public UkkonenState(TreeString str) {
string = str;
lastE = 0;
edgesWithE = new LinkedList<TreeEdge>();
nextPhaseStart = 0;
nextExtStart = 0;
matcher = null;
nextNode = root;
gammaLength = 0;
rule2Node = null;
if (string.getIndex() > 0) {
matcher = findEdge(root, string, 0, string.length(), false);
nextPhaseStart = matcher.matchedTo;
nextExtStart = 0;
lastE = matcher.matchedTo;
logger.log(
Level.FINEST,
String.format(
"String %s can start at phase %d (E:%d)",
string.toString(), nextPhaseStart, lastE));
} else {
matcher = new EdgeMatch(string, 0, string.length());
}
currentSuffix = new StringSuffix(string, 0);
}
private void naiveExtendSuffixTree(int arrayIdx) {
TreeString string = strings.get(arrayIdx);
// the array.length-1 constraint, instead of array.length, is because
// we assume that the terminal character has already been added to the
// string, and we don't want to *just* add the suffix that is that
// character.
for (int i = 0; i <= string.length(); i++) {
logger.log(
Level.FINEST,
String.format("Naive Extension: \"%s\"", string.substring(i, string.length() + 1)));
naiveExtendSuffix(string, i);
}
}
public String getSuffixString() {
StringBuilder sb = new StringBuilder();
for (int i = offset; i <= string.length(); i++) {
sb.append(string.getChar(i));
}
return sb.toString();
}
private void naiveExtendSuffix(TreeString string, int start) {
EdgeMatch em = findEdge(root, string, start, string.length(), false);
StringSuffix stringSuffix = new StringSuffix(string, start);
TreeEdge leafEdge = null;
if (em.completedMatch()) {
leafEdge = em.lastEdge;
} else {
if (em.lastEdge == null) {
leafEdge = new TreeEdge(string, start, string.length(), root);
root.addEdge(leafEdge);
} else {
leafEdge = new TreeEdge(string, em.matchedTo, string.length(), em.lastEdge.tailNode);
if (em.inEdgeMiddle()) {
int offset = em.lastMatchLength();
em.lastEdge.split(offset);
}
em.lastEdge.tailNode.addEdge(leafEdge);
}
}
leafEdge.tailNode.suffixes.add(stringSuffix);
}
public boolean isTerminal() {
return start == string.length();
}