Add bin and edit workflow
Gitea Actions Demo / Explore-Gitea-Actions (push) Failing after 9s

This commit is contained in:
2026-09-16 13:11:16 -06:00
parent c8ac4fcae5
commit 4cee170d66
17576 changed files with 895740 additions and 2 deletions
+855
View File
@@ -0,0 +1,855 @@
# frozen_string_literal: true
#--
# = uri/common.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# License::
# You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative "rfc2396_parser"
require_relative "rfc3986_parser"
module URI
include RFC2396_REGEXP
REGEXP = RFC2396_REGEXP
Parser = RFC2396_Parser
RFC3986_PARSER = RFC3986_Parser.new
Ractor.make_shareable(RFC3986_PARSER) if defined?(Ractor)
RFC2396_PARSER = RFC2396_Parser.new
Ractor.make_shareable(RFC2396_PARSER) if defined?(Ractor)
# URI::Parser.new
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
Ractor.make_shareable(DEFAULT_PARSER) if defined?(Ractor)
module Util # :nodoc:
def make_components_hash(klass, array_hash)
tmp = {}
if array_hash.kind_of?(Array) &&
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
elsif array_hash.kind_of?(Hash)
array_hash.each do |key, value|
begin
tmp[key] = value.clone
rescue TypeError
tmp[key] = value
end
end
else
raise ArgumentError,
"expected Array of or Hash of components of #{klass} (#{klass.component[1..-1].join(', ')})"
end
tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase
return tmp
end
module_function :make_components_hash
end
module Schemes
end
private_constant :Schemes
# Registers the given +klass+ as the class to be instantiated
# when parsing a \URI with the given +scheme+:
#
# URI.register_scheme('MS_SEARCH', URI::Generic) # => URI::Generic
# URI.scheme_list['MS_SEARCH'] # => URI::Generic
#
# Note that after calling String#upcase on +scheme+, it must be a valid
# constant name.
def self.register_scheme(scheme, klass)
Schemes.const_set(scheme.to_s.upcase, klass)
end
# Returns a hash of the defined schemes:
#
# URI.scheme_list
# # =>
# {"MAILTO"=>URI::MailTo,
# "LDAPS"=>URI::LDAPS,
# "WS"=>URI::WS,
# "HTTP"=>URI::HTTP,
# "HTTPS"=>URI::HTTPS,
# "LDAP"=>URI::LDAP,
# "FILE"=>URI::File,
# "FTP"=>URI::FTP}
#
# Related: URI.register_scheme.
def self.scheme_list
Schemes.constants.map { |name|
[name.to_s.upcase, Schemes.const_get(name)]
}.to_h
end
INITIAL_SCHEMES = scheme_list
private_constant :INITIAL_SCHEMES
Ractor.make_shareable(INITIAL_SCHEMES) if defined?(Ractor)
# Returns a new object constructed from the given +scheme+, +arguments+,
# and +default+:
#
# - The new object is an instance of <tt>URI.scheme_list[scheme.upcase]</tt>.
# - The object is initialized by calling the class initializer
# using +scheme+ and +arguments+.
# See URI::Generic.new.
#
# Examples:
#
# values = ['john.doe', 'www.example.com', '123', nil, '/forum/questions/', nil, 'tag=networking&order=newest', 'top']
# URI.for('https', *values)
# # => #<URI::HTTPS https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
# URI.for('foo', *values, default: URI::HTTP)
# # => #<URI::HTTP foo://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
#
def self.for(scheme, *arguments, default: Generic)
const_name = scheme.to_s.upcase
uri_class = INITIAL_SCHEMES[const_name]
uri_class ||= if /\A[A-Z]\w*\z/.match?(const_name) && Schemes.const_defined?(const_name, false)
Schemes.const_get(const_name, false)
end
uri_class ||= default
return uri_class.new(scheme, *arguments)
end
#
# Base class for all URI exceptions.
#
class Error < StandardError; end
#
# 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
# Returns a 9-element array representing the parts of the \URI
# formed from the string +uri+;
# each array element is a string or +nil+:
#
# names = %w[scheme userinfo host port registry path opaque query fragment]
# values = URI.split('https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top')
# names.zip(values)
# # =>
# [["scheme", "https"],
# ["userinfo", "john.doe"],
# ["host", "www.example.com"],
# ["port", "123"],
# ["registry", nil],
# ["path", "/forum/questions/"],
# ["opaque", nil],
# ["query", "tag=networking&order=newest"],
# ["fragment", "top"]]
#
def self.split(uri)
RFC3986_PARSER.split(uri)
end
# Returns a new \URI object constructed from the given string +uri+:
#
# URI.parse('https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top')
# # => #<URI::HTTPS https://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
# URI.parse('http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top')
# # => #<URI::HTTP http://john.doe@www.example.com:123/forum/questions/?tag=networking&order=newest#top>
#
# It's recommended to first ::escape string +uri+
# if it may contain invalid URI characters.
#
def self.parse(uri)
RFC3986_PARSER.parse(uri)
end
# Merges the given URI strings +str+
# per {RFC 2396}[https://www.rfc-editor.org/rfc/rfc2396.html].
#
# Each string in +str+ is converted to an
# {RFC3986 URI}[https://www.rfc-editor.org/rfc/rfc3986.html] before being merged.
#
# Examples:
#
# URI.join("http://example.com/","main.rbx")
# # => #<URI::HTTP http://example.com/main.rbx>
#
# URI.join('http://example.com', 'foo')
# # => #<URI::HTTP http://example.com/foo>
#
# URI.join('http://example.com', '/foo', '/bar')
# # => #<URI::HTTP http://example.com/bar>
#
# URI.join('http://example.com', '/foo', 'bar')
# # => #<URI::HTTP http://example.com/bar>
#
# URI.join('http://example.com', '/foo/', 'bar')
# # => #<URI::HTTP http://example.com/foo/bar>
#
def self.join(*str)
RFC3986_PARSER.join(*str)
end
#
# == Synopsis
#
# URI::extract(str[, schemes][,&blk])
#
# == Args
#
# +str+::
# String to extract URIs from.
# +schemes+::
# Limit URI matching to 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"
#
# 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"]
#
def self.extract(str, schemes = nil, &block) # :nodoc:
warn "URI.extract is obsolete", uplevel: 1 if $VERBOSE
DEFAULT_PARSER.extract(str, schemes, &block)
end
#
# == Synopsis
#
# URI::regexp([match_schemes])
#
# == Args
#
# +match_schemes+::
# Array of schemes. If given, resulting regexp matches to URIs
# whose scheme is one of the match_schemes.
#
# == 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 its number.
#
# == Usage
#
# require 'uri'
#
# # extract first URI from html_string
# html_string.slice(URI.regexp)
#
# # remove ftp URIs
# html_string.sub(URI.regexp(['ftp']), '')
#
# # You should not rely on the number of parentheses
# html_string.scan(URI.regexp) do |*matches|
# p $&
# end
#
def self.regexp(schemes = nil)# :nodoc:
warn "URI.regexp is obsolete", uplevel: 1 if $VERBOSE
DEFAULT_PARSER.make_regexp(schemes)
end
TBLENCWWWCOMP_ = {} # :nodoc:
256.times do |i|
TBLENCWWWCOMP_[-i.chr] = -('%%%02X' % i)
end
TBLENCURICOMP_ = TBLENCWWWCOMP_.dup.freeze
TBLENCWWWCOMP_[' '] = '+'
TBLENCWWWCOMP_.freeze
TBLDECWWWCOMP_ = {} # :nodoc:
