2015-12-16 00:07:31 -05:00
|
|
|
# frozen_string_literal: false
|
2011-05-13 16:03:21 -04:00
|
|
|
#--
|
2004-03-24 06:53:31 -05:00
|
|
|
# = uri/common.rb
|
2002-01-10 03:00:51 -05:00
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# Author:: Akira Yamada <akira@ruby-lang.org>
|
|
|
|
# Revision:: $Id$
|
2009-03-05 22:56:38 -05:00
|
|
|
# License::
|
2004-03-24 06:53:31 -05:00
|
|
|
# You can redistribute it and/or modify it under the same term as Ruby.
|
2002-01-10 03:00:51 -05:00
|
|
|
#
|
2011-05-13 16:03:21 -04:00
|
|
|
# See URI for general documentation
|
|
|
|
#
|
2002-01-10 03:00:51 -05:00
|
|
|
|
2014-06-21 20:22:19 -04:00
|
|
|
require "uri/rfc2396_parser"
|
|
|
|
require "uri/rfc3986_parser"
|
2008-09-10 05:34:49 -04:00
|
|
|
|
2014-06-21 20:22:19 -04:00
|
|
|
module URI
|
|
|
|
REGEXP = RFC2396_REGEXP
|
|
|
|
Parser = RFC2396_Parser
|
|
|
|
RFC3986_PARSER = RFC3986_Parser.new
|
2008-09-10 05:34:49 -04:00
|
|
|
|
2011-05-12 16:39:11 -04:00
|
|
|
# URI::Parser.new
|
2008-09-10 05:34:49 -04:00
|
|
|
DEFAULT_PARSER = Parser.new
|
|
|
|
DEFAULT_PARSER.pattern.each_pair do |sym, str|
|
|
|
|
unless REGEXP::PATTERN.const_defined?(sym)
|
|
|
|
REGEXP::PATTERN.const_set(sym, str)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
DEFAULT_PARSER.regexp.each_pair do |sym, str|
|
|
|
|
const_set(sym, str)
|
|
|
|
end
|
2002-01-10 03:00:51 -05:00
|
|
|
|
2004-07-17 09:14:35 -04:00
|
|
|
module Util # :nodoc:
|
2002-01-10 03:00:51 -05:00
|
|
|
def make_components_hash(klass, array_hash)
|
|
|
|
tmp = {}
|
|
|
|
if array_hash.kind_of?(Array) &&
|
2004-03-24 06:53:31 -05:00
|
|
|
array_hash.size == klass.component.size - 1
|
|
|
|
klass.component[1..-1].each_index do |i|
|
|
|
|
begin
|
|
|
|
tmp[klass.component[i + 1]] = array_hash[i].clone
|
|
|
|
rescue TypeError
|
|
|
|
tmp[klass.component[i + 1]] = array_hash[i]
|
|
|
|
end
|
|
|
|
end
|
2002-01-10 03:00:51 -05:00
|
|
|
|
|
|
|
elsif array_hash.kind_of?(Hash)
|
2004-03-24 06:53:31 -05:00
|
|
|
array_hash.each do |key, value|
|
|
|
|
begin
|
|
|
|
tmp[key] = value.clone
|
|
|
|
rescue TypeError
|
|
|
|
tmp[key] = value
|
|
|
|
end
|
|
|
|
end
|
2002-01-10 03:00:51 -05:00
|
|
|
else
|
2009-03-05 22:56:38 -05:00
|
|
|
raise ArgumentError,
|
2014-08-27 08:21:41 -04:00
|
|
|
"expected Array of or Hash of components of #{klass} (#{klass.component[1..-1].join(', ')})"
|
2002-01-10 03:00:51 -05:00
|
|
|
end
|
|
|
|
tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase
|
|
|
|
|
|
|
|
return tmp
|
|
|
|
end
|
|
|
|
module_function :make_components_hash
|
|
|
|
end
|
|
|
|
|
2011-05-12 16:39:11 -04:00
|
|
|
# module for escaping unsafe characters with codes.
|
2002-01-10 03:00:51 -05:00
|
|
|
module Escape
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI.escape(str [, unsafe])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +str+::
|
|
|
|
# String to replaces in.
|
|
|
|
# +unsafe+::
|
|
|
|
# Regexp that matches all symbols that must be replaced with codes.
|
2016-11-08 06:57:00 -05:00
|
|
|
# By default uses <tt>UNSAFE</tt>.
|
2005-11-12 21:02:24 -05:00
|
|
|
# When this argument is a String, it represents a character set.
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Escapes the string, replacing all unsafe characters with codes.
|
|
|
|
#
|
2016-10-20 04:03:01 -04:00
|
|
|
# This method is obsolete and should not be used. Instead, use
|
2017-01-23 12:02:08 -05:00
|
|
|
# CGI.escape, URI.encode_www_form or URI.encode_www_form_component
|
2016-10-20 04:03:01 -04:00
|
|
|
# depending on your specific use case.
|
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
2005-06-24 00:18:16 -04:00
|
|
|
# enc_uri = URI.escape("http://example.com/?a=\11\15")
|
2004-03-24 06:53:31 -05:00
|
|
|
# p enc_uri
|
2005-06-24 00:18:16 -04:00
|
|
|
# # => "http://example.com/?a=%09%0D"
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# p URI.unescape(enc_uri)
|
2005-06-24 00:18:16 -04:00
|
|
|
# # => "http://example.com/?a=\t\r"
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
2005-11-12 21:02:24 -05:00
|
|
|
# p URI.escape("@?@!", "!?")
|
|
|
|
# # => "@%3F@%21"
|
|
|
|
#
|
2008-09-10 05:34:49 -04:00
|
|
|
def escape(*arg)
|
2017-10-21 10:40:03 -04:00
|
|
|
warn "#{caller(1, 1)[0]}: warning: URI.escape is obsolete" if $VERBOSE
|
2008-09-10 05:34:49 -04:00
|
|
|
DEFAULT_PARSER.escape(*arg)
|
2002-01-10 03:00:51 -05:00
|
|
|
end
|
|
|
|
alias encode escape
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI.unescape(str)
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +str+::
|
|
|
|
# Unescapes the string.
|
|
|
|
#
|
2017-05-26 02:42:11 -04:00
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# This method is obsolete and should not be used. Instead, use
|
|
|
|
# CGI.unescape, URI.decode_www_form or URI.decode_www_form_component
|
|
|
|
# depending on your specific use case.
|
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
2005-06-24 00:18:16 -04:00
|
|
|
# enc_uri = URI.escape("http://example.com/?a=\11\15")
|
2004-03-24 06:53:31 -05:00
|
|
|
# p enc_uri
|
2005-06-24 00:18:16 -04:00
|
|
|
# # => "http://example.com/?a=%09%0D"
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# p URI.unescape(enc_uri)
|
2005-06-24 00:18:16 -04:00
|
|
|
# # => "http://example.com/?a=\t\r"
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
2008-09-10 05:34:49 -04:00
|
|
|
def unescape(*arg)
|
2017-10-21 10:40:03 -04:00
|
|
|
warn "#{caller(1, 1)[0]}: warning: URI.unescape is obsolete" if $VERBOSE
|
2008-09-10 05:34:49 -04:00
|
|
|
DEFAULT_PARSER.unescape(*arg)
|
2002-01-10 03:00:51 -05:00
|
|
|
end
|
|
|
|
alias decode unescape
|
2011-05-13 16:03:21 -04:00
|
|
|
end # module Escape
|
2002-01-10 03:00:51 -05:00
|
|
|
|
|
|
|
extend Escape
|
2008-09-10 05:34:49 -04:00
|
|
|
include REGEXP
|
2002-01-10 03:00:51 -05:00
|
|
|
|
|
|
|
@@schemes = {}
|
2011-05-12 16:39:11 -04:00
|
|
|
# Returns a Hash of the defined schemes
|
2008-09-10 05:34:49 -04:00
|
|
|
def self.scheme_list
|
|
|
|
@@schemes
|
|
|
|
end
|
2009-03-05 22:56:38 -05:00
|
|
|
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# Base class for all URI exceptions.
|
|
|
|
#
|
2002-01-10 03:00:51 -05:00
|
|
|
class Error < StandardError; end
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# Not a URI.
|
|
|
|
#
|
|
|
|
class InvalidURIError < Error; end
|
|
|
|
#
|
|
|
|
# Not a URI component.
|
|
|
|
#
|
|
|
|
class InvalidComponentError < Error; end
|
|
|
|
#
|
|
|
|
# URI is valid, bad usage is not.
|
|
|
|
#
|
|
|
|
class BadURIError < Error; end
|
|
|
|
|
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::split(uri)
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +uri+::
|
|
|
|
# String with URI.
|
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Splits the string on following parts and returns array with result:
|
|
|
|
#
|
|
|
|
# * Scheme
|
|
|
|
# * Userinfo
|
|
|
|
# * Host
|
|
|
|
# * Port
|
|
|
|
# * Registry
|
|
|
|
# * Path
|
|
|
|
# * Opaque
|
|
|
|
# * Query
|
|
|
|
# * Fragment
|
2009-03-05 22:56:38 -05:00
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
|
|
|
# p URI.split("http://www.ruby-lang.org/")
|
|
|
|
# # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil]
|
|
|
|
#
|
2002-01-10 03:00:51 -05:00
|
|
|
def self.split(uri)
|
2014-06-21 20:22:19 -04:00
|
|
|
RFC3986_PARSER.split(uri)
|
2002-01-10 03:00:51 -05:00
|
|
|
end
|
|
|
|
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::parse(uri_str)
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +uri_str+::
|
|
|
|
# String with URI.
|
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Creates one of the URI's subclasses instance from the string.
|
2009-03-05 22:56:38 -05:00
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# == Raises
|
|
|
|
#
|
|
|
|
# URI::InvalidURIError
|
|
|
|
# Raised if URI given is not a correct one.
|
|
|
|
#
|
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
|
|
|
# uri = URI.parse("http://www.ruby-lang.org/")
|
|
|
|
# p uri
|
|
|
|
# # => #<URI::HTTP:0x202281be URL:http://www.ruby-lang.org/>
|
2009-03-05 22:56:38 -05:00
|
|
|
# p uri.scheme
|
|
|
|
# # => "http"
|
|
|
|
# p uri.host
|
|
|
|
# # => "www.ruby-lang.org"
|
|
|
|
#
|
2014-07-27 17:27:10 -04:00
|
|
|
# It's recommended to first ::escape the provided +uri_str+ if there are any
|
|
|
|
# invalid URI characters.
|
|
|
|
#
|
2002-01-10 03:00:51 -05:00
|
|
|
def self.parse(uri)
|
2014-06-21 20:22:19 -04:00
|
|
|
RFC3986_PARSER.parse(uri)
|
2002-01-10 03:00:51 -05:00
|
|
|
end
|
|
|
|
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::join(str[, str, ...])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +str+::
|
2014-07-27 16:34:18 -04:00
|
|
|
# String(s) to work with, will be converted to RFC3986 URIs before merging.
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Joins URIs.
|
|
|
|
#
|
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
2010-09-23 08:22:43 -04:00
|
|
|
# p URI.join("http://example.com/","main.rbx")
|
2015-02-24 13:09:10 -05:00
|
|
|
# # => #<URI::HTTP:0x2022ac02 URL:http://example.com/main.rbx>
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
2010-09-23 08:22:43 -04:00
|
|
|
# p URI.join('http://example.com', 'foo')
|
|
|
|
# # => #<URI::HTTP:0x01ab80a0 URL:http://example.com/foo>
|
|
|
|
#
|
|
|
|
# p URI.join('http://example.com', '/foo', '/bar')
|
|
|
|
# # => #<URI::HTTP:0x01aaf0b0 URL:http://example.com/bar>
|
|
|
|
#
|
|
|
|
# p URI.join('http://example.com', '/foo', 'bar')
|
|
|
|
# # => #<URI::HTTP:0x801a92af0 URL:http://example.com/bar>
|
|
|
|
#
|
|
|
|
# p URI.join('http://example.com', '/foo/', 'bar')
|
|
|
|
# # => #<URI::HTTP:0x80135a3a0 URL:http://example.com/foo/bar>
|
|
|
|
#
|
|
|
|
#
|
2002-02-06 23:51:11 -05:00
|
|
|
def self.join(*str)
|
2014-06-21 20:22:19 -04:00
|
|
|
RFC3986_PARSER.join(*str)
|
2002-02-06 23:51:11 -05:00
|
|
|
end
|
|
|
|
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::extract(str[, schemes][,&blk])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
2009-03-05 22:56:38 -05:00
|
|
|
# +str+::
|
2004-03-24 06:53:31 -05:00
|
|
|
# String to extract URIs from.
|
|
|
|
# +schemes+::
|
|
|
|
# Limit URI matching to a specific schemes.
|
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Extracts URIs from a string. If block given, iterates through all matched URIs.
|
|
|
|
# Returns nil if block given or array with matches.
|
|
|
|
#
|
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require "uri"
|
|
|
|
#
|
2005-06-23 04:22:44 -04:00
|
|
|
# URI.extract("text here http://foo.example.org/bla and here mailto:test@example.com and here also.")
|
|
|
|
# # => ["http://foo.example.com/bla", "mailto:test@example.com"]
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
2003-12-07 23:03:11 -05:00
|
|
|
def self.extract(str, schemes = nil, &block)
|
2017-10-21 10:40:03 -04:00
|
|
|
warn "#{caller(1, 1)[0]}: warning: URI.extract is obsolete" if $VERBOSE
|
2008-09-10 05:34:49 -04:00
|
|
|
DEFAULT_PARSER.extract(str, schemes, &block)
|
2003-12-07 23:03:11 -05:00
|
|
|
end
|
2002-01-10 03:00:51 -05:00
|
|
|
|
2004-03-24 06:53:31 -05:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::regexp([match_schemes])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
2009-03-05 22:56:38 -05:00
|
|
|
# +match_schemes+::
|
2004-03-24 06:53:31 -05:00
|
|
|
# Array of schemes. If given, resulting regexp matches to URIs
|
|
|
|
# whose scheme is one of the match_schemes.
|
2009-03-05 22:56:38 -05:00
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# == Description
|
|
|
|
# Returns a Regexp object which matches to URI-like strings.
|
|
|
|
# The Regexp object returned by this method includes arbitrary
|
|
|
|
# number of capture group (parentheses). Never rely on it's number.
|
2009-03-05 22:56:38 -05:00
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
|
|
|
# # extract first URI from html_string
|
|
|
|
# html_string.slice(URI.regexp)
|
2009-03-05 22:56:38 -05:00
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# # remove ftp URIs
|
|
|
|
# html_string.sub(URI.regexp(['ftp'])
|
2009-03-05 22:56:38 -05:00
|
|
|
#
|
2004-03-24 06:53:31 -05:00
|
|
|
# # You should not rely on the number of parentheses
|
|
|
|
# html_string.scan(URI.regexp) do |*matches|
|
|
|
|
# p $&
|
|
|
|
# end
|
|
|
|
#
|
2003-12-07 23:03:11 -05:00
|
|
|
def self.regexp(schemes = nil)
|
2017-10-21 10:40:03 -04:00
|
|
|
warn "#{caller(1, 1)[0]}: warning: URI.regexp is obsolete" if $VERBOSE
|
2008-09-10 05:34:49 -04:00
|
|
|
DEFAULT_PARSER.make_regexp(schemes)
|
2002-01-10 03:00:51 -05:00
|
|
|
end
|
|
|
|
|
2010-04-10 18:05:02 -04:00
|
|
|
TBLENCWWWCOMP_ = {} # :nodoc:
|
2012-01-23 21:52:09 -05:00
|
|
|
256.times do |i|
|
|
|
|
TBLENCWWWCOMP_[i.chr] = '%%%02X' % i
|
|
|
|
end
|
|
|
|
TBLENCWWWCOMP_[' '] = '+'
|
|
|
|
TBLENCWWWCOMP_.freeze
|
2010-04-10 18:05:02 -04:00
|
|
|
TBLDECWWWCOMP_ = {} # :nodoc:
|
2012-01-23 21:52:09 -05:00
|
|
|
256.times do |i|
|
|
|
|
h, l = i>>4, i&15
|
|
|
|
TBLDECWWWCOMP_['%%%X%X' % [h, l]] = i.chr
|
|
|
|
TBLDECWWWCOMP_['%%%x%X' % [h, l]] = i.chr
|
|
|
|
TBLDECWWWCOMP_['%%%X%x' % [h, l]] = i.chr
|
|
|
|
TBLDECWWWCOMP_['%%%x%x' % [h, l]] = i.chr
|
|
|
|
end
|
|
|
|
TBLDECWWWCOMP_['+'] = ' '
|
|
|
|
TBLDECWWWCOMP_.freeze
|
|
|
|
|
2014-12-29 23:17:10 -05:00
|
|
|
HTML5ASCIIINCOMPAT = defined? Encoding::UTF_7 ? [Encoding::UTF_7, Encoding::UTF_16BE, Encoding::UTF_16LE,
|
|
|
|
Encoding::UTF_32BE, Encoding::UTF_32LE] : [] # :nodoc:
|
2010-03-21 08:36:14 -04:00
|
|
|
|
2010-03-12 04:00:48 -05:00
|
|
|
# Encode given +str+ to URL-encoded form data.
|
|
|
|
#
|
2010-11-29 15:23:59 -05:00
|
|
|
# This method doesn't convert *, -, ., 0-9, A-Z, _, a-z, but does convert SP
|
|
|
|
# (ASCII space) to + and converts others to %XX.
|
2010-03-12 04:00:48 -05:00
|
|
|
#
|
2013-04-25 01:27:41 -04:00
|
|
|
# If +enc+ is given, convert +str+ to the encoding before percent encoding.
|
|
|
|
#
|
2010-11-29 15:23:59 -05:00
|
|
|
# This is an implementation of
|
2014-01-21 03:56:15 -05:00
|
|
|
# http://www.w3.org/TR/2013/CR-html5-20130806/forms.html#url-encoded-form-data
|
2010-03-12 04:00:48 -05:00
|
|
|
#
|
2010-03-17 11:35:38 -04:00
|
|
|
# See URI.decode_www_form_component, URI.encode_www_form
|
2013-04-25 01:27:41 -04:00
|
|
|
def self.encode_www_form_component(str, enc=nil)
|
|
|
|
str = str.to_s.dup
|
|
|
|
if str.encoding != Encoding::ASCII_8BIT
|
|
|
|
if enc && enc != Encoding::ASCII_8BIT
|
|
|
|
str.encode!(Encoding::UTF_8, invalid: :replace, undef: :replace)
|
|
|
|
str.encode!(enc, fallback: ->(x){"&#{x.ord};"})
|
|
|
|
end
|
|
|
|
str.force_encoding(Encoding::ASCII_8BIT)
|
2010-03-17 11:35:38 -04:00
|
|
|
end
|
2010-03-21 08:36:14 -04:00
|
|
|
str.gsub!(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_)
|
2010-03-17 11:35:38 -04:00
|
|
|
str.force_encoding(Encoding::US_ASCII)
|
2010-03-12 04:00:48 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
# Decode given +str+ of URL-encoded form data.
|
|
|
|
#
|
2013-04-16 21:16:58 -04:00
|
|
|
# This decodes + to SP.
|
2010-03-12 04:00:48 -05:00
|
|
|
#
|
2010-03-17 11:35:38 -04:00
|
|
|
# See URI.encode_www_form_component, URI.decode_www_form
|
|
|
|
def self.decode_www_form_component(str, enc=Encoding::UTF_8)
|
2014-08-25 03:29:50 -04:00
|
|
|
raise ArgumentError, "invalid %-encoding (#{str})" if /%(?!\h\h)/ =~ str
|
2013-07-31 05:34:34 -04:00
|
|
|
str.b.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc)
|
2010-03-12 04:00:48 -05:00
|
|
|
end
|
|
|
|
|
|
|
|
# Generate URL-encoded form data from given +enum+.
|
|
|
|
#
|
|
|
|
# This generates application/x-www-form-urlencoded data defined in HTML5
|
|
|
|
# from given an Enumerable object.
|
|
|
|
#
|
2010-03-17 11:35:38 -04:00
|
|
|
# This internally uses URI.encode_www_form_component(str).
|
2010-03-12 04:00:48 -05:00
|
|
|
#
|
2010-11-29 15:23:59 -05:00
|
|
|
# This method doesn't convert the encoding of given items, so convert them
|
|
|
|
# before call this method if you want to send data as other than original
|
|
|
|
# encoding or mixed encoding data. (Strings which are encoded in an HTML5
|
|
|
|
# ASCII incompatible encoding are converted to UTF-8.)
|
2010-03-12 04:00:48 -05:00
|
|
|
#
|
2010-11-29 15:23:59 -05:00
|
|
|
# This method doesn't handle files. When you send a file, use
|
|
|
|
# multipart/form-data.
|
2010-03-12 04:00:48 -05:00
|
|
|
#
|
2013-04-25 01:27:41 -04:00
|
|
|
# This refers http://url.spec.whatwg.org/#concept-urlencoded-serializer
|
2010-03-12 04:00:48 -05:00
|
|
|
#
|
2010-12-01 23:33:56 -05:00
|
|
|
# URI.encode_www_form([["q", "ruby"], ["lang", "en"]])
|
|
|
|
# #=> "q=ruby&lang=en"
|
|
|
|
# URI.encode_www_form("q" => "ruby", "lang" => "en")
|
|
|
|
# #=> "q=ruby&lang=en"
|
|
|
|
# URI.encode_www_form("q" => ["ruby", "perl"], "lang" => "en")
|
|
|
|
# #=> "q=ruby&q=perl&lang=en"
|
|
|
|
# URI.encode_www_form([["q", "ruby"], ["q", "perl"], ["lang", "en"]])
|
|
|
|
# #=> "q=ruby&q=perl&lang=en"
|
|
|
|
#
|
2010-03-17 11:35:38 -04:00
|
|
|
# See URI.encode_www_form_component, URI.decode_www_form
|
2013-04-25 01:27:41 -04:00
|
|
|
def self.encode_www_form(enum, enc=nil)
|
2010-09-29 20:48:01 -04:00
|
|
|
enum.map do |k,v|
|
2010-12-01 23:33:56 -05:00
|
|
|
if v.nil?
|
2013-04-25 01:27:41 -04:00
|
|
|
encode_www_form_component(k, enc)
|
2010-12-01 23:33:56 -05:00
|
|
|
elsif v.respond_to?(:to_ary)
|
|
|
|
v.to_ary.map do |w|
|
2013-04-25 01:27:41 -04:00
|
|
|
str = encode_www_form_component(k, enc)
|
2010-12-01 23:33:56 -05:00
|
|
|
unless w.nil?
|
|
|
|
str << '='
|
2013-04-25 01:27:41 -04:00
|
|
|
str << encode_www_form_component(w, enc)
|
2010-12-01 23:33:56 -05:00
|
|
|
end
|
|
|
|
end.join('&')
|
|
|
|
else
|
2013-04-25 01:27:41 -04:00
|
|
|
str = encode_www_form_component(k, enc)
|
2010-09-29 20:48:01 -04:00
|
|
|
str << '='
|
2013-04-25 01:27:41 -04:00
|
|
|
str << encode_www_form_component(v, enc)
|
2010-03-12 04:00:48 -05:00
|
|
|
end
|
2010-09-29 20:48:01 -04:00
|
|
|
end.join('&')
|
2010-03-12 04:00:48 -05:00
|
|
|
end
|
2010-03-17 11:35:38 -04:00
|
|
|
|
|
|
|
# Decode URL-encoded form data from given +str+.
|
|
|
|
#
|
|
|
|
# This decodes application/x-www-form-urlencoded data
|
|
|
|
# and returns array of key-value array.
|
|
|
|
#
|
2013-04-25 01:27:41 -04:00
|
|
|
# This refers http://url.spec.whatwg.org/#concept-urlencoded-parser ,
|
|
|
|
# so this supports only &-separator, don't support ;-separator.
|
2010-03-17 11:35:38 -04:00
|
|
|
#
|
2015-12-14 21:56:38 -05:00
|
|
|
# ary = URI.decode_www_form("a=1&a=2&b=3")
|
|
|
|
# p ary #=> [['a', '1'], ['a', '2'], ['b', '3']]
|
|
|
|
# p ary.assoc('a').last #=> '1'
|
|
|
|
# p ary.assoc('b').last #=> '3'
|
|
|
|
# p ary.rassoc('a').last #=> '2'
|
|
|
|
# p Hash[ary] # => {"a"=>"2", "b"=>"3"}
|
2010-03-17 11:35:38 -04:00
|
|
|
#
|
|
|
|
# See URI.decode_www_form_component, URI.encode_www_form
|
2013-04-25 01:27:41 -04:00
|
|
|
def self.decode_www_form(str, enc=Encoding::UTF_8, separator: '&', use__charset_: false, isindex: false)
|
|
|
|
raise ArgumentError, "the input of #{self.name}.#{__method__} must be ASCII only string" unless str.ascii_only?
|
2010-04-09 07:58:20 -04:00
|
|
|
ary = []
|
2013-04-25 01:27:41 -04:00
|
|
|
return ary if str.empty?
|
|
|
|
enc = Encoding.find(enc)
|
|
|
|
str.b.each_line(separator) do |string|
|
|
|
|
string.chomp!(separator)
|
|
|
|
key, sep, val = string.partition('=')
|
|
|
|
if isindex
|
|
|
|
if sep.empty?
|
|
|
|
val = key
|
|
|
|
key = ''
|
|
|
|
end
|
|
|
|
isindex = false
|
|
|
|
end
|
|
|
|
|
2013-05-18 14:58:13 -04:00
|
|
|
if use__charset_ and key == '_charset_' and e = get_encoding(val)
|
|
|
|
enc = e
|
|
|
|
use__charset_ = false
|
2013-04-25 01:27:41 -04:00
|
|
|
end
|
|
|
|
|
|
|
|
key.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_)
|
|
|
|
if val
|
|
|
|
val.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_)
|
|
|
|
else
|
|
|
|
val = ''
|
|
|
|
end
|
|
|
|
|
|
|
|
ary << [key, val]
|
2010-03-17 11:35:38 -04:00
|
|
|
end
|
2013-05-18 14:58:13 -04:00
|
|
|
ary.each do |k, v|
|
|
|
|
k.force_encoding(enc)
|
|
|
|
k.scrub!
|
|
|
|
v.force_encoding(enc)
|
|
|
|
v.scrub!
