/// <exception cref="System.Exception"/>
public virtual Pair <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> > > Call()
{
// CollectionValuedMap<String, Integer> tokensMatchedPattern = new
// CollectionValuedMap<String, Integer>();
TwoDimensionalCounter <CandidatePhrase, E> allFreq = new TwoDimensionalCounter <CandidatePhrase, E>();
CollectionValuedMap <E, Triple <string, int, int> > matchedTokensByPat = new CollectionValuedMap <E, Triple <string, int, int> >();
foreach (string sentid in sentids)
{
DataInstance sent = sents[sentid];
IList <CoreLabel> tokens = sent.GetTokens();
foreach (KeyValuePair <SemgrexPattern, E> pEn in patterns)
{
if (pEn.Key == null)
{
throw new Exception("why is the pattern " + pEn + " null?");
}
SemanticGraph graph = ((DataInstanceDep)sent).GetGraph();
//SemgrexMatcher m = pEn.getKey().matcher(graph);
//TokenSequenceMatcher m = pEn.getKey().matcher(sent);
// //Setting this find type can save time in searching - greedy and reluctant quantifiers are not enforced
// m.setFindType(SequenceMatcher.FindType.FIND_ALL);
//Higher branch values makes the faster but uses more memory
//m.setBranchLimit(5);
ICollection <ExtractedPhrase> matched = GetMatchedTokensIndex(graph, pEn.Key, sent, label);
foreach (ExtractedPhrase match in matched)
{
int s = match.startIndex;
int e = match.endIndex + 1;
string phrase = string.Empty;
string phraseLemma = string.Empty;
bool useWordNotLabeled = false;
bool doNotUse = false;
//find if the neighboring words are labeled - if so - club them together
if (constVars.clubNeighboringLabeledWords)
{
for (int i = s - 1; i >= 0; i--)
{
if (tokens[i].Get(constVars.GetAnswerClass()[label]).Equals(label) && (e - i + 1) <= PatternFactory.numWordsCompoundMapped[label])
{
s = i;
}
else
{
//System.out.println("for phrase " + match + " clubbing earlier word. new s is " + s);
break;
}
}
for (int i_1 = e; i_1 < tokens.Count; i_1++)
{
if (tokens[i_1].Get(constVars.GetAnswerClass()[label]).Equals(label) && (i_1 - s + 1) <= PatternFactory.numWordsCompoundMapped[label])
{
e = i_1;
}
else
{
//System.out.println("for phrase " + match + " clubbing next word. new e is " + e);
break;
}
}
}
//to make sure we discard phrases with stopwords in between, but include the ones in which stop words were removed at the ends if removeStopWordsFromSelectedPhrases is true
bool[] addedindices = new bool[e - s];
// Arrays.fill(addedindices, false); // get for free on array initialization
for (int i_2 = s; i_2 < e; i_2++)
{
CoreLabel l = tokens[i_2];
l.Set(typeof(PatternsAnnotations.MatchedPattern), true);
if (!l.ContainsKey(typeof(PatternsAnnotations.MatchedPatterns)) || l.Get(typeof(PatternsAnnotations.MatchedPatterns)) == null)
{
l.Set(typeof(PatternsAnnotations.MatchedPatterns), new HashSet <Pattern>());
}
Pattern pSur = pEn.Value;
System.Diagnostics.Debug.Assert(pSur != null, "Why is " + pEn.Value + " not present in the index?!");
System.Diagnostics.Debug.Assert(l.Get(typeof(PatternsAnnotations.MatchedPatterns)) != null, "How come MatchedPatterns class is null for the token. The classes in the key set are " + l.KeySet());
l.Get(typeof(PatternsAnnotations.MatchedPatterns)).Add(pSur);
foreach (KeyValuePair <Type, object> ig in constVars.GetIgnoreWordswithClassesDuringSelection()[label])
{
if (l.ContainsKey(ig.Key) && l.Get(ig.Key).Equals(ig.Value))
{
doNotUse = true;
}
}
bool containsStop = ContainsStopWord(l, constVars.GetCommonEngWords(), PatternFactory.ignoreWordRegex);
if (removePhrasesWithStopWords && containsStop)
{
doNotUse = true;
}
else
{
if (!containsStop || !removeStopWordsFromSelectedPhrases)
{
if (label == null || l.Get(constVars.GetAnswerClass()[label]) == null || !l.Get(constVars.GetAnswerClass()[label]).Equals(label))
{
useWordNotLabeled = true;
}
phrase += " " + l.Word();
phraseLemma += " " + l.Lemma();
addedindices[i_2 - s] = true;
}
}
}
for (int i_3 = 0; i_3 < addedindices.Length; i_3++)
{
if (i_3 > 0 && i_3 < addedindices.Length - 1 && addedindices[i_3 - 1] == true && addedindices[i_3] == false && addedindices[i_3 + 1] == true)
{
doNotUse = true;
break;
}
}
if (!doNotUse && useWordNotLabeled)
{
matchedTokensByPat.Add(pEn.Value, new Triple <string, int, int>(sentid, s, e - 1));
if (useWordNotLabeled)
{
phrase = phrase.Trim();
phraseLemma = phraseLemma.Trim();
allFreq.IncrementCount(CandidatePhrase.CreateOrGet(phrase, phraseLemma, match.GetFeatures()), pEn.Value, 1.0);
}
}
}
}
}
return(new Pair <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> > >(allFreq, matchedTokensByPat));
}
/// <exception cref="System.Exception"/>
public virtual Triple <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> >, ICollection <CandidatePhrase> > Call()
{
// CollectionValuedMap<String, Integer> tokensMatchedPattern = new
// CollectionValuedMap<String, Integer>();
try
{
ICollection <CandidatePhrase> alreadyLabeledPhrases = new HashSet <CandidatePhrase>();
TwoDimensionalCounter <CandidatePhrase, E> allFreq = new TwoDimensionalCounter <CandidatePhrase, E>();
CollectionValuedMap <E, Triple <string, int, int> > matchedTokensByPat = new CollectionValuedMap <E, Triple <string, int, int> >();
foreach (string sentid in sentids)
{
IList <CoreLabel> sent = sents[sentid].GetTokens();
foreach (KeyValuePair <TokenSequencePattern, E> pEn in patterns)
{
if (pEn.Key == null)
{
throw new Exception("why is the pattern " + pEn + " null?");
}
TokenSequenceMatcher m = ((TokenSequenceMatcher)pEn.Key.GetMatcher(sent));
// //Setting this find type can save time in searching - greedy and reluctant quantifiers are not enforced
// m.setFindType(SequenceMatcher.FindType.FIND_ALL);
//Higher branch values makes the faster but uses more memory
m.SetBranchLimit(5);
while (m.Find())
{
int s = m.Start("$term");
int e = m.End("$term");
System.Diagnostics.Debug.Assert(e - s <= PatternFactory.numWordsCompoundMapped[label], "How come the pattern " + pEn.Key + " is extracting phrases longer than numWordsCompound of " + PatternFactory.numWordsCompoundMapped[label] + " for label "
+ label);
string phrase = string.Empty;
string phraseLemma = string.Empty;
bool useWordNotLabeled = false;
bool doNotUse = false;
//find if the neighboring words are labeled - if so - club them together
if (constVars.clubNeighboringLabeledWords)
{
for (int i = s - 1; i >= 0; i--)
{
if (!sent[i].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
s = i + 1;
break;
}
}
for (int i_1 = e; i_1 < sent.Count; i_1++)
{
if (!sent[i_1].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
e = i_1;
break;
}
}
}
//to make sure we discard phrases with stopwords in between, but include the ones in which stop words were removed at the ends if removeStopWordsFromSelectedPhrases is true
bool[] addedindices = new bool[e - s];
// Arrays.fill(addedindices, false); // not needed as initialized false
for (int i_2 = s; i_2 < e; i_2++)
{
CoreLabel l = sent[i_2];
l.Set(typeof(PatternsAnnotations.MatchedPattern), true);
if (!l.ContainsKey(typeof(PatternsAnnotations.MatchedPatterns)) || l.Get(typeof(PatternsAnnotations.MatchedPatterns)) == null)
{
l.Set(typeof(PatternsAnnotations.MatchedPatterns), new HashSet <Pattern>());
}
