/** Returns previous character */
private int getPrevious() {
char c2 = text.previous();
if (Character.isLowSurrogate(c2) && text.getIndex() > text.getBeginIndex()) {
char c1 = text.previous();
if (Character.isHighSurrogate(c1)) {
return Character.toCodePoint(c1, c2);
} else {
text.next();
}
}
return (int) c2;
}
public int previous() {
int i = iterator.previous();
if (i == CharacterIterator.DONE) {
return DONE;
}
return i;
}
/**
* For the given string, returns the number of UTF-8 bytes required to encode the string.
*
* @param string text to encode
* @return number of UTF-8 bytes required to encode
*/
public static int utf8Length(String string) {
CharacterIterator iter = new StringCharacterIterator(string);
char ch = iter.first();
int size = 0;
while (ch != CharacterIterator.DONE) {
if ((ch >= 0xD800) && (ch < 0xDC00)) {
// surrogate pair?
char trail = iter.next();
if ((trail > 0xDBFF) && (trail < 0xE000)) {
// valid pair
size += 4;
} else {
// invalid pair
size += 3;
iter.previous(); // rewind one
}
} else if (ch < 0x80) {
size++;
} else if (ch < 0x800) {
size += 2;
} else {
// ch < 0x10000, that is, the largest char value
size += 3;
}
ch = iter.next();
}
return size;
}
/** Returns the count of next character. */
private int getCurrentCodePointCount() {
char c1 = text.current();
if (Character.isHighSurrogate(c1) && text.getIndex() < text.getEndIndex()) {
char c2 = text.next();
text.previous();
if (Character.isLowSurrogate(c2)) {
return 2;
}
}
return 1;
}
/** Returns current character */
int getCurrent() {
char c1 = text.current();
if (Character.isHighSurrogate(c1) && text.getIndex() < text.getEndIndex()) {
char c2 = text.next();
text.previous();
if (Character.isLowSurrogate(c2)) {
return Character.toCodePoint(c1, c2);
}
}
return (int) c1;
}
private Object read() {
skipWhiteSpace();
char ch = c;
next();
switch (ch) {
case '"':
token = string();
break;
case '[':
token = array();
break;
case ']':
token = ARRAY_END;
break;
case ',':
token = COMMA;
break;
case '{':
token = object();
break;
case '}':
token = OBJECT_END;
break;
case ':':
token = COLON;
break;
case 't':
if (c != 'r' || next() != 'u' || next() != 'e')
throw new RuntimeException("Invalid JSON token: expected 'true' keyword.");
next();
token = Boolean.TRUE;
break;
case 'f':
if (c != 'a' || next() != 'l' || next() != 's' || next() != 'e')
throw new RuntimeException("Invalid JSON token: expected 'false' keyword.");
next();
token = Boolean.FALSE;
break;
case 'n':
if (c != 'u' || next() != 'l' || next() != 'l')
throw new RuntimeException("Invalid JSON token: expected 'null' keyword.");
next();
token = null;
break;
default:
c = it.previous();
if (Character.isDigit(c) || c == '-') {
token = number();
}
}
// System.out.println("token: " + token); // enable this line to see the token stream
return token;
}
private Object read() {
skipWhiteSpace();
char ch = c;
next();
Object value = null;
switch (ch) {
case '"':
value = string();
break;
case '[':
value = array();
break;
case ']':
value = ARRAY_END;
break;
case ',':
value = COMMA;
break;
case '{':
value = object();
break;
case '}':
value = OBJECT_END;
break;
case ':':
value = COLON;
break;
case 't':
if (c != 'r' || next() != 'u' || next() != 'e')
error("Invalid JSON token: expected 'true' keyword.");
next();
value = Boolean.TRUE;
break;
case 'f':
if (c != 'a' || next() != 'l' || next() != 's' || next() != 'e')
error("Invalid JSON token: expected 'false' keyword.");
next();
value = Boolean.FALSE;
break;
case 'n':
if (c != 'u' || next() != 'l' || next() != 'l')
error("Invalid JSON token: expected 'null' keyword.");
next();
value = null;
break;
default:
c = it.previous();
if (Character.isDigit(c) || c == '-') value = number();
else error("Invalid character '" + c + "', expecting a JSON token.");
}
return value;
}
private char previous() {
c = it.previous();
return c;
}