Module: CGI::Util

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

Constant Summary

RFC822_DAYS =

Abbreviated day-of-week names specified by RFC 822

# File 'lib/cgi/util.rb', line 178
```
%w[ Sun Mon Tue Wed Thu Fri Sat ]
```
RFC822_MONTHS =

Abbreviated month names specified by RFC 822

# File 'lib/cgi/util.rb', line 181
```
%w[ Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec ]
```

TABLE_FOR_ESCAPE_HTML__ =

The set of special characters and their escaped values

# File 'lib/cgi/util.rb', line 30

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

Instance Method Summary

#escape(string)

URL-encode a string.
#escape_element(string, *elements)

Alias for #escapeElement.
#escape_html(string)

Alias for #escapeHTML.
#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 '&"<>.
#h(string)

Alias for #escapeHTML.
#pretty(string, shift = " ")

Prettify (indent) an HTML string.
#rfc1123_date(time)

Format a Time object as a String using the format specified by RFC 1123.
#unescape(string, encoding = @@accept_charset)

URL-decode a string with encoding(optional).
#unescape_element(string, *elements)

Alias for #unescapeElement.
#unescape_html(string)

Alias for #unescapeHTML.
#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.

Instance Method Details

#escape(string)

URL-encode a string.

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

[ GitHub ]

# File 'lib/cgi/util.rb', line 12


def escape(string)
  encoding = string.encoding
  string.b.gsub(/([^ a-zA-Z0-9_.\-~]+)/) do |m|
    '%' + m.unpack('H2' * m.bytesize).join('%').upcase
  end.tr(' ', '+').force_encoding(encoding)
end

#escape_element(string, *elements)

Alias for #escapeElement.

[ GitHub ]

# File 'lib/cgi/util.rb', line 172


alias escape_element escapeElement

#escape_html(string)

Alias for #escapeHTML.

[ GitHub ]

# File 'lib/cgi/util.rb', line 122


alias escape_html escapeHTML

#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/util.rb', line 140


def escapeElement(string, *elements)
  elements = elements[0] if elements[0].kind_of?(Array)
  unless elements.empty?
    string.gsub(/<\/?(?:#{elements.join("|")})(?!\w)(?:.|\n)*?>/i) 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/util.rb', line 41


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
    return string
  end
  string.gsub(/['&\"<>]/, TABLE_FOR_ESCAPE_HTML__)
end

#h(string)

Alias for #escapeHTML.

[ GitHub ]

# File 'lib/cgi/util.rb', line 222


alias h escapeHTML

#pretty(string, shift = " ")

Prettify (indent) an HTML string.

string is the HTML string to indent. shift is the indentation unit to use; it defaults to two spaces.

print CGI::pretty("<HTML><BODY></BODY></HTML>")
  # <HTML>
  #   <BODY>
  #   </BODY>
  # </HTML>

print CGI::pretty("<HTML><BODY></BODY></HTML>", "\t")
  # <HTML>
  #         <BODY>
  #         </BODY>
  # </HTML>

[ GitHub ]

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


def pretty(string, shift = "  ")
  lines = string.gsub(/(?!\A)<.*?>/m, "\n\\0").gsub(/<.*?>(?!\n)/m, "\\0\n")
  end_pos = 0
  while end_pos = lines.index(/^<\/(\w+)/, end_pos)
    element = $1.dup
    start_pos = lines.rindex(/^\s*<#{element}/i, end_pos)
    lines[start_pos ... end_pos] = "__" + lines[start_pos ... end_pos].gsub(/\n(?!\z)/, "\n" + shift) + "__"
  end
  lines.gsub(/^((?:#{Regexp::quote(shift)})*)__(?=<\/?\w)/, '\1')
end

#rfc1123_date(time)

Format a Time object as a String using the format specified by RFC 1123.

CGI::rfc1123_date(Time.now)
  # Sat, 01 Jan 2000 00:00:00 GMT

[ GitHub ]

# File 'lib/cgi/util.rb', line 187


def rfc1123_date(time)
  t = time.clone.gmtime
  return format("%s, %.2d %s %.4d %.2d:%.2d:%.2d GMT",
                RFC822_DAYS[t.wday], t.day, RFC822_MONTHS[t.month-1], t.year,
                t.hour, t.min, t.sec)
end

#unescape(string, encoding = @@accept_charset)

URL-decode a string with encoding(optional).

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

[ GitHub ]

# File 'lib/cgi/util.rb', line 22


def unescape(string,encoding=@@accept_charset)
  str=string.tr('+', ' ').b.gsub(/((?:%[0-9a-fA-F]{2})+)/) do |m|
    [m.delete('%')].pack('H*')
  end.force_encoding(encoding)
  str.valid_encoding? ? str : str.force_encoding(string.encoding)
end

#unescape_element(string, *elements)

Alias for #unescapeElement.

[ GitHub ]

# File 'lib/cgi/util.rb', line 175


alias unescape_element unescapeElement

#unescape_html(string)

Alias for #unescapeHTML.

[ GitHub ]

# File 'lib/cgi/util.rb', line 125


alias unescape_html unescapeHTML

#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/util.rb', line 160


def unescapeElement(string, *elements)
  elements = elements[0] if elements[0].kind_of?(Array)
  unless elements.empty?
    string.gsub(/&lt;\/?(?:#{elements.join("|")})(?!\w)(?:.|\n)*?&gt;/i) 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/util.rb', line 65


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.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
end