cyberweb 0.4.174

data/lib/cyberweb/cgi/core.rb

@@ -0,0 +1,638 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# Methods for generating HTML, parsing CGI-related parameters, and
+# generating HTTP responses.
+# =========================================================================== #
+module Cyberweb
+
+class CGI # === Cyberweb::CGI
+
+  require 'cyberweb/cgi/constants.rb'
+  require 'cyberweb/cgi/query_extension.rb'
+
+  # =========================================================================== #
+  # === MAX_MULTIPART_LENGTH
+  #
+  # MAX_MULTIPART_LENGTH is the maximum length of multipart data.
+  #
+  # The default value is:
+  #
+  #   128 * 1024 * 1024 bytes
+  #
+  # The default can be set to something else in the CGI constructor,
+  # via the :max_multipart_length key in the option hash.
+  #
+  # Also have a look at the CGI.new documentation.
+  # =========================================================================== #
+  MAX_MULTIPART_LENGTH = 128 * 1024 * 1024
+
+  # =========================================================================== #
+  # === $CGI_ENV
+  # =========================================================================== #
+  $CGI_ENV = ENV # for FCGI support, we keep a copy of the old ENV setting.
+
+  # =========================================================================== #
+  # Exception raised when there is an invalid encoding detected
+  # =========================================================================== #
+  class InvalidEncoding < Exception; end
+
+  # ========================================================================= #
+  # === initialize
+  #
+  # Create a new CGI instance.
+  #
+  # :call-seq:
+  #
+  #   CGI.new(tag_maker) { block }
+  #   CGI.new(options_hash = {}) { block }
+  #
+  #
+  # <tt>tag_maker</tt>::
+  #
+  #   This is the same as using the +options_hash+ form with the value <tt>{
+  #   :tag_maker => tag_maker }</tt> Note that it is recommended to use the
+  #   +options_hash+ form, since it also allows you specify the charset you
+  #   will accept.
+  #
+  # <tt>options_hash</tt>::
+  #
+  #   A Hash that recognizes three options:
+  #
+  #   <tt>:accept_charset</tt>::
+  #
+  #     specifies encoding of received query string.  If omitted,
+  #     <tt>@@accept_charset</tt> is used. If the encoding is not
+  #     valid, a CGI::InvalidEncoding will be raised.
+  #
+  #     Example. Suppose <tt>@@accept_charset</tt> is "UTF-8"
+  #
+  #     when not specified:
+  #
+  #         cgi=CGI.new      # @accept_charset # => "UTF-8"
+  #
+  #     when specified as "EUC-JP":
+  #
+  #         cgi=CGI.new(:accept_charset => "EUC-JP") # => "EUC-JP"
+  #
+  #   <tt>:tag_maker</tt>::
+  #
+  #     String that specifies which version of the HTML generation methods
+  #     to use. If not specified, no HTML generation methods will be loaded.
+  #
+  #     The following values are supported:
+  #
+  #       "html3"::   HTML 3.x
+  #       "html4"::   HTML 4.0
+  #       "html4Tr":: HTML 4.0 Transitional
+  #       "html4Fr":: HTML 4.0 with Framesets
+  #       "html5"::   HTML 5
+  #
+  #   <tt>:max_multipart_length</tt>::
+  #
+  #     Specifies maximum length of multipart data. Can be an Integer scalar or
+  #     a lambda, that will be evaluated when the request is parsed. This
+  #     allows more complex logic to be set when determining whether to accept
+  #     multipart data (e.g. consult a registered users upload allowance)
+  #
+  #     Default is 128 * 1024 * 1024 bytes
+  #
+  #         cgi = CGI.new(:max_multipart_length => 268435456) # simple scalar
+  #
+  #         cgi = CGI.new(:max_multipart_length => -> {check_filesystem}) # lambda
+  #
+  # <tt>block</tt>::
+  #
+  #   If provided, the block is called when an invalid encoding
+  #   is encountered.
+  #
+  #   For example:
+  #
+  #     encoding_errors = {}
+  #     cgi  =CGI.new(:accept_charset=>"EUC-JP") do |name,value|
+  #       encoding_errors[name] = value
+  #     end
+  #
+  # Finally, if the CGI object is not created in a standard CGI call
+  # environment (that is, it can't locate REQUEST_METHOD in its environment),
+  # then it will run in "offline" mode.
+  #
+  # In this mode, it reads its parameters from the command line or, failing
+  # that, from standard input.
+  #
+  # Otherwise, cookies and other parameters are parsed automatically 
+  # from the standard CGI locations, which varies according to the
+  # REQUEST_METHOD.
