MongoDB删除重复数据

mongo 4.0

db.article.aggregate(
    [{
        $group: {
            _id:{pmid:'$pmid'},
            count:{$sum:1},
            dups:{$addToSet: '$_id'},
        }
    },
    {
        $match:{count:{$gt:1}}
    }],
    {
        allowDiskUse:true
    }
).cursor.firstBatch.forEach(function(it) {
    it.dups.shift();
    db.article.remove({_id: {$in: it.dups}});
});

mongo 3.x

db.article.aggregate(
    [{
        $group: {
            _id:{pmid:'$pmid'},
            count:{$sum:1},
            dups:{$addToSet: '$_id'},
        }
    },
    {
        $match:{count:{$gt:1}}
    }],
    {
        allowDiskUse:true
    }
).forEach(function(it) {
    it.dups.shift();
    db.article.remove({_id: {$in: it.dups}});
});

参考

• https://www.jianshu.com/p/7685e6692ed6