|
|
|
|
end
|
2010-03-17 11:35:38 -04:00
|
|
|
ary
|
|
|
|
end
|
2013-04-25 01:27:41 -04:00
|
|
|
|
|
|
|
private
|
2016-10-05 22:04:28 -04:00
|
|
|
=begin command for WEB_ENCODINGS_
|
|
|
|
curl https://encoding.spec.whatwg.org/encodings.json|
|
|
|
|
ruby -rjson -e 'H={}
|
|
|
|
h={
|
|
|
|
"shift_jis"=>"Windows-31J",
|
|
|
|
"euc-jp"=>"cp51932",
|
|
|
|
"iso-2022-jp"=>"cp50221",
|
|
|
|
"x-mac-cyrillic"=>"macCyrillic",
|
|
|
|
}
|
|
|
|
JSON($<.read).map{|x|x["encodings"]}.flatten.each{|x|
|
|
|
|
Encoding.find(n=h.fetch(n=x["name"].downcase,n))rescue next
|
|
|
|
x["labels"].each{|y|H[y]=n}
|
|
|
|
}
|
|
|
|
puts "{"
|
|
|
|
H.each{|k,v|puts %[ #{k.dump}=>#{v.dump},]}
|
|
|
|
puts "}"
|
|
|
|
'
|
|
|
|
=end
|
2013-04-25 01:27:41 -04:00
|
|
|
WEB_ENCODINGS_ = {
|
|
|
|
"unicode-1-1-utf-8"=>"utf-8",
|
|
|
|
"utf-8"=>"utf-8",
|
|
|
|
"utf8"=>"utf-8",
|
|
|
|
"866"=>"ibm866",
|
|
|
|
"cp866"=>"ibm866",
|
|
|
|
"csibm866"=>"ibm866",
|
|
|
|
"ibm866"=>"ibm866",
|
|
|
|
"csisolatin2"=>"iso-8859-2",
|
|
|
|
"iso-8859-2"=>"iso-8859-2",
|
|
|
|
"iso-ir-101"=>"iso-8859-2",
|
|
|
|
"iso8859-2"=>"iso-8859-2",
|
|
|
|
"iso88592"=>"iso-8859-2",
|
|
|
|
"iso_8859-2"=>"iso-8859-2",
|
|
|
|
"iso_8859-2:1987"=>"iso-8859-2",
|
|
|
|
"l2"=>"iso-8859-2",
|
|
|
|
"latin2"=>"iso-8859-2",
|
|
|
|
"csisolatin3"=>"iso-8859-3",
|
|
|
|
"iso-8859-3"=>"iso-8859-3",
|
|
|
|
"iso-ir-109"=>"iso-8859-3",
|
|
|
|
"iso8859-3"=>"iso-8859-3",
|
|
|
|
"iso88593"=>"iso-8859-3",
|
|
|
|
"iso_8859-3"=>"iso-8859-3",
|
|
|
|
"iso_8859-3:1988"=>"iso-8859-3",
|
|
|
|
"l3"=>"iso-8859-3",
|
|
|
|
"latin3"=>"iso-8859-3",
|
|
|
|
"csisolatin4"=>"iso-8859-4",
|
|
|
|
"iso-8859-4"=>"iso-8859-4",
|
|
|
|
"iso-ir-110"=>"iso-8859-4",
|
|
|
|
"iso8859-4"=>"iso-8859-4",
|
|
|
|
"iso88594"=>"iso-8859-4",
|
|
|
|
"iso_8859-4"=>"iso-8859-4",
|
|
|
|
"iso_8859-4:1988"=>"iso-8859-4",
|
|
|
|
"l4"=>"iso-8859-4",
|
|
|
|
"latin4"=>"iso-8859-4",
|
|
|
|
"csisolatincyrillic"=>"iso-8859-5",
|
|
|
|
"cyrillic"=>"iso-8859-5",
|
|
|
|
"iso-8859-5"=>"iso-8859-5",
|
|
|
|
"iso-ir-144"=>"iso-8859-5",
|
|
|
|
"iso8859-5"=>"iso-8859-5",
|
|
|
|
"iso88595"=>"iso-8859-5",
|
|
|
|
"iso_8859-5"=>"iso-8859-5",
|
|
|
|
"iso_8859-5:1988"=>"iso-8859-5",
|
|
|
|
"arabic"=>"iso-8859-6",
|
|
|
|
"asmo-708"=>"iso-8859-6",
|
|
|
|
"csiso88596e"=>"iso-8859-6",
|
|
|
|
"csiso88596i"=>"iso-8859-6",
|
|
|
|
"csisolatinarabic"=>"iso-8859-6",
|
|
|
|
"ecma-114"=>"iso-8859-6",
|
|
|
|
"iso-8859-6"=>"iso-8859-6",
|
|
|
|
"iso-8859-6-e"=>"iso-8859-6",
|
|
|
|
"iso-8859-6-i"=>"iso-8859-6",
|
|
|
|
"iso-ir-127"=>"iso-8859-6",
|
|
|
|
"iso8859-6"=>"iso-8859-6",
|
|
|
|
"iso88596"=>"iso-8859-6",
|
|
|
|
"iso_8859-6"=>"iso-8859-6",
|
|
|
|
"iso_8859-6:1987"=>"iso-8859-6",
|
|
|
|
"csisolatingreek"=>"iso-8859-7",
|
|
|
|
"ecma-118"=>"iso-8859-7",
|
|
|
|
"elot_928"=>"iso-8859-7",
|
|
|
|
"greek"=>"iso-8859-7",
|
|
|
|
"greek8"=>"iso-8859-7",
|
|
|
|
"iso-8859-7"=>"iso-8859-7",
|
|
|
|
"iso-ir-126"=>"iso-8859-7",
|
|
|
|
"iso8859-7"=>"iso-8859-7",
|
|
|
|
"iso88597"=>"iso-8859-7",
|
|
|
|
"iso_8859-7"=>"iso-8859-7",
|
|
|
|
"iso_8859-7:1987"=>"iso-8859-7",
|
|
|
|
"sun_eu_greek"=>"iso-8859-7",
|
|
|
|
"csiso88598e"=>"iso-8859-8",
|
|
|
|
"csisolatinhebrew"=>"iso-8859-8",
|
|
|
|
"hebrew"=>"iso-8859-8",
|
|
|
|
"iso-8859-8"=>"iso-8859-8",
|
|
|
|
"iso-8859-8-e"=>"iso-8859-8",
|
|
|
|
"iso-ir-138"=>"iso-8859-8",
|
|
|
|
"iso8859-8"=>"iso-8859-8",
|
|
|
|
"iso88598"=>"iso-8859-8",
|
|
|
|
"iso_8859-8"=>"iso-8859-8",
|
|
|
|
"iso_8859-8:1988"=>"iso-8859-8",
|
|
|
|
"visual"=>"iso-8859-8",
|
|
|
|
"csisolatin6"=>"iso-8859-10",
|
|
|
|
"iso-8859-10"=>"iso-8859-10",
|
|
|
|
"iso-ir-157"=>"iso-8859-10",
|
|
|
|
"iso8859-10"=>"iso-8859-10",
|
|
|
|
"iso885910"=>"iso-8859-10",
|
|
|
|
"l6"=>"iso-8859-10",
|
|
|
|
"latin6"=>"iso-8859-10",
|
|
|
|
"iso-8859-13"=>"iso-8859-13",
|
|
|
|
"iso8859-13"=>"iso-8859-13",
|
|
|
|
"iso885913"=>"iso-8859-13",
|
|
|
|
"iso-8859-14"=>"iso-8859-14",
|
|
|
|
"iso8859-14"=>"iso-8859-14",
|
|
|
|
"iso885914"=>"iso-8859-14",
|
|
|
|
"csisolatin9"=>"iso-8859-15",
|
|
|
|
"iso-8859-15"=>"iso-8859-15",
|
|
|
|
"iso8859-15"=>"iso-8859-15",
|
|
|
|
"iso885915"=>"iso-8859-15",
|
|
|
|
"iso_8859-15"=>"iso-8859-15",
|
|
|
|
"l9"=>"iso-8859-15",
|
|
|
|
"iso-8859-16"=>"iso-8859-16",
|
|
|
|
"cskoi8r"=>"koi8-r",
|
|
|
|
"koi"=>"koi8-r",
|
|
|
|
"koi8"=>"koi8-r",
|
|
|
|
"koi8-r"=>"koi8-r",
|
|
|
|
"koi8_r"=>"koi8-r",
|
2016-10-05 22:01:51 -04:00
|
|
|
"koi8-ru"=>"koi8-u",
|
2013-04-25 01:27:41 -04:00
|
|
|
"koi8-u"=>"koi8-u",
|
|
|
|
"dos-874"=>"windows-874",
|
|
|
|
"iso-8859-11"=>"windows-874",
|
|
|
|
"iso8859-11"=>"windows-874",
|
|
|
|
"iso885911"=>"windows-874",
|
|
|
|
"tis-620"=>"windows-874",
|
|
|
|
"windows-874"=>"windows-874",
|
|
|
|
"cp1250"=>"windows-1250",
|
|
|
|
"windows-1250"=>"windows-1250",
|
|
|
|
"x-cp1250"=>"windows-1250",
|
|
|
|
"cp1251"=>"windows-1251",
|
|
|
|
"windows-1251"=>"windows-1251",
|
|
|
|
"x-cp1251"=>"windows-1251",
|
|
|
|
"ansi_x3.4-1968"=>"windows-1252",
|
|
|
|
"ascii"=>"windows-1252",
|
|
|
|
"cp1252"=>"windows-1252",
|
|
|
|
"cp819"=>"windows-1252",
|
|
|
|
"csisolatin1"=>"windows-1252",
|
|
|
|
"ibm819"=>"windows-1252",
|
|
|
|
"iso-8859-1"=>"windows-1252",
|
|
|
|
"iso-ir-100"=>"windows-1252",
|
|
|
|
"iso8859-1"=>"windows-1252",
|
|
|
|
"iso88591"=>"windows-1252",
|
|
|
|
"iso_8859-1"=>"windows-1252",
|
|
|
|
"iso_8859-1:1987"=>"windows-1252",
|
|
|
|
"l1"=>"windows-1252",
|
|
|
|
"latin1"=>"windows-1252",
|
|
|
|
"us-ascii"=>"windows-1252",
|
|
|
|
"windows-1252"=>"windows-1252",
|
|
|
|
"x-cp1252"=>"windows-1252",
|
|
|
|
"cp1253"=>"windows-1253",
|
|
|
|
"windows-1253"=>"windows-1253",
|
|
|
|
"x-cp1253"=>"windows-1253",
|
|
|
|
"cp1254"=>"windows-1254",
|
|
|
|
"csisolatin5"=>"windows-1254",
|
|
|
|
"iso-8859-9"=>"windows-1254",
|
|
|
|
"iso-ir-148"=>"windows-1254",
|
|
|
|
"iso8859-9"=>"windows-1254",
|
|
|
|
"iso88599"=>"windows-1254",
|
|
|
|
"iso_8859-9"=>"windows-1254",
|
|
|
|
"iso_8859-9:1989"=>"windows-1254",
|
|
|
|
