Xikui Wang created ASTERIXDB-2558:
-------------------------------------
Summary: NGram index doesn't work for a list of constant record
Key: ASTERIXDB-2558
URL: https://issues.apache.org/jira/browse/ASTERIXDB-2558
Project: Apache AsterixDB
Issue Type: Bug
Reporter: Xikui Wang
as the index access method always assume the other side is a dataset.
{code}
DROP DATAVERSE TinySocial IF EXISTS;
CREATE DATAVERSE TinySocial;
USE TinySocial;
CREATE TYPE EmploymentType AS {
organizationName: string,
startDate: date,
endDate: date?
};
CREATE TYPE GleambookUserType AS {
id: int,
alias: string,
name: string,
userSince: datetime,
friendIds: {{ int }},
employment: [EmploymentType]
};
CREATE TYPE ChirpUserType AS {
screenName: string,
lang: string,
friendsCount: int,
statusesCount: int,
name: string,
followersCount: int
};
CREATE DATASET GleambookUsers(GleambookUserType) PRIMARY KEY id;
create index gbUserIdx on GleambookUsers(name) type ngram(3);
CREATE DATASET ChirpUsers(ChirpUserType) PRIMARY KEY screenName;
INSERT INTO GleambookUsers
([
{"id":1,"alias":"Margarita","name":"MargaritaStoddard","nickname":"Mags","userSince":datetime("2012-08-20T10:10:00"),"friendIds":{{2,3,6,10}},"employment":[{"organizationName":"Codetechno","startDate":date("2006-08-06")},{"organizationName":"geomedia","startDate":date("2010-06-17"),"endDate":date("2010-01-26")}],"gender":"F"},
{"id":2,"alias":"Isbel","name":"IsbelDull","nickname":"Izzy","userSince":datetime("2011-01-22T10:10:00"),"friendIds":{{1,4}},"employment":[{"organizationName":"Hexviafind","startDate":date("2010-04-27")}]},
{"id":3,"alias":"Emory","name":"EmoryUnk","userSince":datetime("2012-07-10T10:10:00"),"friendIds":{{1,5,8,9}},"employment":[{"organizationName":"geomedia","startDate":date("2010-06-17"),"endDate":date("2010-01-26")}]},
{"id":4,"alias":"Nicholas","name":"NicholasStroh","userSince":datetime("2010-12-27T10:10:00"),"friendIds":{{2}},"employment":[{"organizationName":"Zamcorporation","startDate":date("2010-06-08")}]},
{"id":5,"alias":"Von","name":"VonKemble","userSince":datetime("2010-01-05T10:10:00"),"friendIds":{{3,6,10}},"employment":[{"organizationName":"Kongreen","startDate":date("2010-11-27")}]},
{"id":6,"alias":"Willis","name":"WillisWynne","userSince":datetime("2005-01-17T10:10:00"),"friendIds":{{1,3,7}},"employment":[{"organizationName":"jaydax","startDate":date("2009-05-15")}]},
{"id":7,"alias":"Suzanna","name":"SuzannaTillson","userSince":datetime("2012-08-07T10:10:00"),"friendIds":{{6}},"employment":[{"organizationName":"Labzatron","startDate":date("2011-04-19")}]},
{"id":8,"alias":"Nila","name":"NilaMilliron","userSince":datetime("2008-01-01T10:10:00"),"friendIds":{{3}},"employment":[{"organizationName":"Plexlane","startDate":date("2010-02-28")}]},
{"id":9,"alias":"Woodrow","name":"WoodrowNehling","nickname":"Woody","userSince":datetime("2005-09-20T10:10:00"),"friendIds":{{3,10}},"employment":[{"organizationName":"Zuncan","startDate":date("2003-04-22"),"endDate":date("2009-12-13")}]},
{"id":10,"alias":"Bram","name":"BramHatch","userSince":datetime("2010-10-16T10:10:00"),"friendIds":{{1,5,9}},"employment":[{"organizationName":"physcane","startDate":date("2007-06-05"),"endDate":date("2011-11-05")}]}
]);
USE TinySocial;
LET CUsers = ([
{"screenName":"NathanGiesen@211","lang":"en","friendsCount":18,"statusesCount":473,"name":"Nathan
Giesen","followersCount":49416},
{"screenName":"ColineGeyer@63","lang":"en","friendsCount":121,"statusesCount":362,"name":"Coline
Geyer","followersCount":17159},
{"screenName":"NilaMilliron_tw","lang":"en","friendsCount":445,"statusesCount":164,"name":"Nila
Milliron","followersCount":22649},
{"screenName":"ChangEwing_573","lang":"en","friendsCount":182,"statusesCount":394,"name":"Chang
Ewing","followersCount":32136}
])
SELECT c.*, (select g from GleambookUsers g where edit_distance(c.name, g.name)
<= 2) as gUsers FROM CUsers c;
{code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)