realityforge-jekyll 0.7.1-java

data/lib/jekyll/post.rb

@@ -0,0 +1,242 @@
+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
+    attr_accessor :data, :content, :output, :ext
+    attr_accessor :date, :slug, :published, :tags, :categories
+
+    # 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 we've added a date and time to the yaml, use that instead of the filename date
+      #Means we'll sort correctly.
+      if self.data.has_key?('date')
+        # ensure Time via to_s and reparse
+        self.date = Time.parse(self.data["date"].to_s)
+      end
+
+      if self.data.has_key?('published') && self.data['published'] == false
+        self.published = false
+      else
+        self.published = true
+      end
+
+      self.tags = self.data.pluralized_array("tag", "tags")
+
+      if self.categories.empty?
+        self.categories = self.data.pluralized_array('category', 'categories')
+      end
+    end
+
+    # Spaceship is based on Post#date, slug
+    #
+    # Returns -1, 0, 1
+    def <=>(other)
+      cmp = self.date <=> other.date
+      if 0 == cmp
+       cmp = self.slug <=> other.slug
+      end
+      return cmp
+    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),
+        "i_day"      => date.strftime("%d").to_i.to_s,
+        "i_month"    => date.strftime("%m").to_i.to_s,
+        "categories" => categories.join('/'),
+        "output_ext" => self.output_ext
+      }.inject(template) { |result, token|
+        result.gsub(/:#{Regexp.escape 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
+      return [] if defined?(JRUBY_VERSION)
+      
+      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
+      }.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
+      self.data.deep_merge({
+        "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 })
+    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 +1,235 @@
+module Jekyll
+
+  class Site
+    attr_accessor :config, :layouts, :posts, :pages, :static_files,
+                  :categories, :exclude, :source, :dest, :lsi, :pygments,
+                  :permalink_style, :tags, :time, :future, :safe, :plugins
+    attr_accessor :converters, :generators
+
+    # Initialize the site
+    #   +config+ is a Hash containing site configurations details
+    #
+    # Returns <Site>
+    def initialize(config)
+      self.config          = config.clone
+
+      self.safe            = config['safe']
+      self.source          = File.expand_path(config['source'])
+      self.dest            = File.expand_path(config['destination'])
+      self.plugins         = File.expand_path(config['plugins'])
+      self.lsi             = config['lsi']
+      self.pygments        = config['pygments']
+      self.permalink_style = config['permalink'].to_sym
+      self.exclude         = config['exclude'] || []
+      self.future          = config['future']
+
+      self.reset
+      self.setup
+    end
+
+    def reset
+      self.time            = if self.config['time']
+                               Time.parse(self.config['time'].to_s)
+                             else
+                               Time.now
+                             end
+      self.layouts         = {}
+      self.posts           = []
+      self.pages           = []
+      self.static_files    = []
+      self.categories      = Hash.new { |hash, key| hash[key] = [] }
+      self.tags            = Hash.new { |hash, key| hash[key] = [] }
+    end
+
+    def setup
+      require 'classifier' if self.lsi
+
+      # If safe mode is off, load in any ruby files under the plugins
+      # directory.
+      unless self.safe
+        Dir[File.join(self.plugins, "**/*.rb")].each do |f|
+          require f
+        end
+      end
+
+      self.converters = Jekyll::Converter.subclasses.select do |c|
+        !self.safe || c.safe
+      end.map do |c|
+        c.new(self.config)
+      end
+
+      self.generators = Jekyll::Generator.subclasses.select do |c|
+        !self.safe || c.safe
+      end.map do |c|
+        c.new(self.config)
+      end
+    end
+
+    # Do the actual work of processing the site and generating the
+    # real deal.  5 phases; reset, read, generate, render, write.  This allows
+    # rendering to have full site payload available.
+    #
+    # Returns nothing
+    def process
+      self.reset
+      self.read
+      self.generate
+      self.render
+      self.write
+    end
+
+    def read
+      self.read_layouts # existing implementation did this at top level only so preserved that
+      self.read_directories
+    end
+
+    # Read all the files in <source>/<dir>/_layouts and create a new Layout
+    # object with each one.
+    #
+    # Returns nothing
+    def read_layouts(dir = '')
+      base = File.join(self.source, dir, "_layouts")
+      return unless File.exists?(base)
+      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
+    end
+
+    # Read all the files in <source>/<dir>/_posts and create a new Post
+    # object with each one.
+    #
+    # Returns nothing
+    def read_posts(dir)
+      base = File.join(self.source, dir, '_posts')
+      return unless File.exists?(base)
+      entries = Dir.chdir(base) { 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.future || post.date <= self.time)
+            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!
+    end
+
+    def generate
+      self.generators.each do |generator|
+        generator.generate(self)
+      end
+    end
+
+    def render
+      self.posts.each do |post|
+        post.render(self.layouts, site_payload)
+      end
+
+      self.pages.each do |page|
+        page.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 static files, pages and posts
+    #
+    # Returns nothing
+    def write
+      self.posts.each do |post|
+        post.write(self.dest)
+      end
+      self.pages.each do |page|
+        page.write(self.dest)
+      end
+      self.static_files.each do |sf|
+        sf.write(self.dest)
+      end
+    end
+
+    # Reads the directories and finds posts, pages and static files that will
+    # become part of the valid site according to the rules in +filter_entries+.
+    #   The +dir+ String is a relative path used to call this method
+    #            recursively as it descends through directories
+    #
+    # Returns nothing
+    def read_directories(dir = '')
+      base = File.join(self.source, dir)
+      entries = filter_entries(Dir.entries(base))
+
+      self.read_posts(dir)
+
+      entries.each do |f|
+        f_abs = File.join(base, f)
+        f_rel = File.join(dir, f)
+        if File.directory?(f_abs)
+          next if self.dest.sub(/\/$/, '') == f_abs
+          read_directories(f_rel)
+        elsif !File.symlink?(f_abs)
+          first3 = File.open(f_abs) { |fd| fd.read(3) }
+          if first3 == "---"
+            # file appears to have a YAML header so process it as a page
+            pages << Page.new(self, self.source, dir, f)
+          else
+            # otherwise treat it as a static file
+            static_files << StaticFile.new(self, self.source, dir, f)
+          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>],
+    #                     "pages" => [<Page>],
+    #                     "categories" => [<Post>]}
+    def site_payload
+      {"site" => self.config.merge({
+          "time"       => self.time,
+          "posts"      => self.posts.sort { |a,b| b <=> a },
+          "pages"      => self.pages,
+          "html_pages" => self.pages.reject { |page| !page.html? },
+          "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 "_"),
+    # or are excluded in the site configuration, unless they are web server
+    # files such as '.htaccess'
+    def filter_entries(entries)
+      entries = entries.reject do |e|
+        unless ['.htaccess'].include?(e)
+          ['.', '_', '#'].include?(e[0..0]) || e[-1..-1] == '~' || self.exclude.include?(e)
+        end
+      end
+    end
+
+  end
+end