我有一个电子邮件列表，其中包含大量重复数据，我想合并某个列中包含重复数据的行。
这是我的表格：
autoid,title,lastname,firstname,middlename,prefix,
fulladdress,address1,address2,
city,state,zip,country,county,phone1,phone2,email,id, ts
我想根据电子邮件和phone1合并重复的行。如果这些内容在两行中相同，那么我想合并行并填充任何空白然后删除第二行。具有较低autoid的行中的数据优先于具有较高id的行。
如果我们可以使用单个mysql查询这样做会很好但是如果我们必须使用可以正常工作的PHP。
答案 0 :(得分：1)
您可以使用
之类的内容将多个行合并为一个行GROUP BY email, phone1
如果你只是插入它，你会得到任何一个组合行。如果您希望值优先于NULL字段，则可以使用聚合功能，例如MIN：
SELECT MIN(title), MIN(lastname), …
FROM tableName
GROUP BY email, phone1
但这决定了每行分别采用哪个值。一个组合行但是以你描述的方式这样做的查询在MySQL中会相当棘手。您可以使用一个查询按照匹配列的顺序列出所有行，然后使用用户变量填充差距来降序autoid。但是不填写不匹配行中的间隙会很困难，因此每个匹配对的一个子查询可能会更好。除了性能和查询的可读性之外，总的来说，使用PHP解决方案可能会更好。
在PHP中，事情应该相当简单：用
查询数据库ORDER BY email, phnone1, autoid ASC
然后在PHP端，对于从数据库中读取的每一行，检查它是否与两个特定列中先前读取的行匹配。如果是，则迭代列，随时替换null。这些天我不是一个PHP编码器，所以其他人可能更适合为此编写代码片段。
答案 1 :(得分：-2)
我们真的不喜欢在StackOverflow上提供完整的代码解决方案，通常我们会帮助您编写自己的代码解决方案，但我不确定我是否能够解释所有步骤而不实际编写代码来自行解决，所以这里有一些入门代码。
这是未经编辑的原始代码
首先 制作您现有表格的副本 ，直到我们知道此代码不会造成损害或丢弃现有数据，然后在副本上执行所有操作，然后再进行熨烫你已经确认它会正常工作然后将它应用到正确的表格中。
使用以下方式创建副本：
CREATE TABLE EmailListCopy LIKE EmailList;
INSERT EmailListCopy SELECT * FROM EmailList;
PHP代码：
<?php
//This script will first query the table for ALL results, store them in arrays,
//then loop through the arrays to search the table for duplicates using individual
//sql queries and then compare the results, update the entry as needed and delete the
//duplicate row. THIS CODE IS NOT OPTIMIZED!! DO NOT RUN CONTINUOUSLY!! This should be
//used for OCCASIONAL merging ONLY!! i.e. Once-a-day or once-a-week etc...
$result="";
$duplicatesFound;
//Setup arrays to hold the original query information
$autoidArray = array();
$titleArray = array();
$lastnameArray = array();
$firstnameArray = array();
$middlenameArray = array();
$prefixArray = array();
$fulladdressArray = array();
$address1Array = array();
$address2Array = array();
$cityArray = array();
$stateArray = array();
$zipArray = array();
$countryArray = array();
$countyArray = array();
$phone1Array = array();
$phone2Array = array();
$emailArray = array();
$idArray = array();
$tsArray = array();
$link=mysqli_connect($hostname,$dbname,$password,$username);
if(mysqli_connect_errno())
{
$result="Error connecting to database: ".mysqli_connect_error();
}
else
{
$stmt=mysqli_prepare($link,"SELECT autoid,title,lastname,firstname,middlename,prefix,fulladdress,address1,address2,city,state,zip,country,county,phone1,phone2,email,id,ts FROM " . $table);
mysqli_stmt_execute($stmt);
mysqli_stmt_bind_result($stmt, $autoid, $title, $lastname, $firstname, $middlename, $prefix, $fulladdress, $address1, $address2, $city, $state, $zip, $country, $county, $phone1, $phone2, $email, $id, $ts);
if(mysqli_stmt_errno($stmt))
{
$result="Error executing SQL statement: ".mysqli_stmt_error($stmt);
}
else
{
mysqli_stmt_store_result($stmt);
if(mysqli_stmt_num_rows($stmt)==0)
{
$result="0 rows returned (Empty table)";
}
else
{
while(mysqli_stmt_fetch($stmt))
{
//Load results into arrays
array_push($autoidArray, $autoid);
array_push($titleArray, $title);
array_push($lastnameArray, $lastname);
array_push($firstnameArray, $firstname);
array_push($middlenameArray, $middlename);
array_push($prefixArray, $prefix);
array_push($fulladdressArray, $fulladdress);
array_push($address1Array, $address1);
array_push($address2Array, $address2);
array_push($cityArray, $city);
array_push($stateArray, $state);
array_push($zipArray, $zip);
array_push($countryArray, $country);
array_push($countyArray, $county);
array_push($phone1Array, $phone1);
array_push($phone2Array, $phone2);
array_push($emailArray, $email);
array_push($idArray, $id);
array_push($tsArray, $ts);
}
}
mysqli_stmt_free_result($stmt);
}
for($i=0;$i<count($emailArray);$i++)
{
$duplicatestmt=mysqli_prepare($link,"SELECT autoid,title,lastname,firstname,middlename,prefix,fulladdress,address1,address2,city,state,zip,country,county,phone1,phone2,email,id,ts FROM " . $table . " WHERE email=? OR phone1=?");
mysqli_stmt_bind_param($duplicatestmt, 'si', $emailArray[$i], $phone1Array[$i]);