+  # ========================================================================= #
+  def initialize(
+      options = {}, &block
+    ) # :yields: name, value
+    reset # Set to a clean initial state here.
+    @accept_charset_error_block = block_given? ? block : nil
+    # ======================================================================= #
+    # The available options:
+    # ======================================================================= #
+    @options = {
+      accept_charset:       @@accept_charset,
+      max_multipart_length: MAX_MULTIPART_LENGTH
+    }
+    # ======================================================================= #
+    # And the passed options to this method.
+    # ======================================================================= #
+    case options
+    when Hash
+      @options.merge!(options)
+    when String # Assume that we wish to add the tag_maker entry here.
+      @options[:tag_maker] = options
+    end
+    @accept_charset = @options[:accept_charset]
+    @max_multipart_length = @options[:max_multipart_length]
+    if defined?(MOD_RUBY) && !ENV.key?('GATEWAY_INTERFACE')
+      Apache.request.setup_cgi_env
+    end
+
+    extend QueryExtension
+
+    initialize_query # set @params, @cookies
+    check_for_which_tag_maker_to_use
+  end
+
+  # ========================================================================= #
+  # === check_for_which_tag_maker_to_use
+  # ========================================================================= #
+  def check_for_which_tag_maker_to_use
+
+    case @options[:tag_maker] # case tag
+    # === html3
+    when 'html3'
+      require 'cyberweb/cgi/html.rb'
+      extend Html3
+      extend HtmlExtension
+    when 'html4'
+      require 'cyberweb/cgi/html.rb'
+      extend Html4
+      extend HtmlExtension
+    when 'html4Tr'
+      require 'cyberweb/cgi/html.rb'
+      extend Html4Tr
+      extend HtmlExtension
+    when 'html4Fr'
+      require 'cyberweb/cgi/html.rb'
+      extend Html4Tr
+      extend Html4Fr
+      extend HtmlExtension
+    # === html5
+    when 'html5'
+      require 'cyberweb/cgi/html.rb'
+      extend Html5
+      extend HtmlExtension
+    end
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    @multipart      = false
+    @output_cookies = nil
+    @output_hidden  = nil
+  end
+
+  # ========================================================================= #
+  # === stdinput
+  #
+  # Synonym for $stdin.
+  # ========================================================================= #
+  def stdinput
+    $stdin
+  end; private :stdinput
+
+  # ========================================================================= #
+  # === stdoutput
+  #
+  # Synonym for $stdout.
+  # ========================================================================= #
+  def stdoutput
+    $stdout
+  end; private :stdoutput
+
+  # ========================================================================= #
+  # === http_header
+  #
+  # Create an HTTP header block as a string.
+  #
+  # :call-seq:
+  #   http_header(content_type_string="text/html")
+  #   http_header(headers_hash)
+  #
+  # Includes the empty line that ends the header block.
+  #
+  # +content_type_string+::
+  #   If this form is used, this string is the <tt>Content-Type</tt>
+  # +headers_hash+::
+  #   A Hash of header values. The following header keys are recognized:
+  #
+  #   type:: The Content-Type header.  Defaults to "text/html"
+  #   charset:: The charset of the body, appended to the Content-Type header.
+  #   nph:: A boolean value.  If true, prepend protocol string and status
+  #         code, and date; and sets default values for "server" and
+  #         "connection" if not explicitly set.
+  #   status::
+  #     The HTTP status code as a String, returned as the Status header.  The
+  #     values are:
+  #
+  #     OK:: 200 OK
+  #     PARTIAL_CONTENT:: 206 Partial Content
+  #     MULTIPLE_CHOICES:: 300 Multiple Choices
+  #     MOVED:: 301 Moved Permanently
+  #     REDIRECT:: 302 Found
+  #     NOT_MODIFIED:: 304 Not Modified
+  #     BAD_REQUEST:: 400 Bad Request
+  #     AUTH_REQUIRED:: 401 Authorization Required
+  #     FORBIDDEN:: 403 Forbidden
+  #     NOT_FOUND:: 404 Not Found
+  #     METHOD_NOT_ALLOWED:: 405 Method Not Allowed
+  #     NOT_ACCEPTABLE:: 406 Not Acceptable
+  #     LENGTH_REQUIRED:: 411 Length Required
+  #     PRECONDITION_FAILED:: 412 Precondition Failed
+  #     SERVER_ERROR:: 500 Internal Server Error
+  #     NOT_IMPLEMENTED:: 501 Method Not Implemented
+  #     BAD_GATEWAY:: 502 Bad Gateway
+  #     VARIANT_ALSO_VARIES:: 506 Variant Also Negotiates
+  #
+  #   server:: The server software, returned as the Server header.
