Module: Unicode::Emoji

Defined in:

lib/unicode/emoji.rb,
lib/unicode/emoji/index.rb,
lib/unicode/emoji/constants.rb

Constant Summary

PROPERTY_NAMES =

{
  E: "Emoji",
  B: "Emoji_Modifier_Base",
  M: "Emoji_Modifier",
  C: "Emoji_Component",
  P: "Emoji_Presentation",
  X: "Extended_Pictographic",
}

EMOJI_VARIATION_SELECTOR =

0xFE0F

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

TEXT_PRESENTATION =

INDEX[:PROPERTIES].select{ |ord, props| props.include?(:E) && !props.include?(:P) }.keys.freeze

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

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

RECOMMENDED_SUBDIVISION_FLAGS =

INDEX[:TAGS].freeze

RECOMMENDED_ZWJ_SEQUENCES =

INDEX[:ZWJ].freeze

LIST =

INDEX[:LIST].freeze.each_value(&:freeze)

LIST_REMOVED_KEYS =

[
  "Smileys & People",
]

REGEX =

Matches basic singleton emoji and all kind of sequences, but restrict zwj and tag sequences to known sequences (rgi)

Regexp.compile(emoji_rgi_sequence)

REGEX_VALID =

Matches basic singleton emoji and all kind of valid sequences

Regexp.compile(emoji_valid_sequence)

REGEX_WELL_FORMED =

Matches basic singleton emoji and all kind of sequences

Regexp.compile(emoji_well_formed_sequence)

REGEX_BASIC =

Matches only basic single, non-textual emoji Ignores “components” like modifiers or simple digits

Regexp.compile(
  "(?!" + emoji_component + ")" + emoji_presentation_sequence
)

REGEX_TEXT =

Matches only basic single, textual emoji Ignores “components” like modifiers or simple digits

Regexp.compile(
  "(?!" + emoji_component + ")" + text_presentation_sequence
)

REGEX_ANY =

Matches any emoji-related codepoint - Use with caution (returns partil matches)

Regexp.compile(
  emoji_character
)

REGEX_INCLUDE_TEXT =

Combined REGEXes which also match for TEXTUAL emoji

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)

REGEX_PICTO =

Regexp.compile(
  picto
)

REGEX_PICTO_NO_EMOJI =

Regexp.compile(
  picto_no_emoji
)

VERSION =

"2.7.1"

EMOJI_VERSION =

"13.1"

CLDR_VERSION =

"38.1"

DATA_DIRECTORY =

File.expand_path(File.dirname(__FILE__) + "/../../../data/").freeze

INDEX_FILENAME =

(DATA_DIRECTORY + "/emoji.marshal.gz").freeze

Class Method Summary

• .get_codepoint_value(char) ⇒ Object
• .list(key = nil, sub_key = nil) ⇒ Object
• .properties(char) ⇒ Object

Class Method Details

.get_codepoint_value(char) ⇒ Object

# File 'lib/unicode/emoji.rb', line 232

def self.get_codepoint_value(char)
  ord = nil

  if char.valid_encoding?
    ord = char.ord
  elsif char.encoding.name == "UTF-8"
    begin
      ord = char.unpack("U*")[0]
    rescue ArgumentError
    end
  end

  if ord
    ord
  else
    raise(ArgumentError, "Unicode::Emoji must be given a valid string")
  end
end

.list(key = nil, sub_key = nil) ⇒ Object

# File 'lib/unicode/emoji.rb', line 224

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

.properties(char) ⇒ Object

# File 'lib/unicode/emoji.rb', line 213

def self.properties(char)
  ord = get_codepoint_value(char)
  props = INDEX[:PROPERTIES][ord]

  if props
    props.map{ |prop| PROPERTY_NAMES[prop] }
  else
    # nothing
  end
end