mysqli_stmt_execute($duplicatestmt);
mysqli_stmt_bind_result($duplicatestmt, $autoid, $title, $lastname, $firstname, $middlename, $prefix, $fulladdress, $address1, $address2, $city, $state, $zip, $country, $county, $phone1, $phone2, $email, $id, $ts);
if(mysqli_stmt_errno($duplicatestmt))
{
$result="Error executing SQL statement: ".mysqli_stmt_error($duplicatestmt);
}
else
{
mysqli_stmt_store_result($duplicatestmt);
if(mysqli_stmt_num_rows($duplicatestmt)==0)
{
//NO Duplicate entry found, loop again;
echo "<p>No Dublicate Found</p>";
}
else
{
while(mysqli_stmt_fetch($duplicatestmt))
{
//Found a duplicate
echo "<p>Dublicate Found</p>";
if($autoid > $autoidArray[$i])
{
if($email=="" && $phone1=="")
{
echo "<p>Both email and phone1 are empty. Skipping...</p>";
else
{
$duplicatesFound++;
//The autoid of the duplicate just found is greater then the autoid of the
//one used to find the duplicate (older). Therefor update the entry and remove the
//duplicate
//
//This checks each of the values and if the lower autoid one is blank, then will add the
//value to the table in the lower autoid row
//NOTE:** If having any problems with the queries below try removing the single quotes -> ' <- from any "autoid=" portion of the query
if($titleArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$title."' WHERE autoid='".$autoidArray[$i]."'");}
if($lastnameArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$firstname."' WHERE autoid='".$autoidArray[$i]."'");}
if($firstnameArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$lastname."' WHERE autoid='".$autoidArray[$i]."'");}
if($middlenameArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$middlename."' WHERE autoid='".$autoidArray[$i]."'");}
if($prefixArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$prefix."' WHERE autoid='".$autoidArray[$i]."'");}
if($fulladdressArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$fulladdress."' WHERE autoid='".$autoidArray[$i]."'");}
if($address1Array[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$address1."' WHERE autoid='".$autoidArray[$i]."'");}
if($address2Array[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$address2."' WHERE autoid='".$autoidArray[$i]."'");}
if($cityArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$city."' WHERE autoid='".$autoidArray[$i]."'");}
if($stateArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$state."' WHERE autoid='".$autoidArray[$i]."'");}
if($zipArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$zip."' WHERE autoid='".$autoidArray[$i]."'");}
if($countryArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$country."' WHERE autoid='".$autoidArray[$i]."'");}
if($countyArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$county."' WHERE autoid='".$autoidArray[$i]."'");}
if($phone1Array[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$phone1."' WHERE autoid='".$autoidArray[$i]."'");}
if($phone2Array[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$phone2."' WHERE autoid='".$autoidArray[$i]."'");}
if($emailArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$email."' WHERE autoid='".$autoidArray[$i]."'");}
if($idArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$id."' WHERE autoid='".$autoidArray[$i]."'");}
if($tsArray[$i]==""){mysqli_query($link,"UPDATE EmailListCopy SET title='".$ts."' WHERE autoid='".$autoidArray[$i]."'");}
//Now that it has been updated, delete the duplicate entry
mysqli_query($link, "DELETE FROM EmailListCopy WHERE autoid='".$autoid."'");
echo "<p>Duplicate to be updated DELETE FROM EmailListCopy WHERE autoid='".$autoid."'</p>";
}
}
else
{
//The duplicate autoid is lower then the one used to query either an entry we already but is still in the arrays, or something else.
//This is to be skipped.
echo "<p>Duplicate not to be updated</p>";
}
}
$result="Merged ".$duplicatesFound." rows.";
}
mysqli_stmt_free_result($stmt);
}
}
mysqli_stmt_close($duplicatestmt);
mysqli_stmt_close($stmt);
mysqli_close($link);
}
echo $result;
?>