From f7f06dd6e84dbc1410f5da626bab822b86234991 Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Tue, 9 Feb 2021 10:05:55 +0100 Subject: [PATCH] Add gunzip module --- .github/filters.yml | 4 +++ software/gunzip/functions.nf | 59 ++++++++++++++++++++++++++++++++++ software/gunzip/main.nf | 34 ++++++++++++++++++++ software/gunzip/meta.yml | 58 +++++++++++++++++++++++++++++++++ tests/software/gunzip/main.nf | 13 ++++++++ tests/software/gunzip/test.yml | 7 ++++ 6 files changed, 175 insertions(+) create mode 100644 software/gunzip/functions.nf create mode 100644 software/gunzip/main.nf create mode 100644 software/gunzip/meta.yml create mode 100644 tests/software/gunzip/main.nf create mode 100644 tests/software/gunzip/test.yml diff --git a/.github/filters.yml b/.github/filters.yml index 18087014..2a32f887 100644 --- a/.github/filters.yml +++ b/.github/filters.yml @@ -104,6 +104,10 @@ gffread: - software/gffread/** - tests/software/gffread/** +gunzip: + - software/gunzip/** + - tests/software/gunzip/** + minimap2_align: - software/minimap2/align/** - tests/software/minimap2/align/** diff --git a/software/gunzip/functions.nf b/software/gunzip/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/gunzip/functions.nf @@ -0,0 +1,59 @@ +/* + * ----------------------------------------------------- + * Utility functions used in nf-core DSL2 module files + * ----------------------------------------------------- + */ + +/* + * Extract name of software tool from process name using $task.process + */ +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +/* + * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules + */ +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.publish_by_id = args.publish_by_id ?: false + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +/* + * Tidy up and join elements of a list to return a path string + */ +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +/* + * Function to save/publish module results + */ +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_id) { + path_list.add(args.publish_id) + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/software/gunzip/main.nf b/software/gunzip/main.nf new file mode 100644 index 00000000..20f6467d --- /dev/null +++ b/software/gunzip/main.nf @@ -0,0 +1,34 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process GUNZIP { + tag "$archive" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') } + + conda (params.enable_conda ? "conda-forge::sed=4.7" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" + } else { + container "biocontainers/biocontainers:v1.2.0_cv1" + } + + input: + path archive + + output: + path "$gunzip", emit: gunzip + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + gunzip = archive.toString() - '.gz' + """ + gunzip -f $options.args $archive + echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//' > ${software}.version.txt + """ +} diff --git a/software/gunzip/meta.yml b/software/gunzip/meta.yml new file mode 100644 index 00000000..066cf567 --- /dev/null +++ b/software/gunzip/meta.yml @@ -0,0 +1,58 @@ +name: gunzip +description: Compresses and decompresses files. +keywords: + - gunzip + - compression +tools: + - bedtools: + description: | + A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types. + documentation: https://bedtools.readthedocs.io/en/latest/content/tools/merge.html +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$params.outdir/` + - publish_dir_mode: + type: string + description: | + Value for the Nextflow `publishDir` mode parameter. + Available: symlink, rellink, link, copy, copyNoFollow, move. + - enable_conda: + type: boolean + description: | + Run the module with Conda using the software specified + via the `conda` directive + - singularity_pull_docker_container: + type: boolean + description: | + Instead of directly downloading Singularity images for use with Singularity, + force the workflow to pull and convert Docker containers instead. +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - archive: + type: file + description: File to be gzipped + pattern: "*.*" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - gunzip: + type: file + description: Compressed gzipped file + pattern: "*.{gz}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@joseespinosa" + - "@drpatelh" diff --git a/tests/software/gunzip/main.nf b/tests/software/gunzip/main.nf new file mode 100644 index 00000000..884134c3 --- /dev/null +++ b/tests/software/gunzip/main.nf @@ -0,0 +1,13 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { GUNZIP } from '../../../software/gunzip/main.nf' addParams( options: [:] ) + +workflow test_gunzip { + + def input = [] + input = [ file("${launchDir}/tests/data/vcf/test.vcf.gz", checkIfExists: true) ] + + GUNZIP ( input ) +} diff --git a/tests/software/gunzip/test.yml b/tests/software/gunzip/test.yml new file mode 100644 index 00000000..cccb7318 --- /dev/null +++ b/tests/software/gunzip/test.yml @@ -0,0 +1,7 @@ +- name: gunzip + command: nextflow run ./tests/software/gunzip -entry test_gunzip -c tests/config/nextflow.config + tags: + - gunzip + files: + - path: output/bcftools/test.vcf + md5sum: 9b291062f1a43aee8e890901324a5616