Unicode Explained

Such presentation might be useful to a knowledgeable person who needs to inspect the

content of a Unicode file that mostly consists of ASCII characters. The program branch-

es according to the General Category (gc) value of the character, as obtained using the

getType function; the gc values as defined in the Unicode standard are given in com-

ments:

public class show {

public static void printc(String symbol, int data) {

System.out.print("[" + symbol +

Integer.toHexString(data) + "]"); }

public static void main(String[] args) {

String msg = "Rhône, 42\u00a0§, price £50";

for(int i = 0; i < msg.length(); i++) {

char ch = msg.charAt(i);

int code = ch;

if(code < 0x7F) { /* ASCII */

System.out.print(ch); }

else switch(Character.getType(ch)) {

case Character.UPPERCASE_LETTER: /* Lu */

case Character.LOWERCASE_LETTER: /* Ll */

case Character.TITLECASE_LETTER: /* Lt */

case Character.MODIFIER_LETTER: /* Lm */

case Character.OTHER_LETTER: /* Lo */

printc("L:", code);

break;

case Character.DECIMAL_DIGIT_NUMBER: /* Nd */

case Character.LETTER_NUMBER: /* Nl */

case Character.OTHER_NUMBER: /* No */

printc("N:", code);

break;

case Character.NON_SPACING_MARK: /* Mn */

case Character.COMBINING_SPACING_MARK: /* Mc */

case Character.ENCLOSING_MARK: /* Me */

printc("~:", code);

break;

case Character.SPACE_SEPARATOR: /* Zs */

printc(" :", code);

break;

case Character.LINE_SEPARATOR: /* Zl */

System.out.println(); ...