php mysql百万级数据去除重复数据
$result = array();
//读取uid列表文件
$fp = fopen('test.txt', 'r');
while(!feof($fp))
{
$uid = fgets($fp);
$uid = trim($uid);
$uid = trim($uid, "r");
$uid = trim($uid, "n");
if($uid == '')
{
continue;
}
//以uid为key去看该值是否存在
if(empty($result[$uid]))
{
$result[$uid] = 1;
}
}
fclose($fp);
//将结果保存到文件
$content = '';
foreach($result as $k => $v)
{
$content .= $k."n";
}
$fp = fopen('result.txt', 'w');
fwrite($fp, $content);
fclose($fp);
?>
//定义数组,用于存放排重后的结果
$result = array();
//读取第一个uid列表文件,放入$result_1
$fp = fopen('test_1.txt', 'r');
while(!feof($fp))
{
$uid = fgets($fp);
$uid = trim($uid);
$uid = trim($uid, "r");
$uid = trim($uid, "n");
if($uid == '')
{
continue;
}
//以uid为key写入$result,如有重复就会覆盖
$result[$uid] = 1;
}
fclose($fp);
//读取第二个uid列表文件,并进行排重操作
$fp = fopen('test_2.txt', 'r');
while(!feof($fp))
{
$uid = fgets($fp);
$uid = trim($uid);
$uid = trim($uid, "r");
$uid = trim($uid, "n");
if($uid == '')
{
continue;
}
//以uid为key去看该值是否存在
if(empty($result[$uid]))
{
$result[$uid] = 1;
}
}
fclose($fp);
//$result里保存的就排重以后的结果,可以输出到文件,代码省略
?>