使用Lucene.net提升网站搜索速度整合记录

最新推荐文章于 2024-11-14 15:58:00 发布

weixin_30376323

最新推荐文章于 2024-11-14 15:58:00 发布

阅读量94

点赞数

文章标签：数据库

原文链接：http://www.cnblogs.com/miao31/p/3388295.html

版权

1.随着网站数据量达到500万条的时候,发现SQL数据库如果使用LIKE语句来查询,总是占用CPU很忙,不管怎么优化,速度还是上不来;

2.经过网上收集资料,HUBBLE.net目前虽然做得不错,但需要配置内存给他,由于服务器4G内存,而且运行了好几个网站,所以考虑采用Lucene.net来做为搜索引擎;

3.虽然本地测试没有问题,但是部署到64位的服务器上还是经过了好几天的折腾,在此都记录一下.

在此记录搜片神器的整个开发过程中遇到的问题和相关的解决方案,希望大家一起交流.

Lucene软件下载编译整合的问题

网站采用了最新Lucene.Net.3.0.3版本的代码,然后配置盘古分词来进行.

由于Lucene.Net升级到了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，

.Net下还有一个盘古分词（http://pangusegment.codeplex.com/），但也不支持Lucene.Net 3.0.3，园子里的大哥们修改的项目地址:

https://github.com/JimLiu/Lucene.Net.Analysis.PanGu

下载后里面有DEMO代码进行整合.

Lucene在软件中集成处理

由于实时处理数据程序是WINFORM程序,所以需要采用软件代码来实时更新索引数据,这样可控性高一些.

引用头文件

using Lucene.Net.Analysis;
using Lucene.Net.Analysis.Standard;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.QueryParsers;
using Lucene.Net.Search;
using Lucene.Net.Store;
using Lucene.Net.Util;
using PanGu;
using Lucene.Net.Analysis.PanGu;
using PanGu.HighLight;
using FSDirectory = Lucene.Net.Store.FSDirectory;
using Version = Lucene.Net.Util.Version;

创建索引

    public static class H31Index
    {
        private static Analyzer analyzer = new PanGuAnalyzer(); //MMSegAnalyzer //StandardAnalyzer
        private static int ONEPAGENUM = 200;
        private static string m_indexPath = "";
        private static IndexWriter iw = null;
        public static void Init(string indexpath)
        {
            m_indexPath = indexpath;
        }

        public static bool OpenIndex()
        {
            try
            {

                DirectoryInfo INDEX_DIR = new DirectoryInfo(m_indexPath+"//Index");
                bool iscreate = true;
                if (INDEX_DIR.Exists)
                    iscreate = false;
                Int32 time21 = System.Environment.TickCount;
                if (iw == null)
                {
                    iw = new IndexWriter(FSDirectory.Open(INDEX_DIR), analyzer, iscreate, new IndexWriter.MaxFieldLength(32));
                    Int32 time22 = System.Environment.TickCount;
                    H31Debug.PrintLn("IndexWriter2[" + type.ToString() + "]:" + " IndexWriter:" + (time22 - time21).ToString() + "ms");
                    return true;
                }
            }
            catch (System.Exception ex)
            {
                H31Debug.PrintLn("OpenIndex" + ex.Message);
            }
            return false;
        }

        public static void CloseIndex()
        {
            try
            {
                if (iw != null)
                {
                    //if (count > 0)
                    {
                        iw.Commit();
                        iw.Optimize();
                    }
                    iw.Dispose();
                    iw = null;
                }            
            }
            catch (System.Exception ex)
            {
                H31Debug.PrintLn("CloseIndex" + ex.Message);
            }

        }

        //建立索引        
public static int AddIndexFromDB()
        {
            int res = 0;
            int count = 0;
            try
            {
                Int32 time0 = System.Environment.TickCount;
                while (count < OneTimeMax && iw != null)
                {
                    Int32 time11 = System.Environment.TickCount;
                    DataSet ds = H31SQL.GetHashListFromDB(type, startnum, startnum + ONEPAGENUM - 1, NewOrUpdate);
                    Int32 time12 = System.Environment.TickCount;
                    int cnt = ds.Tables[0].Rows.Count;
                    if (ds != null&& cnt>0)
                    {
                        Int32 time1 = System.Environment.TickCount;
                        count = count + cnt;
                        for (int i = 0; i < cnt; i++)
                        {
                            //ID,hashKey,recvTime,updateTime,keyContent,keyType,recvTimes,fileCnt,filetotalSize,Detail,viewTimes,viewLevel
                            Document doc = new Document();
                            doc.Add(new Field("ID", ds.Tables[0].Rows[i]["ID"].ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));//存储，索引
                            doc.Add(new Field("hashKey", ds.Tables[0].Rows[i]["hashKey"].ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));//存储，索引
                            doc.Add(new Field("recvTime", ds.Tables[0].Rows[i]["recvTime"].ToString(), Field.Store.YES, Field.Index.NO));//存储，不索引
                            doc.Add(new Field("updateTime", ds.Tables[0].Rows[i]["updateTime"].ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));//存储，索引
                            doc.Add(new Field("keyContent", ds.Tables[0].Rows[i]["keyContent"].ToString(), Field.Store.YES, Field.Index.ANALYZED));//存储，索引
                            //PanGuFenCiTest(ds.Tables[0].Rows[i]["keyContent"].ToString());
                            string typeid=ds.Tables[0].Rows[i]["keyType"].ToString();
                            if(typeid.Length<2)
                                typeid=type.ToString();
                            doc.Add(new Field("keyType", typeid, Field.Store.YES, Field.Index.NO));//存储，不索引
                            doc.Add(new Field("recvTimes", ds.Tables[0].Rows[i]["recvTimes"].ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));//存储，索引
                            doc.Add(new Field("fileCnt", ds.Tables[0].Rows[i]["fileCnt"].ToString(), Field.Store.YES, Field.Index.NO));//存储，不索引
                            doc.Add(new Field("filetotalSize", ds.Tables[0].Rows[i]["filetotalSize"].ToString(), Field.Store.YES, Field.Index.NO));//存储，不索引
                            doc.Add(new Field("Detail", ds.Tables[0].Rows[i]["Detail"].ToString(), Field.Store.YES, Field.Index.NO));//存储，不索引
                            doc.Add(new Field("viewTimes", ds.Tables[0].Rows[i]["viewTimes"].ToString(), Field.Store.YES, Field.Index.NO));//存储，不索引
                            doc.Add(new Field("viewLevel", ds.Tables[0].Rows[i]["viewLevel"].ToString(), Field.Store.YES, Field.Index.NO));//存储，不索引
                            iw.AddDocument(doc);
                        }
                        ds = null;
                        Thread.Sleep(10);
                    }
                    else
                    {
                        res = 1;
                        break;
                    }
                }

                Int32 time10 = System.Environment.TickCount;
                H31Debug.PrintLn("AddIndexFromDB[" + type.ToString() + "],Building index done:" + startnum.ToString() + " Time:" + (time10 - time0).ToString() + "ms");

            }
            catch (System.Exception ex)
            {
                H31Debug.PrintLn(ex.StackTrace);
            }

            return res; 
        }

创建索引代码

查询代码

        //网站搜索代码
        public static void Search(string keyword,int typeid,int pageNo)
        {
            int onePage=20;//一页多少
            int TotalNum=1000;//一次加载多少

            if (pageNo < 0) pageNo = 0;
            if (pageNo * onePage > TotalNum)
                pageNo = TotalNum / onePage;

            //索引加载的目录
            DirectoryInfo INDEX_DIR = new DirectoryInfo(m_indexPath+"//Index//index1");
            IndexSearcher searcher = new IndexSearcher(FSDirectory.Open(INDEX_DIR), true);
            QueryParser qp = new QueryParser(Version.LUCENE_30, "keyContent", analyzer);
            Query query = qp.Parse(keyword); 
            //Console.WriteLine("query> {0}", query);

            //设置排序问题
            Sort sort = new Sort(new SortField[]{new SortField("recvTimes", SortField.INT, true),new SortField("updateTime", SortField.STRING, true)});

            //设置高亮显示的问题
            PanGu.HighLight.SimpleHTMLFormatter simpleHTMLFormatter = new PanGu.HighLight.SimpleHTMLFormatter("<font color=\"red\">", "</font>");
            PanGu.HighLight.Highlighter highlighter =new PanGu.HighLight.Highlighter(simpleHTMLFormatter,new Segment());
            highlighter.FragmentSize = 50;

            TopFieldDocs tds = searcher.Search(query,null, 1000, sort);
            Console.WriteLine("TotalHits: " + tds.TotalHits);

            /* 计算显示的条目 */
            int count = tds.ScoreDocs.Length;
            int start = (pageNo - 1) * onePage;
            int end = pageNo * onePage > count ? count : pageNo * onePage;
            //返回集合列表
            for (int i = start; i < end; i++)
            {
                Document doc = searcher.Doc(tds.ScoreDocs[i].Doc);
                string contentResult = highlighter.GetBestFragment(keyword, doc.Get("keyContent").ToString());
                Console.WriteLine(contentResult + ">>" + doc.Get("recvTimes") + "<<" + doc.Get("updateTime"));
            }

            searcher.Dispose();
        }