在我的情况下,我需要搜索C#,。Net,C ++等关键字,其中标准分析器去除特殊字符,所以我使用空白分析器它不适合我。 索引:
public void Indexing(DataSet ds)
{
string indexFileLocation = @"D:\Lucene.Net\Data";
Lucene.Net.Store.Directory dir = Lucene.Net.Store.FSDirectory.GetDirectory(indexFileLocation, true);
IndexWriter indexWriter = new IndexWriter(dir, new WhitespaceAnalyzer(), Lucene.Net.Index.IndexWriter.MaxFieldLength.UNLIMITED);
if (ds.Tables[0] != null)
{
DataTable dt = ds.Tables[0];
if (dt.Rows.Count > 0)
{
foreach (DataRow dr in dt.Rows)
{
//Create the Document object
Document doc = new Document();
foreach (DataColumn dc in dt.Columns)
{
string check = dc.ToString();
if (check.Equals("Skill_Summary"))
{
doc.Add(new Field(dc.ColumnName, dr[dc.ColumnName].ToString(), Field.Store.YES, Field.Index.ANALYZED));
}
if (check.Equals("Title"))
{
doc.Add(new Field(dc.ColumnName, dr[dc.ColumnName].ToString(), Field.Store.YES, Field.Index.ANALYZED));
}
}
// Write the Document to the catalog
indexWriter.AddDocument(doc);
}
}
}
// Close the writer
indexWriter.Close();
}
和搜索字段如:
string[] searchfields = new string[] { "Skill_Summary", "Title" };
var parser = new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_29, searchfields, new WhitespaceAnalyzer());
string searchText = "C#";
//Split the search string into separate search terms by word
string[] terms = searchText.Split(new[] { " " }, StringSplitOptions.RemoveEmptyEntries);
foreach (string term in terms)
{
finalQuery.Add(parser.Parse(term.Replace("*", "") + "*"), BooleanClause.Occur.MUST);
}
hits = searcher.Search(finalQuery);
如何在我的情况下使用Whitespaceanalyzer和LowerCase过滤器构建自己的分析器?。