Migrates a blog's contents from the Typo blog engine to Jekyll

typo2jekyll.rb

# Author: Toby DiPasquale <[email protected]>
# Modified by: László Bácsi <[email protected]>
require 'fileutils'
require 'rubygems'
require 'sequel'
require 'htmlentities'

begin
  require 'ya2yaml'
  $KCODE = 'u'
  YAML_METHOD = :ya2yaml
rescue LoadError
  YAML_METHOD = :to_yaml
end

class String
  def decode_entities
    coder = HTMLEntities.new
    coder.decode(self)
  end
end

module Jekyll
  module Typo
    # this SQL *should* work for both MySQL and PostgreSQL, but I haven't
    # tested PostgreSQL yet (as of 2008-12-16)
    SQL = <<-EOS
    SELECT c.id id,
           c.type type,
           c.title title,
           COALESCE(c.permalink, c.name) slug,
           c.body body,
           c.extended extended,
           c.keywords tags,
           c.published_at date,
           c.state state,
           COALESCE(tf.name, 'html') filter
      FROM contents c
           LEFT OUTER JOIN text_filters tf
                        ON c.text_filter_id = tf.id
    EOS

    def self.process dbname, user, pass, host='localhost'
      FileUtils.mkdir_p '_posts'
      db = Sequel.mysql dbname, :user => user, :password => pass, :host => host
      db[SQL].each do |post|
        puts "#{post[:type]}: #{post[:title]}"

        name = post[:slug].strip.tr('/', '-')
        if post[:type] == "Article"
          name = "#{post[:date].strftime("%Y-%m-%d")}-#{name}"
          dir = '_posts'
          layout = 'post'
        else
          post[:filter] = "html"
          dir = 'pages'
          layout = 'default'
        end

        # Can have more than one text filter in this field, but we just want
        # the first one for this
        name += '.' + post[:filter].split(' ')[0]

        File.open("#{dir}/#{name}", 'w') do |f|
          f.puts({ 'layout'   => layout,
                   'title'    => post[:title].to_s,
                   'created_at' => post[:date],
                   'tags'     => post[:tags],
                   'typo_id'  => post[:id]
                 }.delete_if { |k, v| v.nil? || v == '' }.send(YAML_METHOD))
          f.puts '---'
          f.puts post[:body].delete("\r").decode_entities
          if post[:extended]
            f.puts post[:extended].delete("\r").decode_entities
          end
        end
      end
    end

  end   # module Typo
end   # module Jekyll

if __FILE__ == $PROGRAM_NAME
  unless ARGV.size < 3
    Jekyll::Typo.process(*ARGV)
  else
    puts "Usage: #{__FILE__} typo_db db_user db_pass [db_host]"
    exit 1
  end
end