public override Query Rewrite(IndexReader reader, MultiTermQuery query) { FilteredTermEnum enumerator = query.GetEnum(reader); BooleanQuery result = new BooleanQuery(true); int count = 0; try { do { Term t = enumerator.Term; if (t != null) { TermQuery tq = new TermQuery(t); // found a match tq.Boost = query.Boost * enumerator.Difference(); // set the boost result.Add(tq, Occur.SHOULD); // add to query count++; } }while (enumerator.Next()); } finally { enumerator.Close(); } query.IncTotalNumberOfTerms(count); return(result); }
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: ICollection <Term> pendingTerms = new List <Term>(); int docCountCutoff = (int)((docCountPercent / 100.0) * reader.MaxDoc); int termCountLimit = System.Math.Min(BooleanQuery.MaxClauseCount, 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 <MultiTermQuery>(query)); result.Boost = query.Boost; return(result); } else if (!enumerator.Next()) { // Enumeration is done, and we hit a small // enough number of terms & docs -- just make a // BooleanQuery, now BooleanQuery bq = new BooleanQuery(true); foreach (Term term in pendingTerms) { TermQuery tq = new TermQuery(term); bq.Add(tq, Occur.SHOULD); } // Strip scores Query result = new ConstantScoreQuery(new QueryWrapperFilter(bq)); result.Boost = query.Boost; query.IncTotalNumberOfTerms(pendingTerms.Count); return(result); } } } finally { enumerator.Close(); } }
public override Query Rewrite(IndexReader reader) { if (!termLongEnough) { // can only match if it's exact return(new TermQuery(Term)); } int maxSize = BooleanQuery.MaxClauseCount; // TODO: Java uses a PriorityQueue. Using Linq, we can emulate it, // however it's considerable slower than the java counterpart. // this should be a temporary thing, fixed before release SortedList <ScoreTerm, ScoreTerm> stQueue = new SortedList <ScoreTerm, ScoreTerm>(); FilteredTermEnum enumerator = GetEnum(reader); try { ScoreTerm st = new ScoreTerm(); do { Term t = enumerator.Term; if (t == null) { break; } float score = enumerator.Difference(); //ignore uncompetetive hits if (stQueue.Count >= maxSize && score <= stQueue.Keys.First().score) { continue; } // add new entry in PQ st.term = t; st.score = score; stQueue.Add(st, st); // possibly drop entries from queue if (stQueue.Count > maxSize) { st = stQueue.Keys.First(); stQueue.Remove(st); } else { st = new ScoreTerm(); } }while (enumerator.Next()); } finally { enumerator.Close(); } BooleanQuery query = new BooleanQuery(true); foreach (ScoreTerm st in stQueue.Keys) { TermQuery tq = new TermQuery(st.term); // found a match tq.Boost = Boost * st.score; // set the boost query.Add(tq, Occur.SHOULD); // add to query } return(query); }