| /* |
| * 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. |
| */ |
| drop dataverse twitter if exists; |
| create dataverse twitter; |
| use dataverse twitter; |
| |
| create type Tweet as open { |
| id: int32, |
| tweetid: int64, |
| loc: point, |
| time: datetime, |
| text: string |
| } |
| |
| create external dataset TwitterData(Tweet) |
| using "org.apache.asterix.external.dataset.adapter.NCFileSystemAdapter" |
| (("path"="nc1://data/twitter/smalltweets.txt"),("format"="adm")); |
| |
| write output to nc1:"/tmp/count-tweets.adm"; |
| |
| for $t in dataset('TwitterData') |
| let $tokens := word-tokens($t.text) |
| for $token in $tokens |
| group by $tok := $token with $token |
| return { "word": $tok, "count": count($token) } |
| |