Module: CGI::Escape

Relationships & Source Files
Extension / Inclusion / Inheritance Descendants
Extended In: `::CGI`
Included In: `::CGI`
Defined in:	lib/cgi/escape.rb, ext/cgi/escape/escape.c, lib/cgi/escape.rb

Overview

Escape/unescape for ::CGI, HTML, URI.

Constant Summary

TABLE_FOR_ESCAPE_HTML__ =

The set of special characters and their escaped values

# File 'lib/cgi/escape.rb', line 72

{
  "'" => '&#39;',
  '&' => '&amp;',
  '"' => '&quot;',
  '<' => '&lt;',
  '>' => '&gt;',
}

Instance Method Summary

#escape(string)

URL-encode a string into application/x-www-form-urlencoded.
#escape_element(string, *elements)

Alias for #escapeElement.
#escape_html(string)

Alias for #escapeHTML.
#escape_uri_component(string)

Alias for #escapeURIComponent.
#escapeElement(string, *elements) (also: #escape_element)

Escape only the tags of certain HTML elements in string.
#escapeHTML(string) (also: #escape_html, #h)

Escape special characters in HTML, namely ‘&"<>.
#escapeURIComponent(string) (also: #escape_uri_component)

URL-encode a string following RFC 3986 Space characters (+“ ”+) are encoded with (+“%20”+).
#h(string)

Alias for #escapeHTML.
#unescape(string, encoding = @@accept_charset)

URL-decode an application/x-www-form-urlencoded string with encoding(optional).
#unescape_element(string, *elements)

Alias for #unescapeElement.
#unescape_html(string)

Alias for #unescapeHTML.
#unescape_uri_component(string, encoding = @@accept_charset)

Alias for #unescapeURIComponent.
#unescapeElement(string, *elements) (also: #unescape_element)

Undo escaping such as that done by CGI.escapeElement().
#unescapeHTML(string) (also: #unescape_html)

Unescape a string that has been HTML-escaped.
#unescapeURIComponent(string, encoding = @@accept_charset) (also: #unescape_uri_component)

URL-decode a string following RFC 3986 with encoding(optional).

Instance Method Details

#escape(string)

URL-encode a string into application/x-www-form-urlencoded. Space characters (+“ ”+) are encoded with plus signs (+“+”+)

url_encoded_string = CGI.escape("'Stop!' said Fred")
   # => "%27Stop%21%27saidFred"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 20


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

#escape_element(string, *elements)

Alias for #escapeElement.

[ GitHub ]

# File 'lib/cgi/escape.rb', line 223


alias escape_element escapeElement

#escape_html(string)

Alias for #escapeHTML.

[ GitHub ]

# File 'lib/cgi/escape.rb', line 164


alias escape_html escapeHTML

#escape_uri_component(string)

Alias for #escapeURIComponent.

[ GitHub ]

# File 'lib/cgi/escape.rb', line 55


alias escape_uri_component escapeURIComponent

#escapeElement(string, *elements) Also known as: #escape_element

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"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 191


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

#escapeHTML(string) Also known as: #escape_html, #h

Escape special characters in HTML, namely ‘&"<>

CGI.escapeHTML('Usage: foo "bar" <baz>')
   # => "Usage: foo &quot;bar&quot; &lt;baz&gt;"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 83


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

#escapeURIComponent(string) Also known as: #escape_uri_component

URL-encode a string following RFC 3986 Space characters (+“ ”+) are encoded with (+“%20”+)

url_encoded_string = CGI.escapeURIComponent("'Stop!' said Fred")
   # => "%27Stop%21%27%20said%20Fred"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 47


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

#h(string)

Alias for #escapeHTML.

[ GitHub ]

# File 'lib/cgi/escape.rb', line 165


alias h escapeHTML

#unescape(string, encoding = @@accept_charset)

URL-decode an application/x-www-form-urlencoded string with encoding(optional).

string = CGI.unescape("%27Stop%21%27saidFred")
   # => "'Stop!' said Fred"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 33


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

#unescape_element(string, *elements)

Alias for #unescapeElement.

[ GitHub ]

# File 'lib/cgi/escape.rb', line 226


alias unescape_element unescapeElement

#unescape_html(string)

Alias for #unescapeHTML.

[ GitHub ]

# File 'lib/cgi/escape.rb', line 168


alias unescape_html unescapeHTML

#unescape_uri_component(string, encoding = @@accept_charset)

Alias for #unescapeURIComponent.

[ GitHub ]

# File 'lib/cgi/escape.rb', line 69


alias unescape_uri_component unescapeURIComponent

#unescapeElement(string, *elements) Also known as: #unescape_element

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>"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 211


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

#unescapeHTML(string) Also known as: #unescape_html

Unescape a string that has been HTML-escaped

CGI.unescapeHTML("Usage: foo &quot;bar&quot; &lt;baz&gt;")
   # => "Usage: foo \"bar\" <baz>"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 105


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.dup
    case match
    when 'apos'                then "'"
    when 'amp'                 then '&'
    when 'quot'                then '"'
    when 'gt'                  then '>'
    when 'lt'                  then '<'
    when /\A#0*(\d+)\z/
      n = $1.to_i
      if n < charlimit
        n.chr(enc)
      else
        "&##{$1};"
      end
    when /\A#x([0-9a-f]+)\z/i
      n = $1.hex
      if n < charlimit
        n.chr(enc)
      else
        "&#x#{$1};"
      end
    else
      "&#{match};"
    end
  end
  string.force_encoding enc
end

#unescapeURIComponent(string, encoding = @@accept_charset) Also known as: #unescape_uri_component

URL-decode a string following RFC 3986 with encoding(optional).

string = CGI.unescapeURIComponent("%27Stop%21%27+said%20Fred")
   # => "'Stop!'+said Fred"

[ GitHub ]

# File 'lib/cgi/escape.rb', line 60


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