Fluentdで集めた、Nginxのログを、MongoDBのMapReduceを使ってアクセス解析入門！！ ref: http://qiita.com/items/849fb219593c4505c997

file0.txt

use nginx
db.access.save({status:200});
db.access.save({status:200});
db.access.save({status:200});
db.access.save({status:200});
db.access.save({status:300});
db.access.save({status:400});
db.access.save({test:123});

db.access.find();
{ "_id" : ObjectId("51b9ffe092e0e471137ad2f2"), "status" : 200 }
{ "_id" : ObjectId("51b9ffe092e0e471137ad2f3"), "status" : 200 }
{ "_id" : ObjectId("51b9ffe092e0e471137ad2f4"), "status" : 200 }
{ "_id" : ObjectId("51b9ffe092e0e471137ad2f5"), "status" : 200 }
{ "_id" : ObjectId("51b9ffe092e0e471137ad2f6"), "status" : 300 }
{ "_id" : ObjectId("51b9ffe092e0e471137ad2f7"), "status" : 400 }
{ "_id" : ObjectId("51b9ffe192e0e471137ad2f8"), "test" : 123 }

file2.txt

$ mongo log.js
MongoDB shell version: 2.4.0
connecting to: test
{
        "result" : "access.status",
        "timeMillis" : 1080,
        "counts" : {
                "input" : 7,
                "emit" : 7,
                "reduce" : 1,
                "output" : 4
        },
        "ok" : 1,
}

file3.txt

$ mongo
MongoDB shell version: 2.4.0
connecting to: test
> use nginx
switched to db nginx
> db.access.status.find();
{ "_id" : "200", "value" : { "count" : 4 } }
{ "_id" : "300", "value" : { "count" : 1 } }
{ "_id" : "400", "value" : { "count" : 1 } }
{ "_id" : "undefined", "value" : { "count" : 1 } }

log.js

var colName = 'access.status';

var map = function() {
  var label = String(this.status);

  emit(
    label,
    {count: 1}
  );
}

//簡単に言うと、
//keyには200
//valuesには[{count:1},{count:1},{count:1}]
//と言った感じでデータが渡ってきてカウントアップしてる感じです。
var reduce = function(key, values) {
  var result = {count: 0};

  values.forEach(function(value) {
    result.count += value.count;
  });

  return result; 
}


mongo = new Mongo('localhost');
mydb = mongo.getDB('nginx');

var res = mydb.access.mapReduce(map, reduce, {out: colName});

shellPrint(res);