annotate separate.xml @ 0:1be50033b476 draft default tip

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

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

#set column_number = $column_names.count(',') + 1

###################
## Start Command ##
###################
csvtk separate --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 first input is tabular ##
    #############################################################
    #if $in_1.is_of_type("tabular"):
        -t -T
    #end if

    ## Set input files ##
    #####################
    $in_1

    ## Specify field to use ##
    ##########################
    -f '$column_text.in_text'

    ## Specific inputs ##
    #####################
    -n '$column_names'
    -N '$column_number'

    #if $how_separate.how == 'sep'
        -s '$how_separate.separator'
    #else
        -r '($how_separate.separator)'
    #end if

    --na '$fill_na'
    $extra_data
    $remove
    
    ## To output ##
    ###############
    > separated

    ]]></command>
    <inputs>
        <expand macro="singular_input"/>
        <expand macro="singular_fields_input"/>
        <conditional name="how_separate">
            <param name="how" type="select" label="Separate input column by:"> 
                <option value="sep">Separator String</option>
                <option value="regex">Regexp</option>
            </param>
            <when value="sep">
                <param name="separator" type="text" value="; " argument="-s"
                    label="Separator string"
                    help="Specify what string separates the data in the column">
                    <expand macro="text_sanitizer" />
                </param>
            </when>
            <when value="regex">
                <param name="separator" type="text" value=".+" argument="-r"
                    label="Set regex search pattern"
                    help="Use regex to match input column information. Example: ^(.+)$ will match all characters.
                    Regex help can be found below. The ' character is invalid">
                    <expand macro="text_sanitizer" />
                </param>
            </when>
        </conditional>
        <param name="column_names" type="text" value="new1,new2" argument="-n"
            label="Specify new column name(s)"
            help="More than one column can be made by separating the names by a comma (,). Ex. 'Genus,Species' would create two columns.">
            <expand macro="text_sanitizer" />
        </param>
        <param name="extra_data" type="select" label="Handle extra data by:"
            help="Extra data is data that does not fit into the new columns made. An example can be found below">
            <option value="--drop">Dropping it</option>
            <option value="--merge">Merging it</option>
        </param>
        <param name="fill_na" type="text" value="NA" argument="--na"
            label="Character string to fill empty columns">
            <expand macro="text_sanitizer" />
        </param>
        <param name="remove" type="boolean" checked="true" argument="-R"
            truevalue="-R"
            falsevalue=""
            label="Remove input column"
        />
        <expand macro="ignore_case" />
        <expand macro="global_parameters" />
    </inputs>
    <outputs>
        <data format_source="in_1" from_work_dir="separated" name="separated" label="${in_1.name} column ${column_text.in_text} separated by ${how_separate.separator}" />
    </outputs>
    <tests>
        <test>
            <param name="in_1" value="collapsed.tsv" />
            <conditional name="column_text">
                <param name="select" value="string" />
                <param name="in_text" value="2" />
            </conditional>
            <conditional name="how_separate">
                <param name="how" value="sep" />
                <param name="separator" value="; " />
            </conditional>
            <param name="column_names" value="1,2" />
            <param name="fill_na" value="NA" />
            <param name="extra_data" value="--drop" />
            <param name="remove" value="true" />
            <output name="separated" file="separated_1.tsv" ftype="tabular" />
        </test>
        <test>
            <param name="in_1" value="collapsed.tsv" />
            <conditional name="column_text">
                <param name="select" value="string" />
                <param name="in_text" value="2" />
            </conditional>
            <conditional name="how_separate">
                <param name="how" value="sep" />
                <param name="separator" value="; " />
            </conditional>
            <param name="column_names" value="1,2" />
            <param name="fill_na" value="N/A" />
            <param name="extra_data" value="--merge" />
            <param name="remove" value="false" />
            <output name="separated" file="separated_2.tsv" ftype="tabular" />
        </test>
    </tests>
    <help><![CDATA[
    
Csvtk - Separate Help
---------------------

Info
####

Csvtk-separate separates columns into new columns based on either an input string or a regex expression.

The regex input for this tool is structured such that your regular expression **does not** need to start with with quotes or brackets. You can
start your expression with a `^` or just go straight into it

For example:

::

    Using `.+` as an input would be used in the code as '(.+)'

    Using ^(.+)$ as an input would yield an input in the code as '(^(.+)$)'

.. class:: warningmark

    Single quotes are not allowed in text inputs!

----


@HELP_INPUT_DATA@


Usage
#####

**Ex. Separate with Dropping Data**

Suppose we had the following table and wanted to separate the scientific name column to create two new columns called genus and species:

+------------+------------------------------+
| Name       | Scientific Name              |
+============+==============================+
| Red Fox    | Vulpes vulpes                |
+------------+------------------------------+
| Salmonella | Salmonella enterica enterica |
+------------+------------------------------+

First, we set our separator to string and use just a space (' ') as the separator as the names are separated by spaces.

Then, we have to set the new column names which can be done by setting the column names to 'Genus,Species' (make sure that the names are
separated by a comma).

Finally, we have to decide if we want to drop the input column and if we want to merge the additional data or drop it.

First table will show dropping of additional data (the second enterica is additional as it cannot fit in its own column)

+------------+------------+----------+
| Name       | Genus      | Species  |
+============+============+==========+
| Red Fox    | Vulpes     | vulpes   |
+------------+------------+----------+
| Salmonella | Salmonella | enterica |
+------------+------------+----------+

|

Here is what it would look like if we merged data instead:

+------------+------------+-------------------+
| Name       | Genus      | Species           |
+============+============+===================+
| Red Fox    | Vulpes     | vulpes            |
+------------+------------+-------------------+
| Salmonella | Salmonella | enterica enterica |
+------------+------------+-------------------+

----


@HELP_COLUMNS@


@HELP_END_STATEMENT@


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