unicode-emoji 1.1.0 → 2.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA256:
-  metadata.gz: c6cdca65a25735347a97f077a43c00b1b30c84fa2aa7b688b7072b1af8624d1f
-  data.tar.gz: e083a936a9f360ca0348fe6a3f76a12aa2fbf94826cbf30fd31db1abc23d9bc7
+SHA1:
+  metadata.gz: 32bec9a0f826ab808cf77b3bf69e8248de000d99
+  data.tar.gz: 6c8a53dc8874ab6bf508aad2a914eded9a7a4889
 SHA512:
-  metadata.gz: d408fec5b09dd66db4ea61fb476cd5c74570d1cd9f43451732619ea303292afeb28e7d65d56eb012676ecbd2bda61e4e03912f3fae66bb26f51abde5ff85ba6b
-  data.tar.gz: 815d375a3de1d1cbedb64ced2530ee2c9c02a52223ced9bff0273231f8de09a135b7043f6159701c76af60046234b353ec14a5ae136aad36f998560e96988841
+  metadata.gz: c5ebaf7c4c6a66331af9c0f927f8f41079aaf89d3389c4ba84533c1f64fbd2b4456657971e05c437987568c6853f844f1084986721cede6da8979696e4efffd6
+  data.tar.gz: 3fc8af7fc6bdcaac8ac14ec148c4322a8d26a1e627895ec54a3a038a85062c9f00d37317208cdbe876cdc31603e83943eac569ee937bccfd7e44df15d239ac19

data/.travis.yml

@@ -2,12 +2,13 @@ sudo: false
 language: ruby
 
 rvm:
+- 2.6.1
+- 2.5.3
+- 2.4.5
+- 2.3.8
 - ruby-head
-- 2.5.1
-- 2.4.4
-- 2.3.7
 - jruby-head
-- jruby-9.1.16.0
+- jruby-9.2.6.0
 
 matrix:
   allow_failures:

data/CHANGELOG.md

@@ -1,5 +1,14 @@
 ## CHANGELOG
 
+### 2.0.0
+
+- Emoji 12.0 data (including valid subdivisions)
+- Introduce new `REGEX_WELL_FORMED` to be able to match for invalid tag and region sequences
+- Introduce new `*_INCLUDE_TEXT` regexes which include matching for textual presentation emoji
+- Refactoring: Update Emoji matching to latest standard while keeping naming close to standard
+- Issue warning when using `#list` method to retrieve outdated category
+- Change matching for ZWJ sequences: Do not limit sequence to a maximum of 3 ZWJs
+
 ### 1.1.0
 
 - Emoji 11.0

data/MIT-LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2017, 2018 Jan Lelis, mail@janlelis.de
+Copyright (c) 2017-2019 Jan Lelis, mail@janlelis.de
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

data/README.md

@@ -1,12 +1,12 @@
-# Unicode::Emoji [![[version]](https://badge.fury.io/rb/unicode-emoji.svg)](http://badge.fury.io/rb/unicode-emoji)  [![[travis]](https://travis-ci.org/janlelis/unicode-emoji.svg)](https://travis-ci.org/janlelis/unicode-emoji)
+# Unicode::Emoji [![[version]](https://badge.fury.io/rb/unicode-emoji.svg)](https://badge.fury.io/rb/unicode-emoji)  [![[travis]](https://travis-ci.org/janlelis/unicode-emoji.svg)](https://travis-ci.org/janlelis/unicode-emoji)
 
 A small Ruby library which provides Unicode Emoji data and regexes.
 
 Also includes a categorized list of recommended Emoji.
 
-Emoji version: **11.0**
+Emoji version: **12.0** (February 2018)
 
-Supported Rubies: **2.5**, **2.4**, **2.3**
+Supported Rubies: **2.6**, **2.5**, **2.4**, **2.3**
 
 If you are stuck on an older Ruby version, checkout the latest [0.9 version](https://rubygems.org/gems/unicode-emoji/versions/0.9.3) of this gem.
 
@@ -20,7 +20,7 @@ gem "unicode-emoji"
 
 ### Regex
 
-Five Emoji regexes are included, which are compiled out of various Emoji Unicode data.
+The gem includes a bunch of Emoji regexes, which are compiled out of various Emoji Unicode data sources.
 
 ```ruby
 require "unicode/emoji"
@@ -40,16 +40,64 @@ string = "String which contains all kinds of emoji:
 string.scan(Unicode::Emoji::REGEX) # => ["😴", "▶️", "🛌🏽", "🇵🇹", "🏴󠁧󠁢󠁳󠁣󠁴󠁿", "2️⃣", "🤾🏽‍♀️"]
 ```
 
+#### Main Regexes
+
+Matches (non-textual) Emoji of all kinds:
+
 Regex                         | Description | Example Matches | Example Non-Matches
 ------------------------------|-------------|-----------------|--------------------
-`Unicode::Emoji::REGEX`       | Matches (non-textual) singleton Emoji (except for singleton components, like a skin tone modifier without base Emoji) and all kind of valid Emoji sequences, but restrict ZWJ and TAG sequences to recommended sequences | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🤾🏽‍♀️` | `😴︎`, `▶`, `🏻`, `🇵🇵`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤠‍🤢`
-`Unicode::Emoji::REGEX_VALID` | Matches (non-textual) singleton Emoji (except for singleton components, like a skin tone modifier without base Emoji) and all kind of valid Emoji sequences | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢` | `😴︎`, `▶`, `🏻`, `🇵🇵`
-`Unicode::Emoji::REGEX_BASIC` | Matches (non-textual) singleton Emoji (except for singleton components, like a skin tone modifier without base Emoji), but no sequences | `😴`, `▶️` | `😴︎`, `▶`, `🏻`, `🛌🏽`, `🇵🇹`, `🇵🇵`,`2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`
-`Unicode::Emoji::REGEX_TEXT`  | Matches only textual singleton Emoji (except for singleton components, like digit 1) | `😴︎`, `▶` | `😴`, `▶️`, `🏻`, `🛌🏽`, `🇵🇹`, `🇵🇵`,`2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`
-`Unicode::Emoji::REGEX_ANY`   | Matches any Emoji-related codepoint (but no variation selectors or tags) | `😴`, `▶`, `🏻`, `🛌`, `🏽`, `🇵`, `🇹`, `2`, `🏴`, `🤾`, `♀`, `🤠`, `🤢` | -
+`Unicode::Emoji::REGEX`       | **Use this if unsure!** Matches (non-textual) singleton Emoji (except for singleton components, like a skin tone modifier without base Emoji) and all kind of *recommended* Emoji sequences | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🤾🏽‍♀️` | `😴︎`, `▶`, `🏻`, `🇵🇵`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤠‍🤢`
+`Unicode::Emoji::REGEX_VALID` | Matches (non-textual) singleton Emoji (except for singleton components, like a skin tone modifier without base Emoji) and all kind of *valid* Emoji sequences | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢` | `😴︎`, `▶`, `🏻`, `🇵🇵`
+`Unicode::Emoji::REGEX_WELL_FORMED` | Matches (non-textual) singleton Emoji (except for singleton components, like a skin tone modifier without base Emoji) and all kind of *well-formed* Emoji sequences | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`,  `🇵🇵` | `😴︎`, `▶`, `🏻`
+
+##### Picking the Right Emoji Regex
+
+- Usually you just want `REGEX` (RGI set)
+- If you want broader matching (e.g. more sub-regions), choose `REGEX_VALID`
+- If you even want to match for invalid sequences, too, use `REGEX_WELL_FORMED`
+
+Please see [the standard](http://www.unicode.org/reports/tr51/#Emoji_Sets) for details.
+
+Property | `REGEX` (RGI / Recommended) | `REGEX_VALID` (Valid) | `REGEX_WELL_FORMED` (Well-formed)
+---------|-----------------------------|-----------------------|----------------------------------
+Region "🇵🇹"                    | Yes | Yes | Yes
+Region "🇵🇵"                   | No  | No  | Yes
+Tag Sequence "🏴󠁧󠁢󠁳󠁣󠁴󠁿"              | Yes | Yes | Yes
+Tag Sequence "🏴󠁧󠁢󠁡󠁧󠁢󠁿"              | No  | Yes | Yes
+Tag Sequence "😴󠁧󠁢󠁡󠁡󠁡󠁿"              | No  | No  | Yes
+ZWJ Sequence "🤾🏽‍♀️"           | Yes | Yes | Yes
+ZWJ Sequence "🤠‍🤢"            | No  | Yes | Yes
 
 More info about valid vs. recommended Emoji in this [blog article on Emojipedia](http://blog.emojipedia.org/unicode-behind-the-curtain/).
 
+#### Singleton Regexes
+
+Matches only simple one-codepoint (+ optional variation selector) Emoji:
+
+Regex                         | Description | Example Matches | Example Non-Matches
+------------------------------|-------------|-----------------|--------------------
+`Unicode::Emoji::REGEX_BASIC` | Matches (non-textual) singleton Emoji (except for singleton components, like a skin tone modifier without base Emoji), but no sequences at all | `😴`, `▶️` | `😴︎`, `▶`, `🏻`, `🛌🏽`, `🇵🇹`, `🇵🇵`,`2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`
+`Unicode::Emoji::REGEX_TEXT`  | Matches only textual singleton Emoji (except for singleton components, like digit 1) | `😴︎`, `▶` | `😴`, `▶️`, `🏻`, `🛌🏽`, `🇵🇹`, `🇵🇵`,`2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`
+
+#### Include Textual Emoji
+
+By default, textual Emoji (emoji characters with text variation selector or those that have a default text presentation) will not be included in the default regexes. However, if you wish to match for them too, you can include them in your regex by appending the `_INCLUDE_TEXT` suffix:
+
+Regex                         | Description | Example Matches | Example Non-Matches
+------------------------------|-------------|-----------------|--------------------
+`Unicode::Emoji::REGEX_INCLUDE_TEXT`       | `REGEX` + `REGEX_TEXT` | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🤾🏽‍♀️`, `😴︎`, `▶` | `🏻`, `🇵🇵`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤠‍🤢`
+`Unicode::Emoji::REGEX_VALID_INCLUDE_TEXT` | `REGEX_VALID` + `REGEX_TEXT` | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`, `😴︎`, `▶` | `🏻`, `🇵🇵`
+`Unicode::Emoji::REGEX_WELL_FORMED_INCLUDE_TEXT` | `REGEX_WELL_FORMED` + `REGEX_TEXT` | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤠‍🤢`,  `🇵🇵`, `😴︎`, `▶` | `🏻`
+
+#### Partial Regexes
+
+Matches potential Emoji parts (often, this is not what you want):
+
+Regex                         | Description | Example Matches | Example Non-Matches
+------------------------------|-------------|-----------------|--------------------
+`Unicode::Emoji::REGEX_ANY`   | Matches any Emoji-related codepoint (but no variation selectors, tags, or zero-width joiners). Please not that this will match Emoji-parts rather than complete Emoji, for example, single digits! | `😴`, `▶`, `🏻`, `🛌`, `🏽`, `🇵`, `🇹`, `2`, `🏴`, `🤾`, `♀`, `🤠`, `🤢` | -
+
+
 ### List
 
