| 1 | # = uri/common.rb
|
|---|
| 2 | #
|
|---|
| 3 | # Author:: Akira Yamada <[email protected]>
|
|---|
| 4 | # Revision:: $Id: common.rb 11747 2007-02-15 02:41:45Z knu $
|
|---|
| 5 | # License::
|
|---|
| 6 | # You can redistribute it and/or modify it under the same term as Ruby.
|
|---|
| 7 | #
|
|---|
| 8 |
|
|---|
| 9 | module URI
|
|---|
| 10 | module REGEXP
|
|---|
| 11 | #
|
|---|
| 12 | # Patterns used to parse URI's
|
|---|
| 13 | #
|
|---|
| 14 | module PATTERN
|
|---|
| 15 | # :stopdoc:
|
|---|
| 16 |
|
|---|
| 17 | # RFC 2396 (URI Generic Syntax)
|
|---|
| 18 | # RFC 2732 (IPv6 Literal Addresses in URL's)
|
|---|
| 19 | # RFC 2373 (IPv6 Addressing Architecture)
|
|---|
| 20 |
|
|---|
| 21 | # alpha = lowalpha | upalpha
|
|---|
| 22 | ALPHA = "a-zA-Z"
|
|---|
| 23 | # alphanum = alpha | digit
|
|---|
| 24 | ALNUM = "#{ALPHA}\\d"
|
|---|
| 25 |
|
|---|
| 26 | # hex = digit | "A" | "B" | "C" | "D" | "E" | "F" |
|
|---|
| 27 | # "a" | "b" | "c" | "d" | "e" | "f"
|
|---|
| 28 | HEX = "a-fA-F\\d"
|
|---|
| 29 | # escaped = "%" hex hex
|
|---|
| 30 | ESCAPED = "%[#{HEX}]{2}"
|
|---|
| 31 | # mark = "-" | "_" | "." | "!" | "~" | "*" | "'" |
|
|---|
| 32 | # "(" | ")"
|
|---|
| 33 | # unreserved = alphanum | mark
|
|---|
| 34 | UNRESERVED = "-_.!~*'()#{ALNUM}"
|
|---|
| 35 | # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
|
|---|
| 36 | # "$" | ","
|
|---|
| 37 | # reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
|
|---|
| 38 | # "$" | "," | "[" | "]" (RFC 2732)
|
|---|
| 39 | RESERVED = ";/?:@&=+$,\\[\\]"
|
|---|
| 40 |
|
|---|
| 41 | # uric = reserved | unreserved | escaped
|
|---|
| 42 | URIC = "(?:[#{UNRESERVED}#{RESERVED}]|#{ESCAPED})"
|
|---|
| 43 | # uric_no_slash = unreserved | escaped | ";" | "?" | ":" | "@" |
|
|---|
| 44 | # "&" | "=" | "+" | "$" | ","
|
|---|
| 45 | URIC_NO_SLASH = "(?:[#{UNRESERVED};?:@&=+$,]|#{ESCAPED})"
|
|---|
| 46 | # query = *uric
|
|---|
| 47 | QUERY = "#{URIC}*"
|
|---|
| 48 | # fragment = *uric
|
|---|
| 49 | FRAGMENT = "#{URIC}*"
|
|---|
| 50 |
|
|---|
| 51 | # domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
|
|---|
| 52 | DOMLABEL = "(?:[#{ALNUM}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
|
|---|
| 53 | # toplabel = alpha | alpha *( alphanum | "-" ) alphanum
|
|---|
| 54 | TOPLABEL = "(?:[#{ALPHA}](?:[-#{ALNUM}]*[#{ALNUM}])?)"
|
|---|
| 55 | # hostname = *( domainlabel "." ) toplabel [ "." ]
|
|---|
| 56 | HOSTNAME = "(?:#{DOMLABEL}\\.)*#{TOPLABEL}\\.?"
|
|---|
| 57 |
|
|---|
| 58 | # RFC 2373, APPENDIX B:
|
|---|
| 59 | # IPv6address = hexpart [ ":" IPv4address ]
|
|---|
| 60 | # IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
|
|---|
| 61 | # hexpart = hexseq | hexseq "::" [ hexseq ] | "::" [ hexseq ]
|
|---|
| 62 | # hexseq = hex4 *( ":" hex4)
|
|---|
| 63 | # hex4 = 1*4HEXDIG
|
|---|
| 64 | #
|
|---|
| 65 | # XXX: This definition has a flaw. "::" + IPv4address must be
|
|---|
| 66 | # allowed too. Here is a replacement.
|
|---|
| 67 | #
|
|---|
| 68 | # IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
|
|---|
| 69 | IPV4ADDR = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}"
|
|---|
| 70 | # hex4 = 1*4HEXDIG
|
|---|
| 71 | HEX4 = "[#{HEX}]{1,4}"
|
|---|
| 72 | # lastpart = hex4 | IPv4address
|
|---|
| 73 | LASTPART = "(?:#{HEX4}|#{IPV4ADDR})"
|
|---|
| 74 | # hexseq1 = *( hex4 ":" ) hex4
|
|---|
| 75 | HEXSEQ1 = "(?:#{HEX4}:)*#{HEX4}"
|
|---|
| 76 | # hexseq2 = *( hex4 ":" ) lastpart
|
|---|
| 77 | HEXSEQ2 = "(?:#{HEX4}:)*#{LASTPART}"
|
|---|
| 78 | # IPv6address = hexseq2 | [ hexseq1 ] "::" [ hexseq2 ]
|
|---|
| 79 | IPV6ADDR = "(?:#{HEXSEQ2}|(?:#{HEXSEQ1})?::(?:#{HEXSEQ2})?)"
|
|---|
| 80 |
|
|---|
| 81 | # IPv6prefix = ( hexseq1 | [ hexseq1 ] "::" [ hexseq1 ] ) "/" 1*2DIGIT
|
|---|
| 82 | # unused
|
|---|
| 83 |
|
|---|
| 84 | # ipv6reference = "[" IPv6address "]" (RFC 2732)
|
|---|
| 85 | IPV6REF = "\\[#{IPV6ADDR}\\]"
|
|---|
| 86 |
|
|---|
| 87 | # host = hostname | IPv4address
|
|---|
| 88 | # host = hostname | IPv4address | IPv6reference (RFC 2732)
|
|---|
| 89 | HOST = "(?:#{HOSTNAME}|#{IPV4ADDR}|#{IPV6REF})"
|
|---|
| 90 | # port = *digit
|
|---|
| 91 | PORT = '\d*'
|
|---|
| 92 | # hostport = host [ ":" port ]
|
|---|
| 93 | HOSTPORT = "#{HOST}(?::#{PORT})?"
|
|---|
| 94 |
|
|---|
| 95 | # userinfo = *( unreserved | escaped |
|
|---|
| 96 | # ";" | ":" | "&" | "=" | "+" | "$" | "," )
|
|---|
| 97 | USERINFO = "(?:[#{UNRESERVED};:&=+$,]|#{ESCAPED})*"
|
|---|
| 98 |
|
|---|
| 99 | # pchar = unreserved | escaped |
|
|---|
| 100 | # ":" | "@" | "&" | "=" | "+" | "$" | ","
|
|---|
| 101 | PCHAR = "(?:[#{UNRESERVED}:@&=+$,]|#{ESCAPED})"
|
|---|
| 102 | # param = *pchar
|
|---|
| 103 | PARAM = "#{PCHAR}*"
|
|---|
| 104 | # segment = *pchar *( ";" param )
|
|---|
| 105 | SEGMENT = "#{PCHAR}*(?:;#{PARAM})*"
|
|---|
| 106 | # path_segments = segment *( "/" segment )
|
|---|
| 107 | PATH_SEGMENTS = "#{SEGMENT}(?:/#{SEGMENT})*"
|
|---|
| 108 |
|
|---|
| 109 | # server = [ [ userinfo "@" ] hostport ]
|
|---|
| 110 | SERVER = "(?:#{USERINFO}@)?#{HOSTPORT}"
|
|---|
| 111 | # reg_name = 1*( unreserved | escaped | "$" | "," |
|
|---|
| 112 | # ";" | ":" | "@" | "&" | "=" | "+" )
|
|---|
| 113 | REG_NAME = "(?:[#{UNRESERVED}$,;+@&=+]|#{ESCAPED})+"
|
|---|
| 114 | # authority = server | reg_name
|
|---|
| 115 | AUTHORITY = "(?:#{SERVER}|#{REG_NAME})"
|
|---|
| 116 |
|
|---|
| 117 | # rel_segment = 1*( unreserved | escaped |
|
|---|
| 118 | # ";" | "@" | "&" | "=" | "+" | "$" | "," )
|
|---|
| 119 | REL_SEGMENT = "(?:[#{UNRESERVED};@&=+$,]|#{ESCAPED})+"
|
|---|
| 120 |
|
|---|
| 121 | # scheme = alpha *( alpha | digit | "+" | "-" | "." )
|
|---|
| 122 | SCHEME = "[#{ALPHA}][-+.#{ALPHA}\\d]*"
|
|---|
| 123 |
|
|---|
| 124 | # abs_path = "/" path_segments
|
|---|
| 125 | ABS_PATH = "/#{PATH_SEGMENTS}"
|
|---|
| 126 | # rel_path = rel_segment [ abs_path ]
|
|---|
| 127 | REL_PATH = "#{REL_SEGMENT}(?:#{ABS_PATH})?"
|
|---|
| 128 | # net_path = "//" authority [ abs_path ]
|
|---|
| 129 | NET_PATH = "//#{AUTHORITY}(?:#{ABS_PATH})?"
|
|---|
| 130 |
|
|---|
| 131 | # hier_part = ( net_path | abs_path ) [ "?" query ]
|
|---|
| 132 | HIER_PART = "(?:#{NET_PATH}|#{ABS_PATH})(?:\\?(?:#{QUERY}))?"
|
|---|
| 133 | # opaque_part = uric_no_slash *uric
|
|---|
| 134 | OPAQUE_PART = "#{URIC_NO_SLASH}#{URIC}*"
|
|---|
| 135 |
|
|---|
| 136 | # absoluteURI = scheme ":" ( hier_part | opaque_part )
|
|---|
| 137 | ABS_URI = "#{SCHEME}:(?:#{HIER_PART}|#{OPAQUE_PART})"
|
|---|
| 138 | # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
|
|---|
| 139 | REL_URI = "(?:#{NET_PATH}|#{ABS_PATH}|#{REL_PATH})(?:\\?#{QUERY})?"
|
|---|
| 140 |
|
|---|
| 141 | # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
|
|---|
| 142 | URI_REF = "(?:#{ABS_URI}|#{REL_URI})?(?:##{FRAGMENT})?"
|
|---|
| 143 |
|
|---|
| 144 | # XXX:
|
|---|
| 145 | X_ABS_URI = "
|
|---|
| 146 | (#{PATTERN::SCHEME}): (?# 1: scheme)
|
|---|
| 147 | (?:
|
|---|
| 148 | (#{PATTERN::OPAQUE_PART}) (?# 2: opaque)
|
|---|
| 149 | |
|
|---|
| 150 | (?:(?:
|
|---|
| 151 | //(?:
|
|---|
| 152 | (?:(?:(#{PATTERN::USERINFO})@)? (?# 3: userinfo)
|
|---|
| 153 | (?:(#{PATTERN::HOST})(?::(\\d*))?))?(?# 4: host, 5: port)
|
|---|
| 154 | |
|
|---|
| 155 | (#{PATTERN::REG_NAME}) (?# 6: registry)
|
|---|
| 156 | )
|
|---|
| 157 | |
|
|---|
| 158 | (?!//)) (?# XXX: '//' is the mark for hostport)
|
|---|
| 159 | (#{PATTERN::ABS_PATH})? (?# 7: path)
|
|---|
| 160 | )(?:\\?(#{PATTERN::QUERY}))? (?# 8: query)
|
|---|
| 161 | )
|
|---|
| 162 | (?:\\#(#{PATTERN::FRAGMENT}))? (?# 9: fragment)
|
|---|
| 163 | "
|
|---|
| 164 | X_REL_URI = "
|
|---|
| 165 | (?:
|
|---|
| 166 | (?:
|
|---|
| 167 | //
|
|---|
| 168 | (?:
|
|---|
| 169 | (?:(#{PATTERN::USERINFO})@)? (?# 1: userinfo)
|
|---|
| 170 | (#{PATTERN::HOST})?(?::(\\d*))? (?# 2: host, 3: port)
|
|---|
| 171 | |
|
|---|
| 172 | (#{PATTERN::REG_NAME}) (?# 4: registry)
|
|---|
| 173 | )
|
|---|
| 174 | )
|
|---|
| 175 | |
|
|---|
| 176 | (#{PATTERN::REL_SEGMENT}) (?# 5: rel_segment)
|
|---|
| 177 | )?
|
|---|
| 178 | (#{PATTERN::ABS_PATH})? (?# 6: abs_path)
|
|---|
| 179 | (?:\\?(#{PATTERN::QUERY}))? (?# 7: query)
|
|---|
| 180 | (?:\\#(#{PATTERN::FRAGMENT}))? (?# 8: fragment)
|
|---|
| 181 | "
|
|---|
| 182 | # :startdoc:
|
|---|
| 183 | end # PATTERN
|
|---|
| 184 |
|
|---|
| 185 | # :stopdoc:
|
|---|
| 186 |
|
|---|
| 187 | # for URI::split
|
|---|
| 188 | ABS_URI = Regexp.new('^' + PATTERN::X_ABS_URI + '$', #'
|
|---|
| 189 | Regexp::EXTENDED, 'N').freeze
|
|---|
| 190 | REL_URI = Regexp.new('^' + PATTERN::X_REL_URI + '$', #'
|
|---|
| 191 | Regexp::EXTENDED, 'N').freeze
|
|---|
| 192 |
|
|---|
| 193 | # for URI::extract
|
|---|
| 194 | URI_REF = Regexp.new(PATTERN::URI_REF, false, 'N').freeze
|
|---|
| 195 | ABS_URI_REF = Regexp.new(PATTERN::X_ABS_URI, Regexp::EXTENDED, 'N').freeze
|
|---|
| 196 | REL_URI_REF = Regexp.new(PATTERN::X_REL_URI, Regexp::EXTENDED, 'N').freeze
|
|---|
| 197 |
|
|---|
| 198 | # for URI::escape/unescape
|
|---|
| 199 | ESCAPED = Regexp.new(PATTERN::ESCAPED, false, 'N').freeze
|
|---|
| 200 | UNSAFE = Regexp.new("[^#{PATTERN::UNRESERVED}#{PATTERN::RESERVED}]",
|
|---|
| 201 | false, 'N').freeze
|
|---|
| 202 |
|
|---|
| 203 | # for Generic#initialize
|
|---|
| 204 | SCHEME = Regexp.new("^#{PATTERN::SCHEME}$", false, 'N').freeze #"
|
|---|
| 205 | USERINFO = Regexp.new("^#{PATTERN::USERINFO}$", false, 'N').freeze #"
|
|---|
| 206 | HOST = Regexp.new("^#{PATTERN::HOST}$", false, 'N').freeze #"
|
|---|
| 207 | PORT = Regexp.new("^#{PATTERN::PORT}$", false, 'N').freeze #"
|
|---|
| 208 | OPAQUE = Regexp.new("^#{PATTERN::OPAQUE_PART}$", false, 'N').freeze #"
|
|---|
| 209 | REGISTRY = Regexp.new("^#{PATTERN::REG_NAME}$", false, 'N').freeze #"
|
|---|
| 210 | ABS_PATH = Regexp.new("^#{PATTERN::ABS_PATH}$", false, 'N').freeze #"
|
|---|
| 211 | REL_PATH = Regexp.new("^#{PATTERN::REL_PATH}$", false, 'N').freeze #"
|
|---|
| 212 | QUERY = Regexp.new("^#{PATTERN::QUERY}$", false, 'N').freeze #"
|
|---|
| 213 | FRAGMENT = Regexp.new("^#{PATTERN::FRAGMENT}$", false, 'N').freeze #"
|
|---|
| 214 | # :startdoc:
|
|---|
| 215 | end # REGEXP
|
|---|
| 216 |
|
|---|
| 217 | module Util # :nodoc:
|
|---|
| 218 | def make_components_hash(klass, array_hash)
|
|---|
| 219 | tmp = {}
|
|---|
| 220 | if array_hash.kind_of?(Array) &&
|
|---|
| 221 | array_hash.size == klass.component.size - 1
|
|---|
| 222 | klass.component[1..-1].each_index do |i|
|
|---|
| 223 | begin
|
|---|
| 224 | tmp[klass.component[i + 1]] = array_hash[i].clone
|
|---|
| 225 | rescue TypeError
|
|---|
| 226 | tmp[klass.component[i + 1]] = array_hash[i]
|
|---|
| 227 | end
|
|---|
| 228 | end
|
|---|
| 229 |
|
|---|
| 230 | elsif array_hash.kind_of?(Hash)
|
|---|
| 231 | array_hash.each do |key, value|
|
|---|
| 232 | begin
|
|---|
| 233 | tmp[key] = value.clone
|
|---|
| 234 | rescue TypeError
|
|---|
| 235 | tmp[key] = value
|
|---|
| 236 | end
|
|---|
| 237 | end
|
|---|
| 238 | else
|
|---|
| 239 | raise ArgumentError,
|
|---|
| 240 | "expected Array of or Hash of components of #{klass.to_s} (#{klass.component[1..-1].join(', ')})"
|
|---|
| 241 | end
|
|---|
| 242 | tmp[:scheme] = klass.to_s.sub(/\A.*::/, '').downcase
|
|---|
| 243 |
|
|---|
| 244 | return tmp
|
|---|
| 245 | end
|
|---|
| 246 | module_function :make_components_hash
|
|---|
| 247 | end
|
|---|
| 248 |
|
|---|
| 249 | module Escape
|
|---|
| 250 | include REGEXP
|
|---|
| 251 |
|
|---|
| 252 | #
|
|---|
| 253 | # == Synopsis
|
|---|
| 254 | #
|
|---|
| 255 | # URI.escape(str [, unsafe])
|
|---|
| 256 | #
|
|---|
| 257 | # == Args
|
|---|
| 258 | #
|
|---|
| 259 | # +str+::
|
|---|
| 260 | # String to replaces in.
|
|---|
| 261 | # +unsafe+::
|
|---|
| 262 | # Regexp that matches all symbols that must be replaced with codes.
|
|---|
| 263 | # By default uses <tt>REGEXP::UNSAFE</tt>.
|
|---|
| 264 | # When this argument is a String, it represents a character set.
|
|---|
| 265 | #
|
|---|
| 266 | # == Description
|
|---|
| 267 | #
|
|---|
| 268 | # Escapes the string, replacing all unsafe characters with codes.
|
|---|
| 269 | #
|
|---|
| 270 | # == Usage
|
|---|
| 271 | #
|
|---|
| 272 | # require 'uri'
|
|---|
| 273 | #
|
|---|
| 274 | # enc_uri = URI.escape("http://example.com/?a=\11\15")
|
|---|
| 275 | # p enc_uri
|
|---|
| 276 | # # => "http://example.com/?a=%09%0D"
|
|---|
| 277 | #
|
|---|
| 278 | # p URI.unescape(enc_uri)
|
|---|
| 279 | # # => "http://example.com/?a=\t\r"
|
|---|
| 280 | #
|
|---|
| 281 | # p URI.escape("@?@!", "!?")
|
|---|
| 282 | # # => "@%3F@%21"
|
|---|
| 283 | #
|
|---|
| 284 | def escape(str, unsafe = UNSAFE)
|
|---|
| 285 | unless unsafe.kind_of?(Regexp)
|
|---|
| 286 | # perhaps unsafe is String object
|
|---|
| 287 | unsafe = Regexp.new("[#{Regexp.quote(unsafe)}]", false, 'N')
|
|---|
| 288 | end
|
|---|
| 289 | str.gsub(unsafe) do |us|
|
|---|
| 290 | tmp = ''
|
|---|
| 291 | us.each_byte do |uc|
|
|---|
| 292 | tmp << sprintf('%%%02X', uc)
|
|---|
| 293 | end
|
|---|
| 294 | tmp
|
|---|
| 295 | end
|
|---|
| 296 | end
|
|---|
| 297 | alias encode escape
|
|---|
| 298 | #
|
|---|
| 299 | # == Synopsis
|
|---|
| 300 | #
|
|---|
| 301 | # URI.unescape(str)
|
|---|
| 302 | #
|
|---|
| 303 | # == Args
|
|---|
| 304 | #
|
|---|
| 305 | # +str+::
|
|---|
| 306 | # Unescapes the string.
|
|---|
| 307 | #
|
|---|
| 308 | # == Usage
|
|---|
| 309 | #
|
|---|
| 310 | # require 'uri'
|
|---|
| 311 | #
|
|---|
| 312 | # enc_uri = URI.escape("http://example.com/?a=\11\15")
|
|---|
| 313 | # p enc_uri
|
|---|
| 314 | # # => "http://example.com/?a=%09%0D"
|
|---|
| 315 | #
|
|---|
| 316 | # p URI.unescape(enc_uri)
|
|---|
| 317 | # # => "http://example.com/?a=\t\r"
|
|---|
| 318 | #
|
|---|
| 319 | def unescape(str)
|
|---|
| 320 | str.gsub(ESCAPED) do
|
|---|
| 321 | $&[1,2].hex.chr
|
|---|
| 322 | end
|
|---|
| 323 | end
|
|---|
| 324 | alias decode unescape
|
|---|
| 325 | end
|
|---|
| 326 |
|
|---|
| 327 | include REGEXP
|
|---|
| 328 | extend Escape
|
|---|
| 329 |
|
|---|
| 330 | @@schemes = {}
|
|---|
| 331 |
|
|---|
| 332 | #
|
|---|
| 333 | # Base class for all URI exceptions.
|
|---|
| 334 | #
|
|---|
| 335 | class Error < StandardError; end
|
|---|
| 336 | #
|
|---|
| 337 | # Not a URI.
|
|---|
| 338 | #
|
|---|
| 339 | class InvalidURIError < Error; end
|
|---|
| 340 | #
|
|---|
| 341 | # Not a URI component.
|
|---|
| 342 | #
|
|---|
| 343 | class InvalidComponentError < Error; end
|
|---|
| 344 | #
|
|---|
| 345 | # URI is valid, bad usage is not.
|
|---|
| 346 | #
|
|---|
| 347 | class BadURIError < Error; end
|
|---|
| 348 |
|
|---|
| 349 | #
|
|---|
| 350 | # == Synopsis
|
|---|
| 351 | #
|
|---|
| 352 | # URI::split(uri)
|
|---|
| 353 | #
|
|---|
| 354 | # == Args
|
|---|
| 355 | #
|
|---|
| 356 | # +uri+::
|
|---|
| 357 | # String with URI.
|
|---|
| 358 | #
|
|---|
| 359 | # == Description
|
|---|
| 360 | #
|
|---|
| 361 | # Splits the string on following parts and returns array with result:
|
|---|
| 362 | #
|
|---|
| 363 | # * Scheme
|
|---|
| 364 | # * Userinfo
|
|---|
| 365 | # * Host
|
|---|
| 366 | # * Port
|
|---|
| 367 | # * Registry
|
|---|
| 368 | # * Path
|
|---|
| 369 | # * Opaque
|
|---|
| 370 | # * Query
|
|---|
| 371 | # * Fragment
|
|---|
| 372 | #
|
|---|
| 373 | # == Usage
|
|---|
| 374 | #
|
|---|
| 375 | # require 'uri'
|
|---|
| 376 | #
|
|---|
| 377 | # p URI.split("http://www.ruby-lang.org/")
|
|---|
| 378 | # # => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil]
|
|---|
| 379 | #
|
|---|
| 380 | def self.split(uri)
|
|---|
| 381 | case uri
|
|---|
| 382 | when ''
|
|---|
| 383 | # null uri
|
|---|
| 384 |
|
|---|
| 385 | when ABS_URI
|
|---|
| 386 | scheme, opaque, userinfo, host, port,
|
|---|
| 387 | registry, path, query, fragment = $~[1..-1]
|
|---|
| 388 |
|
|---|
| 389 | # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
|
|---|
| 390 |
|
|---|
| 391 | # absoluteURI = scheme ":" ( hier_part | opaque_part )
|
|---|
| 392 | # hier_part = ( net_path | abs_path ) [ "?" query ]
|
|---|
| 393 | # opaque_part = uric_no_slash *uric
|
|---|
| 394 |
|
|---|
| 395 | # abs_path = "/" path_segments
|
|---|
| 396 | # net_path = "//" authority [ abs_path ]
|
|---|
| 397 |
|
|---|
| 398 | # authority = server | reg_name
|
|---|
| 399 | # server = [ [ userinfo "@" ] hostport ]
|
|---|
| 400 |
|
|---|
| 401 | if !scheme
|
|---|
| 402 | raise InvalidURIError,
|
|---|
| 403 | "bad URI(absolute but no scheme): #{uri}"
|
|---|
| 404 | end
|
|---|
| 405 | if !opaque && (!path && (!host && !registry))
|
|---|
| 406 | raise InvalidURIError,
|
|---|
| 407 | "bad URI(absolute but no path): #{uri}"
|
|---|
| 408 | end
|
|---|
| 409 |
|
|---|
| 410 | when REL_URI
|
|---|
| 411 | scheme = nil
|
|---|
| 412 | opaque = nil
|
|---|
| 413 |
|
|---|
| 414 | userinfo, host, port, registry,
|
|---|
| 415 | rel_segment, abs_path, query, fragment = $~[1..-1]
|
|---|
| 416 | if rel_segment && abs_path
|
|---|
| 417 | path = rel_segment + abs_path
|
|---|
| 418 | elsif rel_segment
|
|---|
| 419 | path = rel_segment
|
|---|
| 420 | elsif abs_path
|
|---|
| 421 | path = abs_path
|
|---|
| 422 | end
|
|---|
| 423 |
|
|---|
| 424 | # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
|
|---|
| 425 |
|
|---|
| 426 | # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
|
|---|
| 427 |
|
|---|
| 428 | # net_path = "//" authority [ abs_path ]
|
|---|
| 429 | # abs_path = "/" path_segments
|
|---|
| 430 | # rel_path = rel_segment [ abs_path ]
|
|---|
| 431 |
|
|---|
| 432 | # authority = server | reg_name
|
|---|
| 433 | # server = [ [ userinfo "@" ] hostport ]
|
|---|
| 434 |
|
|---|
| 435 | else
|
|---|
| 436 | raise InvalidURIError, "bad URI(is not URI?): #{uri}"
|
|---|
| 437 | end
|
|---|
| 438 |
|
|---|
| 439 | path = '' if !path && !opaque # (see RFC2396 Section 5.2)
|
|---|
| 440 | ret = [
|
|---|
| 441 | scheme,
|
|---|
| 442 | userinfo, host, port, # X
|
|---|
| 443 | registry, # X
|
|---|
| 444 | path, # Y
|
|---|
| 445 | opaque, # Y
|
|---|
| 446 | query,
|
|---|
| 447 | fragment
|
|---|
| 448 | ]
|
|---|
| 449 | return ret
|
|---|
| 450 | end
|
|---|
| 451 |
|
|---|
| 452 | #
|
|---|
| 453 | # == Synopsis
|
|---|
| 454 | #
|
|---|
| 455 | # URI::parse(uri_str)
|
|---|
| 456 | #
|
|---|
| 457 | # == Args
|
|---|
| 458 | #
|
|---|
| 459 | # +uri_str+::
|
|---|
| 460 | # String with URI.
|
|---|
| 461 | #
|
|---|
| 462 | # == Description
|
|---|
| 463 | #
|
|---|
| 464 | # Creates one of the URI's subclasses instance from the string.
|
|---|
| 465 | #
|
|---|
| 466 | # == Raises
|
|---|
| 467 | #
|
|---|
| 468 | # URI::InvalidURIError
|
|---|
| 469 | # Raised if URI given is not a correct one.
|
|---|
| 470 | #
|
|---|
| 471 | # == Usage
|
|---|
| 472 | #
|
|---|
| 473 | # require 'uri'
|
|---|
| 474 | #
|
|---|
| 475 | # uri = URI.parse("http://www.ruby-lang.org/")
|
|---|
| 476 | # p uri
|
|---|
| 477 | # # => #<URI::HTTP:0x202281be URL:http://www.ruby-lang.org/>
|
|---|
| 478 | # p uri.scheme
|
|---|
| 479 | # # => "http"
|
|---|
| 480 | # p uri.host
|
|---|
| 481 | # # => "www.ruby-lang.org"
|
|---|
| 482 | #
|
|---|
| 483 | def self.parse(uri)
|
|---|
| 484 | scheme, userinfo, host, port,
|
|---|
| 485 | registry, path, opaque, query, fragment = self.split(uri)
|
|---|
| 486 |
|
|---|
| 487 | if scheme && @@schemes.include?(scheme.upcase)
|
|---|
| 488 | @@schemes[scheme.upcase].new(scheme, userinfo, host, port,
|
|---|
| 489 | registry, path, opaque, query,
|
|---|
| 490 | fragment)
|
|---|
| 491 | else
|
|---|
| 492 | Generic.new(scheme, userinfo, host, port,
|
|---|
| 493 | registry, path, opaque, query,
|
|---|
| 494 | fragment)
|
|---|
| 495 | end
|
|---|
| 496 | end
|
|---|
| 497 |
|
|---|
| 498 | #
|
|---|
| 499 | # == Synopsis
|
|---|
| 500 | #
|
|---|
| 501 | # URI::join(str[, str, ...])
|
|---|
| 502 | #
|
|---|
| 503 | # == Args
|
|---|
| 504 | #
|
|---|
| 505 | # +str+::
|
|---|
| 506 | # String(s) to work with
|
|---|
| 507 | #
|
|---|
| 508 | # == Description
|
|---|
| 509 | #
|
|---|
| 510 | # Joins URIs.
