postrank-uri.rb in postrank-uri-1.0.4

- old
+ new

@@ -70,13 +70,13 @@
     def extract(text)
       return [] if !text
       urls = []
       text.to_s.scan(URIREGEX[:valid_url]) do |all, before, url, protocol, domain, path, query|
         begin
-          url = clean(url).to_s
+          url = clean(url)
           Domainatrix.parse(url)
-          urls.push url
+          urls.push url.to_s
         rescue NoMethodError
         end
       end
 
       urls.compact
@@ -84,11 +84,11 @@
 
     def extract_href(text, host = nil)
       urls = []
       Nokogiri.HTML(text).search('a').each do |a|
         begin
-          url = normalize(c18n(unescape(a.attr('href'))))
+          url = clean(a.attr('href'), false)
           if url.host.empty?
             next if host.nil?
             url.host = host
           end
 
@@ -110,11 +110,12 @@
       uri.tr('+', ' ').gsub(URIREGEX[:unescape]) do
         [$1.delete('%')].pack('H*')
       end
     end
 
-    def clean(uri)
-      normalize(c18n(unescape(uri))).to_s
+    def clean(uri, string = true)
+      uri = normalize(c18n(unescape(uri)))
+      string ? uri.to_s : uri
     end
 
     def normalize(uri)
       u = parse(uri)
       u.path = u.path.squeeze('/')
\ No newline at end of file