Mercurial > repos > bgruening > split_file_on_column
changeset 2:90b52d8d6f2c draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/split_file_on_column commit 36d05738e78c68091b45779624734e6a47829856-dirty
| author | bgruening |
|---|---|
| date | Wed, 26 Aug 2015 07:32:06 -0400 |
| parents | 0ba6d09a71d6 |
| children | b60f2452580e |
| files | split_file_on_column.tar.gz split_file_on_column.xml test-data/5cols.tabular tool_dependencies.xml |
| diffstat | 4 files changed, 35 insertions(+), 11 deletions(-) [+] |
line wrap: on
line diff
--- a/split_file_on_column.xml Wed Dec 18 10:57:09 2013 -0500 +++ b/split_file_on_column.xml Wed Aug 26 07:32:06 2015 -0400 @@ -1,38 +1,56 @@ -<tool id="tp_split_on_column" name="Split file" force_history_refresh="True" version="0.1.1"> +<tool id="tp_split_on_column" name="Split file" version="0.2"> <description>according to the values of a column</description> <requirements> <requirement type="package" version="4.1.0">gnu_awk</requirement> </requirements> <command> - awk -F'\t' '{print > "primary_${outfile.id}_" \$$column "_visible_${infile.ext}" }' $infile; - echo 'Created' `ls -l | wc -l` 'files:' > $outfile; - ls -1 --hide="*_stdout" --hide="*_stderr" >> $outfile; +<![CDATA[ + awk -F'\t' '{print > \$$column ".$infile.ext" }' $infile +]]> </command> - <inputs> - <param format="txt" name="infile" type="data" label="File to select" /> + <param format="tabular" name="infile" type="data" label="File to select" /> <param name="column" label="on column" type="data_column" data_ref="infile" accept_default="true" /> </inputs> - <outputs> + <collection name="split_output" type="list" label="Table split on first column"> + <discover_datasets pattern="__name_and_ext__" directory="." /> + </collection> + </outputs> + <!--outputs> <data format="input" name="outfile" metadata_source="infile" label="${tool.name} on ${on_string}"/> - </outputs> + </outputs--> <tests> <test> + <param name="infile" value="5cols.tabular" ftype="tabular"/> + <param name="column" value="5" /> + <output_collection name="split_output" type="list"> + <element name="1"> + <assert_contents> + <has_text_matching expression="chr7\t56632\t56652\tcluster\t1" /> + </assert_contents> + </element> + <element name="2"> + <assert_contents> + <has_text_matching expression="chr7\t56761\t56781\tcluster\t2" /> + </assert_contents> + </element> + </output_collection> </test> </tests> <help> +<![CDATA[ **What it does** -This tool splits a file into different smaller files using a specific column. +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:: +Splitting on column 5 from this:: chr7 56632 56652 cluster 1 chr7 56736 56756 cluster 1 @@ -51,5 +69,6 @@ chr7 56775 56795 cluster 2 +]]> </help> </tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/5cols.tabular Wed Aug 26 07:32:06 2015 -0400 @@ -0,0 +1,5 @@ +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
--- a/tool_dependencies.xml Wed Dec 18 10:57:09 2013 -0500 +++ b/tool_dependencies.xml Wed Aug 26 07:32:06 2015 -0400 @@ -1,6 +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" /> + <repository changeset_revision="52a8268bb49f" name="package_gnu_awk_4_1_0" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> </package> </tool_dependency>