brakeman 6.2.2 → 7.0.1

data/bundle/ruby/3.1.0/gems/unicode-emoji-4.0.4/CHANGELOG.md

@@ -0,0 +1,191 @@
+# CHANGELOG
+
+## 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
+  displayed as Emoji in isolation, they are now part of the regexes (see *ED-20* in UTS51).
+- **Breaking change:** Drop `REGEX_ANY` in favor of `REGEX_PROP_EMOJI`
+- Expose regexes for Emoji props (`REGEX_PROP_*`). The advantage over using the native regex properties
+  directly is that you will be able to use the Emoji support level of this gem instead of Ruby's.
+  For example, as of releasing this, the current Emoji version is 16.0, while Ruby is at 15.0.
+  Also see README for a table listing the regexes that match Emoji properties.
+- 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
+
+- 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)
+- Add specs running through `emoji-text.txt` and classify qualification statuses per regex
+- Improve documentation and add detailed table about which regex has which features
+- Native regexes: Use native Emoji props for Emoji text presentation
+- Update CLDR to v46 (valid subdivisions)
+- Further improvements (see commit log)
+
+## 3.7.0
+
+- Bump required Ruby slightly to 2.5
+- Introduce new `REGEX_POSSIBLE` which contains the regex described in
+  https://www.unicode.org/reports/tr51/#EBNF_and_Regex
+- Fix that some valid subdivisions were not decompressed (`REGEX_VALID`)
+- Be stricter about selection of tag characters in `REGEX_WELL_FORMED`
+  - Only U+E0030..U+E0039, U+E0061..U+E007A allowed
+  - Max tag sequence length
+- Use native `/\p{RI}/` regex for regional indicators
+- Separately autoload emoji list, so it can be loaded when other indexes
+  are not needed
+
+## 3.6.0
+
+- `Unicode::Emoji::REGEX_TEXT` now matches non-emoji keycaps like "3⃣"  (U+0033 U+20E3)
+- Minor refactorings
+
+## 3.5.0
+
+- Emoji 16.0
+
+## 3.4.0
+
+- Emoji 15.1
+
+## 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
+
+- Update valid subdivisions to CLDR 42 (no changes)
+
+## 3.3.0
+
+- Emoji 15.0
+
+## 3.2.0
+
+- Update valid subdivisions to CLDR 41
+
+## 3.1.1
+
+- Fix `REGEX` to be able to match complete family emoji, instead of
+  sub-matching partial families, thanks @matt17r
+
+## 3.1.0
+
+- Update valid subdivisions to CLDR 40
+
+## 3.0.0
+
+- Vastly improve memory usage, patch by @radarek
+  - Emoji regexes are now pre-generated and bundled with the release
+  - Regexes use character classes instead of unions when possible
+  - Most constants (e.g. regexes) now get autoloaded
+  - See https://github.com/janlelis/unicode-emoji/pull/9 for more details
+
+## 2.9.0
+
+- Emoji 14.0
+
+## 2.8.0
+
+- Update valid subdivisions to CLDR 39
+
+## 2.7.1
+
+- Update valid subdivisions to CLDR 38.1
+
+## 2.7.0
+
+- Update valid subdivisions to CLDR 38
+- Loosen Ruby dependency to allow Ruby 3.0
+
+## 2.6.0
+
+- Emoji 13.1
+
+## 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
+
+- Emoji 13.0
+
+## 2.3.1
+
+- Fix index to actually include Emoji 12.1
+
+## 2.3.0
+
+- Emoji 12.1
+
+## 2.2.0
+
+- Update subdivisions to CLDR 36
+
+## 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)
+- 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
+- Do not depend on rubygems (only use zlib stdlib for unzipping)
+
+## 1.0.3
+
+- Explicitly load rubygems/util, fixes regression in 1.2.1
+
+## 1.0.2
+
+- Use `Gem::Util` for `gunzip`, removes deprecation warning
+
+## 1.0.1
+
+- Actually set required Ruby version to 2.3 in gemspec
+
+## 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
+
+- Implement native Emoji regex matchers, but do not activate or document, yet
+
+## 0.9.2
+
+- REGEX_TEXT: Do not match if the text emoji is followed by a emoji modifier
+
+## 0.9.1
+
+- Include a categorized list of recommended Emoji
+
+## 0.9.0
+
+- Initial release (Emoji version 5.0)

data/bundle/ruby/3.1.0/gems/unicode-emoji-4.0.4/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at opensource@janlelis.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/bundle/ruby/3.1.0/gems/unicode-emoji-4.0.4/Gemfile

@@ -0,0 +1,7 @@
+source "https://rubygems.org"
+
+gemspec
+
+gem "minitest"
+gem "rake"
+gem "irb" unless RUBY_ENGINE == "jruby"

data/bundle/ruby/3.1.0/gems/unicode-emoji-4.0.4/Gemfile.lock

@@ -0,0 +1,33 @@
+PATH
+  remote: .
+  specs:
+    unicode-emoji (4.0.4)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    io-console (0.6.0)
+    irb (1.8.1)
+      rdoc
+      reline (>= 0.3.8)
+    minitest (5.20.0)
+    psych (5.1.0)
+      stringio
+    rake (13.0.6)
+    rdoc (6.5.0)
+      psych (>= 4.0.0)
+    reline (0.3.8)
+      io-console (~> 0.5)
+    stringio (3.0.8)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  irb
+  minitest
+  rake
+  unicode-emoji!
+
+BUNDLED WITH
+   2.5.21

data/bundle/ruby/3.1.0/gems/unicode-emoji-4.0.4/MIT-LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2017-2024 Jan Lelis, https://janlelis.com
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/bundle/ruby/3.1.0/gems/unicode-emoji-4.0.4/README.md

@@ -0,0 +1,205 @@
+# Unicode::Emoji [![[version]](https://badge.fury.io/rb/unicode-emoji.svg)](https://badge.fury.io/rb/unicode-emoji)  [![[ci]](https://github.com/janlelis/unicode-emoji/workflows/Test/badge.svg)](https://github.com/janlelis/unicode-emoji/actions?query=workflow%3ATest)
+
+Provides various sophisticated regular expressions to work with Emoji in strings,
+incorporating the latest Unicode / Emoji standards.
+
+Additional features:
+
+- A categorized list of Emoji (RGI: Recommended for General Interchange)
+- Retrieve Emoji properties info about specific codepoints (Emoji_Modifier, Emoji_Presentation, etc.)
+
+Emoji version: **16.0** (September 2024)
+
+CLDR version (used for sub-region flags): **46** (October 2024)
+
+## Gemfile
+
+```ruby
+gem "unicode-emoji"
+```
+
+## Usage – Regex Matching
+
+The gem includes multiple Emoji regexes, which are compiled out of various Emoji Unicode data sources.
