Added new module csvtk/split (#1014)

* added module csvtk/split

* removed todo statement

* adjusted meta map names

* changed tests to use generic input files

* added module in pytest

* updated test-data paths

* Apply suggestions from code review

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/csvtk/split/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/csvtk/split/main.nf

@@ -0,0 +1,50 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process CSVTK_SPLIT {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::csvtk=0.23.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/csvtk:0.23.0--h9ee0642_0"
+    } else {
+        container "quay.io/biocontainers/csvtk:0.23.0--h9ee0642_0"
+    }
+
+    input:
+    tuple val(meta), path(csv)
+    val in_format
+    val out_format
+
+    output:
+    tuple val(meta), path("*.${out_extension}"), emit: split_csv
+    path "versions.yml"                        , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def delimiter = in_format == "tsv" ? "--tabs" : (in_format == "csv" ? "--delimiter ',' " : in_format)
+    def out_delimiter = out_format == "tsv" ? "--out-tabs" : (out_format == "csv" ? "--out-delimiter ',' " : out_format)
+    out_extension = out_format == "tsv" ? 'tsv' : 'csv'
+    """
+    sed -i.bak '/^##/d' $csv
+    csvtk \\
+        split \\
+        $options.args \\
+        --num-cpus $task.cpus \\
+        $delimiter \\
+        $out_delimiter \\
+        $csv
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$( csvtk version | sed -e 's/csvtk v//g' ))
+    END_VERSIONS
+    """
+}

modules/csvtk/split/meta.yml

@@ -0,0 +1,52 @@
+name: csvtk_split
+description: Splits CSV/TSV into multiple files according to column values
+keywords:
+  - split
+  - csv
+  - tsv
+tools:
+  - csvtk:
+      description:
+          CSVTK is a cross-platform, efficient and practical CSV/TSV toolkit
+          that allows rapid data investigation and manipulation.
+      homepage: https://bioinf.shenwei.me/csvtk/
+      documentation: https://bioinf.shenwei.me/csvtk/
+      tool_dev_url: https://github.com/shenwei356/csvtk
+      doi: ""
+      licence: ['MIT']
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - csv:
+      type: file
+      description: CSV/TSV file
+      pattern: "*.{csv,tsv}"
+  - in_format:
+      type: string
+      description: Input format (csv, tab, or a delimiting character)
+      pattern: "*"
+  - out_format:
+      type: string
+      description: Output format (csv, tab, or a delimiting character)
+      pattern: "*"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - split_csv:
+      type: file
+      description: Split CSV/TSV file
+      pattern: "*.{csv,tsv}"
+
+authors:
+  - "@SusiJo"

tests/config/pytest_modules.yml

@@ -310,6 +310,10 @@ csvtk/concat:
   - modules/csvtk/concat/**
   - tests/modules/csvtk/concat/**
 
+csvtk/split:
+  - modules/csvtk/split/**
+  - tests/modules/csvtk/split/**
+
 custom/dumpsoftwareversions:
   - modules/custom/dumpsoftwareversions/**
   - tests/modules/custom/dumpsoftwareversions/**

tests/config/test_data.config

@@ -34,7 +34,7 @@ params {
                 contigs_genome_maf_gz                          = "${test_data_dir}/genomics/sarscov2/genome/alignment/last/contigs.genome.maf.gz"
                 contigs_genome_par                             = "${test_data_dir}/genomics/sarscov2/genome/alignment/last/contigs.genome.par"
                 lastdb_tar_gz                                  = "${test_data_dir}/genomics/sarscov2/genome/alignment/last/lastdb.tar.gz"
-                
+
                 baits_interval_list                            = "${test_data_dir}/genomics/sarscov2/genome/picard/baits.interval_list"
                 targets_interval_list                          = "${test_data_dir}/genomics/sarscov2/genome/picard/targets.interval_list"
             }
@@ -249,11 +249,17 @@ params {
             }
         }
         'generic' {
+            'csv' {
+                test_csv = "${test_data_dir}/generic/csv/test.csv"
+            }
             'notebooks' {
                 rmarkdown = "${test_data_dir}/generic/notebooks/rmarkdown/rmarkdown_notebook.Rmd"
                 ipython_md = "${test_data_dir}/generic/notebooks/jupyter/ipython_notebook.md"
                 ipython_ipynb = "${test_data_dir}/generic/notebooks/jupyter/ipython_notebook.ipynb"
             }
+            'tsv' {
+                test_tsv = "${test_data_dir}/generic/tsv/test.tsv"
+            }
             'txt' {
                 hello = "${test_data_dir}/generic/txt/hello.txt"
             }
@@ -285,6 +291,6 @@ params {
                 test_fastq_gz                   = "${test_data_dir}/genomics/bacteroides_fragilis/nanopore/fastq/test.fastq.gz"
                 overlap_paf                     = "${test_data_dir}/genomics/bacteroides_fragilis/nanopore/overlap.paf"
             }
-        }    
+        }
     }
 }

tests/modules/csvtk/split/main.nf

@@ -0,0 +1,27 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CSVTK_SPLIT } from '../../../../modules/csvtk/split/main.nf' addParams( options: [args: "-C '&' --fields 'first_name' "])
+
+workflow test_csvtk_split_tsv {
+
+    input = [
+        [ id:'test' ], // meta map
+        [ file(params.test_data['generic']['tsv']['test_tsv'], checkIfExists: true) ]
+    ]
+    in_format = "tsv"
+    out_format = "tsv"
+    CSVTK_SPLIT ( input, in_format, out_format )
+}
+
+workflow test_csvtk_split_csv {
+
+    input = [
+        [ id:'test' ], // meta map
+        [ file(params.test_data['generic']['csv']['test_csv'], checkIfExists: true) ]
+    ]
+    in_format = "csv"
+    out_format = "csv"
+    CSVTK_SPLIT( input, in_format, out_format )
+}

tests/modules/csvtk/split/test.yml

@@ -0,0 +1,25 @@
+- name: csvtk split test_csvtk_split_tsv
+  command: nextflow run tests/modules/csvtk/split -entry test_csvtk_split_tsv -c tests/config/nextflow.config
+  tags:
+    - csvtk/split
+    - csvtk
+  files:
+    - path: output/csvtk/test-Ken.tsv
+      md5sum: 589a2add7f0b8e998d4959e5d883e7d5
+    - path: output/csvtk/test-Rob.tsv
+      md5sum: 6c5555d689c4e685d35d6e394ad6e1e6
+    - path: output/csvtk/test-Robert.tsv
+      md5sum: 45ae6da8111096746d1736d34220a3ec
+
+- name: csvtk split test_csvtk_split_csv
+  command: nextflow run tests/modules/csvtk/split -entry test_csvtk_split_csv -c tests/config/nextflow.config
+  tags:
+    - csvtk/split
+    - csvtk
+  files:
+    - path: output/csvtk/test-Ken.csv
+      md5sum: 71a931dae6f15f5ddb0318c7d4afe81e
+    - path: output/csvtk/test-Rob.csv
+      md5sum: efc4bc507021043a3bf2fb0724c4a216
+    - path: output/csvtk/test-Robert.csv
+      md5sum: 8de2f076e64252c2abed69b9c2a3a386