public object Search(string keyWord, int pageIndex, int pageSize)
{
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
string indexPath = Directory.GetCurrentDirectory() + "/Index";
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NoLockFactory());
IndexReader reader = IndexReader.Open(directory, true);
//创建IndexSearcher准备进行搜索。
IndexSearcher searcher = new IndexSearcher(reader);
// 查询条件
keyWord = GetKeyWordsSplitBySpace(keyWord, new PanGuTokenizer());
//创建QueryParser查询解析器。用来对查询语句进行语法分析。
//QueryParser调用parser进行语法分析，形成查询语法树，放到Query中。
QueryParser msgQueryParser = new QueryParser(Lucene.Net.Util.Version.LUCENE_29, "Content", new PanGuAnalyzer(true));
Query msgQuery = msgQueryParser.Parse(keyWord);
//TopScoreDocCollector:盛放查询结果的容器
//numHits 获取条数
TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
//IndexSearcher调用search对查询语法树Query进行搜索，得到结果TopScoreDocCollector。
// 使用query这个查询条件进行搜索，搜索结果放入collector
searcher.Search(msgQuery, null, collector);
// 从查询结果中取出第n条到第m条的数据
ScoreDoc[] docs = collector.TopDocs(0, 1000).scoreDocs;
stopwatch.Stop();
// 遍历查询结果
List <ReturnModel> resultList = new List <ReturnModel>();
var pm = new Page <ReturnModel>
{
PageIndex = pageIndex,
PageSize = pageSize,
TotalRows = docs.Length
};
pm.TotalPages = pm.TotalRows / pageSize;
if (pm.TotalRows % pageSize != 0)
{
pm.TotalPages++;
}
for (int i = (pageIndex - 1) * pageSize; i < pageIndex * pageSize && i < docs.Length; i++)
{
var doc = searcher.Doc(docs[i].doc);
var content = HighlightHelper.HighLight(keyWord, doc.Get("Content"));
var result = new ReturnModel
{
Title = doc.Get("Title"),
Content = content,
Count = Regex.Matches(content, "<font").Count
};
resultList.Add(result);
}
pm.LsList = resultList;
var elapsedTime = stopwatch.ElapsedMilliseconds + "ms";
var list = new { list = pm, ms = elapsedTime };
return(list);
}
/// <summary>
/// 获取搜索结果
/// </summary>
protected void btnGetSearchResult_Click(object sender, EventArgs e)
{
string keyword = txtKeyWords.Text;
string indexPath = Context.Server.MapPath("~/Index"); // 索引文档保存位置
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NoLockFactory());
IndexReader reader = IndexReader.Open(directory, true);
IndexSearcher searcher = new IndexSearcher(reader);
// 查询条件
PhraseQuery query = new PhraseQuery();
// 等同于 where contains("msg",kw)
query.Add(new Term("msg", keyword));
// 两个词的距离大于100（经验值）就不放入搜索结果，因为距离太远相关度就不高了
query.SetSlop(100);
// TopScoreDocCollector:盛放查询结果的容器
TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
// 使用query这个查询条件进行搜索，搜索结果放入collector
searcher.Search(query, null, collector);
// 从查询结果中取出第m条到第n条的数据
// collector.GetTotalHits()表示总的结果条数
ScoreDoc[] docs = collector.TopDocs(0, collector.GetTotalHits()).scoreDocs;
// 遍历查询结果
IList <SearchResult> resultList = new List <SearchResult>();
for (int i = 0; i < docs.Length; i++)
{
// 拿到文档的id，因为Document可能非常占内存（DataSet和DataReader的区别）
int docId = docs[i].doc;
// 所以查询结果中只有id，具体内容需要二次查询
// 根据id查询内容：放进去的是Document，查出来的还是Document
Document doc = searcher.Doc(docId);
SearchResult result = new SearchResult();
result.Id = Convert.ToInt32(doc.Get("id"));
result.Msg = HighlightHelper.HighLight(keyword, doc.Get("msg"));
resultList.Add(result);
}
// 绑定到Repeater
rptSearchResult.DataSource = resultList;
rptSearchResult.DataBind();
}
private void BindSearchResult(string keyword, int startIndex, int pageSize, out int totalCount)
{
string indexPath = Context.Server.MapPath("~/Index"); // 索引文档保存位置
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NoLockFactory());
IndexReader reader = IndexReader.Open(directory, true);
IndexSearcher searcher = new IndexSearcher(reader);
#region v1.0 单条件查询
//// 查询条件
//PhraseQuery query = new PhraseQuery();
//// 分词后加入查询
//IEnumerable<string> keyList = SplitHelper.SplitWords(keyword);
//foreach (var key in keyList)
//{
// query.Add(new Term("msg", key));
//}
//// 两个词的距离大于100（经验值）就不放入搜索结果，因为距离太远相关度就不高了
//query.SetSlop(100);
#endregion
#region v2.0 多条件查询
IEnumerable <string> keyList = SplitHelper.SplitWords(keyword);
PhraseQuery queryTitle = new PhraseQuery();
foreach (var key in keyList)
{
queryTitle.Add(new Term("title", key));
}
queryTitle.SetSlop(100);
PhraseQuery queryMsg = new PhraseQuery();
foreach (var key in keyList)
{
queryMsg.Add(new Term("msg", key));
}
queryMsg.SetSlop(100);
BooleanQuery query = new BooleanQuery();
query.Add(queryTitle, BooleanClause.Occur.SHOULD); // SHOULD => 可以有，但不是必须的
query.Add(queryTitle, BooleanClause.Occur.SHOULD); // SHOULD => 可以有，但不是必须的
#endregion
// TopScoreDocCollector:盛放查询结果的容器
TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
// 使用query这个查询条件进行搜索，搜索结果放入collector
searcher.Search(query, null, collector);
// 首先获取总条数
totalCount = collector.GetTotalHits();
// 从查询结果中取出第m条到第n条的数据
ScoreDoc[] docs = collector.TopDocs(startIndex, pageSize).scoreDocs;
// 遍历查询结果
IList <SearchResult> resultList = new List <SearchResult>();
for (int i = 0; i < docs.Length; i++)
{
// 拿到文档的id，因为Document可能非常占内存（DataSet和DataReader的区别）
int docId = docs[i].doc;
// 所以查询结果中只有id，具体内容需要二次查询
// 根据id查询内容：放进去的是Document，查出来的还是Document
Document doc = searcher.Doc(docId);
SearchResult result = new SearchResult();
result.Url = "ViewArticle.aspx?id=" + doc.Get("id");
result.Title = HighlightHelper.HighLight(keyword, doc.Get("title"));
result.Msg = HighlightHelper.HighLight(keyword, doc.Get("msg")) + "......";
resultList.Add(result);
}
// 绑定到Repeater
rptSearchResult.DataSource = resultList;
rptSearchResult.DataBind();
}