unicode-name 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 661337ed0ad17a4c57245aebb540a70e9c3cd348
-  data.tar.gz: 7906428802e6fe31f8718b99ebf0d655558e1410
+  metadata.gz: f3a8de48e9b0cde71e28b66a905775a415258861
+  data.tar.gz: ce9bb0b4e85c1b456ae79a62287ce0e48e4ba238
 SHA512:
-  metadata.gz: 6088029d191d4d4e3320a60e7603dd9a9467725b1c44d893063ed23a94cc7ba2a14348679664a211a8c5f5e2b0a6aa402d32822bcfa28e3c75443daf5cfb3626
-  data.tar.gz: a5b4076597eb6dc9a3e84066906256aa1ac214728c88293ea33aef7d02b79db15554d85f187b5f51af2075ff9daf74c6ea29e52df9494c23e18707ab6a1f5278
+  metadata.gz: 97265bf800a36c2207ae3e2bb74d24473ed91f399e726ae5e1136eacbbdf16be87007fd5fc277f3d0024e339f8c80adfc4c22160fc862c5bcb4a6bfb96b2e68e
+  data.tar.gz: 2a140e46907de2e489279970763b49d5b9ec87059b621af60338835ca69fec7097a02550ccd8d25c778e0ac8678cab38af04f36f681e4c293e1a35212d2e56b7

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 ## CHANGELOG
 
+### 1.1.0
+
+* Support codepoint labels
+
 ### 1.0.0
 
 * Inital release

data/README.md

@@ -1,6 +1,6 @@
 # Unicode::Name [![[version]](https://badge.fury.io/rb/unicode-name.svg)](http://badge.fury.io/rb/unicode-name)  [![[travis]](https://travis-ci.org/janlelis/unicode-name.png)](https://travis-ci.org/janlelis/unicode-name)
 
-Return Unicode character names and aliases.
+Return Unicode codepoint names, aliases, and labels.
 
