目前Sphinx广泛应用在Linux平台上，尽管官方所发布的产品中也有window版本，并且支持mssql数据库，但在使用过程中才发现，其只在发布的windows平台下的版本里才支持mssql数据库，而linux平台下只有MySql,PostgreSQL这两种数据库支持。尽管后来在网上查找资料时发现可以使用UNIXODBC方式在LINUX下链接MsSql数据库，但在unixodbc的官方网站下载的源码包中却发现其并不包含makefile文件，从而导致下载解压的源码包无法编译（看来unixodbc开发者也疏忽了），当然即使ODBC能链接成功，但效率上还是可能存在问题。
而在window下尽管能实现链接mssql和创建索引以及查询，但在进行压力测试时发现即使50并发也会让sphinx守护进程疲于奔命到停止响应（后来在Linux下布署,发现同样数据索引量同一台机器，可以支持至少200-300并发），而sphinx的宿主环境是一台单核1.5G+1.5g内存的普通台式机（现在主流笔记本的配置都比它高得多）。所以就并发性而言,目前主流平台还是建立在linux上.
正因为如此,我才在解决方案中引入了一个mysql数据库，来实现下面三个目标：
1.为LINUX平台下SPHINX提供可访问的数据源。
2.充当快照功能（Slave database）解决当主数据库(Master database)宕机后，不会影响SPHINX创建索引了，这样看就相当于备份功能。
3.解决当创建SPHINX索引时，对主数据库的访问压力。
下面这张图简单说明了Sphinx(Linux) + MySql + Discuz!NT的关系:
如上面所说的，我们在产品中引入了Sphinx客户端API，而服务端则通过LINUX+SPHINX守护进程来实现，所以这篇文章要被分为两个部分，今天要说明的只是Discuz!NT方面的改动。下一篇将会介绍如何在LINUX下配置SPHINX及增量索引等相关工作。好了开始正文吧。
首先为了简化安装，我写了一个文件类用于配置SPHINX客户端信息，如下（Discuz.Config\EntLibConfigInfo.cs）：
/// <summary>
/// Sphinx企业级查询配置信息
/// </summary>
public class SphinxConfig
{
/// <summary>
/// Mysql增量数据库链接地址
/// </summary>
public string MySqlConn;
/// <summary>
/// 是否启用Sphinx搜索
/// </summary>
public bool Enable;
/// <summary>
/// Sphinx服务地址
/// </summary>
public string SphinxServiceHost;
/// <summary>
/// Sphinx服务端口
/// </summary>
public int SphinxServicePort = 3312;
......
}
/// Sphinx企业级查询配置信息
/// </summary>
public class SphinxConfig
{
/// <summary>
/// Mysql增量数据库链接地址
/// </summary>
public string MySqlConn;
/// <summary>
/// 是否启用Sphinx搜索
/// </summary>
public bool Enable;
/// <summary>
/// Sphinx服务地址
/// </summary>
public string SphinxServiceHost;
/// <summary>
/// Sphinx服务端口
/// </summary>
public int SphinxServicePort = 3312;
......
}
该配置类中提供了是否开启SPHINX查询（Enable），以及MYSQL数据库链接，以及SPHINX服务端的地址端口信息等。
下面介绍一下Sphinx的客户端代码(C#)实现，该代码被放到了Discuz.EntLib这个项目中（位于SphinxClient\），而该项目是一个基于GNU的开源项目，其类"SphinxClient"实现了构造方法和相应访问SPHINX服务端守护进程的方法，如下：
这些方法的名称和参数信息与SPHINX开放的API是对应的,而相应的SPHINX文档可以从官方下载,这里只提供一个中文文档的下载地址,也就是CORESEEK的文档链接, 如下:
http://www.coreseek.cn/uploads/pdf/sphinx_doc_zhcn_0.9.pdf
这份手册中介绍了大部分API方法的使用和示例，是目前为止网上找到最全的中文文档了。
有了客户端，我们还要在已有的搜索代码中植入SPHINX查询逻辑代码。
在原来的产品中，搜索功能是使用SQLSERVER全文检索的方法提供的，其原理是：
使用SQLSERVER全文检索方法查询帖子分表(dnt_posts，表结构如下图所示)的MESSAGE字段:
而该字段是Text类型，所以在一次性查询出所有记录的pid字段后，以distinct方法过滤其中记录重复的tid信息，最终会返回tid字段并将其放入到数据库中,相应SQL语句构造方法参照如下(Discuz.Data.SqlServer/GlobalManage.cs)：
private string GetSearchPostContentSQL(int posterId, string searchForumId, int resultOrder, int resultOrderType, int searchTime, int searchTimeType, int postTableId, StringBuilder strKeyWord)
{
StringBuilder sqlBuilder = new StringBuilder();
string orderfield = "lastpost";
switch (resultOrder)
{
case 1:
orderfield = "tid";
break;
case 2:
orderfield = "replies";
break;
case 3:
orderfield = "views";
break;
default:
orderfield = "lastpost";
break;
}
sqlBuilder.AppendFormat("SELECT DISTINCT [{0}posts{1}].[tid],[{0}topics].[{2}] FROM [{0}posts{1}] LEFT JOIN [{0}topics] ON [{0}topics].[tid]=[{0}posts{1}].[tid] WHERE [{0}topics].[displayorder]>=0 ",
BaseConfigs.GetTablePrefix,
postTableId,
orderfield);
if (searchForumId != "")
sqlBuilder.AppendFormat(" AND [{0}posts{1}].[fid] IN ({2})", BaseConfigs.GetTablePrefix, postTableId, searchForumId);
if (posterId != -1)
sqlBuilder.AppendFormat(" AND [{0}posts{1}].[posterid]={2}", BaseConfigs.GetTablePrefix, postTableId, posterId);
if (searchTime != 0)
sqlBuilder.AppendFormat(" AND [{0}posts{1}].[postdatetime] {2} '{3}'",
