Lucene.Net + 盤古分詞

轉載自：http://blog.csdn.net/pukuimin1226/article/details/17558247/

一、Nuget Lucene的盤古分析器會自動添加Lucene及分詞高亮等引用

二、將自動添加的 Dict 字典文件複製到輸出目錄

三、添加盤古分詞及Lucene幫助類

using Lucene.Net.Analysis;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.QueryParsers;
using Lucene.Net.Search;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Reflection;
using System.Web;

namespace WebApplication1.Commons
{
    /// <summary>  
    /// 盤古分詞在lucene.net中的使用幫助類  
    /// 調用PanGuLuceneHelper.instance  
    /// </summary>  
    public class PanGuLuceneHelper
    {
        private PanGuLuceneHelper() { }

        #region 單一實例  
        private static PanGuLuceneHelper _instance = null;
        /// <summary>  
        /// 單一實例  
        /// </summary>  
        public static PanGuLuceneHelper instance
        {
            get
            {
                if (_instance == null) _instance = new PanGuLuceneHelper();
                return _instance;
            }
        }
        #endregion

        #region 分詞測試  
        /// <summary>  
        /// 分詞測試  
        /// </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 建立索引  
        /// <summary>  
        /// 建立索引  
        /// </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表示刪除以前的從新寫入）  
            }
            catch
            {
                writer = new IndexWriter(directory_luce, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);//false表示追加（true表示刪除以前的從新寫入）  
            }
            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); //命名空間名稱 + 類名      

                //建立類的實例      
                //object obj = Activator.CreateInstance(type, true);    
                //獲取公共屬性      
                PropertyInfo[] Propertys = type.GetProperties();
                for (int i = 0; i < Propertys.Length; i++)
                {
                    //Propertys[i].SetValue(Propertys[i], i, null); //設置值  
                    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在寫入索引時必是不分詞，不然是模糊搜索和刪除，會出現混亂  
                    {
                        doc.Add(new Field(name, value, Field.Store.YES, Field.Index.NOT_ANALYZED));//id不分詞  
                    }
                    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字段中查詢數據  
        /// <summary>  
        /// 在title和content字段中查詢數據  
        /// </summary>  
        /// <param name="keyword"></param>  
        /// <returns></returns>  
        public List<MySearchUnit> Search(string keyword)
        {

            string[] fileds = { "title", "content" };//查詢字段  
            //Stopwatch st = new Stopwatch();  
            //st.Start();  
            QueryParser parser = null;// new QueryParser(Lucene.Net.Util.Version.LUCENE_30, field, analyzer);//一個字段查詢  
            parser = new MultiFieldQueryParser(version, fileds, analyzer);//多個字段查詢  
            Query query = parser.Parse(keyword);
            int n = 1000;
            IndexSearcher searcher = new IndexSearcher(directory_luce, true);//true-表示只讀  
            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)//遍歷搜索到的結果  
                {
                    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("查詢時間：" + st.ElapsedMilliseconds + " 毫秒<br/>");  

        }
        #endregion

        #region 在不一樣的分類下再根據title和content字段中查詢數據(分頁)  
        /// <summary>  
        /// 在不一樣的類型下再根據title和content字段中查詢數據(分頁)  
        /// </summary>  
        /// <param name="_flag">分類,傳空值查詢所有</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);//與運算  
            }
            if (keyword != "")
            {
                string[] fileds = { "title", "content" };//查詢字段  
                QueryParser parser = null;// new QueryParser(version, field, analyzer);//一個字段查詢  
                parser = new MultiFieldQueryParser(version, fileds, analyzer);//多個字段查詢  
                Query queryKeyword = parser.Parse(keyword);
                bq.Add(queryKeyword, Occur.MUST);//與運算  
            }