 Unicode version: **8.0.0**
 
@@ -22,8 +22,21 @@ Unicode::Name.aliases "\t" # => {:control=>["CHARACTER TABULATION", "HORIZONTAL
 # Corrections (via .aliases[:correction], then name)
 Unicode::Name.correct "A" # => "LATIN CAPITAL LETTER A"
 Unicode::Name.correct "Ƣ" # => "LATIN CAPITAL LETTER GHA"
+
+# Codepoint labels
+Unicode::Name.label("\0") # => "<control-0000>"
+Unicode::Name.label("\u{D800}") # => "<surrogate-D800>"
+Unicode::Name.label("\u{FFFFF}") # => "<noncharacter-FFFFF>"
+Unicode::Name.label("\u{10C50}") # => "<reserved-10C50>"
+
+# Best readable representation
+Unicode::Name.readable("A") # => "LATIN CAPITAL LETTER A"
+Unicode::Name.readable("\0") # => "NULL"
+Unicode::Name.readable("\u{FFFFD}") # => "<private-use-FFFFD>"
 ```
 
+See [unicode-x](https://github.com/janlelis/unicode-x) for more Unicode related micro libraries.
+
 ## MIT License
 
 - Copyright (C) 2016 Jan Lelis <http://janlelis.com>. Released under the MIT license.

data/lib/unicode/name.rb

@@ -26,12 +26,11 @@ module Unicode
       INDEX[:ALIASES][codepoint]
     end
 
-=begin
     def self.label(char)
       codepoint = char.unpack("U")[0]
-      codepoint_pretty = codepoint.to_s(16).upcase
+      codepoint_pretty = "%.4X" % codepoint
       require_relative "name/index" unless defined? ::Unicode::Name::INDEX
-      require "unicode/types/index" unless defined? ::Unicode::Types::INDEX
+      require "unicode/types" unless defined? ::Unicode::Types
       case Unicode::Types.type(char)
       when "Graphic", "Format"
         nil
@@ -47,7 +46,6 @@ module Unicode
         "<reserved-#{codepoint_pretty}>"
       end
     end
-=end
 
     def self.readable(char)
       unicode_name(char) ||
@@ -55,8 +53,8 @@ module Unicode
       ( as[:control]      && as[:control][0]      ||
         as[:figment]      && as[:figment][0]      ||
         as[:alternate]    && as[:alternate][0]    ||
-        as[:abbreviation] && as[:abbreviation][0]  ) #||
-      # label(char)
+        as[:abbreviation] && as[:abbreviation][0]  ) ||
+      label(char)
     end
   end
 end

data/lib/unicode/name/constants.rb

@@ -1,6 +1,6 @@
 module Unicode
   module Name
-    VERSION = "1.0.0".freeze
+    VERSION = "1.1.0".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/spec/unicode_name_spec.rb

@@ -39,5 +39,41 @@ describe Unicode::Name do
       assert_equal ["NUL"], Unicode::Name.aliases("\0")[:abbreviation]
     end
   end
+
+  describe ".label" do
+    it "will return nil for usual (graphic) characters" do
+      assert_equal nil, Unicode::Name.label("A")
+    end
+
+    it "will return <control-hhhh> for control characters" do
+      assert_equal "<control-0000>", Unicode::Name.label("\0")
+    end
+
+    it "will return <private-use> for private use characters" do
+      assert_equal "<private-use-FFFFD>", Unicode::Name.label("\u{FFFFD}")
+    end
+
+    it "will return <surrogate-hhhh> for codepoints in surrogate area" do
+      assert_equal "<surrogate-D800>", Unicode::Name.label("\u{D800}")
+    end
+
+    it "will return <noncharacter-hhhh> for codepoints defined as noncharacter" do
+      assert_equal "<noncharacter-FFFFF>", Unicode::Name.label("\u{FFFFF}")
+    end
+
+    it "will return <reserved-hhhh> for unassigned codepoints" do
+      assert_equal "<reserved-10C50>", Unicode::Name.label("\u{10C50}")
+    end
+  end
+
+  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 "NULL", Unicode::Name.readable("\0")
+      assert_equal "<noncharacter-FFFFF>", Unicode::Name.readable("\u{FFFFF}")
+      assert_equal "<reserved-10C50>", Unicode::Name.readable("\u{10C50}")
+      assert_equal "<private-use-FFFFD>", Unicode::Name.readable("\u{FFFFD}")
+    end
+  end
 end
 

data/unicode-name.gemspec

@@ -5,8 +5,8 @@ require File.dirname(__FILE__) + "/lib/unicode/name/constants"
 Gem::Specification.new do |gem|
   gem.name          = "unicode-name"
   gem.version       = Unicode::Name::VERSION
-  gem.summary       = "Returns the name and aliases of a Unicode codepoint/character"
-  gem.description   = "[Unicode version: #{Unicode::Name::UNICODE_VERSION}] Returns the name and aliases of a Unicode codepoint/character"
+  gem.summary       = "Returns name/aliases/label of a Unicode codepoint"
+  gem.description   = "[Unicode version: #{Unicode::Name::UNICODE_VERSION}] Returns name/aliases/label of a Unicode codepoint"
   gem.authors       = ["Jan Lelis"]
   gem.email         = ["mail@janlelis.de"]
   gem.homepage      = "https://github.com/janlelis/unicode-name"
@@ -18,4 +18,5 @@ Gem::Specification.new do |gem|
   gem.require_paths = ["lib"]
 
   gem.required_ruby_version = "~> 2.0"
+  gem.add_dependency "unicode-types", "~> 1.0", ">= 1.0.1"
 end

metadata

@@ -1,16 +1,36 @@
 --- !ruby/object:Gem::Specification
 name: unicode-name
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-13 00:00:00.000000000 Z
-dependencies: []
-description: "[Unicode version: 8.0.0] Returns the name and aliases of a Unicode codepoint/character"
+date: 2016-04-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: unicode-types
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.1
+description: "[Unicode version: 8.0.0] Returns name/aliases/label of a Unicode codepoint"
 email:
 - mail@janlelis.de
 executables: []
@@ -30,7 +50,6 @@ files:
 - 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
@@ -56,8 +75,7 @@ rubyforge_project:
 rubygems_version: 2.6.3
 signing_key: 
 specification_version: 4
-summary: Returns the name and aliases of a Unicode codepoint/character
+summary: Returns name/aliases/label of a Unicode codepoint
 test_files:
-- spec/.unicode_name_spec.rb.swp
 - spec/unicode_name_spec.rb
 has_rdoc: