unicode-emoji 4.0.0 → 4.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5cc77126aeb986e5645ebce97fc3e1be5835b9e5adb9764af980e0175d7d9284
-  data.tar.gz: ffd47af7c556ee26951f6c5f30122ecd44520f1a3aa6856c526c4e4dec050e77
+  metadata.gz: 3b08d6adaddfcbca3e754c9a52a0c0d5c772da86ca708affc9799ad113c5a005
+  data.tar.gz: e9f3817a215ef38b7933d69b4f0563d848a03f6a6b8728ecd06a74417fb5f8a7
 SHA512:
-  metadata.gz: 810730ae1a796edc6c80c87d0d4e7c0a5bfdbda45c43f57dfde3a05afee7ee5df8d43f378c5c0de34d9e9bca8e9edfaee67261d16057a0aacc79f50c39d703d2
-  data.tar.gz: f300c259b7389d60130b9f910b1301f31bf60d47c32fd16f86935cdf63c740bb44c28ab8fd38bc643f35cd6b4d7e9a76583d3be156683404439069ccf58d8250
+  metadata.gz: cedad0ceb5f1039be614bbca170cccc3f29e8f05bd7fc74714ed586ddf20edb5da25a6c8fd840acfb7dfbeb918ec6e2218cf427e5e510eb2406235253e32ad74
+  data.tar.gz: 4680b526737abd7491351ff87c5d323f3a6acf5996dffa4c2f4737e10bc8083da16928dbab34362b6014ae5a17863266eb456ab2d382f25350339eaf71a175bf

data/CHANGELOG.md

@@ -1,6 +1,19 @@
 # CHANGELOG
 
-### 4.0.0
+## 4.0.4
+
+- Add `REGEX_TEXT_PRESENTATION` to be able to match for raw default-text Emoji codepoints
+
+## 4.0.3
+
+- Remove emoji-test.txt from Rubygems package
+
+## 4.0.2
+
+- Directly use `RbConfig::CONFIG["UNICODE_EMOJI_VERSION"]` to detect Ruby's Emoji version,
+  drop unicode-version dependency
+
+## 4.0.0
 
 - **Breaking change:** Regexes now include single skin tone modifiers (`🏻`) and hair components (`🦰`).
   They were previously considered to be invalid partial Emoji, however since they are supposed to be
@@ -13,7 +26,7 @@
 - Add `REGEX_EMOJI_KEYCAP` for matching specifically Emoji keycaps
 - Use character class instead of lookbehind for native text emoji and non-emoji pictographic regexes
 
-### 3.8.0
+## 3.8.0
 
 - Add new RGI-based regexes `REGEX_INCLUDE_MQE` and `REGEX_INCLUDE_MQE_UQE` which allows to match
   for minimally-qualified and unqualified RGI sequences (Emoji that lack some VS16)
@@ -23,7 +36,7 @@
 - Update CLDR to v46 (valid subdivisions)
 - Further improvements (see commit log)
 
-### 3.7.0
+## 3.7.0
 
 - Bump required Ruby slightly to 2.5
 - Introduce new `REGEX_POSSIBLE` which contains the regex described in
@@ -36,46 +49,46 @@
 - Separately autoload emoji list, so it can be loaded when other indexes
   are not needed
 
-### 3.6.0
+## 3.6.0
 
 - `Unicode::Emoji::REGEX_TEXT` now matches non-emoji keycaps like "3⃣"  (U+0033 U+20E3)
 - Minor refactorings
 
-### 3.5.0
+## 3.5.0
 
 - Emoji 16.0
 
-### 3.4.0
+## 3.4.0
 
 - Emoji 15.1
 
-### 3.3.2
+## 3.3.2
 
 - Update valid subdivisions to CLDR 43 (no changes)
   -> there won't be any new RGI subdivision flags in Emoji
 
-### 3.3.1
+## 3.3.1
 
 - Update valid subdivisions to CLDR 42 (no changes)
 
-### 3.3.0
+## 3.3.0
 
 - Emoji 15.0
 
-### 3.2.0
+## 3.2.0
 
 - Update valid subdivisions to CLDR 41
 
-### 3.1.1
+## 3.1.1
 
 - Fix `REGEX` to be able to match complete family emoji, instead of
   sub-matching partial families, thanks @matt17r
 
-### 3.1.0
+## 3.1.0
 
 - Update valid subdivisions to CLDR 40
 
-### 3.0.0
+## 3.0.0
 
 - Vastly improve memory usage, patch by @radarek
   - Emoji regexes are now pre-generated and bundled with the release
@@ -83,54 +96,54 @@
   - Most constants (e.g. regexes) now get autoloaded
   - See https://github.com/janlelis/unicode-emoji/pull/9 for more details
 
-### 2.9.0
+## 2.9.0
 
 - Emoji 14.0
 
-### 2.8.0
+## 2.8.0
 
 - Update valid subdivisions to CLDR 39
 
-### 2.7.1
+## 2.7.1
 
 - Update valid subdivisions to CLDR 38.1
 
-### 2.7.0
+## 2.7.0
 
 - Update valid subdivisions to CLDR 38
 - Loosen Ruby dependency to allow Ruby 3.0
 
-### 2.6.0
+## 2.6.0
 
 - Emoji 13.1
 
-### 2.5.0
+## 2.5.0
 
 - Use native Emoji regex properties when current Ruby's Emoji support is the same as our current Emoji version
 - Update valid subdivisions to CLDR 37
 
-### 2.4.0
+## 2.4.0
 
 - Emoji 13.0
 
-### 2.3.1
+## 2.3.1
 
 - Fix index to actually include Emoji 12.1
 
-### 2.3.0
+## 2.3.0
 
 - Emoji 12.1
 
-### 2.2.0
+## 2.2.0
 
 - Update subdivisions to CLDR 36
 
-### 2.1.0
+## 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
+## 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
@@ -139,40 +152,40 @@
 - 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
+## 1.1.0
 
 - Emoji 11.0
 - Do not depend on rubygems (only use zlib stdlib for unzipping)
 
-### 1.0.3
+## 1.0.3
 
 - Explicitly load rubygems/util, fixes regression in 1.2.1
 
-### 1.0.2
+## 1.0.2
 
 - Use `Gem::Util` for `gunzip`, removes deprecation warning
 
-### 1.0.1
+## 1.0.1
 
 - Actually set required Ruby version to 2.3 in gemspec
 
-### 1.0.0
+## 1.0.0
 
 - Drop support for Ruby below 2.3, use 0.9 if you need to
 - Internal refactorings, no API change
 
-### 0.9.3
+## 0.9.3
 
 - Implement native Emoji regex matchers, but do not activate or document, yet
 
-### 0.9.2
+## 0.9.2
 
 - REGEX_TEXT: Do not match if the text emoji is followed by a emoji modifier
 
-### 0.9.1
+## 0.9.1
 
 - Include a categorized list of recommended Emoji
 
-### 0.9.0
+## 0.9.0
 
 - Initial release (Emoji version 5.0)

data/Gemfile.lock

@@ -1,8 +1,7 @@
 PATH
   remote: .
   specs:
-    unicode-emoji (4.0.0)
-      unicode-version (~> 1.0)
+    unicode-emoji (4.0.4)
 
 GEM
   remote: https://rubygems.org/
@@ -20,7 +19,6 @@ GEM
     reline (0.3.8)
       io-console (~> 0.5)
     stringio (3.0.8)
-    unicode-version (1.4.0)
 
 PLATFORMS
   ruby

data/README.md

@@ -37,7 +37,7 @@ string = "String which contains all types of Emoji sequences:
 - Sequence using ZWJ (zero width joiner): 🤾🏽‍♀️
 "
 
-string.scan(Unicode::Emoji::REGEX) # => ["😴", "▶️", "🛌🏽", "🇵🇹", "🏴󠁧󠁢󠁳󠁣󠁴󠁿", "2️⃣", "🤾🏽‍♀️"]
+string.scan(Unicode::Emoji::REGEX) # => ["😴", "▶️", "🛌🏽", "🇵🇹", "🏴󠁧󠁢󠁳󠁣󠁴󠁿", "2️⃣", "🏻", "🤾🏽‍♀️"]
 ```
 
 Depending on your exact usecase, you can choose between multiple levels of Emoji detection:
@@ -79,7 +79,7 @@ Regex                         | Description | Example Matches | Example Non-Matc
 `Unicode::Emoji::REGEX_BASIC` | Matches (non-textual) Basic Emoji, but no sequences at all | `😴`, `▶️`, `🏻` | `😴︎`, `▶`, `🛌🏽`, `🇵🇹`, `🇵🇵`,`2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`, `🏌‍♂️`, `🤠‍🤢`, `1`
 `Unicode::Emoji::REGEX_TEXT`  | Matches only textual singleton Emoji | `😴︎`, `▶` | `😴`, `▶️`, `🏻`, `🛌🏽`, `🇵🇹`, `🇵🇵`,`2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`, `🏌‍♂️`, `🤠‍🤢`, `1`
 
-Here is a list of all Emoji that can be matched using the two regexes: [character.construction/emoji-vs-text](https://character.construction/emoji-vs-text). The `REGEX_BASIC` regex also matches visual Emoji components (skin tone modifiers and hair components).
+Here is a list of all Emoji that can be matched using the two regexes: [character.construction/emoji-vs-text](https://character.construction/emoji-vs-text). The `REGEX_BASIC` regex also matches [visual Emoji components](https://character.construction/emoji-components) (skin tone modifiers and hair components).
 
 While `REGEX_BASIC` is part of the above regexes, `REGEX_TEXT` is only included in the `*_INCLUDE_TEXT` or `*_UQE` variants.
 
@@ -153,6 +153,7 @@ Gem Regex (`Unicode::Emoji`'s Emoji support level) | Native Regex (Ruby's Emoji
 `Unicode::Emoji::REGEX_PROP_MODIFIER_BASE` | `/\p{EBase}/`
 `Unicode::Emoji::REGEX_PROP_COMPONENT`     | `/\p{EComp}/`
 `Unicode::Emoji::REGEX_PROP_PRESENTATION`  | `/\p{EPres}/`
+`Unicode::Emoji::REGEX_TEXT_PRESENTATION`  | `/[\p{Emoji}&&\P{EPres}]/`
 
 #### Extended Pictographic Regex
 

data/data/generate_constants.rb

@@ -300,6 +300,7 @@ def compile(emoji_character:, emoji_modifier:, emoji_modifier_base:, emoji_compo
 
   # Matches only basic single, textual emoji, ignores components like modifiers or simple digits
   regexes[:REGEX_TEXT] = Regexp.compile(text_emoji)
+  regexes[:REGEX_TEXT_PRESENTATION] = Regexp.compile(text_presentation)
 
   # Export regexes for Emoji properties so they can be used with newer Unicode than Ruby's
   regexes[:REGEX_PROP_EMOJI] = Regexp.compile(emoji_character)

data/lib/unicode/emoji/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   module Emoji
-    VERSION = "4.0.0"
+    VERSION = "4.0.4"
     EMOJI_VERSION = "16.0"
     CLDR_VERSION = "46"
     DATA_DIRECTORY = File.expand_path('../../../data', __dir__).freeze
@@ -44,6 +44,6 @@ module Unicode
 
     # The current list of Emoji components that should have a visual representation
     # Currently skin tone modifiers + hair components
-    VISUAL_COMPONENT              = [*0x1F3FB..0x1F3FF, *0x1F9B0..0x1F9B3]
+    VISUAL_COMPONENT              = [*0x1F3FB..0x1F3FF, *0x1F9B0..0x1F9B3].freeze
   end
 end

data/lib/unicode/emoji/generated/regex_text_presentation.rb

@@ -0,0 +1,8 @@
+# This file was generated by a script, please do not edit it by hand.
+# See `$ rake generate_constants` and data/generate_constants.rb for more info.
+
+module Unicode
+  module Emoji
+    REGEX_TEXT_PRESENTATION = /[\#\*0-9©®‼⁉™ℹ↔-↙↩↪⌨⏏⏭-⏯⏱⏲⏸-⏺Ⓜ▪▫▶◀◻◼☀-☄☎☑☘☝☠☢☣☦☪☮☯☸-☺♀♂♟♠♣♥♦♨♻♾⚒⚔-⚗⚙⚛⚜⚠⚧⚰⚱⛈⛏⛑⛓⛩⛰⛱⛴⛷-⛹✂✈✉✌✍✏✒✔✖✝✡✳✴❄❇❣❤➡⤴⤵⬅-⬇〰〽㊗㊙🅰🅱🅾🅿🈂🈷🌡🌤-🌬🌶🍽🎖🎗🎙-🎛🎞🎟🏋-🏎🏔-🏟🏳🏵🏷🐿👁📽🕉🕊🕯🕰🕳-🕹🖇🖊-🖍🖐🖥🖨🖱🖲🖼🗂-🗄🗑-🗓🗜-🗞🗡🗣🗨🗯🗳🗺🛋🛍-🛏🛠-🛥🛩🛰🛳]/
+  end
+end

data/lib/unicode/emoji/generated_native/regex_text_presentation.rb