"l5"=>"windows-1254",
|
|
|
|
"latin5"=>"windows-1254",
|
|
|
|
"windows-1254"=>"windows-1254",
|
|
|
|
"x-cp1254"=>"windows-1254",
|
|
|
|
"cp1255"=>"windows-1255",
|
|
|
|
"windows-1255"=>"windows-1255",
|
|
|
|
"x-cp1255"=>"windows-1255",
|
|
|
|
"cp1256"=>"windows-1256",
|
|
|
|
"windows-1256"=>"windows-1256",
|
|
|
|
"x-cp1256"=>"windows-1256",
|
|
|
|
"cp1257"=>"windows-1257",
|
|
|
|
"windows-1257"=>"windows-1257",
|
|
|
|
"x-cp1257"=>"windows-1257",
|
|
|
|
"cp1258"=>"windows-1258",
|
|
|
|
"windows-1258"=>"windows-1258",
|
|
|
|
"x-cp1258"=>"windows-1258",
|
|
|
|
"x-mac-cyrillic"=>"macCyrillic",
|
|
|
|
"x-mac-ukrainian"=>"macCyrillic",
|
|
|
|
"chinese"=>"gbk",
|
|
|
|
"csgb2312"=>"gbk",
|
|
|
|
"csiso58gb231280"=>"gbk",
|
|
|
|
"gb2312"=>"gbk",
|
|
|
|
"gb_2312"=>"gbk",
|
|
|
|
"gb_2312-80"=>"gbk",
|
|
|
|
"gbk"=>"gbk",
|
|
|
|
"iso-ir-58"=>"gbk",
|
|
|
|
"x-gbk"=>"gbk",
|
|
|
|
"gb18030"=>"gb18030",
|
|
|
|
"big5"=>"big5",
|
|
|
|
"big5-hkscs"=>"big5",
|
|
|
|
"cn-big5"=>"big5",
|
|
|
|
"csbig5"=>"big5",
|
|
|
|
"x-x-big5"=>"big5",
|
|
|
|
"cseucpkdfmtjapanese"=>"cp51932",
|
|
|
|
"euc-jp"=>"cp51932",
|
|
|
|
"x-euc-jp"=>"cp51932",
|
|
|
|
"csiso2022jp"=>"cp50221",
|
|
|
|
"iso-2022-jp"=>"cp50221",
|
|
|
|
"csshiftjis"=>"Windows-31J",
|
2016-10-05 22:01:51 -04:00
|
|
|
"ms932"=>"Windows-31J",
|
2013-04-25 01:27:41 -04:00
|
|
|
"ms_kanji"=>"Windows-31J",
|
|
|
|
"shift-jis"=>"Windows-31J",
|
|
|
|
"shift_jis"=>"Windows-31J",
|
|
|
|
"sjis"=>"Windows-31J",
|
|
|
|
"windows-31j"=>"Windows-31J",
|
|
|
|
"x-sjis"=>"Windows-31J",
|
|
|
|
"cseuckr"=>"euc-kr",
|
|
|
|
"csksc56011987"=>"euc-kr",
|
|
|
|
"euc-kr"=>"euc-kr",
|
|
|
|
"iso-ir-149"=>"euc-kr",
|
|
|
|
"korean"=>"euc-kr",
|
|
|
|
"ks_c_5601-1987"=>"euc-kr",
|
|
|
|
"ks_c_5601-1989"=>"euc-kr",
|
|
|
|
"ksc5601"=>"euc-kr",
|
|
|
|
"ksc_5601"=>"euc-kr",
|
|
|
|
"windows-949"=>"euc-kr",
|
|
|
|
"utf-16be"=>"utf-16be",
|
|
|
|
"utf-16"=>"utf-16le",
|
2016-10-05 22:04:28 -04:00
|
|
|
"utf-16le"=>"utf-16le",
|
2013-04-25 01:27:41 -04:00
|
|
|
} # :nodoc:
|
|
|
|
|
|
|
|
# :nodoc:
|
|
|
|
# return encoding or nil
|
|
|
|
# http://encoding.spec.whatwg.org/#concept-encoding-get
|
|
|
|
def self.get_encoding(label)
|
|
|
|
Encoding.find(WEB_ENCODINGS_[label.to_str.strip.downcase]) rescue nil
|
|
|
|
end
|
2011-05-13 16:03:21 -04:00
|
|
|
end # module URI
|
2004-07-05 10:06:10 -04:00
|
|
|
|
|
|
|
module Kernel
|
2010-07-20 23:32:41 -04:00
|
|
|
|
2004-07-05 10:06:10 -04:00
|
|
|
#
|
2010-07-20 23:32:41 -04:00
|
|
|
# Returns +uri+ converted to a URI object.
|
|
|
|
#
|
2011-07-15 17:28:10 -04:00
|
|
|
def URI(uri)
|
2010-07-20 23:32:41 -04:00
|
|
|
if uri.is_a?(URI::Generic)
|
|
|
|
uri
|
|
|
|
elsif uri = String.try_convert(uri)
|
2011-07-15 17:28:10 -04:00
|
|
|
URI.parse(uri)
|
2010-07-20 23:32:41 -04:00
|
|
|
else
|
|
|
|
raise ArgumentError,
|
|
|
|
"bad argument (expected URI object or URI string)"
|
|
|
|
end
|
2004-07-05 10:06:10 -04:00
|
|
|
end
|
|
|
|
module_function :URI
|
|
|
|
end
|