unicode-display_width 1.1.3 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 139f5127ef080149e50f2156bda03d18748cc384
-  data.tar.gz: 483e9a3386cb9b2c7f67568fb9c9b3570a8f5556
+  metadata.gz: dc469a91d5eda226bed21bce0669da6fa9e5d064
+  data.tar.gz: 5b376806fdd80debc0e1baa8694f0ef1eb697ca2
 SHA512:
-  metadata.gz: ccdd24ab36d9077cdd808ade6e44cc67fcf5c1180eab122a80ecef5aae1adf2439996701dff84d7224fb4f48d5e0ef9a8de70a97a0b7c9395afd1f5cea756ae3
-  data.tar.gz: 4431ed8b567006bda9418af105d666b2050845cb486b75e465990633d0ca395574fa7f2d66e7f0bdc69875bfc35f156a5f622a1e4d82ffa1149b260d46cf7044
+  metadata.gz: 63022c8bd0776c973347dcb3ccbf0a3c79610134f20ea82fd0832b2143517e492bd56f11564a5639c8a88136bf402abde808ae90b0a79a4ea2ff14020f36d496
+  data.tar.gz: 6765c915c17a1cd7a13c9fad7a4fbc6621a99e8c119b148f4a10fd33b4c3b81cf45a2eed2a54fafc6f36c6d268650e68d67740d04190281568b5f87ebb57e9f1

data/CHANGELOG.txt

@@ -1,5 +1,12 @@
 # CHANGELOG
 
+## 1.2.0
+
+- Add zero-width codepoint ranges: U+2060..U+206F, U+FFF0..U+FFF8, U+E0000..U+E0FFF
+- Add full-witdh codepoint ranges: U+3400..U+4DBF, U+4E00..U+9FFF, U+F900..U+FAFF, U+20000..U+2FFFD, U+30000..U+3FFFD
+- Experimental emoji support using the [unicode-emoji](https://github.com/janlelis/unicode-emoji) gem
+- Fix minor bug in index compression scheme
+
 ## 1.1.3
 
 - Fix that non-UTF-8 encodings do not throw errors, patch by @windwiny

data/README.md

@@ -22,7 +22,9 @@ X      | (user defined)               | Overwrites any other values
 3      | `"\u{2E3B}"`                 | THREE-EM DASH
 0      | General Categories: Mn, Me, Cf (non-arabic) | Excludes ARABIC format characters
 0      | `"\u{1160}".."\u{11FF}"`     | HANGUL JUNGSEONG
+0      | `"\u{2060}".."\u{206F}"`, `"\u{FFF0}".."\u{FFF8}"`, `"\u{E0000}".."\u{E0FFF}"` | Ignorable ranges
 2      | East Asian Width: F, W       | Full-width characters
+2      | `"\u{3400}"`..`"\u{4DBF}"`, `"\u{4E00}"`..`"\u{9FFF}"`, `"\u{F900}"`..`"\u{FAFF}"`, `"\u{20000}"`..`"\u{2FFFD}"`, `"\u{30000}"`..`"\u{3FFFD}"` | Full-width ranges
 1 or 2 | East Asian Width: A          | Ambiguous characters, user defined, default: 1
 1      | All other codepoints         | -
 
