2004-03-24 14:53:31 +03:00
|
|
|
# = uri/common.rb
|
2002-01-10 11:00:51 +03:00
|
|
|
#
|
2004-03-24 14:53:31 +03:00
|
|
|
# Author:: Akira Yamada <akira@ruby-lang.org>
|
|
|
|
# Revision:: $Id$
|
2009-03-06 06:56:38 +03:00
|
|
|
# License::
|
2004-03-24 14:53:31 +03:00
|
|
|
# You can redistribute it and/or modify it under the same term as Ruby.
|
2002-01-10 11:00:51 +03:00
|
|
|
#
|
|
|
|
|
|
|
|
module URI
|
|
|
|
module REGEXP
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# Patterns used to parse URI's
|
|
|
|
#
|
2002-01-10 11:00:51 +03:00
|
|
|
module PATTERN
|
2004-03-24 14:53:31 +03:00
|
|
|
# :stopdoc:
|
|
|
|
|
2002-01-10 11:00:51 +03:00
|
|
|
# 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
|
2003-03-29 09:39:50 +03:00
|
|
|
UNRESERVED = "-_.!~*'()#{ALNUM}"
|
2002-01-10 11:00:51 +03:00
|
|
|
# reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
|
|
|
|
# "$" | ","
|
2009-03-06 06:56:38 +03:00
|
|
|
# reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
|
2002-01-10 11:00:51 +03:00
|
|
|
# "$" | "," | "[" | "]" (RFC 2732)
|
|
|
|
RESERVED = ";/?:@&=+$,\\[\\]"
|
|
|
|
|
2008-09-10 13:34:49 +04:00
|
|
|
# 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]
|
2009-03-06 06:56:38 +03:00
|
|
|
scheme, opaque, userinfo, host, port,
|
2008-09-10 13:34:49 +04:00
|
|
|
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
|
2009-03-06 06:56:38 +03:00
|
|
|
raise InvalidURIError,
|
2008-09-10 13:34:49 +04:00
|
|
|
"bad URI(absolute but no scheme): #{uri}"
|
|
|
|
end
|
|
|
|
if !opaque && (!path && (!host && !registry))
|
|
|
|
raise InvalidURIError,
|
2009-03-06 06:56:38 +03:00
|
|
|
"bad URI(absolute but no path): #{uri}"
|
2008-09-10 13:34:49 +04:00
|
|
|
end
|
|
|
|
|
|
|
|
when @regexp[:REL_URI]
|
|
|
|
scheme = nil
|
|
|
|
opaque = nil
|
|
|
|
|
2009-03-06 06:56:38 +03:00
|
|
|
userinfo, host, port, registry,
|
2008-09-10 13:34:49 +04:00
|
|
|
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 = [
|
2009-03-06 06:56:38 +03:00
|
|
|
scheme,
|
2008-09-10 13:34:49 +04:00
|
|
|
userinfo, host, port, # X
|
|
|
|
registry, # X
|
|
|
|
path, # Y
|
|
|
|
opaque, # Y
|
|
|
|
query,
|
|
|
|
fragment
|
|
|
|
]
|
|
|
|
return ret
|
|
|
|
end
|
|
|
|
|
|
|
|
def parse(uri)
|
2009-03-06 06:56:38 +03:00
|
|
|
scheme, userinfo, host, port,
|
2008-09-10 13:34:49 +04:00
|
|
|
registry, path, opaque, query, fragment = self.split(uri)
|
|
|
|
|
|
|
|
if scheme && URI.scheme_list.include?(scheme.upcase)
|
2009-03-06 06:56:38 +03:00
|
|
|
URI.scheme_list[scheme.upcase].new(scheme, userinfo, host, port,
|
|
|
|
registry, path, opaque, query,
|
2008-09-10 13:34:49 +04:00
|
|
|
fragment, self)
|
|
|
|
else
|
2009-03-06 06:56:38 +03:00
|
|
|
Generic.new(scheme, userinfo, host, port,
|
|
|
|
registry, path, opaque, query,
|
2008-09-10 13:34:49 +04:00
|
|
|
fragment, self)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2010-07-21 07:32:41 +04:00
|
|
|
def join(*uris)
|
|
|
|
if uris[0].is_a?(URI::Generic)
|
|
|
|
elsif uri = String.try_convert(uris[0])
|
|
|
|
uris[0] = self.parse(uri)
|
|
|
|
else
|
|
|
|
raise ArgumentError,
|
|
|
|
"bad argument(expected URI object or URI string)"
|
2008-09-10 13:34:49 +04:00
|
|
|
end
|
2010-07-21 07:32:41 +04:00
|
|
|
uris.inject :merge
|
2008-09-10 13:34:49 +04:00
|
|
|
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 = $&
