我正在使用C#导入一个拥有六到八百万行的CSV文件。
我的数据表长这样:
CREATE TABLE [Data] ([ID] VARCHAR(100) NULL,[Raw] VARCHAR(200) NULL)
CREATE INDEX IDLookup ON Data(ID ASC)
我正在使用System.Data.SQLite进行导入。
目前在Windows 7 32位,Core2Duo 2.8GHz和4GB RAM上,处理600万行需要2分55秒。虽然这已经不错了,但我想知道是否有更快的导入方式。
这是我的代码:
public class Data
{
public string IDData { get; set; }
public string RawData { get; set; }
}
string connectionString = @"Data Source=" + Path.GetFullPath(AppDomain.CurrentDomain.BaseDirectory + "\\dbimport");
System.Data.SQLite.SQLiteConnection conn = new System.Data.SQLite.SQLiteConnection(connectionString);
conn.Open();
//Dropping and recreating the table seems to be the quickest way to get old data removed
System.Data.SQLite.SQLiteCommand command = new System.Data.SQLite.SQLiteCommand(conn);
command.CommandText = "DROP TABLE Data";
command.ExecuteNonQuery();
command.CommandText = @"CREATE TABLE [Data] ([ID] VARCHAR(100) NULL,[Raw] VARCHAR(200) NULL)";
command.ExecuteNonQuery();
command.CommandText = "CREATE INDEX IDLookup ON Data(ID ASC)";
command.ExecuteNonQuery();
string insertText = "INSERT INTO Data (ID,RAW) VALUES(@P0,@P1)";
SQLiteTransaction trans = conn.BeginTransaction();
command.Transaction = trans;
command.CommandText = insertText;
Stopwatch sw = new Stopwatch();
sw.Start();
using (CsvReader csv = new CsvReader(new StreamReader(@"C:\Data.txt"), false))
{
var f = csv.Select(x => new Data() { IDData = x[27], RawData = String.Join(",", x.Take(24)) });
foreach (var item in f)
{
command.Parameters.AddWithValue("@P0", item.IDData);
command.Parameters.AddWithValue("@P1", item.RawData);
command.ExecuteNonQuery();
}
}
trans.Commit();
sw.Stop();
Debug.WriteLine(sw.Elapsed.Minutes + "Min(s) " + sw.Elapsed.Seconds + "Sec(s)");
conn.Close();