jekyll_drupal_conversion.rb

require 'rubygems'
require 'sequel'
require 'fileutils'

module Jekyll
  module Drupal

    QUERY = "
      select n.nid node_id,
             n.title post_title,
             n.created post_date,
             nr.body post_content,
             nr.format format,
             ff.name format_name
        from node n, node_revisions nr, filter_formats ff
       where n.status = 1
         and n.nid = nr.nid
         and n.vid = nr.vid
         and nr.format = ff.format
       order by n.changed
      "
    # TODO status = 0 to drafts

    def self.process(dbname, user, pass, host = 'localhost')
      db = Sequel.mysql(dbname, :user => user, :password => pass, :host => host)

      FileUtils.mkdir_p "_posts"

      db[QUERY].each do |post|
        # Get required fields and construct Jekyll compatible name
        title = post[:post_title]
        slug = post[:node_id].to_s
        date = Time.at(post[:post_date])
        content = post[:post_content]
        format_name = post[:format_name]
        if format_name.downcase == "markdown"
          format = "markdown"
        else
          format = "html"
          if format_name.downcase == "filtered html" or format_name.downcase == "full html"
            process_filtered_html!(content)
          end
        end
        name = "%02d-%02d-%02d-%s.%s" % [date.year, date.month, date.day,
                                               slug, format]

        # Get the relevant fields as a hash, delete empty fields and convert
        # to YAML for the header
        data = {
          'layout' => 'post',
          'title' => title.to_s,
          'drupal_format' => format_name
         }.delete_if { |k,v| v.nil? || v == ''}.to_yaml

        # Write out the data and content to file
        File.open("_posts/#{name}", "w") do |f|
          f.puts data
          f.puts "---"
          f.puts content
        end
      end
    end

    def self.process_filtered_html!(content)
      content.gsub!(/\n/, "<br>\n")
    end

    def self.process_source_tags!(content)
      content.gsub!(/<lisp>/, "{% highlight cl %}")
      content.gsub!(/<\/lisp>/, "{% endhighlight %}")
      content.gsub!(/<bash>/, "{% highlight bash %}")
      content.gsub!(/<\/bash>/, "{% endhighlight %}")
      content.gsub!(/<code language="java5">/, "{% highlight java %}")
      # TODO content.gsub!(/<\/code>/, "{% endhighlight %}")
      content.gsub!(/<code language="java">/, "{% highlight java %}")
      # TODO content.gsub!(/<\/code>/, "{% endhighlight %}")
      content.gsub!(/<python>/, "{% highlight python %}")
      content.gsub!(/<\/python>/, "{% endhighlight %}")
    end
  end
end

# Replace the following with your database info
Jekyll::Drupal.process("databasename", "user", "password", "hostname")