unicode-emoji 2.0.0 → 2.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 32bec9a0f826ab808cf77b3bf69e8248de000d99
-  data.tar.gz: 6c8a53dc8874ab6bf508aad2a914eded9a7a4889
+SHA256:
+  metadata.gz: 8d675646d8ef27dbc768ba3d6369e73517a02304fab8e3d347f19fd9547530fd
+  data.tar.gz: d51a73ac0f15a6157b54d10fc4f8abca20f77857ba713a646bf9830c286b7449
 SHA512:
-  metadata.gz: c5ebaf7c4c6a66331af9c0f927f8f41079aaf89d3389c4ba84533c1f64fbd2b4456657971e05c437987568c6853f844f1084986721cede6da8979696e4efffd6
-  data.tar.gz: 3fc8af7fc6bdcaac8ac14ec148c4322a8d26a1e627895ec54a3a038a85062c9f00d37317208cdbe876cdc31603e83943eac569ee937bccfd7e44df15d239ac19
+  metadata.gz: 49c0162a4784b3f67307e558fa40d64024f79c2a67c365e5dda05895249b2c3148a78d0021ecfcf29387583a3c738584dad5634ca1317eb48521cb6511755ae8
+  data.tar.gz: 5dddd9292e205b09330cd2adfc69e838b86cb96ee72b205b4aab2db860667b8e31ce7ea2e55d12dbf8f5b5f08097fa1ee2a51ffff3d5fcaa00f4aafa5f1729aa

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 ## CHANGELOG
 
+### 2.1.0
+
+- Add `REGEX_PICTO` which matches codepoints with the **Extended_Pictographic** property
+- Add `REGEX_PICTO_NO_EMOJI` which matches codepoints with the **Extended_Pictographic** property, but no **Emoji** property
+
 ### 2.0.0
 
 - Emoji 12.0 data (including valid subdivisions)

data/Gemfile

@@ -1,6 +1,7 @@
-source 'https://rubygems.org'
+source "https://rubygems.org"
 
 gemspec
 
-gem 'minitest'
-gem 'rake'
+gem "minitest"
+gem "rake"
+gem "irb"

data/README.md

@@ -89,6 +89,14 @@ Regex                         | Description | Example Matches | Example Non-Matc
 `Unicode::Emoji::REGEX_VALID_INCLUDE_TEXT` | `REGEX_VALID` + `REGEX_TEXT` | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`, `😴︎`, `▶` | `🏻`, `🇵🇵`
 `Unicode::Emoji::REGEX_WELL_FORMED_INCLUDE_TEXT` | `REGEX_WELL_FORMED` + `REGEX_TEXT` | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`,  `🇵🇵`, `😴︎`, `▶` | `🏻`
 
+#### Extended Pictographic Regex
+
+`Unicode::Emoji::REGEX_PICTO` matches single codepoints with the **Extended_Pictographic** property. For example, it will match `✀` BLACK SAFETY SCISSORS.
+
+`Unicode::Emoji::REGEX_PICTO_NO_EMOJI` matches single codepoints with the **Extended_Pictographic** property, but excludes Emoji characters.
+
+See [character.construction/picto](https://character.construction/picto) for a list of all non-Emoji pictographic characters.
+
 #### Partial Regexes
 
 Matches potential Emoji parts (often, this is not what you want):
@@ -115,7 +123,7 @@ Unicode::Emoji.list("Food & Drink", "food-asian")
 
 Please note that categories might change with future versions of the Emoji standard. This gem will issue warnings when attemting to retrieve old categories using the `#list` method.
 
-A markdown file with all recommended Emoji can be found [in this gist](https://gist.github.com/janlelis/72f9be1f0ecca07372c64cf13894b801).
+A list of all Emoji can be found at [character.construction](https://character.construction).
 
 ### Properties
 

data/lib/unicode/emoji.rb

@@ -29,8 +29,9 @@ module Unicode
     EMOJI_COMPONENT               = INDEX[:PROPERTIES].select{ |ord, props| props.include?(:C) }.keys.freeze
     EMOJI_MODIFIER_BASES          = INDEX[:PROPERTIES].select{ |ord, props| props.include?(:B) }.keys.freeze
     EMOJI_MODIFIERS               = INDEX[:PROPERTIES].select{ |ord, props| props.include?(:M) }.keys.freeze
-    # Not needed right now:
-    # EXTENDED_PICTOGRAPHIC         = INDEX[:PROPERTIES].select{ |ord, props| props.include?(:X) }.keys.freeze
+
+    EXTENDED_PICTOGRAPHIC         = INDEX[:PROPERTIES].select{ |ord, props| props.include?(:X) }.keys.freeze
+    EXTENDED_PICTOGRAPHIC_NO_EMOJI= INDEX[:PROPERTIES].select{ |ord, props| props.include?(:X) && !props.include?(:E) }.keys.freeze
     EMOJI_KEYCAPS                 = INDEX[:KEYCAPS].freeze
     VALID_REGION_FLAGS            = INDEX[:FLAGS].freeze
     VALID_SUBDIVISIONS            = INDEX[:SD].freeze
@@ -53,12 +54,16 @@ module Unicode
       emoji_modifier_base = "\\p{Emoji Modifier Base}"
       emoji_component     = "\\p{Emoji Component}"
       emoji_presentation  = "\\p{Emoji Presentation}"
+      picto               = "\\p{Extended Pictographic}"
+      picto_no_emoji      = "\\p{Extended Pictographic}(?<!\\p{Emoji})"
     else
       emoji_character     = pack_and_join[EMOJI_CHAR]
       emoji_modifier      = pack_and_join[EMOJI_MODIFIERS]
       emoji_modifier_base = pack_and_join[EMOJI_MODIFIER_BASES]
       emoji_component     = pack_and_join[EMOJI_COMPONENT]
       emoji_presentation  = pack_and_join[EMOJI_PRESENTATION]
+      picto               = pack_and_join[EXTENDED_PICTOGRAPHIC]
+      picto_no_emoji      = pack_and_join[EXTENDED_PICTOGRAPHIC_NO_EMOJI]
     end
 
     emoji_presentation_sequence = \
@@ -196,6 +201,14 @@ module Unicode
     REGEX_VALID_INCLUDE_TEXT = Regexp.union(REGEX_VALID, REGEX_TEXT)
     REGEX_WELL_FORMED_INCLUDE_TEXT = Regexp.union(REGEX_WELL_FORMED, REGEX_TEXT)
 
+    REGEX_PICTO = Regexp.compile(
+      picto
+    )
+
+    REGEX_PICTO_NO_EMOJI = Regexp.compile(
+      picto_no_emoji
+    )
+
     def self.properties(char)
       ord = get_codepoint_value(char)
       props = INDEX[:PROPERTIES][ord]

data/lib/unicode/emoji/constants.rb

@@ -2,10 +2,10 @@
 
 module Unicode
   module Emoji
-    VERSION = "2.0.0".freeze
-    EMOJI_VERSION = "12.0".freeze
-    DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + '/../../../data/').freeze
-    INDEX_FILENAME = (DATA_DIRECTORY + '/emoji.marshal.gz').freeze
+    VERSION = "2.1.0"
+    EMOJI_VERSION = "12.0"
+    DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/").freeze
+    INDEX_FILENAME = (DATA_DIRECTORY + "/emoji.marshal.gz").freeze
 
     ENABLE_NATIVE_EMOJI_UNICODE_PROPERTIES = false # As of Ruby 2.6.1, Emoji version 11 is included
   end

data/spec/unicode_emoji_spec.rb

@@ -4,8 +4,8 @@ require "minitest/autorun"
 describe Unicode::Emoji do
   describe ".properties" do
     it "returns an Array for Emoji properties if has codepoints" do
-      assert_equal ["Emoji", "Emoji_Presentation"], Unicode::Emoji.properties("😴")
-      assert_equal ["Emoji"], Unicode::Emoji.properties("♠")
+      assert_equal ["Emoji", "Emoji_Presentation", "Extended_Pictographic"], Unicode::Emoji.properties("😴")
+      assert_equal ["Emoji", "Extended_Pictographic"], Unicode::Emoji.properties("♠")
     end
 
     it "returns nil for Emoji properties if has no codepoints" do
@@ -380,6 +380,20 @@ describe Unicode::Emoji do
     end
   end
 
+  describe "REGEX_PICTO" do
+    it "matches codepoints with Extended_Pictograph property (almost all emoji are, but also others)" do
+      matches = "U+1F32D 🌭 HOT DOG, U+203C ‼ DOUBLE EXCLAMATION MARK, U+26E8 ⛨ BLACK CROSS ON SHIELD".scan(Unicode::Emoji::REGEX_PICTO)
+      assert_equal ["🌭", "‼", "⛨"], matches
+    end
+  end
+
+  describe "REGEX_PICTO" do
+    it "matches codepoints with Extended_Pictograph property, but no Emoji property" do
+      matches = "U+1F32D 🌭 HOT DOG, U+203C ‼ DOUBLE EXCLAMATION MARK, U+26E8 ⛨ BLACK CROSS ON SHIELD".scan(Unicode::Emoji::REGEX_PICTO_NO_EMOJI)
+      assert_equal ["⛨"], matches
+    end
+  end
+
   describe ".list" do
     it "returns a grouped list of emoji" do
       assert_includes Unicode::Emoji.list.keys, "Smileys & Emotion"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-emoji
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.1.0
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-02-19 00:00:00.000000000 Z
+date: 2019-03-11 00:00:00.000000000 Z
 dependencies: []
 description: "[Emoji 12.0] Retrieve emoji data about Unicode codepoints. Also contains
   a regex to match emoji."
@@ -52,8 +52,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: Retrieve Emoji data about Unicode codepoints.