From c93e96101a8f97c6972cc080e1aa53006aac31c9 Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Tue, 9 Feb 2021 11:50:32 +0100 Subject: [PATCH] Add untar module --- .github/filters.yml | 4 ++ software/untar/functions.nf | 59 ++++++++++++++++++++++++++++++ software/untar/main.nf | 34 +++++++++++++++++ software/untar/meta.yml | 48 ++++++++++++++++++++++++ tests/data/tar_gz/test.txt.tar.gz | Bin 0 -> 165 bytes tests/software/untar/main.nf | 13 +++++++ tests/software/untar/test.yml | 7 ++++ 7 files changed, 165 insertions(+) create mode 100644 software/untar/functions.nf create mode 100644 software/untar/main.nf create mode 100644 software/untar/meta.yml create mode 100644 tests/data/tar_gz/test.txt.tar.gz create mode 100644 tests/software/untar/main.nf create mode 100644 tests/software/untar/test.yml diff --git a/.github/filters.yml b/.github/filters.yml index 2a32f887..b7b50b7c 100644 --- a/.github/filters.yml +++ b/.github/filters.yml @@ -201,6 +201,10 @@ trimgalore: - software/trimgalore/** - tests/software/trimgalore/** +untar: + - software/untar/** + - tests/software/untar/** + ucsc_bedgraphtobigwig: - software/ucsc/bedgraphtobigwig/** - tests/software/ucsc/bedgraphtobigwig/** diff --git a/software/untar/functions.nf b/software/untar/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/untar/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)}/$args.filename" + } + } +} diff --git a/software/untar/main.nf b/software/untar/main.nf new file mode 100644 index 00000000..8912fb0b --- /dev/null +++ b/software/untar/main.nf @@ -0,0 +1,34 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process UNTAR { + tag "$archive" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') } + + conda (params.enable_conda ? "conda-forge::sed=4.7" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img" + } else { + container "biocontainers/biocontainers:v1.2.0_cv1" + } + + input: + path archive + + output: + path "$untar" , emit: untar + path "*.version.txt", emit: version + + script: + def software = getSoftwareName(task.process) + untar = archive.toString() - '.tar.gz' + """ + tar -xzvf $options.args $archive + echo \$(tar --version 2>&1) | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//' > ${software}.version.txt + """ +} diff --git a/software/untar/meta.yml b/software/untar/meta.yml new file mode 100644 index 00000000..32d03b94 --- /dev/null +++ b/software/untar/meta.yml @@ -0,0 +1,48 @@ +name: untar +description: Extract files. +keywords: + - untar + - uncompress +tools: + - untar: + description: | + Extract tar.gz files. + documentation: https://www.gnu.org/software/tar/manual/ +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$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: + - archive: + type: file + description: File to be untar + pattern: "*.{tar}.{gz}" +output: + - untar: + type: file + description: + pattern: "*.*" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@joseespinosa" + - "@drpatelh" diff --git a/tests/data/tar_gz/test.txt.tar.gz b/tests/data/tar_gz/test.txt.tar.gz new file mode 100644 index 0000000000000000000000000000000000000000..efb3c8ce9981fb647033ba51cf1fb96977665db4 GIT binary patch literal 165 zcmV;W09yYaiwFQMXChz#1MQN*3c@fDM0@rt_6y2J)8u;sZc8LhLbC<&>)jgkBwnP5 zkarmdhGhnpsc_F%?sfzbjn=TKHN!*kSbfDRP#P6#a}ozAX0RRLo~53wh20`mE{;m} zF%|bdC$Vw-aHlSTm;MPdzMpO|`ar-5Sl$8VbY24$@N*6{Q)C|}kRYT?i({W+=?}jy T-e@!$jjy-^Xz=H&00;m8+q6dK literal 0 HcmV?d00001 diff --git a/tests/software/untar/main.nf b/tests/software/untar/main.nf new file mode 100644 index 00000000..b490b0e8 --- /dev/null +++ b/tests/software/untar/main.nf @@ -0,0 +1,13 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { UNTAR } from '../../../software/untar/main.nf' addParams( options: [:] ) + +workflow test_untar { + + def input = [] + input = [ file("${launchDir}/tests/data/tar_gz/test.txt.tar.gz", checkIfExists: true) ] + + UNTAR ( input ) +} diff --git a/tests/software/untar/test.yml b/tests/software/untar/test.yml new file mode 100644 index 00000000..af5645c9 --- /dev/null +++ b/tests/software/untar/test.yml @@ -0,0 +1,7 @@ +- name: untar + command: nextflow run ./tests/software/untar -entry test_untar -c tests/config/nextflow.config + tags: + - untar + files: + - path: output/untar/test.txt + md5sum: 7171d4ec2ad0882fab4b0142536d93a1