Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- set mongo.input.query {"date":{"\$gt":{"\$date":$MAX_DATE}}}
- set mongo.input.split.create_input_splits false
- actions_taken =
- LOAD '$BUFFER_METRICS_MONGO_URI.event.seamless.actions_taken'
- USING com.mongodb.hadoop.pig.MongoLoader(
- 'user_id:chararray,
- visitor_id:chararray,
- client_id:chararray,
- last_modified:chararray,
- date:chararray,
- user_joined_at:chararray,
- value:bag{t:tuple()},
- extra_data:chararray'
- );
- extract = foreach actions_taken generate
- user_id,
- visitor_id,
- client_id,
- last_modified,
- user_joined_at,
- date,
- value,
- extra_data
- ;
- rmf $OUTPUT_PATH/extract-actions-taken;
- store extract into '$OUTPUT_PATH/extract-actions-taken' using PigStorage();
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement