summaryrefslogtreecommitdiff
path: root/lib/uri/common.rb
diff options
context:
space:
mode:
authorakira <akira@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2008-09-10 09:34:49 +0000
committerakira <akira@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2008-09-10 09:34:49 +0000
commit3da03397ce1dca2eaf21149dcdc88a212b6afdc2 (patch)
treef0221b0fc3f567ef4e5cc2684f4d1a652f806f53 /lib/uri/common.rb
parent0bedb3e5b1e80b5fdac2086f9b0c54df56f7313b (diff)
* lib/uri/common.rb (URI::Parser): new class.
* lib/uri/mailto.rb, lib/uri/generic.rb: follow the above change. * test/uri/test_parser.rb: added tests for URI::Parser. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19282 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'lib/uri/common.rb')
-rw-r--r--lib/uri/common.rb530
1 files changed, 323 insertions, 207 deletions
diff --git a/lib/uri/common.rb b/lib/uri/common.rb
index f0d68884de..98dda2a350 100644
--- a/lib/uri/common.rb
+++ b/lib/uri/common.rb
@@ -38,22 +38,232 @@ module URI
# "$" | "," | "[" | "]" (RFC 2732)
RESERVED = ";/?:@&=+$,\\[\\]"
+ # 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 = $&
+ tmp = ''
+ us.each_byte do |uc|
+ tmp << sprintf('%%%02X', uc)
+ end
+ tmp
+ end
+ end
+
+ def unescape(str, escaped = @regexp[:ESCAPED])
+ str.gsub(escaped) { [$&.hex].pack('U') }
+ 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
- URIC = "(?:[#{UNRESERVED}#{RESERVED}]|#{ESCAPED})"
+ ret[:URIC] = uric = "(?:[#{unreserved}#{reserved}]|#{escaped})"
# uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" |
# "&" | "=" | "+" | "$" | ","
- URIC_NO_SLASH = "(?:[#{UNRESERVED};?:@&=+$,]|#{ESCAPED})"
+ ret[:URIC_NO_SLASH] = uric_no_slash = "(?:[#{unreserved};?:@&=+$,]|#{escaped})"
# query = *uric
- QUERY = "#{URIC}*"
+ ret[:QUERY] = query = "#{uric}*"
# fragment = *uric
- FRAGMENT = "#{URIC}*"
+ ret[:FRAGMENT] = fragment = "#{uric}*"
- # domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
- DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
- # toplabel = alpha | alpha *( alphanum | "-" ) alphanum
- TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
# hostname = *( domainlabel "." ) toplabel [ "." ]
- HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?"
+ unless hostname
+ ret[:HOSTNAME] = hostname = "(?:#{domlabel}\\.)*#{toplabel}\\.?"
+ end
# RFC 2373, APPENDIX B:
# IPv6address = hexpart [ ":" IPv4address ]
@@ -66,152 +276,164 @@ module URI
# allowed too. Here is a replacement.
#
# IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
- IPV4ADDR = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"
+ ret[:IPV4ADDR] = ipv4addr = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"
# hex4 = 1*4HEXDIG
- HEX4 = "[#{HEX}]{1,4}"
+ hex4 = "[#{PATTERN::HEX}]{1,4}"
# lastpart = hex4 | IPv4address
- LASTPART = "(?:#{HEX4}|#{IPV4ADDR})"
+ lastpart = "(?:#{hex4}|#{ipv4addr})"
# hexseq1 = *( hex4 ":" ) hex4
- HEXSEQ1 = "(?:#{HEX4}:)*#{HEX4}"
+ hexseq1 = "(?:#{hex4}:)*#{hex4}"
# hexseq2 = *( hex4 ":" ) lastpart
- HEXSEQ2 = "(?:#{HEX4}:)*#{LASTPART}"
+ hexseq2 = "(?:#{hex4}:)*#{lastpart}"
# IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ]
- IPV6ADDR = "(?:#{HEXSEQ2}|(?:#{HEXSEQ1})?::(?:#{HEXSEQ2})?)"
+ ret[:IPV6ADDR] = ipv6addr = "(?:#{hexseq2}|(?:#{hexseq1})?::(?:#{hexseq2})?)"
# IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT
# unused
# ipv6reference = "[" IPv6address "]" (RFC 2732)
- IPV6REF = "\\[#{IPV6ADDR}\\]"
+ ret[:IPV6REF] = ipv6ref = "\\[#{ipv6addr}\\]"
# host = hostname | IPv4address
# host = hostname | IPv4address | IPv6reference (RFC 2732)
- HOST = "(?:#{HOSTNAME}|#{IPV4ADDR}|#{IPV6REF})"
+ ret[:HOST] = host = "(?:#{hostname}|#{ipv4addr}|#{ipv6ref})"
# port = *digit
- PORT = '\d*'
+ port = '\d*'
# hostport = host [ ":" port ]
- HOSTPORT = "#{HOST}(?::#{PORT})?"
