Updating shortcode gem version

* replaced File.realpath in testsuite with File.expand_path
* removed the old YAML hack

.travis.yml

@@ -0,0 +1,4 @@
+rvm:
+  - 1.9.2
+  - 1.8.7
+  - ruby-head

Gemfile

@@ -1,11 +1,15 @@
 source "http://rubygems.org"
 
-gem "rails", "3.0.7"
+ruby '2.0.0'
+
+gem "rails", "4.0.0"
 #gem "capybara", ">= 1.0.0.beta1"
 gem "sqlite3"
 gem "rmagick"
+gem 'shortcode', "0.1.2"
 
 group :development, :test do
+  gem 'byebug'
   gem "rspec-rails", ">= 2.6.0"
   gem "database_cleaner"
   gem 'guard-rspec'
@@ -19,6 +23,4 @@ end
 # gem 'ruby-debug'
 # gem 'ruby-debug19'
 
-gem 'refinerycms'
-gem 'refinerycms-blog'
-gem 'refinerycms-wordpress-import', :path => './'
+gem 'wordpress-import', :path => './'

Gemfile.lock

@@ -1,197 +1,176 @@
 PATH
   remote: ./
   specs:
-    refinerycms-wordpress-import (0.3.0)
+    wordpress-import (0.4.4)
       bundler (~> 1.0)
-      nokogiri (~> 1.4.4)
-      refinerycms (~> 1.0.0)
-      refinerycms-blog (~> 1.5.2)
+      nokogiri (~> 1.6.0)
+      shortcode (~> 0.1.1)
 
 GEM
   remote: http://rubygems.org/
   specs:
-    abstract (1.0.0)
-    actionmailer (3.0.7)
-      actionpack (= 3.0.7)
-      mail (~> 2.2.15)
-    actionpack (3.0.7)
-      activemodel (= 3.0.7)
-      activesupport (= 3.0.7)
-      builder (~> 2.1.2)
-      erubis (~> 2.6.6)
-      i18n (~> 0.5.0)
-      rack (~> 1.2.1)
-      rack-mount (~> 0.6.14)
-      rack-test (~> 0.5.7)
-      tzinfo (~> 0.3.23)
-    activemodel (3.0.7)
-      activesupport (= 3.0.7)
-      builder (~> 2.1.2)
-      i18n (~> 0.5.0)
-    activerecord (3.0.7)
-      activemodel (= 3.0.7)
-      activesupport (= 3.0.7)
-      arel (~> 2.0.2)
-      tzinfo (~> 0.3.23)
-    activeresource (3.0.7)
-      activemodel (= 3.0.7)
-      activesupport (= 3.0.7)
-    activesupport (3.0.7)
-    acts-as-taggable-on (2.0.6)
-    acts_as_indexed (0.7.2)
-    arel (2.0.10)
-    awesome_nested_set (2.0.0)
-      activerecord (>= 3.0.0)
-    babosa (0.3.5)
-    bcrypt-ruby (2.1.4)
-    builder (2.1.2)
-    database_cleaner (0.6.7)
-    devise (1.3.4)
-      bcrypt-ruby (~> 2.1.2)
-      orm_adapter (~> 0.0.3)
-      warden (~> 1.0.3)
-    diff-lcs (1.1.2)
-    dragonfly (0.9.4)
-      rack
-    erubis (2.6.6)
-      abstract (>= 1.0.0)
+    actionmailer (4.0.0)
+      actionpack (= 4.0.0)
+      mail (~> 2.5.3)
+    actionpack (4.0.0)
+      activesupport (= 4.0.0)
+      builder (~> 3.1.0)
+      erubis (~> 2.7.0)
+      rack (~> 1.5.2)
+      rack-test (~> 0.6.2)
+    activemodel (4.0.0)
+      activesupport (= 4.0.0)
+      builder (~> 3.1.0)
+    activerecord (4.0.0)
+      activemodel (= 4.0.0)
+      activerecord-deprecated_finders (~> 1.0.2)
+      activesupport (= 4.0.0)
+      arel (~> 4.0.0)
+    activerecord-deprecated_finders (1.0.3)
+    activesupport (4.0.0)
+      i18n (~> 0.6, >= 0.6.4)
+      minitest (~> 4.2)
+      multi_json (~> 1.3)
+      thread_safe (~> 0.1)
+      tzinfo (~> 0.3.37)
+    arel (4.0.2)
+    atomic (1.1.15)
+    blankslate (2.1.2.4)
+    builder (3.1.4)
+    byebug (2.7.0)
+      columnize (~> 0.3)
+      debugger-linecache (~> 1.2)
+    celluloid (0.15.2)
+      timers (~> 1.1.0)
+    celluloid-io (0.15.0)
+      celluloid (>= 0.15.0)
+      nio4r (>= 0.5.0)
+    coderay (1.1.0)
+    columnize (0.3.6)
+    database_cleaner (1.2.0)
+    debugger-linecache (1.2.0)
+    diff-lcs (1.2.5)
+    erubis (2.7.0)
     fakeweb (1.3.0)
-    ffi (1.0.9)
-    filters_spam (0.3)
-    friendly_id_globalize3 (3.2.1.3)
-      babosa (~> 0.3.0)
-    globalize3 (0.1.0)
-      activemodel (>= 3.0.0)
-      activerecord (>= 3.0.0)
-    guard (0.4.2)
-      thor (~> 0.14.6)
-    guard-bundler (0.1.3)
-      bundler (>= 1.0.0)
-      guard (>= 0.2.2)
-    guard-rspec (0.4.0)
-      guard (>= 0.4.0)
-    i18n (0.5.0)
-    libnotify (0.5.5)
-    mail (2.2.19)
-      activesupport (>= 2.3.6)
-      i18n (>= 0.4.0)
+    ffi (1.9.3)
+    formatador (0.2.4)
+    guard (2.5.1)
+      formatador (>= 0.2.4)
+      listen (~> 2.6)
+      lumberjack (~> 1.0)
+      pry (>= 0.9.12)
+      thor (>= 0.18.1)
+    guard-bundler (2.0.0)
+      bundler (~> 1.0)
+      guard (~> 2.2)
+    guard-rspec (4.2.8)
+      guard (~> 2.1)
+      rspec (>= 2.14, < 4.0)
+    haml (4.0.5)
+      tilt
+    hike (1.2.3)
+    i18n (0.6.9)
+    libnotify (0.8.2)
+      ffi (>= 1.0.11)
+    listen (2.7.0)
+      celluloid (>= 0.15.2)
+      celluloid-io (>= 0.15.0)
+      rb-fsevent (>= 0.9.3)
+      rb-inotify (>= 0.9)
+    lumberjack (1.0.4)
+    mail (2.5.4)
       mime-types (~> 1.16)
       treetop (~> 1.4.8)
-    mime-types (1.16)
-    nokogiri (1.4.4)
-    orm_adapter (0.0.5)
-    polyglot (0.3.1)
-    rack (1.2.3)
-    rack-cache (1.0.2)
-      rack (>= 0.4)
-    rack-mount (0.6.14)
-      rack (>= 1.0.0)
-    rack-test (0.5.7)
+    method_source (0.8.2)
+    mime-types (1.25.1)
+    mini_portile (0.5.2)
+    minitest (4.7.5)
+    multi_json (1.9.0)
+    nio4r (1.0.0)
+    nokogiri (1.6.1)
+      mini_portile (~> 0.5.0)
+    parslet (1.5.0)
+      blankslate (~> 2.0)
+    polyglot (0.3.4)
+    pry (0.9.12.6)
+      coderay (~> 1.0)
+      method_source (~> 0.8)
+      slop (~> 3.4)
+    rack (1.5.2)
+    rack-test (0.6.2)
       rack (>= 1.0)
-    rails (3.0.7)
-      actionmailer (= 3.0.7)
-      actionpack (= 3.0.7)
-      activerecord (= 3.0.7)
-      activeresource (= 3.0.7)
-      activesupport (= 3.0.7)
-      bundler (~> 1.0)
-      railties (= 3.0.7)
-    railties (3.0.7)
-      actionpack (= 3.0.7)
-      activesupport (= 3.0.7)
+    rails (4.0.0)
+      actionmailer (= 4.0.0)
+      actionpack (= 4.0.0)
+      activerecord (= 4.0.0)
+      activesupport (= 4.0.0)
+      bundler (>= 1.3.0, < 2.0)
+      railties (= 4.0.0)
+      sprockets-rails (~> 2.0.0)
+    railties (4.0.0)
+      actionpack (= 4.0.0)
+      activesupport (= 4.0.0)
       rake (>= 0.8.7)
-      thor (~> 0.14.4)
-    rake (0.9.2)
-    refinerycms (1.0.0)
-      bundler (~> 1.0)
-      refinerycms-authentication (= 1.0.0)
-      refinerycms-base (= 1.0.0)
-      refinerycms-core (= 1.0.0)
-      refinerycms-dashboard (= 1.0.0)
-      refinerycms-images (= 1.0.0)
-      refinerycms-pages (= 1.0.0)
-      refinerycms-resources (= 1.0.0)
-      refinerycms-settings (= 1.0.0)
-    refinerycms-authentication (1.0.0)
-      devise (~> 1.3.0)
-      friendly_id_globalize3 (~> 3.2.1)
-      refinerycms-core (= 1.0.0)
-    refinerycms-base (1.0.0)
-    refinerycms-blog (1.5.2)
-      acts-as-taggable-on
-      filters_spam (~> 0.2)
-      refinerycms-core (~> 1.0.0)
-      seo_meta (~> 1.1.0)
-    refinerycms-core (1.0.0)
-      acts_as_indexed (~> 0.7)
-      awesome_nested_set (~> 2.0)
-      friendly_id_globalize3 (~> 3.2.1)
-      globalize3 (~> 0.1)
-      rails (~> 3.0.7)
-      refinerycms-base (= 1.0.0)
-      refinerycms-generators (~> 1.0)
-      refinerycms-settings (= 1.0.0)
-      truncate_html (~> 0.5)
-      will_paginate (~> 3.0.pre)
-    refinerycms-dashboard (1.0.0)
-      refinerycms-core (= 1.0.0)
-    refinerycms-generators (1.0.2)
-    refinerycms-images (1.0.0)
-      dragonfly (~> 0.9.0)
-      rack-cache (>= 0.5.3)
-      refinerycms-core (= 1.0.0)
-    refinerycms-pages (1.0.0)
-      awesome_nested_set (~> 2.0)
-      friendly_id_globalize3 (~> 3.2.1)
-      globalize3 (~> 0.1)
-      refinerycms-core (= 1.0.0)
-      seo_meta (~> 1.1)
-    refinerycms-resources (1.0.0)
-      dragonfly (~> 0.9.0)
-      rack-cache (>= 0.5.3)
-      refinerycms-core (= 1.0.0)
-    refinerycms-settings (1.0.0)
-      refinerycms-base (= 1.0.0)
-    rmagick (2.13.1)
-    rspec (2.6.0)
-      rspec-core (~> 2.6.0)
-      rspec-expectations (~> 2.6.0)
-      rspec-mocks (~> 2.6.0)
-    rspec-core (2.6.4)
-    rspec-expectations (2.6.0)
-      diff-lcs (~> 1.1.2)
-    rspec-mocks (2.6.0)
-    rspec-rails (2.6.1)
-      actionpack (~> 3.0)
-      activesupport (~> 3.0)
-      railties (~> 3.0)
-      rspec (~> 2.6.0)
-    seo_meta (1.1.1)
-      refinerycms-generators (~> 1.0.1)
-    sqlite3 (1.3.3)
-    thor (0.14.6)
-    treetop (1.4.9)
+      thor (>= 0.18.1, < 2.0)
+    rake (10.1.1)
+    rb-fsevent (0.9.4)
+    rb-inotify (0.9.3)
+      ffi (>= 0.5.0)
+    rmagick (2.13.2)
+    rspec (2.14.1)
+      rspec-core (~> 2.14.0)
+      rspec-expectations (~> 2.14.0)
+      rspec-mocks (~> 2.14.0)
+    rspec-core (2.14.8)
+    rspec-expectations (2.14.5)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.14.6)
+    rspec-rails (2.14.1)
+      actionpack (>= 3.0)
+      activemodel (>= 3.0)
+      activesupport (>= 3.0)
+      railties (>= 3.0)
+      rspec-core (~> 2.14.0)
+      rspec-expectations (~> 2.14.0)
+      rspec-mocks (~> 2.14.0)
+    shortcode (0.1.2)
+      haml (~> 4.0)
+      parslet (= 1.5.0)
+    slop (3.5.0)
+    sprockets (2.12.0)
+      hike (~> 1.2)
+      multi_json (~> 1.0)
+      rack (~> 1.0)
+      tilt (~> 1.1, != 1.3.0)
+    sprockets-rails (2.0.1)
+      actionpack (>= 3.0)
+      activesupport (>= 3.0)
+      sprockets (~> 2.8)
+    sqlite3 (1.3.9)
+    thor (0.18.1)
+    thread_safe (0.2.0)
+      atomic (>= 1.1.7, < 2)
+    tilt (1.4.1)
+    timers (1.1.0)
+    treetop (1.4.15)
+      polyglot
       polyglot (>= 0.3.1)
-    truncate_html (0.5.1)
-    tzinfo (0.3.27)
-    warden (1.0.4)
-      rack (>= 1.0)
-    will_paginate (3.0.pre2)
+    tzinfo (0.3.39)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
+  byebug
   database_cleaner
   fakeweb
   ffi
   guard-bundler
   guard-rspec
   libnotify
-  rails (= 3.0.7)
-  refinerycms
-  refinerycms-blog
-  refinerycms-wordpress-import!
+  rails (= 4.0.0)
   rmagick
   rspec-rails (>= 2.6.0)
+  shortcode (= 0.1.2)
   sqlite3
+  wordpress-import!

Guardfile

@@ -1,6 +1,12 @@
 # A sample Guardfile
 # More info at https://github.com/guard/guard#readme
 
+guard 'bundler' do
+  watch('Gemfile')
+  # Uncomment next line if Gemfile contain `gemspec' command
+  watch(/^.+\.gemspec/)
+end
+
 guard 'rspec', :version => 2 do
   watch(%r{^spec/.+_spec\.rb$})
   watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
@@ -8,19 +14,8 @@ guard 'rspec', :version => 2 do
 
   # Rails example
   watch(%r{^spec/.+_spec\.rb$})
-  watch(%r{^app/(.+)\.rb$})                           { |m| "spec/#{m[1]}_spec.rb" }
   watch(%r{^lib/(.+)\.rb$})                           { |m| "spec/lib/#{m[1]}_spec.rb" }
-  watch(%r{^app/controllers/(.+)_(controller)\.rb$})  { |m| ["spec/routing/#{m[1]}_routing_spec.rb", "spec/#{m[2]}s/#{m[1]}_#{m[2]}_spec.rb", "spec/acceptance/#{m[1]}_spec.rb"] }
   watch(%r{^spec/support/(.+)\.rb$})                  { "spec" }
   watch('spec/spec_helper.rb')                        { "spec" }
-  watch('config/routes.rb')                           { "spec/routing" }
-  watch('app/controllers/application_controller.rb')  { "spec/controllers" }
-  # Capybara request specs
-  watch(%r{^app/views/(.+)/.*\.(erb|haml)$})          { |m| "spec/requests/#{m[1]}_spec.rb" }
 end
 
-guard 'bundler' do
-  watch('Gemfile')
-  # Uncomment next line if Gemfile contain `gemspec' command
-  watch(/^.+\.gemspec/)
-end

MIT-LICENSE

@@ -1,4 +1,5 @@
-Copyright 2011 YOURNAME
+Copyright 2014 Will Bradley
+portions Copyright 2011 Marc Remolt
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

README.rdoc

@@ -1,31 +1,32 @@
-= Refinerycms-wordpress-import
+= Wordpress-import
 
-This litte project is an importer for WordPress XML dumps into refinerycms(-blog). 
+This little project is an importer for WordPress XML dumps into Rails.
 
-You can find the source code on github: https://github.com/mremolt/refinerycms-wordpress-import
+It's been somewhat customized for one particular project; you probably want to fork this and modify it to fit your app's schema.
+
+It's a fork of Marc Remolt's Refinerycms-wordpress-import ( https://github.com/mremolt/refinerycms-wordpress-import )
+
+You can find the source code on github: https://github.com/zyphlar/wordpress-import
 
 Keep in mind that links to other pages of your blog are just copied, as WordPress exports them as <a>-Tags. 
 If your site (blog) structure uses new urls, the links WILL break! For example, if you used 
 the popular WP blog url structure "YYYY-MM/slug", be warned that Refinery just uses "blog/slug". 
 So your inner site links will point to the old WP url. 
 
-
 == Prerequisites
 
-As refinerycms-wordpress-import is an addon for RefineryCMS, is shares the prerequisites with it.
-So you'll first need a running installation of refinerycms and refinerycms-blog. Make sure
-the site is running, all migrations are run and you created the first refinery user. 
+TODO
 
 
 == Installation
 
 Just add the gem to your projects Gemfile:
 
-  gem 'refinerycms-wordpress-import'
+  gem 'wordpress-import'
 
 Or if you want to stay on the bleeding edge: 
 
-  gem 'refinerycms-wordpress-import', :git => 'git://github.com/mremolt/refinerycms-wordpress-import.git'
+  gem 'wordpress-import', :git => 'git://github.com/zyphlar/wordpress-import.git'
 
 and run
 

Rakefile

@@ -7,7 +7,7 @@ rescue LoadError
 end
 
 require 'rake'
-require 'rdoc/task'
+#require 'rdoc/task'
 
 require 'rspec/core'
 require 'rspec/core/rake_task'
@@ -16,10 +16,10 @@ RSpec::Core::RakeTask.new(:spec)
 
 task :default => :spec
 
-Rake::RDocTask.new(:rdoc) do |rdoc|
-  rdoc.rdoc_dir = 'rdoc'
-  rdoc.title    = 'Refinerycms-wordpress-import'
-  rdoc.options << '--line-numbers' << '--inline-source'
-  rdoc.rdoc_files.include('README.rdoc')
-  rdoc.rdoc_files.include('lib/**/*.rb')
-end
+#RDoc::Task.new(:rdoc) do |rdoc|
+  #rdoc.rdoc_dir = 'rdoc'
+  #rdoc.title    = 'Refinerycms-wordpress-import'
+  #rdoc.options << '--line-numbers' << '--inline-source'
+  #rdoc.rdoc_files.include('README.rdoc')
+  #rdoc.rdoc_files.include('lib/**/*.rb')
+#end

lib/refinerycms-wordpress-import.rb

@@ -1,7 +0,0 @@
-module Refinery
-  module WordPress
-
-  end
-end
-
-require 'wordpress'

lib/tasks/wordpress.rake

@@ -5,86 +5,137 @@ namespace :wordpress do
   task :reset_blog do
     Rake::Task["environment"].invoke
 
-    %w(taggings tags blog_comments blog_categories blog_categories_blog_posts 
-       blog_posts).each do |table_name|
+    %w(posts post_translations taggings tags).each do |table_name|
       p "Truncating #{table_name} ..."
       ActiveRecord::Base.connection.execute "DELETE FROM #{table_name}"
     end
 
   end
 
-  desc "import blog data from a Refinery::WordPress XML dump"
-  task :import_blog, :file_name do |task, params|
+  desc "import blog data from a WordPressImport XML dump"
+  task :import_blog, :file_name, :blog_slug do |task, params|
     Rake::Task["environment"].invoke
-    dump = Refinery::WordPress::Dump.new(params[:file_name])
+    p "Loading XML from #{params[:file_name]} (using blog #{params[:blog_slug]}) ..."
+    dump = WordPressImport::Dump.new(params[:file_name])
 
-    dump.authors.each(&:to_refinery)
+    p "Importing #{dump.authors.count} authors ..."
+    dump.authors.each(&:to_rails)
     
+    # by default, import all; unless $ONLY_PUBLISHED = "true"
     only_published = ENV['ONLY_PUBLISHED'] == 'true' ? true : false
-    dump.posts(only_published).each(&:to_refinery)
+    p "Importing #{dump.posts(only_published).count} posts ..."
     
-    Refinery::WordPress::Post.create_blog_page_if_necessary
-
-    ENV["MODEL"] = 'BlogPost'
-    Rake::Task["friendly_id:redo_slugs"].invoke
-    ENV.delete("MODEL")
+    if only_published
+      p "(only published posts)" 
+    else
+      p "(export ONLY_PUBLISHED=true to import only published posts)"
     end
 
-  desc "reset blog tables and then import blog data from a Refinery::WordPress XML dump"
-  task :reset_and_import_blog, :file_name do |task, params|
+    dump.posts(only_published).each{|p| p.to_rails(params[:blog_slug]) }
+  end
+
+  desc "reset blog tables and then import blog data from a WordPressImport XML dump"
+  task :reset_and_import_blog, :file_name, :blog_slug do |task, params|
     Rake::Task["environment"].invoke
     Rake::Task["wordpress:reset_blog"].invoke
-    Rake::Task["wordpress:import_blog"].invoke(params[:file_name])
+    Rake::Task["wordpress:import_blog"].invoke(params[:file_name], params[:blog_slug])
   end
 
 
-  desc "Reset the cms relevant tables for a clean import"
-  task :reset_pages do
+  desc "download images in posts to public folder"
+  task :download_post_images, :host_match do |task, params|
+    raise "Error: you must specify a host to match for this download (i.e. rake wordpress:download_post_images['mywebsite']" if params[:host_match].blank?
+
     Rake::Task["environment"].invoke
     
-    %w(page_part_translations page_translations page_parts pages).each do |table_name|
-      p "Truncating #{table_name} ..."
-      ActiveRecord::Base.connection.execute "DELETE FROM #{table_name}"
-    end
+    # scrape images
+    @posts = ::Post.all
+    @posts.each do |post|
+      doc = Nokogiri::HTML(post.body)
+      doc.css("img").each do |img|
+        # find remote file path
+        remote_file = img.attributes["src"].text
+        # load uri
+        begin
+          remote_uri = URI(remote_file)
+        rescue => error
+          puts "Error parsing URL #{remote_file}: #{error.message}"
         end
 
-  desc "import cms data from a WordPress XML dump"
-  task :import_pages, :file_name do |task, params|
-    Rake::Task["environment"].invoke
-    dump = Refinery::WordPress::Dump.new(params[:file_name])
+        # only download if the image is a LFA-hosted image
+        if remote_uri && remote_uri.host.match(params[:host_match]) != nil
+          # find a local path for it
+          local_file = File.expand_path(File.join(Rails.public_path,remote_uri.path))
+          # only download if not already there or if it's zero bytes
+          unless File.size?(local_file)
+            # create local folders if necessary
+            dirname = File.dirname(local_file)
+            unless File.directory?(dirname)
+              FileUtils.mkdir_p(dirname)
+            end
+            # save remote file to local
+            begin
+              remote_file_io = open(remote_file)
+              File.open(local_file,'wb'){ |f| f.write(remote_file_io.read) }
+              puts "Saved file: #{local_file}"
+            rescue OpenURI::HTTPError => error
+              puts "Error saving file #{remote_file}: #{error.message}"
+            end
+          end
+        end
+      end
+    end
+    puts "Finished downloding images from #{@posts.count} posts"
 
-    only_published = ENV['ONLY_PUBLISHED'] == 'true' ? true : false
-    dump.pages(only_published).each(&:to_refinery)
-
-    # After all pages are persisted we can now create the parent - child
-    # relationships. This is necessary, as WordPress doesn't dump the pages in
-    # a correct order. 
-    dump.pages(only_published).each do |dump_page|
-      page = ::Page.find(dump_page.post_id)
-      page.parent_id = dump_page.parent_id
-      page.save!
   end
 
-    Refinery::WordPress::Post.create_blog_page_if_necessary
+  # desc "Reset the cms relevant tables for a clean import"
+  # task :reset_pages do
+  #   Rake::Task["environment"].invoke
 
-    ENV["MODEL"] = 'Page'
-    Rake::Task["friendly_id:redo_slugs"].invoke
-    ENV.delete("MODEL")
-  end
+  #   %w(page_part_translations page_translations page_parts pages).each do |table_name|
+  #     p "Truncating #{table_name} ..."
+  #     ActiveRecord::Base.connection.execute "DELETE FROM #{table_name}"
+  #   end
+  # end
 
-  desc "reset cms tables and then import cms data from a WordPress XML dump"
-  task :reset_and_import_pages, :file_name do |task, params|
-    Rake::Task["environment"].invoke
-    Rake::Task["wordpress:reset_pages"].invoke
-    Rake::Task["wordpress:import_pages"].invoke(params[:file_name])
-  end
+  # desc "import cms data from a WordPress XML dump"
+  # task :import_pages, :file_name do |task, params|
+  #   Rake::Task["environment"].invoke
+  #   dump = WordPressImport::Dump.new(params[:file_name])
+
+  #   only_published = ENV['ONLY_PUBLISHED'] == 'true' ? true : false
+  #   dump.pages(only_published).each(&:to_rails)
+
+  #   # After all pages are persisted we can now create the parent - child
+  #   # relationships. This is necessary, as WordPress doesn't dump the pages in
+  #   # a correct order. 
+  #   dump.pages(only_published).each do |dump_page|
+  #     page = ::Page.find(dump_page.post_id)
+  #     page.parent_id = dump_page.parent_id
+  #     page.save!
+  #   end
+
+  #   WordPressImport::Post.create_blog_page_if_necessary
+        
+  #   ENV["MODEL"] = 'Page'
+  #   Rake::Task["friendly_id:redo_slugs"].invoke
+  #   ENV.delete("MODEL")
+  # end
+  
+  # desc "reset cms tables and then import cms data from a WordPress XML dump"
+  # task :reset_and_import_pages, :file_name do |task, params|
+  #   Rake::Task["environment"].invoke
+  #   Rake::Task["wordpress:reset_pages"].invoke
+  #   Rake::Task["wordpress:import_pages"].invoke(params[:file_name])
+  # end
 
 
   desc "Reset the media relevant tables for a clean import"
   task :reset_media do
     Rake::Task["environment"].invoke
 
-    %w(images resources).each do |table_name|
+    %w(rich_rich_files).each do |table_name|
       p "Truncating #{table_name} ..."
       ActiveRecord::Base.connection.execute "DELETE FROM #{table_name}"
     end
@@ -93,14 +144,27 @@ namespace :wordpress do
   desc "import media data (images and files) from a WordPress XML dump and replace target URLs in pages and posts"
   task :import_and_replace_media, :file_name do |task, params|
     Rake::Task["environment"].invoke
-    dump = Refinery::WordPress::Dump.new(params[:file_name])
+    dump = WordPressImport::Dump.new(params[:file_name])
     
-    attachments = dump.attachments.each(&:to_refinery)
+    p "Importing #{dump.attachments.each_slice(200).first.count} attachments ..."
+    attachments = dump.attachments.each_slice(200).first.each(&:to_rails)
+    unless $ATTACHMENT_EXCEPTIONS.blank?
+      p "----------------------------------------------------------"
+      p "ERRORS WERE ENCOUNTERED IMPORTING ATTACHMENTS:" 
+      $ATTACHMENT_EXCEPTIONS.each{|exception| puts exception}
+      p "----------------------------------------------------------"
+    end
     
-    # parse all created BlogPost and Page bodys and replace the old wordpress media uls 
+    # parse all created Post and Page bodys and replace the old wordpress media urls 
     # with the newly created ones
-    attachments.each do |attachment|
-      attachment.replace_url
+    p "Replacing attachment URLs found in posts/pages ..."
+    attachments.each(&:replace_url)
+
+    unless $REPLACEMENT_EXCEPTIONS.blank?
+      p "----------------------------------------------------------"
+      p "ERRORS WERE ENCOUNTERED REPLACING ATTACHMENTS:" 
+      $REPLACEMENT_EXCEPTIONS.each{|exception| puts exception}
+      p "----------------------------------------------------------"
     end
   end
 
@@ -112,10 +176,12 @@ namespace :wordpress do
   end
 
   desc "reset and import all data (see the other tasks)"
-  task :full_import, :file_name do |task, params|
+  task :full_import, :file_name, :blog_slug do |task, params|
     Rake::Task["environment"].invoke
-    Rake::Task["wordpress:reset_and_import_blog"].invoke(params[:file_name])
-    Rake::Task["wordpress:reset_and_import_pages"].invoke(params[:file_name])
-    Rake::Task["wordpress:reset_import_and_replace_media"].invoke(params[:file_name])
+    Rake::Task["wordpress:reset_and_import_blog"].invoke(params[:file_name],params[:blog_slug])
+    #Rake::Task["wordpress:reset_and_import_pages"].invoke(params[:file_name])
+    #Rake::Task["wordpress:reset_import_and_replace_media"].invoke(params[:file_name])
+    Rake::Task["wordpress:import_and_replace_media"].invoke(params[:file_name])
   end
+
 end

lib/wordpress-import.rb

@@ -0,0 +1,5 @@
+module WordPressImport
+
+end
+
+require 'wordpress'

lib/wordpress.rb

@@ -1,8 +1,8 @@
 require 'nokogiri'
 require "wordpress/railtie" 
+require 'shortcode'
 
-module Refinery
-  module WordPress
+module WordPressImport
 autoload :Author, 'wordpress/author' 
 autoload :Tag, 'wordpress/tag'
 autoload :Category, 'wordpress/category'
@@ -12,5 +12,4 @@ module Refinery
 autoload :Dump, 'wordpress/dump'
 autoload :Attachment, 'wordpress/attachment'
 end
-end
 

lib/wordpress/attachment.rb

@@ -1,9 +1,8 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Attachment
     attr_reader :node
-      attr_reader :refinery_image
-      attr_reader :refinery_resource
+    attr_reader :paperclip_image
+    attr_reader :paperclip_file
 
     def initialize(node)
       @node = node
@@ -41,44 +40,91 @@ module Refinery
       url.match /\.(png|jpg|jpeg|gif)$/ 
     end
 
-      def to_refinery
+    def to_rails
+      begin
         if image?
           to_image
         else
-          to_resource
+          to_file
+        end
+      rescue StandardError => ex
+        message = "ERROR saving attachment #{url} -- #{ex.message}"
+        p message
+        $ATTACHMENT_EXCEPTIONS = [] if $ATTACHMENT_EXCEPTIONS.blank?
+        $ATTACHMENT_EXCEPTIONS << message
+        return nil
       end
     end
 
     def replace_url
+      begin
+        @occurrance_count = 0
         if image?
           replace_image_url
         else
           replace_resource_url
         end
+        p "Replaced #{@occurrance_count} occurrances of #{url}"
+      rescue StandardError => ex
+        message = "ERROR replacing URL #{url} -- #{ex.message}"
+        p message
+        $REPLACEMENT_EXCEPTIONS = [] if $REPLACEMENT_EXCEPTIONS.blank?
+        $REPLACEMENT_EXCEPTIONS << message
+        return nil
+      end
     end
 
     private
 
-      def to_image
-        image = ::Image.new
-        image.created_at = post_date
-        image.image_url = url
-        image.save!
+    def rich_file_clean_file_name(full_file_name)
+      extension = File.extname(full_file_name).gsub(/^\.+/, '')
+      filename = full_file_name.gsub(/\.#{extension}$/, '')
 
-        @refinery_image = image
+      filename = CGI::unescape(filename)
+      filename = CGI::unescape(filename)
+
+      extension = extension.downcase
+      filename = filename.downcase.gsub(/[^a-z0-9]+/i, '-')
+
+      "#{filename}.#{extension}"
+    end
+
+    def to_image
+      # avoid duplicates; use our storage system's filename cleaner for lookup
+      image = ::Rich::RichFile.find_or_initialize_by(rich_file_file_name: rich_file_clean_file_name(file_name))
+
+      if image.rich_file.instance.id.blank?
+        p "Importing image #{file_name}"
+        image.simplified_type = "image"
+        image.created_at = post_date
+        image.rich_file = URI.parse(url)
+        image.save!
+      else
+        p "image #{file_name} already exists..."
+      end
+
+      @paperclip_image = image
       image
     end
 
-      def to_resource
-        resource = ::Resource.new
-        resource.created_at = post_date
-        resource.file_url = url
-        resource.save!
+    def to_file
+      # avoid duplicates; use our storage system's filename cleaner for lookup
+      file = ::Rich::RichFile.find_or_initialize_by(rich_file_file_name: rich_file_clean_file_name(file_name))
 
-        @refinery_resource = resource
-        resource
+      if file.rich_file.instance.id.blank?
+        p "Importing file #{file_name}"
+        file.created_at = post_date
+        file.rich_file = URI.parse(url) if file.rich_file.blank?
+        file.save!
+      else
+        p "file #{file_name} already exists..."
       end
 
+      @paperclip_file = file
+      file
+    end
+
+
     def replace_image_url
       replace_image_url_in_blog_posts
       replace_image_url_in_pages
@@ -90,24 +136,25 @@ module Refinery
     end
 
     def replace_image_url_in_blog_posts
-        replace_url_in_blog_posts(refinery_image.image.url)
+      replace_url_in_blog_posts(paperclip_image.rich_file.url)
     end
     
     def replace_image_url_in_pages
-        replace_url_in_pages(refinery_image.image.url)
+      replace_url_in_pages(paperclip_image.rich_file.url)
     end
 
     def replace_resource_url_in_blog_posts
-        replace_url_in_blog_posts(refinery_resource.file.url)
+      replace_url_in_blog_posts(paperclip_file.rich_file.url)
     end
     
     def replace_resource_url_in_pages
-        replace_url_in_pages(refinery_resource.file.url)
+      replace_url_in_pages(paperclip_file.rich_file.url)
     end
 
     def replace_url_in_blog_posts(new_url)
-        ::BlogPost.all.each do |post|
+      ::Post.all.each do |post|
         if (! post.body.empty?) && post.body.include?(url)
+          @occurrance_count += 1
           post.body = post.body.gsub(url_pattern, new_url)
           post.save!
         end
@@ -116,15 +163,17 @@ module Refinery
 
     def replace_url_in_pages(new_url)
       ::Page.all.each do |page|
-          page.parts.each do |part|
-            if (! part.body.to_s.blank?) && part.body.include?(url)
-              part.body = part.body.gsub(url_pattern, new_url)
+        page.translations.each do |translation|
+          translation.parts.each do |part|
+            if (! part.content.to_s.blank?) && part.content.include?(url)
+              @occurrance_count += 1
+              part.content = part.content.gsub(url_pattern, new_url)
               part.save!
             end
           end
         end
       end
+    end
 
   end
 end
-end

lib/wordpress/author.rb

@@ -1,5 +1,4 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Author
     attr_reader :author_node
 
@@ -7,6 +6,12 @@ module Refinery
       @author_node = author_node
     end
 
+    def name
+      name = author_node.xpath("wp:author_display_name").text
+      name = author_node.xpath("wp:author_first_name").text + " " + author_node.xpath("wp:author_first_name").text if name.blank?
+      name
+    end
+
     def login
       author_node.xpath("wp:author_login").text
     end
@@ -23,15 +28,20 @@ module Refinery
       "WordPress::Author: #{login} <#{email}>"
     end
 
-      def to_refinery
-        user = User.find_or_initialize_by_username_and_email(login, email)
+    def to_rails
+      user = ::User.find_or_initialize_by_email(email)
+      user.wp_username = login
+
       unless user.persisted?
+        user.name = name
         user.password = 'password'
         user.password_confirmation = 'password'
-          user.save
       end
+      user.save
+
+      puts "User #{login} imported."
+
       user
     end
   end
 end
-end

lib/wordpress/category.rb

@@ -1,5 +1,4 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Category
     attr_accessor :name
 
@@ -11,9 +10,8 @@ module Refinery
       name == other.name
     end
 
-      def to_refinery
-        BlogCategory.find_or_create_by_title(name)
-      end
+    def to_rails
+      Tag.find_or_create_by_title(name)
     end
   end
 end

lib/wordpress/comment.rb

@@ -1,5 +1,4 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Comment
     attr_reader :node
 
@@ -45,4 +44,3 @@ module Refinery
     end
   end
 end
-end

lib/wordpress/dump.rb

@@ -1,16 +1,22 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Dump
     attr_reader :doc
 
     def initialize(file_name)
-        file_name = File.absolute_path(file_name)
-
-        raise "Given file '#{file_name}' no file or not readable." \
-          unless File.file?(file_name) && File.readable?(file_name)
+      begin
+        file_name = File.expand_path(file_name)
+        raise "error" unless File.file?(file_name) && File.readable?(file_name)
+      rescue
+        raise "Given file '#{file_name}' is not a file or not readable. Rake tasks take filename arguments like this: rake wordpress:full_import['/path/to/my_file']"
+      end
       
       file = File.open(file_name)
-        @doc = Nokogiri::XML(file)
+      
+      if file.size >= 10485760 # 10MB
+        puts "WARNING: LibXML by default supports 10MB max file size. On some systems your file will be silently truncated; on others, an error will be raised. Consider splitting your file into smaller chunks and running rake tasks individually (authors, then blog/pages, then media), and double-check the import results."
+      end
+
+      @doc = Nokogiri::XML(file.read().gsub("\u0004", "")) # get rid of all EOT characters
     end
 
     def authors
@@ -55,4 +61,3 @@ module Refinery
     end
   end
 end
-end

lib/wordpress/page.rb

@@ -1,5 +1,4 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Page
     include ::ActionView::Helpers::TagHelper
     include ::ActionView::Helpers::TextHelper
@@ -14,6 +13,10 @@ module Refinery
       "WordPress::Page(#{post_id}): #{title}"     
     end
 
+    def link
+      node.xpath("link").text
+    end
+
     def title
       node.xpath("title").text
     end
@@ -23,7 +26,7 @@ module Refinery
     end
 
     def content_formatted
-        formatted = format_syntax_highlighter(format_paragraphs(content))
+      formatted = format_shortcodes(format_syntax_highlighter(format_paragraphs(content)))
 
       # remove all tags inside <pre> that simple_format created
       # TODO: replace format_paragraphs with a method, that ignores pre-tags
@@ -39,7 +42,15 @@ module Refinery
     end
 
     def post_date
-        DateTime.parse node.xpath("wp:post_date").text
+      Time.parse node.xpath("wp:post_date").text
+    end
+
+    def publish_date
+      Time.parse node.xpath("pubDate").text
+    end
+
+    def post_name
+      node.xpath("wp:post_name").text
     end
 
     def post_id
@@ -67,12 +78,20 @@ module Refinery
       post_id == other.post_id
     end
 
-      def to_refinery
-        page = ::Page.create!(:id => post_id, :title => title, 
-          :created_at => post_date, :draft => draft?)
+    #NEED:
+    # creator ->  "user_id"
+    # wp:post_name ->   "slug"
+    # pubDate -> "published_at"
+    #OK:
+    # title      ->  "title"
+    # content:encoded ->     "body"
+    # wp:post_date_gmt -> "created_at"
 
-        page.parts.create(:title => 'Body', :body => content_formatted)
-        page
+    def to_rails
+      # :user_id => creator
+      page = ::Page.create!(:id => post_id, :title => title, 
+        :created_at => post_date, :slug => post_name, 
+        :published_at => publish_date, :body => content_formatted)
     end
 
     private 
@@ -84,8 +103,8 @@ module Refinery
       text = ''.html_safe if text.nil?
       start_tag = tag('p', html_options, true)
       
-        text.gsub!(/\r\n?/, "\n")                    # \r\n and \r -> \n
-        text.gsub!(/\n\n+/, "</p>\n\n#{start_tag}")  # 2+ newline  -> paragraph
+      text.gsub!(/\n\n+/, "</p>#{start_tag}")  # 2+ newline  -> paragraph
+      text.gsub!(/\r?\n/, "<br/>\n")               # \r\n and \n -> line break (must be after the paragraph detection to avoid <br/><br/>)
       text.insert 0, start_tag
 
       text.html_safe.safe_concat("</p>")
@@ -102,6 +121,24 @@ module Refinery
       # -> <pre class="brush: ruby">p "Hello world"</pre> 
       text.gsub(/\[(\w+)\](.+?)\[\/\1\]/m, '<pre class="brush: \1">\2</pre>')
     end
+
+    # Replace Wordpress shortcodes with formatted HTML (see shortcode gem and support/templates folder)
+    def format_shortcodes(text)
+      Shortcode.setup do |config|
+        # the template parser to use
+        config.template_parser = :haml # :erb or :haml supported, :haml is default
+
+         # location of the template files
+        config.template_path = ::File.join(::File.dirname(__FILE__), "..", "..","support/templates/haml")
+
+        # a list of block tags to support e.g. [quote]Hello World[/quote]
+        config.block_tags = [:caption, :column]
+
+        # a list of self closing tags to support e.g. [youtube id="12345"]
+        config.self_closing_tags = [:end_columns, "google-map-v3"]
+      end
+
+      Shortcode.process(text)
     end
   end
 end

lib/wordpress/post.rb

@@ -1,5 +1,4 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Post < Page
     def tags
       # xml dump has "post_tag" for wordpress 3.1 and "tag" for 3.0
@@ -30,56 +29,39 @@ module Refinery
       end
     end
 
-      def to_refinery
-        user = ::User.find_by_username(creator) || ::User.first
-        raise "Referenced User doesn't exist! Make sure the authors are imported first." \
-          unless user
+    # blog_slug is used to identify which blog this import is from
+    def to_rails(blog_slug)
 
-        begin
-          post = ::BlogPost.new :title => title, :body => content_formatted, 
-            :draft => draft?, :published_at => post_date, :created_at => post_date, 
-            :author => user, :tag_list => tag_list
-          post.save!
+      user = ::User.find_by_wp_username(creator)
 
-          ::BlogPost.transaction do
-            categories.each do |category|
-              post.categories << category.to_refinery
+      if user.nil? 
+        raise "User with wp_username #{creator} not found"
       end
 
-            comments.each do |comment|
-              comment = comment.to_refinery
-              comment.post = post
-              comment.save
-            end
-          end
-        rescue ActiveRecord::RecordInvalid 
-          # if the title has already been taken (WP allows duplicates here,
-          # refinery doesn't) append the post_id to it, making it unique
-          post.title = "#{title}-#{post_id}"
-          post.save
-        end
+      post = ::Post.create({ 
+        :wp_post_id => post_id, :slug => post_name,
+        :user_id => user.id, :title => title, 
+        :created_at => post_date, 
+        :published_at => publish_date,
+        :wp_link => link,
+        :wp_blog => blog_slug,
+        :translations_attributes => { "0" => {
+            :locale => "en",
+            :title => title,
+            :body => content_formatted,
+            # merge the translation's category list with the wordpress post's
+            :category_list => categories.collect(&:name) | tags.collect(&:name) 
+          }}
+        })
 
-        post
-      end
-
-      def self.create_blog_page_if_necessary
-        # refinerycms wants a page at /blog, so let's make sure there is one
-        # taken from the original db seeds from refinery-blog
-        unless ::Page.where("link_url = ?", '/blog').exists?
-          page = ::Page.create(
-            :title => "Blog",
-            :link_url => "/blog",
-            :deletable => false,
-            :position => ((::Page.maximum(:position, :conditions => {:parent_id => nil}) || -1)+1),
-            :menu_match => "^/blogs?(\/|\/.+?|)$"
-          )
-
-          ::Page.default_parts.each do |default_page_part|
-            page.parts.create(:title => default_page_part, :body => nil)
-          end
+      if post.errors.blank?
+        puts "Post #{post_name} imported."
+        return post.reload
+      else
+        puts post.inspect
+        raise post.errors.full_messages.to_s
       end
     end
 
   end
 end
-end

lib/wordpress/railtie.rb

@@ -1,10 +1,8 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Railtie < Rails::Railtie
     rake_tasks do
       load "tasks/wordpress.rake"
     end
   end
 end
-end
 

lib/wordpress/tag.rb

@@ -1,5 +1,4 @@
-module Refinery
-  module WordPress
+module WordPressImport
   class Tag
     attr_accessor :name
 
@@ -17,4 +16,3 @@ module Refinery
 
   end
 end
-end

refinerycms-wordpress-import.gemspec

@@ -1,23 +0,0 @@
-# Provide a simple gemspec so you can easily use your enginex
-# project in your rails apps through git.
-Gem::Specification.new do |s|
-  s.name        = "refinerycms-wordpress-import"
-  s.summary     = "Import WordPress XML dumps into refinerycms(-blog)."
-  s.description = "This gem imports a WordPress XML dump into refinerycms (Page, User) and refinerycms-blog (BlogPost, BlogCategory, Tag, BlogComment)"
-  s.version     = "0.3.0"
-  s.date        = "2011-06-13"
-
-  s.authors     = ['Marc Remolt']
-  s.email       = 'marc.remolt@googlemail.com'
-  s.homepage    = 'https://github.com/mremolt/refinerycms-wordpress-import'
-  
-  s.add_dependency 'bundler', '~> 1.0'
-  s.add_dependency 'refinerycms', '~> 1.0.0'
-  s.add_dependency 'refinerycms-blog', '~> 1.5.2'
-  s.add_dependency 'nokogiri', '~> 1.4.4'
-
-  s.add_development_dependency 'rspec-rails'
-  s.add_development_dependency 'database_cleaner'
-
-  s.files = Dir["{app,lib,config}/**/*"] + ["MIT-LICENSE", "Rakefile", "Gemfile", "README.rdoc"]
-end

spec/dummy/config/boot.rb

@@ -1,6 +1,3 @@
-require 'yaml'
-YAML::ENGINE.yamler= 'syck'
-
 require 'rubygems'
 gemfile = File.expand_path('../../../../Gemfile', __FILE__)
 

spec/dummy/config/environments/development.rb

@@ -24,4 +24,6 @@ Dummy::Application.configure do
   config.action_dispatch.best_standards_support = :builtin
 end
 
-Refinery.rescue_not_found = false
+Refinery.rescue_not_found = false# When true will use Amazon's Simple Storage Service on your production machine
+# instead of the default file system for resources and images
+Refinery.s3_backend = !(ENV['S3_KEY'].nil? || ENV['S3_SECRET'].nil?)

spec/dummy/config/environments/production.rb

@@ -47,4 +47,6 @@ Dummy::Application.configure do
   # Send deprecation notices to registered listeners
   config.active_support.deprecation = :notify
 end
-Refinery.rescue_not_found = true
+Refinery.rescue_not_found = true# When true will use Amazon's Simple Storage Service on your production machine
+# instead of the default file system for resources and images
+Refinery.s3_backend = !(ENV['S3_KEY'].nil? || ENV['S3_SECRET'].nil?)

spec/dummy/config/environments/test.rb

@@ -33,4 +33,6 @@ Dummy::Application.configure do
   # Print deprecation notices to the stderr
   config.active_support.deprecation = :stderr
 end
-Refinery.rescue_not_found = false
+Refinery.rescue_not_found = false# When true will use Amazon's Simple Storage Service on your production machine
+# instead of the default file system for resources and images
+Refinery.s3_backend = !(ENV['S3_KEY'].nil? || ENV['S3_SECRET'].nil?)

spec/dummy/db/migrate/20110812162202_add_cached_slugs.rb

@@ -0,0 +1,11 @@
+class AddCachedSlugs < ActiveRecord::Migration
+  def self.up
+    add_column :blog_categories, :cached_slug, :string
+    add_column :blog_posts, :cached_slug, :string
+  end
+
+  def self.down
+    remove_column :blog_categories, :cached_slug
+    remove_column :blog_posts, :cached_slug
+  end
+end

spec/dummy/db/migrate/20110812162203_add_custom_url_field_to_blog_posts.rb

@@ -0,0 +1,9 @@
+class AddCustomUrlFieldToBlogPosts < ActiveRecord::Migration
+  def self.up
+    add_column :blog_posts, :custom_url, :string
+  end
+
+  def self.down
+    remove_column :blog_posts, :custom_url
+  end
+end

spec/dummy/db/migrate/20110812162204_add_custom_teaser_field_to_blog_posts.rb

@@ -0,0 +1,10 @@
+class AddCustomTeaserFieldToBlogPosts < ActiveRecord::Migration
+  def self.up
+    add_column :blog_posts, :custom_teaser, :text
+  end
+
+  def self.down
+    remove_column :blog_posts, :custom_teaser
+  end
+end
+

spec/dummy/db/schema.rb

@@ -10,12 +10,13 @@
 #
 # It's strongly recommended to check this file into your version control system.
 
-ActiveRecord::Schema.define(:version => 20110602094445) do
+ActiveRecord::Schema.define(:version => 20110812162204) do
 
   create_table "blog_categories", :force => true do |t|
     t.string   "title"
     t.datetime "created_at"
     t.datetime "updated_at"
+    t.string   "cached_slug"
   end
 
   add_index "blog_categories", ["id"], :name => "index_blog_categories_on_id"
@@ -48,6 +49,9 @@ ActiveRecord::Schema.define(:version => 20110602094445) do
     t.datetime "created_at"
     t.datetime "updated_at"
     t.integer  "user_id"
+    t.string   "cached_slug"
+    t.string   "custom_url"
+    t.text     "custom_teaser"
   end
 
   add_index "blog_posts", ["id"], :name => "index_blog_posts_on_id"

spec/dummy/db/seeds/pages.rb

@@ -1,3 +1,12 @@
+::Page.reset_column_information
+# Check whether all columns are applied yet by seo_meta.
+unless !defined?(::SeoMeta) || ::SeoMeta.attributes.keys.all? { |k|
+  ::Page.translation_class.instance_methods.include?(k)
+}
+  # Make pages model seo_meta because not all columns are accessible.
+  ::Page.translation_class.send :is_seo_meta
+end
+
 page_position = -1
 
 home_page = Page.create(:title => "Home",

spec/lib/wordpress/attachment_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Refinery::WordPress::Attachment, :type => :model do
+describe WordPressImport::Attachment, :type => :model do
   context "an image attchment" do
     let(:attachment) { test_dump.attachments.first }
 

spec/lib/wordpress/author_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Refinery::WordPress::Author, :type => :model do
+describe WordPressImport::Author, :type => :model do
   let(:author) { test_dump.authors.first }
 
   specify { author.login.should == 'admin' }

spec/lib/wordpress/category_spec.rb

@@ -1,15 +1,15 @@
 require 'spec_helper'
 
-describe Refinery::WordPress::Category, :type => :model do
-  let(:category) { Refinery::WordPress::Category.new('Rant') }
+describe WordPressImport::Category, :type => :model do
+  let(:category) { WordPressImport::Category.new('Rant') }
 
   describe "#name" do
     specify { category.name.should == 'Rant' }
   end
 
   describe "#==" do
-    specify { category.should == Refinery::WordPress::Category.new('Rant') }
-    specify { category.should_not == Refinery::WordPress::Category.new('Tutorials') }
+    specify { category.should == WordPressImport::Category.new('Rant') }
+    specify { category.should_not == WordPressImport::Category.new('Tutorials') }
   end
 
   describe "#to_refinery" do

spec/lib/wordpress/dump_spec.rb

@@ -1,10 +1,10 @@
 require 'spec_helper'
 
-describe Refinery::WordPress::Dump, :type => :model do
+describe WordPressImport::Dump, :type => :model do
   let(:dump) { test_dump }
 
   it "should create a Dump object given a xml file" do
-    dump.should be_a Refinery::WordPress::Dump
+    dump.should be_a WordPressImport::Dump
   end
 
   it "should include a Nokogiri::XML object" do
@@ -13,12 +13,12 @@ describe Refinery::WordPress::Dump, :type => :model do
 
   describe "#tags" do
     let(:tags) do
-      [ Refinery::WordPress::Tag.new('css'), Refinery::WordPress::Tag.new('html'),
-        Refinery::WordPress::Tag.new('php'), Refinery::WordPress::Tag.new('ruby')]
+      [ WordPressImport::Tag.new('css'), WordPressImport::Tag.new('html'),
+        WordPressImport::Tag.new('php'), WordPressImport::Tag.new('ruby')]
     end
 
     specify { dump.tags.count == 4 }
-    specify { dump.tags.first.should be_a(Refinery::WordPress::Tag) }
+    specify { dump.tags.first.should be_a(WordPressImport::Tag) }
 
     it "should return all included tags" do
       tags.each do |tag|
@@ -29,12 +29,12 @@ describe Refinery::WordPress::Dump, :type => :model do
 
   describe "#categories" do
     let(:categories) do
-      [ Refinery::WordPress::Category.new('Rant'), Refinery::WordPress::Category.new('Tutorials'),
-       Refinery::WordPress::Category.new('Uncategorized') ]
+      [ WordPressImport::Category.new('Rant'), WordPressImport::Category.new('Tutorials'),
+       WordPressImport::Category.new('Uncategorized') ]
     end
 
     specify { dump.categories.count == 4 }
-    specify { dump.categories.first.should be_a(Refinery::WordPress::Category) }
+    specify { dump.categories.first.should be_a(WordPressImport::Category) }
 
     it "should return all included categories" do
       categories.each do |cat|
@@ -48,7 +48,7 @@ describe Refinery::WordPress::Dump, :type => :model do
       dump.pages.should have(3).pages
     end
 
-    specify { dump.pages.first.should be_a(Refinery::WordPress::Page) }
+    specify { dump.pages.first.should be_a(WordPressImport::Page) }
 
     it "should return only published pages with only_published=true" do
       dump.pages(true).should have(2).pages
@@ -60,7 +60,7 @@ describe Refinery::WordPress::Dump, :type => :model do
       dump.authors.should have(1).author
     end
 
-    specify { dump.authors.first.should be_a(Refinery::WordPress::Author) }
+    specify { dump.authors.first.should be_a(WordPressImport::Author) }
   end
 
   describe "#posts" do
@@ -68,7 +68,7 @@ describe Refinery::WordPress::Dump, :type => :model do
       dump.posts.should have(3).posts
     end
 
-    specify { dump.posts.first.should be_a(Refinery::WordPress::Post) }
+    specify { dump.posts.first.should be_a(WordPressImport::Post) }
 
     it "should return only published posts with only_published=true" do
       dump.posts(true).should have(2).posts
@@ -80,6 +80,6 @@ describe Refinery::WordPress::Dump, :type => :model do
       dump.attachments.should have(2).attachments
     end
 
-    specify { dump.attachments.first.should be_a(Refinery::WordPress::Attachment) }
+    specify { dump.attachments.first.should be_a(WordPressImport::Attachment) }
   end
 end

spec/lib/wordpress/page_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Refinery::WordPress::Page, :type => :model do
+describe WordPressImport::Page, :type => :model do
   let(:dump) { test_dump }
 
   let(:page) { test_dump.pages.last }

spec/lib/wordpress/post_spec.rb

@@ -1,6 +1,6 @@
 require 'spec_helper'
 
-describe Refinery::WordPress::Post, :type => :model do
+describe WordPressImport::Post, :type => :model do
   let(:post) { test_dump.posts.last }
 
    specify { post.title.should == 'Third blog post' }
@@ -17,15 +17,15 @@ describe Refinery::WordPress::Post, :type => :model do
 
   describe "#categories" do
      specify { post.categories.should have(1).category }
-     specify { post.categories.first.should == Refinery::WordPress::Category.new('Rant') }
+     specify { post.categories.first.should == WordPressImport::Category.new('Rant') }
   end
 
   describe "#tags" do
      specify { post.tags.should have(3).tags }
 
-     specify { post.tags.should include(Refinery::WordPress::Tag.new('css')) }
-     specify { post.tags.should include(Refinery::WordPress::Tag.new('html')) }
-     specify { post.tags.should include(Refinery::WordPress::Tag.new('php')) }
+     specify { post.tags.should include(WordPressImport::Tag.new('css')) }
+     specify { post.tags.should include(WordPressImport::Tag.new('html')) }
+     specify { post.tags.should include(WordPressImport::Tag.new('php')) }
   end
 
    specify { post.tag_list.should == 'css,html,php' }
@@ -63,6 +63,7 @@ describe Refinery::WordPress::Post, :type => :model do
           @comment.body.should == comment.content
           @comment.state.should == 'approved'
           @comment.created_at.should == comment.date
+          @comment.created_at.should == comment.date
         end
       end
     end
@@ -81,14 +82,11 @@ describe Refinery::WordPress::Post, :type => :model do
 
       specify { BlogPost.should have(1).record }
 
-      it "should copy the attributes from Refinery::WordPress::Post" do
-        @post.title.should == post.title
-        @post.body.should == post.content_formatted
-        @post.draft.should == post.draft?
-        @post.published_at.should == post.post_date
-        @post.created_at.should == post.post_date
-        @post.author.username.should == post.creator
-      end
+      specify { @post.title.should == post.title }
+      specify { @post.body.should == post.content_formatted }
+      specify { @post.draft.should == post.draft? }
+      specify { @post.published_at.should == post.post_date }
+      specify { @post.author.username.should == post.creator }
 
       it "should assign a category for each Refinery::WordPress::Category" do
         @post.categories.should have(post.categories.count).records

spec/lib/wordpress/tag_spec.rb

@@ -1,15 +1,15 @@
 require 'spec_helper'
 
-describe Refinery::WordPress::Tag, :type => :model do
-  let(:tag) { Refinery::WordPress::Tag.new('ruby') }
+describe WordPressImport::Tag, :type => :model do
+  let(:tag) { WordPressImport::Tag.new('ruby') }
 
   describe "#name" do
     specify { tag.name.should == 'ruby' }
   end
 
   describe "#==" do
-    specify { tag.should == Refinery::WordPress::Tag.new('ruby') }
-    specify { tag.should_not == Refinery::WordPress::Tag.new('php') }
+    specify { tag.should == WordPressImport::Tag.new('ruby') }
+    specify { tag.should_not == WordPressImport::Tag.new('php') }
   end
 
   describe "#to_refinery" do

spec/refinerycms_wordpress_import_spec.rb

@@ -1,7 +0,0 @@
-require 'spec_helper'
-
-describe Refinery::WordPress do
-  it "should be valid" do
-    Refinery::WordPress.should be_a(Module)
-  end
-end

spec/support/helpers.rb

@@ -1,11 +1,11 @@
-module Refinery::WordPress::SpecHelpers
+module WordPressImport::SpecHelpers
   def test_dump
-    file_name = File.realpath(File.join(File.dirname(__FILE__), '../fixtures/wordpress_dump.xml'))
-    Refinery::WordPress::Dump.new(file_name) 
+    file_name = File.expand_path(File.join(File.dirname(__FILE__), '../fixtures/wordpress_dump.xml'))
+    WordPressImport::Dump.new(file_name) 
   end
 end
 
 RSpec.configure do |config|
-  config.include Refinery::WordPress::SpecHelpers
+  config.include WordPressImport::SpecHelpers
 end
 

spec/wordpress_import_spec.rb

@@ -0,0 +1,7 @@
+require 'spec_helper'
+
+describe WordPressImport do
+  it "should be valid" do
+   WordPressImport.should be_a(Module)
+  end
+end

support/templates/haml/caption.haml

@@ -0,0 +1,24 @@
+-# disabling style_hash for now; setting the width = width+10 doesn't seem to actually be a good thing
+-# style_hash = {:style => "width: #{@attributes[:width].to_i+10}px"} unless @attributes[:width].blank?
+- figure_hash = {:class => @attributes[:align], :id => @attributes[:id]}
+-# figure_hash = figure_hash.merge(style_hash) if style_hash
+- content_image = Nokogiri::HTML(@content).css("img").to_html
+- content_caption = Nokogiri::HTML(@content).text + " #{@attributes[:caption]}"
+- @content = "#{content_image} <figcaption>#{content_caption}</figcaption>" unless content_image.blank?
+%figure{figure_hash}= @content
+
+-# sample wordpress-y css to go along with this html:
+  figure {
+    background: #f1f1f1;
+    margin-bottom: 20px;
+    padding: 4px;
+    text-align: center;
+  }
+  figure img {
+    margin: 5px 5px 0;
+  }
+  figure figcaption {
+    color: #777;
+    font-size: 12px;
+    margin: 5px 5px 24px; 
+  }

support/templates/haml/column.haml

@@ -0,0 +1,4 @@
+.post_column_1{:style =>"width:#{@attributes[:width]}; float: left; padding: #{@attributes[:padding]} 6% #{@attributes[:padding]} #{@attributes[:padding]}; display: inline;"}= @content
+
+-#[column width="47%" padding="0"] foo [/column]
+-# <div class="post_column_1">

support/templates/haml/end_columns.haml

@@ -0,0 +1 @@
+<div style="clear: both;"></div>

support/templates/haml/google-map-v3.haml

@@ -0,0 +1,37 @@
+- addmarkerlist = @attributes[:addmarkerlist].to_s || ""
+
+- name = addmarkerlist.split("{}").last
+- uri_name = URI::encode(name)
+- uri_address = URI::encode(addmarkerlist.split("{}").first)
+
+-# google will open up the business page if we pass it a name
+- uri_address = "#{uri_name},%20#{uri_address}" unless (uri_name == uri_address || name.blank?) 
+
+- gmaps_url = "https://maps.google.com/maps/?q=#{uri_address}&ie=UTF8&t=m"
+<iframe src="#{gmaps_url}&amp;output=embed" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" width="#{@attributes[:width]}" height="#{@attributes[:height]}"></iframe>
+<small>View <a href="#{gmaps_url}">#{name}</a> in a larger map</small>
+
+
+-# [google-map-v3 width="425" 
+  height="350" 
+  zoom="12" 
+  maptype="roadmap" 
+  mapalign="left" 
+  directionhint="false" 
+  language="default" 
+  poweredby="false" 
+  maptypecontrol="true" 
+  pancontrol="true" 
+  zoomcontrol="true" 
+  scalecontrol="true" 
+  streetviewcontrol="true" 
+  scrollwheelcontrol="false" 
+  draggable="true" 
+  tiltfourtyfive="false" 
+  addmarkermashupbubble="false" 
+  addmarkermashupbubble="false" 
+  addmarkerlist="#1 Dream Manor Dr Globe, AZ{}1-default.png{}Dream Manor Inn" 
+  bubbleautopan="true" 
+  showbike="false" 
+  showtraffic="false" 
+  showpanoramio="false"]

wordpress-import.gemspec

@@ -0,0 +1,22 @@
+# Provide a simple gemspec so you can easily use your enginex
+# project in your rails apps through git.
+Gem::Specification.new do |s|
+  s.name        = "wordpress-import"
+  s.summary     = "Import WordPress XML dumps into your Ruby on Rails app."
+  s.description = "This gem imports a WordPress XML dump into Rails (Page, User, BlogPost, BlogCategory, Tag, BlogComment)"
+  s.version     = "0.4.4"
+  s.date        = "2014-03-17"
+
+  s.authors     = ['Will Bradley']
+  s.email       = 'bradley.will@gmail.com'
+  s.homepage    = 'https://github.com/zyphlar/wordpress-import'
+
+  s.add_dependency 'bundler', '~> 1.0'
+  s.add_dependency 'nokogiri', '~> 1.6.0'
+  s.add_dependency 'shortcode', '~> 0.1.1'
+
+  s.add_development_dependency 'rspec-rails'
+  s.add_development_dependency 'database_cleaner'
+
+  s.files = Dir["{app,lib,config}/**/*"] + ["MIT-LICENSE", "Rakefile", "Gemfile", "README.rdoc"]
+end