view split_file_to_collection.xml @ 3:2ddc36385d7a draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/split_file_to_collection commit 8d069684e155d2f5b6fae06d14d98ce41321da53"

<tool id="split_file_to_collection" name="Split file" version="0.2.0">
    <description>to dataset collection</description>
    <macros>
        <xml name="regex_sanitizer">
            <sanitizer>
                <valid>
                    <add preset="string.printable"/>
                    <remove value="&#92;" />
                    <remove value="&apos;" />
                </valid>
                <mapping initial="none">
                    <add source="&#92;" target="__backslash__" />
                    <add source="&apos;" target="__sq__"/>
                </mapping>
            </sanitizer>
        </xml>
        <xml name="numnew_fname">
            <param name="numnew" type="integer" label="Number of new files" min="1" value="1"/>
            <param name="newfilenames" type="text" label="Base name for new files in collection"
                help="This will increment automatically - if input is 'file', then output is 'file0', 'file1', etc." value="split_file"/>
            <conditional name="select_allocate">
                <param name="allocate" type="select" label="Method to allocate records to new files" help="See the information section for a diagram">
                    <option value="random">At random</option>
                    <option value="batch">Maintain record order</option>
                    <option value="byrow" selected="true">Alternate output files</option>
                </param>
                <when value="random">
                    <param name="seed" type="integer" label="Random number seed" help="For reproducibility, set this to some arbitrary integer (i.e. '1010')" value="1010"/>
                </when>
                <when value="batch">
                </when>
                <when value="byrow">
                </when>
            </conditional>
        </xml>
    </macros>
    <requirements>
        <requirement type="package" version="3.5">python</requirement>
    </requirements>
    <command detect_errors="aggressive"><![CDATA[
        mkdir ./out &&
        python '$__tool_directory__/split_file_to_collection.py'
            --out ./out
            --in '$split_parms.input'
            --ftype '$split_parms.select_ftype'
            #if $split_parms.select_ftype == "tabular":
                --top '$split_parms.top'
                --by '$split_parms.split_by.select_split_by'
                #if $split_parms.split_by.select_split_by == "col":
                    --id_column '$split_parms.split_by.id_col'
                    --match '$split_parms.split_by.match_regex'
                    --sub '$split_parms.split_by.sub_regex'
                #else
                    --numnew '$split_parms.split_by.numnew'
                    #if $split_parms.split_by.select_allocate.allocate == "random":
                        --rand
                        --seed '$split_parms.split_by.rand.seed'
                    #end if
                    #if $split_parms.split_by.select_allocate.allocate == "batch":
                        --batch
                    #end if
                #end if
            #else
                #if $split_parms.select_ftype == "generic"
                    --generic_re '$split_parms.generic_regex'
                #end if
                --numnew '$split_parms.numnew'
                #if $split_parms.select_allocate.allocate == "random":
                    --rand
                    --seed '$split_parms.select_allocate.seed'
                #end if
                #if $split_parms.select_allocate.allocate == "batch":
                    --batch
                #end if
            #end if
        #if ($split_parms.select_ftype == "tabular" and $split_parms.split_by.select_split_by == "row"):
             --file_names '$split_parms.split_by.newfilenames'
             --file_ext '$split_parms.select_ftype'
        #end if
        #if $split_parms.select_ftype != "tabular":
            --file_names '$split_parms.newfilenames'
            #if $split_parms.select_ftype == "generic"
                --file_ext '$split_parms.input.ext'
            #else
                --file_ext '$split_parms.select_ftype'
            #end if
        #end if
    ]]></command>
    <inputs>
        <conditional name="split_parms">
            <param name="select_ftype" type="select" label="Select the file type to split">
                <option value="mgf">MGF</option>
                <option value="fastq">FASTQ</option>
                <option value="tabular">Tabular</option>
                <option value="fasta">FASTA</option>
                <option value="txt">Text files</option>
                <option value="generic">Generic</option>
            </param>
            <when value="tabular">
                <param name="input" type="data" format="tabular" label="Tabular file to split"/>
                <param name="top" type="integer" value="0" min="0" label="Number of header lines to transfer to new files"/>
                <conditional name="split_by">
                    <param name="select_split_by" type="select" label="Split by row or by a column?">
                        <option value="row">By row</option>
                        <option value="col">By column</option>
                    </param>
                    <when value="col">
                        <param name="id_col" type="data_column" label="Column to split on" data_ref="input"/>
