lucene.net 3.0.3、结合盘古分词进行搜索的小例子(转)
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。
//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
- }
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_luceprivate 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 directoryprivate 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 analyzerprivate 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 versionprivate 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;
- }
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 教程(转载)
- Lucene(.net)学习
- Lucene的缺点
- web.config 学习之 httpHandlers
- LUCENE 3.6 学习笔记
- Lucene小练九——各种搜索(精确,范围,数字)
- Lucene小练三——索引删除,恢复,更新
- 在 Asp.NET MVC 中使用 SignalR 实现推送功能
- FieldCache在lucene中使用的代码解析,使用场景个人分析
- Lucene3.0.1 学习笔记
转载于:https://www.cnblogs.com/sumg/p/4030036.html
lucene.net 3.0.3、结合盘古分词进行搜索的小例子(转)相关推荐
- 全文检索 使用最新lucene3.0.3+最新盘古分词 pangu2.4 .net 实例
开发环境 vs2015 winform 程序 1 首先需要下载对应的DLL 文章后面统一提供程序下载地址 里面都有 2 配置pangu的参数 也可以不配置 采用默认的即可 3 创建索引,将索引存放到本 ...
- 盘古分词-关键字搜索没有结果(关键字由未收录词组成)
由未收录词A.B.C等组成的任意组合在搜索时没有结果的问题. 解决方案很简单在设置中UnknownWordIdentify选项置为False就可以了. 下面是Pangu代码中处理段: if (coun ...
- 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 Luc ...
- 让盘古分词支持最新的Lucene.Net 3.0.3
原文:让盘古分词支持最新的Lucene.Net 3.0.3 好多年没升级过的Lucene.Net最近居然升级了,到了3.0.3后接口发生了很大变化,原来好多分词库都不能用了,所以上次我把MMSeg给修 ...
- Lucene.Net3.0.3+盘古分词器学习使用
一.Lucene.Net介绍 Lucene.net是Lucene的.net移植版本,是一个开源的全文检索引擎开发包,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,提供了完整的查询引擎和索 ...
- 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)
Lucene.Net+盘古分词器(详细介绍)(转) 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 ...
- java盘古分词_.NET使用Lucene.Net和盘古分词类库实现中文分词
.NET中文分词实现http://http:// 使用 Lucene.Net.dll http://www.apache.org/dist/incubator/lucene.net/binaries/ ...
- Lucene.net和盘古分词使用小结
盘古分词是开源项目,核心技术基于Lucene.net.虽然有点旧(2010年),但是还是可以用的.案例.应用程序.以及源码可以详见以下链接. http://pangusegment.codeplex. ...
- Lucence.Net学习+盘古分词
创建索引库 //读取文件,存储到索引库 public string CreateDatebase() { //获取索引库的路径 var indexPath = AppDomain.CurrentDom ...
最新文章
- mac上mysql关闭不了了_python操作mysql数据库
- 《深入浅出Nodejs》—— 读后总结
- 自学python入门-自学Python编程基础学习笔记 PDF 完整超清版
- 试试Linux下的ip命令,ifconfig已经过时了
- 07-CoreData清除所有数据
- 创建型模式—单例模式
- delphi开发LINUX程序,DELPHI开发LINUX包
- JZOJ 3457. 【NOIP2013模拟联考3】沙耶的玩偶(doll)
- 解决 HttpClient 模拟 http 的get 请求后 ,出现 403 错误
- iOS 8 Xcode6 设置Launch Image 启动图片转
- Docker系列(四)守护式容器
- gsonformat java代码_插件GsonFormat快速實現JavaBean
- 分享10个值得每天一看的精品网站,可以让你全方面得到提升,每一个都会让你大开眼界。
- 如何使用SPSS进行判别分析
- java怎么判断素数_java判断是否为素数(质数)的方法
- Crystal Reports - 根据模板导出PDF文件
- 小程序发布文章-微信小程序视频教程28
- 手把手带你学微信小程序 —— 如何开发属于自己的第三方微信小程序组件库
- 机器学习笔记之基础概念
- ros使用usb摄像头追踪ArUco markers
热门文章
- Dubbo本地伪装 Mock
- jquery validation用法
- keil5图标变成白色_【网上最简单】Chrome安装后打不开任何页面 amp; 改名后图标变成小白块[30秒解决]...
- MyBatis的XML配置文件(二)
- 开启MyBatis(一)
- 【渝粤教育】国家开放大学2018年秋季 1039t高级财务会计 参考试题
- 【渝粤教育】国家开放大学2018年春季 0579-21T电路及磁路(2)(一) 参考试题
- [渝粤教育] 中国地质大学 管理信息系统 复习题
- 【sklearn第十八讲】神经网络模型
- pku 2348 Euclid's Game