 Use `Unicode::Emoji::LIST` or the list method to get a grouped (and ordered) list of Emoji:
@@ -65,6 +113,8 @@ Unicode::Emoji.list("Food & Drink", "food-asian")
 => ["🍱", "🍘", "🍙", "🍚", "🍛", "🍜", "🍝", "🍠", "🍢", "🍣", "🍤", "🍥", "🍡", "\u{1F95F}", "\u{1F960}", "\u{1F961}"]
 ```
 
+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).
 
 ### Properties
@@ -87,5 +137,5 @@ Unicode::Emoji.properties "☝" # => ["Emoji", "Emoji_Modifier_Base"]
 
 ## MIT
 
-- Copyright (C) 2017, 2018 Jan Lelis <http://janlelis.com>. Released under the MIT license.
+- Copyright (C) 2017-2019 Jan Lelis <http://janlelis.com>. Released under the MIT license.
 - Unicode data: http://www.unicode.org/copyright.html#Exhibit1

data/lib/unicode/emoji.rb

@@ -18,8 +18,10 @@ module Unicode
     TEXT_VARIATION_SELECTOR       = 0xFE0E
     EMOJI_TAG_BASE_FLAG           = 0x1F3F4
     CANCEL_TAG                    = 0xE007F
+    TAGS                          = [*0xE0020..0xE007E]
     EMOJI_KEYCAP_SUFFIX           = 0x20E3
     ZWJ                           = 0x200D
+    REGIONAL_INDICATORS           = [*0x1F1E6..0x1F1FF]
 
     EMOJI_CHAR                    = INDEX[:PROPERTIES].select{ |ord, props| props.include?(:E) }.keys.freeze
     EMOJI_PRESENTATION            = INDEX[:PROPERTIES].select{ |ord, props| props.include?(:P) }.keys.freeze
@@ -36,6 +38,10 @@ module Unicode
     RECOMMENDED_ZWJ_SEQUENCES     = INDEX[:ZWJ].freeze
 
     LIST                          = INDEX[:LIST].freeze.each_value(&:freeze)
+    LIST_REMOVED_KEYS             = [
+      "Smileys & People",
+      "Component",
+    ]
 
     pack = ->(ord){ Regexp.escape(Array(ord).pack("U*")) }
     join = -> (*strings){ "(?:" + strings.join("|") + ")" }
@@ -61,6 +67,9 @@ module Unicode
         emoji_presentation + "(?!" + pack[TEXT_VARIATION_SELECTOR] + ")" + pack[EMOJI_VARIATION_SELECTOR] + "?",
       ]
 
+    non_component_emoji_presentation_sequence = \
+      "(?!" + emoji_component + ")" + emoji_presentation_sequence
+
     text_presentation_sequence = \
       join[
         pack_and_join[TEXT_PRESENTATION]+ "(?!" + join[emoji_modifier, pack[EMOJI_VARIATION_SELECTOR]] + ")" + pack[TEXT_VARIATION_SELECTOR] + "?",
@@ -73,9 +82,36 @@ module Unicode
     emoji_keycap_sequence = \
       pack_and_join[EMOJI_KEYCAPS] + pack[[EMOJI_VARIATION_SELECTOR, EMOJI_KEYCAP_SUFFIX]]
 
-    emoji_valid_region_sequence = \
+    emoji_valid_flag_sequence = \
       pack_and_join[VALID_REGION_FLAGS]
 
+    emoji_well_formed_flag_sequence = \
+      "(?:" +
+        pack_and_join[REGIONAL_INDICATORS] +
+        pack_and_join[REGIONAL_INDICATORS] +
+      ")"
+
+    emoji_valid_core_sequence = \
+      join[
+        # emoji_character,
+        emoji_keycap_sequence,
+        emoji_modifier_sequence,
+        non_component_emoji_presentation_sequence,
+        emoji_valid_flag_sequence,
+      ]
+
+    emoji_well_formed_core_sequence = \
+      join[
+        # emoji_character,
+        emoji_keycap_sequence,
+        emoji_modifier_sequence,
+        non_component_emoji_presentation_sequence,
+        emoji_well_formed_flag_sequence,
+      ]
+
+    emoji_rgi_tag_sequence = \
+      pack_and_join[RECOMMENDED_SUBDIVISION_FLAGS]
+
     emoji_valid_tag_sequence = \
       "(?:" +
         pack[EMOJI_TAG_BASE_FLAG] +
@@ -83,35 +119,60 @@ module Unicode
         pack[CANCEL_TAG] +
       ")"
 
-    emoji_zwj_element = \
+    emoji_well_formed_tag_sequence = \
+      "(?:" +
+        join[
+          non_component_emoji_presentation_sequence,
+          emoji_modifier_sequence,
+        ] +
+        pack_and_join[TAGS] + "+" +
+        pack[CANCEL_TAG] +
+      ")"
+
+    emoji_rgi_zwj_sequence = \
+      pack_and_join[RECOMMENDED_ZWJ_SEQUENCES]
+
+    emoji_valid_zwj_element = \
       join[
         emoji_modifier_sequence,
         emoji_presentation_sequence,
         emoji_character,
       ]
 
-    # Matches basic singleton emoji and all kind of sequences, but restrict zwj and tag sequences to known sequences
-    REGEX = Regexp.compile(
-      pack_and_join[RECOMMENDED_ZWJ_SEQUENCES] +
