private CharType determineCharType(char ch) {
CharType charType;
Character.UnicodeBlock unicodeBlock = Character.UnicodeBlock.of(ch); // 한글이면 HANGUL_SYLLABLES
if ((ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z')) {
charType = CharType.ALPHABET;
} else if (ch >= '0' && ch <= '9') {
charType = CharType.NUMBER;
} else if (ch == ' ' || ch == '\t' || ch == '\r' || ch == '\n') {
charType = CharType.SPACE;
} else if (unicodeBlock == HANGUL_SYLLABLES || unicodeBlock == HANGUL_COMPATIBILITY_JAMO) {
charType = CharType.HANGUL;
} else if (unicodeBlock == CJK_COMPATIBILITY_IDEOGRAPHS
|| unicodeBlock == CJK_UNIFIED_IDEOGRAPHS) { // 한중일 호환 한자 || 한중일 공통한자
charType = CharType.HANJA;
} else if (unicodeBlock == LETTERLIKE_SYMBOLS
|| unicodeBlock == CJK_COMPATIBILITY
|| unicodeBlock == CJK_SYMBOLS_AND_PUNCTUATION
|| unicodeBlock == HALFWIDTH_AND_FULLWIDTH_FORMS
|| unicodeBlock == BASIC_LATIN) {
charType = CharType.SYMBOL;
} else {
charType = CharType.ETC;
}
return charType;
}
public List<Character.UnicodeBlock> getListOfLanguage(String data) {
Set<Character.UnicodeBlock> languageSet = new HashSet<Character.UnicodeBlock>();
char[] valueArray = data.toCharArray();
for (int counter = 0; counter < valueArray.length; counter++) {
languageSet.add(Character.UnicodeBlock.of(valueArray[counter]));
}
return (new ArrayList<Character.UnicodeBlock>(languageSet));
}
