Routine to replace [gallery] shortcodes during Jekyll WordPress import

galleryimport.rb

# create a 150x150 thumbnail of the passed image using `sips`
# img is an absolute path to the base image file
def thumbnail_image(img)
  return_dir = Dir.pwd
  Dir.chdir(File.dirname(img))
  width = %x{sips -g pixelWidth #{img.strip}|tail -n 1}.gsub(/pixelWidth: /,'').strip.to_i
  height = %x{sips -g pixelHeight #{img.strip}|tail -n 1}.gsub(/pixelHeight: /,'').strip.to_i
  thumb_name = img.strip.gsub(/^(.*?)(\..{3,4})$/,"\\1-150x150\\2").strip
  thumb = File.expand_path(thumb_name)
  FileUtils.cp(File.expand_path(img),thumb)
  type = width > height ? '--resampleHeight' : '--resampleWidth'
  %x{sips #{type} 150 #{thumb} && sips -c 150 150 #{thumb}}
  Dir.chdir(return_dir)
  return thumb_name
end

# `content` is a passed string containing post_content
# `attachments` is an array of hashes containing 'title' and 'url' for each attachment on the post
# replace_galleries uses kramdown syntax for attributes and classes, adjust as needed
def replace_galleries(content, attachments)
  images = "\n" # unordered list of thumbnails linked to images as references
  imagerefs = "\n" # block of reference defenitions
  counter = 1
  content.gsub!(/\[gallery.*?\]/) do |gall|
    attachments.each do |att|
      image = att['url'].gsub(/^#{@domain}\/wp-content/,'').sub(/-\d+x\d+\./,'.')
      thumb = image.sub(/(.*?)(\..{3,4})/,'\\1-150x150\\2')
      assets_dir = Dir.pwd+"/source"
      return gall unless File.directory?(assets_dir+File.dirname(thumb))
      unless File.exists?(assets_dir+thumb)
        thumb = thumbnail_image(assets_dir+image)
        puts thumb
      end
      title = att['title']

      images += %Q{* [![#{title}][img#{counter}thumb]{: width="150" height="150"}][img#{counter}]\n}
      imagerefs += %Q{[img#{counter}thumb]: #{thumb}\n}
      imagerefs += %Q{[img#{counter}]: #{image} '#{title}'\n}
      counter += 1
    end
    images + "{:.gallery}\n" +imagerefs + "\n"
  end
  content
end

# `content` is the post_content field for the row of the WordPress database query being looped
# `px` is a variable containing the table prefix in the WordPress database
# `db` is a Sequel.mysql object
if content =~ /\[gallery/
  attachments = []

  gquery =
  "SELECT
    posts.guid AS `attachment`,
    posts.post_title AS `title`
  FROM
    #{px}posts AS `posts`
  WHERE
    posts.post_parent = '#{post[:ID]}' AND
    posts.post_type = 'attachment'"

  db[gquery].each do |a|
    attachments << { 'url' => a[:attachment], 'title' => a[:title] }
  end

  replace_galleries(content, attachments) unless attachments.empty?
end