Révision 2967

tmp/org.txm.utils/src/org/txm/utils/AsciiUtils.java (revision 2967)
127 127 
		if (s.length() == 0) {
128 128 
			return s;
129 129 
		}
130
130 

  		





  131
  131
  
    
		// ensure the "w_" prefix presence


  		





  132
  132
  
    
		if (s.startsWith("w")) {


  		





  133
  133
  
    
			if (!s.startsWith("w_")) {


  		





  ......




  136
  136
  
    
		} else {


  		





  137
  137
  
    
			s = "w_" + s;


  		





  138
  138
  
    
		}


  		





  139
  
  
    
		//System.out.println("first="+s);


  		





  
  139
  
    
		// System.out.println("first="+s);


  		





  140
  140
  
    

  		





  141
  
  
    
		String rez = convertNonAscii(s);//.toLowerCase();


  		





  142
  
  
    
		//System.out.println("nonasscii="+rez);


  		





  
  141
  
    
		String rez = convertNonAscii(s);// .toLowerCase();


  		





  
  142
  
    
		// System.out.println("nonasscii="+rez);


  		





  143
  143
  
    
		rez = rez.replaceAll("\\p{Space}++", "_");


  		





  144
  
  
    
		//System.out.println("spaces="+rez);


  		





  
  144
  
    
		// System.out.println("spaces="+rez);


  		





  145
  145
  
    
		rez = rez.replaceAll("[¤€§µ£°().,;:/?!@§%\\\\\"’ʹ'*+\\-}\\]\\[{#~&]", ""); //$NON-NLS-1$ //$NON-NLS-2$ // "[^\\P{P}_]"


  		





  146
  
  
    
		//System.out.println("ponc="+rez);


  		





  
  146
  
    
		// System.out.println("ponc="+rez);


  		





  147
  147
  
    

  		





  148
  148
  
    
		return rez;


  		





  149
  149
  
    
	}


  		





  ......




  172
  172
  
    
			return s;


  		





  173
  173
  
    
		}


  		





  174
  174
  
    
		String rez = s.trim();


  		





  175
  
  
    
		s = s.replaceAll("\\p{Space}++", "_");


  		





  
  175
  
    
		rez = rez.replaceAll("\\p{Space}++", "_");


  		





  176
  176
  
    
		rez = rez.replaceAll("_", "-");


  		





  177
  177
  
    
		rez = convertNonAscii(rez).toLowerCase();


  		





  178
  
  
    
		


  		





  
  178
  
    

  		





  179
  179
  
    
		rez = rez.replaceAll("[¤€§µ£°().,;:/?!@§%\\\\\"’ʹ'*+\\}\\]\\[{#~&]", ""); //$NON-NLS-1$ //$NON-NLS-2$


  		





  180
  180
  
    
		// remove first chars if number


  		





  181
  181
  
    
		char c = rez.charAt(0);


  		





  ......




  199
  199
  
    
	public static void main(String args[]) {


  		





  200
  200
  
    
		String s = "01The result : - - _ тврьдо È,É,Ê,Ë,Û,Ù,Ï,Î,À,Â,Ô,è,é,ê,ë,û,ù,ï,î,à,â,ô,ç  0 1 2 3 4 5 6 7 8 9 10"; //$NON-NLS-1$


  		





  201
  201
  
    
		System.out.println(AsciiUtils.convertNonAscii(s));


  		





  202
  
  
    
		//System.out.println(AsciiUtils.buildId(s));


  		





  
  202
  
    
		// System.out.println(AsciiUtils.buildId(s));


  		





  203
  203
  
    
		String s2 = "w_ТВРЬДОтврьдо_123&é\"'(-è_çà)=/*-+~#{[|`\\^@]}¤;:!§/.?µ%£°";


  		





  204
  
  
    
		System.out.println("nonascii="+AsciiUtils.convertNonAscii(s2));


  		





  205
  
  
    
		System.out.println("word_id="+AsciiUtils.buildWordId(s2));


  		





  206
  
  
    
		System.out.println("attribute_id="+AsciiUtils.buildAttributeId(s2));


  		





  
  204
  
    
		System.out.println("nonascii=" + AsciiUtils.convertNonAscii(s2));


  		





  
  205
  
    
		System.out.println("word_id=" + AsciiUtils.buildWordId(s2));


  		





  
  206
  
    
		System.out.println("attribute_id=" + AsciiUtils.buildAttributeId(s2));


  		





  207
  207
  
    
		// output :


  		





  208
  208
  
    
		// The result : E,E,E,E,U,U,I,I,A,A,O,e,e,e,e,u,u,i,i,a,a,o,c


  		





  209
  209
  
    

  		












Formats disponibles :
  Unified diff