[jira] [Updated] (ASTERIXDB-1418) Doesn't support some a Nested Aggregation Query

[Jianfeng Jia (JIRA)]

     [ 
https://issues.apache.org/jira/browse/ASTERIXDB-1418?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Jianfeng Jia updated ASTERIXDB-1418:
------------------------------------
    Description: 
When I ran the following query
{code}
use dataverse twitter
for $t in dataset ds_tweet_trump
group by
  $county := $t.geo_tag.countyID,
  $timebin := interval-bin($t.create_at, date("2012-01-01"), 
day-time-duration("P1D")) with $t
return {
  "county": $county,
  "time": $timebin,
  "count": count($t),
  "users": count( for $tt in $t distinct by $tt.user.id return $tt.user.id)
  }

{code}

One exception appears:
{code}
Attempting to construct a nested plan with 3 operator descriptors. Currently, 
nested plans can only consist in linear pipelines of Asterix micro operators. 
[AlgebricksException]
{code}

The ddl :
{code}
create dataverse twitter if not exists;
use dataverse twitter

create type typeUser if not exists as open {
    id: int64,
    name: string,
    screen_name : string,
    lang : string,
    location: string,
    create_at: date,
    description: string,
    followers_count: int32,
    friends_count: int32,
    statues_count: int64
}

create type typePlace if not exists as open{
    country : string,
    country_code : string,
    full_name : string,
    id : string,
    name : string,
    place_type : string,
    bounding_box : rectangle
}

create type typeGeoTag if not exists as open {
    stateID: int32,
    stateName: string,
    countyID: int32,
    countyName: string,
    cityID: int32?,
    cityName: string?
}

create type typeTweet if not exists as open{
    create_at : datetime,
    id: int64,
    "text": string,
    in_reply_to_status : int64,
    in_reply_to_user : int64,
    favorite_count : int64,
    coordinate: point?,
    retweet_count : int64,
    lang : string,
    is_retweet: boolean,
    hashtags : {{ string }} ?,
    user_mentions : {{ int64 }} ? ,
    user : typeUser,
    place : typePlace?,
    geo_tag: typeGeoTag
}

create dataset ds_tweet(typeTweet) if not exists primary key id;
//with filter on create_at;
{code}

The logical plan is generated successfully:


  was:
When I ran the following query
{code}
use dataverse twitter
for $t in dataset ds_tweet_trump
group by
  $county := $t.geo_tag.countyID,
  $timebin := interval-bin($t.create_at, date("2012-01-01"), 
day-time-duration("P1D")) with $t
return {
  "county": $county,
  "time": $timebin,
  "count": count($t),
  "users": count( for $tt in $t distinct by $tt.user.id return $tt.user.id)
  }

{code}

One exception appears:
{code}
Attempting to construct a nested plan with 3 operator descriptors. Currently, 
nested plans can only consist in linear pipelines of Asterix micro operators. 
[AlgebricksException]
{code}


> Doesn't support some a Nested Aggregation Query
> -----------------------------------------------
>
>                 Key: ASTERIXDB-1418
>                 URL: https://issues.apache.org/jira/browse/ASTERIXDB-1418
>             Project: Apache AsterixDB
>          Issue Type: Bug
>            Reporter: Jianfeng Jia
>
> When I ran the following query
> {code}
> use dataverse twitter
> for $t in dataset ds_tweet_trump
> group by
>   $county := $t.geo_tag.countyID,
>   $timebin := interval-bin($t.create_at, date("2012-01-01"), 
> day-time-duration("P1D")) with $t
> return {
>   "county": $county,
>   "time": $timebin,
>   "count": count($t),
>   "users": count( for $tt in $t distinct by $tt.user.id return $tt.user.id)
>   }
> {code}
> One exception appears:
> {code}
> Attempting to construct a nested plan with 3 operator descriptors. Currently, 
> nested plans can only consist in linear pipelines of Asterix micro operators. 
> [AlgebricksException]
> {code}
> The ddl :
> {code}
> create dataverse twitter if not exists;
> use dataverse twitter
> create type typeUser if not exists as open {
>     id: int64,
>     name: string,
>     screen_name : string,
>     lang : string,
>     location: string,
>     create_at: date,
>     description: string,
>     followers_count: int32,
>     friends_count: int32,
>     statues_count: int64
> }
> create type typePlace if not exists as open{
>     country : string,
>     country_code : string,
>     full_name : string,
>     id : string,
>     name : string,
>     place_type : string,
>     bounding_box : rectangle
> }
> create type typeGeoTag if not exists as open {
>     stateID: int32,
>     stateName: string,
>     countyID: int32,
>     countyName: string,
>     cityID: int32?,
>     cityName: string?
> }
> create type typeTweet if not exists as open{
>     create_at : datetime,
>     id: int64,
>     "text": string,
>     in_reply_to_status : int64,
>     in_reply_to_user : int64,
>     favorite_count : int64,
>     coordinate: point?,
>     retweet_count : int64,
>     lang : string,
>     is_retweet: boolean,
>     hashtags : {{ string }} ?,
>     user_mentions : {{ int64 }} ? ,
>     user : typeUser,
>     place : typePlace?,
>     geo_tag: typeGeoTag
> }
> create dataset ds_tweet(typeTweet) if not exists primary key id;
> //with filter on create_at;
> {code}
> The logical plan is generated successfully:



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)