.NET开发过程中的全文索引使用技巧之Solr（转）

using System;using System.Collections.Generic;namespace Seek.SearchIndex{ ???public partial class IndexProductModel ???{ ???????public IndexProductModel() ???????{ ???????} ???????#region ?Properties ???????public int ID { get; set; } ???????public int ProductID { get; set; } ???????public string ClassPath { get; set; } ???????public int ClassID1 { get; set; } ???????public int ClassID2 { get; set; } ???????public int ClassID3 { get; set; } ???????public string Title { get; set; } ???????public string Model { get; set; } ???????public string PriceRange { get; set; } ???????public string AttributeValues { get; set; } ???????public string ProductImages { get; set; } ???????public int MemberID { get; set; } ???????public System.DateTime CreateDate { get; set; } ???????public System.DateTime LastEditDate { get; set; } ???????public string FileName { get; set; } ???????public string ProductType { get; set; } ???????public string Summary { get; set; } ???????public string Details { get; set; } ???????public string RelatedKeywords { get; set; } ???????public int MemberGrade { get; set; } ???????#endregion ???}}

<field name="ID" type="string" indexed="true" stored="true" required="true" multiValued="false" /> ???<field name="ProductID" type="int" indexed="true" stored="true"/> ??<!-- 快速高亮配置 termVectors="true" termPositions="true" ?termOffsets="true" --> ??<field name="Title" type="text_en_splitting" indexed="true" stored="true" termVectors="true" termPositions="true" ?termOffsets="true"/> ??<field name="Model" type="text_en_splitting" indexed="true" stored="true" termVectors="true" termPositions="true" ?termOffsets="true"/> ??<field name="ClassPath" type="string" indexed="true" stored="true"/> ??<field name="ClassID1" type="int" indexed="true" stored="true"/> ??<field name="ClassID2" type="int" indexed="true" stored="true"/> ??<field name="ClassID3" type="int" indexed="true" stored="true"/> ??<field name="PriceRange" type="string" indexed="true" stored="true"/> ??<field name="AttributeValues" type="string" indexed="true" stored="true"/> ??<field name="ProductImages" type="string" indexed="true" stored="true"/> ??<field name="MemberID" type="int" indexed="true" stored="true"/> ??<field name="CreateDate" type="date" indexed="true" stored="true"/> ??<field name="LastEditDate" type="date" indexed="true" stored="true"/> ??<field name="FileName" type="string" indexed="true" stored="true"/> ??<field name="ProductType" type="string" indexed="true" stored="true"/> ??<field name="Summary" type="string" indexed="true" stored="false"/> ??<field name="Details" type="string" indexed="true" stored="false"/> ??<field name="RelatedKeywords" type="string" indexed="true" stored="true"/> ??<field name="MemberType" type="string" indexed="true" stored="true"/> ??<field name="MemberGrade" type="int" indexed="true" stored="true"/>

using System;using System.Collections.Generic;using System.Linq;using System.Text;using Seek.SearchIndex;using System.Data;using System.Threading;using System.Configuration;using System.Reflection;using EasyNet.Solr;using EasyNet.Solr.Impl;using EasyNet.Solr.Commons;using System.Xml.Linq;using EasyNet.Solr.Commons.Params;using System.Threading.Tasks;namespace Seek.SearchIndex{ ???/// <summary> ???/// 索引器 ???/// </summary> ???public class Indexer ???{ ???????private readonly static OptimizeOptions optimizeOptions = new OptimizeOptions(); ???????private readonly static CommitOptions commitOptions = new CommitOptions() { SoftCommit = true }; ???????private readonly static ISolrResponseParser<NamedList, EasyNet.Solr.ResponseHeader> binaryResponseHeaderParser = new BinaryResponseHeaderParser(); ???????private readonly static IUpdateParametersConvert<NamedList> updateParametersConvert = new BinaryUpdateParametersConvert(); ???????private readonly static ISolrQueryConnection<NamedList> connection = new SolrQueryConnection<NamedList>() { ServerUrl = ConfigurationManager.AppSettings["SolrServer"] }; ???????private readonly static ISolrUpdateConnection<NamedList, NamedList> solrUpdateConnection = new SolrUpdateConnection<NamedList, NamedList>() { ServerUrl = ConfigurationManager.AppSettings["SolrServer"], ContentType = "application/javabin" }; ???????private readonly static ISolrUpdateOperations<NamedList> solr = new SolrUpdateOperations<NamedList, NamedList>(solrUpdateConnection, updateParametersConvert) { ResponseWriter = "javabin" }; ???????private readonly static ISolrQueryOperations<NamedList> solrQuery = new SolrQueryOperations<NamedList>(connection) { ResponseWriter = "javabin" }; ???????public enum State ???????{ ???????????/// <summary> ???????????/// 运行中 ???????????/// </summary> ???????????Runing, ???????????/// <summary> ???????????/// 停止 ???????????/// </summary> ???????????Stop, ???????????/// <summary> ???????????/// 中断 ???????????/// </summary> ???????????Break ???????} ???????/// <summary> ???????/// 窗口 ???????/// </summary> ???????private Main form; ???????/// <summary> ???????/// 线程 ???????/// </summary> ???????public Thread t; ???????/// <summary> ???????/// 消息状态 ???????/// </summary> ???????public State state = State.Stop; ???????/// <summary> ???????/// 当前索引 ???????/// </summary> ???????private long currentIndex = 0; ???????public long CurrentIndex ???????{ ???????????get { return currentIndex; } ???????????set { currentIndex = value; } ???????} ???????private int _startId = AppCongfig.StartId; ???????public int StartId ???????{ ???????????get { return _startId; } ???????????set { _startId = value; } ???????} ???????/// <summary> ???????/// 产品总数 ???????/// </summary> ???????private int productsCount = 0; ???????/// <summary> ???????/// 起始时间 ???????/// </summary> ???????private DateTime startTime = DateTime.Now; ???????/// <summary> ???????/// 结束时间 ???????/// </summary> ???????private DateTime endTime = DateTime.MinValue; ???????private static object syncLock = new object(); ???????#region 单利模式 ???????private static Indexer instance = null; ???????private Indexer(Main _form) ???????{ ???????????form = _form; ???????????productsCount = DataAccess.GetCount(0); ??????//产品数统计 ???????????form.fullerTsslMaxNum.Text = productsCount.ToString(); ???????????form.fullerProgressBar.Minimum = 0; ???????????form.fullerProgressBar.Maximum = productsCount; ???????} ???????public static Indexer GetInstance(Main form) ???????{ ???????????if (instance == null) ???????????{ ???????????????lock (syncLock) ???????????????{ ???????????????????if (instance == null) ???????????????????{ ???????????????????????instance = new Indexer(form); ???????????????????} ???????????????} ???????????} ???????????return instance; ???????} ???????#endregion ???????/// <summary> ???????/// 启动 ???????/// </summary> ???????public void Start() ???????{ ???????????ThreadStart ts = new ThreadStart(FullerRun); ???????????t = new Thread(ts); ???????????t.Start(); ???????} ???????/// <summary> ???????/// 停止 ???????/// </summary> ???????public void Stop() ???????{ ???????????state = State.Stop; ???????} ???????/// <summary> ???????/// 中断 ???????/// </summary> ???????public void Break() ???????{ ???????????state = State.Break; ???????} ???????/// <summary> ???????/// 创建索引 ???????/// </summary> ???????public void InitIndex(object data) ???????{ ???????????var docs = new List<SolrInputDocument>(); ???????????DataTable list = data as DataTable; ???????????foreach (DataRow pro in list.Rows) ???????????{ ???????????????var model = new SolrInputDocument(); ???????????????PropertyInfo[] properites = typeof(IndexProductModel).GetProperties();//得到实体类属性的集合 ???????????????string[] dateFields = { "CreateDate", "LastEditDate" }; ???????????????string field = string.Empty;//存储fieldname ???????????????foreach (PropertyInfo propertyInfo in properites)//遍历数组 ???????????????{ ???????????????????object val = pro[propertyInfo.Name]; ???????????????????if (val != DBNull.Value) ???????????????????{ ???????????????????????model.Add(propertyInfo.Name, new SolrInputField(propertyInfo.Name, val)); ???????????????????} ???????????????} ???????????????docs.Add(model); ???????????????StartId = Convert.ToInt32(pro["ID"]); ???????????} ???????????GetStartId(); ???????????lock (syncLock) ???????????{ ???????????????if (currentIndex <= productsCount) ???????????????