BaseConfigs.GetTablePrefix,
postTableId,
searchTimeType == 1 ? "<" : ">",
DateTime.Now.AddDays(searchTime).ToString("yyyy-MM-dd 00:00:00"));
string[] keywordlist = Utils.SplitString(strKeyWord.ToString(), " ");
strKeyWord = new StringBuilder();
for (int i = 0; i < keywordlist.Length; i++)
{
if (strKeyWord.Length > 0)
strKeyWord.Append(" OR ");
if (GeneralConfigs.GetConfig().Fulltextsearch == 1)
{
strKeyWord.AppendFormat("CONTAINS(message, '\"*", BaseConfigs.GetTablePrefix, postTableId);
strKeyWord.Append(keywordlist[i]);
strKeyWord.Append("*\"') ");
}
else
strKeyWord.AppendFormat("[{0}posts{1}].[message] LIKE '%{2}%' ",
BaseConfigs.GetTablePrefix,
postTableId,
RegEsc(keywordlist[i]));
}
if (keywordlist.Length > 0)
sqlBuilder.Append(" AND " + strKeyWord.ToString());
sqlBuilder.AppendFormat("ORDER BY [{0}topics].", BaseConfigs.GetTablePrefix);
switch (resultOrder)
{
case 1:
sqlBuilder.Append("[tid]");
break;
case 2:
sqlBuilder.Append("[replies]");
break;
case 3:
sqlBuilder.Append("[views]");
break;
default:
sqlBuilder.Append("[lastpost]");
break;
}
return sqlBuilder.Append(resultOrderType == 1 ? " ASC" : " DESC").ToString();
}
{
StringBuilder sqlBuilder = new StringBuilder();
string orderfield = "lastpost";
switch (resultOrder)
{
case 1:
orderfield = "tid";
break;
case 2:
orderfield = "replies";
break;
case 3:
orderfield = "views";
break;
default:
orderfield = "lastpost";
break;
}
sqlBuilder.AppendFormat("SELECT DISTINCT [{0}posts{1}].[tid],[{0}topics].[{2}] FROM [{0}posts{1}] LEFT JOIN [{0}topics] ON [{0}topics].[tid]=[{0}posts{1}].[tid] WHERE [{0}topics].[displayorder]>=0 ",
BaseConfigs.GetTablePrefix,
postTableId,
orderfield);
if (searchForumId != "")
sqlBuilder.AppendFormat(" AND [{0}posts{1}].[fid] IN ({2})", BaseConfigs.GetTablePrefix, postTableId, searchForumId);
if (posterId != -1)
sqlBuilder.AppendFormat(" AND [{0}posts{1}].[posterid]={2}", BaseConfigs.GetTablePrefix, postTableId, posterId);
if (searchTime != 0)
sqlBuilder.AppendFormat(" AND [{0}posts{1}].[postdatetime] {2} '{3}'",
BaseConfigs.GetTablePrefix,
postTableId,
searchTimeType == 1 ? "<" : ">",
DateTime.Now.AddDays(searchTime).ToString("yyyy-MM-dd 00:00:00"));
string[] keywordlist = Utils.SplitString(strKeyWord.ToString(), " ");
strKeyWord = new StringBuilder();
for (int i = 0; i < keywordlist.Length; i++)
{
if (strKeyWord.Length > 0)
strKeyWord.Append(" OR ");
if (GeneralConfigs.GetConfig().Fulltextsearch == 1)
{
strKeyWord.AppendFormat("CONTAINS(message, '\"*", BaseConfigs.GetTablePrefix, postTableId);
strKeyWord.Append(keywordlist[i]);
strKeyWord.Append("*\"') ");
}
else
strKeyWord.AppendFormat("[{0}posts{1}].[message] LIKE '%{2}%' ",
BaseConfigs.GetTablePrefix,
postTableId,
RegEsc(keywordlist[i]));
}
if (keywordlist.Length > 0)
sqlBuilder.Append(" AND " + strKeyWord.ToString());
sqlBuilder.AppendFormat("ORDER BY [{0}topics].", BaseConfigs.GetTablePrefix);
switch (resultOrder)
{
case 1:
sqlBuilder.Append("[tid]");
break;
case 2:
sqlBuilder.Append("[replies]");
break;
case 3:
sqlBuilder.Append("[views]");
break;
default:
sqlBuilder.Append("[lastpost]");
break;
}
return sqlBuilder.Append(resultOrderType == 1 ? " ASC" : " DESC").ToString();
}
如果上述的构造方法所拼接出的SQL语句被顺利执行后，就会在相应的dnt_searchcaches表中生成一条记录，形如：
<ForumTopics>1,5,6,10,11,12,13,2,26,25,36,41,42,44,52,53,56,61,70,76,57,105,114,115,131,137</ForumTopics>
注：<ForumTopics>表示其是论坛搜索的结果（因为产品中同时也提供了空间相册搜索功能，所以这样加以标识）.
而dnt_searchcacheds数据字典如下（上面的ForumTopics对应表中的tids字段：text类型 ）：
然后根据这些tid记录，按分页的大小一次获取其中一段数据（比如头10条：1,5,6,10,11,12,13,2,26,25），然后再用这段tid集合作为where条件 放到类似下面的查询语句中运行，就会获取相应的主题列表了（查询结果以主题列表而不是帖子列表方式呈现，这也是为什么要在GetSearchPostContentSQL中进行distinct的原因，因为一个主题可以有多个帖子，即1:n）:
select * from dnt_topics where tid in (tid集合)
原理清楚之后，下面就是加入SPHINX查询逻辑了。因为SPHINX对全文索引进行查询时，会返回相应的documemntId,相应对帖子分表中的pid字段，所以只要将逻辑代码放到GetSearchPostContentSQL中就可以了，这里使用了配置文件开关的方式来标识是否执行SPHINX查询，如下：
private string GetSearchPostContentSQL(int posterId, string searchForumId, int resultOrder, int resultOrderType, int searchTime, int searchTimeType, int postTableId, StringBuilder strKeyWord)
{
//如果开启sphinx全文搜索时
if (!string.IsNullOrEmpty(strKeyWord.ToString()) && EntLibConfigs.GetConfig() != null && EntLibConfigs.GetConfig().Sphinxconfig.Enable)
{
return GetSphinxSqlService().GetSearchPostContentSQL(posterId, searchForumId, resultOrder, resultOrderType, searchTime, searchTimeType, postTableId, strKeyWord);
}
StringBuilder sqlBuilder = new StringBuilder();
string orderfield = "lastpost";
switch (resultOrder)
{
case 1:
orderfield = "tid";
break;
......
{
//如果开启sphinx全文搜索时
if (!string.IsNullOrEmpty(strKeyWord.ToString()) && EntLibConfigs.GetConfig() != null && EntLibConfigs.GetConfig().Sphinxconfig.Enable)
{
return GetSphinxSqlService().GetSearchPostContentSQL(posterId, searchForumId, resultOrder, resultOrderType, searchTime, searchTimeType, postTableId, strKeyWord);
}
StringBuilder sqlBuilder = new StringBuilder();
string orderfield = "lastpost";
switch (resultOrder)
{
case 1:
orderfield = "tid";
break;
......
