/// <exception cref="System.Exception"/>
private static void DescendantsHelper(SemanticGraph g, IndexedWord curr, ICollection <IndexedWord> descendantSet, IList <string> allCutOffRels, IList <IndexedWord> doNotAddThese, IList <IndexedWord> seenNodes, bool ignoreCommonTags, IPredicate <CoreLabel
> acceptWord, CollectionValuedMap <int, string> feat)
{
if (seenNodes.Contains(curr))
{
return;
}
seenNodes.Add(curr);
if (descendantSet.Contains(curr) || (doNotAddThese != null && doNotAddThese.Contains(curr)) || !acceptWord.Test(curr.BackingLabel()))
{
return;
}
if (!ignoreCommonTags || !ignoreTags.Contains(curr.Tag().Trim()))
{
descendantSet.Add(curr);
}
foreach (IndexedWord child in g.GetChildren(curr))
{
bool dontuse = false;
if (doNotAddThese != null && doNotAddThese.Contains(child))
{
dontuse = true;
}
GrammaticalRelation rel = null;
if (dontuse == false)
{
rel = g.Reln(curr, child);
dontuse = CheckIfSatisfiesRelConstrains(g, curr, child, allCutOffRels, rel);
}
if (dontuse == false)
{
foreach (string cutOffTagRegex in cutoffTags)
{
if (child.Tag().Matches(cutOffTagRegex))
{
if (Debug >= 5)
{
System.Console.Out.WriteLine("ignored tag " + child + " because it satisfied " + cutOffTagRegex);
}
dontuse = true;
break;
}
}
}
if (dontuse == false)
{
if (!feat.Contains(curr.Index()))
{
feat[curr.Index()] = new List <string>();
}
GetPatternsFromDataMultiClass.GetFeatures(g, curr, false, feat[curr.Index()], rel);
//feat.add(curr.index(), "REL-" + rel.getShortName());
DescendantsHelper(g, child, descendantSet, allCutOffRels, doNotAddThese, seenNodes, ignoreCommonTags, acceptWord, feat);
}
}
}
//Here, the index (startIndex, endIndex) seems to be inclusive of the endIndex
public virtual void PrintSubGraph(SemanticGraph g, IndexedWord w, IList <string> additionalCutOffRels, IList <string> textTokens, ICollection <string> listOfOutput, ICollection <IntPair> listOfOutputIndices, IList <IndexedWord> seenNodes, IList <IndexedWord
> doNotAddThese, bool findSubTrees, ICollection <ExtractedPhrase> extractedPhrases, SemgrexPattern pattern, IPredicate <CoreLabel> acceptWord)
{
try
{
if (seenNodes.Contains(w))
{
return;
}
seenNodes.Add(w);
if (doNotAddThese.Contains(w))
{
return;
}
IList <IndexedWord> andNodes = new List <IndexedWord>();
DescendantsWithReln(g, w, "conj_and", new List <IndexedWord>(), andNodes);
//System.out.println("and nodes are " + andNodes);
foreach (IndexedWord w1 in andNodes)
{
PrintSubGraph(g, w1, additionalCutOffRels, textTokens, listOfOutput, listOfOutputIndices, seenNodes, doNotAddThese, findSubTrees, extractedPhrases, pattern, acceptWord);
}
Sharpen.Collections.AddAll(doNotAddThese, andNodes);
IList <string> allCutOffRels = new List <string>();
if (additionalCutOffRels != null)
{
Sharpen.Collections.AddAll(allCutOffRels, additionalCutOffRels);
}
Sharpen.Collections.AddAll(allCutOffRels, cutoffRelations);
CollectionValuedMap <int, string> featPerToken = new CollectionValuedMap <int, string>();
ICollection <string> feat = new List <string>();
GetPatternsFromDataMultiClass.GetFeatures(g, w, true, feat, null);
ICollection <IndexedWord> words = Descendants(g, w, allCutOffRels, doNotAddThese, ignoreCommonTags, acceptWord, featPerToken);
// words.addAll(andNodes);
// if (includeSiblings == true) {
// for (IndexedWord ws : g.getSiblings(w)) {
// if (additionalCutOffNodes == null
// || !additionalCutOffNodes.contains(g.reln(g.getParent(w),
// ws).getShortName()))
// words.addAll(descendants(g, ws, additionalCutOffNodes, doNotAddThese));
// }
// }
// if(afterand != null){
// Set<IndexedWord> wordsAnd = descendants(g,afterand,
// additionalCutOffNodes);
// words.removeAll(wordsAnd);
// printSubGraph(g,afterand, includeSiblings, additionalCutOffNodes);
// }
//System.out.println("words are " + words);
if (words.Count > 0)
{
int min = int.MaxValue;
int max = -1;
foreach (IndexedWord word in words)
{
if (word.Index() < min)
{
min = word.Index();
}
if (word.Index() > max)
{
max = word.Index();
}
}
IntPair indices;
// Map<Integer, String> ph = new TreeMap<Integer, String>();
// String phrase = "";
// for (IndexedWord word : words) {
// ph.put(word.index(), word.value());
// }
// phrase = StringUtils.join(ph.values(), " ");
if ((max - min + 1) > maxPhraseLength)
{
max = min + maxPhraseLength - 1;
}
indices = new IntPair(min - 1, max - 1);
string phrase = StringUtils.Join(textTokens.SubList(min - 1, max), " ");
phrase = phrase.Trim();
feat.Add("LENGTH-" + (max - min + 1));
for (int i = min; i <= max; i++)
{
Sharpen.Collections.AddAll(feat, featPerToken[i]);
}
//System.out.println("phrase is " + phrase + " index is " + indices + " and maxphraselength is " + maxPhraseLength + " and descendentset is " + words);
ExtractedPhrase extractedPh = new ExtractedPhrase(min - 1, max - 1, pattern, phrase, Counters.AsCounter(feat));
if (!listOfOutput.Contains(phrase) && !doNotAddThese.Contains(phrase))
{
// if (sentElem != null) {
// Element node = new Element(elemString, curNS);
// node.addContent(phrase);
// sentElem.addContent(node);
// }
listOfOutput.Add(phrase);
if (!listOfOutputIndices.Contains(indices))
{
listOfOutputIndices.Add(indices);
extractedPhrases.Add(extractedPh);
}
if (findSubTrees == true)
{
foreach (IndexedWord word_1 in words)
{
if (!seenNodes.Contains(word_1))
{
PrintSubGraph(g, word_1, additionalCutOffRels, textTokens, listOfOutput, listOfOutputIndices, seenNodes, doNotAddThese, findSubTrees, extractedPhrases, pattern, acceptWord);
}
}
}
}
}
}
catch (Exception e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
}