尝试用mongo和php制作一个趋势页面，需要一些关于如何更新文档和查询文档的想法

Question

我们有一个很大的数据库。我们收集时事通讯，我想制作一个趋势页面。目标是使页面实时且快速！我们希望显示过去 2 小时、4 小时、24 小时、过去一周和过去一个月的趋势新闻通讯。

我和

MongoDB

合作了一段时间，我尝试让事情变得简单。我想要一个新的集合，trending，它将时事通讯页面的访问者存储在时间桶中。每次访问时，我都想将新闻通讯的信息添加到保存当时趋势新闻通讯的对象中，以及

$inc

hits

字段进行统计。

我的对象是：

{ 
    "_id" : ObjectId("5d4b4ca5a6bba5f7ffb23b39"), 
    "bucket" : "last2hours", 
    "language" : "nl", 
    "time" : "2019-08-08_00", 
    "newsletters" : {
        "5d4b29ba8ddf870fe15628c7" : {
            "_id" : ObjectId("5d4b29ba8ddf870fe15628c7"), 
            "_slug" : "nieuwsbrief-dalstra-reizen-touring-december-2015", 
            "subject" : "Nieuwsbrief Dalstra Reizen Touring december 2015", 
            "date" : ISODate("2015-12-04T13:15:03.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("557ebcc54c79597761fd71c2"), 
                "_slug" : "dalstra-nl", 
                "name" : "dalstra.nl", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29af8ddf870fe15624ba" : {
            "_id" : ObjectId("5d4b29af8ddf870fe15624ba"), 
            "_slug" : "the-carolina-weddings-show", 
            "subject" : "The Carolina Weddings Show", 
            "date" : ISODate("2015-12-04T13:13:54.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("503b950fffa67e2c790007d7"), 
                "_slug" : "livingsocialcom", 
                "name" : "Livingsocial.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29ad8ddf870fe15623f4" : {
            "_id" : ObjectId("5d4b29ad8ddf870fe15623f4"), 
            "_slug" : "newport-gangster-tour", 
            "subject" : "Newport Gangster Tour", 
            "date" : ISODate("2015-12-04T13:13:22.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("503b950fffa67e2c790007d7"), 
                "_slug" : "livingsocialcom", 
                "name" : "Livingsocial.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29bb8ddf870fe15628f3" : {
            "_id" : ObjectId("5d4b29bb8ddf870fe15628f3"), 
            "_slug" : "springwise-daily-shoe-insoles-control-devices-through-kicking-and-more", 
            "subject" : "Springwise Daily | Shoe insoles control devices through kicking, and more.", 
            "date" : ISODate("2015-12-04T13:15:05.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("5581f0b54c7959e82bfd71c2"), 
                "_slug" : "springwise-com", 
                "name" : "springwise.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(2)
        }
    }
}
{ 
    "_id" : ObjectId("5d4b4ca5a6bba5f7ffb23b3b"), 
    "bucket" : "last2hours", 
    "language" : "nl", 
    "time" : "2019-08-08_01", 
    "newsletters" : {
        "5d4b29ba8ddf870fe15628c7" : {
            "_id" : ObjectId("5d4b29ba8ddf870fe15628c7"), 
            "_slug" : "nieuwsbrief-dalstra-reizen-touring-december-2015", 
            "subject" : "Nieuwsbrief Dalstra Reizen Touring december 2015", 
            "date" : ISODate("2015-12-04T13:15:03.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("557ebcc54c79597761fd71c2"), 
                "_slug" : "dalstra-nl", 
                "name" : "dalstra.nl", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29af8ddf870fe15624ba" : {
            "_id" : ObjectId("5d4b29af8ddf870fe15624ba"), 
            "_slug" : "the-carolina-weddings-show", 
            "subject" : "The Carolina Weddings Show", 
            "date" : ISODate("2015-12-04T13:13:54.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("503b950fffa67e2c790007d7"), 
                "_slug" : "livingsocialcom", 
                "name" : "Livingsocial.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29ad8ddf870fe15623f4" : {
            "_id" : ObjectId("5d4b29ad8ddf870fe15623f4"), 
            "_slug" : "newport-gangster-tour", 
            "subject" : "Newport Gangster Tour", 
            "date" : ISODate("2015-12-04T13:13:22.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("503b950fffa67e2c790007d7"), 
                "_slug" : "livingsocialcom", 
                "name" : "Livingsocial.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29bb8ddf870fe15628f3" : {
            "_id" : ObjectId("5d4b29bb8ddf870fe15628f3"), 
            "_slug" : "springwise-daily-shoe-insoles-control-devices-through-kicking-and-more", 
            "subject" : "Springwise Daily | Shoe insoles control devices through kicking, and more.", 
            "date" : ISODate("2015-12-04T13:15:05.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("5581f0b54c7959e82bfd71c2"), 
                "_slug" : "springwise-com", 
                "name" : "springwise.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(2)
        }
    }
}
{ 
    "_id" : ObjectId("5d4b4ca5a6bba5f7ffb23b3d"), 
    "bucket" : "last4hours", 
    "language" : "nl", 
    "time" : "2019-08-08_00", 
    "newsletters" : {
        "5d4b29ba8ddf870fe15628c7" : {
            "_id" : ObjectId("5d4b29ba8ddf870fe15628c7"), 
            "_slug" : "nieuwsbrief-dalstra-reizen-touring-december-2015", 
            "subject" : "Nieuwsbrief Dalstra Reizen Touring december 2015", 
            "date" : ISODate("2015-12-04T13:15:03.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("557ebcc54c79597761fd71c2"), 
                "_slug" : "dalstra-nl", 
                "name" : "dalstra.nl", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29af8ddf870fe15624ba" : {
            "_id" : ObjectId("5d4b29af8ddf870fe15624ba"), 
            "_slug" : "the-carolina-weddings-show", 
            "subject" : "The Carolina Weddings Show", 
            "date" : ISODate("2015-12-04T13:13:54.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("503b950fffa67e2c790007d7"), 
                "_slug" : "livingsocialcom", 
                "name" : "Livingsocial.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29ad8ddf870fe15623f4" : {
            "_id" : ObjectId("5d4b29ad8ddf870fe15623f4"), 
            "_slug" : "newport-gangster-tour", 
            "subject" : "Newport Gangster Tour", 
            "date" : ISODate("2015-12-04T13:13:22.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("503b950fffa67e2c790007d7"), 
                "_slug" : "livingsocialcom", 
                "name" : "Livingsocial.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(1)
        }, 
        "5d4b29bb8ddf870fe15628f3" : {
            "_id" : ObjectId("5d4b29bb8ddf870fe15628f3"), 
            "_slug" : "springwise-daily-shoe-insoles-control-devices-through-kicking-and-more", 
            "subject" : "Springwise Daily | Shoe insoles control devices through kicking, and more.", 
            "date" : ISODate("2015-12-04T13:15:05.000+0000"), 
            "publisher" : {
                "_id" : ObjectId("5581f0b54c7959e82bfd71c2"), 
                "_slug" : "springwise-com", 
                "name" : "springwise.com", 
                "taal" : "nl"
            }, 
            "hits" : NumberInt(2)
        }
    }
}