通过上述代码，可以看出GetSphinxSqlService()这个方法就是提供SPHINX查询和数据服务的接口，该接口定义如下：
/// <summary>
/// 查询服务数据操作接口
/// </summary>
public interface ISqlService
{
/// <summary>
/// 创建Sphinx的数据表（目前只支持mysql数据库类型）
/// </summary>
/// <param name="tableName">当前分表名称</param>
/// <returns></returns>
bool CreatePostTable(string tableName);
/// <summary>
/// 创建Sphinx数据表帖子
/// </summary>
/// <param name="tableName">当前分表名称</param>
/// <param name="pid">帖子ID</param>
/// <param name="tid">主题ID</param>
/// <param name="fid">所属版块ID</param>
/// <param name="posterid">发帖人</param>
/// <param name="postdatetime">发帖日期</param>
/// <param name="title">标题</param>
/// <param name="message">内容</param>
/// <returns></returns>
int CreatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message);
/// <summary>
/// 更新Sphinx数据表帖子
/// </summary>
/// <param name="tableName">当前分表名称</param>
/// <param name="pid">帖子ID</param>
/// <param name="tid">主题ID</param>
/// <param name="fid">所属版块ID</param>
/// <param name="posterid">发帖人</param>
/// <param name="postdatetime">发帖日期</param>
/// <param name="title">标题</param>
/// <param name="message">内容</param>
/// <returns></returns>
int UpdatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message);
/// <summary>
/// 获取要搜索的主题ID(Tid)信息
/// </summary>
/// <param name="posterId">发帖者id</param>
/// <param name="searchForumId">搜索版块id</param>
/// <param name="resultOrder">结果排序方式</param>
/// <param name="resultOrderType">结果类型类型</param>
/// <param name="searchTime">搜索时间</param>
/// <param name="searchTimeType">搜索时间类型</param>
/// <param name="postTableId">当前分表ID</param>
/// <param name="strKeyWord">关键字</param>
/// <returns></returns>
string GetSearchPostContentSQL(int posterId, string searchForumId, int resultOrder, int resultOrderType, int searchTime, int searchTimeType, int postTableId, System.Text.StringBuilder strKeyWord);
}
/// 查询服务数据操作接口
/// </summary>
public interface ISqlService
{
/// <summary>
/// 创建Sphinx的数据表（目前只支持mysql数据库类型）
/// </summary>
/// <param name="tableName">当前分表名称</param>
/// <returns></returns>
bool CreatePostTable(string tableName);
/// <summary>
/// 创建Sphinx数据表帖子
/// </summary>
/// <param name="tableName">当前分表名称</param>
/// <param name="pid">帖子ID</param>
/// <param name="tid">主题ID</param>
/// <param name="fid">所属版块ID</param>
/// <param name="posterid">发帖人</param>
/// <param name="postdatetime">发帖日期</param>
/// <param name="title">标题</param>
/// <param name="message">内容</param>
/// <returns></returns>
int CreatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message);
/// <summary>
/// 更新Sphinx数据表帖子
/// </summary>
/// <param name="tableName">当前分表名称</param>
/// <param name="pid">帖子ID</param>
/// <param name="tid">主题ID</param>
/// <param name="fid">所属版块ID</param>
/// <param name="posterid">发帖人</param>
/// <param name="postdatetime">发帖日期</param>
/// <param name="title">标题</param>
/// <param name="message">内容</param>
/// <returns></returns>
int UpdatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message);
/// <summary>
/// 获取要搜索的主题ID(Tid)信息
/// </summary>
/// <param name="posterId">发帖者id</param>
/// <param name="searchForumId">搜索版块id</param>
/// <param name="resultOrder">结果排序方式</param>
/// <param name="resultOrderType">结果类型类型</param>
/// <param name="searchTime">搜索时间</param>
/// <param name="searchTimeType">搜索时间类型</param>
/// <param name="postTableId">当前分表ID</param>
/// <param name="strKeyWord">关键字</param>
/// <returns></returns>
string GetSearchPostContentSQL(int posterId, string searchForumId, int resultOrder, int resultOrderType, int searchTime, int searchTimeType, int postTableId, System.Text.StringBuilder strKeyWord);
}
设计这个接口的目的首先是解除Discuz.EntLib.dll与其它DLL文件的互相依赖。第二就是为了当本机用户发表或更新帖子信息时，会调用这个接口的中的相应方法来创建（CreatePost）或更新（UpdatePost）mysql数据库中的相应帖子记录，以确保sphinx获取索引数据的有效性。
可以通过反射的方法实例化该接口对象以便访问其中的方法，如下（GlobalManage.cs）：
#region sphinx SQL服务
private static SphinxConfig.ISqlService sphinxSqlService;
private static SphinxConfig.ISqlService GetSphinxSqlService()
{
if (sphinxSqlService == null)
{
try
{
sphinxSqlService = (SphinxConfig.ISqlService)Activator.CreateInstance(Type.GetType("Discuz.EntLib.SphinxClient.SphinxSqlService, Discuz.EntLib", false, true));
}
catch
{
throw new Exception("请检查BIN目录下有无Discuz.EntLib.dll文件");
}
}
return sphinxSqlService;
}
#endregion
private static SphinxConfig.ISqlService sphinxSqlService;
private static SphinxConfig.ISqlService GetSphinxSqlService()
{
if (sphinxSqlService == null)
{
try
{
sphinxSqlService = (SphinxConfig.ISqlService)Activator.CreateInstance(Type.GetType("Discuz.EntLib.SphinxClient.SphinxSqlService, Discuz.EntLib", false, true));
}
catch
{
throw new Exception("请检查BIN目录下有无Discuz.EntLib.dll文件");
}
}
return sphinxSqlService;
}
#endregion
而在Discuz.EntLib中提供了该接口的MYSQL类型数据库实现方法（Discuz.EntLib\SphinxClient\SphinxSqlService.cs），如下：
public class SphinxSqlService : Discuz.Config.SphinxConfig.ISqlService
{
private SphinxConfig sphinxConfig = EntLibConfigs.GetConfig().Sphinxconfig;
public int CreatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message)
{
DbParameter[] prams = {
MakeParam("?pid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, pid),
MakeParam("?tid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, tid),
MakeParam("?fid", (DbType)MySqlDbType.Int16, 2, ParameterDirection.Input, fid),
MakeParam("?posterid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, posterid),
MakeParam("?postdatetime", (DbType)MySqlDbType.VarString, 20, ParameterDirection.Input, postdatetime),
MakeParam("?title", (DbType)MySqlDbType.VarString, 60, ParameterDirection.Input, title),
MakeParam("?message", (DbType)MySqlDbType.Text, 0, ParameterDirection.Input, message)
};
string commandText = "SET NAMES utf8;INSERT INTO `" + tableName + "` (`pid`,`tid`,`fid`,`posterid`,`postdatetime`,`title`,`message`) VALUES(?pid,?tid,?fid,?posterid,?postdatetime,?title,?message)";
try
{
return TypeConverter.ObjectToInt(ExecuteScalar(commandText, prams));
}
catch
{
CreatePostTable(tableName);
return TypeConverter.ObjectToInt(ExecuteScalar(commandText, prams));
}
}
public bool CreatePostTable(string tableName)
{
EntLibConfigInfo entLibConfigInfo = EntLibConfigs.GetConfig();
//数据库MY.ini文件中也要指定或在安装实例是即指定为utf-8
//SET NAMES utf8;CREATE DATABASE IF NOT EXISTS test;
string commandText = string.Format("SET NAMES utf8;" +
"CREATE TABLE IF NOT EXISTS `{0}` (" +
"`pid` INT(11) NOT NULL ," +
"`tid` INT(11) NOT NULL ," +
"`fid` INT(11) NOT NULL ," +
"`posterid` INT(11) NOT NULL ," +
"`postdatetime` DATETIME NOT NULL," +
"`title` varchar(60) NOT NULL," +
"`message` TEXT NOT NULL," +
"PRIMARY KEY (`pid`)" +
") DEFAULT CHARSET=utf8;",
tableName);
ExecuteScalar(commandText, null);
return true;
}
public int UpdatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message)
{
DbParameter[] prams = {
MakeParam("?pid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, pid),
MakeParam("?tid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, tid),
MakeParam("?fid", (DbType)MySqlDbType.Int16, 2, ParameterDirection.Input, fid),
MakeParam("?posterid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, posterid),
MakeParam("?postdatetime", (DbType)MySqlDbType.VarString, 20, ParameterDirection.Input, postdatetime),
MakeParam("?title", (DbType)MySqlDbType.VarString, 60, ParameterDirection.Input, title),
MakeParam("?message", (DbType)MySqlDbType.Text, 0, ParameterDirection.Input, message)
};
string commandText = "SET NAMES utf8;UPDATE `" + tableName + "` SET `tid` = ?tid, `fid` = ?fid, `posterid`= ?posterid,`postdatetime` = ?postdatetime,`title` = ?title, `message` = ?message WHERE `pid` = ?pid";
try
{
return ExecuteNonQuery(commandText, prams);
}
catch
{
return 0;
}
}
