lib/postrank-uri.rb in postrank-uri-1.0.18 vs lib/postrank-uri.rb in postrank-uri-1.0.20

@@ -1,17 +1,17 @@
-
+# encoding: utf-8
 require 'addressable/uri'
 require 'digest/md5'
 require 'nokogiri'
 require 'public_suffix'
 require 'yaml'
 
 module Addressable
   class URI
     def domain
       host = self.host
-      (host && PublicSuffix.valid?(host)) ? PublicSuffix.parse(host).domain : nil
+      (host && PublicSuffix.valid?(host, default_rule: nil)) ? PublicSuffix.parse(host).domain : nil
     end
 
     def normalized_query
       @normalized_query ||= (begin
         if self.query && self.query.strip != ''
@@ -84,22 +84,23 @@
               (\?#{URIREGEX[:valid_url_query_chars]}*#{URIREGEX[:valid_url_query_ending_chars]})?
             )
           )
         }iox;
 
+    URIREGEX[:reserved_characters] = /%3F|%26/i
     URIREGEX[:escape]   = /([^ a-zA-Z0-9_.-]+)/x
-    URIREGEX[:unescape] = /((?:%[0-9a-fA-F]{2})+)/x
+    URIREGEX[:unescape] = /(%[0-9a-fA-F]{2})/x
     URIREGEX.each_pair{|k,v| v.freeze }
 
     module_function
 
     def extract(text)
       return [] if !text
       urls = []
       text.to_s.scan(URIREGEX[:valid_url]) do |all, before, url, protocol, domain, path, query|
         # Only extract the URL if the domain is valid
-        if PublicSuffix.valid?(domain)
+        if PublicSuffix.valid?(domain, default_rule: nil)
           url = clean(url)
           urls.push url.to_s
         end
       end
 
@@ -129,12 +130,16 @@
     end
 
     def unescape(uri)
       u = parse(uri)
       u.query = u.query.tr('+', ' ') if u.query
-      u.to_s.gsub(URIREGEX[:unescape]) do
-        [$1.delete('%')].pack('H*')
+      u.to_s.gsub(URIREGEX[:unescape]) do |encoded|
+        if encoded.match? URIREGEX[:reserved_characters]
+          encoded
+        else
+          [encoded.delete('%')].pack('H*')
+        end
       end
     end
 
     def clean(uri, opts = {})
       uri = normalize(c14n(unescape(uri), opts))
@@ -223,10 +228,10 @@
 
       is_valid = false
       cleaned_uri = clean(uri, :raw => true)
 
       if host = cleaned_uri.host
-        is_valid = PublicSuffix.valid?(Addressable::IDNA.to_unicode(host))
+        is_valid = PublicSuffix.valid?(Addressable::IDNA.to_unicode(host), default_rule: nil)
       end
 
       is_valid
     end
   end