                        <param name="match_regex" type="text" label="Regex to match contents of id column" value="(.*)">
                            <expand macro="regex_sanitizer"/>
                        </param>
                        <param name="sub_regex" type="text" label="Pattern to replace match with" value="\1">
                            <expand macro="regex_sanitizer"/>
                        </param>
                    </when>
                    <when value="row">
                        <expand macro="numnew_fname"/>
                    </when>
                </conditional>
            </when>
            <when value="mgf">
                <param name="input" type="data" format="mgf" label="MGF file to split"/>
                <expand macro="numnew_fname"/>
            </when>
            <when value="fastq">
                <param name="input" type="data" format="fastq" label="FASTQ file to split"/>
                <expand macro="numnew_fname"/>
            </when>
            <when value="fasta">
                <param name="input" type="data" format="fasta" label="FASTA file to split"/>
                <expand macro="numnew_fname"/>
            </when>
            <when value="txt">
                <param name="input" type="data" format="txt" label="Text file to split"/>
                <expand macro="numnew_fname"/>
            </when>
            <when value="generic">
                <param name="input" type="data" format="txt" label="File to split"/>
                <param name="generic_regex" type="text" label="Regex to match record separator" value="^.*">
                    <expand macro="regex_sanitizer"/>
                </param>
                <expand macro="numnew_fname"/>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <collection name="list_output_tab" type="list" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="__name__" directory="out" visible="false" format="tabular"/>
            <filter>split_parms['select_ftype'] == "tabular"</filter>
        </collection>
        <collection name="list_output_mgf" type="list" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="__name__" directory="out" visible="false" format="mgf"/>
            <filter>split_parms['select_ftype'] == "mgf"</filter>
        </collection>
        <collection name="list_output_fasta" type="list" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="__name__" directory="out" visible="false" format="fasta"/>
            <filter>split_parms['select_ftype'] == "fasta"</filter>
        </collection>
        <collection name="list_output_fastq" type="list" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="__name__" directory="out" visible="false" format="fastq"/>
            <filter>split_parms['select_ftype'] == "fastq"</filter>
        </collection>
        <collection name="list_output_txt" type="list" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="__name__" directory="out" visible="false" format="txt"/>
            <filter>split_parms['select_ftype'] == "txt"</filter>
        </collection>
        <collection name="list_output_generic" type="list" label="${tool.name} on ${on_string}">
            <discover_datasets pattern="__name_and_ext__" directory="out" visible="false"/>
            <filter>split_parms['select_ftype'] == "generic"</filter>
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="input" value="test.tabular" ftype="tabular"/>
            <param name="select_ftype" value="tabular"/>
            <param name="select_split_by" value="col"/>
            <param name="id_col" value="1"/>
            <param name="match_regex" value="(.*)\.mgf"/>
            <param name="sub_regex" value="\1.tab"/>
            <param name="top" value="2"/>
            <output_collection name="list_output_tab" type="list">
                <element name="foo.tab"  file="foo.tab" ftype="tabular"/>
                <element name="foo2.tab" file="foo2.tab" ftype="tabular"/>
                <element name="foo3.tab" file="foo3.tab" ftype="tabular"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.tabular" ftype="tabular"/>
            <param name="select_ftype" value="tabular"/>
            <param name="select_split_by" value="row"/>
            <param name="top" value="2"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="test"/>
            <output_collection name="list_output_tab" type="list">
                <element name="test_000000.tabular" file="test_0.tabular" ftype="tabular"/>
                <element name="test_000001.tabular" file="test_1.tabular" ftype="tabular"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.tabular" ftype="tabular"/>
            <param name="select_ftype" value="tabular"/>
            <param name="select_split_by" value="row"/>
            <param name="top" value="2"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="batch_tab"/>
            <param name="allocate" value="batch"/>
            <output_collection name="list_output_tab" type="list">
                <element name="batch_tab_000000.tabular" file="batch_tab_0.tabular" ftype="tabular"/>
                <element name="batch_tab_000001.tabular" file="batch_tab_1.tabular" ftype="tabular"/>
            </output_collection>
        </test>
        <test>
            <param name="select_ftype" value="txt"/>
            <param name="input" value="karyotype.txt" ftype="txt"/>
            <param name="numnew" value="24"/>
            <param name="newfilenames" value="chr"/>
            <param name="allocate" value="batch"/>

