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.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
}
原文地址:http://blog.csdn.net/pukuimin1226/article/details/17558247
Lucene.Net+盘古分词->开发自己的搜索引擎的更多相关文章
- 【盘古分词】Lucene.Net 盘古分词 实现公众号智能自动回复
盘古分词是一个基于 .net framework 的中英文分词组件.主要功能 中文未登录词识别 盘古分词可以对一些不在字典中的未登录词自动识别 词频优先 盘古分词可以根据词频来解决分词的歧义问题 多元 ...
- 【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 ...
- 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 ...
- 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移植版本,是 ...
- Lucene.Net+盘古分词
前言 各位朋友,谢谢大家的支持,由于文件过大,有考虑到版权的问题,故没有提供下载,本人已建立一个搜索技术交流群:77570783,源代码已上传至群共享,需要的朋友,请自行下载! 首先自问自答几个问题, ...
- 完整的站内搜索Demo(Lucene.Net+盘古分词)
前言 首先自问自答几个问题,以让各位看官了解写此文的目的 什么是站内搜索?与一般搜索的区别? 很多网站都有搜索功能,很多都是用SQL语句的Like实现的,但是Like无法做到模糊匹配(例如我搜索“.n ...
- 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 ...
- 完整的站内搜索实战应用(Lucene.Net+盘古分词)
首先自问自答几个问题,以让各位看官了解写此文的目的 什么是站内搜索?与一般搜索的区别? 多网站都有搜索功能,很多都是用SQL语句的Like实现的,但是Like无法做到模糊匹配(例如我搜索". ...
- Lucene.net 全文检索 盘古分词
lucene.net + 盘古分词 引用: 1.Lucene.Net.dll 2.PanGu.Lucene.Analyzer.dll 3.PanGu.HighLight.dll 4.PanGu.dll ...
随机推荐
- C++强制类型转换操作符 const_cast
const_cast也是一个强制类型转换操作符.<C++ Primer>中是这样描述它的: 1.将转换掉表达式的const性质. 2.只有使用const_cast才能将const性质性质转 ...
- NGUI之输入文本框的使用
ToolBar中的两个红圈 另,代码如下:只需要定义一个变量即可,然后将控件drag到那里,真的是灰常方便呀 还有一个就是保存了(OK的响应),可以简单地理解为存档或读档
- Zabbix网络自动发现规则和自动添加hosts及link模板
Version: zabbix 3.0 一.配置网络发现规则 Device uniqueness criteria:选择主机名作为唯一标识(Configuation Hosts中显示的NAME) 二. ...
- 如何自己编写一个easyui插件续
接着如何自己编写一个easyui插件继续分享一下如何从上一节写的“hello”插件继承出一个“hello2”. 参考了combobox的源码中继承combo,当然我这个简单很多了.都是根据自己的理解来 ...
- C#实体图片下载与批量下载(自动保存功能)
新工作,第一个小任务,制作一个点击下载图片的功能.并提供批量下载操作.图片是字节流的形式,存放在数据库中的. 为了避免直接从数据库中,下载失败,会在本地保存一份. 进行压缩的是SharpZip这个压缩 ...
- 加州大学伯克利分校Stat2.2x Probability 概率初步学习笔记: Section 1 The Two Fundamental Rules (1.5-1.6)
Stat2.2x Probability(概率)课程由加州大学伯克利分校(University of California, Berkeley)于2014年在edX平台讲授. PDF笔记下载(Acad ...
- A.Kaw矩阵代数初步学习笔记 6. Gaussian Elimination
“矩阵代数初步”(Introduction to MATRIX ALGEBRA)课程由Prof. A.K.Kaw(University of South Florida)设计并讲授. PDF格式学习笔 ...
- HDU 1007 Quoit Design
传送门 Time Limit: 10000/5000 MS (Java/Others) Memory Limit: 65536/32768 K (Java/Others) Problem Des ...
- FZU 1894 志愿者选拔(单调队列)
传送门 Description 世博会马上就要开幕了,福州大学组织了一次志愿者选拔活动.参加志愿者选拔的同学们排队接受面试官们的面试.参加面试的同学们按照先来先面试并且先结束的原则接受面试官们的考查. ...
- resultset 对象获取行字段数据时报:java.sql.SQLException: Column 'id' not found.
resultset 对象获取行字段数据时报:java.sql.SQLException: Column 'id' not found. 代码: String sql="SELECT d.co ...