Mercurial > repos > bgruening > split_file_on_column
changeset 0:ad6a989924ac draft
Uploaded
author | bgruening |
---|---|
date | Tue, 17 Dec 2013 15:24:50 -0500 |
parents | |
children | 0ba6d09a71d6 |
files | split_file_on_column.xml tool_dependencies.xml |
diffstat | 2 files changed, 61 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/split_file_on_column.xml Tue Dec 17 15:24:50 2013 -0500 @@ -0,0 +1,55 @@ +<tool id="tp_split_on_column" name="Split file" force_history_refresh="True" version="0.1.1"> + <description>according to the values of a column</description> + <requirements> + <requirement type="package" version="4.1.0">gnu_awk</requirement> + </requirements> + <command> + awk '{print > "primary_${outfile.id}_" \$$column "_visible_${infile.ext}" }' $infile; + echo 'Created' `ls -l | wc -l` 'files:' > $outfile; + ls -1 --hide="*_stdout" --hide="*_stderr" >> $outfile; + </command> + + <inputs> + <param format="txt" name="infile" type="data" label="File to select" /> + <param name="column" label="on column" type="data_column" data_ref="infile" accept_default="true" /> + </inputs> + + <outputs> + <data format="input" name="outfile" metadata_source="infile" label="${tool.name} on ${on_string}"/> + </outputs> + <tests> + <test> + </test> + </tests> + <help> + +**What it does** + +This tool splits a file into different smaller files using a specific column. +It will work like the group tool, but every group is saved to its own file. + +----- + +**Example** + +Splitting on column 4 from this:: + + chr7 56632 56652 cluster 1 + chr7 56736 56756 cluster 1 + chr7 56761 56781 cluster 2 + chr7 56772 56792 cluster 2 + chr7 56775 56795 cluster 2 + +will produce 2 files with different clusters:: + + chr7 56632 56652 cluster 1 + chr7 56736 56756 cluster 1 + + + chr7 56761 56781 cluster 2 + chr7 56772 56792 cluster 2 + chr7 56775 56795 cluster 2 + + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Tue Dec 17 15:24:50 2013 -0500 @@ -0,0 +1,6 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="gnu_awk" version="4.1.0"> + <repository changeset_revision="ec65852050ef" name="package_gnu_awk_4_1_0" owner="iuc" toolshed="http://toolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency>