Convert entities HTML to text

param75 — Thu, 29 Mar 2012 14:27:55 GMT

Hi,
Is there a component or a function to convert entities HTML to text ?
(I use the Entreprise Edition in Java)

Thank you,
Carole

Re: Convert entities HTML to text

Anonymous — Fri, 30 Mar 2012 03:23:24 GMT

Hi Carole
This topic 22254 will help you.
Regards,
Pedro

Re: Convert entities HTML to text

param75 — Mon, 02 Apr 2012 13:53:19 GMT

Hi,
Finally, I used a new routine with the following code :

package routines;
import java.util.*;
public class StringUtils {
	
	 private StringUtils() {}
	 
	 private static HashMap<String,String> htmlEntities;
	  static {
	    htmlEntities = new HashMap<String,String>();
	    htmlEntities.put("<","<");	    	htmlEntities.put(">",">"); 
	    htmlEntities.put("&","&");			htmlEntities.put(""","\""); 
	    htmlEntities.put("à","à"); 		htmlEntities.put("À","À"); 
	    htmlEntities.put("Á", "Á");		htmlEntities.put("á", "á");
	    htmlEntities.put("â","â") ; 		htmlEntities.put("Ã", "Ã");
	    htmlEntities.put("ã", "ã");		htmlEntities.put("ä","ä"); 
	    htmlEntities.put("Ä","Ä")  ; 		htmlEntities.put("Â","Â"); 
	    htmlEntities.put("å","å") ; 		htmlEntities.put("Å","Å"); 
	    htmlEntities.put("æ","æ") ; 		htmlEntities.put("Æ","Æ" ); 
	    htmlEntities.put("ý", "ý");		htmlEntities.put("ÿ", "ÿ");
	    htmlEntities.put("ç","ç"); 		htmlEntities.put("Ç","Ç"); 
	    htmlEntities.put("é","é"); 		htmlEntities.put("É","É" ); 
	    htmlEntities.put("è","è"); 		htmlEntities.put("È","È"); 
	    htmlEntities.put("ê","ê") ; 		htmlEntities.put("Ê","Ê"); 
	    htmlEntities.put("ë","ë")  ; 		htmlEntities.put("Ë","Ë"); 
	    htmlEntities.put("Í", "Í");		htmlEntities.put("í", "í");
	    htmlEntities.put("Î", "Î");		htmlEntities.put("î","î");
	    htmlEntities.put("Ì", "Ì");		htmlEntities.put("ì", "ì");
	    htmlEntities.put("ï","ï")  ; 		htmlEntities.put("Ï","Ï"); 
	    htmlEntities.put("ó","ó");		htmlEntities.put("ô","ô") ; 
	    htmlEntities.put("Ô","Ô"); 		htmlEntities.put("Ó", "Ó");
	    htmlEntities.put("Ò", "Ò");		htmlEntities.put("ò", "ò");
	    htmlEntities.put("Õ", "Õ");		htmlEntities.put("õ", "õ");
	    htmlEntities.put("ö","ö")  ; 		htmlEntities.put("Ö","Ö"); 
	    htmlEntities.put("Ñ","Ñ") ;		htmlEntities.put("ø","ø") ; 
	    htmlEntities.put("Ø","Ø"); 		htmlEntities.put("Ð","Ð") ;
	    htmlEntities.put("ð","ð") ;			htmlEntities.put("Þ","Þ") ; 
	    htmlEntities.put("þ","þ") ; 		htmlEntities.put("ß","ß") ;
	    htmlEntities.put("Ú", "Ú") ;		htmlEntities.put("ú", "ú") ;
	    htmlEntities.put("ù","ù"); 		htmlEntities.put("Ù","Ù"); 
	    htmlEntities.put("û","û"); 		htmlEntities.put("Û","Û") ; 
	    htmlEntities.put("ü","ü"); 		htmlEntities.put("Ü","Ü")  ; 
	    htmlEntities.put(" "," "); 
	    htmlEntities.put("©","\u00a9"); 
	    htmlEntities.put("®","\u00ae"); 
	    htmlEntities.put("€","\u20a0");
	  }
	 
		 /**
	     * unescapeHTML: remplacer les entitees HTML par leur caractère 
	     * 
	     *
	     * {talendTypes} String
	     * 
	     * {Category} User Defined
	     * 
	     * {param} String("champ") input: champ à traiter
	     * 
	     * {example} unescapeHTML("champ") # "text du champ après traitement".
	     */
	  public static final String unescapeHTML(String source) {
	      int i, j;
	      boolean continueLoop;
	      int skip = 0;
	      do {
	         continueLoop = false;
	         i = source.indexOf("&", skip);
	         if (i > -1) {
	           j = source.indexOf(";", i);
	           if (j > i) {
	             String entityToLookFor = source.substring(i, j + 1);
	             String value = (String) htmlEntities.get(entityToLookFor);
	             if (value != null) {
	               source = source.substring(0, i)
	                        + value + source.substring(j + 1);
	               continueLoop = true;
	             }
	             else if (value == null){
	                skip = i+1;
	                continueLoop = true;
	             }
	           }
	         }
	      } while (continueLoop);
	      return source;
	  }
}

topic Convert entities HTML to text in Talend Studio

Convert entities HTML to text

Re: Convert entities HTML to text

Re: Convert entities HTML to text