refinerycms-wordpress-import 0.2.0 → 0.3.0

data/Gemfile

@@ -3,9 +3,17 @@ source "http://rubygems.org"
 gem "rails", "3.0.7"
 #gem "capybara", ">= 1.0.0.beta1"
 gem "sqlite3"
+gem "rmagick"
 
-gem "rspec-rails", ">= 2.6.0"
-gem "database_cleaner"
+group :development, :test do
+  gem "rspec-rails", ">= 2.6.0"
+  gem "database_cleaner"
+  gem 'guard-rspec'
+  gem 'ffi'
+  gem 'guard-bundler'
+  gem 'libnotify' if  RUBY_PLATFORM =~ /linux/i
+  gem 'fakeweb'
+end
 
 # To use debugger (ruby-debug for Ruby 1.8.7+, ruby-debug19 for Ruby 1.9.2+)
 # gem 'ruby-debug'

data/README.rdoc

@@ -4,10 +4,7 @@ This litte project is an importer for WordPress XML dumps into refinerycms(-blog
 
 You can find the source code on github: https://github.com/mremolt/refinerycms-wordpress-import
 
-Keep in mind, this gem imports blog posts and pages, NOT the media files, as they are not
-part of the XML dump! You have to manually readd them to Refinery. 
-
-The same goes for links to other pages on your site. WordPress exports them just as <a>-Tags. 
+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. 
@@ -84,6 +81,39 @@ If you want to clean the tables and import in one task:
 
   rake wordpress:reset_and_import_pages[file_name]
 
+Finally, if you want to reset and import all data including media (see below):
+
+  rake wordpress:full_import[file_name]
+
+
+== Importing media files
+
+The WP XML dump contains absolute links to media files linked inside posts, like:
+
+www.mysite.com/wordpress/wp-content/uploads/2011/05/cv.txt
+
+The dump does NOT contain the files itself! To get them imported, this gem downloads the files 
+from the given URL and imports them to refinery. So for a working media import the old site with
+the media URLs must still be online. 
+
+After importing the files, this gem replaces the old links in pages and blog posts with the 
+new generated ones. It parses all existing records searching for the right pattern. That
+means, you have to import pages and posts FIRST to get the URLs replaced. 
+
+Now to the rake tasks for media import: 
+
+  rake wordpress:reset_media
+
+This task deletes all data from the media tables (images and resources), ensuring a clean import.
+
+  rake wordpress:import_and_replace_media[file_name] 
+
+This task imports all the WordPress media into Refinery. After the import it parses all
+pages and blog posts, replacing the legacy links with the current refinery ones.
+
+If you want to clean the tables and import in one task:
+
+  rake wordpress:reset_import_and_replace_media[file_name] 
 
 == Usage on ZSH
 

data/lib/tasks/wordpress.rake

@@ -48,7 +48,7 @@ namespace :wordpress do
     end
   end
 
-  desc "import cms data from a Refinery::WordPress XML dump"
+  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])
@@ -72,10 +72,50 @@ namespace :wordpress do
     ENV.delete("MODEL")
   end
   
-  desc "reset cms tables and then import cms data from a Refinery::WordPress XML dump"
+  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|
+      p "Truncating #{table_name} ..."
+      ActiveRecord::Base.connection.execute "DELETE FROM #{table_name}"
+    end
+  end
+
+  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])
+    
+    attachments = dump.attachments.each(&:to_refinery)
+    
+    # parse all created BlogPost and Page bodys and replace the old wordpress media uls 
+    # with the newly created ones
+    attachments.each do |attachment|
+      attachment.replace_url
+    end
+  end
+
+  desc "reset media tables and then import media data from a WordPress XML dump"
+  task :reset_import_and_replace_media, :file_name do |task, params|
+    Rake::Task["environment"].invoke
+    Rake::Task["wordpress:reset_media"].invoke
+    Rake::Task["wordpress:import_and_replace_media"].invoke(params[:file_name])
+  end
+
+  desc "reset and import all data (see the other tasks)"
+  task :full_import, :file_name 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])
+  end
 end

data/lib/wordpress.rb

@@ -1,15 +1,16 @@
+require 'nokogiri'
+require "wordpress/railtie" 
+
 module Refinery
   module WordPress
+    autoload :Author, 'wordpress/author' 
+    autoload :Tag, 'wordpress/tag'
+    autoload :Category, 'wordpress/category'
+    autoload :Page, 'wordpress/page'
+    autoload :Post, 'wordpress/post'
+    autoload :Comment, 'wordpress/comment'
+    autoload :Dump, 'wordpress/dump'
+    autoload :Attachment, 'wordpress/attachment'
   end
 end
 
-require 'nokogiri'
-require 'wordpress/author'
-require 'wordpress/tag'
-require 'wordpress/category'
-require 'wordpress/page'
-require 'wordpress/post'
-require 'wordpress/comment'
-require 'wordpress/dump'
-
-require "wordpress/railtie" 

data/lib/wordpress/attachment.rb

@@ -0,0 +1,130 @@
+module Refinery
+  module WordPress
+    class Attachment
+      attr_reader :node
+      attr_reader :refinery_image
+      attr_reader :refinery_resource
+
+      def initialize(node)
+        @node = node
+      end
+
+      def title
+        node.xpath("title").text
+      end
+
+      def description
+        node.xpath("description").text
+      end
+
+      def file_name
+        url.split('/').last
+      end
+
+      def post_date
+        DateTime.parse node.xpath("wp:post_date").text
+      end
+
+      def url
+        node.xpath("wp:attachment_url").text
+      end
+
+      def url_pattern
+        url_parts = url.split('.')
+        extension = url_parts.pop
+        url_without_extension = url_parts.join('.')
+
+        /#{url_without_extension}(-\d+x\d+)?\.#{extension}/
+      end
+
+      def image?
+        url.match /\.(png|jpg|jpeg|gif)$/ 
+      end
+
+      def to_refinery
+        if image?
+          to_image
+        else
+          to_resource
+        end
+      end
+
+      def replace_url
+        if image?
+          replace_image_url
+        else
+          replace_resource_url
+        end
+      end
+
+      private
+
+      def to_image
+        image = ::Image.new
+        image.created_at = post_date
+        image.image_url = url
+        image.save!
+
+        @refinery_image = image
+        image
+      end
+
+      def to_resource
+        resource = ::Resource.new
+        resource.created_at = post_date
+        resource.file_url = url
+        resource.save!
+
+        @refinery_resource = resource
+        resource
+      end
+
+      def replace_image_url
+        replace_image_url_in_blog_posts
+        replace_image_url_in_pages
+      end
+
+      def replace_resource_url
+        replace_resource_url_in_blog_posts
+        replace_resource_url_in_pages
+      end
+
+      def replace_image_url_in_blog_posts
+        replace_url_in_blog_posts(refinery_image.image.url)
+      end
+      
+      def replace_image_url_in_pages
+        replace_url_in_pages(refinery_image.image.url)
+      end
+
+      def replace_resource_url_in_blog_posts
+        replace_url_in_blog_posts(refinery_resource.file.url)
+      end
+      
+      def replace_resource_url_in_pages
+        replace_url_in_pages(refinery_resource.file.url)
+      end
+
+      def replace_url_in_blog_posts(new_url)
+        ::BlogPost.all.each do |post|
+          if (! post.body.empty?) && post.body.include?(url)
+            post.body = post.body.gsub(url_pattern, new_url)
+            post.save!
+          end
+        end
+      end
+
+      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)
+              part.save!
+            end
+          end
+        end
+      end
+
+    end
+  end
+end

data/lib/wordpress/dump.rb

@@ -47,6 +47,12 @@ module Refinery
           Category.new(category.text)
         end
       end
+
+      def attachments
+        doc.xpath("//item[wp:post_type = 'attachment']").collect do |attachment|
+          Attachment.new(attachment)
+        end
+      end
     end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: refinerycms-wordpress-import
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,12 +9,12 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-06-05 00:00:00.000000000 +02:00
+date: 2011-06-13 00:00:00.000000000 +02:00
 default_executable: 
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &14624860 !ruby/object:Gem::Requirement
+  requirement: &17167700 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -22,10 +22,10 @@ dependencies:
         version: '1.0'
   type: :runtime
   prerelease: false
-  version_requirements: *14624860
+  version_requirements: *17167700
 - !ruby/object:Gem::Dependency
   name: refinerycms
-  requirement: &14624380 !ruby/object:Gem::Requirement
+  requirement: &17167080 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -33,10 +33,10 @@ dependencies:
         version: 1.0.0
   type: :runtime
   prerelease: false
-  version_requirements: *14624380
+  version_requirements: *17167080
 - !ruby/object:Gem::Dependency
   name: refinerycms-blog
-  requirement: &14623920 !ruby/object:Gem::Requirement
+  requirement: &17166340 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -44,10 +44,10 @@ dependencies:
         version: 1.5.2
   type: :runtime
   prerelease: false
-  version_requirements: *14623920
+  version_requirements: *17166340
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &14623460 !ruby/object:Gem::Requirement
+  requirement: &17165720 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -55,10 +55,10 @@ dependencies:
         version: 1.4.4
   type: :runtime
   prerelease: false
-  version_requirements: *14623460
+  version_requirements: *17165720
 - !ruby/object:Gem::Dependency
   name: rspec-rails
-  requirement: &14623080 !ruby/object:Gem::Requirement
+  requirement: &17142300 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -66,10 +66,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *14623080
+  version_requirements: *17142300
 - !ruby/object:Gem::Dependency
   name: database_cleaner
-  requirement: &14622620 !ruby/object:Gem::Requirement
+  requirement: &17141620 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -77,7 +77,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *14622620
+  version_requirements: *17141620
 description: This gem imports a WordPress XML dump into refinerycms (Page, User) and
   refinerycms-blog (BlogPost, BlogCategory, Tag, BlogComment)
 email: marc.remolt@googlemail.com
@@ -85,17 +85,18 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/wordpress.rb
-- lib/wordpress/page.rb
-- lib/wordpress/author.rb
+- lib/refinerycms-wordpress-import.rb
+- lib/tasks/wordpress.rake
 - lib/wordpress/comment.rb
+- lib/wordpress/attachment.rb
+- lib/wordpress/author.rb
+- lib/wordpress/dump.rb
+- lib/wordpress/page.rb
+- lib/wordpress/category.rb
 - lib/wordpress/post.rb
 - lib/wordpress/railtie.rb
-- lib/wordpress/category.rb
 - lib/wordpress/tag.rb
-- lib/wordpress/dump.rb
-- lib/tasks/wordpress.rake
-- lib/refinerycms-wordpress-import.rb
+- lib/wordpress.rb
 - MIT-LICENSE
 - Rakefile
 - Gemfile