I'm new to Lucene and trying to sort this out. I'm indexing like this:
Directory dir = FSDirectory.Open(new System.IO.DirectoryInfo(dirIndexDir));
//Create the indexWriter
IndexWriter writer = new IndexWriter(dir, new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29), true,
IndexWriter.MaxFieldLength.UNLIMITED);
Document doc = new Document();
doc.Add(new Field("keyform_type", entry.keyForm.type, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_lang", entry.keyForm.lang, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_dial", entry.keyForm.dial, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_reg", entry.keyForm.reg, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("keyform_term", entry.keyForm.term.Value, Field.Store.YES, Field.Index.ANALYZED));
if(entry.refForm.type!=null)
doc.Add(new Field("refform_type", entry.refForm.type, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.refForm.lang!=null)
doc.Add(new Field("refform_lang", entry.refForm.lang, Field.Store.YES, Field.Index.NOT_ANALYZED));
if (entry.refForm.dial != null)
doc.Add(new Field("refform_dial", entry.refForm.dial, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.refForm.reg!=null)
doc.Add(new Field("refform_reg", entry.refForm.reg, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.refForm.term.Value!=null)
doc.Add(new Field("refform_term", entry.refForm.term.Value, Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("pos", entry.pos, Field.Store.YES, Field.Index.NOT_ANALYZED));
for (int s = 0; s < entry.subject.Count; s++)
{
doc.Add(new Field("subject_"+s, entry.subject[s], Field.Store.YES, Field.Index.NOT_ANALYZED));
}
for (int g = 0; g < entry.sense.gloss.Count; g++)
{
doc.Add(new Field("gloss_"+g, entry.sense.gloss[g], Field.Store.YES, Field.Index.ANALYZED));
}
if (entry.signature.action != null)
doc.Add(new Field("action", entry.signature.action, Field.Store.YES, Field.Index.NOT_ANALYZED));
if (entry.signature.source != null)
doc.Add(new Field("source", entry.signature.source, Field.Store.YES, Field.Index.NOT_ANALYZED));
if(entry.signature.date==0)
doc.Add(new Field("date", entry.signature.date.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
//Add the doc
writer.AddDocument(doc);
writer.Close();
I then query using this code:
//Doesn't matter what term is, same result
string term="workers";
Directory dir = FSDirectory.Open(new System.IO.DirectoryInfo(luceneDir));
IndexSearcher searcher = new IndexSearcher(dir, true);
List<string> b=new List<string>();
b.Add("keyform_gloss");
b.Add("keyform_term");
b.Add("refform_term");
b.Add("refform_gloss");
for (int i = 0; i < nMaxDupes; i++)
b.Add("gloss_" + i.ToString());
MultiFieldQueryParser mfqp = new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_29,
b.ToArray(), new StandardAnalyzer());
Query q = mfqp.Parse(term);
TopDocs td = searcher.Search(q, 300);
for (int i = 0; i < td.totalHits; i++)
{
//Generate a dictionaryEntry for each hit
Document doc = searcher.Doc(i);
//Access the document fields, blah
}
No matter what the value of term is, Lucene returns the first X documents in the index, where X = the number of documents that actually match term. When I browse the index using LUKE, an identical hand-typed query (keyform_term:term gloss_0:term etc) returns both the correct number of results and the correct documents matching those results.
The C# code above, however, always returns the first X documents, which don't necessarily contain the search term in any of the searched fields. They're not even close.
What am I doing wrong? I know the index is good because I can search it in LUKE, so it has to be something in the query...
Thanks!