|
|
|
|
tmp = ''
|
|
|
|
us.each_byte do |uc|
|
|
|
|
tmp << sprintf('%%%02X', uc)
|
|
|
|
end
|
|
|
|
tmp
|
2009-03-02 13:43:04 +03:00
|
|
|
end.force_encoding(Encoding::US_ASCII)
|
2008-09-10 13:34:49 +04:00
|
|
|
end
|
|
|
|
|
|
|
|
def unescape(str, escaped = @regexp[:ESCAPED])
|
2009-03-02 13:43:04 +03:00
|
|
|
str.gsub(escaped) { [$&[1, 2].hex].pack('C') }.force_encoding(str.encoding)
|
2008-09-10 13:34:49 +04:00
|
|
|
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)
|
|
|
|
|
2002-01-10 11:00:51 +03:00
|
|
|
# uric = reserved | unreserved | escaped
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:URIC] = uric = "(?:[#{unreserved}#{reserved}]|#{escaped})"
|
2002-01-10 11:00:51 +03:00
|
|
|
# uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" |
|
|
|
|
# "&" | "=" | "+" | "$" | ","
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:URIC_NO_SLASH] = uric_no_slash = "(?:[#{unreserved};?:@&=+$,]|#{escaped})"
|
2002-01-10 11:00:51 +03:00
|
|
|
# query = *uric
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:QUERY] = query = "#{uric}*"
|
2002-01-10 11:00:51 +03:00
|
|
|
# fragment = *uric
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:FRAGMENT] = fragment = "#{uric}*"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# hostname = *( domainlabel "." ) toplabel [ "." ]
|
2008-09-10 13:34:49 +04:00
|
|
|
unless hostname
|
|
|
|
ret[:HOSTNAME] = hostname = "(?:#{domlabel}\\.)*#{toplabel}\\.?"
|
|
|
|
end
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# 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
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:IPV4ADDR] = ipv4addr = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"
|
2002-01-10 11:00:51 +03:00
|
|
|
# hex4 = 1*4HEXDIG
|
2008-09-10 13:34:49 +04:00
|
|
|
hex4 = "[#{PATTERN::HEX}]{1,4}"
|
2002-01-10 11:00:51 +03:00
|
|
|
# lastpart = hex4 | IPv4address
|
2008-09-10 13:34:49 +04:00
|
|
|
lastpart = "(?:#{hex4}|#{ipv4addr})"
|
2002-01-10 11:00:51 +03:00
|
|
|
# hexseq1 = *( hex4 ":" ) hex4
|
2008-09-10 13:34:49 +04:00
|
|
|
hexseq1 = "(?:#{hex4}:)*#{hex4}"
|
2002-01-10 11:00:51 +03:00
|
|
|
# hexseq2 = *( hex4 ":" ) lastpart
|
2008-09-10 13:34:49 +04:00
|
|
|
hexseq2 = "(?:#{hex4}:)*#{lastpart}"
|
2002-01-10 11:00:51 +03:00
|
|
|
# IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ]
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:IPV6ADDR] = ipv6addr = "(?:#{hexseq2}|(?:#{hexseq1})?::(?:#{hexseq2})?)"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT
|
|
|
|
# unused
|
|
|
|
|
|
|
|
# ipv6reference = "[" IPv6address "]" (RFC 2732)
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:IPV6REF] = ipv6ref = "\\[#{ipv6addr}\\]"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# host = hostname | IPv4address
|
|
|
|
# host = hostname | IPv4address | IPv6reference (RFC 2732)
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:HOST] = host = "(?:#{hostname}|#{ipv4addr}|#{ipv6ref})"
|
2002-01-10 11:00:51 +03:00
|
|
|
# port = *digit
|
2008-09-10 13:34:49 +04:00
|
|
|
port = '\d*'
|
2002-01-10 11:00:51 +03:00
|
|
|
# hostport = host [ ":" port ]
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:HOSTPORT] = hostport = "#{host}(?::#{port})?"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# userinfo = *( unreserved | escaped |
|
|
|
|
