Typo

Preparing for release 0.3.0
Resource import working
2011-06-13 19:03:52 +02:00 · 2011-06-13 19:02:25 +02:00 · 2011-06-13 18:48:17 +02:00 · 2011-06-13 15:02:40 +02:00 · 2011-06-06 19:45:34 +02:00 · 2011-06-06 19:39:27 +02:00
20 changed files with 575 additions and 88 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -4,3 +4,6 @@ pkg/
 spec/dummy/db/*.sqlite3
 spec/dummy/log/*.log
 spec/dummy/tmp/
+*.un~
+refinerycms-wordpress-import-*.gem
+*.swp
--- a/12
+++ b/12
@@ -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'
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,7 +1,7 @@
 PATH
  remote: ./
  specs:
-    refinerycms-wordpress-import (0.1.0)
+    refinerycms-wordpress-import (0.3.0)
      bundler (~> 1.0)
      nokogiri (~> 1.4.4)
      refinerycms (~> 1.0.0)
@@ -42,7 +42,7 @@ GEM
    arel (2.0.10)
    awesome_nested_set (2.0.0)
      activerecord (>= 3.0.0)
-    babosa (0.3.4)
+    babosa (0.3.5)
    bcrypt-ruby (2.1.4)
    builder (2.1.2)
    database_cleaner (0.6.7)
@@ -51,17 +51,27 @@ GEM
      orm_adapter (~> 0.0.3)
      warden (~> 1.0.3)
    diff-lcs (1.1.2)
-    dragonfly (0.9.3)
+    dragonfly (0.9.4)
      rack
    erubis (2.6.6)
      abstract (>= 1.0.0)
+    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)
@@ -91,7 +101,7 @@ GEM
      activesupport (= 3.0.7)
      rake (>= 0.8.7)
      thor (~> 0.14.4)
-    rake (0.9.1)
+    rake (0.9.2)
    refinerycms (1.0.0)
      bundler (~> 1.0)
      refinerycms-authentication (= 1.0.0)
@@ -142,11 +152,12 @@ GEM
      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 (2.6.3)
+    rspec-core (2.6.4)
    rspec-expectations (2.6.0)
      diff-lcs (~> 1.1.2)
    rspec-mocks (2.6.0)
@@ -172,9 +183,15 @@ PLATFORMS

 DEPENDENCIES
  database_cleaner
+  fakeweb
+  ffi
+  guard-bundler
+  guard-rspec
+  libnotify
  rails (= 3.0.7)
  refinerycms
  refinerycms-blog
  refinerycms-wordpress-import!
+  rmagick
  rspec-rails (>= 2.6.0)
  sqlite3
--- a/26
+++ b/26
@@ -0,0 +1,26 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard 'rspec', :version => 2 do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+
+  # 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
--- a/README.rdoc
+++ b/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

--- a/lib/tasks/wordpress.rake
+++ b/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
--- a/lib/wordpress.rb
+++ b/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" 
--- a/lib/wordpress/attachment.rb
+++ b/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
--- a/lib/wordpress/dump.rb
+++ b/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
--- a/refinerycms-wordpress-import.gemspec
+++ b/refinerycms-wordpress-import.gemspec
@@ -4,8 +4,8 @@ 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     = "0.2.0"
-  s.date        = "2011-06-05"
+  s.version     = "0.3.0"
+  s.date        = "2011-06-13"

  s.authors     = ['Marc Remolt']
  s.email       = 'marc.remolt@googlemail.com'
--- a/spec/dummy/db/migrate/20110613120139_create_seo_meta_for_blog.rb
+++ b/spec/dummy/db/migrate/20110613120139_create_seo_meta_for_blog.rb
@@ -0,0 +1,25 @@
+class CreateSeoMetaForBlog < ActiveRecord::Migration
+
+  def self.up
+    unless ::SeoMetum.table_exists?
+      create_table ::SeoMetum.table_name do |t|
+        t.integer :seo_meta_id
+        t.string :seo_meta_type
+
+        t.string :browser_title
+        t.string :meta_keywords
+        t.text :meta_description
+
+        t.timestamps
+      end
+
+      add_index ::SeoMetum.table_name, :id
+      add_index ::SeoMetum.table_name, [:seo_meta_id, :seo_meta_type]
+    end
+  end
+
+  def self.down
+    # can't drop the table because someone else might be using it.
+  end
+
+end
--- a/spec/dummy/db/seeds/refinerycms_blog.rb
+++ b/spec/dummy/db/seeds/refinerycms_blog.rb
@@ -1,16 +1,20 @@
-User.find(:all).each do |user|
-  user.plugins.create(:name => "refinerycms_blog",
-                      :position => (user.plugins.maximum(:position) || -1) +1)
-end
+::User.find(:all).each do |user|
+  if user.plugins.where(:name => 'refinerycms_blog').blank?
+    user.plugins.create(:name => "refinerycms_blog",
+                        :position => (user.plugins.maximum(:position) || -1) +1)
+  end
+end if defined?(::User)

-page = Page.create(
-  :title => "Blog",
-  :link_url => "/blog",
-  :deletable => false,
-  :position => ((Page.maximum(:position, :conditions => {:parent_id => nil}) || -1)+1),
-  :menu_match => "^/blogs?(\/|\/.+?|)$"
-)
+if defined?(::Page)
+  page = ::Page.create(
+    :title => "Blog",
+    :link_url => "/blog",
+    :deletable => false,
+    :position => ((Page.maximum(:position, :conditions => {:parent_id => nil}) || -1)+1),
+    :menu_match => "^/blogs?(\/|\/.+?|)$"
+  )

-Page.default_parts.each do |default_page_part|
-  page.parts.create(:title => default_page_part, :body => nil)
+  ::Page.default_parts.each do |default_page_part|
+    page.parts.create(:title => default_page_part, :body => nil)
+  end
 end
--- a/spec/fixtures/200px-Tux.svg_.png
+++ b/spec/fixtures/200px-Tux.svg_.png
--- a/spec/fixtures/wordpress_dump.xml
+++ b/spec/fixtures/wordpress_dump.xml
@@ -16,7 +16,7 @@
 <!-- 7. WordPress will then import each of the posts, pages, comments, categories, etc. -->
 <!--    contained in this file into your site. -->

-<!-- generator="WordPress/3.1.2" created="2011-05-21 12:27" -->
+<!-- generator="WordPress/3.1.2" created="2011-06-06 18:42" -->
 <rss version="2.0"
 	xmlns:excerpt="http://wordpress.org/export/1.1/excerpt/"
 	xmlns:content="http://purl.org/rss/1.0/modules/content/"
@@ -29,7 +29,7 @@
 	<title>My test blog</title>
 	<link>http://localhost/wordpress</link>
 	<description>Just another WordPress site</description>
-	<pubDate>Sat, 21 May 2011 12:27:19 +0000</pubDate>
+	<pubDate>Mon, 06 Jun 2011 18:42:09 +0000</pubDate>
 	<language>en</language>
 	<wp:wxr_version>1.1</wp:wxr_version>
 	<wp:base_site_url>http://localhost/wordpress</wp:base_site_url>
@@ -69,6 +69,10 @@
 		<wp:post_password></wp:post_password>
 		<wp:is_sticky>0</wp:is_sticky>
 		<category domain="category" nicename="uncategorized"><![CDATA[Uncategorized]]></category>
+		<wp:postmeta>
+			<wp:meta_key>_edit_last</wp:meta_key>
+			<wp:meta_value><![CDATA[1]]></wp:meta_value>
+		</wp:postmeta>
 		<wp:comment>
 			<wp:comment_id>1</wp:comment_id>
 			<wp:comment_author><![CDATA[Mr WordPress]]></wp:comment_author>
@@ -92,13 +96,9 @@
 		<guid isPermaLink="false">http://localhost/wordpress/?page_id=2</guid>
 		<description></description>
 		<content:encoded><![CDATA[This is an example page. It's different from a blog post because it will stay in one place and will show up in your site navigation (in most themes). Most people start with an About page that introduces them to potential site visitors. It might say something like this:
-
-<blockquote>Hi there! I'm a bike messenger by day, aspiring actor by night, and this is my blog. I live in Los Angeles, have a great dog named Jack, and I like pi&#241;a coladas. (And gettin' caught in the rain.)</blockquote>
-
+<blockquote>Hi there! I'm a bike messenger by day, aspiring actor by night, and this is my blog. I live in Los Angeles, have a great dog named Jack, and I like piña coladas. (And gettin' caught in the rain.)</blockquote>
 ...or something like this:
-
 <blockquote>The XYZ Doohickey Company was founded in 1971, and has been providing quality doohickies to the public ever since. Located in Gotham City, XYZ employs over 2,000 people and does all kinds of awesome things for the Gotham community.</blockquote>
-
 As a new WordPress user, you should go to <a href="http://localhost/wordpress/wp-admin/">your dashboard</a> to delete this page and create new pages for your content. Have fun!]]></content:encoded>
 		<excerpt:encoded><![CDATA[]]></excerpt:encoded>
 		<wp:post_id>2</wp:post_id>
@@ -117,6 +117,10 @@ As a new WordPress user, you should go to <a href="http://localhost/wordpress/wp
 			<wp:meta_key>_wp_page_template</wp:meta_key>
 			<wp:meta_value><![CDATA[default]]></wp:meta_value>
 		</wp:postmeta>
+		<wp:postmeta>
+			<wp:meta_key>_edit_last</wp:meta_key>
+			<wp:meta_value><![CDATA[1]]></wp:meta_value>
+		</wp:postmeta>
 	</item>
 	<item>
 		<title>Second blog post </title>
@@ -159,8 +163,12 @@ In hac  habitasse platea dictumst. Nunc quis tortor sed libero hendrerit  dapibu
 		<description></description>
 		<content:encoded><![CDATA[This is just a standard text page example. Lorem ipsum dolor sit amet,  consectetur adipiscing elit. Proin metus dolor, hendrerit sit amet,  aliquet nec, posuere sed, purus. Nullam et velit iaculis odio sagittis  placerat. Duis metus tellus, pellentesque ut, luctus id, egestas a,  lorem. Praesent vitae mauris. Aliquam sed nulla. Sed id nunc vitae leo  suscipit viverra. Proin at leo ut lacus consequat rhoncus. In hac  habitasse platea dictumst. Nunc quis tortor sed libero hendrerit  dapibus.

+<a href="http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_.png"><img class="alignnone size-thumbnail wp-image-13" title="200px-Tux.svg" src="http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_-150x150.png" alt="Tux, the Linux mascot" width="150" height="150" /></a>
+
 Integer interdum purus id erat. Duis nec velit vitae dolor mattis  euismod. Class aptent taciti sociosqu ad litora torquent per conubia  nostra, per inceptos himenaeos. Suspendisse pellentesque dignissim  lacus.

+<a href="http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_.png"><img class="alignnone size-full wp-image-13" title="200px-Tux.svg" src="http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_.png" alt="" width="200" height="235" /></a>
+
 Nulla semper euismod arcu. Suspendisse egestas, erat a  consectetur dapibus, felis orci cursus eros, et sollicitudin purus urna  et metus. Integer eget est sed nunc euismod vestibulum. Integer nulla  dui, tristique in, euismod et, interdum imperdiet, enim. Mauris at  lectus. Sed egestas tortor nec mi.]]></content:encoded>
 		<excerpt:encoded><![CDATA[]]></excerpt:encoded>
 		<wp:post_id>6</wp:post_id>
@@ -182,12 +190,12 @@ Nulla semper euismod arcu. Suspendisse egestas, erat a  consectetur dapibus, fel
 		<wp:postmeta>
 			<wp:meta_key>_edit_last</wp:meta_key>
 			<wp:meta_value><![CDATA[1]]></wp:meta_value>
-    </wp:postmeta>
+		</wp:postmeta>
 		<wp:comment>
 			<wp:comment_id>2</wp:comment_id>
 			<wp:comment_author><![CDATA[admin]]></wp:comment_author>
 			<wp:comment_author_email>admin@example.com</wp:comment_author_email>
-			<wp:comment_author_url></wp:comment_author_url>
+			<wp:comment_author_url>http://www.example.com/</wp:comment_author_url>
 			<wp:comment_author_IP>127.0.0.1</wp:comment_author_IP>
 			<wp:comment_date>2011-05-21 12:26:24</wp:comment_date>
 			<wp:comment_date_gmt>2011-05-21 12:26:24</wp:comment_date_gmt>
@@ -201,7 +209,7 @@ Nulla semper euismod arcu. Suspendisse egestas, erat a  consectetur dapibus, fel
 			<wp:comment_id>3</wp:comment_id>
 			<wp:comment_author><![CDATA[admin]]></wp:comment_author>
 			<wp:comment_author_email>admin@example.com</wp:comment_author_email>
-      <wp:comment_author_url>http://www.example.com/</wp:comment_author_url>
+			<wp:comment_author_url>http://www.example.com/</wp:comment_author_url>
 			<wp:comment_author_IP>127.0.0.1</wp:comment_author_IP>
 			<wp:comment_date>2011-05-21 12:26:30</wp:comment_date>
 			<wp:comment_date_gmt>2011-05-21 12:26:30</wp:comment_date_gmt>
@@ -253,6 +261,8 @@ In hac  habitasse platea dictumst. Nunc quis tortor sed libero hendrerit  dapibu
 		<description></description>
 		<content:encoded><![CDATA[This is just a standard text page example. Lorem ipsum dolor sit amet,  consectetur adipiscing elit. Proin metus dolor, hendrerit sit amet,  aliquet nec, posuere sed, purus. Nullam et velit iaculis odio sagittis  placerat.

+<a href="http://localhost/wordpress/wp-content/uploads/2011/05/cv.txt">This is my CV</a>, please download!
+
 Duis metus tellus, pellentesque ut, luctus id, egestas a,  lorem. Praesent vitae mauris. Aliquam sed nulla. Sed id nunc vitae leo  suscipit <strong>viverra</strong>. Proin at leo ut lacus consequat rhoncus. In hac  habitasse platea dictumst. Nunc quis tortor sed libero hendrerit  dapibus.  Integer interdum purus id erat. Duis nec velit vitae dolor mattis  euismod.

 Class aptent taciti sociosqu ad litora torquent per conubia  nostra, per inceptos himenaeos. Suspendisse pellentesque dignissim  lacus. Nulla semper euismod arcu. Suspendisse egestas, erat a  consectetur dapibus, felis orci cursus eros, et sollicitudin purus urna  et metus. Integer eget est sed nunc euismod vestibulum. Integer nulla  dui, tristique in, euismod et, interdum imperdiet, enim. Mauris at  lectus. Sed egestas tortor nec mi.]]></content:encoded>
@@ -278,5 +288,71 @@ Class aptent taciti sociosqu ad litora torquent per conubia  nostra, per incepto
 			<wp:meta_value><![CDATA[default]]></wp:meta_value>
 		</wp:postmeta>
 	</item>
+	<item>
+		<title>200px-Tux.svg</title>
+		<link>http://localhost/wordpress/?attachment_id=13</link>
+		<pubDate>Sun, 05 Jun 2011 15:26:51 +0000</pubDate>
+		<dc:creator>admin</dc:creator>
+		<guid isPermaLink="false">http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_.png</guid>
+		<description></description>
+		<content:encoded><![CDATA[]]></content:encoded>
+		<excerpt:encoded><![CDATA[]]></excerpt:encoded>
+		<wp:post_id>13</wp:post_id>
+		<wp:post_date>2011-06-05 15:26:51</wp:post_date>
+		<wp:post_date_gmt>2011-06-05 15:26:51</wp:post_date_gmt>
+		<wp:comment_status>open</wp:comment_status>
+		<wp:ping_status>open</wp:ping_status>
+		<wp:post_name>200px-tux-svg</wp:post_name>
+		<wp:status>inherit</wp:status>
+		<wp:post_parent>6</wp:post_parent>
+		<wp:menu_order>0</wp:menu_order>
+		<wp:post_type>attachment</wp:post_type>
+		<wp:post_password></wp:post_password>
+		<wp:is_sticky>0</wp:is_sticky>
+		<wp:attachment_url>http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_.png</wp:attachment_url>
+		<wp:postmeta>
+			<wp:meta_key>_wp_attached_file</wp:meta_key>
+			<wp:meta_value><![CDATA[2011/05/200px-Tux.svg_.png]]></wp:meta_value>
+		</wp:postmeta>
+		<wp:postmeta>
+			<wp:meta_key>_wp_attachment_metadata</wp:meta_key>
+			<wp:meta_value><![CDATA[a:6:{s:5:"width";s:3:"200";s:6:"height";s:3:"235";s:14:"hwstring_small";s:22:"height='96' width='81'";s:4:"file";s:26:"2011/05/200px-Tux.svg_.png";s:5:"sizes";a:2:{s:9:"thumbnail";a:3:{s:4:"file";s:26:"200px-Tux.svg_-150x150.png";s:5:"width";s:3:"150";s:6:"height";s:3:"150";}s:14:"post-thumbnail";a:3:{s:4:"file";s:26:"200px-Tux.svg_-200x198.png";s:5:"width";s:3:"200";s:6:"height";s:3:"198";}}s:10:"image_meta";a:10:{s:8:"aperture";s:1:"0";s:6:"credit";s:0:"";s:6:"camera";s:0:"";s:7:"caption";s:0:"";s:17:"created_timestamp";s:1:"0";s:9:"copyright";s:0:"";s:12:"focal_length";s:1:"0";s:3:"iso";s:1:"0";s:13:"shutter_speed";s:1:"0";s:5:"title";s:0:"";}}]]></wp:meta_value>
+		</wp:postmeta>
+		<wp:postmeta>
+			<wp:meta_key>_wp_attachment_image_alt</wp:meta_key>
+			<wp:meta_value><![CDATA[Tux, the Linux mascot]]></wp:meta_value>
+		</wp:postmeta>
+	</item>
+	<item>
+		<title>cv</title>
+		<link>http://localhost/wordpress/?attachment_id=18</link>
+		<pubDate>Mon, 06 Jun 2011 17:27:50 +0000</pubDate>
+		<dc:creator>admin</dc:creator>
+		<guid isPermaLink="false">http://localhost/wordpress/wp-content/uploads/2011/05/cv.txt</guid>
+		<description></description>
+		<content:encoded><![CDATA[]]></content:encoded>
+		<excerpt:encoded><![CDATA[My CV]]></excerpt:encoded>
+		<wp:post_id>18</wp:post_id>
+		<wp:post_date>2011-06-06 17:27:50</wp:post_date>
+		<wp:post_date_gmt>2011-06-06 17:27:50</wp:post_date_gmt>
+		<wp:comment_status>open</wp:comment_status>
+		<wp:ping_status>open</wp:ping_status>
+		<wp:post_name>cv</wp:post_name>
+		<wp:status>inherit</wp:status>
+		<wp:post_parent>10</wp:post_parent>
+		<wp:menu_order>0</wp:menu_order>
+		<wp:post_type>attachment</wp:post_type>
+		<wp:post_password></wp:post_password>
+		<wp:is_sticky>0</wp:is_sticky>
+		<wp:attachment_url>http://localhost/wordpress/wp-content/uploads/2011/05/cv.txt</wp:attachment_url>
+		<wp:postmeta>
+			<wp:meta_key>_wp_attached_file</wp:meta_key>
+			<wp:meta_value><![CDATA[2011/05/cv.txt]]></wp:meta_value>
+		</wp:postmeta>
+		<wp:postmeta>
+			<wp:meta_key>_wp_attachment_metadata</wp:meta_key>
+			<wp:meta_value><![CDATA[a:0:{}]]></wp:meta_value>
+		</wp:postmeta>
+	</item>
 </channel>
 </rss>
--- a/spec/lib/wordpress/attachment_spec.rb
+++ b/spec/lib/wordpress/attachment_spec.rb
@@ -0,0 +1,93 @@
+require 'spec_helper'
+
+describe Refinery::WordPress::Attachment, :type => :model do
+  context "an image attchment" do
+    let(:attachment) { test_dump.attachments.first }
+
+    specify { attachment.title.should == '200px-Tux.svg' }
+    # doesn't get exported atm. for some reason
+    specify { attachment.description.should == '' }
+    specify { attachment.url.should == 'http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_.png' }
+    specify { attachment.file_name.should == '200px-Tux.svg_.png' }
+    specify { attachment.post_date.should == DateTime.new(2011, 6, 5, 15, 26, 51) }
+    specify { attachment.should be_an_image }
+
+    describe "#to_refinery" do
+      before do
+        @image = attachment.to_refinery
+      end
+
+      it "should create an Image from the Attachment" do
+        @image.should be_a(Image)
+      end
+
+      it "should copy the attributes from Attachment" do
+        @image.created_at.should == attachment.post_date
+        @image.image.url.end_with?(attachment.file_name).should be_true
+      end
+    end
+
+    describe "#replace_url" do
+      let(:post) { BlogPost.first }
+
+      before do
+        test_dump.authors.each(&:to_refinery)
+        test_dump.posts.each(&:to_refinery)
+
+        @image = attachment.to_refinery
+
+        attachment.replace_url
+      end
+
+      specify { post.body.should_not include attachment.url }
+      specify { post.body.should_not include '200px-Tux.svg_-150x150.png' }
+      specify { post.body.should_not include 'wp-content' }
+
+      it "should replace attachment urls in the generated BlogPosts" do
+        post.body.should include(@image.image.url)
+      end
+    end
+  end
+
+  context "a file attachment" do
+    let(:attachment) { test_dump.attachments.last }
+
+    specify { attachment.title.should == 'cv' }
+    specify { attachment.url.should == 'http://localhost/wordpress/wp-content/uploads/2011/05/cv.txt' }
+    specify { attachment.file_name.should == 'cv.txt' }
+    specify { attachment.post_date.should == DateTime.new(2011, 6, 6, 17, 27, 50) }
+    specify { attachment.should_not be_an_image }
+
+    describe '#to_refinery' do
+      before do 
+        @resource = attachment.to_refinery
+      end
+
+      specify { Resource.should have(1).record }
+      specify { @resource.should be_a(Resource) }
+
+      it "should copy the attributes from Attachment" do
+        @resource.created_at.should == attachment.post_date
+        @resource.file.url.end_with?(attachment.file_name).should be_true
+      end
+
+    end
+
+    describe '#replace_resource_url' do
+      let(:page_part) { Page.last.parts.first }
+
+      before do
+        test_dump.pages.each(&:to_refinery)
+        @resource = attachment.to_refinery
+        attachment.replace_url
+      end
+
+      specify { page_part.body.should_not include attachment.url }
+      specify { page_part.body.should_not include 'wp-content' }
+
+      it "should replace attachment urls in the generated BlogPosts" do
+        page_part.body.should include(@resource.file.url)
+      end
+    end
+  end
+end
--- a/spec/lib/wordpress/author_spec.rb
+++ b/spec/lib/wordpress/author_spec.rb
@@ -3,8 +3,8 @@ require 'spec_helper'
 describe Refinery::WordPress::Author, :type => :model do
  let(:author) { test_dump.authors.first }

