lucene.net helper类 【结合盘古分词进行搜索的小例子(分页功能)】
转自:http://blog.csdn.net/pukuimin1226/article/details/17558247
添加:2013-12-25
更新:2013-12-26 新增分页功能。
更新:2013-12-27 新增按分类查询功能,调整索引行新增记录的图片字段。
最新盘古分词dll和词典管理工具下载:http://pangusegment.codeplex.com/
词典下载:http://pangusegment.codeplex.com/releases/view/47411
Lucene.net下载:http://lucenenet.apache.org/download.cgi
//封装类
- using System;
- using System.Collections.Generic;
- using System.Linq;
- using System.Web;
- using Lucene.Net.Analysis;
- using Lucene.Net.Index;
- using Lucene.Net.Documents;
- using System.Reflection;
- using Lucene.Net.QueryParsers;
- using Lucene.Net.Search;
- namespace SearchTest
- {
- /// <summary>
- /// 盘古分词在lucene.net中的使用帮助类
- /// 调用PanGuLuceneHelper.instance
- /// </summary>
- public class PanGuLuceneHelper
- {
- private PanGuLuceneHelper() { }
- #region 单一实例
- private static PanGuLuceneHelper _instance = null;
- /// <summary>
- /// 单一实例
- /// </summary>
- public static PanGuLuceneHelper instance
- {
- get
- {
- if (_instance == null) _instance = new PanGuLuceneHelper();
- return _instance;
- }
- }
- #endregion
- #region 分词测试
- /// <summary>
- /// 分词测试
- /// </summary>
- /// <param name="keyword"></param>
- /// <returns></returns>
- public string Token(string keyword)
- {
- string ret = "";
- System.IO.StringReader reader = new System.IO.StringReader(keyword);
- Lucene.Net.Analysis.TokenStream ts = analyzer.TokenStream(keyword, reader);
- bool hasNext = ts.IncrementToken();
- Lucene.Net.Analysis.Tokenattributes.ITermAttribute ita;
- while (hasNext)
- {
- ita = ts.GetAttribute<Lucene.Net.Analysis.Tokenattributes.ITermAttribute>();
- ret += ita.Term + "|";
- hasNext = ts.IncrementToken();
- }
- ts.CloneAttributes();
- reader.Close();
- analyzer.Close();
- return ret;
- }
- #endregion
- #region 创建索引
- /// <summary>
- /// 创建索引
- /// </summary>
- /// <param name="datalist"></param>
- /// <returns></returns>
- public bool CreateIndex(List<MySearchUnit> datalist)
- {
- IndexWriter writer = null;
- try
- {
- writer = new IndexWriter(directory_luce, analyzer, false, IndexWriter.MaxFieldLength.LIMITED);//false表示追加(true表示删除之前的重新写入)
- }
- catch
- {
- writer = new IndexWriter(directory_luce, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);//false表示追加(true表示删除之前的重新写入)
- }
- foreach (MySearchUnit data in datalist)
- {
- CreateIndex(writer, data);
- }
- writer.Optimize();
- writer.Dispose();
- return true;
- }
- public bool CreateIndex(IndexWriter writer, MySearchUnit data)
- {
- try
- {
- if (data == null) return false;
- Document doc = new Document();
- Type type = data.GetType();//assembly.GetType("Reflect_test.PurchaseOrderHeadManageModel", true, true); //命名空间名称 + 类名
- //创建类的实例
- //object obj = Activator.CreateInstance(type, true);
- //获取公共属性
- PropertyInfo[] Propertys = type.GetProperties();
- for (int i = 0; i < Propertys.Length; i++)
- {
- //Propertys[i].SetValue(Propertys[i], i, null); //设置值
- PropertyInfo pi = Propertys[i];
- string name=pi.Name;
- object objval = pi.GetValue(data, null);
- string value = objval == null ? "" : objval.ToString(); //值
- if (name == "id" || name=="flag" )//id在写入索引时必是不分词,否则是模糊搜索和删除,会出现混乱
- {
- doc.Add(new Field(name, value, Field.Store.YES, Field.Index.NOT_ANALYZED));//id不分词
- }
- else
- {
- doc.Add(new Field(name, value, Field.Store.YES, Field.Index.ANALYZED));
- }
- }
- writer.AddDocument(doc);
- }
- catch (System.IO.FileNotFoundException fnfe)
- {
- throw fnfe;
- }
- return true;
- }
- #endregion
- #region 在title和content字段中查询数据
- /// <summary>
- /// 在title和content字段中查询数据