+ ret[:HOSTPORT] = hostport = "#{host}(?::#{port})?"
# userinfo = *( unreserved | escaped |
# ";" | ":" | "&" | "=" | "+" | "$" | "," )
- USERINFO = "(?:[#{UNRESERVED};:&=+$,]|#{ESCAPED})*"
+ ret[:USERINFO] = userinfo = "(?:[#{unreserved};:&=+$,]|#{escaped})*"
# pchar = unreserved | escaped |
# ":" | "@" | "&" | "=" | "+" | "$" | ","
- PCHAR = "(?:[#{UNRESERVED}:@&=+$,]|#{ESCAPED})"
+ pchar = "(?:[#{unreserved}:@&=+$,]|#{escaped})"
# param = *pchar
- PARAM = "#{PCHAR}*"
+ param = "#{pchar}*"
# segment = *pchar *( ";" param )
- SEGMENT = "#{PCHAR}*(?:;#{PARAM})*"
+ segment = "#{pchar}*(?:;#{param})*"
# path_segments = segment *( "/" segment )
- PATH_SEGMENTS = "#{SEGMENT}(?:/#{SEGMENT})*"
+ ret[:PATH_SEGMENTS] = path_segments = "#{segment}(?:/#{segment})*"
# server = [ [ userinfo "@" ] hostport ]
- SERVER = "(?:#{USERINFO}@)?#{HOSTPORT}"
+ server = "(?:#{userinfo}@)?#{hostport}"
# reg_name = 1*( unreserved | escaped | "$" | "," |
# ";" | ":" | "@" | "&" | "=" | "+" )
- REG_NAME = "(?:[#{UNRESERVED}$,;:@&=+]|#{ESCAPED})+"
+ ret[:REG_NAME] = reg_name = "(?:[#{unreserved}$,;:@&=+]|#{escaped})+"
# authority = server | reg_name
- AUTHORITY = "(?:#{SERVER}|#{REG_NAME})"
+ authority = "(?:#{server}|#{reg_name})"
# rel_segment = 1*( unreserved | escaped |
# ";" | "@" | "&" | "=" | "+" | "$" | "," )
- REL_SEGMENT = "(?:[#{UNRESERVED};@&=+$,]|#{ESCAPED})+"
+ ret[:REL_SEGMENT] = rel_segment = "(?:[#{unreserved};@&=+$,]|#{escaped})+"
# scheme = alpha *( alpha | digit | "+" | "-" | "." )
- SCHEME = "[#{ALPHA}][-+.#{ALPHA}\\d]*"
+ ret[:SCHEME] = scheme = "[#{PATTERN::ALPHA}][-+.#{PATTERN::ALPHA}\\d]*"
# abs_path = "/" path_segments
- ABS_PATH = "/#{PATH_SEGMENTS}"
+ ret[:ABS_PATH] = abs_path = "/#{path_segments}"
# rel_path = rel_segment [ abs_path ]
- REL_PATH = "#{REL_SEGMENT}(?:#{ABS_PATH})?"
+ ret[:REL_PATH] = rel_path = "#{rel_segment}(?:#{abs_path})?"
# net_path = "//" authority [ abs_path ]
- NET_PATH = "//#{AUTHORITY}(?:#{ABS_PATH})?"
+ ret[:NET_PATH] = net_path = "//#{authority}(?:#{abs_path})?"
# hier_part = ( net_path | abs_path ) [ "?" query ]
- HIER_PART = "(?:#{NET_PATH}|#{ABS_PATH})(?:\\?(?:#{QUERY}))?"
+ ret[:HIER_PART] = hier_part = "(?:#{net_path}|#{abs_path})(?:\\?(?:#{query}))?"
# opaque_part = uric_no_slash *uric
- OPAQUE_PART = "#{URIC_NO_SLASH}#{URIC}*"
+ ret[:OPAQUE_PART] = opaque_part = "#{uric_no_slash}#{uric}*"
# absoluteURI = scheme ":" ( hier_part | opaque_part )
- ABS_URI = "#{SCHEME}:(?:#{HIER_PART}|#{OPAQUE_PART})"
+ ret[:ABS_URI] = abs_uri = "#{scheme}:(?:#{hier_part}|#{opaque_part})"
# relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
- REL_URI = "(?:#{NET_PATH}|#{ABS_PATH}|#{REL_PATH})(?:\\?#{QUERY})?"
