javascript - 从用户时间轴获取转推计数

Question

我使用 twitter api 'statuses/user_timeline' 将自己的 twitter tweets 集合存储在 mongodb 中。我正在尝试获取我使用 MongoDb MapReduce 方法发布的推文中的转推 计数，但无法获取。谁能帮帮我。

示例数据:这是存储在mongodb中的文档格式

{
    "_id" : ObjectId("570664d7a9c29761168b4587"),
    "created_at" : "Thu Sep 17 01:17:28 +0000 2015",
    "id" : NumberLong("644319222886039556"),
    "id_str" : "644319222886039556",
    "text" : "Be silent or let your words be worth more than you silence.",
    "entities" : {
        "hashtags" : [ ],
        "symbols" : [ ],
        "user_mentions" : [ ],
        "urls" : [ ]
    },
    "truncated" : false,
    "source" : "<a href=\"http://twitter.com\" rel=\"nofollow\">Twitter Web Client</a>",
    "in_reply_to_status_id" : null,
    "in_reply_to_status_id_str" : null,
    "in_reply_to_user_id" : null,
    "in_reply_to_user_id_str" : null,
    "in_reply_to_screen_name" : null,
    "user" : {
        // Here is the user information who tweeted
        "id" : NumberLong(xxxxxxxxxxxxxxxxx),
        "id_str" : "xxxxxxxxx",
        "name" : "Haridarshan Gorana",
        "screen_name" : "haridarshan2901"
    },
    "geo" : null,
    "coordinates" : null,
    "place" : null,
    "contributors" : null,
    "is_quote_status" : false,
    "retweet_count" : NumberLong(1),
    "favorite_count" : NumberLong(0),
    "favorited" : false,
    "retweeted" : false,
    "lang" : "en"
}

代码:

$map = new \MongoCode("function() { emit(this.id_str, this.retweet_count); }");
$out = "retweets";
$reduce = new \MongoCode('function(key, values) {
    var retweets = 0;
    for(i=0;i<values.length;i++){

        if( values[i].retweet_count > 0 ){
            retweets += values[i].retweet_count;
        }

    }
    return retweets;
}');
$verbose = true;
$cmd = array(
    "map" => $map,
    "reduce" => $reduce,
    "query" => $query,
    "out" => "retweets",
    "verbose" => true
);

$result = $db->command($cmd);

print_r($result);

这给了我这个错误

fatal error :在 null 上调用成员函数 command()

我尝试在 mongo 客户端上运行相同的代码

var mapFunction1 = function() {
    emit(this.id_str, this.retweet_count);
}

var reduceFunction1 = function(id, values) { 
    var retweet = 0; 
    for(i=0;i<values.length;i++){ 
        if(values[i].retweet_count > 0) { 
            retweet += values[i].retweet_count;
        } 
    } 
    return retweet;  
}

db.tweets.mapReduce(
    mapFunction1, 
    reduceFunction1, 
    {
        query: { 
            user: { id: xxxxxxxxx }
        }, 
        out: "retweets", 
        verbose: true
    }
)

控制台输出

{
    "result" : "retweets",
    "timeMillis" : 12,
    "timing" : {
        "mapTime" : 0,
        "emitLoop" : 8,
        "reduceTime" : 0,
        "mode" : "mixed",
        "total" : 12
    },
    "counts" : {
        "input" : 0,
        "emit" : 0,
        "reduce" : 0,
        "output" : 0
    },
    "ok" : 1
}

Answer 1

你的 reducer 正在尝试调用一个属性 retweet_count，而此时只有一个“值”而没有其他属性。您已经在映射器中引用了它。

实际上你的 reduce 可以简单地是:

function(key,values) {
    return Array.sum(values)
}

但是您最好为此简单地使用 .aggregate()。它不仅更简单，而且运行速度更快:

db.tweets.aggregate([
  { "$group": {
    "_id": "$user.id_str",
    "retweets": { "$sum": "$retweet_count" }
  }}
])

或者对于 PHP

$collection->aggregate(
    array(
        '$group' => array(
           '_id' => '$user.id_str',
           'retweets' => array( '$sum' => '$retweet_count' )
        )
    )
)

如果您想向其中添加“查询”，请添加 $match管道阶段在开始。即

$collection->aggregate(
    array(
        '$match' => array(
            'user.id_str' => 'xxxxxxxxx'
        )
    ),    
    array(
        '$group' => array(
           '_id' => '$user.id_str',
           'retweets' => array( '$sum' => '$retweet_count' )
        )
    )
)

当结构实际需要 JavaScript 控制进行处理时，您真的应该只使用mapReduce。