ruby/lib/cgi/escape.rb

# frozen_string_literal: true

# Since Ruby 4.0, \CGI is a small holder for various escaping methods, included from CGI::Escape
#
#    require 'cgi/escape'
#
#    CGI.escape("Ruby programming language")
#    #=> "Ruby+programming+language"
#    CGI.escapeURIComponent("Ruby programming language")
#    #=> "Ruby%20programming%20language"
#
# See CGI::Escape module for methods list and their description.
class CGI
  module Escape; end
  include Escape
  extend Escape
  module EscapeExt; end # :nodoc:
end

# Web-related escape/unescape functionality.
module CGI::Escape
  @@accept_charset = Encoding::UTF_8 unless defined?(@@accept_charset)

  # URL-encode a string into application/x-www-form-urlencoded.
  # Space characters (<tt>" "</tt>) are encoded with plus signs (<tt>"+"</tt>)
  #   url_encoded_string = CGI.escape("'Stop!' said Fred")
  #      # => "%27Stop%21%27+said+Fred"
  def escape(string)
    encoding = string.encoding
    buffer = string.b
    buffer.gsub!(/([^ a-zA-Z0-9_.\-~]+)/) do |m|
      '%' + m.unpack('H2' * m.bytesize).join('%').upcase
    end
    buffer.tr!(' ', '+')
    buffer.force_encoding(encoding)
  end

  # URL-decode an application/x-www-form-urlencoded string with encoding(optional).
  #   string = CGI.unescape("%27Stop%21%27+said+Fred")
  #      # => "'Stop!' said Fred"
  def unescape(string, encoding = @@accept_charset)
    str = string.tr('+', ' ')
    str = str.b
    str.gsub!(/((?:%[0-9a-fA-F]{2})+)/) do |m|
      [m.delete('%')].pack('H*')
    end
    str.force_encoding(encoding)
    str.valid_encoding? ? str : str.force_encoding(string.encoding)
  end

  # URL-encode a string following RFC 3986
  # Space characters (<tt>" "</tt>) are encoded with (<tt>"%20"</tt>)
  #   url_encoded_string = CGI.escapeURIComponent("'Stop!' said Fred")
  #      # => "%27Stop%21%27%20said%20Fred"
  def escapeURIComponent(string)
    encoding = string.encoding
    buffer = string.b
    buffer.gsub!(/([^a-zA-Z0-9_.\-~]+)/) do |m|
      '%' + m.unpack('H2' * m.bytesize).join('%').upcase
    end
    buffer.force_encoding(encoding)
  end
  alias escape_uri_component escapeURIComponent

  # URL-decode a string following RFC 3986 with encoding(optional).
  #   string = CGI.unescapeURIComponent("%27Stop%21%27+said%20Fred")
  #      # => "'Stop!'+said Fred"
  def unescapeURIComponent(string, encoding = @@accept_charset)
    str = string.b
    str.gsub!(/((?:%[0-9a-fA-F]{2})+)/) do |m|
      [m.delete('%')].pack('H*')
    end
    str.force_encoding(encoding)
    str.valid_encoding? ? str : str.force_encoding(string.encoding)
  end

  alias unescape_uri_component unescapeURIComponent

  # The set of special characters and their escaped values
  TABLE_FOR_ESCAPE_HTML__ = { # :nodoc:
    "'" => '&#39;',
    '&' => '&amp;',
    '"' => '&quot;',
    '<' => '&lt;',
    '>' => '&gt;',
  }

  # \Escape special characters in HTML, namely <tt>'&\"<></tt>
  #   CGI.escapeHTML('Usage: foo "bar" <baz>')
  #      # => "Usage: foo &quot;bar&quot; &lt;baz&gt;"
  def escapeHTML(string)
    enc = string.encoding
    unless enc.ascii_compatible?
      if enc.dummy?
        origenc = enc
        enc = Encoding::Converter.asciicompat_encoding(enc)
        string = enc ? string.encode(enc) : string.b
      end
      table = Hash[TABLE_FOR_ESCAPE_HTML__.map {|pair|pair.map {|s|s.encode(enc)}}]
      string = string.gsub(/#{"['&\"<>]".encode(enc)}/, table)
      string.encode!(origenc) if origenc
      string
    else
      string = string.b
      string.gsub!(/['&\"<>]/, TABLE_FOR_ESCAPE_HTML__)
      string.force_encoding(enc)
    end
  end

