qrush-jekyll 0.3.0.1

data/lib/jekyll/converters/wordpress.rb

@@ -0,0 +1,54 @@
+require 'rubygems'
+require 'sequel'
+require 'fileutils'
+
+# 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 WordPress
+    
+    # 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 * from wp_posts where post_status = 'publish' and post_type = 'post'"
+
+    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[:post_name]
+        date = post[:post_date]
+        content = post[:post_content]
+        
+        name = [date.year, date.month, date.day, slug].join('-') + ".markdown"
+
+        # Get the relevant fields as a hash, delete empty fields and convert
+        # to YAML for the header        
+        data = {
+           'layout' => 'post',
+           'title' => title.to_s,
+           'excerpt' => post[:post_excerpt].to_s,
+           'wordpress_id' => post[:ID],
+           'wordpress_url' => post[:guid]
+         }.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
+  end
+end

data/lib/jekyll/convertible.rb

@@ -0,0 +1,60 @@
+module Jekyll
+  module Convertible
+    # Return the contents as a string
+    def to_s
+      self.content || ''
+    end
+    
+    # Read the YAML frontmatter
+    #   +base+ is the String path to the dir containing the file
+    #   +name+ is the String filename of the file
+    #
+    # Returns nothing
+    def read_yaml(base, name)
+      self.content = File.read(File.join(base, name))
+      
+      if self.content =~ /^(---\s*\n.*?)\n---\s*\n/m
+        self.content = self.content[($1.size + 5)..-1]
+        
+        self.data = YAML.load($1)
+      end
+    end
+    
+    # Transform the contents based on the file extension.
+    #
+    # Returns nothing
+    def transform
+      case self.ext[1..-1]
+      when /textile/i
+        self.ext = ".html"
+        self.content = RedCloth.new(self.content).to_html
+      when /markdown/i, /mkdn/i, /md/i
+        self.ext = ".html"
+        self.content = Jekyll.markdown_proc.call(self.content)
+      end
+    end
+    
+    # Add any necessary layouts to this convertible document
+    #   +layouts+ is a Hash of {"name" => "layout"}
+    #   +site_payload+ is the site payload hash
+    #
+    # Returns nothing
+    def do_layout(payload, layouts)
+      # render and transform content (this becomes the final content of the object)
+      self.content = Liquid::Template.parse(self.content).render(payload, [Jekyll::Filters])
+      self.transform
+      
+      # output keeps track of what will finally be written
+      self.output = self.content
+      
+      # recursively render layouts
+      layout = layouts[self.data["layout"]]
+      while layout
+        payload = payload.deep_merge({"content" => self.output, "page" => layout.data})
+        self.output = Liquid::Template.parse(layout.content).render(payload, [Jekyll::Filters])
+        
+        layout = layouts[layout.data["layout"]]
+      end
+    end
+  end
+end

data/lib/jekyll/core_ext.rb

@@ -0,0 +1,22 @@
+class Hash
+  # Merges self with another hash, recursively.
+  # 
+  # This code was lovingly stolen from some random gem:
+  # http://gemjack.com/gems/tartan-0.1.1/classes/Hash.html
+  # 
+  # Thanks to whoever made it.
+  def deep_merge(hash)
+    target = dup
+    
+    hash.keys.each do |key|
+      if hash[key].is_a? Hash and self[key].is_a? Hash
+        target[key] = target[key].deep_merge(hash[key])
+        next
+      end
+      
+      target[key] = hash[key]
+    end
+    
+    target
+  end
+end

data/lib/jekyll/filters.rb

@@ -0,0 +1,39 @@
+module Jekyll
+  
+  module Filters
+    def date_to_string(date)
+      date.strftime("%d %b %Y")
+    end
+
+    def date_to_long_string(date)
+      date.strftime("%d %B %Y")
+    end
+    
+    def date_to_xmlschema(date)
+      date.xmlschema
+    end
+    
+    def xml_escape(input)
+      input.gsub("&", "&amp;").gsub("<", "&lt;").gsub(">", "&gt;")
+    end
+    
+    def number_of_words(input)
+      input.split.length
+    end
+    
+    def array_to_sentence_string(array)
+      connector = "and"
+      case array.length
+      when 0
+        ""
+      when 1
+        array[0].to_s
+      when 2
+        "#{array[0]} #{connector} #{array[1]}"
+      else
+        "#{array[0...-1].join(', ')}, #{connector} #{array[-1]}"
+      end
+    end
+
+  end  
+end

data/lib/jekyll/layout.rb

@@ -0,0 +1,33 @@
+module Jekyll
+
+  class Layout
+    include Convertible
+    
+    attr_accessor :ext
+    attr_accessor :data, :content
+    
+    # Initialize a new Layout.
+    #   +base+ is the String path to the <source>
+    #   +name+ is the String filename of the post file
+    #
+    # Returns <Page>
+    def initialize(base, name)
+      @base = base
+      @name = name
+      
+      self.data = {}
+      
+      self.process(name)
+      self.read_yaml(base, name)
+    end
+    
+    # Extract information from the layout filename
+    #   +name+ is the String filename of the layout file
+    #
+    # Returns nothing
+    def process(name)
+      self.ext = File.extname(name)
+    end
+  end
+
+end

data/lib/jekyll/page.rb

@@ -0,0 +1,64 @@
+module Jekyll
+
+  class Page
+    include Convertible
+    
+    attr_accessor :ext
+    attr_accessor :data, :content, :output
+    
+    # Initialize a new Page.
+    #   +base+ is the String path to the <source>
+    #   +dir+ is the String path between <source> and the file
+    #   +name+ is the String filename of the file
+    #
+    # Returns <Page>
+    def initialize(base, dir, name)
+      @base = base
+      @dir = dir
+      @name = name
+      
+      self.data = {}
+      
+      self.process(name)
+      self.read_yaml(File.join(base, dir), name)
+      #self.transform
+    end
+    
+    # Extract information from the page filename
+    #   +name+ is the String filename of the page file
+    #
+    # Returns nothing
+    def process(name)
+      self.ext = File.extname(name)
+    end
+    
+    # Add any necessary layouts to this post
+    #   +layouts+ is a Hash of {"name" => "layout"}
+    #   +site_payload+ is the site payload hash
+    #
+    # Returns nothing
+    def render(layouts, site_payload)
+      payload = {"page" => self.data}.deep_merge(site_payload)
+      do_layout(payload, layouts)
+    end
+    
+    # Write the generated page file to the destination directory.
+    #   +dest+ is the String path to the destination dir
+    #
+    # Returns nothing
+    def write(dest)
+      FileUtils.mkdir_p(File.join(dest, @dir))
+      
+      name = @name
+      if self.ext != ""
+        name = @name.split(".")[0..-2].join('.') + self.ext
+      end
+      
+      path = File.join(dest, @dir, name)
+      File.open(path, 'w') do |f|
+        f.write(self.output)
+      end
+    end
+  end
+
+end

data/lib/jekyll/post.rb

@@ -0,0 +1,170 @@
+module Jekyll
+
+  class Post
+    include Comparable
+    include Convertible
+        
+    class << self
+      attr_accessor :lsi
+    end
+    
+    MATCHER = /^(.+\/)*(\d+-\d+-\d+)-(.*)(\.[^.]+)$/
+    
+    # Post name validator. Post filenames must be like:
+    #   2008-11-05-my-awesome-post.textile
+    #
+    # Returns <Bool>
+    def self.valid?(name)
+      name =~ MATCHER
+    end
+    
+    attr_accessor :date, :slug, :ext, :categories, :topics
+    attr_accessor :data, :content, :output
+    
+    # Initialize this Post instance.
+    #   +base+ is the String path to the dir containing the post file
+    #   +name+ is the String filename of the post file
+    #   +categories+ is an Array of Strings for the categories for this post
+    #
+    # Returns <Post>
+    def initialize(source, dir, name)
+      @base = File.join(source, dir, '_posts')
+      @name = name
+      
+      self.categories = dir.split('/').reject { |x| x.empty? }
+      
+      parts = name.split('/')
+      self.topics = parts.size > 1 ? parts[0..-2] : []
+      
+      self.process(name)
+      self.read_yaml(@base, name)
+    end
+    
+    # Spaceship is based on Post#date
+    #
+    # Returns -1, 0, 1
+    def <=>(other)
+      self.date <=> other.date
+    end
+    
+    # Extract information from the post filename
+    #   +name+ is the String filename of the post file
+    #
+    # Returns nothing
+    def process(name)
+      m, cats, date, slug, ext = *name.match(MATCHER)
+      self.date = Time.parse(date)
+      self.slug = slug
+      self.ext = ext
+    end
+    
+    # The generated directory into which the post will be placed
+    # upon generation. This is derived from the permalink or, if
+    # permalink is absent, set to the default date
+    # e.g. "/2008/11/05/"
+    #
+    # Returns <String>
+    def dir
+      if permalink
+        permalink.to_s.split("/")[0..-2].join("/")
+      else
+        prefix = self.categories.empty? ? '' : '/' + self.categories.join('/')
+        prefix + date.strftime("/%Y/%m/%d/")
+      end
+    end
+    
+    # The full path and filename of the post.
+    # Defined in the YAML of the post body
+    # (Optional)
+    #
+    # Returns <String>
+    def permalink
+      self.data && self.data['permalink']
+    end
+    
+    # The generated relative url of this post
+    # e.g. /2008/11/05/my-awesome-post.html
+    #
+    # Returns <String>
+    def url
+      self.dir + self.slug + ".html"
+    end
+    
+    # The UID for this post (useful in feeds)
+    # e.g. /2008/11/05/my-awesome-post
+    #
+    # Returns <String>
+    def id
+      self.dir + self.slug
+    end
+        
+    # Calculate related posts.
+    #
+    # Returns [<Post>]
+    def related_posts(posts)
+      return [] unless posts.size > 1
+      
+      if Jekyll.lsi
+        self.class.lsi ||= begin
+          puts "Running the classifier... this could take a while."
+          lsi = Classifier::LSI.new
+          posts.each { |x| $stdout.print(".");$stdout.flush;lsi.add_item(x) }
+          puts ""
+          lsi
+        end
+
+        related = self.class.lsi.find_related(self.content, 11)
+        related - [self]
+      else
+        (posts - [self])[0..9]
+      end
+    end
+    
+    # Add any necessary layouts to this post
+    #   +layouts+ is a Hash of {"name" => "layout"}
+    #   +site_payload+ is the site payload hash
+    #
+    # Returns nothing
+    def render(layouts, site_payload)
+      # construct payload
+      payload =
+      {
+        "site" => { "related_posts" => related_posts(site_payload["site"]["posts"]) },
+        "page" => self.to_liquid
+      }
+      payload = payload.deep_merge(site_payload)
+      
+      do_layout(payload, layouts)
+    end
+    
+    # Write the generated post file to the destination directory.
+    #   +dest+ is the String path to the destination dir
+    #
+    # Returns nothing
+    def write(dest)
+      FileUtils.mkdir_p(File.join(dest, dir))
+      
+      path = File.join(dest, self.url)
+      File.open(path, 'w') do |f|
+        f.write(self.output)
+      end
+    end
+    
+    # Convert this post into a Hash for use in Liquid templates.
+    #
+    # Returns <Hash>
+    def to_liquid
+      { "title" => self.data["title"] || self.slug.split('-').select {|w| w.capitalize! || w }.join(' '),
+        "url" => self.url,
+        "date" => self.date,
+        "id" => self.id,
+        "topics" => self.topics,
+        "content" => self.content }.deep_merge(self.data)
+    end
+    
+    def inspect
+      "<Post: #{self.id}>"
+    end
+  end
+
+end