tidy.rb

# HTML Tidy filter. This is pretty Unix-specific. It uses the external 'tidy'
# command, which it looks for using 'which', and communicates with using open3.

require 'open3'

module Tidy
  # Runs the source through tidy and returns the result. If tidy isn't found,
  # just returns the source as is. The source should be string-like.
  #
  # Takes an optional hash parameter, with the keys :strict and :verbose
  #
  # If :verbose is true, prints warning messages to stderr.
  # The default is :verbose => false.
  #
  # If :strict is true, outputs XHTML with a strict doctype.
  # If :strict is false, outputs XHTML with a transitional doctype.
  # The default is :strict => true.
  def Tidy.Tidy(source, params = {})
    # We're strict unless we're specifically not.
    strict = (params[:strict] == false ? false : true)
    # We're not verbose unless we specificaly are.
    verbose = params[:verbose] || false

    # Find tidy, return unaltered source if we can't.
    tidy = `which tidy 2>&1`
    if (tidy =~ /(not found)/) || tidy.empty?
      if verbose
        $stderr.puts "tidy not found."
      end
      return source
    end

    # Set tidy's options
    tidy_options = ['--indent auto', '--output-xhtml yes', '--quiet yes',
      '--tidy-mark no', '--char-encoding utf8', '--wrap 78']
    if strict
      tidy_options << '--doctype strict'
    else
      tidy_options << '--doctype transitional'
    end

    # Make it go.
    Open3.popen3("tidy #{tidy_options.join(' ')}") {|tidy_in,tidy_out,tidy_err|
      tidy_in.write source
      tidy_in.close

      @result = tidy_out.read
      @errors = tidy_err.read
    }

    if verbose
      $stderr.puts @errors
    end

    return @result
  end
end