public override bool LessThan(Object a, Object b)
{
PQRecord aa = (PQRecord)a;
PQRecord bb = (PQRecord)b;
float fa = aa.score;
float fb = bb.score;
return(fa > fb);
}
/// <summary> Create a PriorityQueue from a word->tf map.
///
/// </summary>
/// <param name="words">a map of words keyed on the word(String) with Int objects as the values.
/// </param>
private PriorityQueue CreateQueue(IDictionary words)
{
// have collected all words in doc and their freqs
int numDocs = ir.NumDocs();
FreqQ res = new FreqQ(words.Count); // will order words by score
IEnumerator it = words.Keys.GetEnumerator();
while (it.MoveNext())
{
// for every word
String word = (String)it.Current;
int tf = ((Int)words[word]).x; // term freq in the source doc
if (minTermFreq > 0 && tf < minTermFreq)
{
continue; // filter out words that don't occur enough times in the source
}
// go through all the fields and find the largest document frequency
String topField = fieldNames[0];
int docFreq = 0;
for (int i = 0; i < fieldNames.Length; i++)
{
int freq = ir.DocFreq(new Term(fieldNames[i], word));
topField = (freq > docFreq) ? fieldNames[i] : topField;
docFreq = (freq > docFreq) ? freq : docFreq;
}
if (minDocFreq > 0 && docFreq < minDocFreq)
{
continue; // filter out words that don't occur in enough docs
}
if (docFreq == 0)
{
continue; // index update problem?
}
float idf = similarity.Idf(docFreq, numDocs);
float score = tf * idf;
// only really need 1st 3 entries, other ones are for troubleshooting
PQRecord pqr = new PQRecord(
word,
topField,
score,
idf,
docFreq,
tf
);
res.Insert(pqr);
}
return(res);
}
/// <summary> Convenience routine to make it easy to return the most interesting words in a document.
/// More advanced users will call {@link #RetrieveTerms(java.io.Reader) retrieveTerms()} directly.
/// </summary>
/// <param name="r">the source document
/// </param>
/// <returns> the most interesting words in the document
///
/// </returns>
/// <seealso cref="#RetrieveTerms(java.io.Reader)">
/// </seealso>
/// <seealso cref="#setMaxQueryTerms">
/// </seealso>
public String[] RetrieveInterestingTerms(StreamReader r)
{
ArrayList al = new ArrayList(maxQueryTerms);
Lucene.Net.Util.PriorityQueue pq = RetrieveTerms(r);
Object cur;
int lim = maxQueryTerms; // have to be careful, retrieveTerms returns all words but that's probably not useful to our caller...
// we just want to return the top words
while (((cur = pq.Pop()) != null) && lim-- > 0)
{
PQRecord ar = (PQRecord)cur;
al.Add(ar.word); // the 1st entry is the interesting word
}
String[] res = new String[al.Count];
// return (System.String[]) SupportClass.ICollectionSupport.ToArray(al, res);
return((String[])al.ToArray(typeof(String)));
}
/// <summary> Create the More like query from a PriorityQueue</summary>
private Query CreateQuery(Lucene.Net.Util.PriorityQueue q)
{
Lucene.Net.Search.BooleanQuery query = new Lucene.Net.Search.BooleanQuery();
Object cur;
int qterms = 0;
float bestScore = 0;
while (((cur = q.Pop()) != null))
{
PQRecord ar = (PQRecord)cur;
Lucene.Net.Search.TermQuery tq = new Lucene.Net.Search.TermQuery(new Term(ar.topField, ar.word));
if (boost)
{
if (qterms == 0)
{
bestScore = ar.score;
}
float myScore = ar.score;
tq.SetBoost(myScore / bestScore);
}
try
{
query.Add(tq, Lucene.Net.Search.BooleanClause.Occur.SHOULD);
}
catch (Lucene.Net.Search.BooleanQuery.TooManyClauses)
{
break;
}
qterms++;
if (maxQueryTerms > 0 && qterms >= maxQueryTerms)
{
break;
}
}
return(query);
}