- /// </summary>
- /// <param name="keyword"></param>
- /// <returns></returns>
- public List<MySearchUnit> Search(string keyword)
- {
- string[] fileds = { "title", "content" };//查询字段
- //Stopwatch st = new Stopwatch();
- //st.Start();
- QueryParser parser = null;// new QueryParser(Lucene.Net.Util.Version.LUCENE_30, field, analyzer);//一个字段查询
- parser = new MultiFieldQueryParser(version, fileds, analyzer);//多个字段查询
- Query query = parser.Parse(keyword);
- int n = 1000;
- IndexSearcher searcher = new IndexSearcher(directory_luce, true);//true-表示只读
- TopDocs docs = searcher.Search(query, (Filter)null, n);
- if (docs == null || docs.TotalHits == 0)
- {
- return null;
- }
- else
- {
- List<MySearchUnit> list = new List<MySearchUnit>();
- int counter = 1;
- foreach (ScoreDoc sd in docs.ScoreDocs)//遍历搜索到的结果
- {
- try
- {
- Document doc = searcher.Doc(sd.Doc);
- string id = doc.Get("id");
- string title = doc.Get("title");
- string content = doc.Get("content");
- string flag = doc.Get("flag");
- string imageurl = doc.Get("imageurl");
- string updatetime = doc.Get("updatetime");
- string createdate = doc.Get("createdate");
- PanGu.HighLight.SimpleHTMLFormatter simpleHTMLFormatter = new PanGu.HighLight.SimpleHTMLFormatter("<font color=\"red\">", "</font>");
- PanGu.HighLight.Highlighter highlighter = new PanGu.HighLight.Highlighter(simpleHTMLFormatter, new PanGu.Segment());
- highlighter.FragmentSize = 50;
- content = highlighter.GetBestFragment(keyword, content);
- string titlehighlight = highlighter.GetBestFragment(keyword, title);
- if (titlehighlight != "") title = titlehighlight;
- list.Add(new MySearchUnit(id, title, content, flag,imageurl, updatetime));
- }
- catch (Exception ex)
- {
- Console.WriteLine(ex.Message);
- }
- counter++;
- }
- return list;
- }
- //st.Stop();
- //Response.Write("查询时间:" + st.ElapsedMilliseconds + " 毫秒<br/>");
- }
- #endregion
- #region 在不同的分类下再根据title和content字段中查询数据(分页)
- /// <summary>
- /// 在不同的类型下再根据title和content字段中查询数据(分页)
- /// </summary>
- /// <param name="_flag">分类,传空值查询全部</param>
- /// <param name="keyword"></param>
- /// <param name="PageIndex"></param>
- /// <param name="PageSize"></param>
- /// <param name="TotalCount"></param>
- /// <returns></returns>
- public List<MySearchUnit> Search(string _flag,string keyword, int PageIndex, int PageSize, out int TotalCount)
- {
- if (PageIndex < 1) PageIndex = 1;
- //Stopwatch st = new Stopwatch();
- //st.Start();
- BooleanQuery bq = new BooleanQuery();
- if (_flag != "")
- {
- QueryParser qpflag = new QueryParser(version, "flag", analyzer);
- Query qflag = qpflag.Parse(_flag);
- bq.Add(qflag, Occur.MUST);//与运算
- }
- if (keyword != "")
- {
- string[] fileds = { "title", "content" };//查询字段
- QueryParser parser = null;// new QueryParser(version, field, analyzer);//一个字段查询
- parser = new MultiFieldQueryParser(version, fileds, analyzer);//多个字段查询
- Query queryKeyword = parser.Parse(keyword);
- bq.Add(queryKeyword, Occur.MUST);//与运算
- }
- TopScoreDocCollector collector = TopScoreDocCollector.Create(PageIndex * PageSize, false);
- IndexSearcher searcher = new IndexSearcher(directory_luce, true);//true-表示只读
- searcher.Search(bq, collector);
- if (collector == null || collector.TotalHits == 0)
- {
- TotalCount = 0;
- return null;
- }
- else
- {
- int start = PageSize * (PageIndex - 1);
- //结束数
- int limit = PageSize;
- ScoreDoc[] hits = collector.TopDocs(start, limit).ScoreDocs;
- List<MySearchUnit> list = new List<MySearchUnit>();
- int counter = 1;
- TotalCount = collector.TotalHits;
- foreach (ScoreDoc sd in hits)//遍历搜索到的结果
- {
- try
- {
- Document doc = searcher.Doc(sd.Doc);
- string id = doc.Get("id");
- string title = doc.Get("title");
- string content = doc.Get("content");
- string flag = doc.Get("flag");
- string imageurl = doc.Get("imageurl");
- string updatetime = doc.Get("updatetime");
- PanGu.HighLight.SimpleHTMLFormatter simpleHTMLFormatter = new PanGu.HighLight.SimpleHTMLFormatter("<font color=\"red\">", "</font>");
- PanGu.HighLight.Highlighter highlighter = new PanGu.HighLight.Highlighter(simpleHTMLFormatter, new PanGu.Segment());
- highlighter.FragmentSize = 50;
- content = highlighter.GetBestFragment(keyword, content);
- string titlehighlight = highlighter.GetBestFragment(keyword, title);
- if (titlehighlight != "") title = titlehighlight;
- list.Add(new MySearchUnit(id, title, content, flag,imageurl, updatetime));
- }
- catch (Exception ex)
- {
- Console.WriteLine(ex.Message);
- }
- counter++;
- }
- return list;
- }
- //st.Stop();
- //Response.Write("查询时间:" + st.ElapsedMilliseconds + " 毫秒<br/>");
- }
- #endregion
- #region 删除索引数据(根据id)
- /// <summary>
- /// 删除索引数据(根据id)
- /// </summary>
- /// <param name="id"></param>
- /// <returns></returns>
- public bool Delete(string id)
- {
- bool IsSuccess = false;
- Term term = new Term("id", id);
- //Analyzer analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);
- //Version version = new Version();
- //MultiFieldQueryParser parser = new MultiFieldQueryParser(version, new string[] { "name", "job" }, analyzer);//多个字段查询
- //Query query = parser.Parse("小王");
- //IndexReader reader = IndexReader.Open(directory_luce, false);
- //reader.DeleteDocuments(term);
- //Response.Write("删除记录结果: " + reader.HasDeletions + "<br/>");
- //reader.Dispose();
- IndexWriter writer = new IndexWriter(directory_luce, analyzer, false, IndexWriter.MaxFieldLength.LIMITED);
- writer.DeleteDocuments(term); // writer.DeleteDocuments(term)或者writer.DeleteDocuments(query);
- ////writer.DeleteAll();
- writer.Commit();
- //writer.Optimize();//
- IsSuccess = writer.HasDeletions();
- writer.Dispose();
- return IsSuccess;
- }
- #endregion
- #region 删除全部索引数据
- /// <summary>
- /// 删除全部索引数据
- /// </summary>
- /// <returns></returns>
- public bool DeleteAll()
- {
- bool IsSuccess = true;
- try
- {
- IndexWriter writer = new IndexWriter(directory_luce, analyzer, false, IndexWriter.MaxFieldLength.LIMITED);
- writer.DeleteAll();
- writer.Commit();
- //writer.Optimize();//
- IsSuccess = writer.HasDeletions();
- writer.Dispose();
- }
- catch
- {
- IsSuccess = false;
- }
- return IsSuccess;
- }
- #endregion
- #region directory_luce
- private Lucene.Net.Store.Directory _directory_luce = null;
- /// <summary>
- /// Lucene.Net的目录-参数
- /// </summary>
- public Lucene.Net.Store.Directory directory_luce
- {
- get
- {
- if (_directory_luce == null) _directory_luce = Lucene.Net.Store.FSDirectory.Open(directory);
- return _directory_luce;
- }
- }
- #endregion
- #region directory
- private System.IO.DirectoryInfo _directory = null;
- /// <summary>
- /// 索引在硬盘上的目录
- /// </summary>
- public System.IO.DirectoryInfo directory
- {
- get
- {
- if (_directory == null)
- {
- string dirPath = AppDomain.CurrentDomain.BaseDirectory + "SearchIndex";
- if (System.IO.Directory.Exists(dirPath) == false) _directory = System.IO.Directory.CreateDirectory(dirPath);
- else _directory = new System.IO.DirectoryInfo(dirPath);
- }
- return _directory;
- }
- }
- #endregion
- #region analyzer
- private Analyzer _analyzer = null;
- /// <summary>
- /// 分析器
- /// </summary>
- public Analyzer analyzer
- {
- get
- {
- //if (_analyzer == null)
- {
- _analyzer = new Lucene.Net.Analysis.PanGu.PanGuAnalyzer();//盘古分词分析器
- //_analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);//标准分析器
- }
- return _analyzer;
- }
- }
- #endregion
- #region version
- private static Lucene.Net.Util.Version _version = Lucene.Net.Util.Version.LUCENE_30;
- /// <summary>
- /// 版本号枚举类
- /// </summary>
- public Lucene.Net.Util.Version version
- {
- get
- {
- return _version;
- }
- }
- #endregion
- }
- #region 索引的一个行单元,相当于数据库中的一行数据
- /// <summary>
- /// 索引的一个行单元,相当于数据库中的一行数据
- /// </summary>
- public class MySearchUnit
- {
- public MySearchUnit(string _id, string _title, string _content, string _flag, string _imageurl, string _updatetime)
- {
- this.id = _id;
- this.title = _title;
- this.content = _content;
- this.flag = _flag;
- this.imageurl = _imageurl;
- this.updatetime = _updatetime;
- }
- /// <summary>
- /// 唯一的id号
- /// </summary>
- public string id { get; set; }
- /// <summary>
- /// 标题
- /// </summary>
- public string title { get; set; }
- /// <summary>
- /// 内容
- /// </summary>
- public string content { get; set; }
- /// <summary>
- /// 其他信息
- /// </summary>
- public string flag { get; set; }
- /// <summary>
- /// 图片路径
- /// </summary>
- public string imageurl { get; set; }
- /// <summary>
- /// 时间
- /// </summary>
- public string updatetime { get; set; }
- }
- #endregion
- }
//调用测试
- protected void Page_Load(object sender, EventArgs e)
- {
- //PanGuLuceneHelper.instance.DeleteAll();//删除全部
- //PanGuLuceneHelper.instance.Delete("1d");//根据id删除
- bool exec = false;
- if (exec)
- {
- List<MySearchUnit> list = new List<MySearchUnit>();
- list.Add(new MySearchUnit("1a", "标题小王", "今天是小王的生日,大家都很高兴去他家喝酒,玩了一整天。", new Random().Next(1, 10).ToString(), "", ""));
- list.Add(new MySearchUnit("1b", "标题小张", "今天是小张的生日,大家都很高兴去他家喝酒,玩了几天。", new Random().Next(1, 10).ToString(), "", ""));
- list.Add(new MySearchUnit("1c", "标题小王", "今天是小王的生日,大家都很高兴去他家喝酒,玩了一整天。", new Random().Next(1, 10).ToString(), "", ""));
- list.Add(new MySearchUnit("1d", "标题小张", "今天是小张的生日,大家都很高兴去他家喝酒,玩了几天。", new Random().Next(1, 10).ToString(), "", ""));
- PanGuLuceneHelper.instance.CreateIndex(list);//添加索引
- }
- int count = 0;
- int PageIndex=2;
- int PageSize=4;
- string html_content = "";
- List<MySearchUnit> searchlist = PanGuLuceneHelper.instance.Search("3","小王 生日",PageIndex,PageSize,out count);
- html_content+=("查询结果:" + count + "条数据<br/>");
- if (searchlist == null || searchlist.Count==0)
- {
- html_content += ("未查询到数据。<br/>");
- }
- else
- {
- foreach (MySearchUnit data in searchlist)
- {
- html_content += (string.Format("id:{0},title:{1},content:{2},flag:{3},updatetime:{4}<br/>", data.id, data.title, data.content, data.flag, data.updatetime));
- }
- }
- html_content += (PanGuLuceneHelper.instance.version);
- div_content.InnerHtml = html_content;
- }
//效果:
第一版源码示例下载:http://download.csdn.net/detail/pukuimin1226/6768179
最新源码示例下载:http://download.csdn.net/detail/pukuimin1226/6776049
百度云盘下载链接:http://pan.baidu.com/s/1o69cCD8
Lucene.Net没有判断数据重复性,同一条数据插入多少遍它就有多少条相同的数据,所以,我们人为地用id区分,在数据量大,全部重新创建索引时间长的情况下(数据量到几万以上就耗资源了,从数据库中查询出来,再写入索引,使得数据库和程序本身都增加负担),增量建立索引是很有必要的。
新增一条数据,就直接添加一条索引;
修改一条数据,先删除同一个id的索引(不管有多少个id相同的,都会一次性删除),再添加一条。
数据库中的id建议大家都用guid去掉“-”,还可以加日期“yyyyMMddHHmmss”这样组合,长度一致看起来美观,也充分保证唯一。
lucene.net helper类 【结合盘古分词进行搜索的小例子(分页功能)】的更多相关文章
- lucene.net 3.0.3、结合盘古分词进行搜索的小例子(转)
lucene.net 3.0.3.结合盘古分词进行搜索的小例子(分页功能) 添加:2013-12-25 更新:2013-12-26 新增分页功能. 更新:2013-12-27 新增按分类查询功能, ...
