Ruby on Rails PL Forum

require 'iconv'
 
def pl2ascii(s)
  ascii = "acelnoszzACELNOSZZ"
  cep = "\271\346\352\263\361\363\234\277\237\245\306\312\243\321\323\214\257\217" 
  s = Iconv.new("cp1250", "UTF-8").iconv(s)
  s.tr!(cep,ascii)  
end
 
puts pl2ascii('zażółć gęślą jaźń ZAŻÓŁĆ GĘŚLĄ JAŹŃ') # => zazolc gesla jazn ZAZOLC GESLA JAZN
 
=begin 
 
Do generacji stringa z kodami cep1250 użyłem Pythona:
 
pl = [oct(ord(c)) for c in unicode('ąćęłńóśżźĄĆĘŁŃÓŚŻŹ', 'utf8').encode('cp1250')]
print ''.join(["\\%s" % c[1:] for c in pl])
# => \271\346\352\263\361\363\234\277\237\245\306\312\243\321\323\214\257\217
 
=end 

import com.ibm.icu.text.Transliterator;
 
public class TextUtils {
	
	static final String suplement = "ł>l;Ł>L;ß>ss";
	
	static final String accentID = 
			"NFD; Suplement; [:Nonspacing Mark:] Remove; NFC";
	
	static final String loginID = 
			"NFD; Suplement; [\\P{ASCII}\\P{Alpha}] Remove; Lower; NFC";
	
	//	"Greek-Latin; Cyrillic-Latin; ru-en;"
	
	static TextUtils singleton = null;
	
	private TextUtils() {	
		Transliterator.registerInstance(
				Transliterator.createFromRules("Any-Suplement",
				suplement, Transliterator.FORWARD));
	}
	
	public static TextUtils getInstance() {
		if (singleton == null) {
			singleton = new TextUtils();
		}
		return singleton;
	}
	
	
	public String transliterate(String customID, String text) {
		Transliterator acc = Transliterator.getInstance(customID);
		System.out.println(acc.getID());
		return acc.transliterate(text);
	}
	
	
	public String removeAccents(String text) {	
		return transliterate(accentID, text);
	}
	
	
	public String prepare4LoginName(String text) {	
		return transliterate(loginID, text);
	}
	
	
	public String prepare4LoginName(String text, int maxChars) {
		String s = transliterate(loginID, text);
		return s.length() > maxChars ? s.substring(0, maxChars) : s;
	}
} 

require 'iconv'

$KCODE = 'u'
require 'jcode' 

expr = /[Ąą]/u  # to 'u' na koncu
puts expr.kcode # => utf8  

# strip all non word chars
result.gsub!(/\W/, ' ') 

class String  
  def to_ascii_brutal
   #foo = self.downcase.strip
   foo = String.new(self)
   #foo = self.clone #.downcase.strip
   foo.gsub!(/[ĄÀ�?ÂÃ]/,'A')
   foo.gsub!(/[âäàãáäå�?ăąǎǟǡǻ�?ȃȧẵặ]/,'a')
   foo.gsub!(/[Ę]/,'E')
   foo.gsub!(/[ëêéèẽēĕėẻȅȇẹȩęḙḛ�?ếễểḕḗệ�?]/,'e')
   foo.gsub!(/[Ì�?ÎĨ]/,'I')
   foo.gsub!(/[�?iìíîĩīĭïỉ�?ịįȉȋḭɨḯ]/,'i')
   foo.gsub!(/[ÒÓÔÕÖ]/,'O')
   foo.gsub!(/[òóôõ�?�?ȯö�?őǒ�?�?ơǫ�?ɵøồốỗổȱȫȭ�?�?ṑṓ�?ớỡởợǭộǿ]/,'o')
   foo.gsub!(/[ÙÚÛŨÜ]/,'U')
   foo.gsub!(/[ùúûũūŭüủůűǔȕȗưụṳųṷṵṹṻǖǜǘǖǚừứữửự]/,'u')
   foo.gsub!(/[ỳýŷỹȳ�?ÿỷẙƴỵ]/,'y')
   foo.gsub!(/[œ]/,'oe')
   foo.gsub!(/[ÆǼǢæ]/,'ae')
   foo.gsub!(/[Ń]/,'N')
   foo.gsub!(/[ñǹń]/,'n')
   foo.gsub!(/[ÇĆ]/,'C')
   foo.gsub!(/[çć]/,'c')
   foo.gsub!(/[ß]/,'ss')
   foo.gsub!(/[œ]/,'oe')
   foo.gsub!(/[ij]/,'ij')
   foo.gsub!(/[Ł]/,'L')
   foo.gsub!(/[�?ł]/,'l')
   foo.gsub!(/[Ś]/,'S')
   foo.gsub!(/[ś]/,'s')
   foo.gsub!(/[ŹŻ]/,'Z')
   foo.gsub!(/[źż]/,'z')
   #foo.sub!(/[\s\'\"\\\/\?\.\=\+\&\%]$/,'')
   #foo.gsub!(/[\s\'\"\\\/\?\.\=\+\&\%]/,'_')
   #foo.gsub!(/_+/,'_')
   foo
  end
  
end 

require 'iconv'
require 'unicode'

class String 
  def to_ascii
    return if self.nil?
    self.chars.split('').collect { |c| (c[0] <= 127) ? c : translation_hash[c[0]] }.join
  end

  protected
    def translation_hash
      @translation_hash ||= setup_translation_hash      
    end
    
    def setup_translation_hash 
      accented_chars   = "ÀÁÂÃÄÅÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛŨÜÝâäàãáäåāăąǎǟǡǻȁȃȧẵặçëêéèẽēĕėẻȅȇẹȩęḙḛềếễểḕḗệḝiìíîĩīĭïỉǐịįȉȋḭɨḯñòóôõōŏȯöỏőǒȍȏơǫọɵøồốỗổȱȫȭṍṏṑṓờớỡởợǭộǿùúûũūŭüủůűǔȕȗưụṳųṷṵṹṻǖǜǘǖǚừứữửựỳýŷỹȳẏÿỷẙƴỵĄĆĘŁŃÓŚŻŹąćęłńóśżź".chars.split('')
      unaccented_chars = "AAAAAACEEEEIIIIDNOOOOOxOUUUUUYaaaaaaaaaaaaaaaaaaaceeeeeeeeeeeeeeeeeeeeeeeeiiiiiiiiiiiiiiiiinoooooooooooooooooooooooooooooooooooouuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuyyyyyyyyyyyACELNOSZZacelnoszz".split('')
  
      translation_hash = {}
      accented_chars.each_with_index { |char, idx| translation_hash[char[0]] = unaccented_chars[idx] }
      translation_hash["Æ".chars[0]] = 'AE'
      translation_hash["æ".chars[0]] = 'ae'
      translation_hash["Œ".chars[0]] = 'OE'
      translation_hash["œ".chars[0]] = 'oe'
      translation_hash["ß".chars[0]] = 'ss'
      translation_hash
    end
end