| private appendCodePoint ( int par0 ) : global::java.lang.StringBuilder | ||
| par0 | int | |
| return | global::java.lang.StringBuilder | |
private int normalizeCharClass(StringBuilder newPattern, int i) {
StringBuilder charClass = new StringBuilder();
StringBuilder eq = null;
int lastCodePoint = -1;
String result;
i++;
charClass.append("[");
while(true) {
int c = normalizedPattern.codePointAt(i);
StringBuilder sequenceBuffer;
if (c == ']' && lastCodePoint != '\\') {
charClass.append((char)c);
break;
} else if (Character.getType(c) == Character.NON_SPACING_MARK) {
sequenceBuffer = new StringBuilder();
sequenceBuffer.appendCodePoint(lastCodePoint);
while(Character.getType(c) == Character.NON_SPACING_MARK) {
sequenceBuffer.appendCodePoint(c);
i += Character.charCount(c);
if (i >= normalizedPattern.length())
break;
c = normalizedPattern.codePointAt(i);
}
String ea = produceEquivalentAlternation(
sequenceBuffer.toString());
charClass.setLength(charClass.length()-Character.charCount(lastCodePoint));
if (eq == null)
eq = new StringBuilder();
eq.append('|');
eq.append(ea);
} else {
charClass.appendCodePoint(c);
i++;
}
if (i == normalizedPattern.length())
throw error(new String("Unclosed character class"));
lastCodePoint = c;
}
if (eq != null) {
result = new String("(?:"+charClass.toString()+eq.toString()+")");
} else {
result = charClass.toString();
}
newPattern.append(result);
return i;
}
private String[] producePermutations(String input) {
if (input.length() == countChars(input, 0, 1))
return new String[] {input};
if (input.length() == countChars(input, 0, 2)) {
int c0 = Character.codePointAt(input, 0);
int c1 = Character.codePointAt(input, Character.charCount(c0));
if (getClass(c1) == getClass(c0)) {
return new String[] {input};
}
String[] result = new String[2];
result[0] = input;
StringBuilder sb = new StringBuilder(2);
sb.appendCodePoint(c1);
sb.appendCodePoint(c0);
result[1] = sb.toString();
return result;
}
int length = 1;
int nCodePoints = countCodePoints(input);
for(int x=1; x<nCodePoints; x++)
length = length * (x+1);
String[] temp = new String[length];
int[] combClass = new int[nCodePoints];
for(int x=0, i=0; x<nCodePoints; x++) {
int c = Character.codePointAt(input, i);
combClass[x] = getClass(c);
i += Character.charCount(c);
}
// For each char, take it out and add the permutations
// of the remaining chars
int index = 0;
int len;
// offset maintains the index in code units.
for(int x=0, offset=0; x<nCodePoints; x++, offset+=len) {
continue1:
len = countChars(input, offset, 1);
boolean skip = false;
for(int y=x-1; y>=0; y--) {
if (combClass[y] == combClass[x]) {
offset+=len;
if (x < nCodePoints) goto continue1;
goto end1;
}
}
StringBuilder sb = new StringBuilder(input);
String otherChars = sb.delete(offset, offset+len).toString();
String[] subResult = producePermutations(otherChars);
String prefix = input.substring(offset, offset+len);
for(int y=0; y<subResult.Length; y++)
temp[index++] = prefix + subResult[y];
}
end1:
String[] _result = new String[index];
for (int x=0; x<index; x++)
_result[x] = temp[x];
return _result;
}
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();
}
