查询在 SQL Server 中工作，但在 RODBC 中不工作

Question

我正在尝试在RODBC 中运行以下查询：

library(RODBC)

sql <- paste("SELECT * INTO #DataQuery FROM ( SELECT * FROM [DSMM_PPCreporting].[dbo].[DSMM_FACT_TABLE] WITH (NOLOCK)  WHERE [DSMM_FACT_TABLE].Client_ID = 85 AND VenueSource=1   AND TimeStamp BETWEEN  '10/1/2014' AND '10/13/2014' AND Venue_ID in (1,14)) xxxx") 
sql <- paste(sql, "SELECT Timestamp as Date, isnull(FlexCategory.FlexCategoryName,'UNASSIGNED') AS [Flex Category], isnull(Venue.Venue,'UNASSIGNED') AS [Venue], isnull(CategoryName,'UNASSIGNED') AS [Campaign], isnull(Device,'UNASSIGNED') AS [Device], ")
sql <- paste(sql, "round(SUM(isNull(cost,0)),2) AS [Cost ($)],SUM(isNull(VenueConversions1PC,0)) +SUM(isNull(VenueConversions,0))  AS [Venue Leads] ")
sql <- paste(sql, "INTO #FlexCategory FROM #DataQuery DSMM_FACT_TABLE WITH (NOLOCK) ")
sql <- paste(sql, "LEFT JOIN Device WITH (NOLOCK) ON DSMM_FACT_TABLE.Device_ID = Device.Device_ID") 
sql <- paste(sql, "LEFT JOIN Venue WITH (NOLOCK) ON DSMM_FACT_TABLE.Venue_ID = Venue.Venue_ID")
sql <- paste(sql, "LEFT JOIN Category WITH (NOLOCK) ON DSMM_FACT_TABLE.Category_ID = Category.Category_ID")
sql <- paste(sql, "LEFT JOIN FlexCategory WITH (NOLOCK) ON Category.FlexCategory_ID = FlexCategory.FlexCategory_ID")
sql <- paste(sql, "GROUP BY Timestamp, isnull(FlexCategory.FlexCategoryName,'UNASSIGNED') ,")
sql <- paste(sql, "isnull(CategoryName,'UNASSIGNED'), ")
sql <- paste(sql, "isnull(Venue.Venue,'UNASSIGNED'),")
sql <- paste(sql, " isnull(Device,'UNASSIGNED')")
sql <- paste(sql, "ORDER BY [Venue Leads] DESC")
sql <- paste(sql, "SELECT * FROM #FlexCategory WITH (NOLOCK)")
##sql <- paste(sql, "DROP TABLE #FlexCategory")
##sql <- paste(sql, "DROP TABLE #DataQuery")

# Connecting R to DSMM and running the SQL query there
connect <- odbcConnect("DSMM")
system.time(Data <- sqlQuery(connect, sql))
close(connect)

此查询在 Microsoft SQL Server 中完美运行：

SELECT * INTO #DataQuery FROM ( SELECT * FROM [DSMM_PPCreporting].[dbo].[DSMM_FACT_TABLE] WITH (NOLOCK)  WHERE [DSMM_FACT_TABLE].Client_ID = 85 AND VenueSource=1   AND TimeStamp BETWEEN  '10/1/2014' AND '10/13/2014' AND Venue_ID in (1,14)) xxxx SELECT Timestamp as Date, isnull(FlexCategory.FlexCategoryName,'UNASSIGNED') AS [Flex Category], isnull(Venue.Venue,'UNASSIGNED') AS [Venue], isnull(CategoryName,'UNASSIGNED') AS [Campaign], isnull(Device,'UNASSIGNED') AS [Device],  round(SUM(isNull(cost,0)),2) AS [Cost ($)],SUM(isNull(VenueConversions1PC,0)) +SUM(isNull(VenueConversions,0))  AS [Venue Leads]  INTO #FlexCategory FROM #DataQuery DSMM_FACT_TABLE WITH (NOLOCK)  LEFT JOIN Device WITH (NOLOCK) ON DSMM_FACT_TABLE.Device_ID = Device.Device_ID LEFT JOIN Venue WITH (NOLOCK) ON DSMM_FACT_TABLE.Venue_ID = Venue.Venue_ID LEFT JOIN Category WITH (NOLOCK) ON DSMM_FACT_TABLE.Category_ID = Category.Category_ID LEFT JOIN FlexCategory WITH (NOLOCK) ON Category.FlexCategory_ID = FlexCategory.FlexCategory_ID GROUP BY Timestamp, isnull(FlexCategory.FlexCategoryName,'UNASSIGNED') , isnull(CategoryName,'UNASSIGNED'),  isnull(Venue.Venue,'UNASSIGNED'),  isnull(Device,'UNASSIGNED') ORDER BY [Venue Leads] DESC SELECT * FROM #FlexCategory WITH (NOLOCK)