SurfacePattern pSur = (SurfacePattern)pEn.Value;
System.Diagnostics.Debug.Assert(pSur != null, "Why is " + pEn.Value + " not present in the index?!");
System.Diagnostics.Debug.Assert(l.Get(typeof(PatternsAnnotations.MatchedPatterns)) != null, "How come MatchedPatterns class is null for the token. The classes in the key set are " + l.KeySet());
l.Get(typeof(PatternsAnnotations.MatchedPatterns)).Add(pSur);
foreach (KeyValuePair <Type, object> ig in constVars.GetIgnoreWordswithClassesDuringSelection()[label])
{
if (l.ContainsKey(ig.Key) && l.Get(ig.Key).Equals(ig.Value))
{
doNotUse = true;
}
}
bool containsStop = ContainsStopWord(l, constVars.GetCommonEngWords(), PatternFactory.ignoreWordRegex);
if (removePhrasesWithStopWords && containsStop)
{
doNotUse = true;
}
else
{
if (!containsStop || !removeStopWordsFromSelectedPhrases)
{
if (label == null || l.Get(constVars.GetAnswerClass()[label]) == null || !l.Get(constVars.GetAnswerClass()[label]).Equals(label))
{
useWordNotLabeled = true;
}
phrase += " " + l.Word();
phraseLemma += " " + l.Lemma();
addedindices[i_2 - s] = true;
}
}
}
for (int i_3 = 0; i_3 < addedindices.Length; i_3++)
{
if (i_3 > 0 && i_3 < addedindices.Length - 1 && addedindices[i_3 - 1] == true && addedindices[i_3] == false && addedindices[i_3 + 1] == true)
{
doNotUse = true;
break;
}
}
if (!doNotUse)
{
matchedTokensByPat.Add(pEn.Value, new Triple <string, int, int>(sentid, s, e - 1));
phrase = phrase.Trim();
if (!phrase.IsEmpty())
{
phraseLemma = phraseLemma.Trim();
CandidatePhrase candPhrase = CandidatePhrase.CreateOrGet(phrase, phraseLemma);
allFreq.IncrementCount(candPhrase, pEn.Value, 1.0);
if (!useWordNotLabeled)
{
alreadyLabeledPhrases.Add(candPhrase);
}
}
}
}
}
}
return(new Triple <TwoDimensionalCounter <CandidatePhrase, E>, CollectionValuedMap <E, Triple <string, int, int> >, ICollection <CandidatePhrase> >(allFreq, matchedTokensByPat, alreadyLabeledPhrases));
}
catch (Exception e)
{
logger.Error(e);
throw;
}
}
/// <exception cref="System.Exception"/>
public virtual Pair <TwoDimensionalCounter <Pair <string, string>, E>, CollectionValuedMap <E, Triple <string, int, int> > > Call()
{
//CollectionValuedMap<String, Integer> tokensMatchedPattern = new CollectionValuedMap<String, Integer>();
CollectionValuedMap <E, Triple <string, int, int> > matchedTokensByPat = new CollectionValuedMap <E, Triple <string, int, int> >();
TwoDimensionalCounter <Pair <string, string>, E> allFreq = new TwoDimensionalCounter <Pair <string, string>, E>();
foreach (string sentid in sentids)
{
IList <CoreLabel> sent = sents[sentid].GetTokens();
//FIND_ALL is faster than FIND_NONOVERLAP
IEnumerable <ISequenceMatchResult <ICoreMap> > matched = multiPatternMatcher.Find(sent, SequenceMatcher.FindType.FindAll);
foreach (ISequenceMatchResult <ICoreMap> m in matched)
{
int s = m.Start("$term");
int e = m.End("$term");
E matchedPat = patterns[m.Pattern()];
matchedTokensByPat.Add(matchedPat, new Triple <string, int, int>(sentid, s, e));
string phrase = string.Empty;
string phraseLemma = string.Empty;
bool useWordNotLabeled = false;
bool doNotUse = false;
//find if the neighboring words are labeled - if so - club them together
if (constVars.clubNeighboringLabeledWords)
{
for (int i = s - 1; i >= 0; i--)
{
if (!sent[i].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
s = i + 1;
break;
}
}
for (int i_1 = e; i_1 < sent.Count; i_1++)
{
if (!sent[i_1].Get(constVars.GetAnswerClass()[label]).Equals(label))
{
e = i_1;
break;
}
}
}
//to make sure we discard phrases with stopwords in between, but include the ones in which stop words were removed at the ends if removeStopWordsFromSelectedPhrases is true
bool[] addedindices = new bool[e - s];
// Arrays.fill(addedindices, false); // unneeded as done on initialization
for (int i_2 = s; i_2 < e; i_2++)
{
CoreLabel l = sent[i_2];
l.Set(typeof(PatternsAnnotations.MatchedPattern), true);
if (!l.ContainsKey(typeof(PatternsAnnotations.MatchedPatterns)))
{
l.Set(typeof(PatternsAnnotations.MatchedPatterns), new HashSet <Pattern>());
}
l.Get(typeof(PatternsAnnotations.MatchedPatterns)).Add(matchedPat);
// if (restrictToMatched) {
// tokensMatchedPattern.add(sentid, i);
// }
foreach (KeyValuePair <Type, object> ig in constVars.GetIgnoreWordswithClassesDuringSelection()[label])
{
if (l.ContainsKey(ig.Key) && l.Get(ig.Key).Equals(ig.Value))
{
doNotUse = true;
}
}
bool containsStop = ContainsStopWord(l, constVars.GetCommonEngWords(), PatternFactory.ignoreWordRegex);
if (removePhrasesWithStopWords && containsStop)
{
doNotUse = true;
}
else
{
if (!containsStop || !removeStopWordsFromSelectedPhrases)
{
if (label == null || l.Get(constVars.GetAnswerClass()[label]) == null || !l.Get(constVars.GetAnswerClass()[label]).Equals(label.ToString()))
{
useWordNotLabeled = true;
}
phrase += " " + l.Word();
phraseLemma += " " + l.Lemma();
addedindices[i_2 - s] = true;
}
}
}
for (int i_3 = 0; i_3 < addedindices.Length; i_3++)
{
if (i_3 > 0 && i_3 < addedindices.Length - 1 && addedindices[i_3 - 1] == true && addedindices[i_3] == false && addedindices[i_3 + 1] == true)
{
doNotUse = true;
break;
}
}
if (!doNotUse && useWordNotLabeled)
{
phrase = phrase.Trim();
phraseLemma = phraseLemma.Trim();
allFreq.IncrementCount(new Pair <string, string>(phrase, phraseLemma), matchedPat, 1.0);
}
}
}
// for (SurfacePattern pat : patterns.keySet()) {
// String patternStr = pat.toString();
//
// TokenSequencePattern p = TokenSequencePattern.compile(constVars.env.get(label), patternStr);
// if (pat == null || p == null)
// throw new RuntimeException("why is the pattern " + pat + " null?");
//
// TokenSequenceMatcher m = p.getMatcher(sent);
// while (m.find()) {
//
// int s = m.start("$term");
// int e = m.end("$term");
//
// String phrase = "";
// String phraseLemma = "";
// boolean useWordNotLabeled = false;
// boolean doNotUse = false;
// for (int i = s; i < e; i++) {
// CoreLabel l = sent.get(i);
// l.set(PatternsAnnotations.MatchedPattern.class, true);
// if (restrictToMatched) {
// tokensMatchedPattern.add(sentid, i);
// }
// for (Entry<Class, Object> ig : constVars.ignoreWordswithClassesDuringSelection.get(label).entrySet()) {
// if (l.containsKey(ig.getKey()) && l.get(ig.getKey()).equals(ig.getValue())) {
// doNotUse = true;
// }
// }
// boolean containsStop = containsStopWord(l, constVars.getCommonEngWords(), constVars.ignoreWordRegex, ignoreWords);
// if (removePhrasesWithStopWords && containsStop) {
// doNotUse = true;
// } else {
// if (!containsStop || !removeStopWordsFromSelectedPhrases) {
//
// if (label == null || l.get(constVars.answerClass.get(label)) == null || !l.get(constVars.answerClass.get(label)).equals(label.toString())) {
// useWordNotLabeled = true;
// }
// phrase += " " + l.word();
// phraseLemma += " " + l.lemma();
//
// }
// }
// }
// if (!doNotUse && useWordNotLabeled) {
// phrase = phrase.trim();
// phraseLemma = phraseLemma.trim();
// allFreq.incrementCount(new Pair<String, String>(phrase, phraseLemma), pat, 1.0);
// }
// }
// }
return(new Pair <TwoDimensionalCounter <Pair <string, string>, E>, CollectionValuedMap <E, Triple <string, int, int> > >(allFreq, matchedTokensByPat));
}