cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Mikhail Krupitskiy (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (CASSANDRA-12573) SASI index. Incorrect results for '%foo%bar%'-like search pattern.
Date Wed, 31 Aug 2016 21:09:21 GMT

     [ https://issues.apache.org/jira/browse/CASSANDRA-12573?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Mikhail Krupitskiy updated CASSANDRA-12573:
-------------------------------------------
    Description: 
We use Cassandra 3.7 and have faced a strange behaviour of SELECT requests with 'LIKE '%foo%bar%''
constraints on a column with SASI index.
Below are few experiments that shows this behaviour.

Experiment 1:
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int primary key, c1 text, c2 text);

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w%a%';
{noformat}
Expected result: qweasd, qwea1.
Actual result: no rows.


Experiment 2 (NOTE: definition of index is changed):
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int primary key, c1 text, c2 text);

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS',
 'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
 'analyzed': 'true'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w%a%';
{noformat}
Expected result: qweasd, qwea1.
Actual result: 1qwe.

Experiment 3 (NOTE: primary key is compound now):
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int, c1 text, c2 text, PRIMARY KEY(id, c1));

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS',
 'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
 'analyzed': 'true'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w%a%';
{noformat}
Expected result: qweasd, qwea1.
Actual result: qwe, qweasd, qwea1, 1qwe.

Experiment 4 (NOTE: search criteria is changed):
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int, c1 text, c2 text, PRIMARY KEY(id, c1));

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS',
 'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
 'analyzed': 'true'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w22%a%';
{noformat}
Expected result: no rows.
Actual result: qweasd, qwea1.

  was:
We use Cassandra 3.7 and have faced a strange behaviour of SELECT requests with 'LIKE '%foo%bar%''
constraints on a column with SASI index.
Below are few experiments that shows this behaviour.

Experiment 1:
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int primary key, c1 text, c2 text);

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w%a%';
{noformat}
Expected result: qweasd, qwea1.
Actual result: no rows.


Experiment 2 (NOTE: definition of index is changed):
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int primary key, c1 text, c2 text);

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS',
 'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
 'analyzed': 'true'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w%a%';
{noformat}
Expected result: qweasd, qwea1.
Actual result: 1qwe.

Experiment 3 (NOTE: primary key is compound now):
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int, c1 text, c2 text, PRIMARY KEY(id, c1));

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS',
 'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
 'analyzed': 'true'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w%a%';
{noformat}
Expected result: qweasd, qwea1.
Actual result: qwe, qweasd, qwea1, 1qwe.

Experiment 4 (NOTE: search criteria is changed):
{noformat}
drop keyspace if exists kmv;
create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;

use kmv;

CREATE TABLE if not exists kmv (id int, c1 text, c2 text, PRIMARY KEY(id, c1));

CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex' WITH
OPTIONS = {
 'mode': 'CONTAINS',
 'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
 'analyzed': 'true'
};

insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;

select c2 from kmv.kmv where c2 like '%w22%a%';
{noformat}
Expected result: qweasd, qwea1.
Actual result: qweasd, qwea1.


> SASI index. Incorrect results for '%foo%bar%'-like search pattern. 
> -------------------------------------------------------------------
>
>                 Key: CASSANDRA-12573
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-12573
>             Project: Cassandra
>          Issue Type: Bug
>            Reporter: Mikhail Krupitskiy
>            Assignee: Arunkumar M
>            Priority: Critical
>
> We use Cassandra 3.7 and have faced a strange behaviour of SELECT requests with 'LIKE
'%foo%bar%'' constraints on a column with SASI index.
> Below are few experiments that shows this behaviour.
> Experiment 1:
> {noformat}
> drop keyspace if exists kmv;
> create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;
> use kmv;
> CREATE TABLE if not exists kmv (id int primary key, c1 text, c2 text);
> CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex'
WITH OPTIONS = {
>  'mode': 'CONTAINS'
> };
> insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
> insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
> insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
> insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;
> select c2 from kmv.kmv where c2 like '%w%a%';
> {noformat}
> Expected result: qweasd, qwea1.
> Actual result: no rows.
> Experiment 2 (NOTE: definition of index is changed):
> {noformat}
> drop keyspace if exists kmv;
> create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;
> use kmv;
> CREATE TABLE if not exists kmv (id int primary key, c1 text, c2 text);
> CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex'
WITH OPTIONS = {
>  'mode': 'CONTAINS',
>  'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
>  'analyzed': 'true'
> };
> insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
> insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
> insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
> insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;
> select c2 from kmv.kmv where c2 like '%w%a%';
> {noformat}
> Expected result: qweasd, qwea1.
> Actual result: 1qwe.
> Experiment 3 (NOTE: primary key is compound now):
> {noformat}
> drop keyspace if exists kmv;
> create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;
> use kmv;
> CREATE TABLE if not exists kmv (id int, c1 text, c2 text, PRIMARY KEY(id, c1));
> CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex'
WITH OPTIONS = {
>  'mode': 'CONTAINS',
>  'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
>  'analyzed': 'true'
> };
> insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
> insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
> insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
> insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;
> select c2 from kmv.kmv where c2 like '%w%a%';
> {noformat}
> Expected result: qweasd, qwea1.
> Actual result: qwe, qweasd, qwea1, 1qwe.
> Experiment 4 (NOTE: search criteria is changed):
> {noformat}
> drop keyspace if exists kmv;
> create keyspace if not exists kmv WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor':'1'}
;
> use kmv;
> CREATE TABLE if not exists kmv (id int, c1 text, c2 text, PRIMARY KEY(id, c1));
> CREATE CUSTOM INDEX ON kmv.kmv  ( c2 ) USING 'org.apache.cassandra.index.sasi.SASIIndex'
WITH OPTIONS = {
>  'mode': 'CONTAINS',
>  'analyzer_class': 'org.apache.cassandra.index.sasi.analyzer.StandardAnalyzer',
>  'analyzed': 'true'
> };
> insert into kmv (id, c1, c2) values (1, 'f21', 'qwe') ;
> insert into kmv (id, c1, c2) values (1, 'f22', 'qweasd') ;
> insert into kmv (id, c1, c2) values (1, 'f23', 'qwea1') ;
> insert into kmv (id, c1, c2) values (1, 'f24', '1qwe') ;
> select c2 from kmv.kmv where c2 like '%w22%a%';
> {noformat}
> Expected result: no rows.
> Actual result: qweasd, qwea1.



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

Mime
View raw message