# ";" | ":" | "&" | "=" | "+" | "$" | "," )
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:USERINFO] = userinfo = "(?:[#{unreserved};:&=+$,]|#{escaped})*"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# pchar = unreserved | escaped |
|
|
|
|
# ":" | "@" | "&" | "=" | "+" | "$" | ","
|
2008-09-10 13:34:49 +04:00
|
|
|
pchar = "(?:[#{unreserved}:@&=+$,]|#{escaped})"
|
2002-01-10 11:00:51 +03:00
|
|
|
# param = *pchar
|
2008-09-10 13:34:49 +04:00
|
|
|
param = "#{pchar}*"
|
2002-01-10 11:00:51 +03:00
|
|
|
# segment = *pchar *( ";" param )
|
2008-09-10 13:34:49 +04:00
|
|
|
segment = "#{pchar}*(?:;#{param})*"
|
2002-01-10 11:00:51 +03:00
|
|
|
# path_segments = segment *( "/" segment )
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:PATH_SEGMENTS] = path_segments = "#{segment}(?:/#{segment})*"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# server = [ [ userinfo "@" ] hostport ]
|
2008-09-10 13:34:49 +04:00
|
|
|
server = "(?:#{userinfo}@)?#{hostport}"
|
2002-01-10 11:00:51 +03:00
|
|
|
# reg_name = 1*( unreserved | escaped | "$" | "," |
|
|
|
|
# ";" | ":" | "@" | "&" | "=" | "+" )
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:REG_NAME] = reg_name = "(?:[#{unreserved}$,;:@&=+]|#{escaped})+"
|
2002-01-10 11:00:51 +03:00
|
|
|
# authority = server | reg_name
|
2008-09-10 13:34:49 +04:00
|
|
|
authority = "(?:#{server}|#{reg_name})"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# rel_segment = 1*( unreserved | escaped |
|
|
|
|
# ";" | "@" | "&" | "=" | "+" | "$" | "," )
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:REL_SEGMENT] = rel_segment = "(?:[#{unreserved};@&=+$,]|#{escaped})+"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# scheme = alpha *( alpha | digit | "+" | "-" | "." )
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:SCHEME] = scheme = "[#{PATTERN::ALPHA}][-+.#{PATTERN::ALPHA}\\d]*"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# abs_path = "/" path_segments
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:ABS_PATH] = abs_path = "/#{path_segments}"
|
2002-01-10 11:00:51 +03:00
|
|
|
# rel_path = rel_segment [ abs_path ]
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:REL_PATH] = rel_path = "#{rel_segment}(?:#{abs_path})?"
|
2002-01-10 11:00:51 +03:00
|
|
|
# net_path = "//" authority [ abs_path ]
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:NET_PATH] = net_path = "//#{authority}(?:#{abs_path})?"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# hier_part = ( net_path | abs_path ) [ "?" query ]
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:HIER_PART] = hier_part = "(?:#{net_path}|#{abs_path})(?:\\?(?:#{query}))?"
|
2002-01-10 11:00:51 +03:00
|
|
|
# opaque_part = uric_no_slash *uric
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:OPAQUE_PART] = opaque_part = "#{uric_no_slash}#{uric}*"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# absoluteURI = scheme ":" ( hier_part | opaque_part )
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:ABS_URI] = abs_uri = "#{scheme}:(?:#{hier_part}|#{opaque_part})"
|
2002-01-10 11:00:51 +03:00
|
|
|
# relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:REL_URI] = rel_uri = "(?:#{net_path}|#{abs_path}|#{rel_path})(?:\\?#{query})?"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:URI_REF] = uri_ref = "(?:#{abs_uri}|#{rel_uri})?(?:##{fragment})?"
