Mailing-List: contact user-help@couchdb.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@couchdb.apache.org
Received-SPF: pass (athena.apache.org: domain of pawelstawicki@gmail.com
 designates 74.125.78.27 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:in-reply-to:references:from:date:message-id:subject:to
         :content-type;
        b=IEF0g6dG0MG8/o4uODFhEjNJSF9Ij5iVOF0KbuwkVhTF9iwKKIhBMIvs9uOhWaPote
         XivwWn0eaY3x2XkvXvZbm9GORRJxAtFq1ZDJkvix4gc8il6qMaANrtu4zqQwIL/bvfYW
         N+V1zZdj0CJRaJHAu7Mq9ThTX5PQvnflnc7TE=
MIME-Version: 1.0
In-Reply-To: <b7770fe31003060726m3d8fe7edx89424a099aa77183@mail.gmail.com>
References: <b7770fe31003060726m3d8fe7edx89424a099aa77183@mail.gmail.com>
From: =?UTF-8?Q?Pawe=C5=82_Stawicki?= <pawelstawicki@gmail.com>
Date: Sun, 7 Mar 2010 22:02:14 +0100
Message-ID: <6adfa88d1003071302x1a7e95b7k1ac303abd4a7a5f2@mail.gmail.com>
Subject: Re: Map reduce and weird output question
To: user@couchdb.apache.org
Content-Type: multipart/alternative; boundary=001636c5a5fc8031b304813c44a9

--001636c5a5fc8031b304813c44a9
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

Just emit all documents with em_type =3D 0 in map function, with [date,
em_uname] as key. Then count in reduce.

Map:
function(doc) {
  if (doc.em_type =3D 0) {
    //If you only want to count, you can emit anything (e.g. 1) instead of
doc here.
    emit([date, em_uname], doc);
  }
}

Reduce:
function(keys, values, rereduce) {
  if (!rereduce) {
    return count_of_values;
  } else {
    return sum_of_values;
  }

  //If you return 1 from emit instead of doc, then count_of_values =3D=3D
sum_of_values
}

Then you can handle everything by grouping:
http://yourserver:5984/yourdb/_view/yourview?group_level=3D2
or group=3Dtrue

Regards
--
Pawe=C5=82 Stawicki
http://pawelstawicki.blogspot.com
http://szczecin.jug.pl


On Sat, Mar 6, 2010 at 16:26, Gregory Tappero <coulix@gmail.com> wrote:

> Hello everyone,
>
> I have the following EdoPing 's type of documents
>
> {
>   "_id": "22add509c1e7bc286832edc5bfe99ce5",
>   "_rev": "1-49663ab8778f445e481143120d0d7086",
>   "doc_type": "EdoPing",
>   "em_uname": "student1",
>   "em_gid": 1,
>   "created_at": "2010-03-03T14:18:19Z",
>   "em_ip": "92.154.70.148",
>   "em_type": 0,
>   "room_url": "z2fudcvcrfa3reaydatre",
>   "room_users": [
>       "tutorsbox"
>   ]
> }
>
> i would like to count all unique em_uname of em_type 0 on a given day dat=
e.
>
> For now i used this map/reduce
> http://friendpaste.com/5xUUQ26bbl9d5KRB8eojwe
>
> Date.prototype.setRFC3339 =3D function(dString){
>    var regexp =3D
>
> /(\d\d\d\d)(-)?(\d\d)(-)?(\d\d)(T)?(\d\d)(:)?(\d\d)(:)?(\d\d)(\.\d+)?(Z|(=
[+-])(\d\d)(:)?(\d\d))/;
>
>    if (dString.toString().match(new RegExp(regexp))) {
>        var d =3D dString.match(new RegExp(regexp));
>        var offset =3D 0;
>
>        this.setUTCDate(1);
>        this.setUTCFullYear(parseInt(d[1],10));
>        this.setUTCMonth(parseInt(d[3],10) - 1);
>        this.setUTCDate(parseInt(d[5],10));
>        this.setUTCHours(parseInt(d[7],10));
>        this.setUTCMinutes(parseInt(d[9],10));
>        this.setUTCSeconds(parseInt(d[11],10));
>        if (d[12])
>            this.setUTCMilliseconds(parseFloat(d[12]) * 1000);
>        else
>            this.setUTCMilliseconds(0);
>        if (d[13] !=3D 'Z') {
>            offset =3D (d[15] * 60) + parseInt(d[17],10);
>            offset *=3D ((d[14] =3D=3D '-') ? -1 : 1);
>            this.setTime(this.getTime() - offset * 60 * 1000);
>        }
>    } else {
>        this.setTime(Date.parse(dString));
>    }
>    return this;
> };
>
> var seenKeys =3D new Array();
>
> function(doc) {
>
>
>    if (doc.doc_type=3D=3D"EdoPing" && doc.em_type=3D=3D0) {
>        date =3D new Date().setRFC3339(doc.created_at);
>        var key =3D doc.em_uname + String(doc.created_at).substring(0,10);
>        if (seenKeys[key] =3D=3D  undefined  ) {
>            seenKeys[key] =3D 1;
>            emit([date.getFullYear(), parseInt(date.getMonth())+1,
> date.getDate() ] , 1);
>         }
>    }
> }
>
>
> It works when saved for this first time but as soon as new EdoPings
> get added it starts emitting rows it has already seen ! (same key)
> creating faulty count results.
>
> Is it ok to have seenKeys outside of the doc function() ?
> What other way could i use to get the same results ?
>
> Thanks,
>
> Greg
>

--001636c5a5fc8031b304813c44a9--