过滤,合并,排序和页面数据从多个来源
本文关键字:数据 合并 排序 过滤 | 更新日期: 2023-09-27 18:17:09
此刻,我正在通过一种方法从DB检索数据,该方法检索IQueryable<T1>
,过滤,排序然后分页它(基本上所有这些都在DB上),然后将结果返回给UI以显示在分页表中。
我需要从另一个DB集成结果,分页似乎是主要问题。
- 模型相似但不相同(相同的字段,不同的名称,在返回之前需要映射到通用领域模型);
- 不可能在DB级别加入;
- 目前在两个db之间有~1000条记录(在(过去18个月),并且可能以基本相同的速度增长(缓慢)。速度;
- 结果总是需要按1-2个字段(日期方向)排序。
我目前在这两种解决方案之间摇摆不定:
- 从两个来源检索所有数据,合并,排序,然后缓存它们;然后在接收请求时简单地过滤和页面所述缓存-但是当集合被修改时,我需要使缓存无效(我可以);
- 过滤每个源上的数据(再次,在DB级别),然后检索,合并,排序&在返回之前呼叫他们。
我正在寻找一个体面的算法性能方面。理想的解决方案可能是两者的结合(缓存+ DB级别的过滤),但我目前还没有考虑到这一点。
我认为你可以使用以下算法。假设页面大小为10,那么对于第0页:
- 从数据库A中获得10个结果,在db级别进行过滤和排序。
- 从数据库B中获得10个结果,在db级别进行过滤和排序(与上述查询并行)
- 将这两个结果组合起来,以正确的排序顺序获得10条记录。所以你有20条记录排序,但只取前10条并显示在UI
第1页:
- 请注意,在上一步中,您使用了多少项从数据库A和B中显示在UI中。例如,您使用了数据库A中的2项和数据库b中的8项。
- 从数据库A获得10个结果,经过过滤和排序,但从位置2开始(跳过2),因为这两个你已经在UI中显示了。
- 从数据库B中获得10个结果,经过过滤和排序,但从位置8开始(跳过8)。
- 与上面相同的方式合并,从20条记录中获得10条。假设现在您使用了来自A的5件物品和来自b的5件物品。现在,您总共显示了来自A的7件物品和来自b的13件物品。使用这些数字作为下一步。
这将不允许(容易地)跳过页面,但据我所知,这不是一个要求。
性能应该与查询单个数据库时的性能相同,因为对A和B的查询可以并行进行。
我在这里创建了一些东西,如果需要,我会回来解释。我不确定我的算法是否适用于所有的边缘情况,它涵盖了我想要的所有情况,但你永远不知道。我将把代码留在这里供您欣赏,我会回答并解释那里所做的事情,如果您需要,请留下评论。
并对值之间存在较大差距的项目列表执行多次测试。
using System;
using System.Collections.Generic;
using System.Linq;
namespace ConsoleApplication1
{
class Program
{
//each time when this objects are accessed, consider as a database call
private static IQueryable<model1> dbsetModel_1;
private static IQueryable<model2> dbsetModel_2;
private static void InitDBSets()
{
var rnd = new Random();
List<model1> dbsetModel1 = new List<model1>();
List<model2> dbsetModel2 = new List<model2>();
for (int i = 1; i < 300; i++)
{
if (i % 2 == 0)
{
dbsetModel1.Add(new model1() { Id = i, OrderNumber = rnd.Next(1, 10), Name = "Test " + i.ToString() });
}
else
{
dbsetModel2.Add(new model2() { Id2 = i, OrderNumber2 = rnd.Next(1, 10), Name2 = "Test " + i.ToString() });
}
}
dbsetModel_1 = dbsetModel1.AsQueryable();
dbsetModel_2 = dbsetModel2.AsQueryable();
}
public static void Main()
{
//generate sort of db data
InitDBSets();
//test
var result2 = GetPage(new PagingFilter() { Page = 5, Limit = 10 });
var result3 = GetPage(new PagingFilter() { Page = 6, Limit = 10 });
var result5 = GetPage(new PagingFilter() { Page = 7, Limit = 10 });
var result6 = GetPage(new PagingFilter() { Page = 8, Limit = 10 });
var result7 = GetPage(new PagingFilter() { Page = 4, Limit = 20 });
var result8 = GetPage(new PagingFilter() { Page = 200, Limit = 10 });
}
private static PagedList<Item> GetPage(PagingFilter filter)
{
int pos = 0;
//load only start pages intervals margins from both database
//this part need to be transformed in a stored procedure on db one, skip, take to return interval start value for each frame
var framesBordersModel1 = new List<Item>();
dbsetModel_1.OrderBy(x => x.Id).ThenBy(z => z.OrderNumber).ToList().ForEach(i => {
pos++;
if (pos - 1 == 0)
{
framesBordersModel1.Add(new Item() { criteria1 = i.Id, criteria2 = i.OrderNumber, model = i });
}
else if ((pos - 1) % filter.Limit == 0)
{
framesBordersModel1.Add(new Item() { criteria1 = i.Id, criteria2 = i.OrderNumber, model = i });
}
});
pos = 0;
//this part need to be transformed in a stored procedure on db two, skip, take to return interval start value for each frame
var framesBordersModel2 = new List<Item>();
dbsetModel_2.OrderBy(x => x.Id2).ThenBy(z => z.OrderNumber2).ToList().ForEach(i => {
pos++;
if (pos - 1 == 0)
{
framesBordersModel2.Add(new Item() { criteria1 = i.Id2, criteria2 = i.OrderNumber2, model = i });
}
else if ((pos -1) % filter.Limit == 0)
{
framesBordersModel2.Add(new Item() { criteria1 = i.Id2, criteria2 = i.OrderNumber2, model = i });
}
});
//decide where is the position of your cursor based on start margins
//int mainCursor = 0;
int cursor1 = 0;
int cursor2 = 0;
//filter pages start from 1, filter.Page cannot be 0, if indeed you have page 0 change a lil' bit he logic
if (framesBordersModel1.Count + framesBordersModel2.Count < filter.Page) throw new Exception("Out of range");
while ( cursor1 + cursor2 < filter.Page -1)
{
if (framesBordersModel1[cursor1].criteria1 < framesBordersModel2[cursor2].criteria1)
{
cursor1++;
}
else if (framesBordersModel1[cursor1].criteria1 > framesBordersModel2[cursor2].criteria1)
{
cursor2++;
}
//you should't get here case main key sound't be duplicate, annyhow
else
{
if (framesBordersModel1[cursor1].criteria2 < framesBordersModel2[cursor2].criteria2)
{
cursor1++;
}
else
{
cursor2++;
}
}
//mainCursor++;
}
//magic starts
//inpar skipable
int skipEndResult = 0;
List<Item> dbFramesMerged = new List<Item>();
if ((cursor1 + cursor2) %2 == 0)
{
dbFramesMerged.AddRange(
dbsetModel_1.OrderBy(x => x.Id)
.ThenBy(z => z.OrderNumber)
.Skip(cursor1*filter.Limit)
.Take(filter.Limit)
.Select(x => new Item() {criteria1 = x.Id, criteria2 = x.OrderNumber, model = x})
.ToList()); //consider as db call EF or Stored Procedure
dbFramesMerged.AddRange(
dbsetModel_2.OrderBy(x => x.Id2)
.ThenBy(z => z.OrderNumber2)
.Skip(cursor2*filter.Limit)
.Take(filter.Limit)
.Select(x => new Item() {criteria1 = x.Id2, criteria2 = x.OrderNumber2, model = x})
.ToList());
; //consider as db call EF or Stored Procedure
}
else
{
skipEndResult = filter.Limit;
if (cursor1 > cursor2)
{
cursor1--;
}
else
{
cursor2--;
}
dbFramesMerged.AddRange(
dbsetModel_1.OrderBy(x => x.Id)
.ThenBy(z => z.OrderNumber)
.Skip(cursor1 * filter.Limit)
.Take(filter.Limit)
.Select(x => new Item() { criteria1 = x.Id, criteria2 = x.OrderNumber, model = x })
.ToList()); //consider as db call EF or Stored Procedure
dbFramesMerged.AddRange(
dbsetModel_2.OrderBy(x => x.Id2)
.ThenBy(z => z.OrderNumber2)
.Skip(cursor2 * filter.Limit)
.Take(filter.Limit)
.Select(x => new Item() { criteria1 = x.Id2, criteria2 = x.OrderNumber2, model = x })
.ToList());
}
IQueryable<Item> qItems = dbFramesMerged.AsQueryable();
PagedList<Item> result = new PagedList<Item>();
result.AddRange(qItems.OrderBy(x => x.criteria1).ThenBy(z => z.criteria2).Skip(skipEndResult).Take(filter.Limit).ToList());
//here again you need db cals to get total count
result.Total = dbsetModel_1.Count() + dbsetModel_2.Count();
result.Limit = filter.Limit;
result.Page = filter.Page;
return result;
}
}
public class PagingFilter
{
public int Limit { get; set; }
public int Page { get; set; }
}
public class PagedList<T> : List<T>
{
public int Total { get; set; }
public int? Page { get; set; }
public int? Limit { get; set; }
}
public class Item : Criteria
{
public object model { get; set; }
}
public class Criteria
{
public int criteria1 { get; set; }
public int criteria2 { get; set; }
//more criterias if you need to order
}
public class model1
{
public int Id { get; set; }
public int OrderNumber { get; set; }
public string Name { get; set; }
}
public class model2
{
public int Id2 { get; set; }
public int OrderNumber2 { get; set; }
public string Name2 { get; set; }
}
}