| #------------------------------------------------------------- |
| # |
| # 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. |
| # |
| #------------------------------------------------------------- |
| |
| # input frame contain two columns of actual words and their stemmed equivalents |
| words = read($1, data_type = "frame", header = TRUE, format = "csv") |
| stemmed = map(words[, 1], "x -> PorterStemmer.stem(x)") |
| # write the results from the stemmer |
| write(stemmed, $2, format = "csv") |
| # write the dictionary equivalents for matching in java file |
| equ = words[, 2] |
| write(equ, $3, format = "csv") |