+  #   connection:: The connection type, returned as the Connection header (for
+  #                instance, "close".
+  #   length:: The length of the content that will be sent, returned as the
+  #            Content-Length header.
+  #   language:: The language of the content, returned as the Content-Language
+  #              header.
+  #   expires:: The time on which the current content expires, as a +Time+
+  #             object, returned as the Expires header.
+  #   cookie::
+  #     A cookie or cookies, returned as one or more Set-Cookie headers.  The
+  #     value can be the literal string of the cookie; a CGI::Cookie object;
+  #     an Array of literal cookie strings or Cookie objects; or a hash all of
+  #     whose values are literal cookie strings or Cookie objects.
+  #
+  #     These cookies are in addition to the cookies held in the
+  #     @output_cookies field.
+  #
+  #   Other headers can also be set; they are appended as key: value.
+  #
+  # Examples:
+  #
+  #   http_header
+  #     # Content-Type: text/html
+  #
+  #   http_header("text/plain")
+  #     # Content-Type: text/plain
+  #
+  #   http_header("nph"        => true,
+  #               "status"     => "OK",  # == "200 OK"
+  #                 # "status"     => "200 GOOD",
+  #               "server"     => ENV['SERVER_SOFTWARE'],
+  #               "connection" => "close",
+  #               "type"       => "text/html",
+  #               "charset"    => "iso-2022-jp",
+  #                 # Content-Type: text/html; charset=iso-2022-jp
+  #               "length"     => 103,
+  #               "language"   => "ja",
+  #               "expires"    => Time.now + 30,
+  #               "cookie"     => [cookie1, cookie2],
+  #               "my_header1" => "my_value"
+  #               "my_header2" => "my_value")
+  #
+  # This method does not perform charset conversion.
+  # ========================================================================= #
+  def http_header(
+      options = 'text/html'
+    )
+    if options.is_a? String
+      content_type = options
+      buf = _header_for_string(content_type)
+    elsif options.is_a? Hash
+      if options.size == 1 && options.has_key?('type')
+        content_type = options['type']
+        buf = _header_for_string(content_type)
+      else
+        buf = _header_for_hash(options.dup)
+      end
+    else
+      raise ArgumentError.new("expected String or Hash but got #{options.class}")
+    end
+    if defined?(MOD_RUBY)
+      _header_for_modruby(buf)
+      return ''
+    else
+      buf << EOL    # empty line of separator
+      return buf
+    end
+  end # http_header()
+
+  # ========================================================================= #
+  # This method is an alias for #http_header, when HTML5 tag maker is
+  # inactive.
+  #
+  # NOTE: use #http_header to create HTTP header blocks, this alias is
+  # only provided for backwards compatibility.
+  #
+  # Using #header with the HTML5 tag maker will create a <header> element.
+  # ========================================================================= #
+  alias header http_header # === header
+
+  # ========================================================================= #
+  # === _header_for_string
+  # ========================================================================= #
+  def _header_for_string(content_type)
+    buf = ''.dup
+    if nph?
