mediacloth 0.0.2 → 0.0.3

data/lib/mediacloth/mediawikiast.rb

@@ -32,6 +32,48 @@ class TextAST < FormattedAST
     #Currently recognized formatting: :Link, :InternalLink, :HLine
 end
 
+#The node to represent a simple Mediawiki link.
+class LinkAST < AST
+    #The link's URL
+    attr_accessor :url
+end
+
+#The node to represent a Mediawiki internal link
+class InternalLinkAST < AST
+    #Holds the link locator, which is composed of a resource name only (e.g. the
+    #name of a wiki page)
+    attr_accessor :locator
+end
+
+#The node to represent a MediaWiki resource reference (embedded images, videos,
+#etc.)
+class ResourceLinkAST < AST
+    #The resource prefix that indicates the type of resource (e.g. an image
+    #resource is prefixed by "Image")
+    attr_accessor :prefix
+    #The resource locator
+    attr_accessor :locator
+end
+
+class InternalLinkItemAST < AST
+end
+
+#The node to represent a table
+class TableAST < AST
+    attr_accessor :options
+end
+
+#The node to represent a table
+class TableRowAST < AST
+    attr_accessor :options
+end
+
+#The node to represent a table
+class TableCellAST < AST
+    #the type of cell, :head or :body
+    attr_accessor :type
+end
+
 #The node to represent a list
 class ListAST < AST
     #Currently recognized types: :Bulleted, :Numbered

data/lib/mediacloth/mediawikihtmlgenerator.rb

@@ -17,60 +17,138 @@ class MediaWikiHTMLGenerator < MediaWikiWalker
         @html = ""
     end
 
+    def parse(ast)
+        @html = super(ast)
+    end
+    
+    #The default link handler. A custom link handler may extend this class.
+    class MediaWikiLinkHandler
+      
+      #Method invoked to resolve references to wiki pages when they occur in an
+      #internal link. In all the following internal links, the page name is
+      #<tt>My Page</tt>:
+      #* <tt>[[My Page]]</tt>
+      #* <tt>[[My Page|Click here to view my page]]</tt>
+      #* <tt>[[My Page|Click ''here'' to view my page]]</tt>
+      #The return value should be a URL that references the page resource.
+      def url_for(resource)
+        "javascript:void(0)"
+      end
+      
+      #Method invoked to resolve references to resources of unknown types. The
+      #type is indicated by the resource prefix. Examples of inline links to
+      #unknown references include:
+      #* <tt>[[Media:video.mpg]]</tt> (prefix <tt>Media</tt>, resource <tt>video.mpg</tt>)
+      #* <tt>[[Image:pretty.png|100px|A ''pretty'' picture]]</tt> (prefix <tt>Image</tt>,
+      #  resource <tt>pretty.png</tt>, and options <tt>100px</tt> and <tt>A
+      #  <i>pretty</i> picture</tt>.
+      #The return value should be a well-formed hyperlink, image, object or 
+      #applet tag.
+      def link_for(prefix, resource, options=[])
+        "<a href=\"javascript:void(0)\">#{prefix}:#{resource}(#{options.join(', ')})</a>"
+      end
+    end
+    
+    #Set this generator's URL handler.
+    def link_handler=(handler)
+      @link_handler = handler
+    end
+    
+    #Returns's this generator URL handler. If no handler was set, returns the default
+    #handler.
+    def link_handler
+      @link_handler ||= MediaWikiLinkHandler.new
+    end
+
 protected
 
     def parse_wiki_ast(ast)
-        super(ast)
+        super(ast).join
     end
 
     def parse_paragraph(ast)
-        @html += "<p>"
-        super(ast)
-        @html += "</p>"
+        "<p>" + super(ast) + "</p>"
     end
 
     def parse_text(ast)
         tag = formatting_to_tag(ast)
         if tag[0].empty?
-            @html += ast.contents
+            ast.contents
         else
-            @html += "<#{tag[0]}#{tag[1]}>#{ast.contents}</#{tag[0]}>"
+            "<#{tag[0]}#{tag[1]}>#{ast.contents}</#{tag[0]}>"
         end
-        super(ast)
     end
 
     def parse_formatted(ast)
         tag = formatting_to_tag(ast)
-        @html += "<#{tag}>"
-        super(ast)
-        @html += "</#{tag}>"
+        "<#{tag}>" + super(ast) + "</#{tag}>"
     end
 
     def parse_list(ast)
         tag = list_tag(ast)
-        @html += "<#{tag}>"
-        super(ast)
-        @html += "</#{tag}>"
+        (["<#{tag}>"] +
+         super(ast) +
+         ["</#{tag}>"]).join
     end
 
     def parse_list_item(ast)
-        @html += "<li>"
-        super(ast)
-        @html += "</li>"
+        "<li>" + super(ast) + "</li>"
     end
 
     def parse_preformatted(ast)
-        super(ast)
     end
 
     def parse_section(ast)
-        @html += "<h#{ast.level}>"
-        @html += ast.contents.strip
-        @html += "</h#{ast.level}>"
-        super(ast)
+        "<h#{ast.level}>" + super(ast) + "</h#{ast.level}>"
+    end
+    
+    def parse_internal_link(ast)
+        text = parse_wiki_ast(ast)
+        text = ast.locator if text.length == 0
+        href = link_handler.url_for(ast.locator)
+        "<a href=\"#{href}\">#{text}</a>"
+    end
+     
+    def parse_resource_link(ast)
+        options = ast.children.map do |node|
+            parse_internal_link_item(node)
+        end
+        link_handler.link_for(ast.prefix, ast.locator, options)
+    end
+
+    #Reimplement this
+    def parse_internal_link_item(ast)
+        text = super(ast)
+        text.strip
+    end
+    
+    def parse_link(ast)
+        text = super(ast)
+        href = ast.url
+        text = href if text.length == 0
+        "<a href=\"#{href}\">#{text}</a>"
     end
 
-private
+    #Reimplement this
+    def parse_table(ast)
+        options = ast.options ? ' ' + ast.options.strip : ''
+        "<table#{options}>" + super(ast) + "</table>\n"
+    end
+
+    #Reimplement this
+    def parse_table_row(ast)
+        options = ast.options ? ' ' + ast.options.strip : ''
+        "<tr#{options}>" + super(ast) + "</tr>\n"
+    end
+
+    #Reimplement this
+    def parse_table_cell(ast)
+        if ast.type == :head
+            "<th>" + super(ast) + "</th>"
+        else
+            "<td>" + super(ast) + "</td>"
+        end
+    end
 
     #returns an array with a tag name and tag attributes
     def formatting_to_tag(ast)
@@ -79,13 +157,6 @@ private
             tag = ["b", ""]
         elsif ast.formatting == :Italic
             tag = ["i", ""]
-        elsif ast.formatting == :Link or ast.formatting == :ExternalLink
-            links = ast.contents.split
-            link = links[0]
-            link_name = links[1, links.length-1].join(" ")
-            link_name = link if link_name.empty?
-            ast.contents = link_name
-            tag = ["a", " href=\"#{link}\" rel=\"nofollow\""]
         elsif ast.formatting == :HLine
             ast.contents = ""
             tag = ["hr", ""]