- lucene.net 3.0.3、结合盘古分词进行搜索的小例子(分页功能)
转自:http://blog.csdn.net/pukuimin1226/article/details/17558247 添加:2013-12-25 更新:2013-12-26 新增分页功能. 更新 ...
- 使用Lucene.net+盘古分词实现搜索查询
这里我的的Demo的逻辑是这样的:首先我基本的数据是储存在Sql数据库中,然后我把我的必需的数据推送到MongoDB中,这样再去利用Lucene.net+盘古创建索引:其中为什么要这样把数据推送到Mo ...
- Lucene.Net+盘古分词->开发自己的搜索引擎
//封装类 using System;using System.Collections.Generic;using System.Linq;using System.Web;using Lucene. ...
- Lucene.net入门学习(结合盘古分词)
Lucene简介 Lucene是apache软件基金会4 jakarta项目组的一个子项目,是一个开放源代码的全文检索引擎工具包,即它不是一个完整的全文检索引擎,而是一个全文检索引擎的架构,提供了完整 ...
- Lucene.net入门学习(结合盘古分词)(转载)
作者:释迦苦僧 出处:http://www.cnblogs.com/woxpp/p/3972233.html 本文版权归作者和博客园共有,欢迎转载,但未经作者同意必须保留此段声明,且在文章页面明显 ...
- 【原创】Lucene.Net+盘古分词器(详细介绍)
本章阅读概要 1.Lucenne.Net简介 2.介绍盘古分词器 3.Lucene.Net实例分析 4.结束语(Demo下载) Lucene.Net简介 Lucene.net是Lucene的.net移 ...
- 站内搜索——Lucene +盘古分词
为了方便的学习站内搜索,下面我来演示一个MVC项目. 1.首先在项目中[添加引入]三个程序集和[Dict]文件夹,并新建一个[分词内容存放目录] Lucene.Net.dll.PanGu.dll.Pa ...
- Lucene.Net+盘古分词器(详细介绍)(转)
出处:http://www.cnblogs.com/magicchaiy/archive/2013/06/07/LuceneNet%E7%9B%98%E5%8F%A4%E5%88%86%E8%AF%8 ...
随机推荐
- Java 父类和子类
package chapter11; public class GeometricObject1 { private String color="white"; private b ...
- 推荐!Sublime Text 最佳插件列表
本文由 伯乐在线 - 艾凌风 翻译,黄利民 校稿.英文出处:ipestov.com.欢迎加入翻译组. 本文收录了作者辛苦收集的Sublime Text最佳插件,很全. 最佳的Sublime Text ...
- python---解决“Unable to find vcvarsall.bat”错误
安装某些module时发生常见的 Unable to find vcvarsall.bat 错误 在eddsn找到了“Unable to find vcvarsall.bat” error when ...
- 一次性编译所有T-Code
SGEN, 然后选择Generate all,或regenerate ...... 转的,My question: 这个不太懂能干什么
- html5的程序接口与元素变化
除了原先的DOM接口,HTML5增加了更多API,如:1. 用于即时2D绘图的Canvas标签2. 定时媒体回放3. 离线数据库存储4.文档编辑5. 拖拽控制6. 浏览历史管理元素变化新的解析顺序新的 ...
- lightoj1074 最短路
题意:有n个城市,每个城市有拥挤值,有一些单向道路,从某个城市到另一个城市的花费是拥挤值差的三次方,当然可能是负的值.问从1点到某点最少的花费,若小于3或不能到达输出“?” 建图的边权是拥挤值差的三次 ...
- 【BZOJ1008】【HNOI2008】越狱
以前水过的水题 原题: 监狱有连续编号为1...N的N个房间,每个房间关押一个犯人,有M种宗教,每个犯人可能信仰其中一种.如果相邻房间的犯人的宗教相同,就可能发生越狱,求有多少种状态可能发生越狱 1& ...
- C语言指针与数组的定义与声明易错分析
部分摘自<C语言深度解剖> 1.定义为数组,声明为指针 在文件1中定义: char a[100]; 在文件2中声明: extern char *a; //这样是错误的 这里的extern告 ...
- Linux驱动设计——内存与IO访问
名词解释 内存空间与IO空间 内存空间是计算机系统里面非系统内存区域的地址空间,现在的通用X86体系提供32位地址,寻址4G字节的内存空间,但一般的计算机只安装256M字节或者更少的内存,剩下的高位内 ...
- Android sdk 镜像服务器资源
大连东软信息学院镜像服务器地址:- http://mirrors.neusoft.edu.cn 端口:80北京化工大学镜像服务器地址:- IPv4: http://ubuntu.buct.edu.cn ...