public static IList <CorpusDocument> GetMoreLikeThis(string indexName, int indexDocumentId, int maxDocs)
{
// See: http://lucene.apache.org/java/2_2_0/api/org/apache/lucene/search/similar/MoreLikeThis.html
var mlt = new MoreLikeThis(Searcher.GetIndexReader());
mlt.SetAnalyzer(new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29));
mlt.SetFieldNames(new[] { "Title", "Content" });
mlt.SetMinWordLen(4); // improve relevancy
var query = mlt.Like(indexDocumentId);
var tsdc = TopScoreDocCollector.create(maxDocs, true);
Searcher.Search(query, tsdc);
var hits = tsdc.TopDocs().ScoreDocs;
var ret = new List <CorpusDocument>(maxDocs);
foreach (var hit in hits)
{
var d = Searcher.Doc(hit.doc);
ret.Add(new CorpusDocument
{
Id = d.Get("Id"),
Title = d.Get("Title"),
});
}
return(ret);
}
public IEnumerable <SearchEngineResult> RelatedContents(int entryId, int max, int blogId)
{
var list = new List <SearchEngineResult>();
//First look for the original doc
Query query = GetIdSearchQuery(entryId);
TopDocs hits = Searcher.Search(query, max);
if (hits.scoreDocs.Length <= 0)
{
return(list);
}
int docNum = hits.scoreDocs[0].doc;
//Setup MoreLikeThis searcher
var reader = DoWriterAction(w => w.GetReader());
var mlt = new MoreLikeThis(reader);
mlt.SetAnalyzer(_analyzer);
mlt.SetFieldNames(new[] { Title, Body, Tags });
mlt.SetMinDocFreq(_settings.Parameters.MinimumDocumentFrequency);
mlt.SetMinTermFreq(_settings.Parameters.MinimumTermFrequency);
mlt.SetBoost(_settings.Parameters.MoreLikeThisBoost);
var moreResultsQuery = mlt.Like(docNum);
return(PerformQuery(list, moreResultsQuery, max + 1, blogId, entryId));
}
public SearchEngineResponse RelatedContents(int entryId, int max, int blogId)
{
var list = new List <SearchEngineResult>();
//First look for the original doc
Query query = GetIdSearchQuery(entryId);
TopDocs hits = Searcher.Search(query, max);
if (hits.scoreDocs.Length <= 0)
{
return(new SearchEngineResponse {
TotalCount = hits.totalHits, Results = list
});
}
int docNum = hits.scoreDocs[0].doc;
//Setup MoreLikeThis searcher
var reader = DoWriterAction(w => w.GetReader());
var mlt = new MoreLikeThis(reader);
mlt.SetAnalyzer(_analyzer);
mlt.SetFieldNames(new[] { Categories, Silouhettes, Tags });
var moreResultsQuery = mlt.Like(docNum);
return(PerformQuery(list, moreResultsQuery, 0, max + 1, blogId, entryId));
}
public StoryCollection Find(int hostId, int storyId)
{
int?docId = ConvertStoryIdtoDocId(hostId, storyId);
if (docId.HasValue)
{
IndexSearcher indexSearch = SearchQuery.GetSearcher(hostId);
IndexReader indexReader = indexSearch.GetIndexReader();
MoreLikeThis mlt = new MoreLikeThis(indexReader);
mlt.SetAnalyzer(new DnkAnalyzer());
//mlt.SetFieldNames(new string[] { "title", "description" });
//these values control the query used to find related/similar stories
//
//-we are only using the title and tags fields,
//-the term must appear 1 or more times,
//-the query will only have 3 terms
//-a word less than 3 char in len with be ignored
//-the term must appear at in at least 4 doc
mlt.SetFieldNames(new string[] { "title", "tags" });
mlt.SetMinTermFreq(1);
mlt.SetMaxQueryTerms(5);
mlt.SetMinWordLen(3);
mlt.SetMinDocFreq(4);
mlt.SetStopWords(StopWords());
mlt.SetBoost(true);
Query mltQuery = mlt.Like(docId.Value);
Hits hits = indexSearch.Search(mltQuery);
List <int> results = new List <int>();
for (int i = 0; i < hits.Length(); i++)
{
Document d = hits.Doc(i);
int hitStoryId = int.Parse(d.GetField("id").StringValue());
if (hitStoryId != storyId)
{
results.Add(hitStoryId);
if (results.Count == NUMBER_OF_RELATED_STORIES_TO_RETURN)
{
break;
}
}
}
return(SearchQuery.LoadStorySearchResults(results));
}
else
{
return(null);
}
}