Mercurial > repos > stevecassidy > nltktools
diff g_stemmer.xml @ 0:e991d4e60c17 draft
planemo upload commit 0203cb3a0b40d9348674b2b098af805e2986abca-dirty
author | stevecassidy |
---|---|
date | Wed, 12 Oct 2016 22:17:53 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/g_stemmer.xml Wed Oct 12 22:17:53 2016 -0400 @@ -0,0 +1,36 @@ +<tool id="Stemmer" name="Stemmer" version="1.0"> + <description>Takes a list of tokens and generates a list of word stems using one of the stemming algorithms</description> + + <requirements> + <requirement type="package" version="3.2.1">nltk</requirement> + </requirements> + + <command interpreter="python"> + g_stemmer.py --input $input1 --output $tab_file --stemmer $stemming_algorithm + </command> + + <inputs> + <param name="input1" type="data" format="txt" label="Select a suitable input file from your history"/> + <param name="stemming_algorithm" type="select" label="Select the stemming algorithm to be used"> + <option value="lancaster">Lancaster Stemmer</option> + <option value="porter">Porter Stemmer</option> + <option value="snowball">Snowball English Stemmer</option> + </param> + <param name="job_name" type="text" size="25" + label="Supply a name for the outputs to remind you what they contain" value="Stemmer"/> + + </inputs> + <outputs> + <data format="tabular" name="tab_file" label="${job_name}"/> + + </outputs> + <options refresh="True"/> + <help> + <![CDATA[ + +Input is a list of tokens, uses one of the NLTK stemming algorithms to generate a list of word stems. + +]]> + + </help> +</tool>