-      ?| + pack_and_join[RECOMMENDED_SUBDIVISION_FLAGS] +
-      ?| + emoji_modifier_sequence +
-      ?| + "(?!" + emoji_component + ")" + emoji_presentation_sequence +
-      ?| + emoji_keycap_sequence +
-      ?| + emoji_valid_region_sequence  +
-      ""
-    )
+    emoji_valid_zwj_sequence = \
+      "(?:" +
+        "(?:" + emoji_valid_zwj_element + pack[ZWJ] + ")+" + emoji_valid_zwj_element +
+      ")"
+
+    emoji_rgi_sequence = \
+      join[
+        emoji_rgi_zwj_sequence,
+        emoji_rgi_tag_sequence,
+        emoji_valid_core_sequence,
+      ]
+
+    emoji_valid_sequence = \
+      join[
+        emoji_valid_zwj_sequence,
+        emoji_valid_tag_sequence,
+        emoji_valid_core_sequence,
+      ]
+
+    emoji_well_formed_sequence = \
+      join[
+        emoji_valid_zwj_sequence,
+        emoji_well_formed_tag_sequence,
+        emoji_well_formed_core_sequence,
+      ]
+
+    # Matches basic singleton emoji and all kind of sequences, but restrict zwj and tag sequences to known sequences (rgi)
+    REGEX = Regexp.compile(emoji_rgi_sequence)
 
     # Matches basic singleton emoji and all kind of valid sequences
-    REGEX_VALID = Regexp.compile(
-      # EMOJI_TAGS.map{ |base, spec| "(?:" + pack[base] + "[" + pack[spec] + "]+" + pack[CANCEL_TAG] + ")" }.join("|") +
-      emoji_valid_tag_sequence +
-      ?| + "(?:" + "(?:" + emoji_zwj_element + pack[ZWJ] + "){1,3}" + emoji_zwj_element + ")" +
-      ?| + emoji_modifier_sequence +
-      ?| + "(?!" + emoji_component + ")" + emoji_presentation_sequence +
-      ?| + emoji_keycap_sequence +
-      ?| + emoji_valid_region_sequence +
-      ""
-    )
+    REGEX_VALID = Regexp.compile(emoji_valid_sequence)
+
+    # Matches basic singleton emoji and all kind of sequences
+    REGEX_WELL_FORMED = Regexp.compile(emoji_well_formed_sequence)
 
     # Matches only basic single, non-textual emoji
     # Ignores "components" like modifiers or simple digits
@@ -125,11 +186,16 @@ module Unicode
       "(?!" + emoji_component + ")" + text_presentation_sequence
     )
 
-    # Matches any emoji-related codepoint
+    # Matches any emoji-related codepoint - Use with caution (returns partil matches)
     REGEX_ANY = Regexp.compile(
       emoji_character
     )
 
+    # Combined REGEXes which also match for TEXTUAL emoji
+    REGEX_INCLUDE_TEXT = Regexp.union(REGEX, REGEX_TEXT)
+    REGEX_VALID_INCLUDE_TEXT = Regexp.union(REGEX_VALID, REGEX_TEXT)
+    REGEX_WELL_FORMED_INCLUDE_TEXT = Regexp.union(REGEX_WELL_FORMED, REGEX_TEXT)
+
     def self.properties(char)
       ord = get_codepoint_value(char)
       props = INDEX[:PROPERTIES][ord]
@@ -143,6 +209,9 @@ module Unicode
 
     def self.list(key = nil, sub_key = nil)
       return LIST unless key || sub_key
+      if LIST_REMOVED_KEYS.include?(key)
+        $stderr.puts "Warning(unicode-emoji): The category of #{key} does not exist anymore"
+      end
       LIST.dig(*[key, sub_key].compact)
     end
 

data/lib/unicode/emoji/constants.rb

@@ -2,12 +2,12 @@
 
 module Unicode
   module Emoji
-    VERSION = "1.1.0".freeze
-    EMOJI_VERSION = "11.0".freeze
+    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
 
-    ENABLE_NATIVE_EMOJI_UNICODE_PROPERTIES = false
+    ENABLE_NATIVE_EMOJI_UNICODE_PROPERTIES = false # As of Ruby 2.6.1, Emoji version 11 is included
   end
 end
 

data/spec/unicode_emoji_spec.rb

@@ -158,7 +158,7 @@ describe Unicode::Emoji do
 
     it "does not match invalid tag sequences" do
       "🏴󠁧󠁢󠁡󠁡󠁡󠁿 GB AAA" =~ Unicode::Emoji::REGEX_VALID
-      assert_equal "🏴", $&
+      assert_equal "🏴", $& # only base flag is matched
     end
 
     it "matches recommended zwj sequences" do
@@ -172,6 +172,88 @@ describe Unicode::Emoji do
     end
   end
 
+  describe "REGEX_WELL_FORMED" do
+    it "matches most singleton emoji codepoints" do
+      "😴 sleeping face" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "😴", $&
+    end
+
+    it "matches singleton emoji in combination with emoji variation selector" do
+      "😴\u{FE0F} sleeping face" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "😴\u{FE0F}", $&
+    end
