StripAccents.java

import java.text.Normalizer;

// Hall of fame:
//  - https://en.wikipedia.org/w/index.php?oldid=674250888 (279 reasons why you should prefer this method)
//  - http://www.unicode.org/reports/tr15/tr15-23.html     (Explanation of different Unicode normalization forms)
//  - http://stackoverflow.com/a/361345/277882             (How to iterate over 20-bit Unicode string in Java)
//  - http://stackoverflow.com/a/29111105/277882           (How to check for combining characters in Java)

class StripAccents {
	public static void main(String[] args) {
		// Check that diacritical marks are stripped correctly and
		// compatibility mappings (for similar-looking characters
		// with different codepoints are applied correctly).
		String string = "BLA áèịöű bla ねこ ﾈｺ ㎏ ṓ";
		String result = Main.normalize(string);
		System.out.println(result);
		if(!result.equals("bla aeiou bla ねこ ネコ kg o")) {
			System.out.println("  Unexpected result!");
		}
	}
	
	public static String normalize(String string) {
		// 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"), become match
		// when searching.
		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();
	}
}