+      buf << "#{$CGI_ENV['SERVER_PROTOCOL'] || 'HTTP/1.0'} 200 OK#{EOL}"
+      buf << "Date: #{CGI.rfc1123_date(Time.now)}#{EOL}"
+      buf << "Server: #{$CGI_ENV['SERVER_SOFTWARE']}#{EOL}"
+      buf << "Connection: close#{EOL}"
+    end
+    buf << "Content-Type: #{content_type}#{EOL}"
+    if @output_cookies
+      @output_cookies.each {|cookie| buf << "Set-Cookie: #{cookie}#{EOL}" }
+    end
+    return buf
+  end # _header_for_string
+  private :_header_for_string
+
+  # ========================================================================= #
+  # === _header_for_hash
+  # ========================================================================= #
+  def _header_for_hash(options)
+    buf = ''.dup
+    # ======================================================================= #
+    # Add charset to option['type']
+    # ======================================================================= #
+    options['type'] ||= 'text/html'.dup
+    charset = options.delete('charset')
+    options['type'] << "; charset=#{charset}" if charset
+    # ======================================================================= #
+    # NPH
+    # ======================================================================= #
+    options.delete('nph') if defined?(MOD_RUBY)
+    if options.delete('nph') || nph?()
+      protocol = $CGI_ENV['SERVER_PROTOCOL'] || 'HTTP/1.0'
+      status = options.delete('status')
+      status = HTTP_STATUS[status] || status || '200 OK'
+      buf << "#{protocol} #{status}#{EOL}"
+      buf << "Date: #{CGI.rfc1123_date(Time.now)}#{EOL}"
+      options['server'] ||= $CGI_ENV['SERVER_SOFTWARE'] || ''
+      options['connection'] ||= 'close'
+    end
+    # ======================================================================= #
+    # common headers
+    # ======================================================================= #
+    status = options.delete('status')
+    buf << "Status: #{HTTP_STATUS[status] || status}#{EOL}" if status
+    server = options.delete('server')
+    buf << "Server: #{server}#{EOL}" if server
+    connection = options.delete('connection')
+    buf << "Connection: #{connection}#{EOL}" if connection
+    type = options.delete('type')
+    buf << "Content-Type: #{type}#{EOL}" #if type
+    length = options.delete('length')
+    buf << "Content-Length: #{length}#{EOL}" if length
+    language = options.delete('language')
+    buf << "Content-Language: #{language}#{EOL}" if language
+    expires = options.delete('expires')
+    buf << "Expires: #{CGI.rfc1123_date(expires)}#{EOL}" if expires
+    # ======================================================================= #
+    # cookie
+    # ======================================================================= #
+    if cookie = options.delete('cookie')
+      case cookie
+      when String, Cookie
+        buf << "Set-Cookie: #{cookie}#{EOL}"
+      when Array
+        arr = cookie
+        arr.each {|c| buf << "Set-Cookie: #{c}#{EOL}" }
+      when Hash
+        hash = cookie
+        hash.each_value {|c| buf << "Set-Cookie: #{c}#{EOL}" }
+      end
+    end
+    if @output_cookies
+      @output_cookies.each {|c| buf << "Set-Cookie: #{c}#{EOL}" }
+    end
+    # ======================================================================= #
+    # Other headers
+    # ======================================================================= #
+    options.each { |key, value|
+      buf << "#{key}: #{value}#{EOL}"
+    }
+    return buf
+  end # _header_for_hash
+  private :_header_for_hash
+
+  # ========================================================================= #
+  # === nph?
+  # ========================================================================= #
+  def nph?
+    return /IIS\/(\d+)/.match($CGI_ENV['SERVER_SOFTWARE']) && $1.to_i < 5
+  end
+
+  # ========================================================================= #
+  # === _header_for_modruby
+  # ========================================================================= #
+  def _header_for_modruby(buf)
+    request = Apache::request
+    buf.scan(/([^:]+): (.+)#{EOL}/o) do |name, value|
+      $stderr.printf("name:%s value:%s\n", name, value) if $DEBUG
+      case name
+      when 'Set-Cookie'
+        request.headers_out.add(name, value)
+      when /^status$/i
+        request.status_line = value
+        request.status = value.to_i
+      when /^content-type$/i
+        request.content_type = value
+      when /^content-encoding$/i
+        request.content_encoding = value
+      when /^location$/i
+        request.status = 302 if request.status == 200
+        request.headers_out[name] = value
+      else
+        request.headers_out[name] = value
+      end
+    end
+    request.send_http_header
+    return ''
+  end; private :_header_for_modruby
+
+  # ========================================================================= #
+  # === out
+  #
+  # Print an HTTP header and body to $DEFAULT_OUTPUT ($>)
+  #
+  # :call-seq:
+  #   cgi.out(content_type_string='text/html')
+  #   cgi.out(headers_hash)
+  #
+  # +content_type_string+::
+  #   If a string is passed, it is assumed to be the content type.
+  #
+  # +headers_hash+::
+  #   This is a Hash of headers, similar to that used by #http_header.
+  #
+  # +block+::
+  #   A block is required and should evaluate to the body of the response.
+  #
+  # <tt>Content-Length</tt> is automatically calculated from the size of
+  # the String returned by the content block.
+  #
+  # If <tt>ENV['REQUEST_METHOD'] == "HEAD"</tt>, then only the header
+  # is output (the content block is still required, but it is ignored).
+  #
+  # If the charset is "iso-2022-jp" or "euc-jp" or "shift_jis" then the
+  # content is converted to this charset, and the language is set to "ja".