{ ???????????????????form.fullerProgressBar.Value = (int)currentIndex; ???????????????} ???????????????form.fullerTsslCurrentNum.Text = currentIndex.ToString(); ???????????} ???????????var result = solr.Update("/update", new UpdateOptions() { ?Docs = docs }); ???????} ???????/// <summary> ???????/// 创建索引 ???????/// </summary> ???????public void CreateIndexer(DataTable dt) ???????{ ???????????GetStartId(); ???????????Parallel.ForEach<DataRow>(dt.AsEnumerable(), (row) => ???????????{ ???????????????//从数据库查询商品详细属性 ???????????????if (row != null) ???????????????{ ???????????????????var docs = new List<SolrInputDocument>(); ???????????????????var model = new SolrInputDocument(); ???????????????????PropertyInfo[] properites = typeof(IndexProductModel).GetProperties();//得到实体类属性的集合 ???????????????????string[] dateFields = { "CreateDate", "LastEditDate" }; ???????????????????string field = string.Empty;//存储fieldname ???????????????????foreach (PropertyInfo propertyInfo in properites)//遍历数组 ???????????????????{ ???????????????????????object val = row[propertyInfo.Name]; ???????????????????????if (val != DBNull.Value) ???????????????????????{ ???????????????????????????model.Add(propertyInfo.Name, new SolrInputField(propertyInfo.Name, val)); ???????????????????????} ???????????????????} ???????????????????docs.Add(model); ???????????????????StartId = Convert.ToInt32(row["ID"]); ???????????????????var result = solr.Update("/update", new UpdateOptions() { Docs = docs }); ???????????????} ???????????}); ???????????//GetStartId(); ???????????lock (syncLock) ???????????{ ???????????????if (currentIndex <= productsCount) ???????????????{ ???????????????????form.fullerProgressBar.Value = (int)currentIndex; ???????????????} ???????????????form.fullerTsslCurrentNum.Text = currentIndex.ToString(); ???????????} ???????} ???????/// <summary> ???????/// 全部索引运行 ???????/// </summary> ???????public void FullerRun() ???????{ ???????????//GetStartId(); ???????????//form.fullerTsslCurrentNum.Text = currentIndex.ToString(); ???????????DataTable dt = DataAccess.GetNextProductsInfo(StartId); ???????????StartId = AppCongfig.StartId; ???????????if (state == State.Break) ???????????{ ???????????????this.SendMesasge("完全索引已继续，起始ID[" + StartId + "]..."); ???????????} ???????????else ???????????{ ???????????????startTime = DateTime.Now; ???????????????this.SendMesasge("完全索引已启动，起始ID[" + StartId + "]..."); ???????????} ???????????state = State.Runing; ???????????form.btnInitIndex.Enabled = false; ???????????form.btnSuspend.Enabled = true; ???????????form.btnStop.Enabled = true; ?????????????????while (dt != null && dt.Rows.Count > 0 && state == State.Runing) ???????????{ ???????????????try ???????????????{ ???????????????????InitIndex(dt);//单线程 ??????????????????// CreateIndexer(dt);//多线程 ???????????????} ???????????????catch (Exception ex) ???????????????{ ???????????????????state = State.Stop; ???????????????????form.btnInitIndex.Enabled = true; ???????????????????form.btnSuspend.Enabled = false; ???????????????????form.btnStop.Enabled = false; ???????????????????GetStartId(); ???????????????????this.SendMesasge(ex.Message.ToString()); ???????????????} ???????????????form.fullerTsslTimeSpan.Text = "已运行 ：" + GetTimeSpanShow(DateTime.Now - startTime) + "，预计还需：" + GetTimeSpanForecast(); ???????????????try ???????????????{ ???????????????????dt = DataAccess.GetNextProductsInfo(StartId);//获取下一组产品 ???????????????} ???????????????catch (Exception err) ???????????????{ ???????????????????this.SendMesasge("获取下一组产品出错，起始ID[" + StartId + "]：" + err.Message); ???????????????} ???????????} ???????????if (state == State.Runing) ???????????{ ???????????????state = State.Stop; ???????????????form.btnInitIndex.Enabled = true; ???????????????form.btnSuspend.Enabled = false; ???????????????form.btnStop.Enabled = false; ???????????????AppCongfig.SetValue("StartId", StartId.ToString()); ???????????????this.SendMesasge("完全索引已完成，总计索引数[" + currentIndex + "]结束的产品Id" + StartId); ???????????} ???????????else if (state == State.Break) ???????????{ ???????????????GetStartId(); ???????????????state = State.Break; ???????????????form.btnInitIndex.Enabled = true; ???????????????form.btnSuspend.Enabled = false; ???????????????form.btnStop.Enabled = false; ???????????????AppCongfig.SetValue("StartId", StartId.ToString()); ???????????????this.SendMesasge("完全索引已暂停，当前索引位置[" + currentIndex + "]结束的产品Id" + StartId); ???????????} ???????????else if (state == State.Stop) ???????????{ ???????????????GetStartId(); ???????????????state = State.Stop; ???????????????this.SendMesasge("完全索引已停止，已索引数[" + currentIndex + "]结束的产品Id" + StartId); ???????????????form.btnInitIndex.Enabled = true; ???????????????form.btnSuspend.Enabled = false; ???????????????form.btnStop.Enabled = false; ???????????????AppCongfig.SetValue("StartId", StartId.ToString()); ???????????????productsCount = DataAccess.GetCount(StartId); ??????//产品数统计 ???????????????form.fullerTsslMaxNum.Text = productsCount.ToString(); ???????????????form.fullerProgressBar.Minimum = 0; ???????????????form.fullerProgressBar.Maximum = productsCount; ???????????} ???????????endTime = DateTime.Now; ???????} ???????/// <summary> ???????/// 多线程构建索引数据方法 ???????/// </summary> ???????/// <param name="threadDataParam"></param> ???????public void MultiThreadCreateIndex(object threadDataParam) ???????{ ???????????InitIndex(threadDataParam); ???????} ???????/// <summary> ???????/// 获取最大的索引id ???????/// </summary> ???????private void GetStartId() ???????{ ???????????IDictionary<string, ICollection<string>> options = new Dictionary<string, ICollection<string>>(); ???????????options[CommonParams.SORT] = new string[] { "ProductID DESC" }; ???????????options[CommonParams.START] = new string[] { "0" }; ???????????options[CommonParams.ROWS] = new string[] { "1" }; ???????????options[HighlightParams.FIELDS] = new string[] { "ProductID" }; ???????????options[CommonParams.Q] = new string[] { "*:*" }; ???????????var result = solrQuery.Query("/select", null, options); ???????????var solrDocumentList = (SolrDocumentList)result.Get("response"); ???????????currentIndex = solrDocumentList.NumFound; ???????????if (solrDocumentList != null && solrDocumentList.Count() > 0) ???????????{ ???????????????StartId = (int)solrDocumentList[0]["ProductID"]; ???????????????//AppCongfig.SetValue("StartId", solrDocumentList[0]["ProductID"].ToString()); ???????????} ???????????else ???????????{ ???????????????StartId = 0; ???????????????// AppCongfig.SetValue("StartId", "0"); ???????????} ???????} ???????/// <summary> ???????/// 优化索引 ???????/// </summary> ???????public void Optimize() ???????{ ???????????this.SendMesasge("开始优化索引，请耐心等待..."); ???????????var result = solr.Update("/update", new UpdateOptions() { OptimizeOptions = optimizeOptions }); ???????????var header = binaryResponseHeaderParser.Parse(result); ???????????this.SendMesasge("优化索引耗时:" + header.QTime + "毫秒"); ???????} ???????/// <summary> ???????/// 发送消息到界面 ???????/// </summary> ???????/// <param name="message">发送消息到界面</param> ???????protected void SendMesasge(string message) ???????{ ???????????form.fullerDgvMessage.Rows.Add(form.fullerDgvMessage.Rows.Count + 1, message, DateTime.Now.ToString()); ???????} ???????/// <summary> ???????/// 获取时间间隔显示 ???????/// </summary> ???????/// <param name="ts">时间间隔</param> ???????/// <returns></returns> ???????protected string GetTimeSpanShow(TimeSpan ts) ???????{ ???????????string text = ""; ???????????if (ts.Days > 0) ???????????{ ???????????????text += ts.Days + "天"; ???????????} ???????????if (ts.Hours > 0) ???????????{ ???????????????text += ts.Hours + "时"; ???????????} ???????????if (ts.Minutes > 0) ???????????{ ???????????????text += ts.Minutes + "分"; ???????????} ???????????if (ts.Seconds > 0) ???????????{ ???????????????text += ts.Seconds + "秒"; ???????????} ???????????return text; ???????} ???????/// <summary> ???????/// 获取预测时间 ???????/// </summary> ???????/// <returns></returns> ???????protected string GetTimeSpanForecast() ???????{ ???????????if (currentIndex != 0) ???????????{ ???????????????TimeSpan tsed = DateTime.Now - startTime; ???????????????double d = ((tsed.TotalMilliseconds / currentIndex) * productsCount) - tsed.TotalMilliseconds; ???????????????return GetTimeSpanShow(TimeSpan.FromMilliseconds(d)); ???????????} ???????????return ""; ???????} ???}}