<tool id="csvtk_mutate" name="csvtk-mutate" version="@VERSION@+@GALAXY_VERSION@">
    <description>new column by regular expression</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_cmd" />
    <command detect_errors="exit_code"><![CDATA[

###################
## Start Command ##
###################
csvtk mutate --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 fields to use ##
    ###########################
    -f '${column_text.in_text}'
    
    ## Column Name and pattern ##
    ############################
    -n '$column_name_input'
    -p '($pattern_input)'
    $remove
    $fill_na
    
    ## To output ##
    ###############
    > mutated

    ]]></command>
    <inputs>
        <expand macro="singular_input"/>
        <conditional name="column_text" >
            <param type="select" name="select" label="Select column based on" argument="-f">
                <option value="string">Column Name</option>
                <option value="column">Column Number</option>
            </param>
            <when value="column">
                <param type="data_column" name="in_text"
                        data_ref="in_1"
                        multiple="False" force_select="True"
                        label="Analyze column number"
                        help="Select column to mutate data from"
                        />
            </when>
            <when value="string">
                <param type="text" name="in_text"
                    optional="False"
                    label="Analyze column name"
                    help="Specify column name to pull data out of with Regex"
                    />
            </when>
        </conditional>
        <param type="text" name="pattern_input"
            value=".+"
            argument="-p"
            label="Set regex search pattern"
            optional="false"
            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>
        <param type="text" name="column_name_input"
            value="new_column"
            argument="-n"
            label="Set new column name"
            optional="false"
            help="Specify output column name for the matched data">
            <expand macro="text_sanitizer" />
        </param>
        <param type="boolean" name="fill_na"
            falsevalue="--na" truevalue=""
            checked="true"
            label="Fill Non-matches"
            help="If NO, mutate will create a blank cell where no regex matches (--na). If YES the full cell value will be copied of non-matched columns"
        />
        <param name="remove" type="boolean" checked="false"
            falsevalue=""
            truevalue="-R"
            argument="-R"
            label="Remove input column"
        />
        <expand macro="ignore_case" />
        <expand macro="global_parameters" />
    </inputs>
    <outputs>
        <data format_source="in_1" name="mutated" from_work_dir="mutated" 
        label='${in_1.name} mutated by column ${column_text.in_text} with pattern ${pattern_input}' />
    </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="1" />
            </conditional>
            <param name="column_name_input" value="new_column" />
            <param name="pattern_input" value=".*" />
            <output name="mutated" file="mutated.tsv" ftype="tabular" />
        </test>
        <test>
            <param name="in_1" value="blood_type.tsv" />
            <conditional name="column_text">
                <param name="select" value="string" />
                <param name="in_text" value="1" />
            </conditional>
            <param name="column_name_input" value="new_column" />
            <param name="pattern_input" value="Darian" />
            <param name="remove" value="true" />
            <param name="fill_na" value="false" />
            <output name="mutated" file="mutate_removed.tsv" ftype="tabular" />
        </test>
    </tests>
    <help><![CDATA[
    
Csvtk - Mutate Help
-------------------

Info
####
Csvtk-mutate is a tool that uses Regular Expressions (Regex) to match data in the specified column. Using this matched data, a
new column is created using that matched data.

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
#####
You can use csvtk to mutate a new column with data matched through regular expressions(regex).

A good Regular expressions cheat sheet that you can use to help yourself build regular expressions can be found at:
https://regexr.com/

**Mutate Examples**

::

    Mutate with Filling empty columns when no regex match:

    Suppose we have the following table and we want to pull out all of the exponent in the column "Colonies"
    without pulling out any of the other characters to make a new column called "Exponent":
    
    +-------------+----------+-----------+
    | Colonies    | Catalase | Coagulase |
    +=============+==========+===========+
    | 1x10^15 cfu | Yes      | No        |
    +-------------+----------+-----------+
    | 1x10^14 cfu | No       | No        |
    +-------------+----------+-----------+
    | 1x10^18 cfu | Yes      | No        |
    +-------------+----------+-----------+
    | 100 cfu     | No       | Yes       |
    +-------------+----------+-----------+ 

    We would use a Regex expression similar to (\^)(\d+) to get the "^" and the exponent into a new
    column giving the following result:

    +-------------+----------+-----------+----------+
    | Colonies    | Catalase | Coagulase | Exponent |
    +=============+==========+===========+==========+
    | 1x10^15 cfu | Yes      | No        | ^15      |
    +-------------+----------+-----------+----------+
    | 1x10^14 cfu | No       | No        | ^14      |
    +-------------+----------+-----------+----------+
    | 1x10^18 cfu | Yes      | No        | ^18      |
    +-------------+----------+-----------+----------+
    | 100 cfu     | No       | Yes       | 100 cfu  | 
    +-------------+----------+-----------+----------+

    As you can see we still have "100 cfu" at the bottom even though it doesn't contain a "^" as we
    did not specify that we wanted to make non-matches blank, we copied over the 100 cfu.

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

    Mutate leaving columns blank with no regex match:

    Suppose we had the same chart as above:

    +-------------+----------+-----------+
    | Colonies    | Catalase | Coagulase |
    +=============+==========+===========+
    | 1x10^15 cfu | Yes      | No        |
    +-------------+----------+-----------+
    | 1x10^14 cfu | No       | No        |
    +-------------+----------+-----------+
    | 1x10^18 cfu | Yes      | No        |
    +-------------+----------+-----------+
    | 100 cfu     | No       | Yes       |
    +-------------+----------+-----------+ 

    Now, if we were to set "Fill Non-matches" to "No", then we would get the following table using the same inputs
    other than the change to fill non-matches:

    +-------------+----------+-----------+----------+
    | Colonies    | Catalase | Coagulase | Exponent |
    +=============+==========+===========+==========+
    | 1x10^15 cfu | Yes      | No        | ^15      |
    +-------------+----------+-----------+----------+
    | 1x10^14 cfu | No       | No        | ^14      |
    +-------------+----------+-----------+----------+
    | 1x10^18 cfu | Yes      | No        | ^18      |
    +-------------+----------+-----------+----------+
    | 100 cfu     | No       | Yes       |          | 
    +-------------+----------+-----------+----------+

----

If your having trouble with the regular expressions, please play around with a builder, there are many others online 
and they are great resources to improve your regex statements or test them before use!

----

@HELP_END_STATEMENT@


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