模块 CGI::Util

常量

TABLE_FOR_ESCAPE_HTML__

特殊字符及其转义值

公共实例方法

escape(字符串) 点击切换源

将字符串 URL 编码为 application/x-www-form-urlencoded。空格字符 (+“ ”+) 使用加号 (+“+”+) 编码

url_encoded_string = CGI.escape("'Stop!' said Fred")
   # => "%27Stop%21%27+said+Fred"
# File lib/cgi/util.rb, line 14
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
escapeElement(字符串, *元素) 点击切换源

仅转义 string 中特定 HTML 元素的标签。

获取一个元素或多个元素或元素数组。每个元素由元素的名称指定,不带尖括号。这匹配该元素的开始和结束标签。打开标签的属性列表也将被转义(例如,属性值周围的双引号)。

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"
# File lib/cgi/util.rb, line 184
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
别名:escape_element
escapeHTML(字符串) 点击切换源

转义 HTML 中的特殊字符,即 ‘&"<>

CGI.escapeHTML('Usage: foo "bar" <baz>')
   # => "Usage: foo &quot;bar&quot; &lt;baz&gt;"
# File lib/cgi/util.rb, line 77
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
别名:escape_html, h
escapeURIComponent(字符串) 点击切换源

根据 RFC 3986 对字符串进行 URL 编码,空格字符 (+“ ”+) 使用 (+“%20”+) 编码

url_encoded_string = CGI.escapeURIComponent("'Stop!' said Fred")
   # => "%27Stop%21%27%20said%20Fred"
# File lib/cgi/util.rb, line 41
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
escape_element(字符串, *元素)

CGI.escapeElement(str) 的同义词

别名:escapeElement
escape_html(字符串)

CGI.escapeHTML(str) 的同义词

别名:escapeHTML
escape_uri_component(字符串)
h(string)
别名:escapeHTML
pretty(string, shift = " ") 点击切换源代码

美化(缩进)HTML 字符串。

string 是要缩进的 HTML 字符串。shift 是要使用的缩进单位;默认为两个空格。

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 246
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) 点击切换源代码

使用 RFC 1123 指定的格式,将 Time 对象格式化为 String

CGI.rfc1123_date(Time.now)
  # Sat, 01 Jan 2000 00:00:00 GMT
# File lib/cgi/util.rb, line 225
def rfc1123_date(time)
  time.getgm.strftime("%a, %d %b %Y %T GMT")
end
unescape(string, encoding = @@accept_charset) 点击切换源代码

使用编码(可选)对 application/x-www-form-urlencoded 字符串进行 URL 解码。

string = CGI.unescape("%27Stop%21%27+said+Fred")
   # => "'Stop!' said Fred"
# File lib/cgi/util.rb, line 27
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
unescapeElement(string, *elements) 点击切换源代码

撤消转义,例如 CGI.escapeElement() 所做的转义

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>"
# File lib/cgi/util.rb, line 204
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
别名:unescape_element
unescapeHTML(string) 点击切换源代码

对已进行 HTML 转义的字符串进行转义

CGI.unescapeHTML("Usage: foo &quot;bar&quot; &lt;baz&gt;")
   # => "Usage: foo \"bar\" <baz>"
# File lib/cgi/util.rb, line 107
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
别名:unescape_html
unescapeURIComponent(string, encoding = @@accept_charset) 点击切换源代码

使用 RFC 3986 和编码(可选)对字符串进行 URL 解码。

string = CGI.unescapeURIComponent("%27Stop%21%27+said%20Fred")
   # => "'Stop!'+said Fred"
# File lib/cgi/util.rb, line 54
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
unescape_element(string, *elements)
别名:unescapeElement
unescape_html(string)

CGI.unescapeHTML(str) 的同义词

别名:unescapeHTML
unescape_uri_component(string, encoding = @@accept_charset)