  # Unescape a string that has been HTML-escaped
  #   CGI.unescapeHTML("Usage: foo &quot;bar&quot; &lt;baz&gt;")
  #      # => "Usage: foo \"bar\" <baz>"
  def unescapeHTML(string)
    enc = string.encoding
    unless enc.ascii_compatible?
      if enc.dummy?
        origenc = enc
        enc = Encoding::Converter.asciicompat_encoding(enc)
        string = enc ? string.encode(enc) : string.b
      end
      string = string.gsub(Regexp.new('&(apos|amp|quot|gt|lt|#[0-9]+|#x[0-9A-Fa-f]+);'.encode(enc))) do
        case $1.encode(Encoding::US_ASCII)
        when 'apos'                then "'".encode(enc)
        when 'amp'                 then '&'.encode(enc)
        when 'quot'                then '"'.encode(enc)
        when 'gt'                  then '>'.encode(enc)
        when 'lt'                  then '<'.encode(enc)
        when /\A#0*(\d+)\z/        then $1.to_i.chr(enc)
        when /\A#x([0-9a-f]+)\z/i  then $1.hex.chr(enc)
        end
      end
      string.encode!(origenc) if origenc
      return string
    end
    return string unless string.include? '&'
    charlimit = case enc
                when Encoding::UTF_8; 0x10ffff
                when Encoding::ISO_8859_1; 256
                else 128
                end
    string = string.b
    string.gsub!(/&(apos|amp|quot|gt|lt|\#[0-9]+|\#[xX][0-9A-Fa-f]+);/) do
      match = $1
      case match
      when 'apos'                then "'"
      when 'amp'                 then '&'
      when 'quot'                then '"'
      when 'gt'                  then '>'
      when 'lt'                  then '<'
      else
        # Numeric character reference. Decode into the binary buffer so that a
        # non-ASCII byte already present in it never triggers an encoding
        # compatibility error on concatenation; the trailing force_encoding
        # re-tags the whole buffer. This mirrors the C extension's
        # optimized_unescape_html.
        n = match.start_with?('#x', '#X') ? match[2..-1].hex : match[1..-1].to_i
        if n >= charlimit
          "&#{match};"            # out of range: keep the reference verbatim
        elsif charlimit > 256
          [n].pack('U').b         # UTF-8: code point bytes, surrogates included (like rb_enc_mbcput)
        else
          n.chr.b                 # ISO-8859-1 / ASCII: single byte
        end
      end
    end
    string.force_encoding enc
  end

  # TruffleRuby runs the pure-Ruby variant faster, do not use the C extension there
  unless RUBY_ENGINE == 'truffleruby'
    begin
      require 'cgi/escape.so'
    rescue LoadError
    end
  end

  # Aliases must be defined on EscapeExt so they resolve to the C methods.
  target = defined?(CGI::EscapeExt) && CGI::EscapeExt.method_defined?(:escapeHTML) ? CGI::EscapeExt : self
  target.module_eval do
    alias escape_html escapeHTML
    alias h escapeHTML
    alias unescape_html unescapeHTML
  end

  # \Escape only the tags of certain HTML elements in +string+.
  #
  # Takes an element or elements or array of elements.  Each element
  # is specified by the name of the element, without angle brackets.
  # This matches both the start and the end tag of that element.
  # The attribute list of the open tag will also be escaped (for
  # instance, the double-quotes surrounding attribute values).
  #
  #   print CGI.escapeElement('<BR><A HREF="url"></A>', "A", "IMG")
  #     # "<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt"
  #
  #   print CGI.escapeElement('<BR><A HREF="url"></A>', ["A", "IMG"])
  #     # "<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt"
  def escapeElement(string, *elements)
    elements = elements[0] if elements[0].kind_of?(Array)
    unless elements.empty?
      string.gsub(/<\/?(?:#{elements.join("|")})\b[^<>]*+>?/im) do
        CGI.escapeHTML($&)
      end
    else
      string
    end
  end

  # Undo escaping such as that done by CGI.escapeElement
  #
  #   print CGI.unescapeElement(
  #           CGI.escapeHTML('<BR><A HREF="url"></A>'), "A", "IMG")
  #     # "&lt;BR&gt;<A HREF="url"></A>"
  #
  #   print CGI.unescapeElement(
  #           CGI.escapeHTML('<BR><A HREF="url"></A>'), ["A", "IMG"])
  #     # "&lt;BR&gt;<A HREF="url"></A>"
  def unescapeElement(string, *elements)
    elements = elements[0] if elements[0].kind_of?(Array)
    unless elements.empty?
      string.gsub(/&lt;\/?(?:#{elements.join("|")})\b(?>[^&]+|&(?![gl]t;)\w+;)*(?:&gt;)?/im) do
        unescapeHTML($&)
      end
    else
      string
    end
  end

  alias escape_element escapeElement

  alias unescape_element unescapeElement

end