Merge pull request jekyll#944 from x3ro/permalink-special-characters

WIP - Improve permalink generation for URLs with special characters

lib/jekyll.rb

@@ -33,6 +33,7 @@ def require_all(path)
 require 'jekyll/configuration'
 require 'jekyll/site'
 require 'jekyll/convertible'
+require 'jekyll/url'
 require 'jekyll/layout'
 require 'jekyll/page'
 require 'jekyll/post'

lib/jekyll/page.rb

@@ -37,7 +37,12 @@ def dir
     #
     # Returns the String permalink or nil if none has been set.
     def permalink
-      self.data && self.data['permalink']
+      return nil if self.data.nil? || self.data['permalink'].nil?
+      if site.config['relative_permalinks']
+        File.join(@dir, self.data['permalink'])
+      else
+        self.data['permalink']
+      end
     end
 
     # The template of the permalink.
@@ -61,29 +66,21 @@ def template
     #
     # Returns the String url.
     def url
-      return @url if @url
-
-      url = if permalink
-        if site.config['relative_permalinks']
-          File.join(@dir, permalink)
-        else
-          permalink
-        end
-      else
-        {
-          "path"       => @dir,
-          "basename"   => self.basename,
-          "output_ext" => self.output_ext,
-        }.inject(template) { |result, token|
-          result.gsub(/:#{token.first}/, token.last)
-        }.gsub(/\/\//, "/")
-      end
+      @url ||= URL.new({
+        :template => template,
+        :placeholders => url_placeholders,
+        :permalink => permalink
+      }).to_s
+    end
 
-      # sanitize url
-      @url = url.split('/').reject{ |part| part =~ /^\.+$/ }.join('/')
-      @url += "/" if url =~ /\/$/
-      @url.gsub!(/\A([^\/])/, '/\1')
-      @url
+    # Returns a hash of URL placeholder names (as symbols) mapping to the
+    # desired placeholder replacements. For details see "url.rb"
+    def url_placeholders
+      {
+        :path       => @dir,
+        :basename   => self.basename,
+        :output_ext => self.output_ext
+      }
     end
 
     # Extract information from the page filename.

lib/jekyll/post.rb

@@ -195,36 +195,31 @@ def template
     end
 
     # The generated relative url of this post.
-    # e.g. /2008/11/05/my-awesome-post.html
     #
-    # Returns the String URL.
+    # Returns the String url.
     def url
-      return @url if @url
-
-      url = if permalink
-        permalink
-      else
-        {
-          "year"       => date.strftime("%Y"),
-          "month"      => date.strftime("%m"),
-          "day"        => date.strftime("%d"),
-          "title"      => CGI.escape(slug),
-          "i_day"      => date.strftime("%d").to_i.to_s,
-          "i_month"    => date.strftime("%m").to_i.to_s,
-          "categories" => categories.map { |c| URI.escape(c.to_s) }.join('/'),
-          "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
+      @url ||= URL.new({
+        :template => template,
+        :placeholders => url_placeholders,
+        :permalink => permalink
+      }).to_s
+    end
 
-      # sanitize url
-      @url = url.split('/').reject{ |part| part =~ /^\.+$/ }.join('/')
-      @url += "/" if url =~ /\/$/
-      @url.gsub!(/\A([^\/])/, '/\1')
-      @url
+    # Returns a hash of URL placeholder names (as symbols) mapping to the
+    # desired placeholder replacements. For details see "url.rb"
+    def url_placeholders
+      {
+        :year        => date.strftime("%Y"),
+        :month       => date.strftime("%m"),
+        :day         => date.strftime("%d"),
+        :title       => CGI.escape(slug),
+        :i_day       => date.strftime("%d").to_i.to_s,
+        :i_month     => date.strftime("%m").to_i.to_s,
+        :categories  => (categories || []).map { |c| URI.escape(c.to_s) }.join('/'),
+        :short_month => date.strftime("%b"),
+        :y_day       => date.strftime("%j"),
+        :output_ext  => self.output_ext
+      }
     end
 
     # The UID for this post (useful in feeds).

lib/jekyll/url.rb

@@ -0,0 +1,67 @@
+# Public: Methods that generate a URL for a resource such as a Post or a Page.
+#
+# Examples
+#
+#   URL.new({
+#     :template => /:categories/:title.html",
+#     :placeholders => {:categories => "ruby", :title => "something"}
+#   }).to_s
+#
+module Jekyll
+  class URL
+
+    # options - One of :permalink or :template must be supplied.
+    #           :template     - The String used as template for URL generation,
+    #                           for example "/:path/:basename:output_ext", where
+    #                           a placeholder is prefixed with a colon.
+    #           :placeholders - A hash containing the placeholders which will be
+    #                           replaced when used inside the template. E.g.
+    #                           { "year" => Time.now.strftime("%Y") } would replace
+    #                           the placeholder ":year" with the current year.
+    #           :permalink    - If supplied, no URL will be generated from the
+    #                           template. Instead, the given permalink will be
+    #                           used as URL.
+    def initialize(options)
+      @template = options[:template]
+      @placeholders = options[:placeholders] || {}
+      @permalink = options[:permalink]
+
+      if (@template || @permalink).nil?
+        raise ArgumentError, "One of :template or :permalink must be supplied."
+      end
+    end
+
+    # The generated relative URL of the resource
+    #
+    # Returns the String URL
+    def to_s
+      sanitize_url(@permalink || generate_url)
+    end
+
+    # Internal: Generate the URL by replacing all placeholders with their
+    # respective values
+    #
+    # Returns the _unsanitizied_ String URL
+    def generate_url
+      @placeholders.inject(@template) do |result, token|
+        result.gsub(/:#{token.first}/, token.last)
+      end
+    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 =~ /^\.+$/ }.join('/')
+
+      # Append a trailing slash to the URL if the unsanitized URL had one
+      url += "/" if in_url =~ /\/$/
+
+      # Always add a leading slash
+      url.gsub!(/\A([^\/])/, '/\1')
+      url
+    end
+  end
+end

test/test_url.rb

@@ -0,0 +1,28 @@
+require 'helper'
+
+class TestURL < Test::Unit::TestCase
+  context "The URL class" do
+
+    should "throw an exception if neither permalink or template is specified" do
+      assert_raises ArgumentError do
+        URL.new(:placeholders => {})
+      end
+    end
+
+    should "replace placeholders in templates" do
+      assert_equal "/foo/bar", URL.new(
+        :template => "/:x/:y",
+        :placeholders => {:x => "foo", :y => "bar"}
+      ).to_s
+    end
+
+    should "return permalink if given" do
+      assert_equal "/le/perma/link", URL.new(
+        :template => "/:x/:y",
+        :placeholders => {:x => "foo", :y => "bar"},
+        :permalink => "/le/perma/link"
+      ).to_s
+    end
+
+  end
+end