annotate split.xml @ 0:92509cf500a4 draft default tip

"planemo upload for repository https://github.com/shenwei356/csvtk commit 3a97e1b79bf0c6cdd37d5c8fb497b85531a563ab"

<tool id="csvtk_split" name="csvtk-split" version="@VERSION@+@GALAXY_VERSION@">
    <description>table into multiple files</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_cmd" />
    <command detect_errors="exit_code"><![CDATA[

## Create directory and set input name ##
#########################################
mkdir -p ./output &&

#set input_name = str($in_1.name)
ln -s '$in_1' $input_name &&

###################
## Start Command ##
###################

csvtk split -o ./output --num-cpus "\${GALAXY_SLOTS:-1}"

    ## Add additional flags as specified ##
    #######################################
    $ignore_case
    $global_param.illegal_rows
    $global_param.empty_rows
    $global_param.header
    $global_param.lazy_quotes

    ## Set Tabular input/output flag if input is tabular ##
    #######################################################
    #if $in_1.is_of_type("tabular"):
        -t -T
    #end if

    ## Set Input ##
    ###############
    '$input_name'

    ## Specify fields for splitting ##
    ##################################
    -F -f '$column_text.in_text'

    ]]></command>
    <inputs>
        <expand macro="singular_input" />
        <expand macro="fields_input" />
        <expand macro="ignore_case" />
        <expand macro="global_parameters" />
    </inputs>
    <outputs>
        <collection name="list_split" type="list" label="${in_1.name} split on column ${column_text.in_text}">
            <discover_datasets pattern="__designation_and_ext__" directory="output" visible="false" format="csv,tabular"/>
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="in_1" value="csv.csv" />
            <conditional name="column_text">
                <param name="select" value="string" />
                <param name="in_text" value="1" />
            </conditional>
            <param name="ignore_case" value="true" />
            <output_collection name="list_split" type="list">
                <element name="csv-bob" file="csv-bob.csv" ftype="csv" />
                <element name="csv-darian" file="csv-darian.csv" ftype="csv" />
                <element name="csv-jack" file="csv-jack.csv" ftype="csv" />
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
    
Csvtk - Split Help
------------------

Info
####
Split input csv/tsv files into multiple csv/tsv files based on a column number(s) or name(s).

This tool will generate as many output files as there are unique data points in the selected column(s).

Examples below.

.. class:: warningmark

    Single quotes are not allowed in text inputs!

@HELP_INPUT_DATA@


Usage
#####
Here we will demonstrate what the tool does when 1 column is selected or when 2+ columns are selected.

**Ex. Split input based on column 1:**

::

    Suppose we have the following input table that we want to split on column 2, the 'Colour' column:

    +--------+--------+----------+
    | Name   | Colour | Food     |
    +========+========+==========+
    | Eric   | Blue   | Apples   |
    +--------+--------+----------+
    | Darian | Blue   | Pancakes |
    +--------+--------+----------+
    | Daniel | Red    | Apples   |
    +--------+--------+----------+
    | Frank  | Blue   | Apples   |
    +--------+--------+----------+

    --------------------------------------------------------------------------------

    Splitting would yield the following 2 tables:

    +--------+--------+----------+
    | Name   | Colour | Food     |
    +========+========+==========+           +--------+--------+----------+
    | Eric   | Blue   | Apples   |           | Name   | Colour | Food     |
    +--------+--------+----------+     +     +========+========+==========+ 
    | Darian | Blue   | Pancakes |           | Daniel | Red    | Apples   |
    +--------+--------+----------+           +--------+--------+----------+
    | Frank  | Blue   | Apples   |
    +--------+--------+----------+

    ---------------------------------------------------------------------------------

----

**Ex. Split on 2 columns:**

::

    Suppose keep the same input but instead split on both the 'Colour' and 'Food' columns:

    +--------+--------+----------+
    | Name   | Colour | Food     |
    +========+========+==========+
    | Eric   | Blue   | Apples   |
    +--------+--------+----------+
    | Darian | Blue   | Pancakes |
    +--------+--------+----------+
    | Daniel | Red    | Apples   |
    +--------+--------+----------+
    | Frank  | Blue   | Apples   |
    +--------+--------+----------+

    --------------------------------------------------------------------------------------------------------

    This split would yield the following three output files:

    +--------+--------+----------+
    | Name   | Colour | Food     |       +--------+--------+----------+       +--------+--------+----------+
    +========+========+==========+       | Name   | Colour | Food     |       | Name   | Colour | Food     |
    | Eric   | Blue   | Apples   |   +   +========+========+==========+   +   +========+========+==========+
    +--------+--------+----------+       | Darian | Blue   | Pancakes |       | Daniel | Red    | Apples   |
    | Frank  | Blue   | Apples   |       +--------+--------+----------+       +--------+--------+----------+
    +--------+--------+----------+

    Here, the value in the cell has to match for both columns for them to be output together. Frank and Eric
    like apples and the colour blue so they get put together. And even though Darian likes the colour blue, he
    prefers pancakes and thus gets his own output file.

----

@HELP_END_STATEMENT@


    ]]></help>
    <expand macro="citations" />
</tool>