这里的目标是只需要查询桶语言时间。因此，如果我想查看过去 2 小时的热门时事通讯，我查询

{bucket: 'last2hours', language: 'nl', time: '2019-08-08_00'}

，然后我就拥有了所需的所有信息。无需聚合。这个

findOne

查询速度很快。

所以我做了一个方法来更新trending集合：

public function setNewsletterTrendingStatistics($newsletter){

            // Buckets
            $trend_buckets = array(
                'last2hours'    => array('steps' => 2,  'step'=>'hour', 'format'=> 'Y-m-d_H'),
                'last4hours'    => array('steps' => 4,  'step'=>'hour', 'format'=> 'Y-m-d_H' ), 
                'last1day'      => array('steps' => 24, 'step'=>'hour', 'format'=> 'Y-m-d_H' ), 
                'lastweek'      => array('steps' => 7,  'step'=>'day',  'format'=> 'Y-m-d' ), 
                'lastmonth'     => array('steps' => 31, 'step'=>'day',  'format'=> 'Y-m-d' ), 
            );
            // $newsletter['date']->toDateTime()->format('U')
            $buckets = array();
            foreach($trend_buckets AS $bucket => $settings){

                for($i=0; $i<$settings['steps']; $i++){
                    $buckets[] = array(
                        'bucket'    => $bucket,
                        'time'      => date($settings['format'], strtotime('+'. $i . ' ' . $settings['step'])),
                        'language'  => $newsletter['publisher']['taal'],
                    );
                }

            }


            // Add the stats to each bucket

            foreach($buckets AS $bucket){
                $query      = array();
                $query      = $bucket;
                $update     =   array(
                                    '$set' => array(
                                        'newsletters.' . (string) $newsletter['_id'] .  '._id'      => $newsletter['_id'],
                                        'newsletters.' . (string) $newsletter['_id'] .  '._slug'    => $newsletter['_slug'],
                                        'newsletters.' . (string) $newsletter['_id'] .  '.subject'  => $newsletter['subject'],
                                        'newsletters.' . (string) $newsletter['_id'] .  '.date'         => $newsletter['date'],
                                        'newsletters.' . (string) $newsletter['_id'] .  '.publisher'    => array(
                                            '_id'       => $newsletter['publisher']['_id'],
                                            '_slug'     => $newsletter['publisher']['_slug'],
                                            'name'      => $newsletter['publisher']['name'],
                                            'taal'      => $newsletter['publisher']['taal'],
                                        ),
                                    ),
                                    '$inc' => array(
                                        'newsletters.' . (string) $newsletter['_id'] .  '.hits' => 1
                                    ),

                                );

                $options    =   array('upsert'=>true);
                $this->FW->mdb->{$this->config['collections']['newsletters_trending']}->updateOne($query, $update, $options);




            }

        }

首先，这是一个好方法吗？有更好的方法吗？其次，我想计算唯一点击数，因此我需要保存一个

IP address

。我想计算

update

查询的唯一点击次数，这样我就不必依赖

findOne

查询。实现这一目标的最佳方法是什么？我知道我可以使用

addtoset

来创建带有

IP addresses

的唯一数组。但接下来我需要数一下这些独特的

IP addresses

。

Answer 1

所以我最终这样做了：

我每小时为每个趋势容器（过去 2 小时、过去 4 小时、今天、上周、上个月）制作了桶。

我在每个页面视图上使用更新查询 $inc 1 填充此容器。

每小时都会有一个 cronjob 结合这些统计数据。所以 2 小时填满 4 小时今天 4 小时填满等等。

这似乎是最好的方法，并且是实时统计数据。