在MySQL中删除重复数据

这就是我最终要做的事情。我和我的同事提出了一个查询，该查询将为我们提供具有重复数据的Event_ID列表（我们实际上使用了Access 2010的查询生成器，并对其进行了MySQL验证）。请记住，这是一个完整的解决方案，其中原始问题没有链接表那么详细。如果您对此有疑问，请随时提出，我将尽力帮助您：

SELECT `Events_new`.`Event_ID`
    FROM Events_new
    GROUP BY `Events_new`.`PCBID`, `Events_new`.`EventType_ID`, `Events_new`.`DateTime`, `Events_new`.`User`
    HAVING (((COUNT(`Events_new`.`PCBID`)) > 1) AND ((COUNT(`Events_new`.`User`)) > 1) AND ((COUNT(`Events_new`.`DateTime`)) > 1))

由此，我Event_ID以迭代的方式处理了每个重复项以删除重复项。基本上，我必须删除从最低的最后一张表开始的所有子行，以免受到外键约束的影响。

这部分代码是用LinqPAD作为C＃语句编写的：（sbCommonFunctions是一个内部DLL，旨在使大多数（但并非全部）数据库函数以相同或更简单的方式处理）

sbCommonFunctions.Database testDB = new sbCommonFunctions.Database();
testDB.Connect("production", "database", "user", "password");
List<string> listEventIDs = new List<string>();
List<string> listEventDetailIDs = new List<string>();
List<string> listTestInformationIDs = new List<string>();
List<string> listTestStepIDs = new List<string>();
List<string> listMeasurementIDs = new List<string>();
string dtQuery = (String.Format(@"SELECT `Events_new`.`Event_ID`
        FROM Events_new
        GROUP BY `Events_new`.`PCBID`,
        `Events_new`.`EventType_ID`,
        `Events_new`.`DateTime`,
        `Events_new`.`User`
        HAVING (((COUNT(`Events_new`.`PCBID`)) > 1)
        AND ((COUNT(`Events_new`.`User`)) > 1) 
        AND ((COUNT(`Events_new`.`DateTime`)) > 1))"));

int iterations = 0;
DataTable dtEventIDs = getDT(dtQuery, testDB);
while (dtEventIDs.Rows.Count > 0)
{
    Console.WriteLine(dtEventIDs.Rows.Count);
    Console.WriteLine(iterations);
    iterations++;
    foreach(DataRowView eventID in dtEventIDs.DefaultView)
    {
        listEventIDs.Add(eventID.Row[0].ToString());
        DataTable dtEventDetails = testDB.QueryDatabase(String.Format(
        "SELECT * FROM EventDetails_new WHERE Event_ID = {0}",
           eventID.Row[0]));
        foreach(DataRowView drvEventDetail in dtEventDetails.DefaultView)
        {
            listEventDetailIDs.Add(drvEventDetail.Row[0].ToString());
        }   
        DataTable dtTestInformation = testDB.QueryDatabase(String.Format(
        @"SELECT TestInformation_ID 
        FROM TestInformation_new 
        WHERE Event_ID = {0}",
            eventID.Row[0]));
        foreach(DataRowView drvTest in dtTestInformation.DefaultView)
        {
            listTestInformationIDs.Add(drvTest.Row[0].ToString());
            DataTable dtTestSteps = testDB.QueryDatabase(String.Format(
            @"SELECT TestSteps_ID 
            FROM TestSteps_new 
            WHERE TestInformation_TestInformation_ID = {0}",
               drvTest.Row[0]));
            foreach(DataRowView drvTestStep in dtTestSteps.DefaultView)
            {
                listTestStepIDs.Add(drvTestStep.Row[0].ToString());
                DataTable dtMeasurements = testDB.QueryDatabase(String.Format(
                @"SELECT Measurements_ID 
                FROM Measurements_new 
                WHERE TestSteps_TestSteps_ID = {0}",
                   drvTestStep.Row[0]));
                foreach(DataRowView drvMeasurements in dtMeasurements.DefaultView)
                {
                    listMeasurementIDs.Add(drvMeasurements.Row[0].ToString());
                }
            }
        }
    }
    testDB.Disconnect();
    string mysqlConnection = 
    "server=server;\ndatabase=database;\npassword=password;\nUser ID=user;";
    MySqlConnection connection = new MySqlConnection(mysqlConnection);
    connection.Open();
    //start unwinding the duplicates from the lowest level upward
    whackDuplicates(listMeasurementIDs, "measurements_new", "Measurements_ID", connection);
    whackDuplicates(listTestStepIDs, "teststeps_new", "TestSteps_ID", connection);
    whackDuplicates(listTestInformationIDs, "testinformation_new", "testInformation_ID", connection);
    whackDuplicates(listEventDetailIDs, "eventdetails_new", "eventdetails_ID", connection);
    whackDuplicates(listEventIDs, "events_new", "event_ID", connection);
    connection.Close();
    //update iterator from inside the clause in case there are more duplicates.
    dtEventIDs = getDT(dtQuery, testDB);    }

}//goofy curly brace to allow LinqPAD to deal with inline classes
public void whackDuplicates(List<string> listOfIDs,
                            string table,
                            string pkID, 
                            MySqlConnection connection)
{
    foreach(string ID in listOfIDs)
    {
        MySqlCommand command = connection.CreateCommand();
        command.CommandText = String.Format(
        "DELETE FROM " + table + " WHERE " + pkID + " = {0}", ID);
        command.ExecuteNonQuery();
    }
}
public DataTable getDT(string query, sbCommonFunctions.Database db)
{
    return db.QueryDatabase(query);
//}/*this is deliberate, LinqPAD has a weird way of dealing with inline
     classes and the last one can't have a closing curly brace (and the 
     first one has to have an extra opening curly brace above it, go figure)
   */

基本上，这是一个巨大的while循环，子句迭代器从子句内部进行更新，直到Event_ID的数目降为零为止（需要5次迭代，某些数据具有多达六个重复项）。