@@ -62,6 +64,22 @@ You can overwrite how to handle specific code points by passing a hash (or even
 Unicode::DisplayWidth.of("a\tb", 1, 0x09 => 10)) # => 12
 ```
 
+### Emoji Support
+
+Experimental emoji support is included. It will adjust the string's size for modifier and zero-width joiner sequences. You will need to add the [unicode-emoji](https://github.com/janlelis/unicode-emoji) gem to your Gemfile:
+
+```ruby
+gem 'unicode-display_width'
+gem 'unicode-emoji'
+```
+
+You can then activate the emoji string width adjustments by passing `emoji: true` as fourth parameter:
+
+```ruby
+Unicode::DisplayWidth.of "🤾🏽‍♀️" # => 5
+Unicode::DisplayWidth.of "🤾🏽‍♀️", 1, {}, emoji: true # => 2
+```
+
 ### Usage with String Extension
 
 Activated by default. Will be deactivated in version 2.0:

data/Rakefile

@@ -37,6 +37,7 @@ desc "#{gemspec.name} | Test"
 task :test do
   sh "rspec spec"
 end
+task :spec => :test
 task :default => :test
 
 # # #

data/lib/unicode/display_width.rb

@@ -5,7 +5,7 @@ module Unicode
   module DisplayWidth
     DEPTHS = [0x10000, 0x1000, 0x100, 0x10].freeze
 
-    def self.of(string, ambiguous = 1, overwrite = {})
+    def self.of(string, ambiguous = 1, overwrite = {}, options = {})
       res = string.codepoints.inject(0){ |total_width, codepoint|
         index_or_value = INDEX
         codepoint_depth_offset = codepoint
@@ -19,8 +19,27 @@ module Unicode
         total_width + (overwrite[codepoint] || width || 1)
       }
 
+      res -= emoji_extra_width_of(string) if options[:emoji]
       res < 0 ? 0 : res
     end
+
+    def self.emoji_extra_width_of(string, ambiguous = 1, overwrite = {}, _ = {})
+      require "unicode/emoji"
+
+      extra_width = 0
+      modifier_regex = /[#{ Unicode::Emoji::EMOJI_MODIFIERS.pack("U*") }]/
+      zwj_regex = /(?<=#{ [Unicode::Emoji::ZWJ].pack("U") })./
+
+      string.scan(Unicode::Emoji::REGEX){ |emoji|
+        extra_width += 2 * emoji.match(modifier_regex).size
+
+        emoji.scan(zwj_regex){ |zwj_succ|
+          extra_width += self.of(zwj_succ, ambiguous, overwrite)
+        }
+      }
+
+      extra_width
+    end
   end
 end
 

data/lib/unicode/display_width/constants.rb

@@ -1,6 +1,6 @@
 module Unicode
   module DisplayWidth
-    VERSION = '1.1.3'
+    VERSION = '1.2.0'
     UNICODE_VERSION = "9.0.0".freeze
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + '/../../../data/').freeze
     INDEX_FILENAME = (DATA_DIRECTORY + '/display_width.marshal.gz').freeze

data/lib/unicode/display_width/string_ext.rb

@@ -1,8 +1,8 @@
 require_relative '../display_width' unless defined? Unicode::DisplayWidth
 
 class String
-  def display_width(ambiguous = 1, overwrite = {})
-    Unicode::DisplayWidth.of(self, ambiguous, overwrite)
+  def display_width(ambiguous = 1, overwrite = {}, options = {})
+    Unicode::DisplayWidth.of(self, ambiguous, overwrite, options)
   end
 
   def display_size(*args)

data/spec/display_width_spec.rb

@@ -1,6 +1,4 @@
-# coding: utf-8
-
-require 'unicode/display_width'
+require_relative '../lib/unicode/display_width'
 
 describe 'Unicode::DisplayWidth.of' do
   describe '[east asian width]' do
@@ -12,6 +10,10 @@ describe 'Unicode::DisplayWidth.of' do
       expect( '一'.display_width ).to eq 2
     end
 
+    it 'returns 2 for W (which are currently unassigned)' do
+      expect( "\u{3FFFD}".display_width ).to eq 2
+    end
+
     it 'returns 1 for N' do
       expect( 'À'.display_width ).to eq 1
     end
@@ -53,6 +55,18 @@ describe 'Unicode::DisplayWidth.of' do
     it 'returns 0 for HANGUL JUNGSEONG chars' do
       expect( 'ᅠ'.display_width ).to eq 0
     end
+
+    it 'returns 0 for U+2060..U+206F' do
+      expect( "\u{2060}".display_width ).to eq 0
+    end
+
+    it 'returns 0 for U+FFF0..U+FFF8' do
+      expect( "\u{FFF0}".display_width ).to eq 0
+    end
+
+    it 'returns 0 for U+E0000..U+E0FFF' do
+      expect( "\u{E0000}".display_width ).to eq 0
+    end
   end
 
   describe '[special characters]' do
@@ -129,4 +143,10 @@ describe 'Unicode::DisplayWidth.of' do
       expect( 'À'.encode("UTF-16LE").display_width ).to eq 1
     end
   end
+
+  describe '[emoji]' do
+    it 'does not count modifiers and zjw sequences for valid emoji' do
+      expect( "🤾🏽‍♀️".display_width(1, {}, emoji: true) ).to eq 2
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-display_width
 version: !ruby/object:Gem::Version
-  version: 1.1.3
+  version: 1.2.0
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-01-13 00:00:00.000000000 Z
+date: 2017-04-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec