680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
|
# File 'lib/mechanize/http/agent.rb', line 680
def resolve(uri, referer = current_page)
referer_uri = referer && referer.uri
if uri.is_a?(URI)
uri = uri.dup
elsif uri.nil?
if referer_uri
return referer_uri
end
raise ArgumentError, "absolute URL needed (not nil)"
else
url = uri.to_s.strip
if url.empty?
if referer_uri
return referer_uri.dup.tap { |u| u.fragment = nil }
end
raise ArgumentError, "absolute URL needed (not #{uri.inspect})"
end
url.gsub!(/[^#{0.chr}-#{126.chr}]/o) { |match|
Mechanize::Util.uri_escape(match)
}
escaped_url = Mechanize::Util.html_unescape(
url.split(/((?:%[0-9A-Fa-f]{2})+|#)/).each_slice(2).map { |x, y|
"#{WEBrick::HTTPUtils.escape(x)}#{y}"
}.join('')
)
begin
uri = URI.parse(escaped_url)
rescue
uri = URI.parse(WEBrick::HTTPUtils.escape(escaped_url))
end
end
uri.host = referer_uri.host if referer_uri && URI::HTTP === uri && uri.host.nil?
scheme = uri.relative? ? 'relative' : uri.scheme.downcase
uri = @scheme_handlers[scheme].call(uri, referer)
if uri.relative?
raise ArgumentError, "absolute URL needed (not #{uri})" unless
referer_uri
if referer.respond_to?(:bases) && referer.parser &&
(lbase = referer.bases.last) && lbase.uri && lbase.uri.absolute?
base = lbase
else
base = nil
end
base = referer_uri + (base ? base.uri : referer_uri)
if uri.path.match(%r{\A(.*?/)(?!/\.\.?(?!/))(/.*)\z}i)
uri = URI((base + $1).to_s + $2)
else
uri = base + uri
end
uri.path.sub!(/^(\/\.\.)+(?=\/)/, '')
end
unless ['http', 'https', 'file'].include?(uri.scheme.downcase)
raise ArgumentError, "unsupported scheme: #{uri.scheme}"
end
case uri.path
when nil
raise ArgumentError, "hierarchical URL needed (not #{uri})"
when ''.freeze
uri.path = '/'
end
uri
end
|