batch text substitution, quick and dirty way

remove_accents.rb

#!/usr/bin/env ruby
# quick and dirty script to convert files with french
# accents to no accent files, it opens all files in same folder,
# and enclosed folders recursively. You can replace entries in the SUBSTITUTION Hash
# to build your own substitution table.  If your files encoding are other than ASCII,
# you can also convert them by uncommenting the Iconv line and putting the right
# encoding in there.
require 'find'
require 'ftools'
require 'iconv'

SUBSTITUTIONS = {
	'é' => 'e', 'É' => 'E', 
	'è' => 'e', 'È' => 'E',
	'ê' => 'e', 'Ê' => 'E',
	'ë' => 'e', 'Ë' => 'E',
	'à' => 'a', 'À' => 'A',
	'â' => 'a', 'Â' => 'A',
	'ä' => 'a', 'Ä' => 'A',
	'á' => 'a', 'Á' => 'A',
	'î' => 'i', 'Î' => 'I',
	'ï' => 'i', 'Ï' => 'I',
	'í' => 'i', 'Í' => 'I',
	'ì' => 'i', 'Ì' => 'I',
	'ô' => 'o', 'Ô' => 'O',
	'ö' => 'o', 'Ö' => 'O',
	'ó' => 'o', 'Ó' => 'O',
	'ò' => 'o', 'Ò' => 'O',
	'û' => 'u', 'Û' => 'U',
	'ü' => 'u', 'Ü' => 'U', 
	'ù' => 'u', 'Ù' => 'U',
	'ú' => 'u', 'Ú' => 'U',
	'ç' => 'c', 'Ç' => 'C',
	'’' => "'"
  # To add substitutions, add a coma at the end of last line, and uncomment next line.
	# '^l/s$' => 'lgs',
	# '^m/s$' => 'mds',
	# '^c/u$' => 'csu',
	# '^b/g$' => 'bkg',
	# '^go$' => 'part',
	# '^rt$' => 'rtone'
}

scriptfile = File.basename(__FILE__)
Dir.chdir( File.dirname(__FILE__))
other_files = Array.new
Find.find(File.dirname(__FILE__)) do |path|
	next if File.directory?(path) or File.basename(path) == scriptfile or File.basename(path)[0..0] == '.'
	other_files << path
end

puts "Funky Character Cleaner\n(c) lp 2009\n"
other_files.each do |path|
	basename = File.basename(path); dirname = File.dirname(path)
	puts "Processing file #{basename}"
	new_basename = 'CLEAN_' + basename; new_path = File.catname(new_basename,dirname)
	File.open(new_path,'w') do |newfile|
		File.open(path,'r') do |oldfile|
      content = oldfile.read
      # Uncomment next line to convert file encondings
			# content = Iconv.conv('UTF-8','MACROMAN', content)
			SUBSTITUTIONS.each do |k,v|
				puts "\treplacing #{k} with #{v}"
				content.gsub!(/#{k}/,"#{v}")
			end
			newfile.print(content)
		end
	end
	puts "substitution done for file #{basename}\nchanges were saved to file #{new_basename}\n\n"
end