing_key:
 specification_version: 4
 summary: Returns name/aliases/label of a Unicode codepoint
 test_files:
+- spec/.unicode_name_spec.rb.swp
 - spec/unicode_name_spec.rb
 has_rdoc: