webgen 0.5.7 → 0.5.8

data/lib/webgen/sourcehandler.rb

@@ -62,7 +62,7 @@ module Webgen
             write_tree(tree)
           end
           puts "...done in " + ('%2.4f' % time.real) + ' seconds'
-        end while tree.node_access[:alcn].any? {|name,node| node.flagged(:created) || node.flagged(:reinit)}
+        end while tree.node_access[:alcn].any? {|name,node| node.flagged?(:created) || node.flagged?(:reinit)}
         :success
       end
 
@@ -86,7 +86,7 @@ module Webgen
             if deleted
               nodes_to_delete << node
               #TODO: delete output path
-            elsif (!node.flagged(:created) && find_all_source_paths[node.node_info[:src]].changed?) || node.meta_info_changed?
+            elsif (!node.flagged?(:created) && find_all_source_paths[node.node_info[:src]].changed?) || node.meta_info_changed?
               node.flag(:reinit)
               paths_to_use << node.node_info[:src]
             elsif node.changed?
@@ -98,7 +98,7 @@ module Webgen
           used_paths.merge(paths_to_use)
           paths = create_nodes_from_paths(tree, used_paths.to_a.sort)
           unused_paths.merge(used_paths - paths)
-          tree.node_access[:alcn].each {|name, node| tree.delete_node(node) if node.flagged(:reinit)}
+          tree.node_access[:alcn].each {|name, node| tree.delete_node(node) if node.flagged?(:reinit)}
           website.cache.reset_volatile_cache
         end until used_paths.empty?
       end
@@ -108,7 +108,7 @@ module Webgen
         output = website.blackboard.invoke(:output_instance)
 
         tree.node_access[:alcn].select do |name, node|
-          use_node = (node != tree.dummy_root && node.flagged(:dirty))
+          use_node = (node != tree.dummy_root && node.flagged?(:dirty))
           node.unflag(:dirty_meta_info)
           node.unflag(:created)
           node.unflag(:dirty)

data/lib/webgen/sourcehandler/base.rb

@@ -10,7 +10,7 @@ module Webgen::SourceHandler
   # This module should be included in every source handler as it provides the default methods for
   # creating nodes.
   #
-  # = Implementing Source Handlers
+  # == Implementing Source Handlers
   #
   # A source handler is a webgen extension that processes source paths to create nodes and that
   # provides the rendered content of these nodes. The nodes are later written to the output
@@ -27,42 +27,53 @@ module Webgen::SourceHandler
   # not need to reside under the Webgen::SourceHandler namespace but all shipped ones do.
   #
   # This base class provides useful default implementations of methods that are used by nearly all
-  # source handler class:
+  # source handler classes:
   # * #create_node
+  # * #output_path
   # * #node_exists?
   #
   # It also provides other utility methods:
   # * #page_from_path
   # * #content
   #
-  # = Nodes Created for Paths
+  # == Nodes Created for Paths
   #
   # The main functions of a source handler class are to create one or more nodes for a source path
   # and to provide the content of these nodes. To achieve this, certain information needs to be set
-  # on a node. If you use the methods provided by this base class, you don't need to set them
-  # explicitly because this is done by the provided methods.
+  # on a created node. If you use the +create_node+ method provided by this base class, you don't
+  # need to set them explicitly because this is done by the method:
   #
-  # <tt>node_info[:processor]</tt>:: Has to be set to the class name of the source handler. This is
+  # [<tt>node_info[:processor]</tt>] Has to be set to the class name of the source handler. This is
   #                                  used by the Node class: all unknown method calls are forwarded
   #                                  to the node processor.
-  # <tt>node_info[:src]</tt>:: Has to be set to the string version of the path that lead to the
+  # [<tt>node_info[:src]</tt>] Has to be set to the string version of the path that lead to the
   #                            creation of the node.
-  # <tt>node_info[:creation_path]</tt>:: Has to be set to the string version of the path that is
+  # [<tt>node_info[:creation_path]</tt>] Has to be set to the string version of the path that is
   #                                      used to create the path.
-  # <tt>meta_info['no_output']</tt>:: Has to be set to +true+ on nodes that are used during a
+  # [<tt>meta_info['no_output']</tt>] Has to be set to +true+ on nodes that are used during a
   #                                   webgen run but do not produce an output file.
-  # <tt>meta_info['modified_at']</tt>:: Is automatically set to the current time if not already set
+  # [<tt>meta_info['modified_at']</tt>] Has to be set to the current time if not already set
   #                                     correctly (ie. if not a Time object).
   #
-  # Note: The difference between +:src+ and +:creation_path+ is that a creation path need not have
-  # an existing source path representation. For example, fragments created from a page source path
-  # have a different +:creation_path+ which includes the fragment part.
+  # If <tt>meta_info['draft']</tt> is set on a path, then no node should be created in +create_node+
+  # and +nil+ has to be returned.
+  #
+  # Note: The difference between +:src+ and +:creation_path+ is that a creation path
+  # need not have an existing source path representation. For example, fragments created from a page
+  # source path have a different +:creation_path+ which includes the fragment part.
   #
   # Additional information that is used only for processing purposes should be stored in the
   # #node_info hash of a node as the #meta_info hash is reserved for real node meta information and
   # should not be changed once the node is created.
   #
-  # = Path Patterns and Invocation order
+  # == Output Path Names
+  #
+  # The method for creating an output path name for a source path is stored in the meta information
+  # +output_path+. If you don't use the provided method +output_path+, have a look at its
+  # implementation to see how to an output path gets created. Individual output path creation
+  # methods are stored as methods in the OutputPathHelpers module.
+  #
+  # == Path Patterns and Invocation order
   #
   # Path patterns define which paths are handled by a specific source handler. These patterns are
   # specified in the <tt>sourcehandler.patterns</tt> configuration hash as a mapping from the source
@@ -76,12 +87,12 @@ module Webgen::SourceHandler
   # invocation rank the earlier the specified source handlers are used.
   #
   # The default invocation ranks are:
-  # 1:: Early. Normally there is no need to use this rank.
-  # 5:: Standard. This is the rank the normal source handler should use.
-  # 9:: Late. This rank should be used by source handlers that operate on/use already created nodes
+  # [1] Early. Normally there is no need to use this rank.
+  # [5] Standard. This is the rank the normal source handler should use.
+  # [9] Late. This rank should be used by source handlers that operate on/use already created nodes
   #     and need to ensure that these nodes are available.
   #
-  # = Default Meta Information
+  # == Default Meta Information
   #
   # Each source handler can define default meta information that gets automatically set on the
   # source paths that are passed to the #create_node method.
@@ -90,7 +101,7 @@ module Webgen::SourceHandler
   # configuration hash as a mapping from the source handler class name to the meta information
   # hash.
   #
-  # = Sample Source Handler Class
+  # == Sample Source Handler Class
   #
   # Following is a simple source handler class example which copies paths from the source to
   # the output location modifying the extension:
@@ -119,9 +130,10 @@ module Webgen::SourceHandler
     #
     # All public methods of this module are considered to be output path creation methods and must
     # have the following parameters:
-    # +parent+:: the parent node
-    # +path+:: the path for which the output name should be created
-    # +use_lang_part+:: controls whether the output path name has to include the language part
+    #
+    # [+parent+] the parent node
+    # [+path+] the path for which the output name should be created
+    # [+use_lang_part+] controls whether the output path name has to include the language part
     module OutputPathHelpers
 
       # Default method for creating an output path for +parent+ and source +path+.
@@ -201,7 +213,7 @@ module Webgen::SourceHandler
         return node
       elsif !node
         node = Webgen::Node.new(parent, output_path, path.cn, path.meta_info)
-      elsif node.flagged(:reinit)
+      elsif node.flagged?(:reinit)
         node.reinit(output_path, path.meta_info)
       else
         return node
@@ -224,7 +236,7 @@ module Webgen::SourceHandler
     def page_from_path(path)
       begin
         page = Webgen::Page.from_data(path.io.data, path.meta_info)
-      rescue Webgen::WebgenPageFormatError => e
+      rescue Webgen::Page::FormatError => e
         raise "Error reading source path <#{path}>: #{e.message}"
       end
       path.meta_info = page.meta_info

data/lib/webgen/sourcehandler/copy.rb

@@ -30,7 +30,7 @@ module Webgen::SourceHandler
     def content(node)
       io = website.blackboard.invoke(:source_paths)[node.node_info[:src]].io
       if node.node_info[:preprocessor]
-        context = Webgen::ContentProcessor::Context.new(:content => io.data, :chain => [node])
+        context = Webgen::Context.new(:content => io.data, :chain => [node])
         website.blackboard.invoke(:content_processor, node.node_info[:preprocessor]).call(context)
         context.content
       else

data/lib/webgen/sourcehandler/feed.rb

@@ -45,7 +45,7 @@ module Webgen::SourceHandler
       block_name = node.node_info[:feed_type] + '_template'
       if node.node_info[:feed].blocks.has_key?(block_name)
         node.node_info[:feed].blocks[block_name].
-          render(Webgen::ContentProcessor::Context.new(:chain => [node])).content
+          render(Webgen::Context.new(:chain => [node])).content
       else
         feed = (website.cache.volatile[:sourcehandler_feed] ||= {})[node.node_info[:src]] ||= build_feed_for(node)
         feed.build_xml(node.node_info[:feed_type], (node.node_info[:feed_type] == 'rss' ? node['rss_version'] || 2.0 : nil))
@@ -90,7 +90,7 @@ module Webgen::SourceHandler
         item = FeedTools::FeedItem.new
         item.title = entry['title']
         item.link = File.join(site_url, entry.path)
-        item.content = entry.node_info[:page].blocks[node['content_block_name'] || 'content'].render(Webgen::ContentProcessor::Context.new(:chain => [entry])).content
+        item.content = entry.node_info[:page].blocks[node['content_block_name'] || 'content'].render(Webgen::Context.new(:chain => [entry])).content
         item.updated = entry['modified_at']
         item.published = entry['created_at'] if entry['created_at'].kind_of?(Time)
         if entry['author']

data/lib/webgen/sourcehandler/fragment.rb

@@ -10,7 +10,7 @@ module Webgen::SourceHandler
     include Webgen::WebsiteAccess
 
     HTML_HEADER_REGEXP = /<h([123456])(?:>|\s([^>]*)>)(.*?)<\/h\1\s*>/i
-    HTML_ATTR_REGEXP = /\s*(\w+)\s*=\s*('|")([^\2]+)\2\s*/
+    HTML_ATTR_REGEXP = /\s*(\w+)\s*=\s*('|")(.+?)\2\s*/
 
     # Parse the string +content+ for headers +h1+, ..., +h6+ and return the found, nested sections.
     #

data/lib/webgen/sourcehandler/metainfo.rb

@@ -28,10 +28,12 @@ module Webgen::SourceHandler
       super(parent, path) do |node|
         [[:mi_paths, 'paths'], [:mi_alcn, 'alcn']].each do |mi_key, block_name|
           node.node_info[mi_key] = {}
-          YAML::load(page.blocks[block_name].content).each do |key, value|
-            key = Webgen::Common.absolute_path(key, parent.absolute_lcn)
-            node.node_info[mi_key][key] = value
-          end if page.blocks.has_key?(block_name)
+          if page.blocks.has_key?(block_name) && (data = YAML::load(page.blocks[block_name].content))
+            data.each do |key, value|
+              key = Webgen::Common.absolute_path(key, parent.absolute_lcn)
+              node.node_info[mi_key][key] = value
+            end
+          end
         end
 
         mark_all_matched_dirty(node, :no_old_data)
@@ -66,7 +68,14 @@ module Webgen::SourceHandler
            (option == :force || (!cached && option == :no_old_data) || mi != cached[:mi_paths][pattern])
        end || mi_node.node_info[:mi_alcn].any? do |pattern, mi|
          node =~ pattern && (option == :force || (!cached && option == :no_old_data) || mi != cached[:mi_alcn][pattern])
-       end)
+       end || (option == :no_old_data && cached &&
+               ((cached[:mi_paths].keys - mi_node.node_info[:mi_paths].keys).any? do |p|
+                 Webgen::Path.match(node.node_info[:creation_path], p)
+                end || (cached[:mi_alcn].keys - mi_node.node_info[:mi_alcn].keys).any? do |p|
+                  node =~ p
+                end)
+               )
+       )
     end
 
     # Mark all nodes that are matched by a path or an alcn specifcation in the meta info node +node+
@@ -99,7 +108,7 @@ module Webgen::SourceHandler
     # node in question has changed.
     def node_meta_info_changed?(node)
       self.nodes.each do |n|
-        if n.flagged(:created) && meta_info_changed?(n, node)
+        if n.flagged?(:created) && meta_info_changed?(n, node)
           node.flag(:dirty_meta_info)
           return
         end

data/lib/webgen/sourcehandler/page.rb

@@ -32,7 +32,7 @@ module Webgen::SourceHandler
 
       if chain.first.node_info[:page].blocks.has_key?(block_name)
         node.node_info[:used_nodes] << chain.first.absolute_lcn
-        context = chain.first.node_info[:page].blocks[block_name].render(Webgen::ContentProcessor::Context.new(:chain => chain))
+        context = chain.first.node_info[:page].blocks[block_name].render(Webgen::Context.new(:chain => chain))
         context.content
       else
         raise "Error rendering <#{node.absolute_lcn}>: no block named '#{block_name}' in <#{chain.first.absolute_lcn}>"
@@ -47,11 +47,15 @@ module Webgen::SourceHandler
     # Checks if the meta information provided by the file in Webgen Page Format changed.
     def meta_info_changed?(node)
       path = website.blackboard.invoke(:source_paths)[node.node_info[:src]]
-      return if node.node_info[:processor] != self.class.name || !path.changed?
+      return if node.node_info[:processor] != self.class.name || (path && !path.changed?)
 
-      old_mi = node.node_info[:sh_page_node_mi]
-      new_mi = Webgen::Page.meta_info_from_data(path.io.data)
-      node.flag(:dirty_meta_info) if old_mi && old_mi != new_mi
+      if !path
+        node.flag(:dirty_meta_info)
+      else
+        old_mi = node.node_info[:sh_page_node_mi]
+        new_mi = Webgen::Page.meta_info_from_data(path.io.data)
+        node.flag(:dirty_meta_info) if old_mi && old_mi != new_mi
+      end
     end
 
   end

data/lib/webgen/sourcehandler/virtual.rb

@@ -14,17 +14,20 @@ module Webgen::SourceHandler
     include Base
     include Webgen::WebsiteAccess
 
+    def initialize # :nodoc:
+      website.blackboard.add_listener(:node_meta_info_changed?, method(:node_meta_info_changed?))
+      @path_data = {}
+    end
+
     # Create all virtual nodes under +parent+ which are specified in +path+.
     def create_node(parent, path)
-      page = page_from_path(path)
       nodes = []
-      YAML::load(page.blocks['content'].content).each do |key, meta_info|
+      read_data(path).each do |key, meta_info|
+        cache_data = [key, meta_info.dup]
+
         key = Webgen::Common.absolute_path(key, parent.absolute_lcn) + (key =~ /\/$/ ? '/' : '')
         temp_parent = create_directories(parent.tree.root, File.dirname(key), path)
 
-        meta_info ||= {}
-        meta_info['modified_at'] = path.meta_info['modified_at']
-        meta_info['no_output'] = true
         output_path = meta_info.delete('url') || key
         output_path = (URI::parse(output_path).absolute? || output_path =~ /^\// ?
                        output_path : File.join(temp_parent.absolute_lcn, output_path))
@@ -35,10 +38,12 @@ module Webgen::SourceHandler
           nodes += website.blackboard.invoke(:create_nodes, parent.tree, temp_parent.absolute_lcn,
                                              Webgen::Path.new(key, path.source_path), self) do |cn_parent, cn_path|
             cn_path.meta_info.update(meta_info)
-            super(cn_parent, cn_path, output_path)
+            super(cn_parent, cn_path, output_path) do |n|
+              n.node_info[:sh_virtual_cache_data] = cache_data
+            end
           end
         end
-      end if page.blocks.has_key?('content')
+      end
       nodes.compact
     end
 
@@ -46,6 +51,23 @@ module Webgen::SourceHandler
     private
     #######
 
+    # Read the entries from the virtual file +data+ and yield the path, and the meta info hash for
+    # each entry. The +parent+ parameter is used for making absolute path values if relative ones
+    # are given.
+    def read_data(path)
+      if !@path_data.has_key?(path) || path.changed?
+        page = page_from_path(path)
+        @path_data[path] = YAML::load(page.blocks['content'].content).collect do |key, meta_info|
+          meta_info ||= {}
+          meta_info['modified_at'] = path.meta_info['modified_at']
+          meta_info['no_output'] = true
+          [key, meta_info]
+        end if page.blocks.has_key?('content')
+        @path_data[path] ||= []
+      end
+      @path_data[path]
+    end
+
     # Create the needed parent directories for a virtual node.
     def create_directories(parent, dirname, path)
       dirname.sub(/^\//, '').split('/').each do |dir|
@@ -72,6 +94,21 @@ module Webgen::SourceHandler
       parent
     end
 
+    # Check if the +node+ is virtual and if, if its meta information has changed. This can only be
+    # the case if the node has been recreated in this run.
+    def node_meta_info_changed?(node)
+      path = website.blackboard.invoke(:source_paths)[node.node_info[:src]]
+      return if node.node_info[:processor] != self.class.name || (path && !path.changed?)
+
+      if !path
+        node.flag(:dirty_meta_info)
+      else
+        old_data = node.node_info[:sh_virtual_cache_data]
+        new_data = read_data(path).find {|key, mi| key == old_data.first}
+        node.flag(:dirty_meta_info) if !new_data || old_data.last != new_data.last
+      end
+    end
+
   end
 
 end

data/lib/webgen/tag/base.rb

@@ -7,7 +7,7 @@ require 'webgen/websiteaccess'
 # This module should be mixed into any class that wants to serve as a webgen tag class. Have a look
 # a the example below to see how a basic tag class looks like.
 #
-# = Tag classes
+# == Tag classes
 #
 # A tag class is a webgen extension that handles specific webgen tags. webgen tags are used to add
 # dynamic content to page and template files and are made for ease of use.
@@ -23,18 +23,21 @@ require 'webgen/websiteaccess'
 # Tag classes *can* also choose to not use this module. If they don't use it they have to provide
 # the following methods: +set_params+, +create_tag_params+, +call+.
 #
-# = Tag parameters
+# == Tag parameters
 #
 # webgen tags allow the specification of parameters in the tag definition. The method
 # +tag_params_list+ returns all configuration entries that can be set this way. And the method
-# +tag_config_base+ is used to resolve partially stated configuration entries. An additional
-# configuration entry option is also used: <tt>:mandatory</tt>. If this key is set to +true+ for a
-# configuration entry, the entry counts as mandatory and needs to be set in the tag definition. If
-# this key is set to +default+, this means that this entry should be the default mandatory parameter
-# (used when only a string is provided in the tag definition). There *should* be only one default
-# mandatory parameter.
+# +tag_config_base+ is used to resolve partially stated configuration entries. The default method
+# uses the full class name, strips a <tt>Webgen::</tt> part at the beginning away, substitutes
+# <tt>.</tt> for <tt>::</tt> and makes everything lowercase.
 #
-# = Sample Tag Class
+# An additional configuration entry option is also used: <tt>:mandatory</tt>. If this key is set to
+# +true+ for a configuration entry, the entry counts as mandatory and needs to be set in the tag
+# definition. If this key is set to +default+, this means that this entry should be the default
+# mandatory parameter (used when only a string is provided in the tag definition). There *should* be
+# only one default mandatory parameter.
+#
+# == Sample Tag Class
 #
 # Following is a simple tag class example which just reverses the body text and adds some
 # information about the context to the result. Note that the class does not reside in the
@@ -90,7 +93,7 @@ module Webgen::Tag::Base
   # The parameter +body+ holds the optional body value for the tag.
   #
   # The +context+ parameter holds all relevant information for processing. Have a look at the
-  # Webgen::ContentProcessor::Context class to see what is available.
+  # Webgen::Context class to see what is available.
   #
   # The method has to return the result of the tag processing and, optionally, a boolean value
   # specifying if the result should further be processed (ie. webgen tags replaced).
@@ -104,13 +107,16 @@ module Webgen::Tag::Base
   private
   #######
 
-  # The base part of the configuration name. This is normally the class name without the Webgen
-  # module downcased and all "::" substituted with "." (e.g. Webgen::Tag::Menu -> tag.menu).
+  # The base part of the configuration name. This isthe class name without the Webgen module
+  # downcased and all "::" substituted with "." (e.g. Webgen::Tag::Menu -> tag.menu). By overriding
+  # this method one can provide a different way of specifying the base part of the configuration
+  # name.
   def tag_config_base
     self.class.name.gsub('::', '.').gsub(/^Webgen\./, '').downcase
   end
 
-  # Return the list of all parameters for the tag class.
+  # Return the list of all parameters for the tag class. All configuration options starting with
+  # +tag_config_base+ are used.
   def tag_params_list
     regexp = /^#{tag_config_base}/
     website.config.data.keys.select {|key| key =~ regexp}

data/lib/webgen/tag/link.rb

@@ -10,6 +10,7 @@ module Webgen::Tag
     # Return a HTML link to the given (A)LCN.
     def call(tag, body, context)
       if (dest_node = context.ref_node.resolve(param('tag.link.path'), context.dest_node.lang))
+        context.dest_node.node_info[:used_meta_info_nodes] << dest_node.absolute_lcn
         context.dest_node.link_to(dest_node, param('tag.link.attr').merge(:lang => context.content_node.lang))
       else
         raise ArgumentError, 'Resolving of path failed'

data/lib/webgen/version.rb

@@ -3,6 +3,6 @@
 module Webgen
 
   # The version of webgen.
-  VERSION = '0.5.7'
+  VERSION = '0.5.8'
 
 end

data/lib/webgen/webgentask.rb

@@ -41,30 +41,33 @@ module Webgen
   # It is assumed that you have already used the 'webgen' command to create the website directory
   # for the site.
   #
-  # === Basics
+  # == Basics
   #
   #   require 'webgen/webgentask'
   #
   #   Webgen::WebgenTask.new
   #
-  # === Attributes
+  # == Attributes
   #
   # The attributes available in the new block are:
   #
-  # * directory         - the root directory of the webgen site
-  #                       (default Dir.pwd)
-  # * config            - the config block for setting additional configuration options
-  # * clobber_outdir    - remove webgens output directory on clobber
-  #                       (default false)
+  # [directory]
+  #    the root directory of the webgen site (default <tt>Dir.pwd</tt>)
+  # [config]
+  #   the config block for setting additional configuration options
+  # [clobber_outdir]
+  #   remove webgens output directory on clobber (default +false+)
   #
-  # === Tasks Provided
+  # == Tasks Provided
   #
   # The tasks provided are :
   #
-  # * webgen         - render the webgen website
-  # * clobber_webgen - remove all the files created during generation
+  # [webgen]
+  #   render the webgen website
+  # [clobber_webgen]
+  #   remove all the files created during generation
   #
-  # === Integrate webgen in other project
+  # == Integrate webgen in other project
   #
   # To integrate webgen tasks in another project you can use rake namespaces.  For example assuming
   # webgen's site directory is +webgen+ under the main project directory use the following code
@@ -96,8 +99,7 @@ module Webgen
     # The directory of the webgen website. This would be the directory of your <tt>config.yaml</tt>
     # file. Or the parent directory of the <tt>src/</tt> directory for webgen.
     #
-    # The default for this is assumed to be
-    #   Dir.pwd
+    # The default for this is assumed to be <tt>Dir.pwd</tt>
     attr_accessor :directory
 
     # The configuration block that is invoked when the Webgen::Website object is initialized. This