/// <summary>
/// Computes a score factor for a simple term and returns an explanation
/// for that score factor.
///
/// <p>
/// The default implementation uses:
///
/// <pre class="prettyprint">
/// idf(docFreq, searcher.maxDoc());
/// </pre>
///
/// Note that <seealso cref="CollectionStatistics#maxDoc()"/> is used instead of
/// <seealso cref="Lucene.Net.Index.IndexReader#numDocs() IndexReader#numDocs()"/> because also
/// <seealso cref="TermStatistics#docFreq()"/> is used, and when the latter
/// is inaccurate, so is <seealso cref="CollectionStatistics#maxDoc()"/>, and in the same direction.
/// In addition, <seealso cref="CollectionStatistics#maxDoc()"/> is more efficient to compute
/// </summary>
/// <param name="collectionStats"> collection-level statistics </param>
/// <param name="termStats"> term-level statistics for the term </param>
/// <returns> an Explain object that includes both an idf score factor
/// and an explanation for the term. </returns>
public virtual Explanation IdfExplain(CollectionStatistics collectionStats, TermStatistics termStats)
{
long df = termStats.DocFreq();
long max = collectionStats.MaxDoc;
float idf = Idf(df, max);
return(new Explanation(idf, "idf(docFreq=" + df + ", maxDocs=" + max + ")"));
}
/// <summary>
/// Fills all member fields defined in {@code BasicStats} in {@code stats}.
/// Subclasses can override this method to fill additional stats.
/// </summary>
protected internal virtual void FillBasicStats(BasicStats stats, CollectionStatistics collectionStats, TermStatistics termStats)
{
// #positions(field) must be >= #positions(term)
Debug.Assert(collectionStats.SumTotalTermFreq() == -1 || collectionStats.SumTotalTermFreq() >= termStats.TotalTermFreq());
long numberOfDocuments = collectionStats.MaxDoc;
long docFreq = termStats.DocFreq();
long totalTermFreq = termStats.TotalTermFreq();
// codec does not supply totalTermFreq: substitute docFreq
if (totalTermFreq == -1)
{
totalTermFreq = docFreq;
}
long numberOfFieldTokens;
float avgFieldLength;
long sumTotalTermFreq = collectionStats.SumTotalTermFreq();
if (sumTotalTermFreq <= 0)
{
// field does not exist;
// We have to provide something if codec doesnt supply these measures,
// or if someone omitted frequencies for the field... negative values cause
// NaN/Inf for some scorers.
numberOfFieldTokens = docFreq;
avgFieldLength = 1;
}
else
{
numberOfFieldTokens = sumTotalTermFreq;
avgFieldLength = (float)numberOfFieldTokens / numberOfDocuments;
}
// TODO: add sumDocFreq for field (numberOfFieldPostings)
stats.NumberOfDocuments = numberOfDocuments;
stats.NumberOfFieldTokens = numberOfFieldTokens;
stats.AvgFieldLength = avgFieldLength;
stats.DocFreq = docFreq;
stats.TotalTermFreq = totalTermFreq;
}
/// <summary>
/// Computes a score factor for a simple term and returns an explanation
/// for that score factor.
///
/// <p>
/// The default implementation uses:
///
/// <pre class="prettyprint">
/// idf(docFreq, searcher.maxDoc());
/// </pre>
///
/// Note that <seealso cref="CollectionStatistics#maxDoc()"/> is used instead of
/// <seealso cref="Lucene.Net.Index.IndexReader#numDocs() IndexReader#numDocs()"/> because also
/// <seealso cref="TermStatistics#docFreq()"/> is used, and when the latter
/// is inaccurate, so is <seealso cref="CollectionStatistics#maxDoc()"/>, and in the same direction.
/// In addition, <seealso cref="CollectionStatistics#maxDoc()"/> is more efficient to compute
/// </summary>
/// <param name="collectionStats"> collection-level statistics </param>
/// <param name="termStats"> term-level statistics for the term </param>
/// <returns> an Explain object that includes both an idf score factor
/// and an explanation for the term. </returns>
public virtual Explanation IdfExplain(CollectionStatistics collectionStats, TermStatistics termStats)
{
long df = termStats.DocFreq();
long max = collectionStats.MaxDoc();
float idf = Idf(df, max);
return new Explanation(idf, "idf(docFreq=" + df + ", maxDocs=" + max + ")");
}
/// <summary>
/// Fills all member fields defined in {@code BasicStats} in {@code stats}.
/// Subclasses can override this method to fill additional stats.
/// </summary>
protected internal virtual void FillBasicStats(BasicStats stats, CollectionStatistics collectionStats, TermStatistics termStats)
{
// #positions(field) must be >= #positions(term)
Debug.Assert(collectionStats.SumTotalTermFreq() == -1 || collectionStats.SumTotalTermFreq() >= termStats.TotalTermFreq());
long numberOfDocuments = collectionStats.MaxDoc;
long docFreq = termStats.DocFreq();
long totalTermFreq = termStats.TotalTermFreq();
// codec does not supply totalTermFreq: substitute docFreq
if (totalTermFreq == -1)
{
totalTermFreq = docFreq;
}
long numberOfFieldTokens;
float avgFieldLength;
long sumTotalTermFreq = collectionStats.SumTotalTermFreq();
if (sumTotalTermFreq <= 0)
{
// field does not exist;
// We have to provide something if codec doesnt supply these measures,
// or if someone omitted frequencies for the field... negative values cause
// NaN/Inf for some scorers.
numberOfFieldTokens = docFreq;
avgFieldLength = 1;
}
else
{
numberOfFieldTokens = sumTotalTermFreq;
avgFieldLength = (float)numberOfFieldTokens / numberOfDocuments;
}
// TODO: add sumDocFreq for field (numberOfFieldPostings)
stats.NumberOfDocuments = numberOfDocuments;
stats.NumberOfFieldTokens = numberOfFieldTokens;
stats.AvgFieldLength = avgFieldLength;
stats.DocFreq = docFreq;
stats.TotalTermFreq = totalTermFreq;
}