|
2002-01-10 11:00:51 +03:00
|
|
|
|
2008-09-10 13:34:49 +04:00
|
|
|
ret[:X_ABS_URI] = "
|
|
|
|
(#{scheme}): (?# 1: scheme)
|
2004-03-24 14:53:31 +03:00
|
|
|
(?:
|
2008-09-10 13:34:49 +04:00
|
|
|
(#{opaque_part}) (?# 2: opaque)
|
2004-03-24 14:53:31 +03:00
|
|
|
|
|
|
|
|
(?:(?:
|
|
|
|
//(?:
|
2008-09-10 13:34:49 +04:00
|
|
|
(?:(?:(#{userinfo})@)? (?# 3: userinfo)
|
|
|
|
(?:(#{host})(?::(\\d*))?))? (?# 4: host, 5: port)
|
2004-03-24 14:53:31 +03:00
|
|
|
|
|
2008-09-10 13:34:49 +04:00
|
|
|
(#{reg_name}) (?# 6: registry)
|
2004-03-24 14:53:31 +03:00
|
|
|
)
|
|
|
|
|
|
2008-09-10 13:34:49 +04:00
|
|
|
(?!//)) (?# XXX: '//' is the mark for hostport)
|
|
|
|
(#{abs_path})? (?# 7: path)
|
|
|
|
)(?:\\?(#{query}))? (?# 8: query)
|
2004-03-24 14:53:31 +03:00
|
|
|
)
|
2008-09-10 13:34:49 +04:00
|
|
|
(?:\\#(#{fragment}))? (?# 9: fragment)
|
2002-01-10 11:00:51 +03:00
|
|
|
"
|
2008-09-10 13:34:49 +04:00
|
|
|
|
|
|
|
ret[:X_REL_URI] = "
|
2002-01-10 11:00:51 +03:00
|
|
|
(?:
|
|
|
|
(?:
|
|
|
|
//
|
|
|
|
(?:
|
2008-09-10 13:34:49 +04:00
|
|
|
(?:(#{userinfo})@)? (?# 1: userinfo)
|
|
|
|
(#{host})?(?::(\\d*))? (?# 2: host, 3: port)
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
2008-09-10 13:34:49 +04:00
|
|
|
(#{reg_name}) (?# 4: registry)
|
2002-01-10 11:00:51 +03:00
|
|
|
)
|
|
|
|
)
|
|
|
|
|
|
2008-09-10 13:34:49 +04:00
|
|
|
(#{rel_segment}) (?# 5: rel_segment)
|
2002-01-10 11:00:51 +03:00
|
|
|
)?
|
2008-09-10 13:34:49 +04:00
|
|
|
(#{abs_path})? (?# 6: abs_path)
|
|
|
|
(?:\\?(#{query}))? (?# 7: query)
|
|
|
|
(?:\\#(#{fragment}))? (?# 8: fragment)
|
2002-01-10 11:00:51 +03:00
|
|
|
"
|
|
|
|
|
2008-09-10 13:34:49 +04:00
|
|
|
ret
|
|
|
|
end
|
|
|
|
|
|
|
|
def initialize_regexp(pattern)
|
|
|
|
ret = {}
|
|
|
|
|
|
|
|
# for URI::split
|
2010-01-01 19:00:46 +03:00
|
|
|
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)
|
2008-09-10 13:34:49 +04:00
|
|
|
|
|
|
|
# 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
|
2002-01-10 11:00:51 +03:00
|
|
|
|
2004-07-17 17:14:35 +04:00
|
|
|
module Util # :nodoc:
|
2002-01-10 11:00:51 +03:00
|
|
|
def make_components_hash(klass, array_hash)
|
|
|
|
tmp = {}
|
|
|
|
if array_hash.kind_of?(Array) &&
|
2004-03-24 14:53:31 +03:00
|
|
|
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 11:00:51 +03:00
|
|
|
|
|
|
|
elsif array_hash.kind_of?(Hash)
|
2004-03-24 14:53:31 +03:00
|
|
|
array_hash.each do |key, value|
|
|
|
|
begin
|
|
|
|
tmp[key] = value.clone
|
|
|
|
rescue TypeError
|
|
|
|
tmp[key] = value
|
|
|
|
end
|
|
|
|
end
|
2002-01-10 11:00:51 +03:00
|
|
|
else
|
2009-03-06 06:56:38 +03:00
|
|
|
raise ArgumentError,
|
2004-03-24 14:53:31 +03:00
|
|
|
"expected Array of or Hash of components of #{klass.to_s} (#{klass.component[1..-1].join(', ')})"
|
2002-01-10 11:00:51 +03:00
|
|
|
end
|
|
|
|
tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase
|
|
|
|
|
|
|
|
return tmp
|
|
|
|
end
|
|
|
|
module_function :make_components_hash
|
|
|
|
end
|
|
|
|
|
|
|
|
module Escape
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI.escape(str [, unsafe])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +str+::
