| Module | URI |
| In: |
lib/open-uri.rb
lib/uri/common.rb lib/uri/ftp.rb lib/uri/generic.rb lib/uri/http.rb lib/uri/https.rb lib/uri/ldap.rb lib/uri/mailto.rb lib/uri.rb |
URI support for Ruby
| Author: | Akira Yamada <akira@ruby-lang.org> |
| Documentation: | Akira Yamada <akira@ruby-lang.org>, Dmitry V. Sabanin <sdmitry@lrn.ru> |
| License: | Copyright (c) 2001 akira yamada <akira@ruby-lang.org> You can redistribute it and/or modify it under the same term as Ruby. |
| Revision: | $Id: uri.rb,v 1.8.2.2 2004/07/17 13:07:46 akira Exp $ |
See URI for documentation
URI::extract(str[, schemes][,&blk])
| str: | String to extract URIs from. |
| schemes: | Limit URI matching to a specific schemes. |
Extracts URIs from a string. If block given, iterates through all matched URIs. Returns nil if block given or array with matches.
require "uri"
URI.extract("text here http://foo.example.org/bla and here mailto:test@example.com and here also.")
# => ["http://foo.example.org/bla", "mailto:test@example.com"]
# File lib/uri/common.rb, line 547
547: def self.extract(str, schemes = nil, &block)
548: if block_given?
549: str.scan(regexp(schemes)) { yield $& }
550: nil
551: else
552: result = []
553: str.scan(regexp(schemes)) { result.push $& }
554: result
555: end
556: end
URI::join(str[, str, ...])
| str: | String(s) to work with |
Joins URIs.
require 'uri'
p URI.join("http://localhost/","main.rbx")
# => #<URI::HTTP:0x2022ac02 URL:http://localhost/main.rbx>
# File lib/uri/common.rb, line 515
515: def self.join(*str)
516: u = self.parse(str[0])
517: str[1 .. -1].each do |x|
518: u = u.merge(x)
519: end
520: u
521: end
URI::parse(uri_str)
| uri_str: | String with URI. |
Creates one of the URI‘s subclasses instance from the string.
Raised if URI given is not a correct one.
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"
# File lib/uri/common.rb, line 479
479: def self.parse(uri)
480: scheme, userinfo, host, port,
481: registry, path, opaque, query, fragment = self.split(uri)
482:
483: if scheme && @@schemes.include?(scheme.upcase)
484: @@schemes[scheme.upcase].new(scheme, userinfo, host, port,
485: registry, path, opaque, query,
486: fragment)
487: else
488: Generic.new(scheme, userinfo, host, port,
489: registry, path, opaque, query,
490: fragment)
491: end
492: end
URI::regexp([match_schemes])
| match_schemes: | Array of schemes. If given, resulting regexp matches to URIs whose scheme is one of the match_schemes. |
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.
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
# File lib/uri/common.rb, line 589
589: def self.regexp(schemes = nil)
590: unless schemes
591: ABS_URI_REF
592: else
593: /(?=#{Regexp.union(*schemes)}:)#{PATTERN::X_ABS_URI}/xn
594: end
595: end
URI::split(uri)
| uri: | String with URI. |
Splits the string on following parts and returns array with result:
* Scheme * Userinfo * Host * Port * Registry * Path * Opaque * Query * Fragment
require 'uri'
p URI.split("http://www.ruby-lang.org/")
# => ["http", nil, "www.ruby-lang.org", nil, nil, "/", nil, nil, nil]
# File lib/uri/common.rb, line 376
376: def self.split(uri)
377: case uri
378: when ''
379: # null uri
380:
381: when ABS_URI
382: scheme, opaque, userinfo, host, port,
383: registry, path, query, fragment = $~[1..-1]
384:
385: # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
386:
387: # absoluteURI = scheme ":" ( hier_part | opaque_part )
388: # hier_part = ( net_path | abs_path ) [ "?" query ]
389: # opaque_part = uric_no_slash *uric
390:
391: # abs_path = "/" path_segments
392: # net_path = "//" authority [ abs_path ]
393:
394: # authority = server | reg_name
395: # server = [ [ userinfo "@" ] hostport ]
396:
397: if !scheme
398: raise InvalidURIError,
399: "bad URI(absolute but no scheme): #{uri}"
400: end
401: if !opaque && (!path && (!host && !registry))
402: raise InvalidURIError,
403: "bad URI(absolute but no path): #{uri}"
404: end
405:
406: when REL_URI
407: scheme = nil
408: opaque = nil
409:
410: userinfo, host, port, registry,
411: rel_segment, abs_path, query, fragment = $~[1..-1]
412: if rel_segment && abs_path
413: path = rel_segment + abs_path
414: elsif rel_segment
415: path = rel_segment
416: elsif abs_path
417: path = abs_path
418: end
419:
420: # URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
421:
422: # relativeURI = ( net_path | abs_path | rel_path ) [ "?" query ]
423:
424: # net_path = "//" authority [ abs_path ]
425: # abs_path = "/" path_segments
426: # rel_path = rel_segment [ abs_path ]
427:
428: # authority = server | reg_name
429: # server = [ [ userinfo "@" ] hostport ]
430:
431: else
432: raise InvalidURIError, "bad URI(is not URI?): #{uri}"
433: end
434:
435: path = '' if !path && !opaque # (see RFC2396 Section 5.2)
436: ret = [
437: scheme,
438: userinfo, host, port, # X
439: registry, # X
440: path, # Y
441: opaque, # Y
442: query,
443: fragment
444: ]
445: return ret
446: end