Mercurial > repos > bgruening > text_processing
diff unsorted_uniq.xml @ 0:5314e5d6f040 draft
Imported from capsule None
author | bgruening |
---|---|
date | Thu, 29 Jan 2015 07:53:17 -0500 |
parents | |
children | 60edf2f8c28f |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/unsorted_uniq.xml Thu Jan 29 07:53:17 2015 -0500 @@ -0,0 +1,93 @@ +<tool id="tp_sorted_uniq" name="Unique" version="@BASE_VERSION@.0"> + <description>occurrences of each record</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <version_command>sort --version | head -n 1</version_command> + <command> +<![CDATA[ + sort -u + $ignore_case + $is_numeric + -t ' ' + #if $adv_opts.adv_opts_selector == "advanced": + -k$adv_opts.column_start,$adv_opts.column_end + #end if + -o "$outfile" + "$infile" +]]> + </command> + <inputs> + <param name="infile" type="data" format="tabular" label="File to scan for unique values" /> + <param name="ignore_case" type="boolean" truevalue="-f" falsevalue="" checked="False" + label="Ignore differences in case when comparing" help="(-f)"/> + <param name="is_numeric" type="boolean" truevalue="-n" falsevalue="" checked="False" + label="Column only contains numeric values" help="(-n)" /> + <conditional name="adv_opts"> + <param name="adv_opts_selector" type="select" label="Advanced Options"> + <option value="basic" selected="True">Hide Advanced Options</option> + <option value="advanced">Show Advanced Options</option> + </param> + <when value="basic" /> + <when value="advanced"> + <param name="column_start" type="data_column" data_ref="infile" label="Column start" help="Unique on specific column range"/> + <param name="column_end" type="data_column" data_ref="infile" label="Column end" help="Unique on specific column range"/> + </when> + </conditional> + </inputs> + <outputs> + <data name="outfile" format_source="infile" metadata_source="infile"/> + </outputs> + <tests> + <test> + <param name="infile" value="1.bed"/> + <param name="is_numeric" value="True"/> + <param name="ignore_case" value="True"/> + <param name="adv_opts_selector" value="advanced"/> + <param name="column_start" value="2"/> + <param name="column_end" value="3"/> + <output name="outfile" file="unique_results1.bed"/> + </test> + </tests> + <help> +<![CDATA[ + .. class:: infomark + +**Syntax** + +This tool returns all unique lines using the 'sort -u' command. It can be used with unsorted files. +If you need additional options, like grouping or counting your unique results, please use the 'Unique lines from sorted file' tool. + +----- + +.. class:: infomark + +The input file needs to be tab separated. Please convert your file if necessary. + +----- + +**Example** + +- Input file:: + + chr1 10 100 gene1 + chr1 105 200 gene2 + chr1 10 100 gene1 + chr2 10 100 gene4 + chr2 1000 1900 gene5 + chr3 15 1656 gene6 + chr2 10 100 gene4 + +- Unique lines will result in:: + + chr1 10 100 gene1 + chr1 105 200 gene2 + chr2 10 100 gene4 + chr2 1000 1900 gene5 + chr3 15 1656 gene6 + +@REFERENCES@ +]]> +</help> +</tool>