Monkey patch kramdown to behave more like `wptexturize` from WordPress # instead of SmartyPants when parsing dashes.

kramdown_dashes_patch.rb

# Hack by Don Melton, based on portions of kramdown by Thomas Leitner.
#
# Monkey patch kramdown to behave more like `wptexturize` from WordPress
# instead of SmartyPants when parsing dashes.
#
# Now double and single hyphen-minus character sequences surrounded by spaces,
# i.e. `' -- '` and `' - '`, are converted to em and en dashes, respectively,
# still surrounded by spaces. Old and new dash conversions are:
#   
#   `'---'`   => em dash
#   `' -- '`  => em dash surrounded by spaces
#   `'--'`    => en dash
#   `' - '`   => en dash surrounded by spaces
#
# Note: kramdown conversion to LaTeX and HTML conversion back to kramdown
# formats are not patched.
require 'kramdown'

module Kramdown

  module Parser

    class Kramdown < Base

      # Cloned from `define_parser` in `parser/kramdown.rb` to *not* check if
      # named parser already exists.
      def self.redefine_parser(name, start_re, span_start = nil, meth_name = "parse_#{name}")
        @@parsers[name] = Data.new(name, start_re, span_start, meth_name)
      end
    end

    class Kramdown

      # Disable warnings while redefining constants.
      original_verbosity = $VERBOSE
      $VERBOSE = nil

      # Add `' -- '` and `' - '` to list of typographic symbols.
      # Note: Any non-Symbol values, e.g. `' &mdash; '`, are not strictly
      # necessary in this array but are included for clarity.
      TYPOGRAPHIC_SYMS = [['---', :mdash], [' -- ', ' &mdash; '], ['--', :ndash], [' - ', ' &ndash; '],
                          ['...', :hellip],
                          ['\\<<', '&lt;&lt;'], ['\\>>', '&gt;&gt;'],
                          ['<< ', :laquo_space], [' >>', :raquo_space],
                          ['<<', :laquo], ['>>', :raquo]]

      # Reset other constants (copied verbatim from `typographic_symbol.rb`)
      # because `TYPOGRAPHIC_SYMS` has been redefined.
      TYPOGRAPHIC_SYMS_SUBST = Hash[*TYPOGRAPHIC_SYMS.flatten]
      TYPOGRAPHIC_SYMS_RE = /#{TYPOGRAPHIC_SYMS.map {|k,v| Regexp.escape(k)}.join('|')}/

      # Re-enable warnings.
      $VERBOSE = original_verbosity

      # Augmented to handle new non-Symbol typographic symbols, i.e. `' -- '`
      # and `' - '`.
      def parse_typographic_syms
        @src.pos += @src.matched_size
        val = TYPOGRAPHIC_SYMS_SUBST[@src.matched]
        if val.kind_of?(Symbol)
          @tree.children << Element.new(:typographic_sym, val)
        elsif @src.matched == ' -- '
          @tree.children << Element.new(:text, ' ')
          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('mdash'))
          @tree.children << Element.new(:text, ' ')
        elsif @src.matched == ' - '
          @tree.children << Element.new(:text, ' ')
          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('ndash'))
          @tree.children << Element.new(:text, ' ')
        elsif @src.matched == '\\<<'
          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('lt'))
          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('lt'))
        else
          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('gt'))
          @tree.children << Element.new(:entity, ::Kramdown::Utils::Entities.entity('gt'))
        end
      end

      # Replace old `:typographic_syms` parser to use augmented map and new
      # regular expression which checks for an optional space before
      # hyphen-minus character input.
      redefine_parser(:typographic_syms, TYPOGRAPHIC_SYMS_RE, '[ \-]-|\\.\\.\\.|(?:\\\\| )?(?:<<|>>)')
    end
  end
end