+
+```ruby
+require "unicode/emoji"
+
+string = "String which contains all types of Emoji sequences:
+
+- Basic Emoji: 😴
+- Textual Emoji with Emoji variation (VS16): ▶️
+- Emoji with skin tone modifier: 🛌🏽
+- Region flag: 🇵🇹
+- Sub-Region flag: 🏴󠁧󠁢󠁳󠁣󠁴󠁿
+- Keycap sequence: 2️⃣
+- Skin tone modifier: 🏻
+- Sequence using ZWJ (zero width joiner): 🤾🏽‍♀️
+"
+
+string.scan(Unicode::Emoji::REGEX) # => ["😴", "▶️", "🛌🏽", "🇵🇹", "🏴󠁧󠁢󠁳󠁣󠁴󠁿", "2️⃣", "🏻", "🤾🏽‍♀️"]
+```
+
+Depending on your exact usecase, you can choose between multiple levels of Emoji detection:
+
+### Main Regexes
+
+Regex                         | Description | Example Matches | Example Non-Matches
+------------------------------|-------------|-----------------|--------------------
+`Unicode::Emoji::REGEX`       | **Use this one if unsure!** Matches (non-textual) Basic Emoji and all kinds of *recommended* Emoji sequences (RGI/FQE) | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🤾🏽‍♀️`, `🏻` |  `🤾🏽‍♀`, `🏌‍♂️`, `😴︎`, `▶`, `🇵🇵`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤠‍🤢`, `1`, `1⃣`
+`Unicode::Emoji::REGEX_VALID` | Matches (non-textual) Basic Emoji and all kinds of *valid* Emoji sequences | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀` ,`🏌‍♂️`, `🤠‍🤢`, `🏻` | `😴︎`, `▶`, `🇵🇵`, `1`, `1⃣`
+`Unicode::Emoji::REGEX_WELL_FORMED` | Matches (non-textual) Basic Emoji and all kinds of *well-formed* Emoji sequences | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`,`🏌‍♂️` , `🤠‍🤢`,  `🇵🇵`, `🏻` | `😴︎`, `▶`, `1`, `1⃣`
+`Unicode::Emoji::REGEX_POSSIBLE` | Matches all singleton Emoji, all kinds of Emoji sequences, and even non-Emoji singleton components like digits. Only exception: Unqualified keycap sequences are not matched | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`, `🏌‍♂️`, `🤠‍🤢`,  `🇵🇵`, `😴︎`, `▶`, `🏻`, `1` | `1⃣`
+
+#### Include Text 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 (except in `REGEX_POSSIBLE`). 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`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🤾🏽‍♀️`, `😴︎`, `▶`, `1⃣` , `🏻`| `🤾🏽‍♀`, `🏌‍♂️`, `🇵🇵`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤠‍🤢`, `1`
+`Unicode::Emoji::REGEX_VALID_INCLUDE_TEXT` | `REGEX_VALID` + `REGEX_TEXT` | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`, `🏌‍♂️`, `🤠‍🤢`, `😴︎`, `▶`, `1⃣` , `🏻` | `🇵🇵`, `1`
+`Unicode::Emoji::REGEX_WELL_FORMED_INCLUDE_TEXT` | `REGEX_WELL_FORMED` + `REGEX_TEXT` | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`, `🏌‍♂️`, `🤠‍🤢`,  `🇵🇵`, `😴︎`, `▶`, `1⃣` , `🏻` | `1`
+
+#### Minimally-qualified and Unqualified Sequences
+
+Regex                         | Description | Example Matches | Example Non-Matches
+------------------------------|-------------|-----------------|--------------------
+`Unicode::Emoji::REGEX_INCLUDE_MQE` | Like `REGEX`, but additionally includes Emoji with missing Emoji Presentation Variation Selectors, where the first partial Emoji has all required Variation Selectors | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`, `🏻` | `🏌‍♂️`, `😴︎`, `▶`, `🇵🇵`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤠‍🤢`, `1`, `1⃣`
+`Unicode::Emoji::REGEX_INCLUDE_MQE_UQE` | Like `REGEX`, but additionally includes Emoji with missing Emoji Presentation Variation Selectors | `😴`, `▶️`, `🛌🏽`, `🇵🇹`, `2️⃣`, `🏴󠁧󠁢󠁳󠁣󠁴󠁿`, `🤾🏽‍♀️`, `🤾🏽‍♀`, `🏌‍♂️`, `🏻` | `😴︎`, `▶`, `🇵🇵`, `🏴󠁧󠁢󠁡󠁧󠁢󠁿`, `🤠‍🤢`, `1`, `1⃣`
+
+[List of MQE and UQE Emoji sequences](https://character.construction/unqualified-emoji)
+
+#### 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) 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](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.
+
+### Comparison 
+
+1) Fully-qualified RGI Emoji ZWJ sequence
+2) Minimally-qualified RGI Emoji ZWJ sequence (lacks Emoji Presentation Selectors, but not in the first Emoji character)
+3) Unqualified RGI Emoji ZWJ sequence (lacks Emoji Presentation Selector, including in the first Emoji character). Unqualified Emoji include all basic Emoji in Text Presentation (see column 11/12).
