Eliminar acentos de String

Question

¿Hay alguna forma en Android que (que yo sepa) no tiene java.text.Normalizer, para eliminar cualquier acento de una cadena. E.g "éàù" se convierte en "eau".

¡Me gustaría evitar analizar el String para verificar cada carácter si es posible!

Answer 1

java.text.Normalizer existe en Android (en las últimas versiones de todos modos). Puedes usarlo.

EDITAR Para referencia, aquí es cómo utilizar Normalizer:

string = Normalizer.normalize(string, Normalizer.Form.NFD); 
string = string.replaceAll("[^\\p{ASCII}]", ""); 

(pegado desde el enlace en los comentarios a continuación)

Answer 2

Todos los grupos de caracteres acentuados están en el conjunto extendido de caracteres ASCII, con valores decimales mayores que 127. Por lo tanto, puede enumerar todos los caracteres de una cadena y si el valor del código de caracteres es mayor que 127, vuelva a asignarlo equivalente deseado No hay una forma fácil de asignar los caracteres acentuados a las contrapartes sin acentos: debería mantener algún tipo de mapa en la memoria para asignar los códigos decimales extendidos a los caracteres sin acentos.

Answer 3

Esto probablemente no es la solución más eficiente, pero que va a hacer el truco y funciona en todas las versiones de Android:

private static Map<Character, Character> MAP_NORM; 
static { // Greek characters normalization 
    MAP_NORM = new HashMap<Character, Character>(); 
    MAP_NORM.put('ά', 'α'); 
    MAP_NORM.put('έ', 'ε'); 
    MAP_NORM.put('ί', 'ι'); 
    MAP_NORM.put('ό', 'ο'); 
    MAP_NORM.put('ύ', 'υ'); 
    MAP_NORM.put('ή', 'η'); 
    MAP_NORM.put('ς', 'σ'); 
    MAP_NORM.put('ώ', 'ω'); 
    MAP_NORM.put('Ά', 'α'); 
    MAP_NORM.put('Έ', 'ε'); 
    MAP_NORM.put('Ί', 'ι'); 
    MAP_NORM.put('Ό', 'ο'); 
    MAP_NORM.put('Ύ', 'υ'); 
    MAP_NORM.put('Ή', 'η'); 
    MAP_NORM.put('Ώ', 'ω'); 
} 

public static String removeAccents(String s) { 
    if (s == null) { 
     return null; 
    } 
    StringBuilder sb = new StringBuilder(s); 

    for(int i = 0; i < s.length(); i++) { 
     Character c = MAP_NORM.get(sb.charAt(i)); 
     if(c != null) { 
      sb.setCharAt(i, c.charValue()); 
     } 
    } 

    return sb.toString(); 
} 

Answer 4

He ajustado la solución de Rabi a mis necesidades, espero que h ELPS a alguien:

private static Map<Character, Character> MAP_NORM; 
public static String removeAccents(String value) 
{ 
    if (MAP_NORM == null || MAP_NORM.size() == 0) 
    { 
     MAP_NORM = new HashMap<Character, Character>(); 
     MAP_NORM.put('À', 'A'); 
     MAP_NORM.put('Á', 'A'); 
     MAP_NORM.put('Â', 'A'); 
     MAP_NORM.put('Ã', 'A'); 
     MAP_NORM.put('Ä', 'A'); 
     MAP_NORM.put('È', 'E'); 
     MAP_NORM.put('É', 'E'); 
     MAP_NORM.put('Ê', 'E'); 
     MAP_NORM.put('Ë', 'E'); 
     MAP_NORM.put('Í', 'I'); 
     MAP_NORM.put('Ì', 'I'); 
     MAP_NORM.put('Î', 'I'); 
     MAP_NORM.put('Ï', 'I'); 
     MAP_NORM.put('Ù', 'U'); 
     MAP_NORM.put('Ú', 'U'); 
     MAP_NORM.put('Û', 'U'); 
     MAP_NORM.put('Ü', 'U'); 
     MAP_NORM.put('Ò', 'O'); 
     MAP_NORM.put('Ó', 'O'); 
     MAP_NORM.put('Ô', 'O'); 
     MAP_NORM.put('Õ', 'O'); 
     MAP_NORM.put('Ö', 'O'); 
     MAP_NORM.put('Ñ', 'N'); 
     MAP_NORM.put('Ç', 'C'); 
     MAP_NORM.put('ª', 'A'); 
     MAP_NORM.put('º', 'O'); 
     MAP_NORM.put('§', 'S'); 
     MAP_NORM.put('³', '3'); 
     MAP_NORM.put('²', '2'); 
     MAP_NORM.put('¹', '1'); 
     MAP_NORM.put('à', 'a'); 
     MAP_NORM.put('á', 'a'); 
     MAP_NORM.put('â', 'a'); 
     MAP_NORM.put('ã', 'a'); 
     MAP_NORM.put('ä', 'a'); 
     MAP_NORM.put('è', 'e'); 
     MAP_NORM.put('é', 'e'); 
     MAP_NORM.put('ê', 'e'); 
     MAP_NORM.put('ë', 'e'); 
     MAP_NORM.put('í', 'i'); 
     MAP_NORM.put('ì', 'i'); 
     MAP_NORM.put('î', 'i'); 
     MAP_NORM.put('ï', 'i'); 
     MAP_NORM.put('ù', 'u'); 
     MAP_NORM.put('ú', 'u'); 
     MAP_NORM.put('û', 'u'); 
     MAP_NORM.put('ü', 'u'); 
     MAP_NORM.put('ò', 'o'); 
     MAP_NORM.put('ó', 'o'); 
     MAP_NORM.put('ô', 'o'); 
     MAP_NORM.put('õ', 'o'); 
     MAP_NORM.put('ö', 'o'); 
     MAP_NORM.put('ñ', 'n'); 
     MAP_NORM.put('ç', 'c'); 
    } 

    if (value == null) { 
     return ""; 
    } 

    StringBuilder sb = new StringBuilder(value); 

    for(int i = 0; i < value.length(); i++) { 
     Character c = MAP_NORM.get(sb.charAt(i)); 
     if(c != null) { 
      sb.setCharAt(i, c.charValue()); 
     } 
    } 

    return sb.toString(); 

} 

Answer 5

Si bien la respuesta de Guillaume funciona despoja todos los caracteres no ASCII de la cadena. Si desea conservar estos tratan este código (donde string es la cadena para simplificar):

// Convert input string to decomposed Unicode (NFD) so that the 
// diacritical marks used in many European scripts (such as the 
// "C WITH CIRCUMFLEX" → ĉ) become separate characters. 
// Also use compatibility decomposition (K) so that characters, 
// that have the exact same meaning as one or more other 
// characters (such as "㎏" → "kg" or "ﾋ" → "ヒ"), match when 
// comparing them. 
string = Normalizer.normalize(string, Normalizer.Form.NFKD); 

StringBuilder result = new StringBuilder(); 

int offset = 0, strLen = string.length(); 
while(offset < strLen) { 
    int character = string.codePointAt(offset); 
    offset += Character.charCount(character); 

    // Only process characters that are not combining Unicode 
    // characters. This way all the decomposed diacritical marks 
    // (and some other not-that-important modifiers), that were 
    // part of the original string or produced by the NFKD 
    // normalizer above, disappear. 
    switch(Character.getType(character)) { 
     case Character.NON_SPACING_MARK: 
     case Character.COMBINING_SPACING_MARK: 
      // Some combining character found 
     break; 

     default: 
      result.appendCodePoint(Character.toLowerCase(character)); 
    } 
} 

// Since we stripped all combining Unicode characters in the 
// previous while-loop there should be no combining character 
// remaining in the string and the composed and decomposed 
// versions of the string should be equivalent. This also means 
// we do not need to convert the string back to composed Unicode 
// before returning it. 
return result.toString();