private void normalize() {
boolean inCharClass = false;
int lastCodePoint = -1;
// Convert pattern into normalizedD form
normalizedPattern = Normalizer.normalize(pattern, Normalizer.Form.NFD);
patternLength = normalizedPattern.length();
// Modify pattern to match canonical equivalences
StringBuilder newPattern = new StringBuilder(patternLength);
for(int i=0; i<patternLength; ) {
int c = normalizedPattern.codePointAt(i);
StringBuilder sequenceBuffer;
if ((Character.getType(c) == Character.NON_SPACING_MARK)
&& (lastCodePoint != -1)) {
sequenceBuffer = new StringBuilder();
sequenceBuffer.appendCodePoint(lastCodePoint);
sequenceBuffer.appendCodePoint(c);
while(Character.getType(c) == Character.NON_SPACING_MARK) {
i += Character.charCount(c);
if (i >= patternLength)
break;
c = normalizedPattern.codePointAt(i);
sequenceBuffer.appendCodePoint(c);
}
String ea = produceEquivalentAlternation(
sequenceBuffer.toString());
newPattern.setLength(newPattern.length()-Character.charCount(lastCodePoint));
newPattern.append("(?:").append(ea).append(")");
} else if (c == '[' && lastCodePoint != '\\') {
i = normalizeCharClass(newPattern, i);
} else {
newPattern.appendCodePoint(c);
}
lastCodePoint = c;
i += Character.charCount(c);
}
normalizedPattern = newPattern.toString();
}