|
|
|
|
# String to replaces in.
|
|
|
|
# +unsafe+::
|
|
|
|
# Regexp that matches all symbols that must be replaced with codes.
|
2004-07-17 17:14:35 +04:00
|
|
|
# By default uses <tt>REGEXP::UNSAFE</tt>.
|
2005-11-13 05:02:24 +03:00
|
|
|
# When this argument is a String, it represents a character set.
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Escapes the string, replacing all unsafe characters with codes.
|
|
|
|
#
|
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
2005-06-24 08:18:16 +04:00
|
|
|
# enc_uri = URI.escape("http://example.com/?a=\11\15")
|
2004-03-24 14:53:31 +03:00
|
|
|
# p enc_uri
|
2005-06-24 08:18:16 +04:00
|
|
|
# # => "http://example.com/?a=%09%0D"
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# p URI.unescape(enc_uri)
|
2005-06-24 08:18:16 +04:00
|
|
|
# # => "http://example.com/?a=\t\r"
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
2005-11-13 05:02:24 +03:00
|
|
|
# p URI.escape("@?@!", "!?")
|
|
|
|
# # => "@%3F@%21"
|
|
|
|
#
|
2008-09-10 13:34:49 +04:00
|
|
|
def escape(*arg)
|
2009-09-06 22:24:53 +04:00
|
|
|
warn "#{caller(1)[0]}: warning: URI.escape is obsolete" if $VERBOSE
|
2008-09-10 13:34:49 +04:00
|
|
|
DEFAULT_PARSER.escape(*arg)
|
2002-01-10 11:00:51 +03:00
|
|
|
end
|
|
|
|
alias encode escape
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI.unescape(str)
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +str+::
|
|
|
|
# Unescapes the string.
|
|
|
|
#
|
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
2005-06-24 08:18:16 +04:00
|
|
|
# enc_uri = URI.escape("http://example.com/?a=\11\15")
|
2004-03-24 14:53:31 +03:00
|
|
|
# p enc_uri
|
2005-06-24 08:18:16 +04:00
|
|
|
# # => "http://example.com/?a=%09%0D"
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# p URI.unescape(enc_uri)
|
2005-06-24 08:18:16 +04:00
|
|
|
# # => "http://example.com/?a=\t\r"
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
2008-09-10 13:34:49 +04:00
|
|
|
def unescape(*arg)
|
2009-09-06 22:24:53 +04:00
|
|
|
warn "#{caller(1)[0]}: warning: URI.unescape is obsolete" if $VERBOSE
|
2008-09-10 13:34:49 +04:00
|
|
|
DEFAULT_PARSER.unescape(*arg)
|
2002-01-10 11:00:51 +03:00
|
|
|
end
|
|
|
|
alias decode unescape
|
|
|
|
end
|
|
|
|
|
|
|
|
extend Escape
|
2008-09-10 13:34:49 +04:00
|
|
|
include REGEXP
|
2002-01-10 11:00:51 +03:00
|
|
|
|
|
|
|
@@schemes = {}
|
2008-09-10 13:34:49 +04:00
|
|
|
def self.scheme_list
|
|
|
|
@@schemes
|
|
|
|
end
|
2009-03-06 06:56:38 +03:00
|
|
|
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# Base class for all URI exceptions.
|
|
|
|
#
|
2002-01-10 11:00:51 +03:00
|
|
|
class Error < StandardError; end
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# 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
|
2009-03-06 06:56:38 +03:00
|
|
|
#
|
2004-03-24 14:53:31 +03:00
|
|
|
# == 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 11:00:51 +03:00
|
|
|
def self.split(uri)
|
2008-09-10 13:34:49 +04:00
|
|
|
DEFAULT_PARSER.split(uri)
|
2002-01-10 11:00:51 +03:00
|
|
|
end
|
|
|
|
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::parse(uri_str)
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +uri_str+::
|
|
|
|
# String with URI.
|
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Creates one of the URI's subclasses instance from the string.
|
2009-03-06 06:56:38 +03:00
|
|
|
#
|
2004-03-24 14:53:31 +03:00
|
|
|
# == 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/>
|
2009-03-06 06:56:38 +03:00
|
|
|
# p uri.scheme
|
|
|
|
# # => "http"
|
|
|
|
# p uri.host
|
|
|
|
# # => "www.ruby-lang.org"
|
|
|
|
#
|
2002-01-10 11:00:51 +03:00
|
|
|
def self.parse(uri)
|
2008-09-10 13:34:49 +04:00
|
|
|
DEFAULT_PARSER.parse(uri)
|
2002-01-10 11:00:51 +03:00
|
|
|
end
|
|
|
|
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::join(str[, str, ...])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
|
|
|
# +str+::
|
|
|
|
# String(s) to work with
|
|
|
|
#
|
|
|
|
# == Description
|
|
|
|
#
|
|
|
|
# Joins URIs.
|
|
|
|
#
|
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
2005-06-24 08:18:16 +04:00
|
|
|
# p URI.join("http://localhost/","main.rbx")
|
|
|
|
# # => #<URI::HTTP:0x2022ac02 URL:http://localhost/main.rbx>
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
2002-02-07 07:51:11 +03:00
|
|
|
def self.join(*str)
|
2008-09-10 13:34:49 +04:00
|
|
|
DEFAULT_PARSER.join(*str)
|
2002-02-07 07:51:11 +03:00
|
|
|
end
|
|
|
|
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::extract(str[, schemes][,&blk])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
2009-03-06 06:56:38 +03:00
|
|
|
# +str+::
|
2004-03-24 14:53:31 +03:00
|
|
|
# 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 12:22:44 +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 14:53:31 +03:00
|
|
|
#
|
2003-12-08 07:03:11 +03:00
|
|
|
def self.extract(str, schemes = nil, &block)
|
2008-09-10 13:34:49 +04:00
|
|
|
DEFAULT_PARSER.extract(str, schemes, &block)
|
2003-12-08 07:03:11 +03:00
|
|
|
end
|
2002-01-10 11:00:51 +03:00
|
|
|
|
2004-03-24 14:53:31 +03:00
|
|
|
#
|
|
|
|
# == Synopsis
|
|
|
|
#
|
|
|
|
# URI::regexp([match_schemes])
|
|
|
|
#
|
|
|
|
# == Args
|
|
|
|
#
|
2009-03-06 06:56:38 +03:00
|
|
|
# +match_schemes+::
|
2004-03-24 14:53:31 +03:00
|
|
|
# Array of schemes. If given, resulting regexp matches to URIs
|
|
|
|
# whose scheme is one of the match_schemes.
|
2009-03-06 06:56:38 +03:00
|
|
|
#
|
2004-03-24 14:53:31 +03:00
|
|
|
# == 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.
|
2009-03-06 06:56:38 +03:00
|
|
|
#
|
2004-03-24 14:53:31 +03:00
|
|
|
# == Usage
|
|
|
|
#
|
|
|
|
# require 'uri'
|
|
|
|
#
|
|
|
|
# # extract first URI from html_string
|
|
|
|
# html_string.slice(URI.regexp)
|
2009-03-06 06:56:38 +03:00
|
|
|
#
|
2004-03-24 14:53:31 +03:00
|
|
|
# # remove ftp URIs
|
|
|
|
# html_string.sub(URI.regexp(['ftp'])
|
2009-03-06 06:56:38 +03:00
|
|
|
#
|
2004-03-24 14:53:31 +03:00
|
|
|
# # You should not rely on the number of parentheses
|
|
|
|
# html_string.scan(URI.regexp) do |*matches|
|
|
|
|
# p $&
|
|
|
|
# end
|
|
|
|
#
|
2003-12-08 07:03:11 +03:00
|
|
|
def self.regexp(schemes = nil)
|
2008-09-10 13:34:49 +04:00
|
|
|
DEFAULT_PARSER.make_regexp(schemes)
|
2002-01-10 11:00:51 +03:00
|
|
|
end
|
|
|
|
|
2010-04-11 02:05:02 +04:00
|
|
|
TBLENCWWWCOMP_ = {} # :nodoc:
|
|
|
|
TBLDECWWWCOMP_ = {} # :nodoc:
|
2010-03-21 15:36:14 +03:00
|
|
|
HTML5ASCIIINCOMPAT = [Encoding::UTF_7, Encoding::UTF_16BE, Encoding::UTF_16LE,
|
2010-04-11 02:05:02 +04:00
|
|
|
Encoding::UTF_32BE, Encoding::UTF_32LE] # :nodoc:
|
2010-03-21 15:36:14 +03:00
|
|
|
|
2010-03-12 12:00:48 +03:00
|
|
|
# Encode given +str+ to URL-encoded form data.
|
|
|
|
#
|
|
|
|
# This doesn't convert *, -, ., 0-9, A-Z, _, a-z,
|
|
|
|
# does convert SP to +, and convert others to %XX.
|
|
|
|
#
|
|
|
|
# This refers http://www.w3.org/TR/html5/forms.html#url-encoded-form-data
|
|
|
|
#
|
2010-03-17 18:35:38 +03:00
|
|
|
# See URI.decode_www_form_component, URI.encode_www_form
|
|
|
|
def self.encode_www_form_component(str)
|
2010-03-12 12:00:48 +03:00
|
|
|
if TBLENCWWWCOMP_.empty?
|
|
|
|
256.times do |i|
|
2010-03-21 15:36:14 +03:00
|
|
|
TBLENCWWWCOMP_[i.chr] = '%%%02X' % i
|
2010-03-12 12:00:48 +03:00
|
|
|
end
|
2010-03-21 15:36:14 +03:00
|
|
|
TBLENCWWWCOMP_[' '] = '+'
|
2010-03-12 12:00:48 +03:00
|
|
|
TBLENCWWWCOMP_.freeze
|
|
|
|
end
|
2010-03-17 18:35:38 +03:00
|
|
|
str = str.to_s
|
2010-03-21 15:36:14 +03:00
|
|
|
if HTML5ASCIIINCOMPAT.include?(str.encoding)
|
|
|
|
str = str.encode(Encoding::UTF_8)
|
2010-03-17 18:35:38 +03:00
|
|
|
else
|
2010-03-21 15:36:14 +03:00
|
|
|
str = str.dup
|
2010-03-17 18:35:38 +03:00
|
|
|
end
|
2010-03-21 15:36:14 +03:00
|
|
|
str.force_encoding(Encoding::ASCII_8BIT)
|
|
|
|
str.gsub!(/[^*\-.0-9A-Z_a-z]/, TBLENCWWWCOMP_)
|
2010-03-17 18:35:38 +03:00
|
|
|
str.force_encoding(Encoding::US_ASCII)
|
2010-03-12 12:00:48 +03:00
|
|
|
end
|
|
|
|
|
|
|
|
# Decode given +str+ of URL-encoded form data.
|
|
|
|
#
|
|
|
|
# This decods + to SP.
|
|
|
|
#
|
2010-03-17 18:35:38 +03:00
|
|
|
# See URI.encode_www_form_component, URI.decode_www_form
|
|
|
|
def self.decode_www_form_component(str, enc=Encoding::UTF_8)
|
2010-03-12 12:00:48 +03:00
|
|
|
if TBLDECWWWCOMP_.empty?
|
|
|
|
256.times do |i|
|
2010-03-17 18:35:38 +03:00
|
|
|
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
|
2010-03-12 12:00:48 +03:00
|
|
|
end
|
2010-03-21 15:36:14 +03:00
|
|
|
TBLDECWWWCOMP_['+'] = ' '
|
2010-03-12 12:00:48 +03:00
|
|
|
TBLDECWWWCOMP_.freeze
|
|
|
|
end
|
2010-04-11 02:05:02 +04:00
|
|
|
raise ArgumentError, "invalid %-encoding (#{str})" unless /\A(?:%\h\h|[^%]+)*\z/ =~ str
|
2010-03-21 15:36:14 +03:00
|
|
|
str.gsub(/\+|%\h\h/, TBLDECWWWCOMP_).force_encoding(enc)