|
|---|
| 511 | #
|
|---|
| 512 | # == Usage
|
|---|
| 513 | #
|
|---|
| 514 | # require 'uri'
|
|---|
| 515 | #
|
|---|
| 516 | # p URI.join("http://localhost/","main.rbx")
|
|---|
| 517 | # # => #<URI::HTTP:0x2022ac02 URL:http://localhost/main.rbx>
|
|---|
| 518 | #
|
|---|
| 519 | def self.join(*str)
|
|---|
| 520 | u = self.parse(str[0])
|
|---|
| 521 | str[1 .. -1].each do |x|
|
|---|
| 522 | u = u.merge(x)
|
|---|
| 523 | end
|
|---|
| 524 | u
|
|---|
| 525 | end
|
|---|
| 526 |
|
|---|
| 527 | #
|
|---|
| 528 | # == Synopsis
|
|---|
| 529 | #
|
|---|
| 530 | # URI::extract(str[, schemes][,&blk])
|
|---|
| 531 | #
|
|---|
| 532 | # == Args
|
|---|
| 533 | #
|
|---|
| 534 | # +str+::
|
|---|
| 535 | # String to extract URIs from.
|
|---|
| 536 | # +schemes+::
|
|---|
| 537 | # Limit URI matching to a specific schemes.
|
|---|
| 538 | #
|
|---|
| 539 | # == Description
|
|---|
| 540 | #
|
|---|
| 541 | # Extracts URIs from a string. If block given, iterates through all matched URIs.
|
|---|
| 542 | # Returns nil if block given or array with matches.
|
|---|
| 543 | #
|
|---|
| 544 | # == Usage
|
|---|
| 545 | #
|
|---|
| 546 | # require "uri"
|
|---|
| 547 | #
|
|---|
| 548 | # URI.extract("text here http://foo.example.org/bla and here mailto:[email protected] and here also.")
|
|---|
| 549 | # # => ["http://foo.example.com/bla", "mailto:[email protected]"]
|
|---|
| 550 | #
|
|---|
| 551 | def self.extract(str, schemes = nil, &block)
|
|---|
| 552 | if block_given?
|
|---|
| 553 | str.scan(regexp(schemes)) { yield $& }
|
|---|
| 554 | nil
|
|---|
| 555 | else
|
|---|
| 556 | result = []
|
|---|
| 557 | str.scan(regexp(schemes)) { result.push $& }
|
|---|
| 558 | result
|
|---|
| 559 | end
|
|---|
| 560 | end
|
|---|
| 561 |
|
|---|
| 562 | #
|
|---|
| 563 | # == Synopsis
|
|---|
| 564 | #
|
|---|
| 565 | # URI::regexp([match_schemes])
|
|---|
| 566 | #
|
|---|
| 567 | # == Args
|
|---|
| 568 | #
|
|---|
| 569 | # +match_schemes+::
|
|---|
| 570 | # Array of schemes. If given, resulting regexp matches to URIs
|
|---|
| 571 | # whose scheme is one of the match_schemes.
|
|---|
| 572 | #
|
|---|
| 573 | # == Description
|
|---|
| 574 | # Returns a Regexp object which matches to URI-like strings.
|
|---|
| 575 | # The Regexp object returned by this method includes arbitrary
|
|---|
| 576 | # number of capture group (parentheses). Never rely on it's number.
|
|---|
| 577 | #
|
|---|
| 578 | # == Usage
|
|---|
| 579 | #
|
|---|
| 580 | # require 'uri'
|
|---|
| 581 | #
|
|---|
| 582 | # # extract first URI from html_string
|
|---|
| 583 | # html_string.slice(URI.regexp)
|
|---|
| 584 | #
|
|---|
| 585 | # # remove ftp URIs
|
|---|
| 586 | # html_string.sub(URI.regexp(['ftp'])
|
|---|
| 587 | #
|
|---|
| 588 | # # You should not rely on the number of parentheses
|
|---|
| 589 | # html_string.scan(URI.regexp) do |*matches|
|
|---|
| 590 | # p $&
|
|---|
| 591 | # end
|
|---|
| 592 | #
|
|---|
| 593 | def self.regexp(schemes = nil)
|
|---|
| 594 | unless schemes
|
|---|
| 595 | ABS_URI_REF
|
|---|
| 596 | else
|
|---|
| 597 | /(?=#{Regexp.union(*schemes)}:)#{PATTERN::X_ABS_URI}/xn
|
|---|
| 598 | end
|
|---|
| 599 | end
|
|---|
| 600 |
|
|---|
| 601 | end
|
|---|
| 602 |
|
|---|
| 603 | module Kernel
|
|---|
| 604 | # alias for URI.parse.
|
|---|
| 605 | #
|
|---|
| 606 | # This method is introduced at 1.8.2.
|
|---|
| 607 | def URI(uri_str) # :doc:
|
|---|
| 608 | URI.parse(uri_str)
|
|---|
| 609 | end
|
|---|
| 610 | module_function :URI
|
|---|
| 611 | end
|
|---|