+4) Non-RGI Emoji ZWJ sequence
+5) Valid Region made from a pair of Regional Indicators
+6) Any Region made from a pair of Regional Indicators
+7) RGI Flag Emoji Tag Sequences (England, Scotland, Wales)
+8) Valid Flag Emoji Tag Sequences (any known subdivision)
+9) Any Emoji Tag Sequences (any tag sequence with any base)
+10) Basic Default Emoji Presentation Characters or Text characters with Emoji Presentation Selector
+11) Basic Default Text Presentation Characters or Basic Emoji with Text Presentation Selector
+12) Non-Emoji (unqualified) keycap
+
+Regex | 1 RGI/FQE | 2 RGI/MQE | 3 RGI/UQE | 4 Non-RGI | 5 Valid Re­gion | 6 Any Re­gion | 7 RGI Tag | 8 Valid Tag | 9 Any Tag | 10 Basic Emoji | 11 Basic Text | 12 Text Key­cap
+-|-|-|-|-|-|-|-|-|-|-|-|-
+REGEX                          | ✅ | ❌ | ❌    | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌
+REGEX INCLUDE TEXT             | ✅ | ❌ | ❌    | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅
+REGEX INCLUDE MQE              | ✅ | ✅ | ❌    | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌
+REGEX INCLUDE MQE UQE          | ✅ | ✅ | ✅    | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅
+REGEX VALID                    | ✅ | ✅ | (✅)¹ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌
+REGEX VALID INCLUDE TEXT       | ✅ | ✅ | ✅    | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅
+REGEX WELL FORMED              | ✅ | ✅ | (✅)¹ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌
+REGEX WELL FORMED INCLUDE TEXT | ✅ | ✅ | ✅    | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅
+REGEX POSSIBLE                 | ✅ | ✅ | ✅    | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌
+REGEX BASIC                    | ❌ | ❌ | ❌    | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌
+REGEX TEXT                     | ❌ | ❌ | ❌    | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅
+
+¹ Matches all unqualified Emoji, except for textual singleton Emoji (see columns 11, 12)
+
+See [spec files](/spec) for detailed examples about which regex matches which kind of Emoji.
+
+### Picking the Right Emoji Regex
+
+- Usually you just want `REGEX` (recommended Emoji set, RGI)
+- Use `REGEX_INCLUDE_MQE` or `REGEX_INCLUDE_MQE_UQE` if you want to catch Emoji sequences with missing Variation Selectors.
+- If you want broader matching (any ZWJ sequences, more sub-region flags), choose `REGEX_VALID`
+- If you need to match any region flag and any tag sequence, choose `REGEX_WELL_FORMED`
+- Use the `_INCLUDE_TEXT` suffix with any of the above base regexes, if you want to also match basic textual Emoji
+- And finally, there is also the option to use `REGEX_POSSIBLE`, which is a simplified test for possible Emoji, comparable to `REGEX_WELL_FORMED*`. It might contain false positives, however, the regex is less complex and [suggested in the Unicode standard itself](https://www.unicode.org/reports/tr51/#EBNF_and_Regex) as a first check.
