public override Query Rewrite(IndexReader reader, MultiTermQuery query)
{
// Get the enum and start visiting terms. If we
// exhaust the enum before hitting either of the
// cutoffs, we use ConstantBooleanQueryRewrite; else,
// ConstantFilterRewrite:
System.Collections.ArrayList pendingTerms = new System.Collections.ArrayList();
int docCountCutoff = (int)((docCountPercent / 100.0) * reader.MaxDoc());
int termCountLimit = System.Math.Min(BooleanQuery.GetMaxClauseCount(), termCountCutoff);
int docVisitCount = 0;
FilteredTermEnum enumerator = query.GetEnum(reader);
try
{
while (true)
{
Term t = enumerator.Term();
if (t != null)
{
pendingTerms.Add(t);
// Loading the TermInfo from the terms dict here
// should not be costly, because 1) the
// query/filter will load the TermInfo when it
// runs, and 2) the terms dict has a cache:
docVisitCount += reader.DocFreq(t);
}
if (pendingTerms.Count >= termCountLimit || docVisitCount >= docCountCutoff)
{
// Too many terms -- make a filter.
Query result = new ConstantScoreQuery(new MultiTermQueryWrapperFilter(query));
result.SetBoost(query.GetBoost());
return(result);
}
else if (!enumerator.Next())
{
// Enumeration is done, and we hit a small
// enough number of terms & docs -- just make a
// BooleanQuery, now
System.Collections.IEnumerator it = pendingTerms.GetEnumerator();
BooleanQuery bq = new BooleanQuery(true);
while (it.MoveNext())
{
TermQuery tq = new TermQuery((Term)it.Current);
bq.Add(tq, BooleanClause.Occur.SHOULD);
}
// Strip scores
Query result = new ConstantScoreQuery(new QueryWrapperFilter(bq));
result.SetBoost(query.GetBoost());
query.IncTotalNumberOfTerms(pendingTerms.Count);
return(result);
}
}
}
finally
{
enumerator.Close();
}
}
public override Query Rewrite(IndexReader reader)
{
FilteredTermEnum enumerator = GetEnum(reader);
int maxClauseCount = BooleanQuery.GetMaxClauseCount();
ScoreTermQueue stQueue = new ScoreTermQueue(maxClauseCount);
ScoreTerm reusableST = null;
try
{
do
{
float score = 0.0f;
Term t = enumerator.Term();
if (t != null)
{
score = enumerator.Difference();
if (reusableST == null)
{
reusableST = new ScoreTerm(t, score);
}
else if (score >= reusableST.score)
{
// reusableST holds the last "rejected" entry, so, if
// this new score is not better than that, there's no
// need to try inserting it
reusableST.score = score;
reusableST.term = t;
}
else
{
continue;
}
reusableST = (ScoreTerm)stQueue.InsertWithOverflow(reusableST);
}
}while (enumerator.Next());
}
finally
{
enumerator.Close();
}
BooleanQuery query = new BooleanQuery(true);
int size = stQueue.Size();
for (int i = 0; i < size; i++)
{
ScoreTerm st = (ScoreTerm)stQueue.Pop();
TermQuery tq = new TermQuery(st.term); // found a match
tq.SetBoost(GetBoost() * st.score); // set the boost
query.Add(tq, BooleanClause.Occur.SHOULD); // add to query
}
return(query);
}
public override Query Rewrite(IndexReader reader)
{
FilteredTermEnum enumerator = GetEnum(reader);
int maxClauseCount = BooleanQuery.GetMaxClauseCount();
ScoreTermQueue stQueue = new ScoreTermQueue(maxClauseCount);
try
{
do
{
float minScore = 0.0f;
float score = 0.0f;
Term t = enumerator.Term();
if (t != null)
{
score = enumerator.Difference();
// terms come in alphabetical order, therefore if queue is full and score
// not bigger than minScore, we can skip
if (stQueue.Size() < maxClauseCount || score > minScore)
{
stQueue.Insert(new ScoreTerm(t, score));
minScore = ((ScoreTerm)stQueue.Top()).score; // maintain minScore
}
}
}while (enumerator.Next());
}
finally
{
enumerator.Close();
}
BooleanQuery query = new BooleanQuery(true);
int size = stQueue.Size();
for (int i = 0; i < size; i++)
{
ScoreTerm st = (ScoreTerm)stQueue.Pop();
TermQuery tq = new TermQuery(st.term); // found a match
tq.SetBoost(GetBoost() * st.score); // set the boost
query.Add(tq, BooleanClause.Occur.SHOULD); // add to query
}
return(query);
}