patcito-maruku 0.6.0

data/lib/maruku/output/to_latex_entities.rb

@@ -0,0 +1,101 @@
+#--
+#   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
+#++
+
+
+require 'rexml/document'
+
+module MaRuKu; module Out; module Latex
+	
+	include REXML
+	
+	def to_latex_entity 
+		MaRuKu::Out::Latex.need_entity_table
+		
+		entity_name = self.entity_name
+	
+		entity = ENTITY_TABLE[entity_name]
+		if not entity
+			maruku_error "I don't know how to translate entity '#{entity_name}' "+
+			"to LaTeX."
+			return ""
+		end
+		replace = entity.latex_string
+		
+		entity.latex_packages.each do |p|
+			@doc.latex_require_package p
+		end
+		
+#		if replace =~ /^\\/
+#			replace = replace + " "
+#		end
+		
+ 		if replace
+			return replace + "{}"
+		else
+			tell_user "Cannot translate entity #{entity_name.inspect} to LaTeX."
+			return entity_name
+		end
+	end
+	
+	class LatexEntity
+		attr_accessor :html_num
+		attr_accessor :html_entity
+		attr_accessor :latex_string
+		attr_accessor :latex_packages
+	end
+	
+	def Latex.need_entity_table
+		Latex.init_entity_table if ENTITY_TABLE.empty?
+	end
+	
+	# create hash @@entity_to_latex
+	def Latex.init_entity_table
+#		$stderr.write "Creating entity table.."
+#		$stderr.flush
+		doc = Document.new(File.read(File.dirname(__FILE__) + "/../../../data/entities.xml"))
+		doc.elements.each("//char") do |c| 
+			num =  c.attributes['num'].to_i
+			name =  c.attributes['name']
+			package =  c.attributes['package']
+			
+			convert =  c.attributes['convertTo']
+			convert.gsub!(/@DOUBLEQUOT/,'"')
+			convert.gsub!(/@QUOT/,"'")
+			convert.gsub!(/@GT/,">")
+			convert.gsub!(/@LT/,"<")
+			convert.gsub!(/@AMP/,"&")
+			convert.freeze
+			
+			e = LatexEntity.new
+			e.html_num = num
+			e.html_entity = name
+			e.latex_string = convert
+			e.latex_packages = package ? package.split : []
+			
+			ENTITY_TABLE[num] = e
+			ENTITY_TABLE[name] = e
+		end
+#		$stderr.puts "..done."
+	end
+	
+	ENTITY_TABLE = {}
+
+end end end
+

data/lib/maruku/output/to_latex_strings.rb

@@ -0,0 +1,64 @@
+#--
+#   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
+#++
+
+
+
+class String
+
+	# These are TeX's special characters
+	LATEX_ADD_SLASH = [ '{', '}', '$', '&', '#', '_', '%']
+
+	# These, we transform to {\tt \char<ascii code>}
+	LATEX_TO_CHARCODE = [ '^', '~', '>', '<']
+
+	def escape_to_latex(s)
+		s2 = ""
+		s.each_char do |b|
+			if LATEX_TO_CHARCODE.include? b
+				s2 += "{\\tt \\symbol{#{b.ord}}}" 
+			elsif LATEX_ADD_SLASH.include? b
+				s2 << ?\\ << b
+			elsif b == '\\'
+			# there is no backslash in cmr10 fonts
+				s2 += "$\\backslash$"
+			else
+				s2 << b
+			end
+		end
+		s2
+	end
+	
+	# escapes special characters
+	def to_latex
+		s = escape_to_latex(self)
+		OtherGoodies.each do |k, v|
+			s.gsub!(k, v)
+		end
+		s
+	end
+	
+	# other things that are good on the eyes
+	OtherGoodies = {
+		/(\s)LaTeX/ => '\1\\LaTeX\\xspace ', # XXX not if already \LaTeX
+#		'HTML' => '\\textsc{html}\\xspace ',
+#		'PDF' => '\\textsc{pdf}\\xspace '
+	}
+	
+end

data/lib/maruku/output/to_markdown.rb

@@ -0,0 +1,164 @@
+#--
+#   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
+#++
+
+
+class String
+	# XXX: markdown escaping
+	def to_md(c=nil)
+		to_s
+	end
+	
+	# " andrea censi " => [" andrea ", "censi "]
+	def mysplit
+		split.map{|x| x+" "}
+	end
+end
+
+
+module MaRuKu; module Out; module Markdown 
+	
+	DefaultLineLength = 40
+	
+	def to_md(context={})
+		children_to_md(context)
+	end
+	
+	def to_md_paragraph(context)
+		line_length = context[:line_length] || DefaultLineLength
+		wrap(@children, line_length, context)+"\n"
+	end
+	
+	def to_md_li_span(context)
+		len = (context[:line_length] || DefaultLineLength) - 2
+		s = wrap(@children, len-2, context).rstrip.gsub(/^/, '  ')
+		s[0] = ?*
+		s + "\n"
+	end
+	
+	def to_md_abbr_def(context)
+		"*[#{self.abbr}]: #{self.text}\n"
+	end
+	
+	def to_md_ol(context)
+		len = (context[:line_length] || DefaultLineLength) - 2
+		md = ""
+		self.children.each_with_index do |li, i|
+			s = (w=wrap(li.children, len-2, context)).rstrip.gsub(/^/, '    ')+"\n"
+			s[0,4] = "#{i+1}.  "[0,4]
+#			puts w.inspect
+			md += s
+		end
+		md + "\n"
+	end
+
+	def to_md_ul(context)
+		len = (context[:line_length] || DefaultLineLength) - 2
+		md = ""
+		self.children.each_with_index do |li, i|
+			w = wrap(li.children, len-2, context)
+#			puts "W: "+ w.inspect
+			s = add_indent(w)
+#			puts "S: " +s.inspect
+			s[0,1] = "-"
+			md += s
+		end
+		md + "\n"
+	end
+	
+	def add_indent(s,char="    ")
+		t = s.split("\n").map{|x| char+x }.join("\n")
+		s << ?\n if t[-1] == ?\n
+		s
+	end
+	
+	# Convert each child to html
+	def children_to_md(context)
+		array_to_md(@children, context)
+	end
+	
+	def wrap(array, line_length, context)
+		out = ""
+		line = ""
+		array.each do |c|
+			if c.kind_of?(MDElement) &&  c.node_type == :linebreak
+				out << line.strip << "  \n"; line="";
+				next
+			end
+		
+			pieces =
+			if c.kind_of? String
+				c.to_md.mysplit
+			else
+				[c.to_md(context)].flatten
+			end
+		
+	#			puts "Pieces: #{pieces.inspect}"
+			pieces.each do |p|
+				if p.size + line.size > line_length
+					out << line.strip << "\n"; 
+					line = ""
+				end
+				line << p
+			end
+		end
+		out << line.strip << "\n" if line.size > 0
+		out << ?\n if not out[-1] == ?\n
+		out
+	end
+
+
+	def array_to_md(array, context, join_char='')
+		e = []
+		array.each do |c|
+			method = c.kind_of?(MDElement) ? 
+			   "to_md_#{c.node_type}" : "to_md"
+			
+			if not c.respond_to?(method)
+				#raise "Object does not answer to #{method}: #{c.class} #{c.inspect[0,100]}"
+#				tell_user "Using default for #{c.node_type}"
+				method = 'to_md'
+			end
+			
+#			puts "#{c.inspect} created with method #{method}"
+			h =  c.send(method, context)
+			
+			if h.nil?
+				raise "Nil md for #{c.inspect} created with method #{method}"
+			end
+			
+			if h.kind_of?Array
+				e = e + h
+			else
+				e << h
+			end
+		end
+		e.join(join_char)
+	end
+	
+end end end
+
+module MaRuKu; class MDDocument
+	alias old_md to_md
+	def to_md(context={})
+		s = old_md(context)
+#		puts s
+		s
+	end	
+end end

data/lib/maruku/output/to_s.rb

@@ -0,0 +1,54 @@
+#--
+#   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
+#++
+
+
+module MaRuKu
+	
+class MDElement
+	
+	# Strips all formatting from the string
+	def to_s
+		 children_to_s
+	end
+	
+	def children_to_s
+		@children.join
+	end
+	
+	# Generate an id for headers. Assumes @children is set.
+	def generate_id
+		title = children_to_s
+		title.gsub!(/ /,'_')
+		title.downcase!
+		title.gsub!(/[^\w_]/,'')
+		title.strip!
+		
+		if title.size == 0
+			$uid ||= 0
+			$uid += 1
+			title = "id#{$uid}"
+		end
+
+		@doc.id_counter += 1
+		title << "_" + @doc.id_counter.to_s
+	end
+end
+
+end

data/lib/maruku/string_utils.rb

@@ -0,0 +1,185 @@
+#--
+#   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
+#++
+
+require 'strscan'
+
+module MaRuKu
+  # Utility functions for dealing with strings.
+  module Strings
+    TAB_SIZE = 4
+
+    # Split a string into multiple lines,
+    # on line feeds and/or carriage returns.
+    #
+    # @param s [String]
+    # @return [String]
+    def split_lines(s)
+      s.split(/\r\n|\r|\n/)
+    end
+
+    # Parses email headers, returning a hash.
+    # `hash[:data]` is the message;
+    # that is, anything past the headers.
+    #
+    # Keys are downcased and converted to symbols;
+    # spaces become underscores. For example:
+    #
+    #     !!!plain
+    #     My key: true
+    #
+    # becomes:
+    #
+    #     {:my_key => true}
+    #
+    # @param s [String] The email
+    # @return [Symbol => String] The header values
+    def parse_email_headers(s)
+      headers = {}
+      scanner = StringScanner.new(s)
+
+      while scanner.scan(/(\w[\w\s\-]+): +(.*)\n/)
+        k, v = normalize_key_and_value(scanner[1], scanner[2])
+        headers[k.to_sym] = v
+      end
+
+      headers[:data] = scanner.rest
+      headers
+    end
+
+    # Returns the number of leading spaces,
+    # considering that a tab counts as {TAB_SIZE} spaces.
+    #
+    # @param s [String]
+    # @return [Fixnum]
+    def number_of_leading_spaces(s)
+      spaces = s.scan(/^\s*/).first
+      spaces.count(" ") + spaces.count("\t") * TAB_SIZE
+    end
+
+    # This returns the position of the first non-list character
+    # in a list item.
+    #
+    # @example
+    # spaces_before_first_char('*Hello') #=> 1
+    # spaces_before_first_char('* Hello') #=> 2
+    # spaces_before_first_char(' * Hello') #=> 3
+    # spaces_before_first_char(' *   Hello') #=> 5
+    # spaces_before_first_char('1.Hello') #=> 2
+    # spaces_before_first_char(' 1.  Hello') #=> 5
+    #
+    # @param s [String]
+    # @return [Fixnum]
+    def spaces_before_first_char(s)
+      match = 
+        case s.md_type
+        when :ulist; s.match(/\s*.(\s*\{(.*?)\})?\s*/)
+        when :olist; s.match(/s*\d+.(\s*\{(.*?)\})?\s*/)
+        else
+          tell_user "MARUKU BUG: '#{s.inspect}' is not a list"
+          nil
+        end
+      match ? [match.end(0), match[0]] : [0, nil]
+    end
+
+    # Replace spaces with underscores and remove non-word characters.
+    #
+    # @param s [String]
+    # @return [String]
+    def sanitize_ref_id(s)
+      s.strip.downcase.gsub(' ', '_').gsub(/[^\w]/, '')
+    end
+
+    # Remove line-initial `>` characters for a quotation.
+    #
+    # @param s [String]
+    # @return [String]
+    def unquote(s)
+      s.gsub(/^>\s?/, '')
+    end
+
+    # Removes indentation from the beginning of `s`,
+    # up to at most `n` spaces.
+    # Tabs are counted as {TAB_SIZE} spaces.
+    #
+    # @param s [String]
+    # @param n [Fixnum]
+    # @return [String]
+    def strip_indent(s, n)
+      while n > 0
+        case s[0]
+        when ?\s; n -= 1
+        when ?\t; n -= TAB_SIZE
+        else; return s
+        end
+        s = s[1..-1]
+      end
+      return s
+    end
+
+    # Escapes a string so that it can be safely used in a Bourne shell command line.
+    #
+    # Note that a resulted string should be used unquoted
+    # and is not intended for use in double quotes nor in single quotes.
+    #
+    # This is a copy of the Shellwords.shellescape function in Ruby 1.8.7.
+    # It's included for Ruby 1.8.6 compatibility.
+    #
+    # @param str [String]
+    # @return [String]
+    def shellescape(str)
+      # An empty argument will be skipped, so return empty quotes.
+      return "''" if str.empty?
+
+      str = str.dup
+
+      # Process as a single byte sequence because not all shell
+      # implementations are multibyte aware.
+      str.gsub!(/([^A-Za-z0-9_\-.,:\/@\n])/n, "\\\\\\1")
+
+      # A LF cannot be escaped with a backslash because a backslash + LF
+      # combo is regarded as line continuation and simply ignored.
+      str.gsub!(/\n/, "'\n'")
+
+      return str
+    end
+
+    private
+
+    # Normalize the key/value pairs for email headers.
+    # Keys are downcased and converted to symbols;
+    # spaces become underscores.
+    #
+    # Values of `"yes"`, `"true"`, `"no"`, and `"false"`
+    # are converted to appropriate booleans.
+    #
+    # @param k [String]
+    # @param v [String]
+    # @return [Array(String, String or Boolean)]
+    def normalize_key_and_value(k, v)
+      k = k.strip.downcase.gsub(/\s+/, '_')
+      v = v.strip
+
+      # check synonyms
+      return k, true if %w[yes true].include?(v.downcase)
+      return k, false if %w[no false].include?(v.downcase)
+      return k, v
+    end
+  end
+end