static String htmldecode(final String input) {
if (input == null) ret null;
final int MIN_ESCAPE = 2;
final int MAX_ESCAPE = 6;
StringWriter writer = null;
int len = input.length();
int i = 1;
int st = 0;
while (true) {
// look for '&'
while (i < len && input.charAt(i-1) != '&')
i++;
if (i >= len)
break;
// found '&', look for ';'
int j = i;
while (j < len && j < i + MAX_ESCAPE + 1 && input.charAt(j) != ';')
j++;
if (j == len || j < i + MIN_ESCAPE || j == i + MAX_ESCAPE + 1) {
i++;
continue;
}
// found escape
if (input.charAt(i) == '#') {
// numeric escape
int k = i + 1;
int radix = 10;
final char firstChar = input.charAt(k);
if (firstChar == 'x' || firstChar == 'X') {
k++;
radix = 16;
}
try {
int entityValue = Integer.parseInt(input.substring(k, j), radix);
if (writer == null)
writer = new StringWriter(input.length());
writer.append(input.substring(st, i - 1));
if (entityValue > 0xFFFF) {
final char[] chrs = Character.toChars(entityValue);
writer.write(chrs[0]);
writer.write(chrs[1]);
} else {
writer.write(entityValue);
}
} catch (NumberFormatException ex) {
i++;
continue;
}
}
else {
// named escape
CharSequence value = htmldecode_lookupMap.get(input.substring(i, j));
if (value == null) {
i++;
continue;
}
if (writer == null)
writer = new StringWriter(input.length());
writer.append(input.substring(st, i - 1));
writer.append(value);
}
// skip escape
st = j + 1;
i = st;
}
if (writer != null) {
writer.append(input.substring(st, len));
return writer.toString();
}
return input;
}
private static final HashMap htmldecode_lookupMap;
static {
htmldecode_lookupMap = new HashMap();
for (final CharSequence[] seq : htmldecode_escapes())
htmldecode_lookupMap.put(seq[1].toString(), seq[0]);
}