+
+    it "does not match singleton emoji when in combination with text variation selector" do
+      "😴\u{FE0E} sleeping face" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_nil $&
+    end
+
+    it "does not match textual singleton emoji" do
+      "▶ play button" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_nil $&
+    end
+
+    it "matches textual singleton emoji in combination with emoji variation selector" do
+      "▶\u{FE0F} play button" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "▶\u{FE0F}", $&
+    end
+
+    it "does not match singleton 'component' emoji codepoints" do
+      "🏻 light skin tone" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_nil $&
+    end
+
+    it "matches modified emoji if modifier base emoji is used" do
+      "🛌🏽 person in bed: medium skin tone" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🛌🏽", $&
+    end
+
+    it "does not match modified emoji if no modifier base emoji is used" do
+      "🌵🏽 cactus" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🌵", $&
+    end
+
+    it "matches valid region flags" do
+      "🇵🇹 Portugal" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🇵🇹", $&
+    end
+
+    it "does match invalid region flags" do
+      "🇵🇵 PP Land" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🇵🇵", $&
+    end
+
+    it "matches emoji keycap sequences" do
+      "2️⃣ keycap: 2" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "2️⃣", $&
+    end
+
+    it "matches recommended tag sequences" do
+      "🏴󠁧󠁢󠁳󠁣󠁴󠁿 Scotland" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🏴󠁧󠁢󠁳󠁣󠁴󠁿", $&
+    end
+
+    it "matches valid tag sequences, even though they are not recommended" do
+      "🏴󠁧󠁢󠁡󠁧󠁢󠁿 GB AGB" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🏴󠁧󠁢󠁡󠁧󠁢󠁿", $&
+    end
+
+    it "does match invalid tag sequences" do
+      "😴󠁧󠁢󠁡󠁡󠁡󠁿 GB AAA" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "😴󠁧󠁢󠁡󠁡󠁡󠁿", $&
+    end
+
+    it "matches recommended zwj sequences" do
+      "🤾🏽‍♀️ woman playing handball: medium skin tone" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🤾🏽‍♀️", $&
+    end
+
+    it "matches valid zwj sequences, even though they are not recommended" do
+      "🤠‍🤢 vomiting cowboy" =~ Unicode::Emoji::REGEX_WELL_FORMED
+      assert_equal "🤠‍🤢", $&
+    end
+  end
+
   describe "REGEX_BASIC" do
     it "matches most singleton emoji codepoints" do
       "😴 sleeping face" =~ Unicode::Emoji::REGEX_BASIC
@@ -300,15 +382,21 @@ describe Unicode::Emoji do
 
   describe ".list" do
     it "returns a grouped list of emoji" do
-      assert_includes Unicode::Emoji.list.keys, "Smileys & People"
+      assert_includes Unicode::Emoji.list.keys, "Smileys & Emotion"
     end
 
     it "sub-groups the list of emoji" do
-      assert_includes Unicode::Emoji.list("Smileys & People").keys, "face-positive"
+      assert_includes Unicode::Emoji.list("Smileys & Emotion").keys, "face-glasses"
     end
 
     it "has emoji in sub-groups" do
-      assert_includes Unicode::Emoji.list("Smileys & People", "face-positive"), "😎"
+      assert_includes Unicode::Emoji.list("Smileys & Emotion", "face-glasses"), "😎"
+    end
+
+    it "issues a warning if attempting to retrieve old category" do
+      assert_output nil, "Warning(unicode-emoji): The category of Smileys & People does not exist anymore\n" do
+        assert_nil Unicode::Emoji.list("Smileys & People", "face-positive")
+      end
     end
   end
 end

metadata

@@ -1,16 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: unicode-emoji
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 2.0.0
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-06-05 00:00:00.000000000 Z
+date: 2019-02-19 00:00:00.000000000 Z
 dependencies: []
-description: "[Emoji 11.0] Retrieve emoji data about Unicode codepoints. Also contains
+description: "[Emoji 12.0] Retrieve emoji data about Unicode codepoints. Also contains
   a regex to match emoji."
 email:
 - mail@janlelis.de
@@ -53,7 +53,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
 summary: Retrieve Emoji data about Unicode codepoints.