refinerycms-wordpress-import 0.1.0 → 0.2.0

data/README.rdoc

@@ -2,19 +2,31 @@
 
 This litte project is an importer for WordPress XML dumps into refinerycms(-blog). 
 
-So far, only blog-relevant data gets imported, I'm working on the cms pages part. 
-
 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. 
+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. 
 
+
 == Installation
 
-As there is no official release out yet, just add this repos to your projects Gemfile:
+Just add the gem to your projects Gemfile:
+
+  gem 'refinerycms-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'
 
@@ -22,9 +34,10 @@ and run
 
   bundle
 
+
 == Usage
 
-Importing the XML dump is done via 3 rake tasks:
+Importing the XML dump is done via rake tasks:
 
   rake wordpress:reset_blog 
 
@@ -49,6 +62,41 @@ The task will then skip all posts that are not published.
 
 This one combines the two previous tasks. 
 
+If you also want to import the cms part of WordPress, three more rake tasks manage
+the import into RefineryCMS Pages:
+
+  rake wordpress:reset_pages
+
+This task deletes all data from the cms tables, ensuring a clean import. Otherwise existing 
+pages could break the import because of duplicate IDs. 
+
+  rake wordpress:import_pages[file_name] 
+
+This task imports all the WordPress pages into Refinery. The page structure (parent - child)
+is preserved. 
+
+If you want to skip the draft pages, add the ONLY_PUBLISHED parameter to this task, 
+just like with wordpress:import_blog.
+
+  rake wordpress:import_pages[file_name] ONLY_PUBLISHED=true
+
+If you want to clean the tables and import in one task:
+
+  rake wordpress:reset_and_import_pages[file_name]
+
+
+== Usage on ZSH
+
+One more hint for users of zsh (like myself): 
+
+The square brackets following the rake task need to be escaped on zsh, as they have a 
+special meaning there. So the syntax is:
+
+  rake wordpress:reset_and_import_blog\[file_name\]
+
+Ugly, but it works. This is the case for all rake tasks by the way, not just mine. 
+
+
 == Feedback
 
 This is still a very new gem. It manages to import my own blog and a standard WordPress 3.1 dump with some sample posts. 

data/lib/tasks/wordpress.rake

@@ -5,7 +5,8 @@ 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(taggings tags blog_comments blog_categories blog_categories_blog_posts 
+       blog_posts).each do |table_name|
       p "Truncating #{table_name} ..."
       ActiveRecord::Base.connection.execute "DELETE FROM #{table_name}"
     end
@@ -22,12 +23,13 @@ namespace :wordpress do
     only_published = ENV['ONLY_PUBLISHED'] == 'true' ? true : false
     dump.posts(only_published).each(&:to_refinery)
 
+    Refinery::WordPress::Post.create_blog_page_if_necessary
+
     ENV["MODEL"] = 'BlogPost'
     Rake::Task["friendly_id:redo_slugs"].invoke
     ENV.delete("MODEL")
   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|
     Rake::Task["environment"].invoke
@@ -35,4 +37,45 @@ namespace :wordpress do
     Rake::Task["wordpress:import_blog"].invoke(params[:file_name])
   end
 
+
+  desc "Reset the cms relevant tables for a clean import"
+  task :reset_pages do
+    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
+  end
+
+  desc "import cms data from a Refinery::WordPress XML dump"
+  task :import_pages, :file_name do |task, params|
+    Rake::Task["environment"].invoke
+    dump = Refinery::WordPress::Dump.new(params[:file_name])
+
+    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
+        
+    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 Refinery::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
 end

data/lib/wordpress/dump.rb

@@ -19,10 +19,13 @@ module Refinery
         end
       end
 
-      def pages
-        doc.xpath("//item[wp:post_type = 'page']").collect do |page|
+      def pages(only_published=false)
+        pages = doc.xpath("//item[wp:post_type = 'page']").collect do |page|
           Page.new(page)
         end
+
+        pages = pages.select(&:published?) if only_published
+        pages
       end
 
       def posts(only_published=false)

data/lib/wordpress/page.rb

@@ -23,23 +23,10 @@ module Refinery
       end
 
       def content_formatted
-        # WordPress doesn't export <p>-Tags, so let's run a simple_format over
-        # the content. As we trust ourselves, no sanatize.
-        formatted = simple_format(content, {}, { :sanitize => false })
-
-        # Support for SyntaxHighlighter (http://alexgorbatchev.com/SyntaxHighlighter/):
-        # In WordPress you can (via a plugin) enclose code in [lang][/lang]
-        # blocks, which are converted to a <pre>-tag with a class corresponding
-        # to the language.
-        # 
-        # Example:
-        # [ruby]p "Hello World"[/ruby] 
-        # -> <pre class="brush: ruby">p "Hello world"</pre> 
-        formatted.gsub!(/\[(\w+)\]/, '<pre class="brush: \1">')
-        formatted.gsub!(/\[\/\w+\]/, '</pre>')
+        formatted = format_syntax_highlighter(format_paragraphs(content))
 
         # remove all tags inside <pre> that simple_format created
-        # TODO: replace simple_format with a method, that ignores pre-tags
+        # TODO: replace format_paragraphs with a method, that ignores pre-tags
         formatted.gsub!(/(<pre.*?>)(.+?)(<\/pre>)/m) do |match| 
           "#{$1}#{strip_tags($2)}#{$3}"
         end
@@ -60,7 +47,8 @@ module Refinery
       end
 
       def parent_id
-        node.xpath("wp:post_parent").text.to_i
+        dump_id = node.xpath("wp:post_parent").text.to_i
+        dump_id == 0 ? nil : dump_id
       end
 
       def status
@@ -80,12 +68,40 @@ module Refinery
       end
 
       def to_refinery
-        page = ::Page.create!(:title => title, :created_at => post_date, 
-                              :draft => draft?, :parent_id => parent_id)
+        page = ::Page.create!(:id => post_id, :title => title, 
+          :created_at => post_date, :draft => draft?)
 
         page.parts.create(:title => 'Body', :body => content_formatted)
         page
       end
+
+      private 
+
+      def format_paragraphs(text, html_options={})
+        # WordPress doesn't export <p>-Tags, so let's run a simple_format over
+        # the content. As we trust ourselves, no sanatize. This code is heavily
+        # inspired by the simple_format rails helper
+        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.insert 0, start_tag
+
+        text.html_safe.safe_concat("</p>")
+      end
+
+      def format_syntax_highlighter(text)
+        # Support for SyntaxHighlighter (http://alexgorbatchev.com/SyntaxHighlighter/):
+        # In WordPress you can (via a plugin) enclose code in [lang][/lang]
+        # blocks, which are converted to a <pre>-tag with a class corresponding
+        # to the language.
+        # 
+        # Example:
+        # [ruby]p "Hello World"[/ruby] 
+        # -> <pre class="brush: ruby">p "Hello world"</pre> 
+        text.gsub(/\[(\w+)\](.+?)\[\/\1\]/m, '<pre class="brush: \1">\2</pre>')
+      end
     end
   end
 end

data/lib/wordpress/post.rb

@@ -61,6 +61,25 @@ module Refinery
 
         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
+        end
+      end
+
     end
   end
 end

metadata

@@ -1,93 +1,90 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: refinerycms-wordpress-import
-version: !ruby/object:Gem::Version 
+version: !ruby/object:Gem::Version
+  version: 0.2.0
   prerelease: 
-  version: 0.1.0
 platform: ruby
-authors: 
+authors:
 - Marc Remolt
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2011-06-03 00:00:00 +02:00
+date: 2011-06-05 00:00:00.000000000 +02:00
 default_executable: 
-dependencies: 
-- !ruby/object:Gem::Dependency 
+dependencies:
+- !ruby/object:Gem::Dependency
   name: bundler
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  requirement: &14624860 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        version: "1.0"
+      - !ruby/object:Gem::Version
+        version: '1.0'
   type: :runtime
-  version_requirements: *id001
-- !ruby/object:Gem::Dependency 
-  name: refinerycms
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  version_requirements: *14624860
+- !ruby/object:Gem::Dependency
+  name: refinerycms
+  requirement: &14624380 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
+      - !ruby/object:Gem::Version
         version: 1.0.0
   type: :runtime
-  version_requirements: *id002
-- !ruby/object:Gem::Dependency 
-  name: refinerycms-blog
   prerelease: false
-  requirement: &id003 !ruby/object:Gem::Requirement 
+  version_requirements: *14624380
+- !ruby/object:Gem::Dependency
+  name: refinerycms-blog
+  requirement: &14623920 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
+      - !ruby/object:Gem::Version
         version: 1.5.2
   type: :runtime
-  version_requirements: *id003
-- !ruby/object:Gem::Dependency 
-  name: nokogiri
   prerelease: false
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  version_requirements: *14623920
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &14623460 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
+      - !ruby/object:Gem::Version
         version: 1.4.4
   type: :runtime
-  version_requirements: *id004
-- !ruby/object:Gem::Dependency 
-  name: rspec-rails
   prerelease: false
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  version_requirements: *14623460
+- !ruby/object:Gem::Dependency
+  name: rspec-rails
+  requirement: &14623080 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :development
-  version_requirements: *id005
-- !ruby/object:Gem::Dependency 
-  name: database_cleaner
   prerelease: false
-  requirement: &id006 !ruby/object:Gem::Requirement 
+  version_requirements: *14623080
+- !ruby/object:Gem::Dependency
+  name: database_cleaner
+  requirement: &14622620 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :development
-  version_requirements: *id006
-description: This gem imports a WordPress XML dump into refinerycms (Page [soon], User) and refinerycms-blog (BlogPost, BlogCategory, Tag, BlogComment)
+  prerelease: false
+  version_requirements: *14622620
+description: This gem imports a WordPress XML dump into refinerycms (Page, User) and
+  refinerycms-blog (BlogPost, BlogCategory, Tag, BlogComment)
 email: marc.remolt@googlemail.com
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
+files:
 - lib/wordpress.rb
 - lib/wordpress/page.rb
 - lib/wordpress/author.rb
@@ -106,30 +103,26 @@ files:
 has_rdoc: true
 homepage: https://github.com/mremolt/refinerycms-wordpress-import
 licenses: []
-
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
 rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: Import WordPress XML dumps into refinerycms(-blog).
 test_files: []
-