Added gt/gff3validator (nf-core#4718)

* Added gt/gff3validator

* Make error handling a bit more intuitive

* Fixed a problem with info echo and simplified test assertions

---------

Co-authored-by: Leon Rauschning <[email protected]>

modules/nf-core/gt/gff3validator/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "gt_gff3validator"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::genometools-genometools=1.6.5"

modules/nf-core/gt/gff3validator/main.nf

@@ -0,0 +1,61 @@
+process GT_GFF3VALIDATOR {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/genometools-genometools:1.6.5--py310h3db02ab_0':
+        'biocontainers/genometools-genometools:1.6.5--py310h3db02ab_0' }"
+
+    input:
+    tuple val(meta), path(gff3)
+
+    output:
+    tuple val(meta), path('*.success.log')  , emit: success_log , optional: true
+    tuple val(meta), path('*.error.log')    , emit: error_log   , optional: true
+    path "versions.yml"                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    gt \\
+        gff3validator \\
+        "$gff3" \\
+        > "${prefix}.stdout" \\
+        2> >(tee "${prefix}.stderr" >&2) \\
+        || echo "Errors from gt-gff3validator printed to ${prefix}.error.log"
+
+    if grep -q "input is valid GFF3" "${prefix}.stdout"; then
+        echo "Validation successful..."
+        # emit stdout to the success output channel
+        mv \\
+            "${prefix}.stdout" \\
+            "${prefix}.success.log"
+    else
+        echo "Validation failed..."
+        # emit stderr to the error output channel
+        mv \\
+            "${prefix}.stderr" \\
+            "${prefix}.error.log"
+    fi
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        genometools: \$(gt --version | head -1 | sed 's/gt (GenomeTools) //')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch "${prefix}.success.log"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        genometools: \$(gt --version | head -1 | sed 's/gt (GenomeTools) //')
+    END_VERSIONS
+    """
+}

modules/nf-core/gt/gff3validator/meta.yml

@@ -0,0 +1,49 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "gt_gff3validator"
+description: "GenomeTools gt-gff3validator utility to strictly validate a GFF3 file"
+keywords:
+  - genome
+  - gff3
+  - annotation
+  - validation
+tools:
+  - "gt":
+      description: "The GenomeTools genome analysis system"
+      homepage: "https://genometools.org/index.html"
+      documentation: "https://genometools.org/documentation.html"
+      tool_dev_url: "https://github.com/genometools/genometools"
+      doi: "10.1109/TCBB.2013.68"
+      licence: ["ISC"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test' ]`
+  - gff3:
+      type: file
+      description: Input gff3 file
+      pattern: "*.{gff,gff3}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test' ]`
+  - success_log:
+      type: file
+      description: Log file for successful validation
+      pattern: "*.success.log"
+  - error_log:
+      type: file
+      description: Log file for failed validation
+      pattern: "*.error.log"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@GallVp"
+maintainers:
+  - "@GallVp"

modules/nf-core/gt/gff3validator/tests/main.nf.test

@@ -0,0 +1,98 @@
+nextflow_process {
+
+    name "Test Process GT_GFF3VALIDATOR"
+    script "../main.nf"
+    process "GT_GFF3VALIDATOR"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "gt"
+    tag "gt/gff3validator"
+    tag "gt/gff3"
+
+    test("sarscov2-gff3-valid") {
+
+        config './nextflow.config'
+
+        setup {
+            run("GT_GFF3") {
+                script "../../../../nf-core/gt/gff3"
+
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test' ],
+                        file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true)
+                    ]
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """
+                input[0] = GT_GFF3.out.gt_gff3
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+                { assert path(process.out.success_log[0][1]).text.contains("input is valid GFF3") },
+                { assert process.out.error_log == [] }
+            )
+        }
+
+    }
+
+    test("sarscov2-gff3-stub") {
+
+        options '-stub'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2-gff3-invalid") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    file(params.test_data['homo_sapiens']['genome']['genome_gff3'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+                { assert process.out.success_log == [] },
+                { assert path(process.out.error_log[0][1]).text.contains("gt gff3validator: error:") }
+            )
+        }
+
+    }
+}

modules/nf-core/gt/gff3validator/tests/nextflow.config

@@ -0,0 +1,5 @@
+process {
+    withName: GT_GFF3 {
+        ext.args = '-tidy -retainids'
+    }
+}

modules/nf-core/gt/gff3validator/tests/tags.yml

@@ -0,0 +1,2 @@
+gt/gff3validator:
+  - "modules/nf-core/gt/gff3validator/**"