1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
ruby--ruby/lib/uri/common.rb
naruse 7aab2aad6e * lib/uri/common.rb (initialize_regexp): allow leading
and trailing white space, and forbid extra characters
  on another lines. [ruby-core:26223]
  RFC 3986  Appendix C.  Delimiting a URI in Context
  draft-duerst-iri-bis-07  7.2.  Web Address processing

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@26229 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2010-01-01 16:00:46 +00:00

729 lines
20 KiB
Ruby

# = uri/common.rb
#
# Author:: Akira Yamada <akira@ruby-lang.org>
# Revision:: $Id$
# License::
# You can redistribute it and/or modify it under the same term as Ruby.
#
module URI
module 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 Parser
include 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 generetes set of regexps for parsing URIs.
#
# You can use the following keys:
#
# * <tt>:ESCAPED</tt> (URI::PATTERN::ESCAPED in default)
# * <tt>:UNRESERVED</tt> (URI::PATTERN::UNRESERVED in default)
# * <tt>:DOMLABEL</tt> (URI::PATTERN::DOMLABEL in default)
# * <tt>:TOPLABEL</tt> (URI::PATTERN::TOPLABEL in default)
# * <tt>:HOSTNAME</tt> (URI::PATTERN::HOSTNAME in default)
#
# == Examples
#
# p = URI::Parser.new(:ESCPAED => "(?:%[a-fA-F0-9]{2}|%u[a-fA-F0-9]{4})"
# u = p.parse("http://example.jp/%uABCD") #=> #<URI::HTTP:0xb78cf4f8 URL:http://example.jp/%uABCD>
# URI.parse(u.to_s) #=> raises URI::InvalidURIError
#
# s = "http://examle.com/ABCD"
# u1 = p.parse(s) #=> #<URI::HTTP:0xb78c3220 URL:http://example.com/ABCD>
# u2 = URI.parse(s) #=> #<URI::HTTP:0xb78b6d54 URL:http://example.com/ABCD>
# u1 == u2 #=> true
# u1.eql?(u2) #=> false
#
def initialize(opts = {})
@pattern = initialize_pattern(opts)
@pattern.each_value {|v| v.freeze}
@pattern.freeze
@regexp = initialize_regexp(@pattern)
@regexp.each_value {|v| v.freeze}
@regexp.freeze
end
attr_reader :pattern, :regexp
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
def parse(uri)
scheme, userinfo, host, port,
registry, path, opaque, query, fragment = self.split(uri)
if scheme && URI.scheme_list.include?(scheme.upcase)
URI.scheme_list[scheme.upcase].new(scheme, userinfo, host, port,
registry, path, opaque, query,
fragment, self)
else
Generic.new(scheme, userinfo, host, port,
registry, path, opaque, query,
fragment, self)
end
end
def join(*str)
u = self.parse(str[0])
str[1 .. -1].each do |x|
u = u.merge(x)
end
u
end
def extract(str, schemes = nil, &block)
if block_given?
str.scan(make_regexp(schemes)) { yield $& }
nil
else
result = []
str.scan(make_regexp(schemes)) { result.push $& }
result
end
end
def make_regexp(schemes = nil)
unless schemes
@regexp[:ABS_URI_REF]
else
/(?=#{Regexp.union(*schemes)}:)#{@pattern[:X_ABS_URI]}/x
end
end
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 = $&
tmp = ''
us.each_byte do |uc|
tmp << sprintf('%%%02X', uc)
end
tmp
end.force_encoding(Encoding::US_ASCII)
end
def unescape(str, escaped = @regexp[:ESCAPED])
str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(str.encoding)
end
@@to_s = Kernel.instance_method(:to_s)
def inspect
@@to_s.bind(self).call
end
private
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] = domlabel = opts.delete(:DOMLABEL) || PATTERN::DOMLABEL
ret[:TOPLABEL] = 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 [ "." ]
unless hostname
ret[:HOSTNAME] = hostname = "(?:#{domlabel}\\.)*#{toplabel}\\.?"
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
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] = 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
