Refactor URL processing/generation into separate module

This is done to prepare for improved permalink generation
for URLs containing special characters, as proposed in
issue #782

lib/jekyll.rb

@@ -30,6 +30,7 @@ require 'pygments'
 require 'jekyll/core_ext'
 require 'jekyll/site'
 require 'jekyll/convertible'
+require 'jekyll/url'
 require 'jekyll/layout'
 require 'jekyll/page'
 require 'jekyll/post'

lib/jekyll/page.rb

@@ -1,6 +1,7 @@
 module Jekyll
   class Page
     include Convertible
+    include URL
 
     attr_writer :dir
     attr_accessor :site, :pager
@@ -69,28 +70,13 @@ module Jekyll
       end
     end
 
-    # The generated relative url of this page. e.g. /about.html.
+    # See url.rb for an explanation
-    #
+    def url_placeholders
-    # Returns the String url.
-    def url
-      return @url if @url
-
-      url = if permalink
-        permalink
-      else
       {
         "path"       => @dir,
         "basename"   => self.basename,
-          "output_ext" => self.output_ext,
+        "output_ext" => self.output_ext
-        }.inject(template) { |result, token|
+      }
-          result.gsub(/:#{token.first}/, token.last)
-        }.gsub(/\/\//, "/")
-      end
-
-      # sanitize url
-      @url = url.split('/').reject{ |part| part =~ /^\.+$/ }.join('/')
-      @url += "/" if url =~ /\/$/
-      @url
     end
 
     # Extract information from the page filename.

lib/jekyll/post.rb

@@ -2,6 +2,7 @@ module Jekyll
   class Post
     include Comparable
     include Convertible
+    include URL
 
     class << self
       attr_accessor :lsi
@@ -153,16 +154,8 @@ module Jekyll
       end
     end
 
-    # The generated relative url of this post.
+    # See url.rb for an explanation
-    # e.g. /2008/11/05/my-awesome-post.html
+    def url_placeholders
-    #
-    # Returns the String URL.
-    def url
-      return @url if @url
-
-      url = if permalink
-        permalink
-      else
       {
         "year"       => date.strftime("%Y"),
         "month"      => date.strftime("%m"),
@@ -174,15 +167,7 @@ module Jekyll
         "short_month" => date.strftime("%b"),
         "y_day"      => date.strftime("%j"),
         "output_ext" => self.output_ext
-        }.inject(template) { |result, token|
+      }
-          result.gsub(/:#{Regexp.escape token.first}/, token.last)
-        }.gsub(/\/\//, "/")
-      end
-
-      # sanitize url
-      @url = url.split('/').reject{ |part| part =~ /^\.+$/ }.join('/')
-      @url += "/" if url =~ /\/$/
-      @url
     end
 
     # The UID for this post (useful in feeds).

lib/jekyll/url.rb

@@ -0,0 +1,53 @@
+# The URL module provides methods that generate a URL for a resource in which they're
+# included, such as a Post or a Page.
+#
+# Requires
+#
+#   self.permalink  - If a permalink is set in the included instance, that permalink
+#                     will be returned instead of any URL that might've been generated
+#
+#   self.url_placeholders - Placeholders that may be used in the URL, which will be replaced
+#                         with the values when the URL is generated. Must return a Hash
+#                         mapping placeholder names to their values. For example, if this
+#                         method returned
+#
+#                           { "year" => Time.now.strftime("%Y") }
+#
+#                         Every occurrence of ":year" (note the colon) would be replaced with
+#                         the current year.
+#
+#
+
+module Jekyll
+  module URL
+
+    # The generated relative url of this page. e.g. /about.html.
+    #
+    # Returns the String url.
+    def url
+      @url ||= sanitize_url(permalink || generate_url)
+    end
+
+    # Generate the URL by replacing all placeholders with their respective values
+    #
+    # Returns the _unsanitizied_ String URL
+    def generate_url
+      url_placeholders.inject(template) { |result, token|
+        result.gsub(/:#{token.first}/, token.last)
+      }
+    end
+
+    # Returns a sanitized String URL
+    def sanitize_url(in_url)
+      # Remove all double slashes
+      url = in_url.gsub(/\/\//, "/")
+
+      # Remove every URL segment that consists solely of dots
+      url = url.split('/').reject{ |part| part =~ /^\.+$/ }.join('/')
+
+      # Append a trailing slash to the URL if the unsanitized URL had one
+      url += "/" if in_url =~ /\/$/
+      url
+    end
+  end
+end