/**
* Takes a Tree and a collinizer and returns a Collection of {@link Constituent}s for PARSEVAL
* evaluation. Some notes on this particular parseval:
*
* <ul>
* <li>It is character-based, which allows it to be used on segmentation/parsing combination
* evaluation.
* <li>whether it gives you labeled or unlabeled bracketings depends on the value of the <code>
* labelConstituents</code> parameter
* </ul>
*
* (Note that I haven't checked this rigorously yet with the PARSEVAL definition -- Roger.)
*/
public static Collection<Constituent> parsevalObjectify(
Tree t, TreeTransformer collinizer, boolean labelConstituents) {
Collection<Constituent> spans = new ArrayList<Constituent>();
Tree t1 = collinizer.transformTree(t);
if (t1 == null) {
return spans;
}
for (Tree node : t1) {
if (node.isLeaf() || node.isPreTerminal() || (node != t1 && node.parent(t1) == null)) {
continue;
}
int leftEdge = t1.leftCharEdge(node);
int rightEdge = t1.rightCharEdge(node);
if (labelConstituents) spans.add(new LabeledConstituent(leftEdge, rightEdge, node.label()));
else spans.add(new SimpleConstituent(leftEdge, rightEdge));
}
return spans;
}
protected static void updateTreeLabels(
Tree root, Tree tree, MutableInteger offset, MutableInteger leafIndex) {
if (tree.isLeaf()) {
leafIndex.value++;
return;
}
String labelValue = tree.label().value().toUpperCase();
int begin = root.leftCharEdge(tree);
int end = root.rightCharEdge(tree);
// System.out.println(labelValue+"("+begin+","+end+")");
int length = end - begin;
// apply offset to begin extent
begin += offset.value;
// calculate offset delta based on label
if (double_quote_lable_pattern.matcher(labelValue).matches() && length > 1) {
offset.value--;
log.debug("Quotes label pattern fired: " + offset);
} else if (bracket_label_pattern.matcher(labelValue).matches()) {
offset.value -= 4;
log.debug("Bracket label pattern fired: " + offset);
} else if (tree.isPreTerminal()) {
Tree leaf = tree.firstChild();
String text = leaf.label().value();
Matcher matcher = escaped_char_pattern.matcher(text);
while (matcher.find()) {
offset.value--;
}
}
for (Tree child : tree.children()) updateTreeLabels(root, child, offset, leafIndex);
// apply offset to end extent
end += offset.value;
// set begin and end offsets on node
MapLabel label = new MapLabel(tree.label());
label.put(BEGIN_KEY, begin);
label.put(END_KEY, end);
label.put(MapLabel.INDEX_KEY, leafIndex.value);
tree.setLabel(label);
}