我知道我的 SQL 连接运行良好，并且我使用的另一个查询运行良好，例如以下代码在 R 中运行良好，并将数据框加载到全局环境中：

sql <- "SELECT  TK_ID, Client_ID, tk.searchterm_id, SearchTerm,  RegionName, CityName, Timestamp FROM [DSMM_PPCreporting].[dbo].[tk] "
sql <- paste(sql, "left join [DSMM_PPCreporting].[dbo].searchterm (nolock) on [DSMM_PPCreporting].[dbo].tk.searchterm_id=[DSMM_PPCreporting].[dbo].searchterm.searchterm_id ")
sql <- paste(sql, "left join [DSMM_PPCreporting].[dbo].Region (nolock) on [DSMM_PPCreporting].[dbo].tk.Region_ID=[DSMM_PPCreporting].[dbo].Region.Region_ID ")
sql <- paste(sql, "left join [DSMM_PPCreporting].[dbo].City (nolock) on [DSMM_PPCreporting].[dbo].tk.city_id=[DSMM_PPCreporting].[dbo].city.city_ID ")
#sql <- paste(sql, "where convert(Date, [LastUpdate]) = dateadd(day, datediff(day, 1, GETDATE()), 0)") 
sql <- paste(sql, "where convert(Date, [LastUpdate]) >= '2014-10-15' and convert(Date, [LastUpdate]) <= dateadd(day, datediff(day, 1, GETDATE()), 0)")
# Connecting R to DSMM and running the SQL query there
connect <- odbcConnect("DSMM")
system.time(Data <- sqlQuery(connect, sql))
close(connect)

我知道一些SQL server 命令在RODBC 中不起作用，这可能是问题吗？如果是这样，有人可以向我指出哪些SQL 服务器函数在RODBC 中不起作用，所以生病尝试更改查询（如果可能）。

我试图找到一些关于哪些 SQL Server 命令在 RODBC 中不起作用的信息，但没有任何成功。

Answer 1

我在 ingres 数据库上使用 RJDBC 时遇到了类似的问题，我认为原因是内存问题。

我正在使用内部选择从 R 中运行一个大型查询（这也会有大量数据）。它不起作用并返回类似

的错误

.verify.JDBC.result(r, "Unable to retrieve JDBC result set for "..中的错误..

直接在数据库上运行相同的查询工作得非常好（虽然花了一段时间）。起初我还认为它可能是内部选择。但是，我有另一个带有内部选择的查询，它工作正常，当我只运行内部选择中的部分时，它也不起作用。

我断定这是内存问题，因为后来，当使用数据库的用户减少时，确实从 R 运行了相同的查询（现在仍然如此）。 当然不是 RODBC 或 RJDBC 不支持内部选择。我已经使用了两种配置的内部选择，它们工作正常。

对我来说，这个查询通过内部选择获得了特别大量的数据。我认为这就是为什么我可以同时运行另一个类似的查询，只使用更小的时间范围（因此内部选择获得的数据更少）。 希望这有助于找出问题所在。

Answer 2

似乎RODBC 不支持内部选择语句：

此代码有效：

sql <- paste("SELECT TimeStamp FROM [DSMM_PPCreporting].[dbo].[DSMM_FACT_TABLE]  WHERE [DSMM_FACT_TABLE].Client_ID = 85 AND VenueSource=1   AND TimeStamp BETWEEN  '10/1/2014' AND '10/13/2014' AND Venue_ID in (1,14)") 
connect <- odbcConnect("DSMM")
Data <- sqlQuery(connect, sql)
close(connect)

虽然不是这样：

sql <- paste("SELECT *  FROM (SELECT TimeStamp FROM [DSMM_PPCreporting].[dbo].[DSMM_FACT_TABLE]  WHERE [DSMM_FACT_TABLE].Client_ID = 85 AND VenueSource=1   AND TimeStamp BETWEEN  '10/1/2014' AND '10/13/2014' AND Venue_ID in (1,14))") 
connect <- odbcConnect("DSMM")
Data <- sqlQuery(connect, sql)
close(connect)