Make auto_link parse a greater subset of valid url formats.

git-svn-id: http://svn-commit.rubyonrails.org/rails/trunk@4896 5ecf4fe2-1ee6-0310-87b1-e25e094e27de

actionpack/CHANGELOG

 *SVN*
 
+* Make auto_link parse a greater subset of valid url formats. [Jamis Buck]
+
 * Integration tests: headers beginning with X aren't excluded from the HTTP_ prefix, so X-Requested-With becomes HTTP_X_REQUESTED_WITH as expected. [Mike Clark]
 
 * Tighten rescue clauses.  #5985 [james@grayproductions.net]

actionpack/lib/action_view/helpers/text_helper.rb

@@ -313,23 +313,26 @@ def set_cycle(name, cycle_object)
           @_cycles[name] = cycle_object
         end
       
-        AUTO_LINK_RE = /
-                        (                       # leading text
-                          <\w+.*?>|             #   leading HTML tag, or
-                          [^=!:'"\/]|           #   leading punctuation, or 
-                          ^                     #   beginning of line
+        AUTO_LINK_RE = %r{
+                        (                        # leading text
+                          <\w+.*?>|              #   leading HTML tag, or
+                          [^=!:'"/]|             #   leading punctuation, or 
+                          ^                      #   beginning of line
                         )
                         (
-                          (?:http[s]?:\/\/)|    # protocol spec, or
-                          (?:www\.)             # www.*
+                          (?:https?://)|         # protocol spec, or
+                          (?:www\.)              # www.*
                         ) 
                         (
-                          ([\w]+:?[=?&\/.-]?)*    # url segment
-                          \w+[\/]?              # url tail
-                          (?:\#\w*)?            # trailing anchor
+                          [-\w]+                 # subdomain or domain
+                          (?:\.[-\w]+)*          # remaining subdomains or domain
+                          (?::\d+)?              # port
+                          (?:/(?:[~\w%.;-]+)?)*  # path
+                          (?:\?[\w%&=.;-]+)?     # query string
+                          (?:\#\w*)?             # trailing anchor
                         )
-                        ([[:punct:]]|\s|<|$)    # trailing text
-                       /x unless const_defined?(:AUTO_LINK_RE)
+                        ([[:punct:]]|\s|<|$)     # trailing text
+                       }x unless const_defined?(:AUTO_LINK_RE)
 
         # Turns all urls into clickable links.  If a block is given, each url
         # is yielded and the result is used as the link text.  Example:
@@ -339,7 +342,7 @@ def set_cycle(name, cycle_object)
         def auto_link_urls(text, href_options = {})
           extra_options = tag_options(href_options.stringify_keys) || ""
           text.gsub(AUTO_LINK_RE) do
-            all, a, b, c, d = $&, $1, $2, $3, $5
+            all, a, b, c, d = $&, $1, $2, $3, $4
             if a =~ /<a\s/i # don't replace URL's that are already linked
               all
             else

actionpack/test/template/text_helper_test.rb

@@ -114,6 +114,24 @@ def test_pluralization
     assert_equal("2 counts", pluralize(2, "count"))
   end
 
+  def test_auto_link_parsing
+    urls = %w(http://www.rubyonrails.com
+              http://www.rubyonrails.com:80
+              http://www.rubyonrails.com/~minam
+              https://www.rubyonrails.com/~minam
+              http://www.rubyonrails.com/~minam/url%20with%20spaces
+              http://www.rubyonrails.com/foo.cgi?something=here
+              http://www.rubyonrails.com/foo.cgi?something=here&and=here
+              http://www.rubyonrails.com/contact;new
+              http://www.rubyonrails.com/contact;new%20with%20spaces
+              http://www.rubyonrails.com/contact;new?with=query&string=params
+              http://www.rubyonrails.com/~minam/contact;new?with=query&string=params)
+
+    urls.each do |url|
+      assert_equal %(<a href="#{url}">#{url}</a>), auto_link(url)
+    end
+  end
+
   def test_auto_linking
     email_raw    = 'david@loudthinking.com'
     email_result = %{<a href="mailto:#{email_raw}">#{email_raw}</a>}