New module: bamtools/split (#798)

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 📦 NEW: Add galgal6 chr30 test data

* 📦 NEW: Add bamtools module

* 👌 IMPROVE: Ignore test data

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Add some pacbio test files

* 🐛 FIX: Add Pacbio index to test_data.config

* 👌 IMPROVE: Re add 10000 data test

* 👌 IMPROVE: Add some pbindex

* 🐛 FIX: Add pbi extension to files

* 📦 NEW: Add galgal6 chr30 test data

* 📦 NEW: Add bamtools module

* 👌 IMPROVE: Ignore test data

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Final version of test datasets config

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Update with new versions.yml file

* 🐛 FIX: Update meta.yml + correct typos

* Update modules/bamtools/split/meta.yml

Add bam, split, chunk tags

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* 🐛 FIX: Correct meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/bamtools/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/bamtools/split/main.nf

@@ -0,0 +1,41 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process BAMTOOLS_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::bamtools=2.5.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/bamtools:2.5.1--h9a82719_9"
+    } else {
+        container "quay.io/biocontainers/bamtools:2.5.1--h9a82719_9"
+    }
+
+    input:
+    tuple val(meta), path(bam)
+
+    output:
+    tuple val(meta), path("*.bam"), emit: bam
+    path "versions.yml"           , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    bamtools \\
+        split \\
+        -in $bam \\
+        $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        bamtools: \$( bamtools --version | grep -e 'bamtools' | sed 's/^.*bamtools //' )
+    END_VERSIONS
+    """
+}

modules/bamtools/split/meta.yml

@@ -0,0 +1,45 @@
+name: bamtools_split
+description: BamTools provides both a programmer's API and an end-user's toolkit for handling BAM files.
+keywords:
+  - bamtools
+  - bamtools/split
+  - bam
+  - split
+  - chunk
+tools:
+  - bamtools:
+      description: C++ API & command-line toolkit for working with BAM data
+      homepage: http://github.com/pezmaster31/bamtools
+      documentation: https://github.com/pezmaster31/bamtools/wiki
+      tool_dev_url: http://github.com/pezmaster31/bamtools
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: A BAM file to split
+      pattern: "*.bam"
+
+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"
+  - bam:
+      type: file
+      description: Several Bam files
+      pattern: "*.bam"
+
+authors:
+  - "@sguizard"

tests/config/pytest_modules.yml

@@ -34,6 +34,10 @@ bamaligncleaner:
   - modules/bamaligncleaner/**
   - tests/modules/bamaligncleaner/**
 
+bamtools/split:
+  - modules/bamtools/split/**
+  - tests/modules/bamtools/split/**
+
 bandage/image:
   - modules/bandage/image/**
   - tests/modules/bandage/image/**

tests/modules/bamtools/split/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BAMTOOLS_SPLIT } from '../../../../modules/bamtools/split/main.nf' addParams( options: [args:"-reference"] )
+
+workflow test_bamtools_split {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ]
+
+    BAMTOOLS_SPLIT ( input )
+}

tests/modules/bamtools/split/test.yml

@@ -0,0 +1,10 @@
+- name: bamtools split test_bamtools_split
+  command: nextflow run tests/modules/bamtools/split -entry test_bamtools_split -c tests/config/nextflow.config
+  tags:
+    - bamtools
+    - bamtools/split
+  files:
+    - path: output/bamtools/test.paired_end.sorted.REF_chr22:16570000-16610000.bam
+      md5sum: 256535b9a3ab5864be0f7dea2218d159
+    - path: output/bamtools/test.paired_end.sorted.REF_unmapped.bam
+      md5sum: 568e058d871d8bc319330360bcae4e43