The Document protocol handler parses complete text documents.
input = ACCESS({source='document', wrapper='GenericPush', transport='File',protocol='Document', dataHandler='Tuple',options=[['delay','100']], schema=[ ['content','String']] }) |
CREATE STREAM document (content String) WRAPPER 'GenericPush' PROTOCOL 'Document' TRANSPORT 'File' DATAHANDLER 'Tuple' OPTIONS ( 'delay' '100') |