sql - 如何使用连接执行 AND？

Question

我有以下数据结构和数据:

CREATE TABLE `parent` (
  `id` int(11) NOT NULL auto_increment,
  `name` varchar(10) NOT NULL,
  PRIMARY KEY  (`id`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1;

INSERT INTO `parent` VALUES(1, 'parent 1');
INSERT INTO `parent` VALUES(2, 'parent 2');

CREATE TABLE `other` (
  `id` int(11) NOT NULL auto_increment,
  `name` varchar(10) NOT NULL,
  PRIMARY KEY  (`id`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1;

INSERT INTO `other` VALUES(1, 'other 1');
INSERT INTO `other` VALUES(2, 'other 2');

CREATE TABLE `relationship` (
  `id` int(11) NOT NULL auto_increment,
  `parent_id` int(11) NOT NULL,
  `other_id` int(11) NOT NULL,
  PRIMARY KEY  (`id`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1;

INSERT INTO `relationship` VALUES(1, 1, 1);
INSERT INTO `relationship` VALUES(2, 1, 2);
INSERT INTO `relationship` VALUES(3, 2, 1);

我想找到包含其他 1 和 2 的父记录。

这是我想出来的，但我想知道是否有更好的方法:

SELECT p.id, p.name
FROM parent AS p
    LEFT JOIN relationship AS r1 ON (r1.parent_id = p.id)
    LEFT JOIN relationship AS r2 ON (r2.parent_id = p.id)
WHERE r1.other_id = 1 AND r2.other_id = 2;

结果是1，“parent 1”是正确的。问题是，一旦您获得 5+ 个连接的列表，它就会变得困惑，并且随着关系表的增长，它会变慢。

有没有更好的办法？

我正在使用 MySQL 和 PHP，但这可能非常通用。

Answer 1

好的，我测试了这个。从最好到最差的查询是:

查询 1:连接(0.016 秒；基本上即时)

SELECT p.id, name
FROM parent p
JOIN relationship r1 ON p.id = r1.parent_id AND r1.other_id = 100
JOIN relationship r2 ON p.id = r2.parent_id AND r2.other_id = 101
JOIN relationship r3 ON p.id = r3.parent_id AND r3.other_id = 102
JOIN relationship r4 ON p.id = r4.parent_id AND r4.other_id = 103

查询 2:EXISTS(0.625 秒)

SELECT id, name
FROM parent p
WHERE EXISTS (SELECT 1 FROM relationship WHERE parent_id = p.id AND other_id = 100)
AND EXISTS (SELECT 1 FROM relationship WHERE parent_id = p.id AND other_id = 101)
AND EXISTS (SELECT 1 FROM relationship WHERE parent_id = p.id AND other_id = 102)
AND EXISTS (SELECT 1 FROM relationship WHERE parent_id = p.id AND oth

查询 3:聚合(1.016 秒)

SELECT p.id, p.name来自父 pWHERE (SELECT COUNT(*) FROM relationship WHERE parent_id = p.id AND other_id IN (100,101,102,103))

查询 4:UNION 聚合(2.39 秒)

SELECT id, name FROM (
  SELECT p1.id, p1.name
  FROM parent AS p1 LEFT JOIN relationship as r1 ON(r1.parent_id=p1.id)
  WHERE r1.other_id = 100
  UNION ALL
  SELECT p2.id, p2.name
  FROM parent AS p2 LEFT JOIN relationship as r2 ON(r2.parent_id=p2.id)
  WHERE r2.other_id = 101
  UNION ALL
  SELECT p3.id, p3.name
  FROM parent AS p3 LEFT JOIN relationship as r3 ON(r3.parent_id=p3.id)
  WHERE r3.other_id = 102
  UNION ALL
  SELECT p4.id, p4.name
  FROM parent AS p4 LEFT JOIN relationship as r4 ON(r4.parent_id=p4.id)
  WHERE r4.other_id = 103
) a
GROUP BY id, name
HAVING count(*) = 4

实际上上面生成了错误的数据，所以它要么是错误的，要么是我做错了什么。不管怎样，以上只是一个坏主意。

如果速度不快，那么您需要查看查询的解释计划。您可能只是缺少适当的索引。试试看:

CREATE INDEX ON relationship (parent_id, other_id)

在你沿着聚合路线 (SELECT COUNT(*) FROM ...) 走之前，你应该阅读 SQL Statement - “Join” Vs “Group By and Having” .

注意:以上时间是基于:

CREATE TABLE parent (
  id INT PRIMARY KEY,
  name VARCHAR(50)
);

CREATE TABLE other (
  id INT PRIMARY KEY,
  name VARCHAR(50)
);

CREATE TABLE relationship (
  id INT PRIMARY KEY,
  parent_id INT,
  other_id INT
);

CREATE INDEX idx1 ON relationship (parent_id, other_id);
CREATE INDEX idx2 ON relationship (other_id, parent_id);

以及近 800,000 条记录:

<?php
ini_set('max_execution_time', 600);

$start = microtime(true);

echo "<pre>\n";
mysql_connect('localhost', 'scratch', 'scratch');
if (mysql_error()) {
    echo "Connect error: " . mysql_error() . "\n";
}
mysql_select_db('scratch');
if (mysql_error()) {
    echo "Selct DB error: " . mysql_error() . "\n";
}

define('PARENTS', 100000);
define('CHILDREN', 100000);
define('MAX_CHILDREN', 10);
define('SCATTER', 10);
$rel = 0;
for ($i=1; $i<=PARENTS; $i++) {
    query("INSERT INTO parent VALUES ($i, 'Parent $i')");
    $potential = range(max(1, $i - SCATTER), min(CHILDREN, $i + SCATTER));
    $elements = sizeof($potential);
    $other = rand(1, min(MAX_CHILDREN, $elements - 4));
    $j = 0;
    while ($j < $other) {
        $index = rand(0, $elements - 1);
        if (isset($potential[$index])) {
            $c = $potential[$index];
            $rel++;
            query("INSERT INTO relationship VALUES ($rel, $i, $c)");
            unset($potential[$index]);
            $j++;
        }
    }
}
for ($i=1; $i<=CHILDREN; $i++) {
    query("INSERT INTO other VALUES ($i, 'Other $i')");
}

$count = PARENTS + CHILDREN + $rel;
$stop = microtime(true);
$duration = $stop - $start;
$insert = $duration / $count;

echo "$count records added.\n";
echo "Program ran for $duration seconds.\n";
echo "Insert time $insert seconds.\n";
echo "</pre>\n";

function query($str) {
    mysql_query($str);
    if (mysql_error()) {
        echo "$str: " . mysql_error() . "\n";
    }
}
?>

所以再次加入 carry the day。