module CGI::Util
Constants
- RFC822_DAYS
-
Abbreviated day-of-week names specified by RFC 822
- RFC822_MONTHS
-
Abbreviated month names specified by RFC 822
- TABLE_FOR_ESCAPE_HTML__
-
The set of special characters and their escaped values
Public Instance Methods
# File lib/cgi/util.rb, line 7
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 URL-encode a string.
url_encoded_string = CGI::escape("'Stop!' said Fred")
# => "%27Stop%21%27+said+Fred"
# File lib/cgi/util.rb, line 111
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 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><A HREF="url"></A>"
print CGI::escapeElement('<BR><A HREF="url"></A>', ["A", "IMG"])
# "<BR><A HREF="url"></A>"
# File lib/cgi/util.rb, line 36 def escapeHTML(string) string.gsub(/['&\"<>]/, TABLE_FOR_ESCAPE_HTML__) end
Escape special characters in HTML, namely &"<>
CGI::escapeHTML('Usage: foo "bar" <baz>')
# => "Usage: foo "bar" <baz>"
# File lib/cgi/util.rb, line 182
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 = $1.dup
start_pos = lines.rindex(/^\s*<#{element}/i, end_pos)
lines[start_pos ... end_pos] = "__" + lines[start_pos ... end_pos].gsub(/\n(?!\z)/, "\n" + shift) + "__"
end
lines.gsub(/^((?:#{Regexp::quote(shift)})*)__(?=<\/?\w)/, '\1')
end Prettify (indent) an HTML string.
string is the HTML string to indent. shift is the indentation unit to use; it defaults to two spaces.
print CGI::pretty("<HTML><BODY></BODY></HTML>")
# <HTML>
# <BODY>
# </BODY>
# </HTML>
print CGI::pretty("<HTML><BODY></BODY></HTML>", "\t")
# <HTML>
# <BODY>
# </BODY>
# </HTML>
# File lib/cgi/util.rb, line 158
def rfc1123_date(time)
t = time.clone.gmtime
return format("%s, %.2d %s %.4d %.2d:%.2d:%.2d GMT",
RFC822_DAYS[t.wday], t.day, RFC822_MONTHS[t.month-1], t.year,
t.hour, t.min, t.sec)
end Format a Time object as a String using the format specified by RFC 1123.
CGI::rfc1123_date(Time.now) # Sat, 01 Jan 2000 00:00:00 GMT
# File lib/cgi/util.rb, line 17
def unescape(string,encoding=@@accept_charset)
str=string.tr('+', ' ').b.gsub(/((?:%[0-9a-fA-F]{2})+)/) do |m|
[m.delete('%')].pack('H*')
end.force_encoding(encoding)
str.valid_encoding? ? str : str.force_encoding(string.encoding)
end URL-decode a string with encoding(optional).
string = CGI::unescape("%27Stop%21%27+said+Fred")
# => "'Stop!' said Fred"
# File lib/cgi/util.rb, line 131
def unescapeElement(string, *elements)
elements = elements[0] if elements[0].kind_of?(Array)
unless elements.empty?
string.gsub(/<\/?(?:#{elements.join("|")})(?!\w)(?:.|\n)*?>/i) do
unescapeHTML($&)
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")
# "<BR><A HREF="url"></A>"
print CGI::unescapeElement(
CGI::escapeHTML('<BR><A HREF="url"></A>'), ["A", "IMG"])
# "<BR><A HREF="url"></A>"
# File lib/cgi/util.rb, line 43
def unescapeHTML(string)
return string unless string.include? '&'
enc = string.encoding
if enc != Encoding::UTF_8 && [Encoding::UTF_16BE, Encoding::UTF_16LE, Encoding::UTF_32BE, Encoding::UTF_32LE].include?(enc)
return 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
end
asciicompat = Encoding.compatible?(string, "a")
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 enc == Encoding::UTF_8 or
enc == Encoding::ISO_8859_1 && n < 256 or
asciicompat && n < 128
n.chr(enc)
else
"&##{$1};"
end
when /\A#x([0-9a-f]+)\z/i
n = $1.hex
if enc == Encoding::UTF_8 or
enc == Encoding::ISO_8859_1 && n < 256 or
asciicompat && n < 128
n.chr(enc)
else
"&#x#{$1};"
end
else
"&#{match};"
end
end
end Unescape a string that has been HTML-escaped
CGI::unescapeHTML("Usage: foo "bar" <baz>")
# => "Usage: foo \"bar\" <baz>"
Synonym for CGI::unescapeElement(str)
Ruby Core © 1993–2017 Yukihiro Matsumoto
Licensed under the Ruby License.
Ruby Standard Library © contributors
Licensed under their own licenses.