From e8fd7ebbc3d412ee881231e09af2a421e263e400 Mon Sep 17 00:00:00 2001 From: Matt Di Pasquale Date: Mon, 29 Nov 2010 18:41:40 -0500 Subject: [PATCH] Add Drupal migrator --- lib/jekyll/migrators/drupal.rb | 86 ++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) create mode 100644 lib/jekyll/migrators/drupal.rb diff --git a/lib/jekyll/migrators/drupal.rb b/lib/jekyll/migrators/drupal.rb new file mode 100644 index 00000000..be198197 --- /dev/null +++ b/lib/jekyll/migrators/drupal.rb @@ -0,0 +1,86 @@ +require 'rubygems' +require 'sequel' +require 'fileutils' +require 'yaml' + +# NOTE: This converter requires Sequel and the MySQL gems. +# The MySQL gem can be difficult to install on OS X. Once you have MySQL +# installed, running the following commands should work: +# $ sudo gem install sequel +# $ sudo gem install mysql -- --with-mysql-config=/usr/local/mysql/bin/mysql_config + +module Jekyll + module Drupal + + # Reads a MySQL database via Sequel and creates a post file for each + # post in wp_posts that has post_status = 'publish'. + # This restriction is made because 'draft' posts are not guaranteed to + # have valid dates. + QUERY = "SELECT node.nid, node.title, node_revisions.body, node.created, node.status FROM node, node_revisions WHERE (node.type = 'blog' OR node.type = 'story') AND node.vid = node_revisions.vid" + + def self.process(dbname, user, pass, host = 'localhost') + db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host, :encoding => 'utf8') + + FileUtils.mkdir_p "_posts" + FileUtils.mkdir_p "_drafts" + + # Create the refresh layout + # Change the refresh url if you customized your permalink config + File.open("_layouts/refresh.html", "w") do |f| + f.puts < + + + + + + +EOF + end + + db[QUERY].each do |post| + # Get required fields and construct Jekyll compatible name + node_id = post[:nid] + title = post[:title] + content = post[:body] + created = post[:created] + time = Time.at(created) + is_published = post[:status] == 1 + dir = is_published ? "_posts" : "_drafts" + slug = title.strip.downcase.gsub(/(&|&)/, ' and ').gsub(/[\s\.\/\\]/, '-').gsub(/[^\w-]/, '').gsub(/[-_]{2,}/, '-').gsub(/^[-_]/, '').gsub(/[-_]$/, '') + name = time.strftime("%Y-%m-%d-") + slug + '.md' + + # Get the relevant fields as a hash, delete empty fields and convert + # to YAML for the header + data = { + 'layout' => 'post', + 'title' => title.to_s, + 'created' => created, + }.delete_if { |k,v| v.nil? || v == ''}.to_yaml + + # Write out the data and content to file + File.open("#{dir}/#{name}", "w") do |f| + f.puts data + f.puts "---" + f.puts content + end + + # Make a file to redirect from the old Drupal URL + if is_published + FileUtils.mkdir_p "node/#{node_id}" + File.open("node/#{node_id}/index.md", "w") do |f| + f.puts "---" + f.puts "layout: refresh" + f.puts "refresh_to_post_id: /#{time.strftime("%Y/%m/%d/") + slug}" + f.puts "---" + end + end + end + + # TODO: Make dirs & files for nodes of type 'page' + # Make refresh pages for these as well + + # TODO: Make refresh dirs & files according to entries in url_alias table + end + end +end