jroes-jekyll 0.5.1

data/lib/jekyll/post.rb

@@ -0,0 +1,247 @@
+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 :site, :date, :slug, :ext, :published, :data, :content, :output, :tags
+    attr_writer :categories
+
+    def categories
+      @categories ||= []
+    end
+
+    # Initialize this Post instance.
+    #   +site+ is the Site
+    #   +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(site, source, dir, name)
+      @site = site
+      @base = File.join(source, dir, '_posts')
+      @name = name
+
+      self.categories = dir.split('/').reject { |x| x.empty? }
+      self.process(name)
+      self.read_yaml(@base, name)
+
+      if self.data.has_key?('published') && self.data['published'] == false
+        self.published = false
+      else
+        self.published = true
+      end
+
+      if self.data.has_key?("tag")
+        self.tags = [self.data["tag"]]
+      elsif self.data.has_key?("tags")
+        self.tags = self.data['tags']
+      else
+        self.tags = []
+      end
+
+      if self.categories.empty?
+        if self.data.has_key?('category')
+          self.categories << self.data['category']
+        elsif self.data.has_key?('categories')
+          # Look for categories in the YAML-header, either specified as
+          # an array or a string.
+          if self.data['categories'].kind_of? String
+            self.categories = self.data['categories'].split
+          else
+            self.categories = self.data['categories']
+          end
+        end
+      end
+    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/" if the permalink style is :date, otherwise nothing
+    #
+    # Returns <String>
+    def dir
+      File.dirname(url)
+    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
+
+    def template
+      case self.site.permalink_style
+      when :pretty
+        "/:categories/:year/:month/:day/:title"
+      when :none
+        "/:categories/:title.html"
+      when :date
+        "/:categories/:year/:month/:day/:title.html"
+      else
+        self.site.permalink_style.to_s
+      end
+    end
+
+    # The generated relative url of this post
+    # e.g. /2008/11/05/my-awesome-post.html
+    #
+    # Returns <String>
+    def url
+      return permalink if permalink
+
+      @url ||= {
+        "year"       => date.strftime("%Y"),
+        "month"      => date.strftime("%m"),
+        "day"        => date.strftime("%d"),
+        "title"      => CGI.escape(slug),
+        "categories" => categories.sort.join('/')
+      }.inject(template) { |result, token|
+        result.gsub(/:#{token.first}/, token.last)
+      }.gsub(/\/\//, "/")
+    end
+
+    # The UID for this post (useful in feeds)
+    # e.g. /2008/11/05/my-awesome-post
+    #
+    # Returns <String>
+    def id
+      File.join(self.dir, self.slug)
+    end
+
+    # Calculate related posts.
+    #
+    # Returns [<Post>]
+    def related_posts(posts)
+      return [] unless posts.size > 1
+
+      if self.site.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))
+
+      # The url needs to be unescaped in order to preserve the correct filename
+      path = File.join(dest, CGI.unescape(self.url))
+
+      if template[/\.html$/].nil?
+        FileUtils.mkdir_p(path)
+        path = File.join(path, "index.html")
+      end
+
+      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,
+        "categories" => self.categories,
+        "next"       => self.next,
+        "previous"   => self.previous,
+        "tags"       => self.tags,
+        "content"    => self.content }.deep_merge(self.data)
+    end
+
+    def inspect
+      "<Post: #{self.id}>"
+    end
+
+    def next
+      pos = self.site.posts.index(self)
+
+      if pos && pos < self.site.posts.length-1
+        self.site.posts[pos+1]
+      else
+        nil
+      end
+    end
+
+    def previous
+      pos = self.site.posts.index(self)
+      if pos && pos > 0
+        self.site.posts[pos-1]
+      else
+        nil
+      end
+    end
+  end
+
+end

data/lib/jekyll/site.rb

@@ -0,0 +1,266 @@
+module Jekyll
+
+  class Site
+    attr_accessor :config, :layouts, :posts, :categories, :exclude,
+                  :source, :dest, :lsi, :pygments, :permalink_style, :tags
+
+    # Initialize the site
+    #   +config+ is a Hash containing site configurations details
+    #
+    # Returns <Site>
+    def initialize(config)
+      self.config          = config.clone
+
+      self.source          = config['source']
+      self.dest            = config['destination']
+      self.lsi             = config['lsi']
+      self.pygments        = config['pygments']
+      self.permalink_style = config['permalink'].to_sym
+      self.exclude         = config['exclude'] || []
+
+      self.reset
+      self.setup
+    end
+
+    def reset
+      self.layouts         = {}
+      self.posts           = []
+      self.categories      = Hash.new { |hash, key| hash[key] = [] }
+      self.tags            = Hash.new { |hash, key| hash[key] = [] }
+    end
+
+    def setup
+      # Check to see if LSI is enabled.
+      require 'classifier' if self.lsi
+
+      # Set the Markdown interpreter (and Maruku self.config, if necessary)
+      case self.config['markdown']
+        when 'rdiscount'
+          begin
+            require 'rdiscount'
+
+            def markdown(content)
+              RDiscount.new(content).to_html
+            end
+
+          rescue LoadError
+            puts 'You must have the rdiscount gem installed first'
+          end
+        when 'maruku'
+          begin
+            require 'maruku'
+
+            def markdown(content)
+              Maruku.new(content).to_html
+            end
+
+            if self.config['maruku']['use_divs']
+              require 'maruku/ext/div'
+              puts 'Maruku: Using extended syntax for div elements.'
+            end
+
+            if self.config['maruku']['use_tex']
+              require 'maruku/ext/math'
+              puts "Maruku: Using LaTeX extension. Images in `#{self.config['maruku']['png_dir']}`."
+
+              # Switch off MathML output
+              MaRuKu::Globals[:html_math_output_mathml] = false
+              MaRuKu::Globals[:html_math_engine] = 'none'
+
+              # Turn on math to PNG support with blahtex
+              # Resulting PNGs stored in `images/latex`
+              MaRuKu::Globals[:html_math_output_png] = true
+              MaRuKu::Globals[:html_png_engine] =  self.config['maruku']['png_engine']
+              MaRuKu::Globals[:html_png_dir] = self.config['maruku']['png_dir']
+              MaRuKu::Globals[:html_png_url] = self.config['maruku']['png_url']
+            end
+          rescue LoadError
+            puts "The maruku gem is required for markdown support!"
+          end
+      end
+    end
+
+    def textile(content)
+      RedCloth.new(content).to_html
+    end
+
+    # Do the actual work of processing the site and generating the
+    # real deal.
+    #
+    # Returns nothing
+    def process
+      self.reset
+      self.read_layouts
+      self.transform_pages
+      self.write_posts
+    end
+
+    # Read all the files in <source>/_layouts into memory for later use.
+    #
+    # Returns nothing
+    def read_layouts
+      base = File.join(self.source, "_layouts")
+      entries = []
+      Dir.chdir(base) { entries = filter_entries(Dir['*.*']) }
+
+      entries.each do |f|
+        name = f.split(".")[0..-2].join(".")
+        self.layouts[name] = Layout.new(self, base, f)
+      end
+    rescue Errno::ENOENT => e
+      # ignore missing layout dir
+    end
+
+    # Read all the files in <base>/_posts and create a new Post object with each one.
+    #
+    # Returns nothing
+    def read_posts(dir)
+      base = File.join(self.source, dir, '_posts')
+      entries = []
+      Dir.chdir(base) { entries = filter_entries(Dir['**/*']) }
+
+      # first pass processes, but does not yet render post content
+      entries.each do |f|
+        if Post.valid?(f)
+          post = Post.new(self, self.source, dir, f)
+
+          if post.published
+            self.posts << post
+            post.categories.each { |c| self.categories[c] << post }
+            post.tags.each { |c| self.tags[c] << post }
+          end
+        end
+      end
+
+      self.posts.sort!
+
+      # second pass renders each post now that full site payload is available
+      self.posts.each do |post|
+        post.render(self.layouts, site_payload)
+      end
+
+      self.categories.values.map { |ps| ps.sort! { |a, b| b <=> a} }
+      self.tags.values.map { |ps| ps.sort! { |a, b| b <=> a} }
+    rescue Errno::ENOENT => e
+      # ignore missing layout dir
+    end
+
+    # Write each post to <dest>/<year>/<month>/<day>/<slug>
+    #
+    # Returns nothing
+    def write_posts
+      self.posts.each do |post|
+        post.write(self.dest)
+      end
+    end
+
+    # Copy all regular files from <source> to <dest>/ ignoring
+    # any files/directories that are hidden or backup files (start
+    # with "." or "#" or end with "~") or contain site content (start with "_")
+    # unless they are "_posts" directories or web server files such as
+    # '.htaccess'
+    #   The +dir+ String is a relative path used to call this method
+    #            recursively as it descends through directories
+    #
+    # Returns nothing
+    def transform_pages(dir = '')
+      base = File.join(self.source, dir)
+      entries = filter_entries(Dir.entries(base))
+      directories = entries.select { |e| File.directory?(File.join(base, e)) }
+      files = entries.reject { |e| File.directory?(File.join(base, e)) }
+
+      # we need to make sure to process _posts *first* otherwise they
+      # might not be available yet to other templates as {{ site.posts }}
+      if directories.include?('_posts')
+        directories.delete('_posts')
+        read_posts(dir)
+      end
+      
+      [directories, files].each do |entries|
+        entries.each do |f|
+          if File.directory?(File.join(base, f))
+            next if self.dest.sub(/\/$/, '') == File.join(base, f)
+            transform_pages(File.join(dir, f))
+          elsif Pager.pagination_enabled?(self.config, f)
+            paginate_posts(f, dir)
+          else
+            first3 = File.open(File.join(self.source, dir, f)) { |fd| fd.read(3) }
+
+            if first3 == "---"
+              # file appears to have a YAML header so process it as a page
+              page = Page.new(self, self.source, dir, f)
+              page.render(self.layouts, site_payload)
+              page.write(self.dest)
+            else
+              # otherwise copy the file without transforming it
+              FileUtils.mkdir_p(File.join(self.dest, dir))
+              FileUtils.cp(File.join(self.source, dir, f), File.join(self.dest, dir, f))
+            end
+          end
+        end
+      end
+    end
+
+    # Constructs a hash map of Posts indexed by the specified Post attribute
+    #
+    # Returns {post_attr => [<Post>]}
+    def post_attr_hash(post_attr)
+      # Build a hash map based on the specified post attribute ( post attr => array of posts )
+      # then sort each array in reverse order
+      hash = Hash.new { |hash, key| hash[key] = Array.new }
+      self.posts.each { |p| p.send(post_attr.to_sym).each { |t| hash[t] << p } }
+      hash.values.map { |sortme| sortme.sort! { |a, b| b <=> a} }
+      return hash
+    end
+
+    # The Hash payload containing site-wide data
+    #
+    # Returns {"site" => {"time" => <Time>,
+    #                     "posts" => [<Post>],
+    #                     "categories" => [<Post>]}
+    def site_payload
+      {"site" => {
+          "time"       => Time.now,
+          "posts"      => self.posts.sort { |a,b| b <=> a },
+          "categories" => post_attr_hash('categories'),
+          "tags"       => post_attr_hash('tags')}}
+    end
+
+    # Filter out any files/directories that are hidden or backup files (start
+    # with "." or "#" or end with "~") or contain site content (start with "_")
+    # unless they are "_posts" directories or web server files such as
+    # '.htaccess'
+    def filter_entries(entries)
+      entries = entries.reject do |e|
+        unless ['_posts', '.htaccess'].include?(e)
+          ['.', '_', '#'].include?(e[0..0]) || e[-1..-1] == '~' || self.exclude.include?(e)
+        end
+      end
+    end
+
+    # Paginates the blog's posts. Renders the index.html file into paginated directories, ie: page2, page3...
+    # and adds more wite-wide data
+    #
+    # {"paginator" => { "page" => <Number>,
+    #                   "per_page" => <Number>,
+    #                   "posts" => [<Post>],
+    #                   "total_posts" => <Number>,
+    #                   "total_pages" => <Number>,
+    #                   "previous_page" => <Number>,
+    #                   "next_page" => <Number> }}
+    def paginate_posts(file, dir)
+      all_posts = self.posts.sort { |a,b| b <=> a }
+      page = Page.new(self, self.source, dir, file)
+
+      pages = Pager.calculate_pages(all_posts, self.config['paginate'].to_i)
+
+      (1..pages).each do |num_page|
+        pager = Pager.new(self.config, num_page, all_posts, pages)
+
+        page.render(self.layouts, site_payload.merge({'paginator' => pager.to_hash}))
+        suffix = "page#{num_page}" if num_page > 1
+        page.write(self.dest, suffix)
+      end
+    end
+  end
+end

data/lib/jekyll/tags/highlight.rb

@@ -0,0 +1,56 @@
+module Jekyll
+
+  class HighlightBlock < Liquid::Block
+    include Liquid::StandardFilters
+
+    # we need a language, but the linenos argument is optional.
+    SYNTAX = /(\w+)\s?(:?linenos)?\s?/
+
+    def initialize(tag_name, markup, tokens)
+      super
+      if markup =~ SYNTAX
+        @lang = $1
+        if defined? $2
+          # additional options to pass to Albino.
+          @options = { 'O' => 'linenos=inline' }
+        else
+          @options = {}
+        end
+      else
+        raise SyntaxError.new("Syntax Error in 'highlight' - Valid syntax: highlight <lang> [linenos]")
+      end
+    end
+
+    def render(context)
+      if context.registers[:site].pygments
+        render_pygments(context, super.to_s)
+      else
+        render_codehighlighter(context, super.to_s)
+      end
+    end
+
+    def render_pygments(context, code)
+      if context["content_type"] == "markdown"
+        return "\n" + Albino.new(code, @lang).to_s(@options) + "\n"
+      elsif context["content_type"] == "textile"
+        return "<notextile>" + Albino.new(code, @lang).to_s(@options) + "</notextile>"
+      else
+        return Albino.new(code, @lang).to_s(@options)
+      end
+    end
+
+    def render_codehighlighter(context, code)
+    #The div is required because RDiscount blows ass
+      <<-HTML
+<div>
+  <pre>
+    <code class='#{@lang}'>#{h(code).strip}</code>
+  </pre>
+</div>
+      HTML
+    end
+  end
+
+end
+
+Liquid::Template.register_tag('highlight', Jekyll::HighlightBlock)

data/lib/jekyll/tags/include.rb

@@ -0,0 +1,31 @@
+module Jekyll
+
+  class IncludeTag < Liquid::Tag
+    def initialize(tag_name, file, tokens)
+      super
+      @file = file.strip
+    end
+
+    def render(context)
+      if @file !~ /^[a-zA-Z0-9_\/\.-]+$/ || @file =~ /\.\// || @file =~ /\/\./
+        return "Include file '#{@file}' contains invalid characters or sequences"
+      end
+
+      Dir.chdir(File.join(context.registers[:site].source, '_includes')) do
+        choices = Dir['**/*'].reject { |x| File.symlink?(x) }
+        if choices.include?(@file)
+          source = File.read(@file)
+          partial = Liquid::Template.parse(source)
+          context.stack do
+            partial.render(context)
+          end
+        else
+          "Included file '#{@file}' not found in _includes directory"
+        end
+      end
+    end
+  end
+
+end
+
+Liquid::Template.register_tag('include', Jekyll::IncludeTag)

data/lib/jekyll.rb

@@ -0,0 +1,84 @@
+$:.unshift File.dirname(__FILE__)     # For use/testing when no gem is installed
+
+# rubygems
+require 'rubygems'
+
+# core
+require 'fileutils'
+require 'time'
+require 'yaml'
+
+# stdlib
+
+# 3rd party
+require 'liquid'
+require 'redcloth'
+
+# internal requires
+require 'jekyll/core_ext'
+require 'jekyll/pager'
+require 'jekyll/site'
+require 'jekyll/convertible'
+require 'jekyll/layout'
+require 'jekyll/page'
+require 'jekyll/post'
+require 'jekyll/filters'
+require 'jekyll/tags/highlight'
+require 'jekyll/tags/include'
+require 'jekyll/albino'
+
+module Jekyll
+  # Default options. Overriden by values in _config.yml or command-line opts.
+  # (Strings rather symbols used for compatability with YAML)
+  DEFAULTS = {
+    'auto'         => false,
+    'server'       => false,
+    'server_port'  => 4000,
+
+    'source'       => '.',
+    'destination'  => File.join('.', '_site'),
+
+    'lsi'          => false,
+    'pygments'     => false,
+    'markdown'     => 'maruku',
+    'permalink'    => 'date',
+
+    'maruku'       => {
+      'use_tex'    => false,
+      'use_divs'   => false,
+      'png_engine' => 'blahtex',
+      'png_dir'    => 'images/latex',
+      'png_url'    => '/images/latex'
+    }
+  }
+
+  # Generate a Jekyll configuration Hash by merging the default options
+  # with anything in _config.yml, and adding the given options on top
+  #   +override+ is a Hash of config directives
+  #
+  # Returns Hash
+  def self.configuration(override)
+    # _config.yml may override default source location, but until
+    # then, we need to know where to look for _config.yml
+    source = override['source'] || Jekyll::DEFAULTS['source']
+
+    # Get configuration from <source>/_config.yml
+    config = {}
+    config_file = File.join(source, '_config.yml')
+    begin
+      config = YAML.load_file(config_file)
+      puts "Configuration from #{config_file}"
+    rescue => err
+      puts "WARNING: Could not read configuration. Using defaults (and options)."
+      puts "\t" + err
+    end
+
+    # Merge DEFAULTS < _config.yml < override
+    Jekyll::DEFAULTS.deep_merge(config).deep_merge(override)
+  end
+
+  def self.version
+    yml = YAML.load(File.read(File.join(File.dirname(__FILE__), *%w[.. VERSION.yml])))
+    "#{yml[:major]}.#{yml[:minor]}.#{yml[:patch]}"
+  end
+end