Да. Он полностью поддерживает Unicode.
Но для анализа вы должны явно назначить подходящие стеммеры и правильные стоп-слова.
Что касается образца. Вот копия с нашего последнего проекта
directory = new RAMDirectory();
analyzer = new StandardAnalyzer(version, new Hashtable());
var indexWriter = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
using (var session = sessionFactory.OpenStatelessSession())
{
organizations = session.CreateCriteria(typeof(Organization)).List<Organization>();
foreach (var organization in organizations)
{
var document = new Document();
document.Add(new Field("Id", organization.ID.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
document.Add(new Field("FullName", organization.FullName, Field.Store.NO, Field.Index.ANALYZED_NO_NORMS));
document.Add(new Field("ObjectTypeInvariantName", typeof(Organization).FullName, Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
indexWriter.AddDocument(document);
}
var persistentType = typeof(Order);
var classMetadata = DbContext.SessionFactory.GetClassMetadata(persistentType);
var properties = new List<PropertyInfo>();
for (int i = 0; i < classMetadata.PropertyTypes.Length; i++)
{
var propertyType = classMetadata.PropertyTypes[i];
if (propertyType.IsCollectionType || propertyType.IsEntityType) continue;
properties.Add(typeof(Order).GetProperty(classMetadata.PropertyNames[i]));
}
orders = session.CreateCriteria(typeof(Order)).List<Order>();
var idProperty = typeof(Order).GetProperty(classMetadata.IdentifierPropertyName);
foreach (var order in orders)
{
var document = new Document();
document.Add(new Field("Id", idProperty.GetValue(order, null).ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
document.Add(new Field("ObjectTypeInvariantName", typeof(Order).FullName, Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
foreach (var property in properties)
{
var value = property.GetValue(order, null);
if (value != null)
{
document.Add(new Field(property.Name, value.ToString(), Field.Store.NO, Field.Index.ANALYZED_NO_NORMS));
}
}
indexWriter.AddDocument(document);
}
indexWriter.Optimize(true);
indexWriter.Commit();
return indexWriter.GetReader();
}
Я запрашиваю объекты организации из NHibernate и помещаю их в Lucene.NET
Вот простой поиск
var searchValue = textEdit1.Text;
var parser = new QueryParser(version, "FullName", analyzer);
parser.SetLocale(new CultureInfo("ru-RU"));
Query query = parser.Parse(searchValue);
var indexSearcher = new IndexSearcher(directory, true);
var docs = indexSearcher.Search(query, 10);
lblSearchTotal.Text = string.Format(totalPattern, docs.totalHits, organizations.Count() + orders.Count);
resultPanel.Controls.Clear();
foreach (var found in docs.scoreDocs)
{
var document = indexSearcher.Doc(found.doc);
var objectId = document.Get("Id");
var objectType = document.Get("ObjectTypeInvariantName");
if (resultPanel.Controls.Count > 0)
{
var labelSeparator = CreateSeparatorLabelControl();
resultPanel.Controls.Add(labelSeparator);
}
var labelCard = CreateFoundLabelControl();
resultPanel.Controls.Add(labelCard);
var organization = organizations.Where(o => o.ID.ToString() == objectId).FirstOrDefault();
if (organization != null)
{
labelCard.Text = string.Format("<b>{0}</b></br>{1}", organization.AccountNumber, organization.FullName);
labelCard.Tag = organization;
//labels[count].Text = string.Format("<b>{0}</b></br>{1}", organization.AccountNumber, organization.FullName);
//labels[count].Visible = true;
}
else
{
labelCard.Text = string.Format("Найден объект типа '{0}' с идентификатором '{1}'", objectType, objectId);
labelCard.Tag = mainForm.GetObject(objectType, objectId);
}
labelCard.Visible = true;
//count++;
}