class FriendlyId::SlugString

This method can be used by developers wishing to debug the {APPROXIMATIONS} hashes, which are written in a hard-to-read format. @return Hash @example

> ruby -rrubygems -rlib/friendly_id -e 'p FriendlyId::SlugString.dump_approximations'

{:common => {“À”=>“A”, “Á”=>“A”, “”=>“A”, “Ô=>“A”, “Ä”=>“A”, “Å”=>“A”, “Æ”=>“AE”, “Ç”=>“C”, “È”=>“E”, “É”=>“E”, “Ê”=>“E”, “Ë”=>“E”, “Ì”=>“I”, “Í”=>“I”, “Δ=>“I”, “Ï”=>“I”, “Д=>“D”, “Ñ”=>“N”, “Ò”=>“O”, “Ó”=>“O”, “Ô”=>“O”, “Õ”=>“O”, “Ö”=>“O”, “×”=>“x”, “Ø”=>“O”, “Ù”=>“U”, “Ú”=>“U”, “Û”=>“U”, “Ü”=>“U”, “Ý”=>“Y”, “Þ”=>“Th”, “ß”=>“ss”, “à”=>“a”, “á”=>“a”, “â”=>“a”, “ã”=>“a”, “ä”=>“a”, “å”=>“a”, “æ”=>“ae”, “ç”=>“c”, “è”=>“e”, “é”=>“e”, “ê”=>“e”, “ë”=>“e”, “ì”=>“i”, “í”=>“i”, “î”=>“i”, “ï”=>“i”, “ð”=>“d”, “ñ”=>“n”, “ò”=>“o”, “ó”=>“o”, “ô”=>“o”, “õ”=>“o”, “ö”=>“o”, “ø”=>“o”, “ù”=>“u”, “ú”=>“u”, “û”=>“u”, “ü”=>“u”, “ý”=>“y”, “þ”=>“th”, “ÿ”=>“y”, “Ā”=>“A”, “ā”=>“a”, “Ă”=>“A”, “ă”=>“a”, “Ą”=>“A”, “ą”=>“a”, “Ć”=>“C”, “ć”=>“c”, “Ĉ”=>“C”, “ĉ”=>“c”, “Ċ”=>“C”, “ċ”=>“c”, “Č”=>“C”, “č”=>“c”, “Ď”=>“D”, “ď”=>“d”, “Đ”=>“D”, “đ”=>“d”, “Ē”=>“E”, “ē”=>“e”, “Ĕ”=>“E”, “ĕ”=>“e”, “Ė”=>“E”, “ė”=>“e”, “Ę”=>“E”, “ę”=>“e”, “Ě”=>“E”, “ě”=>“e”, “Ĝ”=>“G”, “ĝ”=>“g”, “Ğ”=>“G”, “ğ”=>“g”, “Ġ”=>“G”, “ġ”=>“g”, “Ģ”=>“G”, “ģ”=>“g”, “Ĥ”=>“H”, “ĥ”=>“h”, “Ħ”=>“H”, “ħ”=>“h”, “Ĩ”=>“I”, “ĩ”=>“i”, “Ī”=>“I”, “ī”=>“i”, “Ĭ”=>“I”, “ĭ”=>“i”, “Į”=>“I”, “į”=>“i”, “İ”=>“I”, “ı”=>“i”, “IJ”=>“IJ”, “ij”=>“ij”, “Ĵ”=>“J”, “ĵ”=>“j”, “Ķ”=>“K”, “ķ”=>“k”, “ĸ”=>“k”, “Ĺ”=>“L”, “ĺ”=>“l”, “Ļ”=>“L”, “ļ”=>“l”, “Ľ”=>“L”, “ľ”=>“l”, “Ŀ”=>“L”, “ŀ”=>“l”, “Ł”=>“L”, “ł”=>“l”, “Ń”=>“N”, “ń”=>“n”, “Ņ”=>“N”, “ņ”=>“n”, “Ň”=>“N”, “ň”=>“n”, “ʼn”=>“'n”, “Ŋ”=>“NG”, “ŋ”=>“ng”, “Ō”=>“O”, “ō”=>“o”, “Ŏ”=>“O”, “ŏ”=>“o”, “Ő”=>“O”, “ő”=>“o”, “Œ”=>“OE”, “œ”=>“oe”, “Ŕ”=>“R”, “ŕ”=>“r”, “Ŗ”=>“R”, “ŗ”=>“r”, “Ř”=>“R”, “ř”=>“r”, “Ś”=>“S”, “ś”=>“s”, “Ŝ”=>“S”, “ŝ”=>“s”, “Ş”=>“S”, “ş”=>“s”, “Š”=>“S”, “š”=>“s”, “Ţ”=>“T”, “ţ”=>“t”, “Ť”=>“T”, “ť”=>“t”, “Ŧ”=>“T”, “ŧ”=>“t”, “Ũ”=>“U”, “ũ”=>“u”, “Ū”=>“U”, “ū”=>“u”, “Ŭ”=>“U”, “ŭ”=>“u”, “Ů”=>“U”, “ů”=>“u”, “Ű”=>“U”, “ű”=>“u”, “Ų”=>“U”, “ų”=>“u”, “Ŵ”=>“W”, “ŵ”=>“w”, “Ŷ”=>“Y”, “ŷ”=>“y”, “Ÿ”=>“Y”, “Ź”=>“Z”, “ź”=>“z”, “Ż”=>“Z”, “ż”=>“z”, “Ž”=>“Z”, “ž”=>“z”}, :german => {“ü”=>“ue”, “ö”=>“oe”, “ä”=>“ae”}, :spanish => {“Ñ”=>“Nn”, “ñ”=>“nn”}}

# File lib/friendly_id/slug_string.rb, line 102
def self.dump_approximations
  Hash[APPROXIMATIONS.map do |name, approx|
    [name, Hash[approx.map {|key, value| [[key].pack("U*"), [value].flatten.pack("U*")]}]]
  end]
end

@param string [String] The string to use as the basis of the SlugString.

