comparison uniq.xml @ 0:07d1c048ec1b draft default tip

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

0:07d1c048ec1b

<tool id="csvtk_uniq" name="csvtk-unique" version="@VERSION@+@GALAXY_VERSION@">
    <description> first values in column(s)</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_cmd" />
    <command detect_errors="exit_code"><![CDATA[

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

csvtk uniq --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 ##
    ###############
    '$in_1'

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

    ## If Only Wanted input columns ##
    ##################################
    #if $only_input_columns == 'Yes'
        | csvtk cut -F -f '$column_text.in_text'

        #if $in_1.is_of_type("tabular"):
            -t -T
        #end if
    #end if

    ## To output ##
    ###############
    > uniq

    ]]></command>
    <inputs>
        <expand macro="singular_input" />
        <expand macro="fields_input" />
        <expand macro="ignore_case" />
        <param name="only_input_columns" type="boolean"
            truevalue="Yes"
            falsevalue="No"
            label="Keep only input column(s)"
            help="All columns not specified as part of the input will be removed"
        />
        <expand macro="global_parameters" />
    </inputs>
    <outputs>
        <data format_source="in_1" name="uniq" from_work_dir="uniq" label="${in_1.name} unique values in column(s) ${column_text.in_text}" />
    </outputs>
    <tests>
        <test>
            <param name="in_1" value="blood_type.tsv" />
            <conditional name="column_text">
                <param name="select" value="string" />
                <param name="in_text" value="2,3" />
            </conditional>
            <output name="uniq" file="uniq.tsv" ftype="tabular" />
        </test>
    </tests>
    <help><![CDATA[
    
Csvtk - Unique Help
-------------------

Info
####

Csvtk unique pulls the first unique values from the column(s) specified to create

.. class:: warningmark

    Single quotes are not allowed in text inputs!

@HELP_INPUT_DATA@


Usage
#####

To run csvtk-uniq, all you need is a valid (as defined above) CSV or TSV and the column(s) that you want the to find unique values in.

**Ex. Unique on one column:**

Suppose you had a table as such

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

If you ran csvtk-unique on the Colour column, you would end up with the following table:

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

As only the first instance of the value in the column is kept.

----

**Ex. Unique on more than one column:**

Same input table

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

Now if you ran csvtk-unique on the Colour and Food column, you would end up with the following table:

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

Only the last row was not kept as there was already a unique pair found of "Blue" and "Apples".

**Note:** If you want to only have the unique values of the columns and get rid of the additional columns, run a "cut program" to cut out the wanted columns
and then csvtk unique to only get the wanted values.

----

@HELP_COLUMNS@


@HELP_END_STATEMENT@


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