MongoDB Map / Reduce Array聚合问题
|
我有一个MongoDB集合，其文档使用了多个层次的嵌套，我希望从中提取从其字段子集编译的多维数组。我有一个适合我的解决方案，但是我想更好地理解“幂等”的概念及其与reduce函数相关的后果。
{
\"host_name\" : \"gateway\",
\"service_description\" : \"PING\",
\"last_update\" : 1305777787,
\"performance_object\" : [
[ \"rta\", 0.105, \"ms\", 100, 500, 0 ],
[ \"pl\", 0, \"%\", 20, 60, 0 ]
]
}
var M = function() {
var hn = this.host_name,
sv = this.service_description,
ts = this.last_update;
this.performance_object.forEach(function(P){
emit( {
host: hn,
service: sv,
metric: P[0]
}, {
time: ts,
value: P[1]
} );
});
}
var R = function(key,values) {
var result = {
time: [],
value: []
};
values.forEach(function(V){
result.time.push(V.time);
result.value.push(V.value);
});
return result;
}
db.runCommand({
mapreduce: <colname>,
out: <col2name>,
map: M,
reduce: R
});
{
\"_id\" : {
\"host\" : \"localhost\",
\"service\" : \"Disk Space\",
\"metric\" : \"/var/bck\"
},
\"value\" : {
\"time\" : [
[ 1306719302, 1306719601, 1306719903, ... ],
[ 1306736404, 1306736703, 1306737002, ... ],
[ 1306766401, 1306766701, 1306767001, ... ]
],
\"value\" : [
[ 122, 23423, 25654, ... ],
[ 336114, 342511, 349067, ... ],
[ 551196, 551196, 551196, ... ]
]
}
}
[ [1306719302,122], [1306719601,23423], [1306719903,25654], ... ]
var M = function() {
var hn = this.host_name,
sv = this.service_description,
ts = this.last_update;
this.performance_object.forEach(function(P){
emit( {
host: hn,
service: sv,
metric: P[0]
}, {
value: [ ts, P[1] ]
} );
});
}
var R = function(key,values) {
var result = {
value: []
};
values.forEach(function(V){
result.value.push(V.value);
});
return result;
}
db.runCommand({
mapreduce: <colname>,
out: <col2name>,
map: M,
reduce: R
});
{
\"_id\" : {
\"host\" : \"localhost\",
\"service\" : \"Disk Space\",
\"metric\" : \"/var/bck\"
},
\"value\" : {
\"value\" : [
[ [1306736404,336114],[1306736703,342511],[1306737002,349067], ... ],
[ [1306766401,551196],[1306766701,551196],[1306767001,551196], ... ],
[ [1306719302,122],[1306719601,122],[1306719903,122], ... ]
]
}
}
...
var F = function(key,values) {
return (Array.concat.apply([],values.value)).sort(function(a,b){
if (a[0] < b[0]) return -1;
if (a[0] > b[0]) return 1;
return 0;
});
}
db.runCommand({
mapreduce: <colname>,
out: <col2name>,
map: M,
reduce: R,
finalize: F
});
{
\"_id\" : {
\"host\" : \"localhost\",
\"service\" : \"Disk Space\",
\"metric\" : \"/mnt/bck\"
},
\"value\" : [ [1306719302,122],[1306719601,122],[1306719903,122],, ... ]
}
var M = function() {
emit( {
host: this.host,
service: this.service,
metric: this.metric
} , {
data: [ [ this.timestamp, this.data ] ]
} );
}
var R = function(key,values) {
var result = [];
values.forEach(function(V){
Array.prototype.push.apply(result, V.data);
});
return { data: result };
}
var F = function(key,values) {
return values.data.sort(function(a,b){
return (a[0]<b[0]) ? -1 : (a[0]>b[0]) ? 1 : 0;
});
}
没有找到相关结果
已邀请:
1 个回复
弛保矮瘦敖
{time:<timestamp>,value:<value>}{time:[<timestamps>],value:[<values]}emit(<id>, {time: [ts], value: [P[1]]})）和类似的。 好吧，我实际上不明白为什么您不使用时间/值对数组而不是数组，即map函数中的function14ѭ或emit(<id>, { pairs: [ [ts, P[1]] ] })。这样，您甚至不需要finalize函数（可能要从pairs属性“解包”数组：因为reduce函数无法返回数组，因此您必须将其包装在对象中）