/**
* Escapes the specified token.
*
* @param token token
* @return escaped token
*/
public static byte[] escape(final byte[] token) {
final TokenBuilder tb = new TokenBuilder();
for (final byte t : token) {
if (t >= 0x20 && t <= 0x7e) tb.addByte(t);
else hex(tb, t);
}
return tb.finish();
}
/**
* Returns a URI encoded token.
*
* @param token token
* @param iri input
* @return encoded token
*/
public static byte[] uri(final byte[] token, final boolean iri) {
final TokenBuilder tb = new TokenBuilder();
for (final byte t : token) {
if (letterOrDigit(t) || contains(iri ? IRIRES : RES, t)) tb.addByte(t);
else hex(tb, t);
}
return tb.finish();
}
/**
* Replaces the specified character and returns the result token.
*
* @param token token to be checked
* @param search the character to be replaced
* @param replace the new character
* @return resulting token
*/
public static byte[] replace(final byte[] token, final int search, final int replace) {
final TokenBuilder tb = new TokenBuilder(token.length);
final int tl = token.length;
for (int i = 0; i < tl; i += cl(token, i)) {
final int c = cp(token, i);
tb.add(c == search ? replace : c);
}
return tb.finish();
}
/**
* Deletes the specified character from the token.
*
* @param token token
* @param ch character to be removed
* @return resulting token
*/
public static byte[] delete(final byte[] token, final int ch) {
// skip step if specified ascii character is not contained
if (ch < 0x80 && !contains(token, ch)) return token;
// remove character
final TokenBuilder tb = new TokenBuilder(token.length);
final int tl = token.length;
for (int i = 0; i < tl; i += cl(token, i)) {
final int c = cp(token, i);
if (c != ch) tb.add(c);
}
return tb.finish();
}
/**
* Converts a string to a UTF8 byte array.
*
* @param string string to be converted
* @return byte array
*/
private static byte[] utf8(final String string) {
final char[] arr = string.toCharArray();
final int al = arr.length;
final TokenBuilder tb = new TokenBuilder(al << 1);
for (int c = 0; c < al; ++c) {
final char ch = arr[c];
tb.add(
Character.isHighSurrogate(ch) && c < al - 1 && Character.isLowSurrogate(arr[c + 1])
? Character.toCodePoint(ch, arr[++c])
: ch);
}
return tb.finish();
}
/**
* Splits a token around matches of the given separator.
*
* @param token token to be split
* @param sep separation character
* @return array
*/
public static byte[][] split(final byte[] token, final int sep) {
final int l = token.length;
final byte[][] split = new byte[l][];
int s = 0;
final TokenBuilder tb = new TokenBuilder();
for (int i = 0; i < l; i += cl(token, i)) {
final int c = cp(token, i);
if (c == sep) {
if (!tb.isEmpty()) {
split[s++] = tb.finish();
tb.reset();
}
} else {
tb.add(c);
}
}
if (!tb.isEmpty()) split[s++] = tb.finish();
return Array.copyOf(split, s);
}
/**
* Adds the specified byte in hex code.
*
* @param tb token builder
* @param b byte to be added
*/
private static void hex(final TokenBuilder tb, final byte b) {
tb.add('%');
tb.addByte(HEX[(b & 0xFF) >> 4]);
tb.addByte(HEX[b & 0xFF & 15]);
}