            <output_collection name="list_output_txt" type="list">
                <element name="chr_000000.txt" file="chr_000000.txt" ftype="txt"/>
                <element name="chr_000001.txt" file="chr_000001.txt" ftype="txt"/>
                <element name="chr_000002.txt" file="chr_000002.txt" ftype="txt"/>
                <element name="chr_000003.txt" file="chr_000003.txt" ftype="txt"/>
                <element name="chr_000004.txt" file="chr_000004.txt" ftype="txt"/>
                <element name="chr_000005.txt" file="chr_000005.txt" ftype="txt"/>
                <element name="chr_000006.txt" file="chr_000006.txt" ftype="txt"/>
                <element name="chr_000007.txt" file="chr_000007.txt" ftype="txt"/>
                <element name="chr_000008.txt" file="chr_000008.txt" ftype="txt"/>
                <element name="chr_000009.txt" file="chr_000009.txt" ftype="txt"/>
                <element name="chr_000010.txt" file="chr_000010.txt" ftype="txt"/>
                <element name="chr_000011.txt" file="chr_000011.txt" ftype="txt"/>
                <element name="chr_000012.txt" file="chr_000012.txt" ftype="txt"/>
                <element name="chr_000013.txt" file="chr_000013.txt" ftype="txt"/>
                <element name="chr_000014.txt" file="chr_000014.txt" ftype="txt"/>
                <element name="chr_000015.txt" file="chr_000015.txt" ftype="txt"/>
                <element name="chr_000016.txt" file="chr_000016.txt" ftype="txt"/>
                <element name="chr_000017.txt" file="chr_000017.txt" ftype="txt"/>
                <element name="chr_000018.txt" file="chr_000018.txt" ftype="txt"/>
                <element name="chr_000019.txt" file="chr_000019.txt" ftype="txt"/>
                <element name="chr_000020.txt" file="chr_000020.txt" ftype="txt"/>
                <element name="chr_000021.txt" file="chr_000021.txt" ftype="txt"/>
                <element name="chr_000022.txt" file="chr_000022.txt" ftype="txt"/>
                <element name="chr_000023.txt" file="chr_000023.txt" ftype="txt"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="psm.tabular" ftype="tabular"/>
            <param name="select_ftype" value="tabular"/>
            <param name="select_split_by" value="col"/>
            <param name="id_col" value="10"/>
            <param name="match_regex" value="(.*)\.mgf"/>
            <param name="sub_regex" value="\1.tab"/>
            <param name="top" value="1"/>
            <output_collection name="list_output_tab" type="list">
                <element name="file1.tab" file="file1.tab" ftype="tabular"/>
                <element name="file2.tab" file="file2.tab" ftype="tabular"/>
                <element name="file3.tab" file="file3.tab" ftype="tabular"/>
                <element name="file4.tab" file="file4.tab" ftype="tabular"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="demo758Dacentroid.mgf" ftype="mgf"/>
            <param name="select_ftype" value="mgf"/>
            <param name="numnew" value="3"/>
            <param name="newfilenames" value="demo"/>
            <output_collection name="list_output_mgf" type="list">
                <element name="demo_000000.mgf" file="demo_0.mgf" ftype="mgf"/>
                <element name="demo_000001.mgf" file="demo_1.mgf" ftype="mgf"/>
                <element name="demo_000002.mgf" file="demo_2.mgf" ftype="mgf"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.fasta" ftype="fasta"/>
            <param name="select_ftype" value="fasta"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="test"/>
            <output_collection name="list_output_fasta" type="list">
                <element name="test_000000.fasta" file="test_0.fasta" ftype="fasta"/>
                <element name="test_000001.fasta" file="test_1.fasta" ftype="fasta"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.fastq" ftype="fastq"/>
            <param name="select_ftype" value="fastq"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="test"/>
            <output_collection name="list_output_fastq" type="list">
                <element name="test_000000.fastq" file="test_0.fastq" ftype="fastq"/>
                <element name="test_000001.fastq" file="test_1.fastq" ftype="fastq"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.fasta" ftype="fasta"/>
            <param name="select_ftype" value="fasta"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="rand"/>
            <param name="allocate" value="random"/>
            <param name="seed" value="1010"/>
            <output_collection name="list_output_fasta" type="list">
                <element name="rand_000000.fasta" file="rand_0.fasta" ftype="fasta"/>
                <element name="rand_000001.fasta" file="rand_1.fasta" ftype="fasta"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.fasta" ftype="fasta"/>
            <param name="select_ftype" value="fasta"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="fasta_batch"/>
            <param name="allocate" value="batch"/>
            <output_collection name="list_output_fasta" type="list">
                <element name="fasta_batch_000000.fasta" file="fasta_batch_0.fasta" ftype="fasta"/>
                <element name="fasta_batch_000001.fasta" file="fasta_batch_1.fasta" ftype="fasta"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.tabular" ftype="txt"/>
            <param name="select_ftype" value="txt"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="test"/>
            <output_collection name="list_output_txt" type="list">
                <element name="test_000000.txt" file="test_0.tabular" ftype="txt" lines_diff="1"/>
                <element name="test_000001.txt" file="test_1.tabular" ftype="txt" lines_diff="1"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.tabular" ftype="txt"/>
            <param name="select_ftype" value="generic"/>
            <param name="generic_regex" value="^.*"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="test"/>
            <output_collection name="list_output_generic" type="list">
                <element name="test_000000" file="test_0.tabular" ftype="txt" lines_diff="1"/>
                <element name="test_000001" file="test_1.tabular" ftype="txt" lines_diff="1"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="test.fasta" ftype="fasta"/>
            <param name="select_ftype" value="generic"/>
            <param name="generic_regex" value="^>.*"/>
            <param name="numnew" value="2"/>
            <param name="newfilenames" value="rand"/>
            <param name="allocate" value="random"/>
            <param name="seed" value="1010"/>
            <output_collection name="list_output_generic" type="list">
                <element name="rand_000000" file="rand_0.fasta" ftype="fasta"/>
                <element name="rand_000001" file="rand_1.fasta" ftype="fasta"/>
            </output_collection>
        </test>
        <test>
            <param name="input" value="3_molecules.sdf" ftype="sdf"/>
            <param name="select_ftype" value="generic"/>
            <param name="generic_regex" value="^\$\$\$\$.*"/>
            <param name="numnew" value="1000"/>
            <param name="newfilenames" value="mol"/>
            <param name="allocate" value="batch"/>
            <output_collection name="list_output_generic" type="list">
                <element name="mol_000000" file="mol_0.sdf" ftype="sdf"/>
                <element name="mol_000001" file="mol_1.sdf" ftype="sdf"/>
                <element name="mol_000002" file="mol_2.sdf" ftype="sdf"/>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
**Split file into a dataset collection**