@@ -0,0 +1,8 @@
+# This file was generated by a script, please do not edit it by hand.
+# See `$ rake generate_constants` and data/generate_constants.rb for more info.
+
+module Unicode
+  module Emoji
+    REGEX_TEXT_PRESENTATION = /[\p{Emoji}&&\P{EPres}]/
+  end
+end

data/lib/unicode/emoji.rb

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
 
-require "unicode/version"
-
 require_relative "emoji/constants"
 
 module Unicode
@@ -34,7 +32,7 @@ module Unicode
     end
 
     generated_constants_dirpath = File.expand_path(
-      EMOJI_VERSION == Unicode::Version.emoji_version ? "emoji/generated_native/" : "emoji/generated/",
+      EMOJI_VERSION == RbConfig::CONFIG["UNICODE_EMOJI_VERSION"] ? "emoji/generated_native/" : "emoji/generated/",
       __dir__
     )
 
@@ -50,6 +48,7 @@ module Unicode
       REGEX_POSSIBLE
       REGEX_BASIC
       REGEX_TEXT
+      REGEX_TEXT_PRESENTATION
       REGEX_PROP_EMOJI
       REGEX_PROP_MODIFIER
       REGEX_PROP_MODIFIER_BASE

data/unicode-emoji.gemspec

@@ -12,13 +12,11 @@ Gem::Specification.new do |gem|
   gem.homepage      = "https://github.com/janlelis/unicode-emoji"
   gem.license       = "MIT"
 
-  gem.files         = Dir["{**/}{.*,*}"].select{ |path| File.file?(path) && path !~ /^pkg/ }
+  gem.files         = Dir["{**/}{.*,*}"].select{ |path| File.file?(path) && path !~ /^pkg/ && path !~ /spec\/data\/[^.]/ }
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
   gem.require_paths = ["lib"]
   gem.metadata      = { "rubygems_mfa_required" => "true" }
 
   gem.required_ruby_version = ">= 2.5", "< 4.0"
-
-  gem.add_dependency "unicode-version", "~> 1.0"
 end

metadata

@@ -1,29 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: unicode-emoji
 version: !ruby/object:Gem::Version
-  version: 4.0.0
+  version: 4.0.4
 platform: ruby
 authors:
 - Jan Lelis
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-11-06 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: unicode-version
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
+date: 2024-11-19 00:00:00.000000000 Z
+dependencies: []
 description: "[Emoji 16.0] Provides Unicode Emoji data and regexes, incorporating
   the latest Unicode and Emoji standards. Includes a categorized list of recommended
   Emoji."
@@ -61,6 +47,7 @@ files:
 - lib/unicode/emoji/generated/regex_prop_modifier_base.rb
 - lib/unicode/emoji/generated/regex_prop_presentation.rb
 - lib/unicode/emoji/generated/regex_text.rb
+- lib/unicode/emoji/generated/regex_text_presentation.rb
 - lib/unicode/emoji/generated/regex_valid.rb
 - lib/unicode/emoji/generated/regex_valid_include_text.rb
 - lib/unicode/emoji/generated/regex_well_formed.rb
@@ -80,6 +67,7 @@ files:
 - lib/unicode/emoji/generated_native/regex_prop_modifier_base.rb
 - lib/unicode/emoji/generated_native/regex_prop_presentation.rb
 - lib/unicode/emoji/generated_native/regex_text.rb
+- lib/unicode/emoji/generated_native/regex_text_presentation.rb
 - lib/unicode/emoji/generated_native/regex_valid.rb
 - lib/unicode/emoji/generated_native/regex_valid_include_text.rb
 - lib/unicode/emoji/generated_native/regex_well_formed.rb
@@ -88,7 +76,6 @@ files:
 - lib/unicode/emoji/lazy_constants.rb
 - lib/unicode/emoji/list.rb
 - spec/data/.keep
-- spec/data/emoji-test.txt
 - spec/emoji_test_txt_spec.rb
 - spec/unicode_emoji_spec.rb
 - unicode-emoji.gemspec
@@ -121,6 +108,5 @@ specification_version: 4
 summary: Emoji data and regex
 test_files:
 - spec/data/.keep
-- spec/data/emoji-test.txt
 - spec/emoji_test_txt_spec.rb
 - spec/unicode_emoji_spec.rb