public string GetSearchPostContentSQL(int posterId, string searchForumId, int resultOrder, int resultOrderType, int searchTime, int searchTimeType, int postTableId, StringBuilder strKeyWord)
{
if (string.IsNullOrEmpty(strKeyWord.ToString()))
return "";
SphinxClient cli = new SphinxClient(sphinxConfig.SphinxServiceHost, sphinxConfig.SphinxServicePort);
cli.SetLimits(0, 300000);//30万条数据（单个帖子分表一般不应超过30万条记录）
if (searchForumId != "")
cli.SetFilter("fid", TypeConverter.StrToInt(searchForumId), false);
if (posterId != -1)
cli.SetFilter("posterid", posterId, false);
if (searchTime != 0)
{
if (searchTimeType == 1) //"<" 多少天之前 即： searchTimeType == 1
cli.SetFilterRange("postdatetime", DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now.AddYears(-10)), DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now.AddDays(searchTime)), false);
else //">" 多少天之内
cli.SetFilterRange("postdatetime", DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now.AddDays(searchTime)), DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now), false);
}
if(resultOrderType == 1) //" ASC"
cli.SetGroupBy("tid", (int)ResultsGroupFunction.Attribute, "tid ASC");
else // DESC
cli.SetGroupBy("tid", (int)ResultsGroupFunction.Attribute);
cli.SetGroupDistinct("tid");
string orderBy = "";
switch (resultOrder)
{
case 1://tid
orderBy = "tid";
break;
case 2://replies
orderBy = "tid";
break;
case 3://views
orderBy = "tid";
break;
default:
orderBy = "postdatetime";
break;
}
cli.SetSortMode((int)ResultsSortMode.Extended, orderBy + (resultOrderType == 1 ? " ASC" : " DESC"));
foreach (string keyword in Utils.SplitString(strKeyWord.ToString(), " "))
{
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId);//搜索主索引
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId + "_stem");//搜索增量索引
}
cli.SetWeights(new int[] {1,100});
SphinxResult[] results = cli.RunQueries();
string postid = "";
foreach (SphinxResult sr in results)
{
foreach(SphinxMatch sphinxMatch in sr.matches)
{
if (postid.Length < 280000)//防止SQL语句过长而无法被执行，这里指定最长为28万
{
postid += sphinxMatch.docId + ",";
}
}
}
if (string.IsNullOrEmpty(postid)) //当没有搜索到任何数据时
return "";
StringBuilder sqlBuilder = new StringBuilder();
sqlBuilder.AppendFormat("SELECT [{0}posts{1}].[tid] FROM [{0}posts{1}] LEFT JOIN [{0}topics] ON [{0}topics].[tid]=[{0}posts{1}].[tid] WHERE [{0}posts{1}].[pid] IN ({2}) AND [{0}topics].[displayorder]>=0 ",
BaseConfigs.GetTablePrefix,
postTableId,
postid.TrimEnd(','));
return sqlBuilder.ToString();
}
....
}
{
private SphinxConfig sphinxConfig = EntLibConfigs.GetConfig().Sphinxconfig;
public int CreatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message)
{
DbParameter[] prams = {
MakeParam("?pid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, pid),
MakeParam("?tid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, tid),
MakeParam("?fid", (DbType)MySqlDbType.Int16, 2, ParameterDirection.Input, fid),
MakeParam("?posterid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, posterid),
MakeParam("?postdatetime", (DbType)MySqlDbType.VarString, 20, ParameterDirection.Input, postdatetime),
MakeParam("?title", (DbType)MySqlDbType.VarString, 60, ParameterDirection.Input, title),
MakeParam("?message", (DbType)MySqlDbType.Text, 0, ParameterDirection.Input, message)
};
string commandText = "SET NAMES utf8;INSERT INTO `" + tableName + "` (`pid`,`tid`,`fid`,`posterid`,`postdatetime`,`title`,`message`) VALUES(?pid,?tid,?fid,?posterid,?postdatetime,?title,?message)";
try
{
return TypeConverter.ObjectToInt(ExecuteScalar(commandText, prams));
}
catch
{
CreatePostTable(tableName);
return TypeConverter.ObjectToInt(ExecuteScalar(commandText, prams));
}
}
public bool CreatePostTable(string tableName)
{
EntLibConfigInfo entLibConfigInfo = EntLibConfigs.GetConfig();
//数据库MY.ini文件中也要指定或在安装实例是即指定为utf-8
//SET NAMES utf8;CREATE DATABASE IF NOT EXISTS test;
string commandText = string.Format("SET NAMES utf8;" +
"CREATE TABLE IF NOT EXISTS `{0}` (" +