This tool splits a data sets consisting of records into multiple data sets within a collection.
A record can be for instance simply a line, a FASTA sequence (header + sequence), a FASTQ sequence
(headers + sequence + qualities), etc. The important property is that the begin of a new record
can be speciefied by a regular expression, e.g. ".*" for lines, ">.*" for FASTA, or "@.*" for FASTQ.
The tool has presets for text, tabular data sets (which are split by line), FASTA, FASTQ, and MGF.
For other data types the text delimiting records can be specified manually using the generic splitter.

If splitting by line (or by some other item, like a FASTA entry or an MGF record, the splitting can be either done alternating, in original record order, or at random.

If t records are to be distributed to n new data sets, then the i-th record goes to data set

* floor(i / t * n) (for batch),
* i % n (for alternating), or
* a random data set

For instance, t=5 records are distributed as follows on n=2 data sets

= === === ====
i bat alt rand
= === === ====
0 0   0   0
1 0   1   1
2 0   0   1
3 1   1   0
4 1   0   0
= === === ====

If the five records are distributed on n=3 data sets:

= === === ====
i bat alt rand
= === === ====
0 0   0   0
1 0   1   1
2 1   2   2
3 1   0   0
4 2   1   1
= === === ====

Note that there are no guarantees when splitting at random that every result file will be non-empty, so downstream tools should be able to gracefully handle empty files.

If a tabular file is used as input, you may choose to split by line or by column. If split by column, a new file is created for each unique value in the column.
In addition, (Python) regular expressions may be used to transform the value in the column to a new value. Caution should be used with this feature, as it could transform all values to the same value, or other unexpected behavior.
The default regular expression uses each value in the column without modifying it.
    ]]></help>
    <citations>
        <citation type="bibtex">
@misc{githubsplit,
  author = {Easterly, Caleb},
  year = {2018},
  title = {A Galxy tool for splitting a file into a collection},
  publisher = {GitHub},
  journal = {GitHub repository},
  url = {https://github.com/bgruening/galaxytools/tools/text_processing/split_file_to_collection},
}</citation>
    </citations>
</tool>