# File lib/friendly_id/slug_string.rb, line 110
def initialize(string)
  super string.to_s
end

Approximate an ASCII string. This works only for Western strings using characters that are Roman-alphabet characters + diacritics. Non-letter characters are left unmodified.

string = SlugString.new "Łódź, Poland"
string.approximate_ascii                 # => "Lodz, Poland"
string = SlugString.new "日本"
string.approximate_ascii                 # => "日本"

You can pass any key(s) from {APPROXIMATIONS} as arguments. This allows for contextual approximations. By default; :spanish and :german are provided:

string = SlugString.new "Jürgen Müller"
string.approximate_ascii                 # => "Jurgen Muller"
string.approximate_ascii :german        # => "Juergen Mueller"
string = SlugString.new "¡Feliz año!"
string.approximate_ascii                 # => "¡Feliz ano!"
string.approximate_ascii :spanish       # => "¡Feliz anno!"

You can modify the built-in approximations, or add your own:

# Make Spanish use "nh" rather than "nn"
FriendlyId::SlugString::APPROXIMATIONS[:spanish] = {
  # Ñ => "Nh"
  209 => [78, 104],
  # ñ => "nh"
  241 => [110, 104]
}

It's also possible to use a custom approximation for all strings:

FriendlyId::SlugString.approximations << :german

Notice that this method does not simply convert to ASCII; if you want to remove non-ASCII characters such as “¡” and “¿”, use {#to_ascii!}:

string.approximate_ascii!(:spanish)       # => "¡Feliz anno!"
string.to_ascii!                          # => "Feliz anno!"

@param *args <Symbol> @return String

# File lib/friendly_id/slug_string.rb, line 155
def approximate_ascii!(*args)
  @maps = (self.class.approximations + args + [:common]).flatten.uniq
  @wrapped_string = normalize_utf8(:c).unpack("U*").map { |char| approx_char(char) }.flatten.pack("U*")
end

Removes leading and trailing spaces or dashses, and replaces multiple whitespace characters with a single space. @return String

# File lib/friendly_id/slug_string.rb, line 163
def clean!
  @wrapped_string = @wrapped_string.gsub(/\A\-|\-\z/, '').gsub(/\s+/u, ' ').strip
end

Lowercases the string. Note that this works for Unicode strings, though your milage may vary with Greek and Turkic strings. @return String

# File lib/friendly_id/slug_string.rb, line 170
def downcase!
  @wrapped_string = apply_mapping :lowercase_mapping
end

Normalize the string for use as a FriendlyId. Note that in this context, normalize means, strip, remove non-letters/numbers, downcasing and converting whitespace to dashes. ActiveSupport::Multibyte::Chars#normalize is aliased to normalize_utf8 in this subclass. @return String

# File lib/friendly_id/slug_string.rb, line 217
def normalize!
  clean!
  word_chars!
  downcase!
  with_dashes!
end

Normalize the string for a given {FriendlyId::Configuration}. @param config [FriendlyId::Configuration] @return String

# File lib/friendly_id/slug_string.rb, line 199
def normalize_for!(config)
  if config.normalizer?
    @wrapped_string = config.normalizer.call(to_s)
  else
    approximate_ascii! if config.approximate_ascii?
    to_ascii! if config.strip_non_ascii?
    normalize!
  end
end

Delete any non-ascii characters. @return String

# File lib/friendly_id/slug_string.rb, line 232
def to_ascii!
  @wrapped_string = normalize_utf8(:c).unpack("U*").reject {|char| char > 127}.pack("U*")
end

Truncate the string to max length. @return String

# File lib/friendly_id/slug_string.rb, line 226
def truncate!(max)
  @wrapped_string = self[0...max].to_s if length > max
end

Upper-cases the string. Note that this works for Unicode strings, though your milage may vary with Greek and Turkic strings. @return String

# File lib/friendly_id/slug_string.rb, line 239
def upcase!
  @wrapped_string = apply_mapping :uppercase_mapping
end

Validate that the slug string is not blank or reserved, and truncate it to the max length if necessary. @param config [FriendlyId::Configuration] @return String @raise FriendlyId::BlankError @raise FriendlyId::ReservedError

# File lib/friendly_id/slug_string.rb, line 249
def validate_for!(config)
  truncate!(config.max_length)
  raise FriendlyId::BlankError if blank?
  raise FriendlyId::ReservedError if config.reserved?(self)
  self
end

Replaces whitespace with dashes (“-”). @return String

# File lib/friendly_id/slug_string.rb, line 258
def with_dashes!
  @wrapped_string = @wrapped_string.gsub(/[\s\-]+/u, '-')
end

Remove any non-word characters. @return String

# File lib/friendly_id/slug_string.rb, line 176
def word_chars!
  @wrapped_string = normalize_utf8(:c).unpack("U*").map { |char|
    case char
    # control chars
    when 0..31
    # punctuation; 45 is "-" (HYPHEN-MINUS) and allowed
    when 33..44
    # more puncuation
    when 46..47
    # more puncuation and other symbols
    when 58..64
    # brackets and other symbols
    when 91..96
    # braces, pipe, tilde, etc.
    when 123..191
    else char
    end
  }.compact.pack("U*")
end