Can someone please help activate stemming on my code. Tried a lot but without much success :(
My current code
Directory createIndex(DataTable table)
{
var directory = new RAMDirectory();
using (Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30))
using (var writer = new IndexWriter(directory, analyzer, new IndexWriter.MaxFieldLength(1000)))
{
foreach (DataRow row in table.Rows)
{
var document = new Document();
document.Add(new Field("DishName", row["DishName"].ToString(), Field.Store.YES, Field.Index.ANALYZED));
document.Add(new Field("CustomisationID", row["CustomisationID"].ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(document);
}
writer.Optimize();
writer.Flush(true, true, true);
}
return directory;
}
private DataTable SearchDishName(string textSearch)
{
string MatchingCutomisationIDs = "0"; //There is no Dish with ID zero, this is just to easen the coding..
var ds = new DataSet();
ds.ReadXml(System.Web.HttpContext.Current.Server.MapPath("~/App_data/MyDataset.xml"));
DataTable Sample = new DataTable();
Sample = ds.Tables[0];
var table = Sample.Clone();
var Index = createIndex(Sample);
using (var reader = IndexReader.Open(Index, true))
using (var searcher = new IndexSearcher(reader))
{
using (Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30))
{
var queryParser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, "DishName", analyzer);
var collector = TopScoreDocCollector.Create(1000, true);
try
{
var query = queryParser.Parse(textSearch);
searcher.Search(query, collector);
}
catch
{ }
var matches = collector.TopDocs().ScoreDocs;
foreach (var item in matches)
{
var id = item.Doc;
var doc = searcher.Doc(id);
var row = table.NewRow();
row["CustomisationID"] = doc.GetField("CustomisationID").StringValue;
table.Rows.Add(row);
}
}
}
return table;
}
StandardAnalyzer
does not include stemming. Use SnowballAnalyzer
instead. Such as, for English text:
Analyzer analyzer = new SnowballAnalyzer(Lucene.Net.Util.Version.LUCENE_30, "English")