Cathy Daw created CASSANDRA-4459:
------------------------------------
Summary: pig driver casts ints as bytearray
Key: CASSANDRA-4459
URL: https://issues.apache.org/jira/browse/CASSANDRA-4459
Project: Cassandra
Issue Type: Bug
Environment: C* 1.1.2 embedded in DSE
Reporter: Cathy Daw
Assignee: Brandon Williams
we seem to be auto-mapping C* int columns to bytearray in Pig, and farther down
I can't seem to find a way to cast that to int and do an average.
{code}
grunt> cassandra_users = LOAD 'cassandra://cqldb/users' USING
CassandraStorage();
grunt> dump cassandra_users;
(bobhatter,(act,22),(fname,bob),(gender,m),(highSchool,Cal
High),(lname,hatter),(sat,500),(state,CA),{})
(alicesmith,(act,27),(fname,alice),(gender,f),(highSchool,Tuscon
High),(lname,smith),(sat,650),(state,AZ),{})
// notice sat and act columns are bytearray values
grunt> describe cassandra_users;
cassandra_users: {key: chararray,act: (name: chararray,value: bytearray),fname:
(name: chararray,value: chararray),
gender: (name: chararray,value: chararray),highSchool: (name: chararray,value:
chararray),lname: (name: chararray,value: chararray),
sat: (name: chararray,value: bytearray),state: (name: chararray,value:
chararray),columns: {(name: chararray,value: chararray)}}
grunt> users_by_state = GROUP cassandra_users BY state;
grunt> dump users_by_state;
((state,AX),{(aoakley,(highSchool,Phoenix
High),(lname,Oakley),state,(act,22),(sat,500),(gender,m),(fname,Anne),{})})
((state,AZ),{(gjames,(highSchool,Tuscon
High),(lname,James),state,(act,24),(sat,650),(gender,f),(fname,Geronomo),{})})
((state,CA),{(philton,(highSchool,Beverly
High),(lname,Hilton),state,(act,37),(sat,220),(gender,m),(fname,Paris),{}),(jbrown,(highSchool,Cal
High),(lname,Brown),state,(act,20),(sat,700),(gender,m),(fname,Jerry),{})})
// Error - use explicit cast
grunt> user_avg = FOREACH users_by_state GENERATE cassandra_users.state,
AVG(cassandra_users.sat);
grunt> dump user_avg;
2012-07-22 17:15:04,361 [main] ERROR org.apache.pig.tools.grunt.Grunt - ERROR
1045: Could not infer the matching function for org.apache.pig.builtin.AVG as
multiple or none of them fit. Please use an explicit cast.
// Unable to cast as int
grunt> user_avg = FOREACH users_by_state GENERATE cassandra_users.state,
AVG((int)cassandra_users.sat);
grunt> dump user_avg;
2012-07-22 17:07:39,217 [main] ERROR org.apache.pig.tools.grunt.Grunt - ERROR
1052: Cannot cast bag with schema sat: bag({name: chararray,value: bytearray})
to int
{code}
*Seed data in CQL*
{code}
CREATE KEYSPACE cqldb with
strategy_class = 'org.apache.cassandra.locator.SimpleStrategy'
and strategy_options:replication_factor=3;
use cqldb;
CREATE COLUMNFAMILY users (
KEY text PRIMARY KEY,
fname text, lname text, gender varchar,
act int, sat int, highSchool text, state varchar);
insert into users (KEY, fname, lname, gender, act, sat, highSchool, state)
values (gjames, Geronomo, James, f, 24, 650, 'Tuscon High', 'AZ');
insert into users (KEY, fname, lname, gender, act, sat, highSchool, state)
values (aoakley, Anne, Oakley, m , 22, 500, 'Phoenix High', 'AX');
insert into users (KEY, fname, lname, gender, act, sat, highSchool, state)
values (jbrown, Jerry, Brown, m , 20, 700, 'Cal High', 'CA');
insert into users (KEY, fname, lname, gender, act, sat, highSchool, state)
values (philton, Paris, Hilton, m , 37, 220, 'Beverly High', 'CA');
select * from users;
{code}
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