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
# Returns a URL-encoded string derived from the given string +str+.
#
# The returned string:
#
# - Preserves:
#
# - Characters <tt>'*'</tt>, <tt>'.'</tt>, <tt>'-'</tt>, and <tt>'_'</tt>.
# - Character in ranges <tt>'a'..'z'</tt>, <tt>'A'..'Z'</tt>,
# and <tt>'0'..'9'</tt>.
#
# Example:
#
# URI.encode_www_form_component('*.-_azAZ09')
# # => "*.-_azAZ09"
#
# - Converts:
#
# - Character <tt>' '</tt> to character <tt>'+'</tt>.
# - Any other character to "percent notation";
# the percent notation for character <i>c</i> is <tt>'%%%X' % c.ord</tt>.
#
# Example:
#
# URI.encode_www_form_component('Here are some punctuation characters: ,;?:')
# # => "Here+are+some+punctuation+characters%3A+%2C%3B%3F%3A"
#
# Encoding:
#
# - If +str+ has encoding Encoding::ASCII_8BIT, argument +enc+ is ignored.
# - Otherwise +str+ is converted first to Encoding::UTF_8
# (with suitable character replacements),
# and then to encoding +enc+.
#
# In either case, the returned string has forced encoding Encoding::US_ASCII.
#
# Related: URI.encode_uri_component (encodes <tt>' '</tt> as <tt>'%20'</tt>).
def self.encode_www_form_component(str, enc=nil)
_encode_uri_component(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_, str, enc)
end
# Returns a string decoded from the given \URL-encoded string +str+.
#
# The given string is first encoded as Encoding::ASCII-8BIT (using String#b),
# then decoded (as below), and finally force-encoded to the given encoding +enc+.
#
# The returned string:
#
# - Preserves:
#
# - Characters <tt>'*'</tt>, <tt>'.'</tt>, <tt>'-'</tt>, and <tt>'_'</tt>.
# - Character in ranges <tt>'a'..'z'</tt>, <tt>'A'..'Z'</tt>,
# and <tt>'0'..'9'</tt>.
#
# Example:
#
# URI.decode_www_form_component('*.-_azAZ09')
# # => "*.-_azAZ09"
#
# - Converts:
#
# - Character <tt>'+'</tt> to character <tt>' '</tt>.
# - Each "percent notation" to an ASCII character.
#
# Example:
#
# URI.decode_www_form_component('Here+are+some+punctuation+characters%3A+%2C%3B%3F%3A')
# # => "Here are some punctuation characters: ,;?:"
#
# Related: URI.decode_uri_component (preserves <tt>'+'</tt>).
def self.decode_www_form_component(str, enc=Encoding::UTF_8)
_decode_uri_component(/\+|%\h\h/, str, enc)
end
# Like URI.encode_www_form_component, except that <tt>' '</tt> (space)
# is encoded as <tt>'%20'</tt> (instead of <tt>'+'</tt>).
def self.encode_uri_component(str, enc=nil)
_encode_uri_component(/[^*\-.0-9A-Z_a-z]/, TBLENCURICOMP_, str, enc)
end
# Like URI.decode_www_form_component, except that <tt>'+'</tt> is preserved.
def self.decode_uri_component(str, enc=Encoding::UTF_8)
_decode_uri_component(/%\h\h/, str, enc)
end
def self._encode_uri_component(regexp, table, str, enc)
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)
end
str.gsub!(regexp, table)
str.force_encoding(Encoding::US_ASCII)
end
private_class_method :_encode_uri_component
def self._decode_uri_component(regexp, str, enc)
raise ArgumentError, "invalid %-encoding (#{str})" if /%(?!\h\h)/.match?(str)
str.b.gsub(regexp, TBLDECWWWCOMP_).force_encoding(enc)
end
private_class_method :_decode_uri_component
# Returns a URL-encoded string derived from the given
# {Enumerable}[https://docs.ruby-lang.org/en/master/Enumerable.html#module-Enumerable-label-Enumerable+in+Ruby+Classes]
# +enum+.
#
# The result is suitable for use as form data
# for an \HTTP request whose <tt>Content-Type</tt> is
# <tt>'application/x-www-form-urlencoded'</tt>.
#
# The returned string consists of the elements of +enum+,
# each converted to one or more URL-encoded strings,
# and all joined with character <tt>'&'</tt>.
#
# Simple examples:
#
# URI.encode_www_form([['foo', 0], ['bar', 1], ['baz', 2]])
# # => "foo=0&bar=1&baz=2"
# URI.encode_www_form({foo: 0, bar: 1, baz: 2})
# # => "foo=0&bar=1&baz=2"
#
# The returned string is formed using method URI.encode_www_form_component,
# which converts certain characters:
#
# URI.encode_www_form('f#o': '/', 'b-r': '$', 'b z': '@')
# # => "f%23o=%2F&b-r=%24&b+z=%40"
#
# When +enum+ is Array-like, each element +ele+ is converted to a field:
#
# - If +ele+ is an array of two or more elements,
# the field is formed from its first two elements
# (and any additional elements are ignored):
#
# name = URI.encode_www_form_component(ele[0], enc)
# value = URI.encode_www_form_component(ele[1], enc)
# "#{name}=#{value}"
#
# Examples:
#
# URI.encode_www_form([%w[foo bar], %w[baz bat bah]])
# # => "foo=bar&baz=bat"
# URI.encode_www_form([['foo', 0], ['bar', :baz, 'bat']])
# # => "foo=0&bar=baz"
#
# - If +ele+ is an array of one element,
# the field is formed from <tt>ele[0]</tt>:
#
# URI.encode_www_form_component(ele[0])
#
# Example:
#
# URI.encode_www_form([['foo'], [:bar], [0]])
# # => "foo&bar&0"
#
# - Otherwise the field is formed from +ele+:
#
# URI.encode_www_form_component(ele)
#
# Example:
#
# URI.encode_www_form(['foo', :bar, 0])
# # => "foo&bar&0"
#
# The elements of an Array-like +enum+ may be mixture:
#
# URI.encode_www_form([['foo', 0], ['bar', 1, 2], ['baz'], :bat])
# # => "foo=0&bar=1&baz&bat"
#
# When +enum+ is Hash-like,
# each +key+/+value+ pair is converted to one or more fields:
#
# - If +value+ is
# {Array-convertible}[https://docs.ruby-lang.org/en/master/implicit_conversion_rdoc.html#label-Array-Convertible+Objects],
# each element +ele+ in +value+ is paired with +key+ to form a field:
#
# name = URI.encode_www_form_component(key, enc)
# value = URI.encode_www_form_component(ele, enc)
# "#{name}=#{value}"
#
# Example:
#
# URI.encode_www_form({foo: [:bar, 1], baz: [:bat, :bam, 2]})
# # => "foo=bar&foo=1&baz=bat&baz=bam&baz=2"
#
# - Otherwise, +key+ and +value+ are paired to form a field:
#
# name = URI.encode_www_form_component(key, enc)
# value = URI.encode_www_form_component(value, enc)
# "#{name}=#{value}"
#
# Example:
#
# URI.encode_www_form({foo: 0, bar: 1, baz: 2})
# # => "foo=0&bar=1&baz=2"
#
# The elements of a Hash-like +enum+ may be mixture:
#
# URI.encode_www_form({foo: [0, 1], bar: 2})
# # => "foo=0&foo=1&bar=2"
#
def self.encode_www_form(enum, enc=nil)
enum.map do |k,v|
if v.nil?
encode_www_form_component(k, enc)
elsif v.respond_to?(:to_ary)
v.to_ary.map do |w|
str = encode_www_form_component(k, enc)
unless w.nil?
str << '='
str << encode_www_form_component(w, enc)
end
end.join('&')
else
str = encode_www_form_component(k, enc)
str << '='
str << encode_www_form_component(v, enc)
end
end.join('&')
end
# Returns name/value pairs derived from the given string +str+,
# which must be an ASCII string.
#
# The method may be used to decode the body of Net::HTTPResponse object +res+
# for which <tt>res['Content-Type']</tt> is <tt>'application/x-www-form-urlencoded'</tt>.
#
# The returned data is an array of 2-element subarrays;
# each subarray is a name/value pair (both are strings).
# Each returned string has encoding +enc+,
# and has had invalid characters removed via
# {String#scrub}[https://docs.ruby-lang.org/en/master/String.html#method-i-scrub].
#
# A simple example:
#
# URI.decode_www_form('foo=0&bar=1&baz')
# # => [["foo", "0"], ["bar", "1"], ["baz", ""]]
#
# The returned strings have certain conversions,
# similar to those performed in URI.decode_www_form_component:
#
# URI.decode_www_form('f%23o=%2F&b-r=%24&b+z=%40')
# # => [["f#o", "/"], ["b-r", "$"], ["b z", "@"]]
#
# The given string may contain consecutive separators:
#
# URI.decode_www_form('foo=0&&bar=1&&baz=2')
# # => [["foo", "0"], ["", ""], ["bar", "1"], ["", ""], ["baz", "2"]]
#
# A different separator may be specified:
#
# URI.decode_www_form('foo=0--bar=1--baz', separator: '--')
# # => [["foo", "0"], ["bar", "1"], ["baz", ""]]
#
def self.decode_www_form(str, enc=Encoding::UTF_8, separator: '&', use__charset_: false, isindex: false)
raise ArgumentError, "the input of #{self.name}.#{__method__} must be ASCII only string" unless str.ascii_only?
ary = []
return ary if str.empty?
enc = Encoding.find(enc)
str.b.each_line(separator) do |string|
string.chomp!(separator)
key, sep, val = string.partition('=')
if isindex
if sep.empty?
val = key
key = +''
end
isindex = false
end
if use__charset_ and key == '_charset_' and e = get_encoding(val)
enc = e
use__charset_ = false
end
key.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_)
if val
val.gsub!(/\+|%\h\h/, TBLDECWWWCOMP_)
else
val = +''
end
ary << [key, val]
end
ary.each do |k, v|
k.force_encoding(enc)
k.scrub!
v.force_encoding(enc)
v.scrub!
end
ary
end
private
=begin command for WEB_ENCODINGS_
curl https://encoding.spec.whatwg.org/encodings.json|
ruby -rjson -e 'H={}
h={
"shift_jis"=>"Windows-31J",
"euc-jp"=>"cp51932",
"iso-2022-jp"=>"cp50221",
"x-mac-cyrillic"=>"macCyrillic",
}
JSON($<.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
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",
"koi8-ru"=>"koi8-u",
"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",
"ms932"=>"Windows-31J",
"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",
"utf-16le"=>"utf-16le",
} # :nodoc:
Ractor.make_shareable(WEB_ENCODINGS_) if defined?(Ractor)
# :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
end # module URI
module Kernel
#
# Returns a \URI object derived from the given +uri+,
# which may be a \URI string or an existing \URI object:
#
# # Returns a new URI.
# uri = URI('http://github.com/ruby/ruby')
# # => #<URI::HTTP http://github.com/ruby/ruby>
# # Returns the given URI.
# URI(uri)
# # => #<URI::HTTP http://github.com/ruby/ruby>
#
def URI(uri)
if uri.is_a?(URI::Generic)
uri
elsif uri = String.try_convert(uri)
URI.parse(uri)
else
raise ArgumentError,
"bad argument (expected URI object or URI string)"
end
end
module_function :URI
end
+100
View File
@@ -0,0 +1,100 @@
# frozen_string_literal: true
require_relative 'generic'
module URI
#
# The "file" URI is defined by RFC8089.
#
class File < Generic
# A Default port of nil for URI::File.
DEFAULT_PORT = nil
#
# An Array of the available components for URI::File.
#
COMPONENT = [
:scheme,
:host,
:path
].freeze
#
# == Description
#
# Creates a new URI::File object from components, with syntax checking.
#
# The components accepted are +host+ and +path+.
#
# The components should be provided either as an Array, or as a Hash
# with keys formed by preceding the component names with a colon.
#
# If an Array is used, the components must be passed in the
# order <code>[host, path]</code>.
#
# A path from e.g. the File class should be escaped before
# being passed.
#
# Examples:
#
# require 'uri'
#
# uri1 = URI::File.build(['host.example.com', '/path/file.zip'])
# uri1.to_s # => "file://host.example.com/path/file.zip"
#
# uri2 = URI::File.build({:host => 'host.example.com',
# :path => '/ruby/src'})
# uri2.to_s # => "file://host.example.com/ruby/src"
#
# uri3 = URI::File.build({:path => URI::escape('/path/my file.txt')})
# uri3.to_s # => "file:///path/my%20file.txt"
#
def self.build(args)
tmp = Util::make_components_hash(self, args)
super(tmp)
end
# Protected setter for the host component +v+.
#
# See also URI::Generic.host=.
#
def set_host(v)
v = "" if v.nil? || v == "localhost"
@host = v
end
# do nothing
def set_port(v)
end
# raise InvalidURIError
def check_userinfo(user)
raise URI::InvalidURIError, "can not set userinfo for file URI"
end
# raise InvalidURIError
def check_user(user)
raise URI::InvalidURIError, "can not set user for file URI"
end
# raise InvalidURIError
def check_password(user)
raise URI::InvalidURIError, "can not set password for file URI"
end
# do nothing
def set_userinfo(v)
end
# do nothing
def set_user(v)
end
# do nothing
def set_password(v)
end
end
register_scheme 'FILE', File
end
+267
View File
@@ -0,0 +1,267 @@
# frozen_string_literal: false
# = uri/ftp.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# License:: You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'generic'
module URI
#
# FTP URI syntax is defined by RFC1738 section 3.2.
#
# This class will be redesigned because of difference of implementations;
# the structure of its path. draft-hoffman-ftp-uri-04 is a draft but it
# is a good summary about the de facto spec.
# http://tools.ietf.org/html/draft-hoffman-ftp-uri-04
#
class FTP < Generic
# A Default port of 21 for URI::FTP.
DEFAULT_PORT = 21
#
# An Array of the available components for URI::FTP.
#
COMPONENT = [
:scheme,
:userinfo, :host, :port,
:path, :typecode
].freeze
#
# Typecode is "a", "i", or "d".
#
# * "a" indicates a text file (the FTP command was ASCII)
# * "i" indicates a binary file (FTP command IMAGE)
# * "d" indicates the contents of a directory should be displayed
#
TYPECODE = ['a', 'i', 'd'].freeze
# Typecode prefix ";type=".
TYPECODE_PREFIX = ';type='.freeze
def self.new2(user, password, host, port, path,
typecode = nil, arg_check = true) # :nodoc:
# Do not use this method! Not tested. [Bug #7301]
# This methods remains just for compatibility,
# Keep it undocumented until the active maintainer is assigned.
typecode = nil if typecode.size == 0
if typecode && !TYPECODE.include?(typecode)
raise ArgumentError,
"bad typecode is specified: #{typecode}"
end
# do escape
self.new('ftp',
[user, password],
host, port, nil,
typecode ? path + TYPECODE_PREFIX + typecode : path,
nil, nil, nil, arg_check)
end
#
# == Description
#
# Creates a new URI::FTP object from components, with syntax checking.
#
# The components accepted are +userinfo+, +host+, +port+, +path+, and
# +typecode+.
#
# The components should be provided either as an Array, or as a Hash
# with keys formed by preceding the component names with a colon.
#
# If an Array is used, the components must be passed in the
# order <code>[userinfo, host, port, path, typecode]</code>.
#
# If the path supplied is absolute, it will be escaped in order to
# make it absolute in the URI.
#
# Examples:
#
# require 'uri'
#
# uri1 = URI::FTP.build(['user:password', 'ftp.example.com', nil,
# '/path/file.zip', 'i'])
# uri1.to_s # => "ftp://user:password@ftp.example.com/%2Fpath/file.zip;type=i"
#
# uri2 = URI::FTP.build({:host => 'ftp.example.com',
# :path => 'ruby/src'})
# uri2.to_s # => "ftp://ftp.example.com/ruby/src"
#
def self.build(args)
# Fix the incoming path to be generic URL syntax
# FTP path -> URL path
# foo/bar /foo/bar
# /foo/bar /%2Ffoo/bar
#
if args.kind_of?(Array)
args[3] = '/' + args[3].sub(/^\//, '%2F')
else
args[:path] = '/' + args[:path].sub(/^\//, '%2F')
end
tmp = Util::make_components_hash(self, args)
if tmp[:typecode]
if tmp[:typecode].size == 1
tmp[:typecode] = TYPECODE_PREFIX + tmp[:typecode]
end
tmp[:path] << tmp[:typecode]
end
return super(tmp)
end
#
# == Description
#
# Creates a new URI::FTP object from generic URL components with no
# syntax checking.
#
# Unlike build(), this method does not escape the path component as
# required by RFC1738; instead it is treated as per RFC2396.
#
# Arguments are +scheme+, +userinfo+, +host+, +port+, +registry+, +path+,
# +opaque+, +query+, and +fragment+, in that order.
#
def initialize(scheme,
userinfo, host, port, registry,
path, opaque,
query,
fragment,
parser = nil,
arg_check = false)
raise InvalidURIError unless path
path = path.sub(/^\//,'')
path.sub!(/^%2F/,'/')
super(scheme, userinfo, host, port, registry, path, opaque,
query, fragment, parser, arg_check)
@typecode = nil
if tmp = @path.index(TYPECODE_PREFIX)
typecode = @path[tmp + TYPECODE_PREFIX.size..-1]
@path = @path[0..tmp - 1]
if arg_check
self.typecode = typecode
else
self.set_typecode(typecode)
end
end
end
# typecode accessor.
#
# See URI::FTP::COMPONENT.
attr_reader :typecode
# Validates typecode +v+,
# returns +true+ or +false+.
#
def check_typecode(v)
if TYPECODE.include?(v)
return true
else
raise InvalidComponentError,
"bad typecode(expected #{TYPECODE.join(', ')}): #{v}"
end
end
private :check_typecode
# Private setter for the typecode +v+.
#
# See also URI::FTP.typecode=.
#
def set_typecode(v)
@typecode = v
end
protected :set_typecode
#
# == Args
#
# +v+::
# String
#
# == Description
#
# Public setter for the typecode +v+
# (with validation).
#
# See also URI::FTP.check_typecode.
#
# == Usage
#
# require 'uri'
#
# uri = URI.parse("ftp://john@ftp.example.com/my_file.img")
# #=> #<URI::FTP ftp://john@ftp.example.com/my_file.img>
# uri.typecode = "i"
# uri
# #=> #<URI::FTP ftp://john@ftp.example.com/my_file.img;type=i>
#
def typecode=(typecode)
check_typecode(typecode)
set_typecode(typecode)
typecode
end
def merge(oth) # :nodoc:
tmp = super(oth)
if self != tmp
tmp.set_typecode(oth.typecode)