"`pid` INT(11) NOT NULL ," +
"`tid` INT(11) NOT NULL ," +
"`fid` INT(11) NOT NULL ," +
"`posterid` INT(11) NOT NULL ," +
"`postdatetime` DATETIME NOT NULL," +
"`title` varchar(60) NOT NULL," +
"`message` TEXT NOT NULL," +
"PRIMARY KEY (`pid`)" +
") DEFAULT CHARSET=utf8;",
tableName);
ExecuteScalar(commandText, null);
return true;
}
public int UpdatePost(string tableName, int pid, int tid, int fid, int posterid, string postdatetime, string title, string message)
{
DbParameter[] prams = {
MakeParam("?pid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, pid),
MakeParam("?tid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, tid),
MakeParam("?fid", (DbType)MySqlDbType.Int16, 2, ParameterDirection.Input, fid),
MakeParam("?posterid", (DbType)MySqlDbType.Int32, 4, ParameterDirection.Input, posterid),
MakeParam("?postdatetime", (DbType)MySqlDbType.VarString, 20, ParameterDirection.Input, postdatetime),
MakeParam("?title", (DbType)MySqlDbType.VarString, 60, ParameterDirection.Input, title),
MakeParam("?message", (DbType)MySqlDbType.Text, 0, ParameterDirection.Input, message)
};
string commandText = "SET NAMES utf8;UPDATE `" + tableName + "` SET `tid` = ?tid, `fid` = ?fid, `posterid`= ?posterid,`postdatetime` = ?postdatetime,`title` = ?title, `message` = ?message WHERE `pid` = ?pid";
try
{
return ExecuteNonQuery(commandText, prams);
}
catch
{
return 0;
}
}
public string GetSearchPostContentSQL(int posterId, string searchForumId, int resultOrder, int resultOrderType, int searchTime, int searchTimeType, int postTableId, StringBuilder strKeyWord)
{
if (string.IsNullOrEmpty(strKeyWord.ToString()))
return "";
SphinxClient cli = new SphinxClient(sphinxConfig.SphinxServiceHost, sphinxConfig.SphinxServicePort);
cli.SetLimits(0, 300000);//30万条数据（单个帖子分表一般不应超过30万条记录）
if (searchForumId != "")
cli.SetFilter("fid", TypeConverter.StrToInt(searchForumId), false);
if (posterId != -1)
cli.SetFilter("posterid", posterId, false);
if (searchTime != 0)
{
if (searchTimeType == 1) //"<" 多少天之前 即： searchTimeType == 1
cli.SetFilterRange("postdatetime", DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now.AddYears(-10)), DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now.AddDays(searchTime)), false);
else //">" 多少天之内
cli.SetFilterRange("postdatetime", DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now.AddDays(searchTime)), DateTimeHelper.ConvertToUnixTimestamp(DateTime.Now), false);
}
if(resultOrderType == 1) //" ASC"
cli.SetGroupBy("tid", (int)ResultsGroupFunction.Attribute, "tid ASC");
else // DESC
cli.SetGroupBy("tid", (int)ResultsGroupFunction.Attribute);
cli.SetGroupDistinct("tid");
string orderBy = "";
switch (resultOrder)
{
case 1://tid
orderBy = "tid";
break;
case 2://replies
orderBy = "tid";
break;
case 3://views
orderBy = "tid";
break;
default:
orderBy = "postdatetime";
break;
}
cli.SetSortMode((int)ResultsSortMode.Extended, orderBy + (resultOrderType == 1 ? " ASC" : " DESC"));
foreach (string keyword in Utils.SplitString(strKeyWord.ToString(), " "))
{
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId);//搜索主索引
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId + "_stem");//搜索增量索引
}
cli.SetWeights(new int[] {1,100});
SphinxResult[] results = cli.RunQueries();
string postid = "";
foreach (SphinxResult sr in results)
{
foreach(SphinxMatch sphinxMatch in sr.matches)
{
if (postid.Length < 280000)//防止SQL语句过长而无法被执行，这里指定最长为28万
{
postid += sphinxMatch.docId + ",";
}
}
}
if (string.IsNullOrEmpty(postid)) //当没有搜索到任何数据时
return "";
StringBuilder sqlBuilder = new StringBuilder();
sqlBuilder.AppendFormat("SELECT [{0}posts{1}].[tid] FROM [{0}posts{1}] LEFT JOIN [{0}topics] ON [{0}topics].[tid]=[{0}posts{1}].[tid] WHERE [{0}posts{1}].[pid] IN ({2}) AND [{0}topics].[displayorder]>=0 ",
BaseConfigs.GetTablePrefix,
postTableId,
postid.TrimEnd(','));
return sqlBuilder.ToString();
}
....
}
上面方法中的GetSearchPostContentSQL即是SPHINX查询对象的构造和执行过程了，大家可以参照SPHINX的官方文档或之前所说的那个中文文档来查询对应的语句语法。如果该方法执行正确，就会获取一个SQL语句，该语句与SQLSERVER进行全文检索时所调用的方法返回的SQL语句结果相同。
不过上面代码中的这段代码要在这里解释一下，因为它与后面所讲述的“增量索引”是相互对应的：
foreach (string keyword in Utils.SplitString(strKeyWord.ToString(), " "))
{
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId);//搜索主索引
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId + "_stem");//搜索增量索引
}
{
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId);//搜索主索引
cli.AddQuery(keyword, BaseConfigs.GetTablePrefix + "posts" + postTableId + "_stem");//搜索增量索引
}
上面代码是执行查询时所使用的索引名称和关键字绑定，因为考虑到创建大数据量表索引时的时间会相对较长，所以这里引入了增量索引，也就是主索引中存储的是整个数据表中的索引信息（某时间段之前），而增量索引只保存指定条件（会在下文中说明）的"新记录（某时间段之后）"信息。我们可以让“创建主索引”的工作在一天中服务器最闲的时候来生成（比如凌晨4-5点钟），而增量索引每几分钟（甚至一分钟）生成一次。这样当查询时我们同时指定这两个索引来能实现“准实时”的查询效果了。
除了在搜索时调用了该服务接口的相应方法，再有就是在创建或更新帖子信息时也调用了相应方法，比如创建帖子时（Discuz.Forum\Posts.cs）：
/// <summary>
/// 创建帖子
/// </summary>
/// <param name="postInfo">帖子信息类</param>
/// <returns>返回帖子id</returns>
public static int CreatePost(PostInfo postInfo)
{
int pid = Data.Posts.CreatePost(postInfo, GetPostTableId(postInfo.Tid));
//本帖具有正反方立场
if (postInfo.Debateopinion > 0)
{
DebatePostExpandInfo dpei = new DebatePostExpandInfo();
dpei.Tid = postInfo.Tid;
dpei.Pid = pid;
dpei.Opinion = postInfo.Debateopinion;
dpei.Diggs = 0;
Data.Debates.CreateDebateExpandInfo(dpei);
}
RemoveShowTopicCache(postInfo.Tid.ToString());
//将数据同步到sphinx增量表中
if (pid > 0 && EntLibConfigs.GetConfig() != null && EntLibConfigs.GetConfig().Sphinxconfig.Enable)
{
GetSphinxSqlService().CreatePost(GetPostTableName(), pid, postInfo.Tid, postInfo.Fid, postInfo.Posterid, postInfo.Postdatetime, postInfo.Title, postInfo.Message);
}
return pid;
}
/// 创建帖子
/// </summary>
/// <param name="postInfo">帖子信息类</param>
/// <returns>返回帖子id</returns>
public static int CreatePost(PostInfo postInfo)
{
int pid = Data.Posts.CreatePost(postInfo, GetPostTableId(postInfo.Tid));
//本帖具有正反方立场
if (postInfo.Debateopinion > 0)
{
DebatePostExpandInfo dpei = new DebatePostExpandInfo();
dpei.Tid = postInfo.Tid;
dpei.Pid = pid;
dpei.Opinion = postInfo.Debateopinion;
dpei.Diggs = 0;
Data.Debates.CreateDebateExpandInfo(dpei);
}
RemoveShowTopicCache(postInfo.Tid.ToString());
//将数据同步到sphinx增量表中
if (pid > 0 && EntLibConfigs.GetConfig() != null && EntLibConfigs.GetConfig().Sphinxconfig.Enable)
{
GetSphinxSqlService().CreatePost(GetPostTableName(), pid, postInfo.Tid, postInfo.Fid, postInfo.Posterid, postInfo.Postdatetime, postInfo.Title, postInfo.Message);
}
return pid;
}
和更新帖子时：
/// <summary>
/// 更新指定帖子信息
/// </summary>
/// <param name="postsInfo">帖子信息</param>
/// <returns>更新数量</returns>
public static int UpdatePost(PostInfo postInfo)
{
if (postInfo == null || postInfo.Pid < 1)
return 0;
RemoveShowTopicCache(postInfo.Tid.ToString());
//将数据同步到sphinx增量表中
if (postInfo.Pid > 0 && EntLibConfigs.GetConfig() != null && EntLibConfigs.GetConfig().Sphinxconfig.Enable)
{
GetSphinxSqlService().UpdatePost(GetPostTableName(), postInfo.Pid, postInfo.Tid, postInfo.Fid, postInfo.Posterid, postInfo.Postdatetime, postInfo.Title, postInfo.Message);
}
return Data.Posts.UpdatePost(postInfo, GetPostTableId(postInfo.Tid));
}
/// 更新指定帖子信息
/// </summary>
/// <param name="postsInfo">帖子信息</param>
/// <returns>更新数量</returns>
public static int UpdatePost(PostInfo postInfo)
{
if (postInfo == null || postInfo.Pid < 1)
return 0;
RemoveShowTopicCache(postInfo.Tid.ToString());
//将数据同步到sphinx增量表中
if (postInfo.Pid > 0 && EntLibConfigs.GetConfig() != null && EntLibConfigs.GetConfig().Sphinxconfig.Enable)
{
GetSphinxSqlService().UpdatePost(GetPostTableName(), postInfo.Pid, postInfo.Tid, postInfo.Fid, postInfo.Posterid, postInfo.Postdatetime, postInfo.Title, postInfo.Message);
}
return Data.Posts.UpdatePost(postInfo, GetPostTableId(postInfo.Tid));
}
到这时，架构中的Discuz!NT客户端部分甚本上就介绍完了。下一篇文章中将会介绍在服务器如果安装，配置SPHINX以及定时生成主和增量索引等工作。
原文链接:http://www.cnblogs.com/daizhj/archive/2010/06/28/discuznt_entlib_sphinx_one.html
BLOG: http://daizhj.cnblogs.com/
作者:daizhj,代震军