/*
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *   http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied.  See the License for the
 * specific language governing permissions and limitations
 * under the License.
 */
/*
* Description  : Create an external dataset that contains a tuples, the lines from a large (35kb) text file in HDFS.
                 The input file is sufficiently large to guarantee that # of bytes > than internal buffer of size 8192.
                 This causes a record to span across the buffer size boundaries.
                 Perform a word-count over the data in the dataset.
* Expected Res : Success
* Date         : 7th Jan 2013
*/

drop  dataverse test if exists;
create  dataverse test;

use test;


create type test.LineType as
 closed {
  content : string
}

create external  dataset TextDataset(LineType) using `hdfs`((`hdfs`=`hdfs://127.0.0.1:31888`),(`path`=`/asterix/large_text`),(`input-format`=`text-input-format`),(`format`=`delimited-text`),(`delimiter`=`.`));