public override bool Collect(BytesRef bytes)
{
int pos = PendingTerms.Add(bytes);
DocVisitCount += TermsEnum.DocFreq();
if (PendingTerms.Size() >= TermCountLimit || DocVisitCount >= DocCountCutoff)
{
HasCutOff = true;
return(false);
}
TermState termState = TermsEnum.TermState();
Debug.Assert(termState != null);
if (pos < 0)
{
pos = (-pos) - 1;
Array.TermState[pos].Register(termState, ReaderContext.Ord, TermsEnum.DocFreq(), TermsEnum.TotalTermFreq());
}
else
{
Array.TermState[pos] = new TermContext(TopReaderContext, termState, ReaderContext.Ord, TermsEnum.DocFreq(), TermsEnum.TotalTermFreq());
}
return(true);
}
public virtual void CollectTermContext(IndexReader reader, IList <AtomicReaderContext> leaves, TermContext[] contextArray, Term[] queryTerms)
{
TermsEnum termsEnum = null;
foreach (AtomicReaderContext context in leaves)
{
Fields fields = context.AtomicReader.Fields;
if (fields == null)
{
// reader has no fields
continue;
}
for (int i = 0; i < queryTerms.Length; i++)
{
Term term = queryTerms[i];
TermContext termContext = contextArray[i];
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.index.Terms terms = fields.terms(term.field());
Terms terms = fields.Terms(term.Field());
if (terms == null)
{
// field does not exist
continue;
}
termsEnum = terms.Iterator(termsEnum);
Debug.Assert(termsEnum != null);
if (termsEnum == TermsEnum.EMPTY)
{
continue;
}
if (termsEnum.SeekExact(term.Bytes()))
{
if (termContext == null)
{
contextArray[i] = new TermContext(reader.Context, termsEnum.TermState(), context.Ord, termsEnum.DocFreq(), termsEnum.TotalTermFreq());
}
else
{
termContext.Register(termsEnum.TermState(), context.Ord, termsEnum.DocFreq(), termsEnum.TotalTermFreq());
}
}
}
}
}
public virtual void CollectTermContext(IndexReader reader, IList <AtomicReaderContext> leaves, TermContext[] contextArray, Term[] queryTerms)
{
TermsEnum termsEnum = null;
foreach (AtomicReaderContext context in leaves)
{
Fields fields = context.AtomicReader.Fields;
if (fields == null)
{
// reader has no fields
continue;
}
for (int i = 0; i < queryTerms.Length; i++)
{
Term term = queryTerms[i];
TermContext termContext = contextArray[i];
Terms terms = fields.Terms(term.Field);
if (terms == null)
{
// field does not exist
continue;
}
termsEnum = terms.Iterator(termsEnum);
Debug.Assert(termsEnum != null);
if (termsEnum == TermsEnum.EMPTY)
{
continue;
}
if (termsEnum.SeekExact(term.Bytes))
{
if (termContext == null)
{
contextArray[i] = new TermContext(reader.Context, termsEnum.TermState(), context.Ord, termsEnum.DocFreq(), termsEnum.TotalTermFreq());
}
else
{
termContext.Register(termsEnum.TermState(), context.Ord, termsEnum.DocFreq(), termsEnum.TotalTermFreq());
}
}
}
}
}
public override bool Collect(BytesRef bytes)
{
int e = Terms.Add(bytes);
TermState state = TermsEnum.TermState();
Debug.Assert(state != null);
if (e < 0)
{
// duplicate term: update docFreq
int pos = (-e) - 1;
Array.TermState[pos].Register(state, ReaderContext.Ord, TermsEnum.DocFreq(), TermsEnum.TotalTermFreq());
Debug.Assert(Array.Boost[pos] == BoostAtt.Boost, "boost should be equal in all segment TermsEnums");
}
else
{
// new entry: we populate the entry initially
Array.Boost[e] = BoostAtt.Boost;
Array.TermState[e] = new TermContext(TopReaderContext, state, ReaderContext.Ord, TermsEnum.DocFreq(), TermsEnum.TotalTermFreq());
OuterInstance.CheckMaxClauseCount(Terms.Size());
}
return(true);
}
public override Spans GetSpans(AtomicReaderContext context, Bits acceptDocs, IDictionary <Term, TermContext> termContexts)
{
TermContext termContext;
termContexts.TryGetValue(term, out termContext);
TermState state;
if (termContext == null)
{
// this happens with span-not query, as it doesn't include the NOT side in extractTerms()
// so we seek to the term now in this segment..., this sucks because its ugly mostly!
Fields fields = context.AtomicReader.Fields;
if (fields != null)
{
Terms terms = fields.Terms(term.Field());
if (terms != null)
{
TermsEnum termsEnum = terms.Iterator(null);
if (termsEnum.SeekExact(term.Bytes()))
{
state = termsEnum.TermState();
}
else
{
state = null;
}
}
else
{
state = null;
}
}
else
{
state = null;
}
}
else
{
state = termContext.Get(context.Ord);
}
if (state == null) // term is not present in that reader
{
return(TermSpans.EMPTY_TERM_SPANS);
}
TermsEnum termsEnum_ = context.AtomicReader.Terms(term.Field()).Iterator(null);
termsEnum_.SeekExact(term.Bytes(), state);
DocsAndPositionsEnum postings = termsEnum_.DocsAndPositions(acceptDocs, null, DocsAndPositionsEnum.FLAG_PAYLOADS);
if (postings != null)
{
return(new TermSpans(postings, term));
}
else
{
// term does exist, but has no positions
throw new InvalidOperationException("field \"" + term.Field() + "\" was indexed without position data; cannot run SpanTermQuery (term=" + term.Text() + ")");
}
}
public override bool Collect(BytesRef bytes)
{
float boost = boostAtt.Boost;
// make sure within a single seg we always collect
// terms in order
Debug.Assert(CompareToLastTerm(bytes));
//System.out.println("TTR.collect term=" + bytes.utf8ToString() + " boost=" + boost + " ord=" + readerContext.ord);
// ignore uncompetitive hits
if (StQueue.Size() == MaxSize)
{
ScoreTerm t = StQueue.Top();
if (boost < t.Boost)
{
return(true);
}
if (boost == t.Boost && termComp.Compare(bytes, t.Bytes) > 0)
{
return(true);
}
}
ScoreTerm t2;
TermState state = termsEnum.TermState();
Debug.Assert(state != null);
if (visitedTerms.TryGetValue(bytes, out t2))
{
// if the term is already in the PQ, only update docFreq of term in PQ
Debug.Assert(t2.Boost == boost, "boost should be equal in all segment TermsEnums");
t2.TermState.Register(state, ReaderContext.Ord, termsEnum.DocFreq(), termsEnum.TotalTermFreq());
}
else
{
// add new entry in PQ, we must clone the term, else it may get overwritten!
st.Bytes.CopyBytes(bytes);
st.Boost = boost;
visitedTerms[st.Bytes] = st;
Debug.Assert(st.TermState.DocFreq == 0);
st.TermState.Register(state, ReaderContext.Ord, termsEnum.DocFreq(), termsEnum.TotalTermFreq());
StQueue.Add(st);
// possibly drop entries from queue
if (StQueue.Size() > MaxSize)
{
st = StQueue.Pop();
visitedTerms.Remove(st.Bytes);
st.TermState.Clear(); // reset the termstate!
}
else
{
st = new ScoreTerm(termComp, new TermContext(TopReaderContext));
}
Debug.Assert(StQueue.Size() <= MaxSize, "the PQ size must be limited to maxSize");
// set maxBoostAtt with values to help FuzzyTermsEnum to optimize
if (StQueue.Size() == MaxSize)
{
t2 = StQueue.Top();
maxBoostAtt.MaxNonCompetitiveBoost = t2.Boost;
maxBoostAtt.CompetitiveTerm = t2.Bytes;
}
}
return(true);
}