Add hmmer/eslreformat (#2009)

* Created hmmer/eslalimask from template

* esl-alimask module with --rf-is-mask test case

* Add optional file output

* Add hmmer to test name

* Move from process_single to process_low

* Test for versions.yml, plus content

* Prettier

* Avoid gzipping input alignment

* hmmer/eslreformat from template

* Started on main.nf

* meta.id to prefix

* Continued work

* Fix version string so it's from *this* tool

* hmmer/eslreformat

* Prettier

* Get tests/config/pytest_modules.yml back

* Delete extra hmmer/eslalimask in pytest_modules.yml

* More prettier

* Fix path to versions.yml in test

* Remove 'format' param

* Fix problems with format param deletion

* Document format param

modules/hmmer/eslreformat/main.nf

@@ -0,0 +1,36 @@
+process HMMER_ESLREFORMAT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::hmmer=3.3.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/hmmer:3.3.2--h1b792b2_1':
+        'quay.io/biocontainers/hmmer:3.3.2--h1b792b2_1' }"
+
+    input:
+    tuple val(meta), path(seqfile)
+
+    output:
+    tuple val(meta), path("*.sequences.gz"), emit: seqreformated
+    path "versions.yml"                    , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    esl-reformat \\
+        -o ${prefix}.sequences \\
+        $args \\
+        $seqfile
+
+    gzip ${prefix}.sequences
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        hmmer/easel: \$(esl-reformat -h | grep -o '^# Easel [0-9.]*' | sed 's/^# Easel *//')
+    END_VERSIONS
+    """
+}

modules/hmmer/eslreformat/meta.yml

@@ -0,0 +1,41 @@
+name: "hmmer_eslreformat"
+description: reformats sequence files, see HMMER documentation for details. The module requires that the format is specified in ext.args in a config file, and that this comes last. See the tools help for possible values.
+keywords:
+  - sort
+tools:
+  - "hmmer":
+      description: "Biosequence analysis using profile hidden Markov models"
+      homepage: http://hmmer.org/
+      documentation: http://hmmer.org/documentation.html
+      tool_dev_url: None
+      doi: "http://dx.doi.org/10.1371/journal.pcbi.1002195"
+      licence: ["BSD-3-Clause"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - seqfile:
+      type: file
+      description: Sequences, aligned or not, in any supported format
+      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: "versions.yml"
+  - seqreformated:
+      type: file
+      description: Reformated sequence file
+      pattern: "*.sequences.gz"
+
+authors:
+  - "@erikrikarddaniel"

tests/config/pytest_modules.yml

@@ -1154,6 +1154,10 @@ hmmer/eslalimask:
   - modules/hmmer/eslalimask/**
   - tests/modules/hmmer/eslalimask/**
 
+hmmer/eslreformat:
+  - modules/hmmer/eslreformat/**
+  - tests/modules/hmmer/eslreformat/**
+
 hmmer/hmmalign:
   - modules/hmmer/hmmalign/**
   - tests/modules/hmmer/hmmalign/**

tests/modules/hmmer/eslreformat/main.nf

@@ -0,0 +1,20 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { HMMER_HMMALIGN                             } from '../../../../modules/hmmer/hmmalign/main.nf'
+include { HMMER_ESLREFORMAT as HMMER_ESLREFORMAT_AFA } from '../../../../modules/hmmer/eslreformat/main.nf'
+
+workflow test_hmmer_eslreformat_afa {
+    
+    input = [
+        [ id:'test' ], // meta map
+        file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/hmmer/e_coli_k12_16s.fna.gz')      // Change to params.test_data syntax after the data is included in tests/config/test_data.config
+    ]
+
+    hmm   = file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/hmmer/bac.16S_rRNA.hmm.gz')
+
+    HMMER_HMMALIGN ( input, hmm )
+
+    HMMER_ESLREFORMAT_AFA ( HMMER_HMMALIGN.out.sthlm )
+}

tests/modules/hmmer/eslreformat/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: HMMER_ESLREFORMAT_AFA {
+        ext.args   = 'afa'
+    }
+    
+}

tests/modules/hmmer/eslreformat/test.yml

@@ -0,0 +1,12 @@
+- name: hmmer eslreformat test_hmmer_eslreformat_afa
+  command: nextflow run ./tests/modules/hmmer/eslreformat -entry test_hmmer_eslreformat_afa -c ./tests/config/nextflow.config  -c ./tests/modules/hmmer/eslreformat/nextflow.config
+  tags:
+    - hmmer/eslreformat
+    - hmmer
+  files:
+    - path: output/hmmer/test.sequences.gz
+      contains:
+        - ">CP025268.1"
+    - path: output/hmmer/versions.yml
+      contains:
+        - "easel:"