Linq 和DefaultView两种方法去掉DataTable 里的重复行
在做项目的时候经常会遇到DataTable 里的数据重复,或者合并两个DataTable后有数据重复
一般我们是想把重复的删除掉,还有其它的方式实现比如用Linq和DataTable的DefaultView来去掉重复的行
做了一个小例子,很简单的大家可以看一下,最后有完整的代码
也可以直接下载工程:RemoveDupRowDemo.rar
先看一下效果
先写一个数据源
DataTable _dt = new DataTable();
_dt.Columns.Add("id", typeof(int));
_dt.Columns.Add("name", typeof(string));
_dt.Columns.Add("address", typeof(string));
DataRow _dr = _dt.NewRow();
_dr["id"] = 1;
_dr["name"] = "lipeng";
_dr["address"] = "DongXiaoKou";
_dt.Rows.Add(_dr);
_dt.Rows.Add(_dr.ItemArray);
_dt.Rows.Add(_dr.ItemArray);
_dr = _dt.NewRow();
_dr["id"] = 2;
_dr["name"] = "xiaoNa";
_dr["address"] = "DongXiaoKou";
_dt.Rows.Add(_dr);
_dr = _dt.NewRow();
_dr["id"] = 3;
_dr["name"] = "BingLi";
_dr["address"] = "TianTongYuan";
_dt.Rows.Add(_dr);
_dt.Rows.Add(_dr.ItemArray);
Console.WriteLine("--------------------原来有重复数据的Table----------------------");
_dt.AsEnumerable().ToList().ForEach(
x =>
{
Console.WriteLine(x["id"].ToString() + " " + x["name"].ToString() + " " + x["address"].ToString());
});
Console.WriteLine();
先用Linq的Distinct方法实现,因为每行有好多列,要实现IEqualityComparer<T>接口
public class DataTableRowCompare : IEqualityComparer<DataRow> { #region IEqualityComparer<DataRow> 成员 public bool Equals(DataRow x, DataRow y) { return (x.Field<int>("id") == y.Field<int>("id")); } public int GetHashCode(DataRow obj) { return obj.ToString().GetHashCode(); } #endregion }
在Main里实现 吧
Console.WriteLine("--------------------用Linq去重复后的Table----------------------"); var _comPresult = _dt.AsEnumerable().Distinct(new DataTableRowCompare()); DataTable _resultDt = _comPresult.CopyToDataTable(); _resultDt.AsEnumerable().ToList().ForEach( x => { Console.WriteLine(x["id"].ToString() + " " + x["name"].ToString() + " " + x["address"].ToString()); }); Console.WriteLine();
用Table里的DefalutView实面DefalutView有个ToTable方法可以做到去重复
Console.WriteLine("--------------------用DefaultView去重复后的Table----------------------"); DataTable _dtDefalut = _dt.DefaultView.ToTable(true, "id", "name", "address"); _dtDefalut.AsEnumerable().ToList().ForEach( x => { Console.WriteLine(x["id"].ToString() + " " + x["name"].ToString() + " " + x["address"].ToString()); }); Console.ReadLine();
个人感觉 还是Linq的好一点,用DefaultView如果你的列少的话还好些,如果列太多的话工作量就太大了
下面给一下完整的代码
using System; using System.Collections.Generic; using System.Linq; using System.Text; using System.Data; namespace RemoveDupRowDemo { class Program { static void Main(string[] args) { DataTable _dt = new DataTable(); _dt.Columns.Add("id", typeof(int)); _dt.Columns.Add("name", typeof(string)); _dt.Columns.Add("address", typeof(string)); DataRow _dr = _dt.NewRow(); _dr["id"] = 1; _dr["name"] = "lipeng"; _dr["address"] = "DongXiaoKou"; _dt.Rows.Add(_dr); _dt.Rows.Add(_dr.ItemArray); _dt.Rows.Add(_dr.ItemArray); _dr = _dt.NewRow(); _dr["id"] = 2; _dr["name"] = "xiaoNa"; _dr["address"] = "DongXiaoKou"; _dt.Rows.Add(_dr); _dr = _dt.NewRow(); _dr["id"] = 3; _dr["name"] = "BingLi"; _dr["address"] = "TianTongYuan"; _dt.Rows.Add(_dr); _dt.Rows.Add(_dr.ItemArray); Console.WriteLine("--------------------原来有重复数据的Table----------------------"); _dt.AsEnumerable().ToList().ForEach( x => { Console.WriteLine(x["id"].ToString() + " " + x["name"].ToString() + " " + x["address"].ToString()); }); Console.WriteLine(); Console.WriteLine("--------------------用Linq去重复后的Table----------------------"); var _comPresult = _dt.AsEnumerable().Distinct(new DataTableRowCompare()); DataTable _resultDt = _comPresult.CopyToDataTable(); _resultDt.AsEnumerable().ToList().ForEach( x => { Console.WriteLine(x["id"].ToString() + " " + x["name"].ToString() + " " + x["address"].ToString()); }); Console.WriteLine(); Console.WriteLine("--------------------用DefaultView去重复后的Table----------------------"); DataTable _dtDefalut = _dt.DefaultView.ToTable(true, "id", "name", "address"); _dtDefalut.AsEnumerable().ToList().ForEach( x => { Console.WriteLine(x["id"].ToString() + " " + x["name"].ToString() + " " + x["address"].ToString()); }); Console.ReadLine(); } } public class DataTableRowCompare : IEqualityComparer<DataRow> { #region IEqualityComparer<DataRow> 成员 public bool Equals(DataRow x, DataRow y) { return (x.Field<int>("id") == y.Field<int>("id")); } public int GetHashCode(DataRow obj) { return obj.ToString().GetHashCode(); } #endregion } }