添加索引代码:
public class IndexManage
{
public static void AddIndex(List<QuestionItem> itemList)
{
Analyzer analyzer =new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29);
Lucene.Net.Store.FSDirectory fs = Lucene.Net.Store.FSDirectory.Open(new DirectoryInfo("IndexDirectory"));
IndexWriter writer =new IndexWriter(fs, analyzer,true,IndexWriter.MaxFieldLength.UNLIMITED);
foreach (var item in itemList)
{
AddDocument(writer, item);
}
writer.Commit();
writer.Optimize();
writer.Close();
}
private static void AddDocument(IndexWriter writer, QuestionItem item)
{
Document document =new Document();
document.Add(new Field("qid", item.QID.ToString(), Field.Store.YES, Field.Index.ANALYZED));
document.Add(new Field("title", item.Title, Field.Store.YES,Field.Index.ANALYZED));
document.Add(new Field("content", item.Content, Field.Store.YES, Field.Index.ANALYZED));
document.Add(new Field("supply", item.Supply, Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(document);
}
}
搜索代码:
public class SearchManage
{
public static List<QuestionItem> Search(string keyword)
{
Analyzer analyzer =new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29);
Lucene.Net.Store.FSDirectory fs = Lucene.Net.Store.FSDirectory.Open(new DirectoryInfo("IndexDirectory"));
IndexSearcher searcher =new IndexSearcher(fs,true);
MultiFieldQueryParser parser =new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_29,new string[] { "title", "content","supply" }, analyzer);
parser.SetDefaultOperator(QueryParser.Operator.OR);
Query query = parser.Parse(keyword);
var hits = searcher.Search(query, 2500);
List<QuestionItem> itemList =new List<QuestionItem>();
for (int i =0; i < hits.scoreDocs.Length; i++)
{
var doc =searcher.Doc ( hits.scoreDocs[i].doc);
itemList.Add(new QuestionItem() {
QID=Int32.Parse(doc.Get("qid")),
Title=doc.Get("title"),
Content=doc.Get("content"),
Supply=doc.Get("supply")
});
}
searcher.Close();
return itemList;
}
}
QuestionItem模型是:
public class QuestionItem
{
public int QID { get;set; }
public string Title{get;set;}
public string Content { get; set; }
public string Supply { get; set; }
}
测试代码是:
public static void Show()
{
AddIndex();
List<QuestionItem> itemList = SearchManage.Search("a");
Console.WriteLine("search result:");
foreach (var item in itemList)
{
Console.WriteLine(item.QID +""+ item.Title +""+ item.Content +""+ item.Supply);
}
}
private static void AddIndex()
{
List<QuestionItem> itemList =new List<QuestionItem>() {
new QuestionItem(){QID=1,Title="a",Content="ab",Supply="abc"},
new QuestionItem(){QID=2,Title="b",Content="a",Supply="fds a"},
new QuestionItem(){QID=3,Title="c",Content="c defg",Supply="as dfg hjk"},
new QuestionItem(){QID=4,Title="d",Content="def a b",Supply="kjhgf ds a"},
new QuestionItem(){QID=5,Title="e",Content="ef ab c",Supply="a sdf g hjkl"}
};
IndexManage.AddIndex(itemList);
}
现在的问题是: 搜索“a”,没有结果,但对于“ab”,“b”,“c”有结果,一个非常奇怪的问题,谁能帮帮我?
答案 0 :(得分:2)
StandardAnalyzer使用默认停用词列表,其中一个是'a'。如果你不想要停用词,你可以使用带有空集的构造函数作为第二个参数:
Analyzer ana = new StandardAnalyzer(LUCENE_30, Collections.emptySet());
或.net这样:
Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29, new Hashtable());