end
return tmp
end
# Returns the path from an FTP URI.
#
# RFC 1738 specifically states that the path for an FTP URI does not
# include the / which separates the URI path from the URI host. Example:
#
# <code>ftp://ftp.example.com/pub/ruby</code>
#
# The above URI indicates that the client should connect to
# ftp.example.com then cd to pub/ruby from the initial login directory.
#
# If you want to cd to an absolute directory, you must include an
# escaped / (%2F) in the path. Example:
#
# <code>ftp://ftp.example.com/%2Fpub/ruby</code>
#
# This method will then return "/pub/ruby".
#
def path
return @path.sub(/^\//,'').sub(/^%2F/,'/')
end
# Private setter for the path of the URI::FTP.
def set_path(v)
super("/" + v.sub(/^\//, "%2F"))
end
protected :set_path
# Returns a String representation of the URI::FTP.
def to_s
save_path = nil
if @typecode
save_path = @path
@path = @path + TYPECODE_PREFIX + @typecode
end
str = super
if @typecode
@path = save_path
end
return str
end
end
register_scheme 'FTP', FTP
end
File diff suppressed because it is too large Load Diff
+125
View File
@@ -0,0 +1,125 @@
# frozen_string_literal: false
# = uri/http.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# License:: You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'generic'
module URI
#
# The syntax of HTTP URIs is defined in RFC1738 section 3.3.
#
# Note that the Ruby URI library allows HTTP URLs containing usernames and
# passwords. This is not legal as per the RFC, but used to be
# supported in Internet Explorer 5 and 6, before the MS04-004 security
# update. See <URL:http://support.microsoft.com/kb/834489>.
#
class HTTP < Generic
# A Default port of 80 for URI::HTTP.
DEFAULT_PORT = 80
# An Array of the available components for URI::HTTP.
COMPONENT = %i[
scheme
userinfo host port
path
query
fragment
].freeze
#
# == Description
#
# Creates a new URI::HTTP object from components, with syntax checking.
#
# The components accepted are userinfo, host, port, path, query, and
# fragment.
#
# The components should be provided either as an Array, or as a Hash
# with keys formed by preceding the component names with a colon.
#
# If an Array is used, the components must be passed in the
# order <code>[userinfo, host, port, path, query, fragment]</code>.
#
# Example:
#
# uri = URI::HTTP.build(host: 'www.example.com', path: '/foo/bar')
#
# uri = URI::HTTP.build([nil, "www.example.com", nil, "/path",
# "query", 'fragment'])
#
# Currently, if passed userinfo components this method generates
# invalid HTTP URIs as per RFC 1738.
#
def self.build(args)
tmp = Util.make_components_hash(self, args)
super(tmp)
end
#
# == Description
#
# Returns the full path for an HTTP request, as required by Net::HTTP::Get.
#
# If the URI contains a query, the full path is URI#path + '?' + URI#query.
# Otherwise, the path is simply URI#path.
#
# Example:
#
# uri = URI::HTTP.build(path: '/foo/bar', query: 'test=true')
# uri.request_uri # => "/foo/bar?test=true"
#
def request_uri
return unless @path
url = @query ? "#@path?#@query" : @path.dup
url.start_with?(?/.freeze) ? url : ?/ + url
end
#
# == Description
#
# Returns the authority for an HTTP uri, as defined in
# https://datatracker.ietf.org/doc/html/rfc3986/#section-3.2.
#
#
# Example:
#
# URI::HTTP.build(host: 'www.example.com', path: '/foo/bar').authority #=> "www.example.com"
# URI::HTTP.build(host: 'www.example.com', port: 8000, path: '/foo/bar').authority #=> "www.example.com:8000"
# URI::HTTP.build(host: 'www.example.com', port: 80, path: '/foo/bar').authority #=> "www.example.com"
#
def authority
if port == default_port
host
else
"#{host}:#{port}"
end
end
#
# == Description
#
# Returns the origin for an HTTP uri, as defined in
# https://datatracker.ietf.org/doc/html/rfc6454.
#
#
# Example:
#
# URI::HTTP.build(host: 'www.example.com', path: '/foo/bar').origin #=> "http://www.example.com"
# URI::HTTP.build(host: 'www.example.com', port: 8000, path: '/foo/bar').origin #=> "http://www.example.com:8000"
# URI::HTTP.build(host: 'www.example.com', port: 80, path: '/foo/bar').origin #=> "http://www.example.com"
# URI::HTTPS.build(host: 'www.example.com', path: '/foo/bar').origin #=> "https://www.example.com"
#
def origin
"#{scheme}://#{authority}"
end
end
register_scheme 'HTTP', HTTP
end
+23
View File
@@ -0,0 +1,23 @@
# frozen_string_literal: false
# = uri/https.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# License:: You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'http'
module URI
# The default port for HTTPS URIs is 443, and the scheme is 'https:' rather
# than 'http:'. Other than that, HTTPS URIs are identical to HTTP URIs;
# see URI::HTTP.
class HTTPS < HTTP
# A Default port of 443 for URI::HTTPS
DEFAULT_PORT = 443
end
register_scheme 'HTTPS', HTTPS
end
+261
View File
@@ -0,0 +1,261 @@
# frozen_string_literal: false
# = uri/ldap.rb
#
# Author::
# Takaaki Tateishi <ttate@jaist.ac.jp>
# Akira Yamada <akira@ruby-lang.org>
# License::
# URI::LDAP is copyrighted free software by Takaaki Tateishi and Akira Yamada.
# You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'generic'
module URI
#
# LDAP URI SCHEMA (described in RFC2255).
#--
# ldap://<host>/<dn>[?<attrs>[?<scope>[?<filter>[?<extensions>]]]]
#++
class LDAP < Generic
# A Default port of 389 for URI::LDAP.
DEFAULT_PORT = 389
# An Array of the available components for URI::LDAP.
COMPONENT = [
:scheme,
:host, :port,
:dn,
:attributes,
:scope,
:filter,
:extensions,
].freeze
# Scopes available for the starting point.
#
# * SCOPE_BASE - the Base DN
# * SCOPE_ONE - one level under the Base DN, not including the base DN and
# not including any entries under this
# * SCOPE_SUB - subtrees, all entries at all levels
#
SCOPE = [
SCOPE_ONE = 'one',
SCOPE_SUB = 'sub',
SCOPE_BASE = 'base',
].freeze
#
# == Description
#
# Creates a new URI::LDAP object from components, with syntax checking.
#
# The components accepted are host, port, dn, attributes,
# scope, filter, and extensions.
#
# The components should be provided either as an Array, or as a Hash
# with keys formed by preceding the component names with a colon.
#
# If an Array is used, the components must be passed in the
# order <code>[host, port, dn, attributes, scope, filter, extensions]</code>.
#
# Example:
#
# uri = URI::LDAP.build({:host => 'ldap.example.com',
# :dn => '/dc=example'})
#
# uri = URI::LDAP.build(["ldap.example.com", nil,
# "/dc=example;dc=com", "query", nil, nil, nil])
#
def self.build(args)
tmp = Util::make_components_hash(self, args)
if tmp[:dn]
tmp[:path] = tmp[:dn]
end
query = []
[:extensions, :filter, :scope, :attributes].collect do |x|
next if !tmp[x] && query.size == 0
query.unshift(tmp[x])
end
tmp[:query] = query.join('?')
return super(tmp)
end
#
# == Description
#
# Creates a new URI::LDAP object from generic URI components as per
# RFC 2396. No LDAP-specific syntax checking is performed.
#
# Arguments are +scheme+, +userinfo+, +host+, +port+, +registry+, +path+,
# +opaque+, +query+, and +fragment+, in that order.
#
# Example:
#
# uri = URI::LDAP.new("ldap", nil, "ldap.example.com", nil, nil,
# "/dc=example;dc=com", nil, "query", nil)
#
# See also URI::Generic.new.
#
def initialize(*arg)
super(*arg)
if @fragment
raise InvalidURIError, 'bad LDAP URL'
end
parse_dn
parse_query
end
# Private method to cleanup +dn+ from using the +path+ component attribute.
def parse_dn
raise InvalidURIError, 'bad LDAP URL' unless @path
@dn = @path[1..-1]
end
private :parse_dn
# Private method to cleanup +attributes+, +scope+, +filter+, and +extensions+
# from using the +query+ component attribute.
def parse_query
@attributes = nil
@scope = nil
@filter = nil
@extensions = nil
if @query
attrs, scope, filter, extensions = @query.split('?')
@attributes = attrs if attrs && attrs.size > 0
@scope = scope if scope && scope.size > 0
@filter = filter if filter && filter.size > 0
@extensions = extensions if extensions && extensions.size > 0
end
end
private :parse_query
# Private method to assemble +query+ from +attributes+, +scope+, +filter+, and +extensions+.
def build_path_query
@path = '/' + @dn
query = []
[@extensions, @filter, @scope, @attributes].each do |x|
next if !x && query.size == 0
query.unshift(x)
end
@query = query.join('?')
end
private :build_path_query
# Returns dn.
def dn
@dn
end
# Private setter for dn +val+.
def set_dn(val)
@dn = val
build_path_query
@dn
end
protected :set_dn
# Setter for dn +val+.
def dn=(val)
set_dn(val)
val
end
# Returns attributes.
def attributes
@attributes
end
# Private setter for attributes +val+.
def set_attributes(val)
@attributes = val
build_path_query
@attributes
end
protected :set_attributes
# Setter for attributes +val+.
def attributes=(val)
set_attributes(val)
val
end
# Returns scope.
def scope
@scope
end
# Private setter for scope +val+.
def set_scope(val)
@scope = val
build_path_query
@scope
end
protected :set_scope
# Setter for scope +val+.
def scope=(val)
set_scope(val)
val
end
# Returns filter.
def filter
@filter
end
# Private setter for filter +val+.
def set_filter(val)
@filter = val
build_path_query
@filter
end
protected :set_filter
# Setter for filter +val+.
def filter=(val)
set_filter(val)
val
end
# Returns extensions.
def extensions
@extensions
end
# Private setter for extensions +val+.
def set_extensions(val)
@extensions = val
build_path_query
@extensions
end
protected :set_extensions
# Setter for extensions +val+.
def extensions=(val)
set_extensions(val)
val
end
# Checks if URI has a path.
# For URI::LDAP this will return +false+.
def hierarchical?
false
end
end
register_scheme 'LDAP', LDAP
end
+22
View File
@@ -0,0 +1,22 @@
# frozen_string_literal: false
# = uri/ldap.rb
#
# License:: You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'ldap'
module URI
# The default port for LDAPS URIs is 636, and the scheme is 'ldaps:' rather
# than 'ldap:'. Other than that, LDAPS URIs are identical to LDAP URIs;
# see URI::LDAP.
class LDAPS < LDAP
# A Default port of 636 for URI::LDAPS
DEFAULT_PORT = 636
end
register_scheme 'LDAPS', LDAPS
end
+293
View File
@@ -0,0 +1,293 @@
# frozen_string_literal: false
# = uri/mailto.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# License:: You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'generic'
module URI
#
# RFC6068, the mailto URL scheme.
#
class MailTo < Generic
include RFC2396_REGEXP
# A Default port of nil for URI::MailTo.
DEFAULT_PORT = nil
# An Array of the available components for URI::MailTo.
COMPONENT = [ :scheme, :to, :headers ].freeze
# :stopdoc:
# "hname" and "hvalue" are encodings of an RFC 822 header name and
# value, respectively. As with "to", all URL reserved characters must
# be encoded.
#
# "#mailbox" is as specified in RFC 822 [RFC822]. This means that it
# consists of zero or more comma-separated mail addresses, possibly
# including "phrase" and "comment" components. Note that all URL
# reserved characters in "to" must be encoded: in particular,
# parentheses, commas, and the percent sign ("%"), which commonly occur
# in the "mailbox" syntax.
#
# Within mailto URLs, the characters "?", "=", "&" are reserved.
# ; RFC 6068
# hfields = "?" hfield *( "&" hfield )
# hfield = hfname "=" hfvalue
# hfname = *qchar
# hfvalue = *qchar
# qchar = unreserved / pct-encoded / some-delims
# some-delims = "!" / "$" / "'" / "(" / ")" / "*"
# / "+" / "," / ";" / ":" / "@"
#
# ; RFC3986
# unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
# pct-encoded = "%" HEXDIG HEXDIG
HEADER_REGEXP = /\A(?<hfield>(?:%\h\h|[!$'-.0-;@-Z_a-z~])*=(?:%\h\h|[!$'-.0-;@-Z_a-z~])*)(?:&\g<hfield>)*\z/
# practical regexp for email address
# https://html.spec.whatwg.org/multipage/input.html#valid-e-mail-address
EMAIL_REGEXP = /\A[a-zA-Z0-9.!\#$%&'*+\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*\z/
# :startdoc:
#
# == Description
#
# Creates a new URI::MailTo object from components, with syntax checking.
#
# Components can be provided as an Array or Hash. If an Array is used,
# the components must be supplied as <code>[to, headers]</code>.
#
# If a Hash is used, the keys are the component names preceded by colons.
#
# The headers can be supplied as a pre-encoded string, such as
# <code>"subject=subscribe&cc=address"</code>, or as an Array of Arrays
# like <code>[['subject', 'subscribe'], ['cc', 'address']]</code>.
#
# Examples:
#
# require 'uri'
#
# m1 = URI::MailTo.build(['joe@example.com', 'subject=Ruby'])
# m1.to_s # => "mailto:joe@example.com?subject=Ruby"
#
# m2 = URI::MailTo.build(['john@example.com', [['Subject', 'Ruby'], ['Cc', 'jack@example.com']]])
# m2.to_s # => "mailto:john@example.com?Subject=Ruby&Cc=jack@example.com"
#
# m3 = URI::MailTo.build({:to => 'listman@example.com', :headers => [['subject', 'subscribe']]})
# m3.to_s # => "mailto:listman@example.com?subject=subscribe"
#
def self.build(args)
tmp = Util.make_components_hash(self, args)
case tmp[:to]
when Array
tmp[:opaque] = tmp[:to].join(',')
when String
tmp[:opaque] = tmp[:to].dup
else
tmp[:opaque] = ''
end
if tmp[:headers]
query =
case tmp[:headers]
when Array
tmp[:headers].collect { |x|
if x.kind_of?(Array)
x[0] + '=' + x[1..-1].join
else
x.to_s
end
}.join('&')
when Hash
tmp[:headers].collect { |h,v|
h + '=' + v
}.join('&')
else
tmp[:headers].to_s
end
unless query.empty?
tmp[:opaque] << '?' << query
end
end
super(tmp)
end
#
# == Description
#
# Creates a new URI::MailTo object from generic URL components with
# no syntax checking.
#
# This method is usually called from URI::parse, which checks
# the validity of each component.
#
def initialize(*arg)
super(*arg)
@to = nil
@headers = []
# The RFC3986 parser does not normally populate opaque
@opaque = "?#{@query}" if @query && !@opaque
unless @opaque
raise InvalidComponentError,
"missing opaque part for mailto URL"
end
to, header = @opaque.split('?', 2)
# allow semicolon as a addr-spec separator
# http://support.microsoft.com/kb/820868
unless /\A(?:[^@,;]+@[^@,;]+(?:\z|[,;]))*\z/ =~ to
raise InvalidComponentError,
"unrecognised opaque part for mailtoURL: #{@opaque}"
end
if arg[10] # arg_check
self.to = to
self.headers = header
else
set_to(to)
set_headers(header)
end
end
# The primary e-mail address of the URL, as a String.
attr_reader :to
# E-mail headers set by the URL, as an Array of Arrays.
attr_reader :headers
# Checks the to +v+ component.
def check_to(v)
return true unless v
return true if v.size == 0
v.split(/[,;]/).each do |addr|
# check url safety as path-rootless
if /\A(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*\z/ !~ addr
raise InvalidComponentError,
"an address in 'to' is invalid as URI #{addr.dump}"
end
# check addr-spec
# don't s/\+/ /g
addr.gsub!(/%\h\h/, URI::TBLDECWWWCOMP_)
if EMAIL_REGEXP !~ addr
raise InvalidComponentError,
"an address in 'to' is invalid as uri-escaped addr-spec #{addr.dump}"
end
end
true
end
private :check_to
# Private setter for to +v+.
def set_to(v)
@to = v
end
protected :set_to
# Setter for to +v+.
def to=(v)
check_to(v)
set_to(v)
v
end
# Checks the headers +v+ component against either
# * HEADER_REGEXP
def check_headers(v)
return true unless v
return true if v.size == 0
if HEADER_REGEXP !~ v
raise InvalidComponentError,
"bad component(expected opaque component): #{v}"
end
true
end
private :check_headers
# Private setter for headers +v+.
def set_headers(v)
@headers = []
if v
v.split('&').each do |x|
@headers << x.split(/=/, 2)
end
end
end
protected :set_headers
# Setter for headers +v+.
def headers=(v)
check_headers(v)
set_headers(v)
v
end
# Constructs String from URI.
def to_s
@scheme + ':' +
if @to
@to
else
''
end +
if @headers.size > 0
'?' + @headers.collect{|x| x.join('=')}.join('&')
else
''
end +
if @fragment
'#' + @fragment
else
''
end
end
# Returns the RFC822 e-mail text equivalent of the URL, as a String.
#
# Example:
#
# require 'uri'
#
# uri = URI.parse("mailto:ruby-list@ruby-lang.org?Subject=subscribe&cc=myaddr")
# uri.to_mailtext
# # => "To: ruby-list@ruby-lang.org\nSubject: subscribe\nCc: myaddr\n\n\n"
#
def to_mailtext
to = URI.decode_www_form_component(@to)
head = ''
body = ''
@headers.each do |x|
case x[0]
when 'body'
body = URI.decode_www_form_component(x[1])
when 'to'
to << ', ' + URI.decode_www_form_component(x[1])
else
head << URI.decode_www_form_component(x[0]).capitalize + ': ' +
URI.decode_www_form_component(x[1]) + "\n"
end
end
"To: #{to}
#{head}
#{body}
"
end
alias to_rfc822text to_mailtext
end
register_scheme 'MAILTO', MailTo
end
@@ -0,0 +1,539 @@
# frozen_string_literal: false
#--
# = uri/common.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# License::
# You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
module URI
#
# Includes URI::REGEXP::PATTERN
#
module RFC2396_REGEXP
#
# Patterns used to parse URI's
#
module PATTERN
# :stopdoc:
# RFC 2396 (URI Generic Syntax)
# RFC 2732 (IPv6 Literal Addresses in URL's)
# RFC 2373 (IPv6 Addressing Architecture)
# alpha = lowalpha | upalpha
ALPHA = "a-zA-Z"
# alphanum = alpha | digit
ALNUM = "#{ALPHA}\\d"
# hex = digit | "A" | "B" | "C" | "D" | "E" | "F" |
# "a" | "b" | "c" | "d" | "e" | "f"
HEX = "a-fA-F\\d"
# escaped = "%" hex hex
ESCAPED = "%[#{HEX}]{2}"
# mark = "-" | "_" | "." | "!" | "~" | "*" | "'" |
# "(" | ")"
# unreserved = alphanum | mark
UNRESERVED = "\\-_.!~*'()#{ALNUM}"
# reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
# "$" | ","
# reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
# "$" | "," | "[" | "]" (RFC 2732)
RESERVED = ";/?:@&=+$,\\[\\]"
# domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
# toplabel = alpha | alpha *( alphanum | "-" ) alphanum
TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
# hostname = *( domainlabel "." ) toplabel [ "." ]
HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?"
# :startdoc:
end # PATTERN
# :startdoc:
end # REGEXP
# Class that parses String's into URI's.
#
# It contains a Hash set of patterns and Regexp's that match and validate.
#
class RFC2396_Parser
include RFC2396_REGEXP
#
# == Synopsis
#
# URI::Parser.new([opts])
#
# == Args
#
# The constructor accepts a hash as options for parser.
# Keys of options are pattern names of URI components
# and values of options are pattern strings.
# The constructor generates set of regexps for parsing URIs.
#
# You can use the following keys:
#
# * :ESCAPED (URI::PATTERN::ESCAPED in default)
# * :UNRESERVED (URI::PATTERN::UNRESERVED in default)
# * :DOMLABEL (URI::PATTERN::DOMLABEL in default)
# * :TOPLABEL (URI::PATTERN::TOPLABEL in default)
# * :HOSTNAME (URI::PATTERN::HOSTNAME in default)
#
# == Examples
#
# p = URI::Parser.new(:ESCAPED => "(?:%[a-fA-F0-9]{2}|%u[a-fA-F0-9]{4})")
# u = p.parse("http://example.jp/%uABCD") #=> #<URI::HTTP http://example.jp/%uABCD>
# URI.parse(u.to_s) #=> raises URI::InvalidURIError
#
# s = "http://example.com/ABCD"
# u1 = p.parse(s) #=> #<URI::HTTP http://example.com/ABCD>
# u2 = URI.parse(s) #=> #<URI::HTTP http://example.com/ABCD>
# u1 == u2 #=> true
# u1.eql?(u2) #=> false
#
def initialize(opts = {})
@pattern = initialize_pattern(opts)
@pattern.each_value(&:freeze)
@pattern.freeze
@regexp = initialize_regexp(@pattern)
@regexp.each_value(&:freeze)
@regexp.freeze
end
# The Hash of patterns.
#
# See also URI::Parser.initialize_pattern.
attr_reader :pattern
# The Hash of Regexp.
#
# See also URI::Parser.initialize_regexp.
attr_reader :regexp
# Returns a split URI against +regexp[:ABS_URI]+.
def split(uri)
case uri
when ''
# null uri
when @regexp[:ABS_URI]
scheme, opaque, userinfo, host, port,
registry, path, query, fragment = $~[1..-1]
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
# absoluteURI = scheme ":" ( hier_part | opaque_part )
# hier_part = ( net_path | abs_path ) [ "?" query ]
# opaque_part = uric_no_slash *uric
# abs_path = "/" path_segments
# net_path = "//" authority [ abs_path ]
# authority = server | reg_name
# server = [ [ userinfo "@" ] hostport ]
if !scheme
raise InvalidURIError,
"bad URI(absolute but no scheme): #{uri}"
end
if !opaque && (!path && (!host && !registry))
raise InvalidURIError,
"bad URI(absolute but no path): #{uri}"
end
when @regexp[:REL_URI]
scheme = nil
opaque = nil
userinfo, host, port, registry,
rel_segment, abs_path, query, fragment = $~[1..-1]
if rel_segment && abs_path
path = rel_segment + abs_path
elsif rel_segment
path = rel_segment
elsif abs_path
path = abs_path
end
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
# relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
# net_path = "//" authority [ abs_path ]
# abs_path = "/" path_segments
# rel_path = rel_segment [ abs_path ]
# authority = server | reg_name
# server = [ [ userinfo "@" ] hostport ]
else
raise InvalidURIError, "bad URI(is not URI?): #{uri}"
end
path = '' if !path && !opaque # (see RFC2396 Section 5.2)
ret = [
scheme,
userinfo, host, port, # X
registry, # X
path, # Y
opaque, # Y
query,
fragment
]
return ret
end
#
# == Args
#
# +uri+::
# String
#
# == Description
#
# Parses +uri+ and constructs either matching URI scheme object
# (File, FTP, HTTP, HTTPS, LDAP, LDAPS, or MailTo) or URI::Generic.
#
# == Usage
#
# p = URI::Parser.new
# p.parse("ldap://ldap.example.com/dc=example?user=john")
# #=> #<URI::LDAP ldap://ldap.example.com/dc=example?user=john>
#
def parse(uri)
URI.for(*self.split(uri), self)
end
#
# == Args
#
# +uris+::
# an Array of Strings
#
# == Description
#
# Attempts to parse and merge a set of URIs.
#
def join(*uris)
uris[0] = convert_to_uri(uris[0])
uris.inject :merge
end
#
# :call-seq:
# extract( str )
# extract( str, schemes )
# extract( str, schemes ) {|item| block }
#
# == Args
#
# +str+::
# String to search
# +schemes+::
# Patterns to apply to +str+
#
# == Description
#
# Attempts to parse and merge a set of URIs.
# If no +block+ given, then returns the result,
# else it calls +block+ for each element in result.
#
# See also URI::Parser.make_regexp.
#
def extract(str, schemes = nil)
if block_given?
str.scan(make_regexp(schemes)) { yield $& }
nil
else
result = []
str.scan(make_regexp(schemes)) { result.push $& }
result
end
end
# Returns Regexp that is default +self.regexp[:ABS_URI_REF]+,
# unless +schemes+ is provided. Then it is a Regexp.union with +self.pattern[:X_ABS_URI]+.
def make_regexp(schemes = nil)
unless schemes
@regexp[:ABS_URI_REF]
else
/(?=#{Regexp.union(*schemes)}:)#{@pattern[:X_ABS_URI]}/x
end
end
#
# :call-seq:
# escape( str )
# escape( str, unsafe )
#
# == Args
#
# +str+::
# String to make safe
# +unsafe+::
# Regexp to apply. Defaults to +self.regexp[:UNSAFE]+
#
# == Description
#
# Constructs a safe String from +str+, removing unsafe characters,
# replacing them with codes.
#
def escape(str, unsafe = @regexp[:UNSAFE])
unless unsafe.kind_of?(Regexp)
# perhaps unsafe is String object
unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false)
end
str.gsub(unsafe) do
us = $&
tmp = ''
us.each_byte do |uc|
tmp << sprintf('%%%02X', uc)
end
tmp
end.force_encoding(Encoding::US_ASCII)
end
#
# :call-seq:
# unescape( str )
# unescape( str, escaped )
#
# == Args
#
# +str+::
# String to remove escapes from
# +escaped+::
# Regexp to apply. Defaults to +self.regexp[:ESCAPED]+
#
# == Description
#
# Removes escapes from +str+.
#
def unescape(str, escaped = @regexp[:ESCAPED])
enc = str.encoding
enc = Encoding::UTF_8 if enc == Encoding::US_ASCII
str.gsub(escaped) { [$&[1, 2]].pack('H2').force_encoding(enc) }
end
@@to_s = Kernel.instance_method(:to_s)
if @@to_s.respond_to?(:bind_call)
def inspect
@@to_s.bind_call(self)
end
else
def inspect
@@to_s.bind(self).call
end
end
private
# Constructs the default Hash of patterns.
def initialize_pattern(opts = {})
ret = {}
ret[:ESCAPED] = escaped = (opts.delete(:ESCAPED) || PATTERN::ESCAPED)
ret[:UNRESERVED] = unreserved = opts.delete(:UNRESERVED) || PATTERN::UNRESERVED
ret[:RESERVED] = reserved = opts.delete(:RESERVED) || PATTERN::RESERVED
ret[:DOMLABEL] = opts.delete(:DOMLABEL) || PATTERN::DOMLABEL
ret[:TOPLABEL] = opts.delete(:TOPLABEL) || PATTERN::TOPLABEL
ret[:HOSTNAME] = hostname = opts.delete(:HOSTNAME)
# RFC 2396 (URI Generic Syntax)
# RFC 2732 (IPv6 Literal Addresses in URL's)
# RFC 2373 (IPv6 Addressing Architecture)
# uric = reserved | unreserved | escaped
ret[:URIC] = uric = "(?:[#{unreserved}#{reserved}]|#{escaped})"
# uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" |
# "&" | "=" | "+" | "$" | ","
ret[:URIC_NO_SLASH] = uric_no_slash = "(?:[#{unreserved};?:@&=+$,]|#{escaped})"
# query = *uric
ret[:QUERY] = query = "#{uric}*"
# fragment = *uric
ret[:FRAGMENT] = fragment = "#{uric}*"
# hostname = *( domainlabel "." ) toplabel [ "." ]
# reg-name = *( unreserved / pct-encoded / sub-delims ) # RFC3986
unless hostname
ret[:HOSTNAME] = hostname = "(?:[a-zA-Z0-9\\-.]|%\\h\\h)+"
end
# RFC 2373, APPENDIX B:
# IPv6address = hexpart [ ":" IPv4address ]
# IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
# hexpart = hexseq | hexseq "::" [ hexseq ] | "::" [ hexseq ]
# hexseq = hex4 *( ":" hex4)
# hex4 = 1*4HEXDIG
#
# XXX: This definition has a flaw. "::" + IPv4address must be
# allowed too. Here is a replacement.
#
# IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
ret[:IPV4ADDR] = ipv4addr = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"
# hex4 = 1*4HEXDIG
hex4 = "[#{PATTERN::HEX}]{1,4}"
# lastpart = hex4 | IPv4address
lastpart = "(?:#{hex4}|#{ipv4addr})"
# hexseq1 = *( hex4 ":" ) hex4
hexseq1 = "(?:#{hex4}:)*#{hex4}"
# hexseq2 = *( hex4 ":" ) lastpart
hexseq2 = "(?:#{hex4}:)*#{lastpart}"
# IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ]
ret[:IPV6ADDR] = ipv6addr = "(?:#{hexseq2}|(?:#{hexseq1})?::(?:#{hexseq2})?)"
# IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT
# unused
# ipv6reference = "[" IPv6address "]" (RFC 2732)
ret[:IPV6REF] = ipv6ref = "\\[#{ipv6addr}\\]"
# host = hostname | IPv4address
# host = hostname | IPv4address | IPv6reference (RFC 2732)
ret[:HOST] = host = "(?:#{hostname}|#{ipv4addr}|#{ipv6ref})"
# port = *digit
ret[:PORT] = port = '\d*'
# hostport = host [ ":" port ]
ret[:HOSTPORT] = hostport = "#{host}(?::#{port})?"
# userinfo = *( unreserved | escaped |
# ";" | ":" | "&" | "=" | "+" | "$" | "," )
ret[:USERINFO] = userinfo = "(?:[#{unreserved};:&=+$,]|#{escaped})*"
# pchar = unreserved | escaped |
# ":" | "@" | "&" | "=" | "+" | "$" | ","
pchar = "(?:[#{unreserved}:@&=+$,]|#{escaped})"
# param = *pchar
param = "#{pchar}*"
# segment = *pchar *( ";" param )
segment = "#{pchar}*(?:;#{param})*"
# path_segments = segment *( "/" segment )
ret[:PATH_SEGMENTS] = path_segments = "#{segment}(?:/#{segment})*"
# server = [ [ userinfo "@" ] hostport ]
server = "(?:#{userinfo}@)?#{hostport}"
# reg_name = 1*( unreserved | escaped | "$" | "," |
# ";" | ":" | "@" | "&" | "=" | "+" )
ret[:REG_NAME] = reg_name = "(?:[#{unreserved}$,;:@&=+]|#{escaped})+"
# authority = server | reg_name
authority = "(?:#{server}|#{reg_name})"
# rel_segment = 1*( unreserved | escaped |
# ";" | "@" | "&" | "=" | "+" | "$" | "," )
ret[:REL_SEGMENT] = rel_segment = "(?:[#{unreserved};@&=+$,]|#{escaped})+"
# scheme = alpha *( alpha | digit | "+" | "-" | "." )
ret[:SCHEME] = scheme = "[#{PATTERN::ALPHA}][\\-+.#{PATTERN::ALPHA}\\d]*"
# abs_path = "/" path_segments
ret[:ABS_PATH] = abs_path = "/#{path_segments}"
# rel_path = rel_segment [ abs_path ]
ret[:REL_PATH] = rel_path = "#{rel_segment}(?:#{abs_path})?"
# net_path = "//" authority [ abs_path ]
ret[:NET_PATH] = net_path = "//#{authority}(?:#{abs_path})?"
# hier_part = ( net_path | abs_path ) [ "?" query ]
ret[:HIER_PART] = hier_part = "(?:#{net_path}|#{abs_path})(?:\\?(?:#{query}))?"
# opaque_part = uric_no_slash *uric
ret[:OPAQUE_PART] = opaque_part = "#{uric_no_slash}#{uric}*"
# absoluteURI = scheme ":" ( hier_part | opaque_part )
ret[:ABS_URI] = abs_uri = "#{scheme}:(?:#{hier_part}|#{opaque_part})"
# relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
ret[:REL_URI] = rel_uri = "(?:#{net_path}|#{abs_path}|#{rel_path})(?:\\?#{query})?"
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
ret[:URI_REF] = "(?:#{abs_uri}|#{rel_uri})?(?:##{fragment})?"
ret[:X_ABS_URI] = "
(#{scheme}): (?# 1: scheme)
(?:
(#{opaque_part}) (?# 2: opaque)
|
(?:(?:
//(?:
(?:(?:(#{userinfo})@)? (?# 3: userinfo)
(?:(#{host})(?::(\\d*))?))? (?# 4: host, 5: port)
|
(#{reg_name}) (?# 6: registry)
)
|
(?!//)) (?# XXX: '//' is the mark for hostport)
(#{abs_path})? (?# 7: path)
)(?:\\?(#{query}))? (?# 8: query)
)
(?:\\#(#{fragment}))? (?# 9: fragment)
"
ret[:X_REL_URI] = "
(?:
(?:
//
(?:
(?:(#{userinfo})@)? (?# 1: userinfo)
(#{host})?(?::(\\d*))? (?# 2: host, 3: port)
|
(#{reg_name}) (?# 4: registry)
)
)
|
(#{rel_segment}) (?# 5: rel_segment)
)?
(#{abs_path})? (?# 6: abs_path)
(?:\\?(#{query}))? (?# 7: query)
(?:\\#(#{fragment}))? (?# 8: fragment)
"
