Add eido/validate module (#2048)

* Add eido/validate module

* Apply first batch of updates after code review

* Remove readlink, update sed, update paths

* Move sample table index parameter to config

* Update tests/modules/eido/validate/test.yml

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

* Update tests/modules/eido/validate/test.yml

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

* Update tests/modules/eido/validate/test.yml

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

* Update tests/modules/eido/validate/test.yml

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

* Update modules/eido/validate/main.nf

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

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

modules/eido/validate/main.nf

@@ -0,0 +1,32 @@
+process EIDO_VALIDATE {
+    tag '$samplesheet'
+    label 'process_single'
+
+    conda (params.enable_conda ? "conda-forge::eido=0.1.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://containers.biocontainers.pro/s3/SingImgsRepo/eido/0.1.9_cv1/eido_0.1.9_cv1.sif' :
+        'biocontainers/eido:0.1.9_cv1' }"
+
+    input:
+    path samplesheet
+    path schema
+
+    output:
+    path "versions.yml"  , emit: versions
+    path "*.log"         , emit: log
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args   = task.ext.args   ?: ''
+    def prefix = task.ext.prefix ?: "validation"
+    """
+    eido validate $args $samplesheet -s $schema -e > ${prefix}.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        eido: \$(echo \$(eido --version 2>&1) | sed 's/^.*eido //;s/ .*//' ))
+    END_VERSIONS
+    """
+}

modules/eido/validate/meta.yml

@@ -0,0 +1,38 @@
+name: "eido_validate"
+description: Validate samplesheet or PEP config against a schema
+keywords:
+  - eido
+  - validate
+  - schema
+  - format
+  - pep
+tools:
+  - "validate":
+      description: "Validate samplesheet or PEP config against a schema."
+      homepage: "http://eido.databio.org/en/latest/"
+      documentation: "http://eido.databio.org/en/latest/"
+      doi: "10.1093/gigascience/giab077"
+      licence: "BSD-2-Clause"
+
+input:
+  - samplesheet:
+      type: file
+      description: Samplesheet or PEP file to be validated
+      pattern: "*.{yaml,yml,csv}"
+  - schema:
+      type: file
+      description: Schema that the samplesheet will be validated against
+      pattern: "*.{yaml,yml}"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - log:
+      type: file
+      description: File containing validation log.
+      pattern: "*.log"
+
+authors:
+  - "@rafalstepien"

tests/config/pytest_modules.yml

@@ -691,6 +691,10 @@ elprep/filter:
   - modules/elprep/filter/**
   - tests/modules/elprep/filter/**
 
+eido/validate:
+  - modules/eido/validate/**
+  - tests/modules/eido/validate/**
+
 elprep/merge:
   - modules/elprep/merge/**
   - tests/modules/elprep/merge/**

tests/modules/eido/validate/main.nf

@@ -0,0 +1,21 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { EIDO_VALIDATE } from '../../../../modules/eido/validate/main.nf'
+
+workflow test_eido_validate_on_nextflow_samplesheet {
+
+    samplesheet = file("https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/pep/test_nextflow_original_samplesheet.csv", checkIfExists: true)
+    schema = file("https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/pep/test_samplesheet_schema.yaml", checkIfExists: true)
+
+    EIDO_VALIDATE ( samplesheet, schema )
+}
+
+workflow test_eido_validate_on_pep_config {
+
+    samplesheet = file("https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/pep/test_pep_format_files/config.yaml", checkIfExists: true)
+    schema = file("https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/pep/test_samplesheet_schema.yaml", checkIfExists: true)
+
+    EIDO_VALIDATE ( samplesheet, schema )
+}

tests/modules/eido/validate/nextflow.config

@@ -0,0 +1,8 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: 'EIDO_VALIDATE' {
+        ext.args = '--st-index sample'
+    }
+
+}

tests/modules/eido/validate/test.yml

@@ -0,0 +1,17 @@
+- name: eido validate test_eido_validate_on_nextflow_samplesheet
+  command: nextflow run ./tests/modules/eido/validate -entry test_eido_validate_on_nextflow_samplesheet -c ./tests/config/nextflow.config  -c ./tests/modules/eido/validate/nextflow.config
+  tags:
+    - eido/validate
+    - eido
+  files:
+    - path: output/eido/validation.log
+      md5sum: 3a197c21ebf411aac7616bf9b4470de3
+
+- name: eido validate test_eido_validate_on_pep_config
+  command: nextflow run ./tests/modules/eido/validate -entry test_eido_validate_on_pep_config -c ./tests/config/nextflow.config  -c ./tests/modules/eido/validate/nextflow.config
+  tags:
+    - eido/validate
+    - eido
+  files:
+    - path: output/eido/validation.log
+      md5sum: 3a197c21ebf411aac7616bf9b4470de3