add csvtk/concat module (#785)

* add csvtk/concat module

* Update modules/csvtk/concat/main.nf

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>

* allow alternate delimiters

* Update main.nf

* Update modules/csvtk/concat/main.nf

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

* Update modules/csvtk/concat/main.nf

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

* Update modules/csvtk/concat/main.nf

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

* Update modules/csvtk/concat/main.nf

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

* Update modules/csvtk/concat/main.nf

* Apply suggestions from code review

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
This commit is contained in:
Robert A. Petit III 2021-10-05 14:48:47 -06:00 committed by GitHub
parent bb7beff497
commit 8179bab819
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 210 additions and 0 deletions

View file

@ -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// Do not publish versions.yml unless running from pytest workflow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"
}
}

View file

@ -0,0 +1,49 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
params.options = [:]
options = initOptions(params.options)
process CSVTK_CONCAT {
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("*.${out_format}"), emit: csv
path "versions.yml" , emit: versions
script:
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
def delimiter = in_format == "tsv" ? "\t" : (in_format == "csv" ? "," : in_format)
def out_delimiter = out_format == "tsv" ? "\t" : (out_format == "csv" ? "," : out_format)
"""
csvtk \\
concat \\
$options.args \\
--num-cpus $task.cpus \\
--delimiter "${delimiter}" \\
--out-delimiter "${out_delimiter}" \\
--out-file ${prefix}.${out_format} \\
$csv
cat <<-END_VERSIONS > versions.yml
${getProcessName(task.process)}:
csvtk: \$(echo \$( csvtk version | sed -e "s/csvtk v//g" ))
END_VERSIONS
"""
}

View file

@ -0,0 +1,51 @@
name: csvtk_concat
description: Concatenate two or more CSV (or TSV) tables into a single table
keywords:
- concatenate
- tsv
- csv
tools:
- csvtk:
description: A cross-platform, efficient, practical CSV/TSV toolkit
homepage: http://bioinf.shenwei.me/csvtk
documentation: http://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 formatted files
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: "version.yml"
- csv:
type: file
description: Concatenated CSV/TSV file
pattern: "*.{csv,tsv}"
authors:
- "@rpetit3"

View file

@ -266,6 +266,10 @@ cooler/dump:
- modules/cooler/dump/**
- tests/modules/cooler/dump/**
csvtk/concat:
- modules/csvtk/concat/**
- tests/modules/csvtk/concat/**
custom/dumpsoftwareversions:
- modules/custom/dumpsoftwareversions/**
- tests/modules/custom/dumpsoftwareversions/**

View file

@ -0,0 +1,20 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { CSVTK_CONCAT } from '../../../../modules/csvtk/concat/main.nf' addParams( options: [:] )
workflow test_csvtk_concat {
input = [
[ id:'test' ], // meta map
[ file("https://github.com/nf-core/test-datasets/raw/bacass/bacass_hybrid.csv", checkIfExists: true),
file("https://github.com/nf-core/test-datasets/raw/bacass/bacass_long.csv", checkIfExists: true),
file("https://github.com/nf-core/test-datasets/raw/bacass/bacass_short.csv", checkIfExists: true) ]
]
in_format = "tsv"
out_format = "csv"
CSVTK_CONCAT ( input, in_format, out_format )
}

View file

@ -0,0 +1,8 @@
- name: csvtk concat
command: nextflow run ./tests/modules/csvtk/concat -entry test_csvtk_concat -c tests/config/nextflow.config
tags:
- csvtk
- csvtk/concat
files:
- path: output/csvtk/test.csv
md5sum: 917fe5d857f04b58e0f49c384d167cec