            TopScoreDocCollector collector = TopScoreDocCollector.Create(PageIndex * PageSize, false);
            IndexSearcher searcher = new IndexSearcher(directory_luce, true);//true-表示只讀  
            searcher.Search(bq, collector);
            if (collector == null || collector.TotalHits == 0)
            {
                TotalCount = 0;
                return null;
            }
            else
            {
                int start = PageSize * (PageIndex - 1);
                //結束數  
                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)//遍歷搜索到的結果  
                {
                    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("查詢時間：" + st.ElapsedMilliseconds + " 毫秒<br/>");  

        }
        #endregion

        #region 刪除索引數據（根據id）  
        /// <summary>  
        /// 刪除索引數據（根據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);//多個字段查詢  
            //Query query = parser.Parse("小王");  

            //IndexReader reader = IndexReader.Open(directory_luce, false);  
            //reader.DeleteDocuments(term);  
            //Response.Write("刪除記錄結果： " + 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 刪除所有索引數據  
        /// <summary>  
        /// 刪除所有索引數據  
        /// </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的目錄-參數  
        /// </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>  
        /// 索引在硬盤上的目錄  
        /// </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.PanGuAnalyzer();//盤古分詞分析器  
                    //_analyzer = new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30);//標準分析器  
                }
                return _analyzer;
            }
        }
        #endregion

        #region version  
        private static Lucene.Net.Util.Version _version = Lucene.Net.Util.Version.LUCENE_30;
        /// <summary>  
        /// 版本號枚舉類  
        /// </summary>  
        public Lucene.Net.Util.Version version
        {
            get
            {
                return _version;
            }
        }
        #endregion
    }

    #region 索引的一個行單元，至關於數據庫中的一行數據  
    /// <summary>  
    /// 索引的一個行單元，至關於數據庫中的一行數據  
    /// </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>  
        /// 惟一的id號  
        /// </summary>  
        public string id { get; set; }
        /// <summary>  
        /// 標題  
        /// </summary>  
        public string title { get; set; }
        /// <summary>  
        /// 內容  
        /// </summary>  
        public string content { get; set; }
        /// <summary>  
        /// 其餘信息  
        /// </summary>  
        public string flag { get; set; }
        /// <summary>  
        /// 圖片路徑  
        /// </summary>  
        public string imageurl { get; set; }
        /// <summary>  
        /// 時間  
        /// </summary>  
        public string updatetime { get; set; }
    }
    #endregion
}

四、使用 建立索引及搜索

        public ActionResult Index()
        {
            //PanGuLuceneHelper.instance.DeleteAll();//刪除所有  

            //PanGuLuceneHelper.instance.Delete("1d");//根據id刪除  
            bool exec = false;
            if (exec)
            {
                List<MySearchUnit> list = new List<MySearchUnit>();
                list.Add(new MySearchUnit("1a", "標題小王", "今天是小王的生日，你們都很高興去他家喝酒，玩了一成天。", new Random().Next(1, 10).ToString(), "", ""));
                list.Add(new MySearchUnit("1b", "標題小張", "今天是小張的生日，你們都很高興去他家喝酒，玩了幾天。", new Random().Next(1, 10).ToString(), "", ""));
                list.Add(new MySearchUnit("1c", "標題小王", "今天是小王的生日，你們都很高興去他家喝酒，玩了一成天。", new Random().Next(1, 10).ToString(), "", ""));
                list.Add(new MySearchUnit("1d", "標題小張", "今天是小張的生日，你們都很高興去他家喝酒，玩了幾天。", new Random().Next(1, 10).ToString(), "", ""));
                PanGuLuceneHelper.instance.CreateIndex(list);//添加索引  
            }
            int count = 0;
            int PageIndex = 1;
            int PageSize = 4;
            string html_content = "";
            List<MySearchUnit> searchlist = PanGuLuceneHelper.instance.Search("", "幾天", PageIndex, PageSize, out count);
            html_content += ("查詢結果：" + count + "條數據<br/>");
            if (searchlist == null || searchlist.Count == 0)
            {
                html_content += ("未查詢到數據。<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);
            return  Content(html_content);
        }