using System.Collections;
using System.IO;using Lucene.Net.Analysis;namespace NSharp.SearchEngine.Lucene.Analysis.Cjk
{/**//*** Filters CJKTokenizer with StopFilter.** @author Che, Dong*/public class CJKAnalyzer : Analyzer{//~ Static fields/initializers ---------------------------------------------/**//*** An array containing some common English words that are not usually* useful for searching and some double-byte interpunctions.*/public static string[] STOP_WORDS = {"a", "and", "are", "as", "at", "be","but", "by", "for", "if", "in","into", "is", "it", "no", "not","of", "on", "or", "s", "such", "t","that", "the", "their", "then","there", "these", "they", "this","to", "was", "will", "with", "","www"};//~ Instance fields --------------------------------------------------------/**//*** stop word list*/private Hashtable stopTable;//~ Constructors -----------------------------------------------------------/**//*** Builds an analyzer which removes words in {@link #STOP_WORDS}.*/public CJKAnalyzer(){stopTable = StopFilter.MakeStopSet(STOP_WORDS);}/**//*** Builds an analyzer which removes words in the provided array.** @param stopWords stop word array*/public CJKAnalyzer(string[] stopWords){stopTable = StopFilter.MakeStopSet(stopWords);}//~ Methods ----------------------------------------------------------------/**//*** get token stream from input** @param fieldName lucene field name* @param reader    input reader* @return TokenStream*/public override TokenStream TokenStream(string fieldName, TextReader reader){TokenStream ts = new CJKTokenizer(reader);return new StopFilter(ts, stopTable);//return new StopFilter(new CJKTokenizer(reader), stopTable);
        }}
}

using CZBK.ItcastOA.Model;
using CZBK.ItcastOA.WebApp.Models;
using Lucene.Net.Analysis.PanGu;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.Search;
using Lucene.Net.Store;
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Web;
using System.Web.Mvc;namespace CZBK.ItcastOA.WebApp.Controllers
{public class SearchController : Controller{//// GET: /Search/IBLL.IBooksService BooksService { get; set; }public ActionResult Index(){return View();}/// <summary>/// 表单中有多个Submit，单击每个Submit都会提交表单，但是只会将用户所单击的表单元素的value值提交到服务端。/// </summary>/// <returns></returns>public ActionResult SearchContent(){//如果等于查询if (!string.IsNullOrEmpty(Request["btnSearch"])){List<ViewModelContent>list=ShowSearchContent();ViewData["list"] = list;//视图重载，表示返回到index对应的视图return View("Index");}//添加词库，但是此处的添加功能不再使用，因为被封装了else{CreateSerachContent();}return Content("ok");}/// <summary>/// 实现搜索功能，/// </summary>/// <returns></returns>private List<ViewModelContent> ShowSearchContent(){string indexPath = @"C:\lucenedir";//下面出需要把盘古分词类放置在common文件夹中，并且引用List<string> list =Common.WebCommon.PanGuSplitWord(Request["txtSearch"]);//使用盘古分词对用户输入的搜索条件进行拆分，并且接受用户的输入信息。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();//因为前面的只是查询一个词，所以不需要for循环foreach (string word in list)//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，此处需要在model中定义ViewModelContent类List<ViewModelContent> viewModelList = new List<ViewModelContent>();for (int i = 0; i < docs.Length; i++){////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.ViewModelContent viewModel = new ViewModelContent();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=Convert.ToInt32(doc.Get("Id"));// 取出放进字段的值viewModel.Title=doc.Get("Title");viewModel.Content =Common.WebCommon.CreateHightLight(Request["txtSearch"],doc.Get("Content"));//将搜索的关键字高亮显示。
                viewModelList.Add(viewModel);}return viewModelList;}/// <summary>/// 实现插入功能，该功能被封装在indexManager中，下面的注释，并且不使用/// </summary>private void CreateSerachContent(){//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。//将路径写到配置文件中。//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=BooksService.LoadEntities(b=>true).ToList();//foreach (var bookModel in list)//{//    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C
        }}
}

using CZBK.ItcastOA.Model.EnumType;
using Lucene.Net.Analysis.PanGu;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.Store;
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading;
using System.Web;namespace Models
{public sealed class IndexManager{//创建单例模式，首先第一步，定义一个静态示例的IndexManager类private static readonly IndexManager indexManager = new IndexManager();/// <summary>/// 第二步，提供一个私有的构造方法，指不能被继承， 只能在本类中使用/// </summary>private IndexManager(){}//第三部，该方法是公开的，因为需要在类的外面调用类的实例public static IndexManager GetInstance(){return indexManager;}public Queue<ViewModelContent> queue = new Queue<ViewModelContent>();/// <summary>/// 向队列中添加数据/// </summary>/// <param name="id"></param>/// <param name="title"></param>/// <param name="content"></param>public void AddQueue(int id, string title, string content){ViewModelContent viewModel = new ViewModelContent();viewModel.Id = id;viewModel.Title = title;viewModel.Content = content;viewModel.LuceneTypeEnum = LuceneTypeEnum.Add; queue.Enqueue(viewModel);}/// <summary>/// 要删除的数据/// </summary>/// <param name="id"></param>public void DeleteQueue(int id){ViewModelContent viewModel = new ViewModelContent();viewModel.Id = id;viewModel.LuceneTypeEnum = LuceneTypeEnum.Delete;queue.Enqueue(viewModel);}/// <summary>/// 开始一个线程/// </summary>public void StartThread(){Thread thread = new Thread(WriteIndexContent);thread.IsBackground = true;thread.Start();}/// <summary>/// 检查队列中是否有数据，如果有数据获取。/// </summary>private void WriteIndexContent(){while (true){if (queue.Count > 0){CreateIndexContent();}else{Thread.Sleep(3000);}}}private void CreateIndexContent(){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。//将路径写到配置文件中。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FileSystembool 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。//如果队列中有数据，获取队列中的数据写到Lucene.Net中。while(queue.Count>0){ViewModelContent viewModel=queue.Dequeue();writer.DeleteDocuments(new Term("Id",viewModel.Id.ToString()));//删除if (viewModel.LuceneTypeEnum == LuceneTypeEnum.Delete){continue;}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", viewModel.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", viewModel.Title, Field.Store.YES, Field.Index.ANALYZED, Lucene.Net.Documents.Field.TermVector.WITH_POSITIONS_OFFSETS));document.Add(new Field("Content", viewModel.Content, 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C
        }}
}