/**
* This method ensures that the output String has only valid XML unicode characters as specified
* by the XML 1.0 standard. For reference, please see the standard. This method will return an
* empty String if the input is null or empty.
*
* @author Donoiu Cristian, GPL The String whose non-valid characters we want to remove. in
* String, stripped of non-valid characters.
*/
public static String removeInvalidXMLCharacters(String s) {
StringBuilder out = new StringBuilder(); // Used to hold the output.
int codePoint; // Used to reference the current character.
// String ss = "\ud801\udc00"; // This is actualy one unicode
// character, represented by two code units!!!.
// System.out.println(ss.codePointCount(0, ss.length()));// See: 1
int i = 0;
while (i < s.length()) {
// System.out.println("i=" + i);
codePoint = s.codePointAt(i); // This is the unicode code of the character.
if ((codePoint == 0x9)
|| // Consider testing larger ranges first to improve speed.
(codePoint == 0xA)
|| (codePoint == 0xD)
|| ((codePoint >= 0x20) && (codePoint <= 0xD7FF))
|| ((codePoint >= 0xE000) && (codePoint <= 0xFFFD))
|| ((codePoint >= 0x10000) && (codePoint <= 0x10FFFF))) {
out.append(Character.toChars(codePoint));
}
i +=
Character.charCount(
codePoint); // Increment with the number of code units(java chars) needed to represent
// a Unicode char.
}
return out.toString();
}