ret
end
# Constructs the default Hash of Regexp's.
def initialize_regexp(pattern)
ret = {}
# for URI::split
ret[:ABS_URI] = Regexp.new('\A\s*+' + pattern[:X_ABS_URI] + '\s*\z', Regexp::EXTENDED)
ret[:REL_URI] = Regexp.new('\A\s*+' + pattern[:X_REL_URI] + '\s*\z', Regexp::EXTENDED)
# for URI::extract
ret[:URI_REF] = Regexp.new(pattern[:URI_REF])
ret[:ABS_URI_REF] = Regexp.new(pattern[:X_ABS_URI], Regexp::EXTENDED)
ret[:REL_URI_REF] = Regexp.new(pattern[:X_REL_URI], Regexp::EXTENDED)
# for URI::escape/unescape
ret[:ESCAPED] = Regexp.new(pattern[:ESCAPED])
ret[:UNSAFE] = Regexp.new("[^#{pattern[:UNRESERVED]}#{pattern[:RESERVED]}]")
# for Generic#initialize
ret[:SCHEME] = Regexp.new("\\A#{pattern[:SCHEME]}\\z")
ret[:USERINFO] = Regexp.new("\\A#{pattern[:USERINFO]}\\z")
ret[:HOST] = Regexp.new("\\A#{pattern[:HOST]}\\z")
ret[:PORT] = Regexp.new("\\A#{pattern[:PORT]}\\z")
ret[:OPAQUE] = Regexp.new("\\A#{pattern[:OPAQUE_PART]}\\z")
ret[:REGISTRY] = Regexp.new("\\A#{pattern[:REG_NAME]}\\z")
ret[:ABS_PATH] = Regexp.new("\\A#{pattern[:ABS_PATH]}\\z")
ret[:REL_PATH] = Regexp.new("\\A#{pattern[:REL_PATH]}\\z")
ret[:QUERY] = Regexp.new("\\A#{pattern[:QUERY]}\\z")
ret[:FRAGMENT] = Regexp.new("\\A#{pattern[:FRAGMENT]}\\z")
ret
end
def convert_to_uri(uri)
if uri.is_a?(URI::Generic)
uri
elsif uri = String.try_convert(uri)
parse(uri)
else
raise ArgumentError,
"bad argument (expected URI object or URI string)"
end
end
end # class Parser
end # module URI
@@ -0,0 +1,183 @@
# frozen_string_literal: true
module URI
class RFC3986_Parser # :nodoc:
# URI defined in RFC3986
HOST = %r[
(?<IP-literal>\[(?:
(?<IPv6address>
(?:\h{1,4}:){6}
(?<ls32>\h{1,4}:\h{1,4}
| (?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)
\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>)
)
| ::(?:\h{1,4}:){5}\g<ls32>
| \h{1,4}?::(?:\h{1,4}:){4}\g<ls32>
| (?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>
| (?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>
| (?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>
| (?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>
| (?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}
| (?:(?:\h{1,4}:){,6}\h{1,4})?::
)
| (?<IPvFuture>v\h++\.[!$&-.0-9:;=A-Z_a-z~]++)
)\])
| \g<IPv4address>
| (?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])*+)
]x
USERINFO = /(?:%\h\h|[!$&-.0-9:;=A-Z_a-z~])*+/
SCHEME = %r[[A-Za-z][+\-.0-9A-Za-z]*+].source
SEG = %r[(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/])].source
SEG_NC = %r[(?:%\h\h|[!$&-.0-9;=@A-Z_a-z~])].source
FRAGMENT = %r[(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/?])*+].source
RFC3986_URI = %r[\A
(?<seg>#{SEG}){0}
(?<URI>
(?<scheme>#{SCHEME}):
(?<hier-part>//
(?<authority>
(?:(?<userinfo>#{USERINFO.source})@)?
(?<host>#{HOST.source.delete(" \n")})
(?::(?<port>\d*+))?
)
(?<path-abempty>(?:/\g<seg>*+)?)
| (?<path-absolute>/((?!/)\g<seg>++)?)
| (?<path-rootless>(?!/)\g<seg>++)
| (?<path-empty>)
)
(?:\?(?<query>[^\#]*+))?
(?:\#(?<fragment>#{FRAGMENT}))?
)\z]x
RFC3986_relative_ref = %r[\A
(?<seg>#{SEG}){0}
(?<relative-ref>
(?<relative-part>//
(?<authority>
(?:(?<userinfo>#{USERINFO.source})@)?
(?<host>#{HOST.source.delete(" \n")}(?<!/))?
(?::(?<port>\d*+))?
)
(?<path-abempty>(?:/\g<seg>*+)?)
| (?<path-absolute>/\g<seg>*+)
| (?<path-noscheme>#{SEG_NC}++(?:/\g<seg>*+)?)
| (?<path-empty>)
)
(?:\?(?<query>[^#]*+))?
(?:\#(?<fragment>#{FRAGMENT}))?
)\z]x
attr_reader :regexp
def initialize
@regexp = default_regexp.each_value(&:freeze).freeze
end
def split(uri) #:nodoc:
begin
uri = uri.to_str
rescue NoMethodError
raise InvalidURIError, "bad URI(is not URI?): #{uri.inspect}"
end
uri.ascii_only? or
raise InvalidURIError, "URI must be ascii only #{uri.dump}"
if m = RFC3986_URI.match(uri)
query = m["query"]
scheme = m["scheme"]
opaque = m["path-rootless"]
if opaque
opaque << "?#{query}" if query
[ scheme,
nil, # userinfo
nil, # host
nil, # port
nil, # registry
nil, # path
opaque,
nil, # query
m["fragment"]
]
else # normal
[ scheme,
m["userinfo"],
m["host"],
m["port"],
nil, # registry
(m["path-abempty"] ||
m["path-absolute"] ||
m["path-empty"]),
nil, # opaque
query,
m["fragment"]
]
end
elsif m = RFC3986_relative_ref.match(uri)
[ nil, # scheme
m["userinfo"],
m["host"],
m["port"],
nil, # registry,
(m["path-abempty"] ||
m["path-absolute"] ||
m["path-noscheme"] ||
m["path-empty"]),
nil, # opaque
m["query"],
m["fragment"]
]
else
raise InvalidURIError, "bad URI(is not URI?): #{uri.inspect}"
end
end
def parse(uri) # :nodoc:
URI.for(*self.split(uri), self)
end
def join(*uris) # :nodoc:
uris[0] = convert_to_uri(uris[0])
uris.inject :merge
end
@@to_s = Kernel.instance_method(:to_s)
if @@to_s.respond_to?(:bind_call)
def inspect
@@to_s.bind_call(self)
end
else
def inspect
@@to_s.bind(self).call
end
end
private
def default_regexp # :nodoc:
{
SCHEME: %r[\A#{SCHEME}\z]o,
USERINFO: %r[\A#{USERINFO}\z]o,
HOST: %r[\A#{HOST}\z]o,
ABS_PATH: %r[\A/#{SEG}*+\z]o,
REL_PATH: %r[\A(?!/)#{SEG}++\z]o,
QUERY: %r[\A(?:%\h\h|[!$&-.0-9:;=@A-Z_a-z~/?])*+\z],
FRAGMENT: %r[\A#{FRAGMENT}\z]o,
OPAQUE: %r[\A(?:[^/].*)?\z],
PORT: /\A[\x09\x0a\x0c\x0d ]*+\d*[\x09\x0a\x0c\x0d ]*\z/,
}
end
def convert_to_uri(uri)
if uri.is_a?(URI::Generic)
uri
elsif uri = String.try_convert(uri)
parse(uri)
else
raise ArgumentError,
"bad argument (expected URI object or URI string)"
end
end
end # class Parser
end # module URI
+6
View File
@@ -0,0 +1,6 @@
module URI
# :stopdoc:
VERSION_CODE = '001302'.freeze
VERSION = VERSION_CODE.scan(/../).collect{|n| n.to_i}.join('.').freeze
# :startdoc:
end
+83
View File
@@ -0,0 +1,83 @@
# frozen_string_literal: false
# = uri/ws.rb
#
# Author:: Matt Muller <mamuller@amazon.com>
# License:: You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'generic'
module URI
#
# The syntax of WS URIs is defined in RFC6455 section 3.
#
# Note that the Ruby URI library allows WS URLs containing usernames and
# passwords. This is not legal as per the RFC, but used to be
# supported in Internet Explorer 5 and 6, before the MS04-004 security
# update. See <URL:http://support.microsoft.com/kb/834489>.
#
class WS < Generic
# A Default port of 80 for URI::WS.
DEFAULT_PORT = 80
# An Array of the available components for URI::WS.
COMPONENT = %i[
scheme
userinfo host port
path
query
].freeze
#
# == Description
#
# Creates a new URI::WS object from components, with syntax checking.
#
# The components accepted are userinfo, host, port, path, and query.
#
# The components should be provided either as an Array, or as a Hash
# with keys formed by preceding the component names with a colon.
#
# If an Array is used, the components must be passed in the
# order <code>[userinfo, host, port, path, query]</code>.
#
# Example:
#
# uri = URI::WS.build(host: 'www.example.com', path: '/foo/bar')
#
# uri = URI::WS.build([nil, "www.example.com", nil, "/path", "query"])
#
# Currently, if passed userinfo components this method generates
# invalid WS URIs as per RFC 1738.
#
def self.build(args)
tmp = Util.make_components_hash(self, args)
super(tmp)
end
#
# == Description
#
# Returns the full path for a WS URI, as required by Net::HTTP::Get.
#
# If the URI contains a query, the full path is URI#path + '?' + URI#query.
# Otherwise, the path is simply URI#path.
#
# Example:
#
# uri = URI::WS.build(path: '/foo/bar', query: 'test=true')
# uri.request_uri # => "/foo/bar?test=true"
#
def request_uri
return unless @path
url = @query ? "#@path?#@query" : @path.dup
url.start_with?(?/.freeze) ? url : ?/ + url
end
end
register_scheme 'WS', WS
end
+23
View File
@@ -0,0 +1,23 @@
# frozen_string_literal: false
# = uri/wss.rb
#
# Author:: Matt Muller <mamuller@amazon.com>
# License:: You can redistribute it and/or modify it under the same term as Ruby.
#
# See URI for general documentation
#
require_relative 'ws'
module URI
# The default port for WSS URIs is 443, and the scheme is 'wss:' rather
# than 'ws:'. Other than that, WSS URIs are identical to WS URIs;
# see URI::WS.
class WSS < WS
# A Default port of 443 for URI::WSS
DEFAULT_PORT = 443
end
register_scheme 'WSS', WSS
end