+  #
+  # Example:
+  #
+  #   cgi = CGI.new
+  #   cgi.out{ "string" }
+  #     # Content-Type: text/html
+  #     # Content-Length: 6
+  #     #
+  #     # string
+  #
+  #   cgi.out("text/plain") { "string" }
+  #     # Content-Type: text/plain
+  #     # Content-Length: 6
+  #     #
+  #     # string
+  #
+  #   cgi.out("nph"        => true,
+  #           "status"     => "OK",  # == "200 OK"
+  #           "server"     => ENV['SERVER_SOFTWARE'],
+  #           "connection" => "close",
+  #           "type"       => "text/html",
+  #           "charset"    => "iso-2022-jp",
+  #             # Content-Type: text/html; charset=iso-2022-jp
+  #           "language"   => "ja",
+  #           "expires"    => Time.now + (3600 * 24 * 30),
+  #           "cookie"     => [cookie1, cookie2],
+  #           "my_header1" => "my_value",
+  #           "my_header2" => "my_value") { "string" }
+  #      # HTTP/1.1 200 OK
+  #      # Date: Sun, 15 May 2011 17:35:54 GMT
+  #      # Server: Apache 2.2.0
+  #      # Connection: close
+  #      # Content-Type: text/html; charset=iso-2022-jp
+  #      # Content-Length: 6
+  #      # Content-Language: ja
+  #      # Expires: Tue, 14 Jun 2011 17:35:54 GMT
+  #      # Set-Cookie: foo
+  #      # Set-Cookie: bar
+  #      # my_header1: my_value
+  #      # my_header2: my_value
+  #      #
+  #      # string
+  # ========================================================================= #
+  def out(options = 'text/html') # :yield:
+    options = { 'type' => options } if options.is_a? String
+    content = yield
+    options['length'] = content.bytesize.to_s
+    output = stdoutput
+    output.binmode if defined? output.binmode
+    output.print http_header(options)
+    output.print content unless 'HEAD' == env_table['REQUEST_METHOD']
+  end
+
+  # ========================================================================= #
+  # === print
+  #
+  # Print an argument or list of arguments to the default output stream
+  #
+  #   cgi = CGI.new
+  #   cgi.print    # default:  cgi.print == $DEFAULT_OUTPUT.print
+  # ========================================================================= #
+  def print(*options)
+    stdoutput.print(*options)
+  end
+
+  # ========================================================================= #
+  # === CGI.parse
+  #
+  # Parse an HTTP query string into a hash of key=>value pairs.
+  #
+  #   params = CGI::parse("query_string")
+  #     # {"name1" => ["value1", "value2", ...],
+  #     #  "name2" => ["value1", "value2", ...], ... }
+  # ========================================================================= #
+  def self.parse(query)
+    params = {}
+    splitted = query.split(/[&;]/)
+    splitted.each { |pairs|
+      key, value = pairs.split('=', 2).map {|v|
+        CGI.unescape(v)
+      }
+      next unless key
+      params[key] ||= []
+      params[key].push(value) if value
+    }
+    params.default = [].freeze
+    return params
+  end
+
+  # =========================================================================== #
+  # Maximum content length of post data
+  # MAX_CONTENT_LENGTH  = 2 * 1024 * 1024
+  # =========================================================================== #
+
+  # =========================================================================== #
+  # === MAX_MULTIPART_COUNT
+  #
+  # Maximum number of request parameters when multipart
+  # =========================================================================== #
+  MAX_MULTIPART_COUNT = 128
+
+  # =========================================================================== #
+  # Return the accept character set for this CGI instance.
+  # =========================================================================== #
+  attr_reader :accept_charset
+
+  # =========================================================================== #
+  # @@accept_charset is default accept character set.
+  #
+  # This default value default is "UTF-8"
+  # If you want to change the default accept character set
+  # when create a new CGI instance, set this:
+  #
+  #   CGI.accept_charset = 'EUC-JP'
+  # =========================================================================== #
+  @@accept_charset = 'UTF-8'
+
+  # =========================================================================== #
+  # === CGI.accept_charset?
+  #
+  # Return the accept character set for all new CGI instances.
+  # =========================================================================== #
+  def self.accept_charset?
+    @@accept_charset
+  end; self.instance_eval { alias accept_charset accept_charset? } # === CGI.accept_charset
+
+  # =========================================================================== #
+  # === CGI.accept_charset=
+  #
+  # Set the accepted character set for all new CGI instances.
+  # =========================================================================== #
+  def self.accept_charset=(i)
+    @@accept_charset = i
+  end
+
+  # ========================================================================= #
+  # === env_table
+  #
+  # Synonym for ENV.
+  # ========================================================================= #
+  def env_table
+    ENV
+  end; private :env_table
+
+end; end # class CGI