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("^#{pattern[:SCHEME]}$")
ret[:USERINFO] = Regexp.new("^#{pattern[:USERINFO]}$")
ret[:HOST] = Regexp.new("^#{pattern[:HOST]}$")
ret[:PORT] = Regexp.new("^#{pattern[:PORT]}$")
ret[:OPAQUE] = Regexp.new("^#{pattern[:OPAQUE_PART]}$")
ret[:REGISTRY] = Regexp.new("^#{pattern[:REG_NAME]}$")
ret[:ABS_PATH] = Regexp.new("^#{pattern[:ABS_PATH]}$")
ret[:REL_PATH] = Regexp.new("^#{pattern[:REL_PATH]}$")
ret[:QUERY] = Regexp.new("^#{pattern[:QUERY]}$")
ret[:FRAGMENT] = Regexp.new("^#{pattern[:FRAGMENT]}$")
ret
end
end # class Parser
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
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.to_s} (#{klass.component[1..-1].join(', ')})"
end
tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase
return tmp
end
module_function :make_components_hash
end
module Escape
#
# == Synopsis
#
# URI.escape(str [, unsafe])
#
# == Args
#
# +str+::
# String to replaces in.
# +unsafe+::
# Regexp that matches all symbols that must be replaced with codes.
# By default uses <tt>REGEXP::UNSAFE</tt>.
# When this argument is a String, it represents a character set.
#
# == Description
#
# Escapes the string, replacing all unsafe characters with codes.
#
# == Usage
#
# require 'uri'
#
# enc_uri = URI.escape("http://example.com/?a=\11\15")
# p enc_uri
# # => "http://example.com/?a=%09%0D"
#
# p URI.unescape(enc_uri)
# # => "http://example.com/?a=\t\r"
#
# p URI.escape("@?@!", "!?")
# # => "@%3F@%21"
#
def escape(*arg)
warn "#{caller(1)[0]}: warning: URI.escape is obsolete" if $VERBOSE
DEFAULT_PARSER.escape(*arg)
end
alias encode escape
#
# == Synopsis
#
# URI.unescape(str)
#
# == Args
#
# +str+::
# Unescapes the string.
#
# == Usage
#
# require 'uri'
#
# enc_uri = URI.escape("http://example.com/?a=\11\15")
# p enc_uri
# # => "http://example.com/?a=%09%0D"
#
# p URI.unescape(enc_uri)
# # => "http://example.com/?a=\t\r"
#
def unescape(*arg)
warn "#{caller(1)[0]}: warning: URI.unescape is obsolete" if $VERBOSE
DEFAULT_PARSER.unescape(*arg)
end
alias decode unescape
end
extend Escape
include REGEXP
@@schemes = {}
def self.scheme_list
@@schemes
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
#
# == 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
#
# == Usage
#
# require 'uri'
#
# p URI.split("http://www.ruby-lang.org/")
# # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil]
#
def self.split(uri)
DEFAULT_PARSER.split(uri)
end
#
# == Synopsis
#
# URI::parse(uri_str)
#
# == Args
#
# +uri_str+::
# String with URI.
#
# == Description
#
# Creates one of the URI's subclasses instance from the string.
#
# == 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/>
# p uri.scheme
# # => "http"
# p uri.host
# # => "www.ruby-lang.org"
#
def self.parse(uri)
DEFAULT_PARSER.parse(uri)
end
#
# == Synopsis
#
# URI::join(str[, str, ...])
#
# == Args
#
# +str+::
# String(s) to work with
#
# == Description
#
# Joins URIs.
#
# == Usage
#
# require 'uri'
#
# p URI.join("http://localhost/","main.rbx")
# # => #<URI::HTTP:0x2022ac02 URL:http://localhost/main.rbx>
#
def self.join(*str)
DEFAULT_PARSER.join(*str)
end
#
# == Synopsis
#
# URI::extract(str[, schemes][,&blk])
#
# == Args
#
# +str+::
# 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"
#
# 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)
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 it's 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)
DEFAULT_PARSER.make_regexp(schemes)
end
end
module Kernel
# alias for URI.parse.
#
# This method is introduced at 1.8.2.
def URI(uri_str) # :doc:
URI.parse(uri_str)
end
module_function :URI
end