-  it { author.login.should == 'admin' }
-  it { author.email.should == 'admin@example.com' }
+  specify { author.login.should == 'admin' }
+  specify { author.email.should == 'admin@example.com' }

  describe "#to_refinery" do
    before do 
--- a/spec/lib/wordpress/dump_spec.rb
+++ b/spec/lib/wordpress/dump_spec.rb
@@ -18,6 +18,7 @@ describe Refinery::WordPress::Dump, :type => :model do
    end

    specify { dump.tags.count == 4 }
+    specify { dump.tags.first.should be_a(Refinery::WordPress::Tag) }

    it "should return all included tags" do
      tags.each do |tag|
@@ -33,6 +34,7 @@ describe Refinery::WordPress::Dump, :type => :model do
    end

    specify { dump.categories.count == 4 }
+    specify { dump.categories.first.should be_a(Refinery::WordPress::Category) }

    it "should return all included categories" do
      categories.each do |cat|
@@ -46,6 +48,8 @@ describe Refinery::WordPress::Dump, :type => :model do
      dump.pages.should have(3).pages
    end

+    specify { dump.pages.first.should be_a(Refinery::WordPress::Page) }
+
    it "should return only published pages with only_published=true" do
      dump.pages(true).should have(2).pages
    end
@@ -55,6 +59,8 @@ describe Refinery::WordPress::Dump, :type => :model do
    it "should return all authors" do
      dump.authors.should have(1).author
    end
+
+    specify { dump.authors.first.should be_a(Refinery::WordPress::Author) }
  end

  describe "#posts" do
@@ -62,8 +68,18 @@ describe Refinery::WordPress::Dump, :type => :model do
      dump.posts.should have(3).posts
    end

+    specify { dump.posts.first.should be_a(Refinery::WordPress::Post) }
+
    it "should return only published posts with only_published=true" do
      dump.posts(true).should have(2).posts
    end
  end
+
+  describe "#attachments" do
+    it "should return all attachments" do
+      dump.attachments.should have(2).attachments
+    end
+
+    specify { dump.attachments.first.should be_a(Refinery::WordPress::Attachment) }
+  end
 end
--- a/spec/lib/wordpress/page_spec.rb
+++ b/spec/lib/wordpress/page_spec.rb
@@ -5,15 +5,15 @@ describe Refinery::WordPress::Page, :type => :model do

  let(:page) { test_dump.pages.last }

-  it { page.title.should == 'About me' }
-  it { page.content.should include('Lorem ipsum dolor sit') }
-  it { page.creator.should == 'admin' }
-  it { page.post_date.should == DateTime.new(2011, 5, 21, 12, 25, 42) }
-  it { page.post_id.should == 10 }
-  it { page.parent_id.should == 8 }
+   specify { page.title.should == 'About me' }
+   specify { page.content.should include('Lorem ipsum dolor sit') }
+   specify { page.creator.should == 'admin' }
+   specify { page.post_date.should == DateTime.new(2011, 5, 21, 12, 25, 42) }
+   specify { page.post_id.should == 10 }
+   specify { page.parent_id.should == 8 }

-  it { page.should == dump.pages.last }
-  it { page.should_not == dump.pages.first }
+   specify { page.should == dump.pages.last }
+   specify { page.should_not == dump.pages.first }

  describe "#to_refinery" do
    include ::ActionView::Helpers::TagHelper
--- a/spec/lib/wordpress/post_spec.rb
+++ b/spec/lib/wordpress/post_spec.rb
@@ -3,32 +3,32 @@ require 'spec_helper'
 describe Refinery::WordPress::Post, :type => :model do
  let(:post) { test_dump.posts.last }

-  it { post.title.should == 'Third blog post' }
-  it { post.content.should include('Lorem ipsum dolor sit') }
-  it { post.content_formatted.should include('Lorem ipsum dolor sit') }
-  it { post.creator.should == 'admin' }
-  it { post.post_date.should == DateTime.new(2011, 5, 21, 12, 24, 45) }
-  it { post.post_id.should == 6 }
-  it { post.parent_id.should == nil }
-  it { post.status.should == 'publish' }
+   specify { post.title.should == 'Third blog post' }
+   specify { post.content.should include('Lorem ipsum dolor sit') }
+   specify { post.content_formatted.should include('Lorem ipsum dolor sit') }
+   specify { post.creator.should == 'admin' }
+   specify { post.post_date.should == DateTime.new(2011, 5, 21, 12, 24, 45) }
+   specify { post.post_id.should == 6 }
+   specify { post.parent_id.should == nil }
+   specify { post.status.should == 'publish' }

-  it { post.should == test_dump.posts.last }
-  it { post.should_not == test_dump.posts.first }
+   specify { post.should == test_dump.posts.last }
+   specify { post.should_not == test_dump.posts.first }

  describe "#categories" do
-    it { post.categories.should have(1).category }
-    it { post.categories.first.should == Refinery::WordPress::Category.new('Rant') }
+     specify { post.categories.should have(1).category }
+     specify { post.categories.first.should == Refinery::WordPress::Category.new('Rant') }
  end

  describe "#tags" do
-    it { post.tags.should have(3).tags }
+     specify { post.tags.should have(3).tags }

-    it { post.tags.should include(Refinery::WordPress::Tag.new('css')) }
-    it { post.tags.should include(Refinery::WordPress::Tag.new('html')) }
-    it { post.tags.should include(Refinery::WordPress::Tag.new('php')) }
+     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')) }
  end

-  it { post.tag_list.should == 'css,html,php' }
+   specify { post.tag_list.should == 'css,html,php' }

  describe "#comments" do
    it "should return all attached comments" do
@@ -38,14 +38,14 @@ describe Refinery::WordPress::Post, :type => :model do
    context "the last comment" do
      let(:comment) { post.comments.last }

-      it { comment.author.should == 'admin' }
-      it { comment.email.should == 'admin@example.com' }
-      it { comment.url.should == 'http://www.example.com/' }
-      it { comment.date.should == DateTime.new(2011, 5, 21, 12, 26, 30) }
-      it { comment.content.should include('Another one!') }
-      it { comment.should be_approved }
+       specify { comment.author.should == 'admin' }
+       specify { comment.email.should == 'admin@example.com' }
+       specify { comment.url.should == 'http://www.example.com/' }
+       specify { comment.date.should == DateTime.new(2011, 5, 21, 12, 26, 30) }
+       specify { comment.content.should include('Another one!') }
+       specify { comment.should be_approved }

-      it { comment.should == post.comments.last }
+       specify { comment.should == post.comments.last }

      describe "#to_refinery" do
        before do 
@@ -79,7 +79,7 @@ describe Refinery::WordPress::Post, :type => :model do
        @post = post.to_refinery
      end

-      it { BlogPost.should have(1).record } 
+       specify { BlogPost.should have(1).record } 

      it "should copy the attributes from Refinery::WordPress::Post" do
        @post.title.should == post.title
@@ -106,7 +106,7 @@ describe Refinery::WordPress::Post, :type => :model do

      end

-      it { BlogPost.should have(2).records } 
+       specify { BlogPost.should have(2).records } 

      it "should create the BlogPost with #post_id attached" do
        @post.title.should == "#{post.title}-#{post.post_id}"
--- a/spec/support/fakeweb.rb
+++ b/spec/support/fakeweb.rb
@@ -0,0 +1,12 @@
+require "fakeweb"
+
+FakeWeb.allow_net_connect = false
+
+# Simulating download of wordpress file attachments. The dump expects the files
+# to be at the given URLs
+FakeWeb.register_uri(:get, 
+  "http://localhost/wordpress/wp-content/uploads/2011/05/200px-Tux.svg_.png", 
+  :body => File.new('spec/fixtures/200px-Tux.svg_.png').read, 
+  :content_type => "image/png")
+
+FakeWeb.register_uri(:get, "http://localhost/wordpress/wp-content/uploads/2011/05/cv.txt", :body => "Hello World!", :content_type => "text/plain")
Author	SHA1	Message	Date
Marc Remolt	32bb8a528a	Typo	2011-06-13 19:03:52 +02:00
Marc Remolt	309ec660b9	Preparing for release 0.3.0	2011-06-13 19:02:25 +02:00
Marc Remolt	90665484c7	Resource import working * added rake tasks	2011-06-13 18:48:17 +02:00
Marc Remolt	a24ea686fa	Image import working * bundle update * replacement of image URLs now considers wordpress thumbnails (like -150x150) * added Guard for autotesting	2011-06-13 15:02:40 +02:00
Marc Remolt	7265d31f62	Some specs for file Attachment	2011-06-06 19:45:34 +02:00
Marc Remolt	2581895c7c	Updated test dump and adapted specs * We now have a second attachment, a simple text file	2011-06-06 19:39:27 +02:00
Marc Remolt	7550dfa164	First shot at attachment import * only images for now * only blog posts for now * thumbnailed images are not yet replaced in blog posts body	2011-06-05 19:14:52 +02:00
Marc Remolt	9a2b5acef6	Spec improvements * replaced it with specify on {...} blocks	2011-06-05 17:55:00 +02:00
Marc Remolt	772cfdc25b	Started on attachment import * created Attachment * created Dump#attachments * specs * replaced require with autoload	2011-06-05 17:43:30 +02:00