+ ret[:REL_URI] = rel_uri = "(?:#{net_path}|#{abs_path}|#{rel_path})(?:\\?#{query})?"
# URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
- URI_REF = "(?:#{ABS_URI}|#{REL_URI})?(?:##{FRAGMENT})?"
+ ret[:URI_REF] = uri_ref = "(?:#{abs_uri}|#{rel_uri})?(?:##{fragment})?"
- # XXX:
- X_ABS_URI = "
- (#{PATTERN::SCHEME}): (?# 1: scheme)
+ ret[:X_ABS_URI] = "
+ (#{scheme}): (?# 1: scheme)
(?:
- (#{PATTERN::OPAQUE_PART}) (?# 2: opaque)
+ (#{opaque_part}) (?# 2: opaque)
|
(?:(?:
//(?:
- (?:(?:(#{PATTERN::USERINFO})@)? (?# 3: userinfo)
- (?:(#{PATTERN::HOST})(?::(\\d*))?))?(?# 4: host, 5: port)
+ (?:(?:(#{userinfo})@)? (?# 3: userinfo)
+ (?:(#{host})(?::(\\d*))?))? (?# 4: host, 5: port)
|
- (#{PATTERN::REG_NAME}) (?# 6: registry)
+ (#{reg_name}) (?# 6: registry)
)
|
- (?!//)) (?# XXX: '//' is the mark for hostport)
- (#{PATTERN::ABS_PATH})? (?# 7: path)
- )(?:\\?(#{PATTERN::QUERY}))? (?# 8: query)
+ (?!//)) (?# XXX: '//' is the mark for hostport)
+ (#{abs_path})? (?# 7: path)
+ )(?:\\?(#{query}))? (?# 8: query)
)
- (?:\\#(#{PATTERN::FRAGMENT}))? (?# 9: fragment)
+ (?:\\#(#{fragment}))? (?# 9: fragment)
"
- X_REL_URI = "
+
+ ret[:X_REL_URI] = "
(?:
(?:
//
(?:
- (?:(#{PATTERN::USERINFO})@)? (?# 1: userinfo)
- (#{PATTERN::HOST})?(?::(\\d*))? (?# 2: host, 3: port)
+ (?:(#{userinfo})@)? (?# 1: userinfo)
+ (#{host})?(?::(\\d*))? (?# 2: host, 3: port)
|
- (#{PATTERN::REG_NAME}) (?# 4: registry)
+ (#{reg_name}) (?# 4: registry)
)
)
|
- (#{PATTERN::REL_SEGMENT}) (?# 5: rel_segment)
+ (#{rel_segment}) (?# 5: rel_segment)
)?
- (#{PATTERN::ABS_PATH})? (?# 6: abs_path)
- (?:\\?(#{PATTERN::QUERY}))? (?# 7: query)
- (?:\\#(#{PATTERN::FRAGMENT}))? (?# 8: fragment)
+ (#{abs_path})? (?# 6: abs_path)
+ (?:\\?(#{query}))? (?# 7: query)
+ (?:\\#(#{fragment}))? (?# 8: fragment)
"
- # :startdoc:
- end # PATTERN
- # :stopdoc:
-
- # for URI::split
- ABS_URI = Regexp.new('^' + PATTERN::X_ABS_URI + '$', #'
- Regexp::EXTENDED).freeze
- REL_URI = Regexp.new('^' + PATTERN::X_REL_URI + '$', #'
- Regexp::EXTENDED).freeze
-
- # for URI::extract
- URI_REF = Regexp.new(PATTERN::URI_REF).freeze
- ABS_URI_REF = Regexp.new(PATTERN::X_ABS_URI, Regexp::EXTENDED).freeze
- REL_URI_REF = Regexp.new(PATTERN::X_REL_URI, Regexp::EXTENDED).freeze
-
- # for URI::escape/unescape
- ESCAPED = Regexp.new(PATTERN::ESCAPED).freeze
- UNSAFE = Regexp.new("[^#{PATTERN::UNRESERVED}#{PATTERN::RESERVED}]").freeze
-
- # for Generic#initialize
- SCHEME = Regexp.new("^#{PATTERN::SCHEME}$").freeze #"
- USERINFO = Regexp.new("^#{PATTERN::USERINFO}$").freeze #"
- HOST = Regexp.new("^#{PATTERN::HOST}$").freeze #"
- PORT = Regexp.new("^#{PATTERN::PORT}$").freeze #"
- OPAQUE = Regexp.new("^#{PATTERN::OPAQUE_PART}$").freeze #"
- REGISTRY = Regexp.new("^#{PATTERN::REG_NAME}$").freeze #"
- ABS_PATH = Regexp.new("^#{PATTERN::ABS_PATH}$").freeze #"
- REL_PATH = Regexp.new("^#{PATTERN::REL_PATH}$").freeze #"
- QUERY = Regexp.new("^#{PATTERN::QUERY}$").freeze #"
- FRAGMENT = Regexp.new("^#{PATTERN::FRAGMENT}$").freeze #"
- # :startdoc:
- end # REGEXP
+ ret
+ end
+
+ def initialize_regexp(pattern)
+ ret = {}
+
+ # for URI::split
+ ret[:ABS_URI] = Regexp.new('^' + pattern[:X_ABS_URI] + '$', Regexp::EXTENDED)
+ ret[:REL_URI] = Regexp.new('^' + pattern[:X_REL_URI] + '$', Regexp::EXTENDED)
+
+ # for URI::extract
+ ret[:URI_REF] = Regexp.new(pattern[:URI_REF])
+ ret[:ABS_URI_REF] = Regexp.new(pattern[:X_ABS_URI], Regexp::EXTENDED)
+ ret[:REL_URI_REF] = Regexp.new(pattern[:X_REL_URI], Regexp::EXTENDED)
+
+ # for URI::escape/unescape
+ ret[:ESCAPED] = Regexp.new(pattern[:ESCAPED])
+ ret[:UNSAFE] = Regexp.new("[^#{pattern[:UNRESERVED]}#{pattern[:RESERVED]}]")
+
+ # for Generic#initialize
+ ret[:SCHEME] = Regexp.new("^#{pattern[:SCHEME]}$")
+ 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)
@@ -246,8 +468,6 @@ module URI
end
module Escape
- include REGEXP
-
#
# == Synopsis
#
@@ -280,19 +500,8 @@ module URI
# p URI.escape("@?@!", "!?")
# # => "@%3F@%21"
#
- def escape(str, unsafe = UNSAFE)
- unless unsafe.kind_of?(Regexp)
- # perhaps unsafe is String object
- unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false, 'N')
- end
- str.gsub(unsafe) do
- us = $&
- tmp = ''
- us.each_byte do |uc|
- tmp << sprintf('%%%02X', uc)
- end
- tmp
- end
+ def escape(*arg)
+ DEFAULT_PARSER.escape(*arg)
end
alias encode escape
#
@@ -316,18 +525,19 @@ module URI
# p URI.unescape(enc_uri)
# # => "http://example.com/?a=\t\r"
#
- def unescape(str)
- str.gsub(ESCAPED) do
- $&[1,2].hex.chr
- end
+ def unescape(*arg)
+ DEFAULT_PARSER.unescape(*arg)
end
alias decode unescape
end
- include REGEXP
extend Escape
+ include REGEXP
@@schemes = {}
+ def self.scheme_list
+ @@schemes
+ end
#
# Base class for all URI exceptions.
@@ -378,75 +588,7 @@ module URI
# # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil]
#
def self.split(uri)
- case uri
- when ''
- # null uri
-
- when 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 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
+ DEFAULT_PARSER.split(uri)
end
#
@@ -481,18 +623,7 @@ module URI
# # => "www.ruby-lang.org"
#
def self.parse(uri)
- scheme, userinfo, host, port,
- registry, path, opaque, query, fragment = self.split(uri)
-
- if scheme && @@schemes.include?(scheme.upcase)
- @@schemes[scheme.upcase].new(scheme, userinfo, host, port,
- registry, path, opaque, query,
- fragment)
- else
- Generic.new(scheme, userinfo, host, port,
- registry, path, opaque, query,
- fragment)
- end
+ DEFAULT_PARSER.parse(uri)
end
#
@@ -517,11 +648,7 @@ module URI
# # => #<URI::HTTP:0x2022ac02 URL:http://localhost/main.rbx>
#
def self.join(*str)
- u = self.parse(str[0])
- str[1 .. -1].each do |x|
- u = u.merge(x)
- end
- u
+ DEFAULT_PARSER.join(*str)
end
#
@@ -549,14 +676,7 @@ module URI
# # => ["http://foo.example.com/bla", "mailto:test@example.com"]
#
def self.extract(str, schemes = nil, &block)
- if block_given?
- str.scan(regexp(schemes)) { yield $& }
- nil
- else
- result = []
- str.scan(regexp(schemes)) { result.push $& }
- result
- end
+ DEFAULT_PARSER.extract(str, schemes, &block)
end
#
@@ -591,11 +711,7 @@ module URI
# end
#
def self.regexp(schemes = nil)
- unless schemes
- ABS_URI_REF
- else
- /(?=#{Regexp.union(*schemes)}:)#{PATTERN::X_ABS_URI}/xn
- end
+ DEFAULT_PARSER.make_regexp(schemes)
end
end