Turns out this was a lot easier than I expected. I just used the example implementation at http://lucene.apache.org/java/2_9_0/api/core/org/apache/lucene/search/Collector.html and recorded the doc numbers passed to the Collect()
method in a List, exposing this as a public Docs
property.
I then simply iterate this property, passing the number back to the Searcher
to get the proper Document
:
var searcher = new IndexSearcher( reader );
var collector = new IntegralCollector(); // my custom Collector
searcher.Search( query, collector );
var result = new Document[ collector.Docs.Count ];
for ( int i = 0; i < collector.Docs.Count; i++ )
result[ i ] = searcher.Doc( collector.Docs[ i ] );
searcher.Close(); // this is probably not needed
reader.Close();
So far it seems to be working fine in preliminary tests.
Update: Here's the code for IntegralCollector
:
internal class IntegralCollector: Lucene.Net.Search.Collector {
private int _docBase;
private List<int> _docs = new List<int>();
public List<int> Docs {
get { return _docs; }
}
public override bool AcceptsDocsOutOfOrder() {
return true;
}
public override void Collect( int doc ) {
_docs.Add( _docBase + doc );
}
public override void SetNextReader( Lucene.Net.Index.IndexReader reader, int docBase ) {
_docBase = docBase;
}
public override void SetScorer( Lucene.Net.Search.Scorer scorer ) {
}
}