Lucene.net应用
1、加入盘古分词方法
/// <summary> /// 对输入的搜索的条件进行分词 /// </summary> /// <param name="str"></param> /// <returns></returns> public static List<string> GetPanGuWord(string str) { Analyzer analyzer = new PanGuAnalyzer(); TokenStream tokenStream = analyzer.TokenStream("", new StringReader(str)); Lucene.Net.Analysis.Token token = null; List<string> list = new List<string>(); while ((token = tokenStream.Next()) != null) { list.Add(token.TermText()); } return list; }
2、创建视图显示的MODEL(ViewModel)
using System; using System.Collections.Generic; using System.Linq; using System.Web; namespace CZBK.ItcastOA.WebApp.Models { public class ViewSarchContentModel { public string Id { get; set; } public string Title { get; set; } public string Content { get; set; } } }
3、根据数据库表中字段创建索引
/// <summary> /// 负责向写数据 /// </summary> private void CreateSearchIndex() { string indexPath = @"C:\lucenedir";//注意和磁盘上文件夹的大小写一致,否则会报错。将创建的分词内容放在该目录下。 FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NativeFSLockFactory());//指定索引文件(打开索引目录) FS指的是就是FileSystem bool isUpdate = IndexReader.IndexExists(directory);//IndexReader:对索引进行读取的类。该语句的作用:判断索引库文件夹是否存在以及索引特征文件是否存在。 if (isUpdate) { //同时只能有一段代码对索引库进行写操作。当使用IndexWriter打开directory时会自动对索引库文件上锁。 //如果索引目录被锁定(比如索引过程中程序异常退出),则首先解锁(提示一下:如果我现在正在写着已经加锁了,但是还没有写完,这时候又来一个请求,那么不就解锁了吗?这个问题后面会解决) if (IndexWriter.IsLocked(directory)) { IndexWriter.Unlock(directory); } } IndexWriter writer = new IndexWriter(directory, new PanGuAnalyzer(), !isUpdate, Lucene.Net.Index.IndexWriter.MaxFieldLength.UNLIMITED);//向索引库中写索引。这时在这里加锁。 List<Books>list= BookService.LoadEntities(c=>true).ToList(); foreach (Books bookModel in list) { writer.DeleteDocuments(new Term("Id",bookModel.Id.ToString())); Document document = new Document();//表示一篇文档。 //Field.Store.YES:表示是否存储原值。只有当Field.Store.YES在后面才能用doc.Get("number")取出值来.Field.Index. NOT_ANALYZED:不进行分词保存 document.Add(new Field("Id",bookModel.Id.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED)); //Field.Index. ANALYZED:进行分词保存:也就是要进行全文的字段要设置分词 保存(因为要进行模糊查询) //Lucene.Net.Documents.Field.TermVector.WITH_POSITIONS_OFFSETS:不仅保存分词还保存分词的距离。 document.Add(new Field("Title", bookModel.Title, Field.Store.YES, Field.Index.ANALYZED, Lucene.Net.Documents.Field.TermVector.WITH_POSITIONS_OFFSETS)); document.Add(new Field("Content", bookModel.ContentDescription, Field.Store.YES, Field.Index.ANALYZED, Lucene.Net.Documents.Field.TermVector.WITH_POSITIONS_OFFSETS)); writer.AddDocument(document); } writer.Close();//会自动解锁。 directory.Close();//不要忘了Close,否则索引结果搜不到 }
4、搜索
private List<ViewSarchContentModel> SearchBookContent() { string indexPath = @"C:\lucenedir"; List<string> kw =Common.WebCommon.GetPanGuWord(Request["txtContent"]); FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NoLockFactory()); IndexReader reader = IndexReader.Open(directory, true); IndexSearcher searcher = new IndexSearcher(reader); //搜索条件 PhraseQuery query = new PhraseQuery(); foreach (string word in kw)//先用空格,让用户去分词,空格分隔的就是词“计算机 专业” { query.Add(new Term("Content", word)); } //query.Add(new Term("body","语言"));--可以添加查询条件,两者是add关系.顺序没有关系. //query.Add(new Term("body", "大学生")); //query.Add(new Term("body", kw));//body中含有kw的文章 query.SetSlop(100);//多个查询条件的词之间的最大距离.在文章中相隔太远 也就无意义.(例如 “大学生”这个查询条件和"简历"这个查询条件之间如果间隔的词太多也就没有意义了。) //TopScoreDocCollector是盛放查询结果的容器 TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true); searcher.Search(query, null, collector);//根据query查询条件进行查询,查询结果放入collector容器 ScoreDoc[] docs = collector.TopDocs(0, collector.GetTotalHits()).scoreDocs;//得到所有查询结果中的文档,GetTotalHits():表示总条数 TopDocs(300, 20);//表示得到300(从300开始),到320(结束)的文档内容. //可以用来实现分页功能 List<ViewSarchContentModel> list = new List<ViewSarchContentModel>(); for (int i = 0; i < docs.Length; i++) { ViewSarchContentModel viewModel = new ViewSarchContentModel(); // //搜索ScoreDoc[]只能获得文档的id,这样不会把查询结果的Document一次性加载到内存中。降低了内存压力,需要获得文档的详细内容的时候通过searcher.Doc来根据文档id来获得文档的详细内容对象Document. int docId = docs[i].doc;//得到查询结果文档的id(Lucene内部分配的id) Document doc = searcher.Doc(docId);//找到文档id对应的文档详细信息 viewModel.Id = doc.Get("Id"); viewModel.Title = doc.Get("Title"); viewModel.Content =Common.WebCommon.CreateHightLight(Request["txtContent"], doc.Get("Content"));//搜索内容关键字高亮显示 list.Add(viewModel); } return list; }
5、返回给VIEW
public ActionResult SearchContent() { if (!string.IsNullOrEmpty(Request["btnSearch"])) { List<ViewSarchContentModel>list= SearchBookContent(); ViewData["searchList"] = list; ViewData["searchWhere"] = Request["txtContent"]; return View("Index"); } else { CreateSearchIndex(); } return Content("ok"); }
6、视图表现
@{ Layout = null; } @using CZBK.ItcastOA.WebApp.Models <!DOCTYPE html> <html> <head> <meta name="viewport" content="width=device-width" /> <title>文档搜索</title> <script src="~/Scripts/jquery-1.7.1.min.js"></script> <style type="text/css"> .search-text2{ display:block; width:528px; height:26px; line-height:26px; float:left; margin:3px 5px; border:1px solid; font-family:'Microsoft Yahei'; font-size:14px;} .search-btn2{width:102px; height:32px; line-height:32px; cursor:pointer; border:0px; background-color:#d6000f;font-family:'Microsoft Yahei'; font-size:16px;color:#f3f3f3;} .search-list{width:600px; overflow:hidden; margin:10px 20px 0px 20px;} .search-list dt{font-family:'Microsoft Yahei'; font-size:16px; line-height:20px; margin-bottom:7px; font-weight:normal;} .search-list .search-detail{font-size:12px; color:#666666;margin-bottom:5px; font-family:Arial;line-height:16px;} .search-list dt a{color:#2981a9;} </style> </head> <body> <!-- JiaThis Button BEGIN --> <script type="text/javascript" > var jiathis_config = { data_track_clickback: true, showClose: true, hideMore: false } </script> <script type="text/javascript" src="http://v3.jiathis.com/code/jiathis_r.js?uid=1986459&type=left&btn=l.gif&move=0" charset="utf-8"></script> <!-- JiaThis Button END --> <div> <form method="get" action="/Search/SearchContent"> <input type="text" value="@ViewData["searchWhere"]" name="txtContent" autocomplete="off" class="search-text2"/> <input type="submit" value="搜一搜" name="btnSearch" class="search-btn2" /> <input type="submit" value="创建索引库" name="btnCreate" /> </form> <dl class="search-list"> @if (ViewData["searchList"] != null) { foreach (ViewSarchContentModel viewModel in (List<ViewSarchContentModel>)ViewData["searchList"]) { <dt><a href="/Book/ShowDetail/?id=@viewModel.Id"> @viewModel.Title</a></dt> <dd class="search-detail">@MvcHtmlString.Create(viewModel.Content)</dd> } } </dl> </div> </body> </html>
改变输入框、按钮样式,高亮显示
<style type="text/css"> .search-text2{ display:block; width:528px; height:26px; line-height:26px; float:left; margin:3px 5px; border:1px solid; font-family:'Microsoft Yahei'; font-size:14px;} .search-btn2{width:102px; height:32px; line-height:32px; cursor:pointer; border:0px; background-color:#d6000f;font-family:'Microsoft Yahei'; font-size:16px;color:#f3f3f3;} .search-list{width:600px; overflow:hidden; margin:10px 20px 0px 20px;} .search-list dt{font-family:'Microsoft Yahei'; font-size:16px; line-height:20px; margin-bottom:7px; font-weight:normal;} .search-list .search-detail{font-size:12px; color:#666666;margin-bottom:5px; font-family:Arial;line-height:16px;} .search-list dt a{color:#2981a9;} </style>
盘古分词的高亮组件PanGu.HighLight.dll,引用高亮显示组件
// /创建HTMLFormatter,参数为高亮单词的前后缀 public static string CreateHightLight(string keywords, string Content) { PanGu.HighLight.SimpleHTMLFormatter simpleHTMLFormatter = new PanGu.HighLight.SimpleHTMLFormatter("<font color=\"red\">", "</font>"); //创建Highlighter ,输入HTMLFormatter 和盘古分词对象Semgent PanGu.HighLight.Highlighter highlighter = new PanGu.HighLight.Highlighter(simpleHTMLFormatter, new Segment()); //设置每个摘要段的字符数 highlighter.FragmentSize = 150; //获取最匹配的摘要段 return highlighter.GetBestFragment(keywords, Content); }
keywords搜索关键词,Content搜索结果
viewModel.Content =Common.WebCommon.CreateHightLight(Request["txtContent"], doc.Get("Content"));//搜索内容关键字高亮显示
视图中
<dd class="search-detail">@MvcHtmlString.Create(viewModel.Content)</dd>
@输出进行了编码,用@会输出HTML标签
Lucene每次生成索引不会删除、覆盖以前生成的,会造成搜索时搜索到重复的记录,所以生成前先要删除一次(实质没有删除文件,只是给文件个删除标记)
writer.DeleteDocuments(new Term("Id",bookModel.Id.ToString()));
搜索页面采用<form method="get" .............>,并采用静态页面:有利于网站推广
分享到
加<script src="~/Scripts/jquery-1.7.1.min.js"></script>
并将以下代码放入body
<!-- JiaThis Button BEGIN -->
<script type="text/javascript" >
var jiathis_config = {
data_track_clickback: true,
showClose: true,
hideMore: false
}
</script>
<script type="text/javascript" src="http://v3.jiathis.com/code/jiathis_r.js?uid=1986459&type=left&btn=l.gif&move=0" charset="utf-8"></script>
<!-- JiaThis Button END -->