add module: Add fastx/collapser (nf-core#5250)

* Add fastx_collapser module

* docs: Specify it's a decompressed file

* Update modules/nf-core/fastx/collapser/meta.yml

Co-authored-by: Friederike Hanssen <[email protected]>

---------

Co-authored-by: Friederike Hanssen <[email protected]>

modules/nf-core/fastx/collapser/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "fastx_collapser"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::fastx_toolkit=0.0.14"

modules/nf-core/fastx/collapser/main.nf

@@ -0,0 +1,46 @@
+process FASTX_COLLAPSER {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/fastx_toolkit:0.0.14--hdbdd923_11':
+        'biocontainers/fastx_toolkit:0.0.14--hdbdd923_11' }"
+
+    input:
+    tuple val(meta), path(fastx)
+
+    output:
+    tuple val(meta), path("${prefix}.fasta"), emit: fasta
+    path "versions.yml"                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    fastx_collapser \\
+        $args \\
+        -i $fastx \\
+        -o ${prefix}.fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fastx:  \$(echo \$(fastx_collapser -h) | sed -nE 's/.*([0-9]+\\.[0-9]+\\.[0-9]+).*/\\1/p' ))
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        fastx:  \$(echo \$(fastx_collapser -h) | sed -nE 's/.*([0-9]+\\.[0-9]+\\.[0-9]+).*/\\1/p' ))
+    END_VERSIONS
+    """
+}

modules/nf-core/fastx/collapser/meta.yml

@@ -0,0 +1,51 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "fastx_collapser"
+description: Collapses identical sequences in a FASTQ/A file into a single sequence (while maintaining reads counts)
+keywords:
+  - collapse
+  - genomics
+  - fasta
+  - fastq
+tools:
+  - "fastx":
+      description: "A collection of command line tools for Short-Reads FASTA/FASTQ files preprocessing"
+      homepage: "http://hannonlab.cshl.edu/fastx_toolkit/"
+      documentation: "http://hannonlab.cshl.edu/fastx_toolkit/commandline.html"
+      tool_dev_url: "https://github.com/agordon/fastx_toolkit"
+      licence: ["AGPL"]
+
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - fastx:
+      type: file
+      description: Decompressed FASTA/FASTQ input file
+      pattern: "*.{fastq,fasta}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - fasta:
+      type: file
+      description: Collapsed FASTA file
+      pattern: "*.fasta"
+
+authors:
+  - "@jvfe"
+maintainers:
+  - "@jvfe"

modules/nf-core/fastx/collapser/tests/main.nf.test

@@ -0,0 +1,61 @@
+// nf-core modules test fastx/collapser
+nextflow_process {
+
+    name "Test Process FASTX_COLLAPSER"
+    script "../main.nf"
+    process "FASTX_COLLAPSER"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "fastx"
+    tag "fastx/collapser"
+
+    test("homo_sapiens - fasta") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    file(params.test_data['homo_sapiens']['pacbio']['ccs_fa'], checkIfExists: true)
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert path(process.out.fasta[0][1]).text.contains(">1-1") },
+                { assert process.out.fasta[0][1] ==~ ".*/test.fasta" },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("homo_sapiens - fasta - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test'], // meta map
+                    file(params.test_data['homo_sapiens']['pacbio']['ccs_fa'], checkIfExists: true)
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/fastx/collapser/tests/tags.yml

@@ -0,0 +1,2 @@
+fastx/collapser:
+  - "modules/nf-core/fastx/collapser/**"