couchdb - CouchDB 中奇怪的映射减少行为。减少？

Question

我在 couchdb 方面遇到了 mapreduce 问题(两个函数如下所示):当我使用 grouplevel = 2(精确)运行它时，我得到了准确的输出:

{"rows":[
 {"key":["2011-01-11","staff-1"],"value":{"total":895.72,"count":2,"services":6,"services_ignored":6,"services_liked":0,"services_disliked":0,"services_disliked_avg":0,"Revise":{"total":275.72,"count":1},"Review":{"total":620,"count":1}}},
 {"key":["2011-01-11","staff-2"],"value":{"total":8461.689999999999,"count":2,"services":41,"services_ignored":37,"services_liked":4,"services_disliked":0,"services_disliked_avg":0,"Revise":{"total":4432.4,"count":1},"Review":{"total":4029.29,"count":1}}},
 {"key":["2011-01-11","staff-3"],"value":{"total":2100.72,"count":1,"services":10,"services_ignored":4,"services_liked":3,"services_disliked":3,"services_disliked_avg":2.3333333333333335,"Revise":{"total":2100.72,"count":1}}},

但是，更改为 grouplevel=1 以便所有不同人员键的值都应按日期分组，不再提供准确的输出(请注意，总数是正确的，但所有其他值都是错误的):

{"rows":[
  {"key":["2011-01-11"],"value":{"total":11458.130000000001,"count":2,"services":0,"services_ignored":0,"services_liked":0,"services_disliked":0,"services_disliked_avg":0,"None":{"total":11458.130000000001,"count":2}}},

我唯一的理论是这与 rereduce 有关，我还没有了解到。我应该探索这个选项还是我在这里错过了其他东西？

这是 map 功能:

function(doc) {
if(doc.doc_type == 'Feedback') {
    emit([doc.date.split('T')[0], doc.staff_id], doc);
}
}

这是减少:

function(keys, vals) {
// sum all key points by status: total, count, services (liked, rejected, ignored)
var ret = {
    'total':0,
    'count':0, 
    'services': 0,
    'services_ignored': 0,
    'services_liked': 0,
    'services_disliked': 0,
    'services_disliked_avg': 0,
};

var total_disliked_score = 0;

// handle status
function handle_status(doc) {
    if(!doc.status || doc.status == '' || doc.status == undefined) {
        status = 'None';
    } else if (doc.status == 'Declined') {
        status = 'Rejected';
    } else {
        status = doc.status;
    }
    if(!ret[status]) ret[status] = {'total':0, 'count':0};
    ret[status]['total'] += doc.total;  
    ret[status]['count'] += 1;
};

// handle likes / dislikes
function handle_services(services) {
    ret.services += services.length;
    for(var a in services) {
        if (services[a].user_likes == 10) {
            ret.services_liked += 1;
        } else if (services[a].user_likes >= 1) {
            ret.services_disliked += 1;
            total_disliked_score += services[a].user_likes;
            if (total_disliked_score >= ret.services_disliked) {
                ret.services_disliked_avg = total_disliked_score / ret.services_disliked;
            }
        } else {
            ret.services_ignored += 1;
        }
    }
}

// loop thru docs 
for(var i in vals) {
    // increment the total $
    ret.total += vals[i].total;
    ret.count += 1;

    // update totals and sums for the status of this route
    handle_status(vals[i]);

    // do the likes / dislikes stats
    if(vals[i].groups) {
        for(var ii in vals[i].groups) {
            if(vals[i].groups[ii].services) {
                handle_services(vals[i].groups[ii].services); 
            }
        }
    }

    // handle deleted services
    if(vals[i].hidden_services) {
        if (vals[i].hidden_services) {
            handle_services(vals[i].hidden_services);
        }
    }
}

return ret;
}

Answer 1

这是一个典型的错误。请记住，CouchDB 缩减分几个步骤进行，其中一些步骤将接收其他缩减步骤的结果作为输入。但是，您的代码似乎假设 vals[i] 将是 { "groups": _ , "hidden_​​services": _ , _ } 形式的对象，表示单个文档。当发生rereduce时，此代码将失败，因为 vals[i] 将采用以下形式 { "count": _ , "services": _ , _ } 表示先前缩减步骤的结果。

因此，例如，通过使用 ret.count += 1 进行计数，您计算的是中间归约结果的数量，而不是文档的数量。

一种解决方案是编写两个版本的reduce 代码，一个用于处理原始reduce，另一个用于处理rereduce 步骤。您可以通过查看第三个参数来确定给定的调用是初始调用还是 rereduce 调用(如果是初始调用，则为 false；如果为 rereduce，则为 true)。

另一个解决方案是让map函数发出与reduce函数返回的形式相同的预处理值 { "count": _ , "services": _ , _ } ，并且让reduce函数仅仅将这些值的成员加在一起。