|
2010-03-12 12:00:48 +03:00
|
|
|
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 18:35:38 +03:00
|
|
|
# This internally uses URI.encode_www_form_component(str).
|
2010-03-12 12:00:48 +03:00
|
|
|
#
|
|
|
|
# This doesn't convert encodings of give items, so convert them before call
|
|
|
|
# this method if you want to send data as other than original encoding or
|
2010-03-21 15:36:14 +03:00
|
|
|
# mixed encoding data. (strings which is encoded in HTML5 ASCII incompatible
|
|
|
|
# encoding is converted to UTF-8)
|
2010-03-12 12:00:48 +03:00
|
|
|
#
|
|
|
|
# This doesn't treat files. When you send a file, use multipart/form-data.
|
|
|
|
#
|
|
|
|
# This refers http://www.w3.org/TR/html5/forms.html#url-encoded-form-data
|
|
|
|
#
|
2010-03-17 18:35:38 +03:00
|
|
|
# See URI.encode_www_form_component, URI.decode_www_form
|
2010-03-12 12:00:48 +03:00
|
|
|
def self.encode_www_form(enum)
|
|
|
|
str = nil
|
|
|
|
enum.each do |k,v|
|
|
|
|
if str
|
|
|
|
str << '&'
|
|
|
|
else
|
2010-04-11 02:05:02 +04:00
|
|
|
str = nil.to_s
|
2010-03-12 12:00:48 +03:00
|
|
|
end
|
2010-03-17 18:35:38 +03:00
|
|
|
str << encode_www_form_component(k)
|
2010-03-12 12:00:48 +03:00
|
|
|
str << '='
|
2010-03-17 18:35:38 +03:00
|
|
|
str << encode_www_form_component(v)
|
2010-03-12 12:00:48 +03:00
|
|
|
end
|
|
|
|
str
|
|
|
|
end
|
2010-03-17 18:35:38 +03:00
|
|
|
|
2010-04-11 02:05:02 +04:00
|
|
|
WFKV_ = '(?:%\h\h|[^%#=;&]+)' # :nodoc:
|
2010-04-09 15:58:20 +04:00
|
|
|
|
2010-03-17 18:35:38 +03:00
|
|
|
# Decode URL-encoded form data from given +str+.
|
|
|
|
#
|
|
|
|
# This decodes application/x-www-form-urlencoded data
|
|
|
|
# and returns array of key-value array.
|
|
|
|
# This internally uses URI.decode_www_form_component.
|
|
|
|
#
|
|
|
|
# _charset_ hack is not supported now because the mapping from given charset
|
|
|
|
# to Ruby's encoding is not clear yet.
|
|
|
|
# see also http://www.w3.org/TR/html5/syntax.html#character-encodings-0
|
|
|
|
#
|
|
|
|
# This refers http://www.w3.org/TR/html5/forms.html#url-encoded-form-data
|
|
|
|
#
|
|
|
|
# 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"}
|
|
|
|
#
|
|
|
|
# See URI.decode_www_form_component, URI.encode_www_form
|
|
|
|
def self.decode_www_form(str, enc=Encoding::UTF_8)
|
2010-04-11 02:05:02 +04:00
|
|
|
return [] if str.empty?
|
2010-04-09 15:58:20 +04:00
|
|
|
unless /\A#{WFKV_}*=#{WFKV_}*(?:[;&]#{WFKV_}*=#{WFKV_}*)*\z/o =~ str
|
2010-03-17 18:35:38 +03:00
|
|
|
raise ArgumentError, "invalid data of application/x-www-form-urlencoded (#{str})"
|
|
|
|
end
|
2010-04-09 15:58:20 +04:00
|
|
|
ary = []
|
|
|
|
$&.scan(/([^=;&]+)=([^;&]*)/) do
|
2010-03-17 18:35:38 +03:00
|
|
|
ary << [decode_www_form_component($1, enc), decode_www_form_component($2, enc)]
|
|
|
|
end
|
|
|
|
ary
|
|
|
|
end
|
2004-03-24 14:53:31 +03:00
|
|
|
end
|
2004-07-05 18:06:10 +04:00
|
|
|
|
|
|
|
module Kernel
|
2010-07-21 07:32:41 +04:00
|
|
|
|
2004-07-05 18:06:10 +04:00
|
|
|
#
|
2010-07-21 07:32:41 +04:00
|
|
|
# Returns +uri+ converted to a URI object.
|
|
|
|
#
|
|
|
|
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
|
2004-07-05 18:06:10 +04:00
|
|
|
end
|
|
|
|
module_function :URI
|
|
|
|
end
|