数据列表过滤重复值几种方法的性能比较

一.测试数据10 0000,过滤后结果只9810条

二.算法说明

方法一:用hashtable来保存数据列表,用hashtable的ContainsKey来判断是否重复来过滤.

方法二:用string的contains来判断是否重复来过滤.

三.算法代码

/// <summary>
        /// 方法一.用hashtable来过滤重复值
        /// </summary>
        /// <param name="sender"></param>
        /// <param name="e"></param>
        protected void Button1_Click(object sender, EventArgs e)
        {
            DateTime begin = DateTime.Now;
            Hashtable hash = new Hashtable();            
            ds = SqlHelper.ExecuteDataset(DBstr, CommandType.Text, sql);
            //过滤机制
            int len = ds.Tables[0].Rows.Count;
           // string tmp = "";
            for (int i = 0; i < len; i++)
            {
                if (!hash.ContainsKey(ds.Tables[0].Rows[i][0]))
                {                   
                    hash.Add(ds.Tables[0].Rows[i][0], ds.Tables[0].Rows[i][0]);                  
                }

            }     
            DataTable dt = new DataTable();
            DataColumn dcValue = new DataColumn("value", typeof(string));
            dt.Columns.Add(dcValue);
            //取得hasttable中的数据放到datatable中            
            IDictionaryEnumerator myEnumerator = hash.GetEnumerator();
            while (myEnumerator.MoveNext())
            {
                dt.Rows.Add(new string[] { Convert.ToString(myEnumerator.Key)});
            }            
            //绑定数据
            
            GridView1.DataSource = dt;
            GridView1.DataBind();
            ;
            lblmsg.Text = string.Format("共:{0}条,耗时:{1}", dt.Rows.Count, ((double)(((TimeSpan)(DateTime.Now - begin)).TotalSeconds)).ToString());
        }

        /// <summary>
        ///方法二. 采用string的Contains来过滤重复值
        /// </summary>
        /// <param name="sender"></param>
        /// <param name="e"></param>
        protected void Button2_Click(object sender, EventArgs e)
        {
            DateTime begin = DateTime.Now;
            StringBuilder strfilter = new StringBuilder();
            ds = SqlHelper.ExecuteDataset(DBstr, CommandType.Text, sql);
            //过滤机制
            int len = ds.Tables[0].Rows.Count;
            // string tmp = "";
            DataTable dt = new DataTable();
            DataColumn dcValue = new DataColumn("value", typeof(string));
            dt.Columns.Add(dcValue);
            for (int i = 0; i < len; i++)
            {               
                if (!("|" + strfilter.ToString()).Contains("|" + ds.Tables[0].Rows[i][0].ToString() + "|"))
                {
                     dt.Rows.Add(ds.Tables[0].Rows[i][0]);
                     strfilter.Append(ds.Tables[0].Rows[i][0].ToString() + "|");
                }
            }
            GridView1.DataSource = dt;
            GridView1.DataBind();
            ;
            lblmsg.Text = string.Format("共:{0}条,耗时:{1}", dt.Rows.Count, ((double)(((TimeSpan)(DateTime.Now - begin)).TotalSeconds)).ToString());

        }

四.测试结果

五.结论

在数据过滤过程中用hashtable性能明显优于string的contains或indexOf的方法.