使用Lucene.NET实现站内搜索

导入lucene.net 开发包

lucene 是apache软件基金会一个开放源代码的全文检索引擎工具包，是一个全文检索引擎的架构，提供了完整的查询引擎和索引引擎，部分文本分析引擎。lucene的目的是为软件开发人员提供一个简单易用的工具包，以方便的在目标系统中实现全文检索的功能，或者是以此为基础建立起完整的全文检索引擎。lucene.net 是 .net 版的lucene。

你可以在这里到最新的lucene.net

创建索引、更新索引、删除索引

搜索，根据索引查找

indexhelper 添加、更新、删除索引

using system;
using lucene.net.store;
using lucene.net.index;
using lucene.net.analysis.pangu;
using lucene.net.documents;

namespace bll
{
  class indexhelper
  {
    /// <summary>
    /// 日志小助手
    /// </summary>
    static common.loghelper logger = new common.loghelper(typeof(searchbll));
    /// <summary>
    /// 索引保存的位置，保存在配置文件中从配置文件读取
    /// </summary>
    static string indexpath = common.configurationhelper.appsettingmappath("indexpath");
    
    /// <summary>
    /// 创建索引文件或更新索引文件
    /// </summary>
    /// <param name="item">索引信息</param>
    public static void createindex(model.helpermodel.indexfilehelper item)
    {
      try
      {
        //索引存储库
        fsdirectory directory = fsdirectory.open(new system.io.directoryinfo(indexpath), new nativefslockfactory());
        //判断索引是否存在
        bool isupdate = indexreader.indexexists(directory);
        if (isupdate)
        {
          //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
          if (indexwriter.islocked(directory))
          {
            //解锁索引库
            indexwriter.unlock(directory);
          }
        }
        //创建indexwriter对象，添加索引
        indexwriter writer = new indexwriter(directory, new panguanalyzer(), !isupdate, lucene.net.index.indexwriter.maxfieldlength.unlimited);
        //获取新闻 title部分
        string title = item.filetitle;
        //获取新闻主内容
        string body = item.filecontent;
        //为避免重复索引，所以先删除number=i的记录，再重新添加
        //尤其是更新的话，更是必须要先删除之前的索引
        writer.deletedocuments(new term("id", item.filename));
        //创建索引文件 document
        document document = new document();
        //只有对需要全文检索的字段才analyzed
        //添加id字段
        document.add(new field("id", item.filename, field.store.yes, field.index.not_analyzed));
        //添加title字段
        document.add(new field("title", title, field.store.yes, field.index.not_analyzed));
        //添加body字段
        document.add(new field("body", body, field.store.yes, field.index.analyzed, lucene.net.documents.field.termvector.with_positions_offsets));
        //添加url字段
        document.add(new field("url", item.filepath, field.store.yes, field.index.not_analyzed));
        //写入索引库
        writer.adddocument(document);
        //关闭资源
        writer.close();
        //不要忘了close，否则索引结果搜不到
        directory.close();
        //记录日志
        logger.debug(string.format("索引{0}创建成功",item.filename));
      }
      catch (systemexception ex)
      {
        //记录错误日志
        logger.error(ex);
        throw;
      }
      catch (exception ex)
      {
        //记录错误日志
        logger.error(ex);
        throw;
      }
    }

    /// <summary>
    /// 根据id删除相应索引
    /// </summary>
    /// <param name="guid">要删除的索引id</param>
    public static void deleteindex(string guid)
    {
      try
      {
        ////索引存储库
        fsdirectory directory = fsdirectory.open(new system.io.directoryinfo(indexpath), new nativefslockfactory());
        //判断索引库是否存在索引
        bool isupdate = indexreader.indexexists(directory);
        if (isupdate)
        {
          //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
          if (indexwriter.islocked(directory))
          {
            indexwriter.unlock(directory);
          }
        }
        indexwriter writer = new indexwriter(directory, new panguanalyzer(), !isupdate, lucene.net.index.indexwriter.maxfieldlength.unlimited);
        //删除索引文件
        writer.deletedocuments(new term("id", guid));
        writer.close();
        directory.close();//不要忘了close，否则索引结果搜不到
        logger.debug(string.format("删除索引{0}成功", guid));
      }
      catch (exception ex)
      {
        //记录日志
        logger.error(ex);
        //抛出异常
        throw;
      }
    }
  }
}

search 通过查找索引实现搜索

using lucene.net.analysis;
using lucene.net.analysis.pangu;
using lucene.net.documents;
using lucene.net.index;
using lucene.net.search;
using lucene.net.store;
using model.helpermodel;
using system;
using system.collections.generic;

namespace bll
{
  public static class searchbll
  {
    //一个类中可能会有多处输出到日志，多处需要记录日志，常将logger做成static 静态变量
    /// <summary>
    /// 日志助手
    /// </summary>
    static common.loghelper logger = new common.loghelper(typeof(searchbll));
    /// <summary>
    /// 索引保存位置
    /// </summary>
    static string indexpath = common.configurationhelper.appsettingmappath("indexpath");
    /// <summary>
    /// 搜索
    /// </summary>
    /// <param name="keywords">用户搜索的关键词</param>
    /// <returns>返回搜索的结果</returns>
    public static list<searchresult> search(string keywords)
    {
      try
      {
        //索引存储库
        fsdirectory directory = fsdirectory.open(new system.io.directoryinfo(indexpath), new nolockfactory());
        //创建indexreader对象
        indexreader reader = indexreader.open(directory, true);
        //创建indexsearcher对象
        indexsearcher searcher = new indexsearcher(reader);
        //新建phrasequery 查询对象
        phrasequery query = new phrasequery();
        //把用户输入的关键词进行拆词
        foreach (string word in splitword(keywords))
        {
          //添加搜索关键词
          query.add(new term("body", word));
        }
        //设置分词间距为100字之内
        query.setslop(100);
        topscoredoccollector collector = topscoredoccollector.create(1000, true);
        //根据查询条件查询结果
        searcher.search(query, null, collector);
        //搜索到的scoredoc结果
        scoredoc[] docs = collector.topdocs(0, collector.gettotalhits()).scoredocs;
        //保存搜索结果的list
        list<searchresult> listresult = new list<searchresult>();
        for (int i = 0; i < docs.length; i++)
        {
          //取到文档的编号（主键，这个是lucene .net分配的）
          //检索结果中只有文档的id，如果要取document，则需要doc再去取
          //降低内容占用
          int docid = docs[i].doc;
          //根据id找document
          document doc = searcher.doc(docid);
          string number = doc.get("id");
          string title = doc.get("title");
          string body = doc.get("body");
          string url = doc.get("url");
          //建立一个搜索结果对象
          searchresult result = new searchresult();
          result.number = number;
          result.title = title;
          result.bodypreview = preview(body, keywords);
          result.url = url;
          //添加到结果列表
          listresult.add(result);
        }
        if (listresult.count == 0)
        {
          return null;
        }
        else
        {
          return listresult;
        }
      }
      catch (systemexception ex)
      {
        logger.error(ex);
        return null;
      }
      catch (exception ex)
      {
        logger.error(ex);
        return null;
      }
    }

    /// <summary>
    /// 获取内容预览
    /// </summary>
    /// <param name="body">内容</param>
    /// <param name="keyword">关键词</param>
    /// <returns></returns>
    private static string preview(string body, string keyword)
    {
      //创建htmlformatter,参数为高亮单词的前后缀 
      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 pangu.segment());
      //设置每个摘要段的字符数 
      highlighter.fragmentsize = 100;
      //获取最匹配的摘要段 
      string bodypreview = highlighter.getbestfragment(keyword, body);
      return bodypreview;
    }

    /// <summary>
    /// 盘古分词，对用户输入的搜索关键词进行分词
    /// </summary>
    /// <param name="str">用户输入的关键词</param>
    /// <returns>分词之后的结果组成的数组</returns>
    private static string[] splitword(string str)
    {
      list<string> list = new list<string>();
      analyzer analyzer = new panguanalyzer();
      tokenstream tokenstream = analyzer.tokenstream("", new system.io.stringreader(str));
      lucene.net.analysis.token token = null;
      while ((token = tokenstream.next()) != null)
      {
        list.add(token.termtext());
      }
      return list.toarray();
    }
  }
}

searchresult 模型

namespace model.helpermodel
{
  public class searchresult
  {
    public string number { get; set; }

    public string title { get; set; }

    public string bodypreview { get; set; }

    public string url { get; set; }
  }
}

以上所述就是本文的全部内容了，希望大家能够喜欢。