maruku 0.4.0 → 0.4.1

data/lib/maruku/input/parse_doc.rb

@@ -21,6 +21,7 @@
 
 require 'iconv'
 
+
 module MaRuKu; module In; module Markdown; module BlockLevelParser
 		
 	def parse_doc(s)
@@ -31,10 +32,20 @@ module MaRuKu; module In; module Markdown; module BlockLevelParser
 		
 		self.attributes.merge! meta2
 		
+=begin maruku_doc
+Attribute: encoding
+Scope:     document
+Summary:   Encoding for the document.
+
+If the `encoding` attribute is specified, then the content
+will be converted from the specified encoding to UTF-8.
+
+Conversion happens using the `iconv` library.
+=end
+
 		enc = self.attributes[:encoding]
 		self.attributes.delete :encoding
 		if enc && enc.downcase != 'utf-8'
-#			puts "Converting from #{enc} to UTF-8."
 			converted = Iconv.new('utf-8', enc).iconv(data)
 			
 #			puts "Data: #{data.inspect}: #{data}"
@@ -71,8 +82,19 @@ module MaRuKu; module In; module Markdown; module BlockLevelParser
 			expand_attribute_list(e.al, e.attributes)
 #			puts "#{e.node_type}: #{e.attributes.inspect}"
 		end
-		
-#		puts self.inspect
+	
+=begin maruku_doc
+Attribute: exec
+Scope:     document
+Summary:   Enables execution of XML instructions.
+
+Disabled by default because of security concerns.
+=end
+
+		if Maruku::Globals[:unsafe_features]
+			self.execute_code_blocks
+			# TODO: remove executed code blocks
+		end
 	end
 	
 	# Expands an attribute list in an Hash
@@ -111,6 +133,38 @@ module MaRuKu; module In; module Markdown; module BlockLevelParser
 		end
 	end
 
+	def execute_code_blocks
+		self.each_element(:xml_instr) do |e|
+			if e.target == 'maruku'
+				puts e.attributes.inspect
+				code = e.code
+				result = nil
+				begin
+					 e.instance_eval(code)
+				rescue Exception => e
+					maruku_error "Exception while executing this:\n"+
+						add_tabs(code, 1, ">")+
+						"\nThe error was:\n"+
+						add_tabs(e.inspect+"\n"+e.caller.join("\n"), 1, "|")
+					next
+				rescue RuntimeError => e
+					maruku_error "2: Exception while executing this:\n"+
+						add_tabs(code, 1, ">")+
+						"\nThe error was:\n"+
+						add_tabs(e.inspect, 1, "|")
+				rescue SyntaxError => e
+					maruku_error "2: Exception while executing this:\n"+
+						add_tabs(code, 1, ">")+
+						"\nThe error was:\n"+
+						add_tabs(e.inspect, 1, "|")
+				end
+				if result.kind_of?(String)
+					puts "Result is : #{result.inspect}"
+				end
+			end
+		end
+	end
+	
 	def search_abbreviations
 		self.abbreviations.each do |abbrev, title|
 			reg = Regexp.new(Regexp.escape(abbrev))

data/lib/maruku/input/parse_span_better.rb

@@ -89,8 +89,13 @@ module MaRuKu; module In; module Markdown; module SpanLevelParser
 				# 3) url "<http:// ", "<ftp:// ..."
 				# 4) email "<andrea@... ", "<mailto:andrea@..."
 				# 5) on itself! "a < b	"
+				# 6) Start of <<guillemettes>>
 				
 				case d = src.next_char
+					when ?<;  # guillemettes
+						src.ignore_chars(2)
+						con.push_char ?<
+						con.push_char ?<
 					when ?!; 
 						if src.cur_chars_are '<!--'
 							read_inline_html(src, con)
@@ -98,7 +103,7 @@ module MaRuKu; module In; module Markdown; module SpanLevelParser
 							con.push_char src.shift_char
 						end
 					when ?? 
-						read_server_directive(src, con) 
+						read_xml_instr_span(src, con) 
 					when ?\ , ?\t 
 						con.push_char src.shift_char
 					else
@@ -117,7 +122,13 @@ module MaRuKu; module In; module Markdown; module SpanLevelParser
 				end
 			when ?\\
 				d = src.next_char
-				if escaped.include? d
+				if d == ?'
+					src.ignore_chars(2)
+					con.push_element md_entity('apos')
+				elsif d == ?"
+					src.ignore_chars(2)
+					con.push_element md_entity('quot')
+				elsif escaped.include? d
 					src.ignore_chars(2)
 					con.push_char d
 				else
@@ -236,13 +247,22 @@ module MaRuKu; module In; module Markdown; module SpanLevelParser
 			con.elements.pop if s.size == 0 
 		end
 		
-		con.elements
+		educated = educate(con.elements)
+
+		educated
 	end
 	
-	def read_server_directive(src, con) 
-		delim = "?>"
+	def read_xml_instr_span(src, con) 
+		src.ignore_chars(2) # starting <?
+
+		# read target <?target code... ?>
+		target = if m = src.read_regexp(/(\w+)/)
+			m[1]
+		else
+			''
+		end
 		
-		src.ignore_chars delim.size
+		delim = "?>"
 		
 		code = 
 			read_simple(src, escaped=[], break_on_chars=[], 
@@ -251,7 +271,7 @@ module MaRuKu; module In; module Markdown; module SpanLevelParser
 		src.ignore_chars delim.size
 		
 		code = (code || "").strip
-		con.push_element md_server(code)
+		con.push_element md_xml_instr(target, code)
 	end
 
 	def read_url_el(src,con)
@@ -340,7 +360,7 @@ module MaRuKu; module In; module Markdown; module SpanLevelParser
 				"#{exit_on_chars.map{|x|""<<x}.inspect})"+
 				" already read: #{text.inspect}"
 				maruku_error s, src
-				maruku_recover "I boldly continue", src, con
+				maruku_recover "I boldly continue", src
 				break
 			when ?\\
 				d = src.next_char

data/lib/maruku/input/rubypants.rb

@@ -0,0 +1,225 @@
+#--
+#   Copyright (C) 2006  Andrea Censi  <andrea (at) rubyforge.org>
+#
+# This file is part of Maruku.
+# 
+#   Maruku is free software; you can redistribute it and/or modify
+#   it under the terms of the GNU General Public License as published by
+#   the Free Software Foundation; either version 2 of the License, or
+#   (at your option) any later version.
+# 
+#   Maruku is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#   GNU General Public License for more details.
+# 
+#   You should have received a copy of the GNU General Public License
+#   along with Maruku; if not, write to the Free Software
+#   Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+#++
+
+#
+# NOTA BENE: 
+#
+# The following algorithm is a rip-off of RubyPants written by 
+# Christian Neukirchen. 
+#
+# RubyPants is a Ruby port of SmartyPants written by John Gruber.
+#
+# This file is distributed under the GPL, which I guess is compatible
+# with the terms of the RubyPants license.
+#
+# -- Andrea Censi
+
+
+# = RubyPants -- SmartyPants ported to Ruby
+#
+# Ported by Christian Neukirchen <mailto:chneukirchen@gmail.com>
+#   Copyright (C) 2004 Christian Neukirchen
+#
+# Incooporates ideas, comments and documentation by Chad Miller
+#   Copyright (C) 2004 Chad Miller
+#
+# Original SmartyPants by John Gruber
+#   Copyright (C) 2003 John Gruber
+#
+
+#
+# = RubyPants -- SmartyPants ported to Ruby
+#
+#
+# [snip]
+#
+# == Authors
+# 
+# John Gruber did all of the hard work of writing this software in
+# Perl for Movable Type and almost all of this useful documentation.
+# Chad Miller ported it to Python to use with Pyblosxom.
+#
+# Christian Neukirchen provided the Ruby port, as a general-purpose
+# library that follows the *Cloth API.
+# 
+#
+# == Copyright and License
+# 
+# === SmartyPants license:
+# 
+# Copyright (c) 2003 John Gruber
+# (http://daringfireball.net)
+# All rights reserved.
+# 
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 
+# * Redistributions of source code must retain the above copyright
+#   notice, this list of conditions and the following disclaimer.
+# 
+# * Redistributions in binary form must reproduce the above copyright
+#   notice, this list of conditions and the following disclaimer in
+#   the documentation and/or other materials provided with the
+#   distribution.
+# 
+# * Neither the name "SmartyPants" nor the names of its contributors
+#   may be used to endorse or promote products derived from this
+#   software without specific prior written permission.
+# 
+# This software is provided by the copyright holders and contributors
+# "as is" and any express or implied warranties, including, but not
+# limited to, the implied warranties of merchantability and fitness
+# for a particular purpose are disclaimed. In no event shall the
+# copyright owner or contributors be liable for any direct, indirect,
+# incidental, special, exemplary, or consequential damages (including,
+# but not limited to, procurement of substitute goods or services;
+# loss of use, data, or profits; or business interruption) however
+# caused and on any theory of liability, whether in contract, strict
+# liability, or tort (including negligence or otherwise) arising in
+# any way out of the use of this software, even if advised of the
+# possibility of such damage.
+# 
+# === RubyPants license
+# 
+# RubyPants is a derivative work of SmartyPants and smartypants.py.
+# 
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 
+# * Redistributions of source code must retain the above copyright
+#   notice, this list of conditions and the following disclaimer.
+# 
+# * Redistributions in binary form must reproduce the above copyright
+#   notice, this list of conditions and the following disclaimer in
+#   the documentation and/or other materials provided with the
+#   distribution.
+# 
+# This software is provided by the copyright holders and contributors
+# "as is" and any express or implied warranties, including, but not
+# limited to, the implied warranties of merchantability and fitness
+# for a particular purpose are disclaimed. In no event shall the
+# copyright owner or contributors be liable for any direct, indirect,
+# incidental, special, exemplary, or consequential damages (including,
+# but not limited to, procurement of substitute goods or services;
+# loss of use, data, or profits; or business interruption) however
+# caused and on any theory of liability, whether in contract, strict
+# liability, or tort (including negligence or otherwise) arising in
+# any way out of the use of this software, even if advised of the
+# possibility of such damage.
+# 
+#
+# == Links
+#
+# John Gruber:: http://daringfireball.net
+# SmartyPants:: http://daringfireball.net/projects/smartypants
+#
+# Chad Miller:: http://web.chad.org
+#
+# Christian Neukirchen:: http://kronavita.de/chris
+
+
+module MaRuKu; module In; module Markdown; module SpanLevelParser
+	Punct_class = '[!"#\$\%\'()*+,\-.\/:;<=>?\@\[\\\\\]\^_`{|}~]'
+	Close_class = %![^\ \t\r\n\\[\{\(\-]!
+
+	Rules = [
+		[/---/,   :mdash          ],
+		[/--/,    :ndash          ],
+		['...',   :hellip         ],
+		['. . .', :hellip         ],
+		["``",    :ldquo          ],
+		["''",    :rdquo          ],
+		[/<<\s/,  [:laquo, :nbsp] ],
+		[/\s>>/,  [:nbsp, :raquo] ],
+		[/<</,    :laquo          ],
+		[/>>/,    :raquo          ],
+		
+#		def educate_single_backticks(str)
+#		["`", :lsquo]
+#		["'", :rsquo]
+
+		# Special case if the very first character is a quote followed by
+		# punctuation at a non-word-break. Close the quotes by brute
+		# force:
+		[/^'(?=#{Punct_class}\B)/, :rsquo],
+		[/^"(?=#{Punct_class}\B)/, :rdquo],
+		# Special case for double sets of quotes, e.g.:
+		#   <p>He said, "'Quoted' words in a larger quote."</p>
+		[/"'(?=\w)/, [:ldquo, :lsquo]    ],
+		[/'"(?=\w)/, [:lsquo, :ldquo]    ],
+		# Special case for decade abbreviations (the '80s):
+		[/'(?=\d\ds)/, :rsquo            ],
+		# Get most opening single quotes:
+		[/(\s)'(?=\w)/, [:one, :lsquo]   ],
+		# Single closing quotes:
+		[/(#{Close_class})'/, [:one, :rsquo]],
+		[/'(\s|s\b|$)/, [:rsquo, :one]],
+		# Any remaining single quotes should be opening ones:
+		[/'/, :lsquo],
+		# Get most opening double quotes:
+		[/(\s)"(?=\w)/, [:one, :ldquo]],
+		# Double closing quotes:
+		[/(#{Close_class})"/, [:one, :rdquo]],
+		[/"(\s|s\b|$)/, [:rdquo, :one]],
+		# Any remaining quotes should be opening ones:
+		[/"/, :ldquo]
+	].
+	map{|reg, subst| # People should do the thinking, machines should do the work.
+		reg = Regexp.new(Regexp.escape(reg)) if not reg.kind_of? Regexp
+		subst = [subst] if not subst.kind_of?Array
+		[reg, subst]}
+
+# note: input will be destroyed
+def apply_one_rule(reg, subst, input)
+	output = []
+	while first = input.shift
+		if first.kind_of?(String) && (m = reg.match(first))
+			output.push    m. pre_match if m. pre_match.size > 0
+			 input.unshift m.post_match if m.post_match.size > 0
+			subst.reverse.each do |x|
+				input.unshift( x == :one ? m[1] : md_entity(x.to_s) ) end
+		else
+			output.push first
+		end
+	end
+	return output
+end
+	
+def educate(elements)
+	Rules.each do |reg, subst|
+		elements = apply_one_rule(reg, subst, elements)
+	end
+	# strips empty strings
+	elements.delete_if {|x| x.kind_of?(String) && x.size == 0}
+	final = []
+	# join consecutive strings
+	elements.each do |x|
+		if x.kind_of?(String) && final.last.kind_of?(String)
+			final.last << x
+		else
+			final << x
+		end
+	end
+	return final
+end
+
+end end end end

data/lib/maruku/input/type_detection.rb

@@ -46,6 +46,7 @@ module MaRuKu; module Strings
 		# line that were mistaken for raw_html
 		return :text     if l=~EMailAddress or l=~ URL
 		# raw html is like PHP Markdown Extra: at most three spaces before
+		return :xml_instr if l =~ %r{^\s*<\?}
 		return :raw_html if l =~ %r{^[ ]?[ ]?[ ]?</?\s*\w+}
 		return :raw_html if l =~ %r{[ ]{0,3}<\!\-\-}
 		return :ulist    if l =~ /^\s?([\*\-\+])\s+.*\w+/

data/lib/maruku/output/to_html.rb

@@ -40,8 +40,6 @@ class REXML::Element
 	 public :write_children 
 end
 
-
-
 # This module groups all functions related to HTML export.
 module MaRuKu; module Out; module HTML
 	include REXML
@@ -64,7 +62,6 @@ module MaRuKu; module Out; module HTML
 		
 		doc = Document.new(nil,{:respect_whitespace =>:all})
 		doc << div
-		#add_whitespace(doc)
 		
 		# REXML Bug? if indent!=-1 whitespace is not respected for 'pre' elements
 		# containing code.
@@ -98,7 +95,7 @@ module MaRuKu; module Out; module HTML
 		root = Element.new('html', doc)
 		root.add_namespace('http://www.w3.org/1999/xhtml')
 		
-		lang = @attributes[:lang] || 'en'
+		lang = self.attributes[:lang] || 'en'
 		root.attributes['lang'] = lang
 		root.attributes['xml:lang'] = lang
 		
@@ -110,15 +107,12 @@ module MaRuKu; module Out; module HTML
 			me.attributes['content'] = 'text/html; charset=utf-8'	
 		
 			# Create title element
-			doc_title = @attributes[:title] || @attributes[:subject] || ""
+			doc_title = self.attributes[:title] || self.attributes[:subject] || ""
 			title = Element.new 'title', head
 				title << Text.new(doc_title)
 				
-			# Encoding
-			
-			
 			
-			css = @attributes[:css]
+			css = self.attributes[:css]
 			if css
 				# <link type="text/css" rel="stylesheet" href="..." />
 				link = Element.new 'link'
@@ -145,7 +139,6 @@ module MaRuKu; module Out; module HTML
 			
 		root << body
 		
-	#	add_whitespace(doc)
 		doc
 	end
 	
@@ -195,7 +188,7 @@ module MaRuKu; module Out; module HTML
 				span << Text.new('Created by ')
 				a = Element.new('a', span)
 					a.attributes['href'] = 'http://maruku.rubyforge.org'
-					a.attributes['title'] = 'Maruku: a Markdown interpreter'
+					a.attributes['title'] = 'Maruku: a Markdown interpreter for Ruby'
 					a << Text.new('Maruku')
 				span << Text.new(nice_date+".")
 		div
@@ -227,7 +220,7 @@ module MaRuKu; module Out; module HTML
 	end
 
 
-	def to_html_hrule; Element.new 'hr' end
+	def to_html_hrule; create_html_element 'hr' end
 	def to_html_linebreak; Element.new 'br' end
 
 	# renders children as html and wraps into an element of given name
@@ -314,7 +307,7 @@ module MaRuKu; module Out; module HTML
 	def to_html_code; 
 		source = self.raw_code
 
-		lang = @attributes[:lang] || @doc.attributes[:code_lang] 
+		lang = self.attributes[:lang] || @doc.attributes[:code_lang] 
 
 		lang = 'xml' if lang=='html'
 		use_syntax = get_setting(:html_use_syntax)
@@ -329,12 +322,6 @@ module MaRuKu; module Out; module HTML
 				
 				html = convertor.convert( source )
 			
-				show_spaces = get_setting(:code_show_spaces) 
-				if show_spaces
-					s.gsub!(/\t/,'&raquo;'+'&nbsp;'*3)
-					s.gsub!(/ /,'&not;')
-				end
-			
 				pre = Document.new(html, {:respect_whitespace =>:all}).root
 				pre.attributes['class'] = lang
 				pre
@@ -365,6 +352,8 @@ module MaRuKu; module Out; module HTML
 		
 		s  = s.gsub(/&/,'&amp;')
 		s = Text.normalize(s)
+		s  = s.gsub(/\&apos;/,'&#39;') # IE bug
+		s  = s.gsub(/'/,'&#39;') # IE bug
 
 		show_spaces = get_setting(:code_show_spaces) 
 		if show_spaces
@@ -372,7 +361,7 @@ module MaRuKu; module Out; module HTML
 			s.gsub!(/ /,'&not;')
 		end
 
-		text = Text.new(s, true, nil, false )
+		text = Text.new(s, respect_ws=true, parent=nil, raw=true )
 		
 		code << text
 		pre
@@ -411,8 +400,8 @@ module MaRuKu; module Out; module HTML
 		if ref = @doc.refs[id]
 			url = ref[:url]
 			title = ref[:title]
-			a.attributes['href']=url if url
-			a.attributes['title']=title if title
+			a.attributes['href'] = url if url
+			a.attributes['title'] = title if title
 		else
 			maruku_error"Could not find ref_id = #{id.inspect} for #{self.inspect}"
 			tell_user "Not creating a link for ref_id = #{id.inspect}."
@@ -422,18 +411,17 @@ module MaRuKu; module Out; module HTML
 	end
 	
 	def to_html_im_link
-		a =  wrap_as_element 'a'
-		url = self.url
-		title = self.title
-		if url
+		if url = self.url
+			title = self.title
+			a =  wrap_as_element 'a'
 			a.attributes['href'] = url
 			a.attributes['title'] = title if title
+			return a
 		else
 			maruku_error"Could not find url in #{self.inspect}"
 			tell_user "Not creating a link for ref_id = #{id.inspect}."
 			return wrap_as_element('span')
 		end
-		return a
 	end
 	
 	def add_ws(e)
@@ -471,9 +459,7 @@ module MaRuKu; module Out; module HTML
 			url = ref[:url]
 			a.attributes['src'] = url
 			[:title, :class, :style].each do |s| 
-				if ref[s] then
-					a.attributes[s.to_s] = ref[s]
-				end
+				a.attributes[s.to_s] = ref[s] if ref[s]
 			end
 		else
 			maruku_error"Could not find id = #{id.inspect} for\n #{self.inspect}"
@@ -485,17 +471,16 @@ module MaRuKu; module Out; module HTML
 	end
 	
 	def to_html_im_image
-		a =  Element.new 'img'
-		url = self.url
-		title = self.title
-		if not url
+		if not url = self.url
 			maruku_error"Image with no url: #{self.inspect}"
 			tell_user "Could not create image with ref_id = #{id.inspect};"+
 			 +" Using SPAN element as replacement."
 			return wrap_as_element('span')
 		end
-		a.attributes['src'] = url
-		a.attributes['title'] = title if title
+		title = self.title
+		a =  Element.new 'img'
+			a.attributes['src'] = url
+			a.attributes['title'] = title if title
 		return a
 	end
 
@@ -555,17 +540,14 @@ module MaRuKu; module Out; module HTML
 			
 		sup
 	end
+	
 ## Definition lists ###
-	def to_html_definition_list
-		wrap_as_element('dl')
-	end
-	def to_html_definition		
-		children_to_html
-	end
-	def to_html_definition_term; wrap_as_element('dt') end
-	def to_html_definition_data; wrap_as_element('dd') end	
+	def to_html_definition_list() add_ws wrap_as_element('dl') end
+	def to_html_definition() children_to_html end
+	def to_html_definition_term() add_ws wrap_as_element('dt') end
+	def to_html_definition_data() add_ws wrap_as_element('dd') end	
 
-## Table ###	
+	# FIXME: Ugly code
 	def to_html_table
 		align = self.align
 		num_columns = align.size
@@ -575,7 +557,7 @@ module MaRuKu; module Out; module HTML
 		i = num_columns
 		while i<@children.size
 			rows << @children.slice(i, num_columns)
-			i+=num_columns
+			i += num_columns
 		end
 		
 		table = create_html_element 'table'
@@ -604,7 +586,24 @@ module MaRuKu; module Out; module HTML
 	
 	def to_html_entity 
 		entity_name = self.entity_name
-		Text.new('&%s;' % [entity_name])
+		
+		# Fix for Internet Explorer
+		if entity_name == 'apos'
+			entity_name = 39
+		end
+		
+		if entity_name.kind_of? Fixnum
+#			Entity.new(entity_name)
+			Text.new('&#%d;' % [entity_name],  false, nil, true)
+		else
+			Text.new('&%s;' % [entity_name])
+		end
+	end
+
+	def to_html_xml_instr
+		target = self.target || ''
+		code = self.code || ''
+		REXML::Instruction.new(target, code)
 	end
 
 	# Convert each child to html