+
+### Examples
+
+Desc | Emoji | Escaped | `REGEX` (RGI/FQE) | `REGEX_INCLUDE_MQE` (RGI/MQE) | `REGEX_VALID` | `REGEX_WELL_FORMED` / `REGEX_POSSIBLE`
+-----|-------|---------|---------------|-----------------------|-----------------------------------|-----------------
+RGI ZWJ Sequence   | 🤾🏽‍♀️ | `\u{1F93E 1F3FD 200D 2640 FE0F}` | ✅ | ✅ | ✅ | ✅
+RGI ZWJ Sequence MQE | 🤾🏽‍♀ | `\u{1F93E 1F3FD 200D 2640}` | ❌ | ✅ | ✅ | ✅
+Valid ZWJ Sequence, Non-RGI | 🤠‍🤢 | `\u{1F920 200D 1F922}` | ❌ | ❌  | ✅ | ✅
+Known Region       | 🇵🇹 | `\u{1F1F5 1F1F9}` | ✅ | ✅ | ✅ | ✅
+Unknown Region     | 🇵🇵 | `\u{1F1F5 1F1F5}` | ❌ | ❌  | ❌  | ✅
+RGI Tag Sequence   | 🏴󠁧󠁢󠁳󠁣󠁴󠁿 | `\u{1F3F4 E0067 E0062 E0073 E0063 E0074 E007F}` | ✅ | ✅ | ✅ | ✅
+Valid Tag Sequence | 🏴󠁧󠁢󠁡󠁧󠁢󠁿 | `\u{1F3F4 E0067 E0062 E0061 E0067 E0062 E007F}` | ❌ | ❌  | ✅ | ✅
+Well-formed Tag Sequence | 😴󠁧󠁢󠁡󠁡󠁡󠁿 | `\u{1F634 E0067 E0062 E0061 E0061 E0061 E007F}` | ❌ | ❌  | ❌  | ✅
+
+Please see [the standard](https://www.unicode.org/reports/tr51/#Emoji_Sets) for more details, examples, explanations.
+
+More info about valid vs. recommended Emoji can also be found in this [blog article on Emojipedia](https://blog.emojipedia.org/unicode-behind-the-curtain/).
+
+### Emoji Property Regexes
+
+Ruby includes native regex Emoji properties, as listed in the following table. You can also opt-in to use the `*_PROP_*` regexes to get the Emoji support level of this gem (instead of Ruby's).
+
+Gem Regex (`Unicode::Emoji`'s Emoji support level) | Native Regex (Ruby's Emoji support level)
+---------------------------------------------------|------------------------------------------
+`Unicode::Emoji::REGEX_PROP_EMOJI`         | `/\p{Emoji}/`
+`Unicode::Emoji::REGEX_PROP_MODIFIER`      | `/\p{EMod}/`
+`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
+
+`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.
+
+## Usage – List
+
+Use `Unicode::Emoji::LIST` or the **list** method to get a ordered and categorized list of Emoji:
+
+```ruby
+Unicode::Emoji.list.keys
+# => ["Smileys & Emotion", "People & Body", "Component", "Animals & Nature", "Food & Drink", "Travel & Places", "Activities", "Objects", "Symbols", "Flags"]
+
+Unicode::Emoji.list("Food & Drink").keys
+# => ["food-fruit", "food-vegetable", "food-prepared", "food-asian", "food-marine", "food-sweet", "drink", "dishware"]
+
+Unicode::Emoji.list("Food & Drink", "food-asian")
+=> ["🍱", "🍘", "🍙", "🍚", "🍛", "🍜", "🍝", "🍠", "🍢", "🍣", "🍤", "🍥", "🥮", "🍡", "🥟", "🥠", "🥡"]
+```
+
+Please note that categories might change with future versions of the Emoji standard, although this has not happened often.
+
+A list of all Emoji (generated from this gem) can be found at [character.construction/emoji](https://character.construction/emoji).
+
+## Usage – Properties Data
+
+Allows you to access the codepoint data for a single character form Unicode's [emoji-data.txt](https://www.unicode.org/Public/16.0.0/ucd/emoji/emoji-data.txt) file:
+
+```ruby
+require "unicode/emoji"
+
+Unicode::Emoji.properties "☝" # => ["Emoji", "Emoji_Modifier_Base"]
+```
+
+## Also See
+
+- [Unicode® Technical Standard #51](https://www.unicode.org/reports/tr51/)
+- [Emoji categories](https://unicode.org/emoji/charts/emoji-ordering.html)
+- Ruby gem which displays [Emoji sequence names](https://github.com/janlelis/unicode-sequence_name) ([as website](https://character.construction/name))
+- Part of [unicode-x](https://github.com/janlelis/unicode-x)
+
+## MIT
+
+- Copyright (C) 2017-2024 Jan Lelis <https://janlelis.com>. Released under the MIT license.
+- Unicode data: https://www.unicode.org/copyright.html#Exhibit1