/**
* Create a mock node, to be added to the dependency tree but which is not part of the original
* sentence.
*
* @param toCopy The CoreLabel to copy from initially.
* @param word The new word to add.
* @param POS The new part of speech to add.
* @return A CoreLabel copying most fields from toCopy, but with a new word and POS tag (as well
* as a new index).
*/
@SuppressWarnings("UnusedDeclaration")
private CoreLabel mockNode(CoreLabel toCopy, String word, String POS) {
CoreLabel mock = new CoreLabel(toCopy);
mock.setWord(word);
mock.setLemma(word);
mock.setValue(word);
mock.setNER("O");
mock.setTag(POS);
mock.setIndex(sentenceLength + 5);
return mock;
}
/**
* Parse a CoNLL formatted tree into a SemanticGraph object (along with a list of tokens).
*
* @param conll The CoNLL formatted tree.
* @return A pair of a SemanticGraph and a token list, corresponding to the parse of the sentence
* and to tokens in the sentence.
*/
protected Pair<SemanticGraph, List<CoreLabel>> mkTree(String conll) {
List<CoreLabel> sentence = new ArrayList<>();
SemanticGraph tree = new SemanticGraph();
for (String line : conll.split("\n")) {
if (line.trim().equals("")) {
continue;
}
String[] fields = line.trim().split("\\s+");
int index = Integer.parseInt(fields[0]);
String word = fields[1];
CoreLabel label = IETestUtils.mkWord(word, index);
sentence.add(label);
if (fields[2].equals("0")) {
tree.addRoot(new IndexedWord(label));
} else {
tree.addVertex(new IndexedWord(label));
}
if (fields.length > 4) {
label.setTag(fields[4]);
}
if (fields.length > 5) {
label.setNER(fields[5]);
}
if (fields.length > 6) {
label.setLemma(fields[6]);
}
}
int i = 0;
for (String line : conll.split("\n")) {
if (line.trim().equals("")) {
continue;
}
String[] fields = line.trim().split("\\s+");
int parent = Integer.parseInt(fields[2]);
String reln = fields[3];
if (parent > 0) {
tree.addEdge(
new IndexedWord(sentence.get(parent - 1)),
new IndexedWord(sentence.get(i)),
new GrammaticalRelation(Language.UniversalEnglish, reln, null, null),
1.0,
false);
}
i += 1;
}
return Pair.makePair(tree, sentence);
}
/** Set the tags of the original tokens and the leaves if they aren't already set */
public static void setMissingTags(CoreMap sentence, Tree tree) {
List<TaggedWord> taggedWords = null;
List<Label> leaves = null;
List<CoreLabel> tokens = sentence.get(TokensAnnotation.class);
for (int i = 0; i < tokens.size(); ++i) {
CoreLabel token = tokens.get(i);
if (token.tag() == null) {
if (taggedWords == null) {
taggedWords = tree.taggedYield();
}
if (leaves == null) {
leaves = tree.yield();
}
token.setTag(taggedWords.get(i).tag());
Label leaf = leaves.get(i);
if (leaf instanceof HasTag) {
((HasTag) leaf).setTag(taggedWords.get(i).tag());
}
}
}
}
